diff options
933 files changed, 30947 insertions, 12172 deletions
@@ -130,6 +130,7 @@ Domen Puncer <domen@coderock.org> Douglas Gilbert <dougg@torque.net> Ed L. Cashin <ecashin@coraid.com> Erik Kaneda <erik.kaneda@intel.com> <erik.schmauss@intel.com> +Eugen Hristev <eugen.hristev@collabora.com> <eugen.hristev@microchip.com> Evgeniy Polyakov <johnpol@2ka.mipt.ru> Ezequiel Garcia <ezequiel@vanguardiasur.com.ar> <ezequiel@collabora.com> Felipe W Damasio <felipewd@terra.com.br> @@ -214,6 +215,7 @@ Jisheng Zhang <jszhang@kernel.org> <jszhang@marvell.com> Jisheng Zhang <jszhang@kernel.org> <Jisheng.Zhang@synaptics.com> Johan Hovold <johan@kernel.org> <jhovold@gmail.com> Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com> +John Crispin <john@phrozen.org> <blogic@openwrt.org> John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de> John Stultz <johnstul@us.ibm.com> Jordan Crouse <jordan@cosmicpenguin.net> <jcrouse@codeaurora.org> @@ -1173,6 +1173,10 @@ D: Future Domain TMC-16x0 SCSI driver (author) D: APM driver (early port) D: DRM drivers (author of several) +N: Veaceslav Falico +E: vfalico@gmail.com +D: Co-maintainer and co-author of the network bonding driver. + N: János Farkas E: chexum@shadow.banki.hu D: romfs, various (mostly networking) fixes @@ -4179,6 +4183,10 @@ S: B-1206 Jingmao Guojigongyu S: 16 Baliqiao Nanjie, Beijing 101100 S: People's Repulic of China +N: Vlad Yasevich +E: vyasevich@gmail.com +D: SCTP protocol maintainer. + N: Aviad Yehezkel E: aviadye@nvidia.com D: Kernel TLS implementation and offload support. diff --git a/Documentation/ABI/testing/sysfs-class-net-peak_usb b/Documentation/ABI/testing/sysfs-class-net-peak_usb new file mode 100644 index 000000000000..9e3d0bf4d4b2 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-net-peak_usb @@ -0,0 +1,19 @@ + +What: /sys/class/net/<iface>/peak_usb/can_channel_id +Date: November 2022 +KernelVersion: 6.2 +Contact: Stephane Grosjean <s.grosjean@peak-system.com> +Description: + PEAK PCAN-USB devices support user-configurable CAN channel + identifiers. Contrary to a USB serial number, these identifiers + are writable and can be set per CAN interface. This means that + if a USB device exports multiple CAN interfaces, each of them + can be assigned a unique channel ID. + This attribute provides read-only access to the currently + configured value of the channel identifier. Depending on the + device type, the identifier has a length of 8 or 32 bit. The + value read from this attribute is always an 8 digit 32 bit + hexadecimal value in big endian format. If the device only + supports an 8 bit identifier, the upper 24 bit of the value are + set to zero. + diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index c8ae7c897f14..74cec76be9f2 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1245,13 +1245,17 @@ PAGE_SIZE multiple when read back. This is a simple interface to trigger memory reclaim in the target cgroup. - This file accepts a string which contains the number of bytes to - reclaim. + This file accepts a single key, the number of bytes to reclaim. + No nested keys are currently supported. Example:: echo "1G" > memory.reclaim + The interface can be later extended with nested keys to + configure the reclaim behavior. For example, specify the + type of memory to reclaim from (anon, file, ..). + Please note that the kernel can over or under reclaim from the target cgroup. If less bytes are reclaimed than the specified amount, -EAGAIN is returned. @@ -1263,13 +1267,6 @@ PAGE_SIZE multiple when read back. This means that the networking layer will not adapt based on reclaim induced by memory.reclaim. - This file also allows the user to specify the nodes to reclaim from, - via the 'nodes=' key, for example:: - - echo "1G nodes=0,1" > memory.reclaim - - The above instructs the kernel to reclaim memory from nodes 0,1. - memory.peak A read-only single value file which exists on non-root cgroups. diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 6394f5dc2303..466c560b0c30 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -215,6 +215,12 @@ rmem_max The maximum receive socket buffer size in bytes. +rps_default_mask +---------------- + +The default RPS CPU mask used on newly created network devices. An empty +mask means RPS disabled by default. + tstamp_allow_data ----------------- Allow processes to receive tx timestamps looped together with the original diff --git a/Documentation/devicetree/bindings/.gitignore b/Documentation/devicetree/bindings/.gitignore index a77719968a7e..51ddb26d93f0 100644 --- a/Documentation/devicetree/bindings/.gitignore +++ b/Documentation/devicetree/bindings/.gitignore @@ -2,3 +2,8 @@ *.example.dts /processed-schema*.yaml /processed-schema*.json + +# +# We don't want to ignore the following even if they are dot-files +# +!.yamllint diff --git a/Documentation/devicetree/bindings/i2c/renesas,rzv2m.yaml b/Documentation/devicetree/bindings/i2c/renesas,rzv2m.yaml index c46378efc123..92e899905ef8 100644 --- a/Documentation/devicetree/bindings/i2c/renesas,rzv2m.yaml +++ b/Documentation/devicetree/bindings/i2c/renesas,rzv2m.yaml @@ -16,7 +16,7 @@ properties: compatible: items: - enum: - - renesas,i2c-r9a09g011 # RZ/V2M + - renesas,r9a09g011-i2c # RZ/V2M - const: renesas,rzv2m-i2c reg: @@ -66,7 +66,7 @@ examples: #include <dt-bindings/interrupt-controller/arm-gic.h> i2c0: i2c@a4030000 { - compatible = "renesas,i2c-r9a09g011", "renesas,rzv2m-i2c"; + compatible = "renesas,r9a09g011-i2c", "renesas,rzv2m-i2c"; reg = <0xa4030000 0x80>; interrupts = <GIC_SPI 232 IRQ_TYPE_EDGE_RISING>, <GIC_SPI 236 IRQ_TYPE_EDGE_RISING>; diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml index 9f7d3e11aacb..8449e14af9f3 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml @@ -108,7 +108,7 @@ properties: msi-controller: description: - Only present if the Message Based Interrupt functionnality is + Only present if the Message Based Interrupt functionality is being exposed by the HW, and the mbi-ranges property present. mbi-ranges: diff --git a/Documentation/devicetree/bindings/mfd/mscc,ocelot.yaml b/Documentation/devicetree/bindings/mfd/mscc,ocelot.yaml index 1d1fee1a16c1..8bd1abfc44d9 100644 --- a/Documentation/devicetree/bindings/mfd/mscc,ocelot.yaml +++ b/Documentation/devicetree/bindings/mfd/mscc,ocelot.yaml @@ -57,6 +57,15 @@ patternProperties: enum: - mscc,ocelot-miim + "^ethernet-switch@[0-9a-f]+$": + type: object + $ref: /schemas/net/mscc,vsc7514-switch.yaml + unevaluatedProperties: false + properties: + compatible: + enum: + - mscc,vsc7512-switch + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/net/amlogic,gxl-mdio-mux.yaml b/Documentation/devicetree/bindings/net/amlogic,gxl-mdio-mux.yaml new file mode 100644 index 000000000000..27ae004dbea0 --- /dev/null +++ b/Documentation/devicetree/bindings/net/amlogic,gxl-mdio-mux.yaml @@ -0,0 +1,64 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/amlogic,gxl-mdio-mux.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Amlogic GXL MDIO bus multiplexer + +maintainers: + - Jerome Brunet <jbrunet@baylibre.com> + +description: + This is a special case of a MDIO bus multiplexer. It allows to choose between + the internal mdio bus leading to the embedded 10/100 PHY or the external + MDIO bus on the Amlogic GXL SoC family. + +allOf: + - $ref: mdio-mux.yaml# + +properties: + compatible: + const: amlogic,gxl-mdio-mux + + reg: + maxItems: 1 + + clocks: + maxItems: 1 + + clock-names: + items: + - const: ref + +required: + - compatible + - reg + - clocks + - clock-names + +unevaluatedProperties: false + +examples: + - | + eth_phy_mux: mdio@558 { + compatible = "amlogic,gxl-mdio-mux"; + reg = <0x558 0xc>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&refclk>; + clock-names = "ref"; + mdio-parent-bus = <&mdio0>; + + external_mdio: mdio@0 { + reg = <0x0>; + #address-cells = <1>; + #size-cells = <0>; + }; + + internal_mdio: mdio@1 { + reg = <0x1>; + #address-cells = <1>; + #size-cells = <0>; + }; + }; diff --git a/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml b/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml index 1eb98c9a1a26..d3f45d29fa0a 100644 --- a/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml +++ b/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml @@ -30,13 +30,17 @@ properties: - items: - enum: + - renesas,r8a779a0-canfd # R-Car V3U + - renesas,r8a779g0-canfd # R-Car V4H + - const: renesas,rcar-gen4-canfd # R-Car Gen4 + + - items: + - enum: - renesas,r9a07g043-canfd # RZ/G2UL and RZ/Five - renesas,r9a07g044-canfd # RZ/G2{L,LC} - renesas,r9a07g054-canfd # RZ/V2L - const: renesas,rzg2l-canfd # RZ/G2L family - - const: renesas,r8a779a0-canfd # R-Car V3U - reg: maxItems: 1 @@ -60,7 +64,7 @@ properties: $ref: /schemas/types.yaml#/definitions/flag description: The controller can operate in either CAN FD only mode (default) or - Classical CAN only mode. The mode is global to both the channels. + Classical CAN only mode. The mode is global to all channels. Specify this property to put the controller in Classical CAN only mode. assigned-clocks: @@ -80,6 +84,10 @@ patternProperties: The controller supports multiple channels and each is represented as a child node. Each channel can be enabled/disabled individually. + properties: + phys: + maxItems: 1 + additionalProperties: false required: @@ -159,7 +167,7 @@ allOf: properties: compatible: contains: - const: renesas,r8a779a0-canfd + const: renesas,rcar-gen4-canfd then: patternProperties: "^channel[2-7]$": false diff --git a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt index df9e844dd6bc..2681168777a1 100644 --- a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt +++ b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt @@ -158,6 +158,7 @@ KSZ9031: no link will be established. KSZ9131: +LAN8841: All skew control options are specified in picoseconds. The increment step is 100ps. Unlike KSZ9031, the values represent picoseccond delays. diff --git a/Documentation/devicetree/bindings/net/motorcomm,yt8xxx.yaml b/Documentation/devicetree/bindings/net/motorcomm,yt8xxx.yaml new file mode 100644 index 000000000000..157e3bbcaf6f --- /dev/null +++ b/Documentation/devicetree/bindings/net/motorcomm,yt8xxx.yaml @@ -0,0 +1,117 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/motorcomm,yt8xxx.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: MotorComm yt8xxx Ethernet PHY + +maintainers: + - Frank Sae <frank.sae@motor-comm.com> + +allOf: + - $ref: ethernet-phy.yaml# + +properties: + compatible: + enum: + - ethernet-phy-id4f51.e91a + - ethernet-phy-id4f51.e91b + + rx-internal-delay-ps: + description: | + RGMII RX Clock Delay used only when PHY operates in RGMII mode with + internal delay (phy-mode is 'rgmii-id' or 'rgmii-rxid') in pico-seconds. + enum: [ 0, 150, 300, 450, 600, 750, 900, 1050, 1200, 1350, 1500, 1650, + 1800, 1900, 1950, 2050, 2100, 2200, 2250, 2350, 2500, 2650, 2800, + 2950, 3100, 3250, 3400, 3550, 3700, 3850, 4000, 4150 ] + default: 1950 + + tx-internal-delay-ps: + description: | + RGMII TX Clock Delay used only when PHY operates in RGMII mode with + internal delay (phy-mode is 'rgmii-id' or 'rgmii-txid') in pico-seconds. + enum: [ 0, 150, 300, 450, 600, 750, 900, 1050, 1200, 1350, 1500, 1650, 1800, + 1950, 2100, 2250 ] + default: 1950 + + motorcomm,clk-out-frequency-hz: + description: clock output on clock output pin. + enum: [0, 25000000, 125000000] + default: 0 + + motorcomm,keep-pll-enabled: + description: | + If set, keep the PLL enabled even if there is no link. Useful if you + want to use the clock output without an ethernet link. + type: boolean + + motorcomm,auto-sleep-disabled: + description: | + If set, PHY will not enter sleep mode and close AFE after unplug cable + for a timer. + type: boolean + + motorcomm,tx-clk-adj-enabled: + description: | + This configuration is mainly to adapt to VF2 with JH7110 SoC. + Useful if you want to use tx-clk-xxxx-inverted to adj the delay of tx clk. + type: boolean + + motorcomm,tx-clk-10-inverted: + description: | + Use original or inverted RGMII Transmit PHY Clock to drive the RGMII + Transmit PHY Clock delay train configuration when speed is 10Mbps. + type: boolean + + motorcomm,tx-clk-100-inverted: + description: | + Use original or inverted RGMII Transmit PHY Clock to drive the RGMII + Transmit PHY Clock delay train configuration when speed is 100Mbps. + type: boolean + + motorcomm,tx-clk-1000-inverted: + description: | + Use original or inverted RGMII Transmit PHY Clock to drive the RGMII + Transmit PHY Clock delay train configuration when speed is 1000Mbps. + type: boolean + +unevaluatedProperties: false + +examples: + - | + mdio { + #address-cells = <1>; + #size-cells = <0>; + phy-mode = "rgmii-id"; + ethernet-phy@4 { + /* Only needed to make DT lint tools work. Do not copy/paste + * into real DTS files. + */ + compatible = "ethernet-phy-id4f51.e91a"; + + reg = <4>; + rx-internal-delay-ps = <2100>; + tx-internal-delay-ps = <150>; + motorcomm,clk-out-frequency-hz = <0>; + motorcomm,keep-pll-enabled; + motorcomm,auto-sleep-disabled; + }; + }; + - | + mdio { + #address-cells = <1>; + #size-cells = <0>; + phy-mode = "rgmii"; + ethernet-phy@5 { + /* Only needed to make DT lint tools work. Do not copy/paste + * into real DTS files. + */ + compatible = "ethernet-phy-id4f51.e91a"; + + reg = <5>; + motorcomm,clk-out-frequency-hz = <125000000>; + motorcomm,keep-pll-enabled; + motorcomm,auto-sleep-disabled; + }; + }; diff --git a/Documentation/devicetree/bindings/net/mscc,vsc7514-switch.yaml b/Documentation/devicetree/bindings/net/mscc,vsc7514-switch.yaml index 5ffe831e59e4..8ee2c7d7ff42 100644 --- a/Documentation/devicetree/bindings/net/mscc,vsc7514-switch.yaml +++ b/Documentation/devicetree/bindings/net/mscc,vsc7514-switch.yaml @@ -18,13 +18,52 @@ description: | packets using CPU. Additionally, PTP is supported as well as FDMA for faster packet extraction/injection. -$ref: ethernet-switch.yaml# +allOf: + - if: + properties: + compatible: + const: mscc,vsc7514-switch + then: + $ref: ethernet-switch.yaml# + required: + - interrupts + - interrupt-names + properties: + reg: + minItems: 21 + reg-names: + minItems: 21 + ethernet-ports: + patternProperties: + "^port@[0-9a-f]+$": + $ref: ethernet-switch-port.yaml# + unevaluatedProperties: false + + - if: + properties: + compatible: + const: mscc,vsc7512-switch + then: + $ref: /schemas/net/dsa/dsa.yaml# + properties: + reg: + maxItems: 20 + reg-names: + maxItems: 20 + ethernet-ports: + patternProperties: + "^port@[0-9a-f]+$": + $ref: /schemas/net/dsa/dsa-port.yaml# + unevaluatedProperties: false properties: compatible: - const: mscc,vsc7514-switch + enum: + - mscc,vsc7512-switch + - mscc,vsc7514-switch reg: + minItems: 20 items: - description: system target - description: rewriter target @@ -49,6 +88,7 @@ properties: - description: fdma target reg-names: + minItems: 20 items: - const: sys - const: rew @@ -86,35 +126,16 @@ properties: - const: xtr - const: fdma - ethernet-ports: - type: object - - properties: - '#address-cells': - const: 1 - '#size-cells': - const: 0 - - additionalProperties: false - - patternProperties: - "^port@[0-9a-f]+$": - - $ref: ethernet-switch-port.yaml# - - unevaluatedProperties: false - required: - compatible - reg - reg-names - - interrupts - - interrupt-names - ethernet-ports -additionalProperties: false +unevaluatedProperties: false examples: + # VSC7514 (Switchdev) - | switch@1010000 { compatible = "mscc,vsc7514-switch"; @@ -162,5 +183,51 @@ examples: }; }; }; + # VSC7512 (DSA) + - | + ethernet-switch@1{ + compatible = "mscc,vsc7512-switch"; + reg = <0x71010000 0x10000>, + <0x71030000 0x10000>, + <0x71080000 0x100>, + <0x710e0000 0x10000>, + <0x711e0000 0x100>, + <0x711f0000 0x100>, + <0x71200000 0x100>, + <0x71210000 0x100>, + <0x71220000 0x100>, + <0x71230000 0x100>, + <0x71240000 0x100>, + <0x71250000 0x100>, + <0x71260000 0x100>, + <0x71270000 0x100>, + <0x71280000 0x100>, + <0x71800000 0x80000>, + <0x71880000 0x10000>, + <0x71040000 0x10000>, + <0x71050000 0x10000>, + <0x71060000 0x10000>; + reg-names = "sys", "rew", "qs", "ptp", "port0", "port1", + "port2", "port3", "port4", "port5", "port6", + "port7", "port8", "port9", "port10", "qsys", + "ana", "s0", "s1", "s2"; + + ethernet-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + ethernet = <&mac_sw>; + phy-handle = <&phy0>; + phy-mode = "internal"; + }; + port@1 { + reg = <1>; + phy-handle = <&phy1>; + phy-mode = "internal"; + }; + }; + }; ... diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml index 01f9d4e236e9..a7feb497eb89 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml @@ -19,8 +19,8 @@ description: | additional information and example. patternProperties: - # 25 LDOs - "^LDO([1-9]|[1][0-9]|2[0-5])$": + # 25 LDOs, without LDO10-12 + "^LDO([1-9]|1[3-9]|2[0-5])$": type: object $ref: regulator.yaml# unevaluatedProperties: false @@ -30,6 +30,23 @@ patternProperties: required: - regulator-name + "^LDO(1[0-2])$": + type: object + $ref: regulator.yaml# + unevaluatedProperties: false + description: + Properties for single LDO regulator. + + properties: + samsung,ext-control-gpios: + maxItems: 1 + description: + LDO10, LDO11 and LDO12 can be configured to external control over + GPIO. + + required: + - regulator-name + # 5 bucks "^BUCK[1-5]$": type: object diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml index c6720764e765..a2884e3113da 100644 --- a/Documentation/devicetree/bindings/riscv/cpus.yaml +++ b/Documentation/devicetree/bindings/riscv/cpus.yaml @@ -83,7 +83,7 @@ properties: insensitive, letters in the riscv,isa string must be all lowercase to simplify parsing. $ref: "/schemas/types.yaml#/definitions/string" - pattern: ^rv(?:64|32)imaf?d?q?c?b?v?k?h?(?:_[hsxz](?:[a-z])+)*$ + pattern: ^rv(?:64|32)imaf?d?q?c?b?k?j?p?v?h?(?:[hsxz](?:[a-z])+)?(?:_[hsxz](?:[a-z])+)*$ # RISC-V requires 'timebase-frequency' in /cpus, so disallow it here timebase-frequency: false diff --git a/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml b/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml index 0a7aa29563c1..21c8ea08ff0a 100644 --- a/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml @@ -40,6 +40,8 @@ properties: description: Indicates that the setting of RTC time is allowed by the host CPU. + wakeup-source: true + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/sound/everest,es8326.yaml b/Documentation/devicetree/bindings/sound/everest,es8326.yaml index 07781408e788..07781408e788 100755..100644 --- a/Documentation/devicetree/bindings/sound/everest,es8326.yaml +++ b/Documentation/devicetree/bindings/sound/everest,es8326.yaml diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index 161766b1de50..99bb8594753c 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.yaml +++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml @@ -847,6 +847,8 @@ patternProperties: description: Moortec Semiconductor Ltd. "^mosaixtech,.*": description: Mosaix Technologies, Inc. + "^motorcomm,.*": + description: MotorComm, Inc. "^motorola,.*": description: Motorola, Inc. "^moxa,.*": diff --git a/Documentation/isdn/interface_capi.rst b/Documentation/isdn/interface_capi.rst index fe2421444b76..4d63b34b35cf 100644 --- a/Documentation/isdn/interface_capi.rst +++ b/Documentation/isdn/interface_capi.rst @@ -323,7 +323,7 @@ If the lowest bit of showcapimsgs is set, kernelcapi logs controller and application up and down events. In addition, every registered CAPI controller has an associated traceflag -parameter controlling how CAPI messages sent from and to tha controller are +parameter controlling how CAPI messages sent from and to the controller are logged. The traceflag parameter is initialized with the value of the showcapimsgs parameter when the controller is registered, but can later be changed via the MANUFACTURER_REQ command KCAPI_CMD_TRACE. diff --git a/Documentation/isdn/m_isdn.rst b/Documentation/isdn/m_isdn.rst index 9957de349e69..5847a164287e 100644 --- a/Documentation/isdn/m_isdn.rst +++ b/Documentation/isdn/m_isdn.rst @@ -3,7 +3,7 @@ mISDN Driver ============ mISDN is a new modular ISDN driver, in the long term it should replace -the old I4L driver architecture for passiv ISDN cards. +the old I4L driver architecture for passive ISDN cards. It was designed to allow a broad range of applications and interfaces but only have the basic function in kernel, the interface to the user space is based on sockets with a own address family AF_ISDN. diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml index e23e3c94a932..bbcfa2472b04 100644 --- a/Documentation/netlink/genetlink-c.yaml +++ b/Documentation/netlink/genetlink-c.yaml @@ -218,9 +218,7 @@ properties: to a single enum. "directional" has the messages sent to the kernel and from the kernel enumerated separately. - "notify-split" has the notifications and request-response types in - different enums. - enum: [ unified, directional, notify-split ] + enum: [ unified ] name-prefix: description: | Prefix for the C enum name of the command. The name is formed by concatenating diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml index 88db2431ef26..5642925c4ceb 100644 --- a/Documentation/netlink/genetlink-legacy.yaml +++ b/Documentation/netlink/genetlink-legacy.yaml @@ -241,9 +241,7 @@ properties: to a single enum. "directional" has the messages sent to the kernel and from the kernel enumerated separately. - "notify-split" has the notifications and request-response types in - different enums. - enum: [ unified, directional, notify-split ] + enum: [ unified, directional ] # Trim name-prefix: description: | Prefix for the C enum name of the command. The name is formed by concatenating @@ -307,6 +305,13 @@ properties: type: array items: type: string + # Start genetlink-legacy + value: + description: | + ID of this message if value for request and response differ, + i.e. requests and responses have different message enums. + $ref: '#/$defs/uint' + # End genetlink-legacy reply: *subop-attr-list pre: description: Hook for a function to run before the main callback (pre_doit or start). diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml index b5e712bbe7e7..62a922755ce2 100644 --- a/Documentation/netlink/genetlink.yaml +++ b/Documentation/netlink/genetlink.yaml @@ -188,9 +188,7 @@ properties: to a single enum. "directional" has the messages sent to the kernel and from the kernel enumerated separately. - "notify-split" has the notifications and request-response types in - different enums. - enum: [ unified, directional, notify-split ] + enum: [ unified ] name-prefix: description: | Prefix for the C enum name of the command. The name is formed by concatenating diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml new file mode 100644 index 000000000000..82f4e6f8ddd3 --- /dev/null +++ b/Documentation/netlink/specs/ethtool.yaml @@ -0,0 +1,392 @@ +name: ethtool + +protocol: genetlink-legacy + +doc: Partial family for Ethtool Netlink. + +attribute-sets: + - + name: header + attributes: + - + name: dev-index + type: u32 + value: 1 + - + name: dev-name + type: string + - + name: flags + type: u32 + + - + name: bitset-bit + attributes: + - + name: index + type: u32 + value: 1 + - + name: name + type: string + - + name: value + type: flag + - + name: bitset-bits + attributes: + - + name: bit + type: nest + nested-attributes: bitset-bit + value: 1 + - + name: bitset + attributes: + - + name: nomask + type: flag + value: 1 + - + name: size + type: u32 + - + name: bits + type: nest + nested-attributes: bitset-bits + + - + name: string + attributes: + - + name: index + type: u32 + value: 1 + - + name: value + type: string + - + name: strings + attributes: + - + name: string + type: nest + value: 1 + multi-attr: true + nested-attributes: string + - + name: stringset + attributes: + - + name: id + type: u32 + value: 1 + - + name: count + type: u32 + - + name: strings + type: nest + multi-attr: true + nested-attributes: strings + - + name: stringsets + attributes: + - + name: stringset + type: nest + multi-attr: true + value: 1 + nested-attributes: stringset + - + name: strset + attributes: + - + name: header + value: 1 + type: nest + nested-attributes: header + - + name: stringsets + type: nest + nested-attributes: stringsets + - + name: counts-only + type: flag + + - + name: privflags + attributes: + - + name: header + value: 1 + type: nest + nested-attributes: header + - + name: flags + type: nest + nested-attributes: bitset + + - + name: rings + attributes: + - + name: header + value: 1 + type: nest + nested-attributes: header + - + name: rx-max + type: u32 + - + name: rx-mini-max + type: u32 + - + name: rx-jumbo-max + type: u32 + - + name: tx-max + type: u32 + - + name: rx + type: u32 + - + name: rx-mini + type: u32 + - + name: rx-jumbo + type: u32 + - + name: tx + type: u32 + - + name: rx-buf-len + type: u32 + - + name: tcp-data-split + type: u8 + - + name: cqe-size + type: u32 + - + name: tx-push + type: u8 + + - + name: mm-stat + attributes: + - + name: pad + value: 1 + type: pad + - + name: reassembly-errors + type: u64 + - + name: smd-errors + type: u64 + - + name: reassembly-ok + type: u64 + - + name: rx-frag-count + type: u64 + - + name: tx-frag-count + type: u64 + - + name: hold-count + type: u64 + - + name: mm + attributes: + - + name: header + value: 1 + type: nest + nested-attributes: header + - + name: pmac-enabled + type: u8 + - + name: tx-enabled + type: u8 + - + name: tx-active + type: u8 + - + name: tx-min-frag-size + type: u32 + - + name: tx-min-frag-size + type: u32 + - + name: verify-enabled + type: u8 + - + name: verify-status + type: u8 + - + name: verify-time + type: u32 + - + name: max-verify-time + type: u32 + - + name: stats + type: nest + nested-attributes: mm-stat + +operations: + enum-model: directional + list: + - + name: strset-get + doc: Get string set from the kernel. + + attribute-set: strset + + do: &strset-get-op + request: + value: 1 + attributes: + - header + - stringsets + - counts-only + reply: + value: 1 + attributes: + - header + - stringsets + dump: *strset-get-op + + # TODO: fill in the requests in between + + - + name: privflags-get + doc: Get device private flags. + + attribute-set: privflags + + do: &privflag-get-op + request: + value: 13 + attributes: + - header + reply: + value: 14 + attributes: + - header + - flags + dump: *privflag-get-op + - + name: privflags-set + doc: Set device private flags. + + attribute-set: privflags + + do: + request: + attributes: + - header + - flags + - + name: privflags-ntf + doc: Notification for change in device private flags. + notify: privflags-get + + - + name: rings-get + doc: Get ring params. + + attribute-set: rings + + do: &ring-get-op + request: + attributes: + - header + reply: + attributes: + - header + - rx-max + - rx-mini-max + - rx-jumbo-max + - tx-max + - rx + - rx-mini + - rx-jumbo + - tx + - rx-buf-len + - tcp-data-split + - cqe-size + - tx-push + dump: *ring-get-op + - + name: rings-set + doc: Set ring params. + + attribute-set: rings + + do: + request: + attributes: + - header + - rx + - rx-mini + - rx-jumbo + - tx + - rx-buf-len + - tcp-data-split + - cqe-size + - tx-push + - + name: rings-ntf + doc: Notification for change in ring params. + notify: rings-get + + # TODO: fill in the requests in between + + - + name: mm-get + doc: Get MAC Merge configuration and state + + attribute-set: mm + + do: &mm-get-op + request: + value: 42 + attributes: + - header + reply: + value: 42 + attributes: + - header + - pmac-enabled + - tx-enabled + - tx-active + - tx-min-frag-size + - rx-min-frag-size + - verify-enabled + - verify-time + - max-verify-time + - stats + dump: *mm-get-op + - + name: mm-set + doc: Set MAC Merge configuration + + attribute-set: mm + + do: + request: + attributes: + - header + - verify-enabled + - verify-time + - tx-enabled + - pmac-enabled + - tx-min-frag-size + - + name: mm-ntf + doc: Notification for change in MAC Merge configuration. + notify: mm-get diff --git a/Documentation/networking/af_xdp.rst b/Documentation/networking/af_xdp.rst index 60b217b436be..247c6c4127e9 100644 --- a/Documentation/networking/af_xdp.rst +++ b/Documentation/networking/af_xdp.rst @@ -419,7 +419,7 @@ XDP_UMEM_REG setsockopt ----------------------- This setsockopt registers a UMEM to a socket. This is the area that -contain all the buffers that packet can recide in. The call takes a +contain all the buffers that packet can reside in. The call takes a pointer to the beginning of this area and the size of it. Moreover, it also has parameter called chunk_size that is the size that the UMEM is divided into. It can only be 2K or 4K at the moment. If you have an @@ -592,7 +592,7 @@ A: When a netdev of a physical NIC is initialized, Linux usually A number of other ways are possible all up to the capabilities of the NIC you have. -Q: Can I use the XSKMAP to implement a switch betwen different umems +Q: Can I use the XSKMAP to implement a switch between different umems in copy mode? A: The short answer is no, that is not supported at the moment. The diff --git a/Documentation/networking/arcnet-hardware.rst b/Documentation/networking/arcnet-hardware.rst index ac249ac8fcf2..982215723582 100644 --- a/Documentation/networking/arcnet-hardware.rst +++ b/Documentation/networking/arcnet-hardware.rst @@ -1902,7 +1902,7 @@ of 32 possible I/O Base addresses using the following tables:: 6 | 10 The I/O address is sum of all switches set to "1". Remember that -the I/O address space bellow 0x200 is RESERVED for mainboard, so +the I/O address space below 0x200 is RESERVED for mainboard, so switch 1 should be ALWAYS SET TO OFF. diff --git a/Documentation/networking/batman-adv.rst b/Documentation/networking/batman-adv.rst index b85563ea3682..8a0dcb1894b4 100644 --- a/Documentation/networking/batman-adv.rst +++ b/Documentation/networking/batman-adv.rst @@ -159,7 +159,7 @@ Please send us comments, experiences, questions, anything :) IRC: #batadv on ircs://irc.hackint.org/ Mailing-list: - b.a.t.m.a.n@open-mesh.org (optional subscription at + b.a.t.m.a.n@lists.open-mesh.org (optional subscription at https://lists.open-mesh.org/mailman3/postorius/lists/b.a.t.m.a.n.lists.open-mesh.org/) You can also contact the Authors: diff --git a/Documentation/networking/can.rst b/Documentation/networking/can.rst index 90121deef217..d7e1ada905b2 100644 --- a/Documentation/networking/can.rst +++ b/Documentation/networking/can.rst @@ -931,7 +931,7 @@ ival1: ival2: Throttle the received message rate down to the value of ival2. This is useful to reduce messages for the application when the signal inside the - CAN frame is stateless as state changes within the ival2 periode may get + CAN frame is stateless as state changes within the ival2 period may get lost. Broadcast Manager Multiplex Message Receive Filter diff --git a/Documentation/networking/can_ucan_protocol.rst b/Documentation/networking/can_ucan_protocol.rst index 638ac1ee7914..935d872ae87c 100644 --- a/Documentation/networking/can_ucan_protocol.rst +++ b/Documentation/networking/can_ucan_protocol.rst @@ -50,7 +50,7 @@ Setup Packet ``wIndex`` USB Interface Index (0 for device commands) ``wLength`` * Host to Device - Number of bytes to transmit * Device to Host - Maximum Number of bytes to - receive. If the device send less. Commom ZLP + receive. If the device send less. Common ZLP semantics are used. ================= ===================================================== diff --git a/Documentation/networking/cdc_mbim.rst b/Documentation/networking/cdc_mbim.rst index 0048409c06b4..37f968acc473 100644 --- a/Documentation/networking/cdc_mbim.rst +++ b/Documentation/networking/cdc_mbim.rst @@ -93,7 +93,7 @@ MBIM function can be looked up using sysfs. For example:: USB configuration descriptors ----------------------------- The wMaxControlMessage field of the CDC MBIM functional descriptor -limits the maximum control message size. The managament application is +limits the maximum control message size. The management application is responsible for negotiating a control message size complying with the requirements in section 9.3.1 of [1], taking this descriptor field into consideration. diff --git a/Documentation/networking/device_drivers/atm/iphase.rst b/Documentation/networking/device_drivers/atm/iphase.rst index 92d9b757d75a..388c7101e2cb 100644 --- a/Documentation/networking/device_drivers/atm/iphase.rst +++ b/Documentation/networking/device_drivers/atm/iphase.rst @@ -4,7 +4,7 @@ ATM (i)Chip IA Linux Driver Source ================================== - READ ME FISRT + READ ME FIRST -------------------------------------------------------------------------------- diff --git a/Documentation/networking/device_drivers/can/ctu/ctucanfd-driver.rst b/Documentation/networking/device_drivers/can/ctu/ctucanfd-driver.rst index 40c92ea272af..1a4fc6607582 100644 --- a/Documentation/networking/device_drivers/can/ctu/ctucanfd-driver.rst +++ b/Documentation/networking/device_drivers/can/ctu/ctucanfd-driver.rst @@ -577,7 +577,7 @@ CTU CAN FD IP Core and Driver Development Acknowledgment * Linux driver development * continuous integration platform architect and GHDL updates - * theses `Open-source and Open-hardware CAN FD Protocol Support <https://dspace.cvut.cz/bitstream/handle/10467/80366/F3-DP-2019-Jerabek-Martin-Jerabek-thesis-2019-canfd.pdf>`_ + * thesis `Open-source and Open-hardware CAN FD Protocol Support <https://dspace.cvut.cz/bitstream/handle/10467/80366/F3-DP-2019-Jerabek-Martin-Jerabek-thesis-2019-canfd.pdf>`_ * Jiri Novak <jnovak@fel.cvut.cz> @@ -603,7 +603,7 @@ CTU CAN FD IP Core and Driver Development Acknowledgment * Jan Charvat * implemented CTU CAN FD functional model for QEMU which has been integrated into QEMU mainline (`docs/system/devices/can.rst <https://www.qemu.org/docs/master/system/devices/can.html>`_) - * Bachelor theses Model of CAN FD Communication Controller for QEMU Emulator + * Bachelor thesis Model of CAN FD Communication Controller for QEMU Emulator Notes ----- diff --git a/Documentation/networking/device_drivers/can/ctu/fsm_txt_buffer_user.svg b/Documentation/networking/device_drivers/can/ctu/fsm_txt_buffer_user.svg index b371650788f4..381323423b4c 100644 --- a/Documentation/networking/device_drivers/can/ctu/fsm_txt_buffer_user.svg +++ b/Documentation/networking/device_drivers/can/ctu/fsm_txt_buffer_user.svg @@ -129,10 +129,10 @@ </g> </g> <text transform="matrix(.264583 0 0 .264583 91.8919 139.964)" x="26.959213" y="9.11724" fill="#2aa1ff" filter="url(#filter1204-6-2-9-1-3-1)" font-size="12px" stroke-width="3.77953" text-align="center" text-anchor="middle" style="line-height:1.1" xml:space="preserve"><tspan x="26.959213" y="9.11724" text-align="center">Set</tspan><tspan x="26.959213" y="22.31724" text-align="center">abort</tspan></text> - <text transform="translate(49.0277 104.823)" x="57.620724" y="16.855087" filter="url(#filter1204)" font-size="3.175px" text-align="center" text-anchor="middle" style="line-height:1.1" xml:space="preserve"><tspan x="57.620724" y="16.855087" text-align="center">Transmission</tspan><tspan x="57.620724" y="20.347588" text-align="center">unsuccesfull</tspan></text> + <text transform="translate(49.0277 104.823)" x="57.620724" y="16.855087" filter="url(#filter1204)" font-size="3.175px" text-align="center" text-anchor="middle" style="line-height:1.1" xml:space="preserve"><tspan x="57.620724" y="16.855087" text-align="center">Transmission</tspan><tspan x="57.620724" y="20.347588" text-align="center">unsuccessful</tspan></text> <g font-size="12px" stroke-width="3.77953" text-anchor="middle"> <text transform="matrix(.264583 0 0 .264583 68.5988 118.913)" x="38.824219" y="9.1171875" filter="url(#filter1204)" text-align="center" style="line-height:1.1" xml:space="preserve"><tspan x="38.824219" y="9.1171875" text-align="center">Transmission</tspan><tspan x="38.824219" y="22.317188" text-align="center">starts</tspan></text> - <text transform="matrix(.264583 0 0 .264583 106.802 130.509)" x="38.824219" y="9.1171875" filter="url(#filter1204)" text-align="center" style="line-height:1.1" xml:space="preserve"><tspan x="38.824219" y="9.1171875" text-align="center">Transmission</tspan><tspan x="38.824219" y="22.317188" text-align="center">succesfull</tspan></text> + <text transform="matrix(.264583 0 0 .264583 106.802 130.509)" x="38.824219" y="9.1171875" filter="url(#filter1204)" text-align="center" style="line-height:1.1" xml:space="preserve"><tspan x="38.824219" y="9.1171875" text-align="center">Transmission</tspan><tspan x="38.824219" y="22.317188" text-align="center">successful</tspan></text> <text transform="matrix(.264583 0 0 .264583 107.77 145.476)" x="38.824219" y="9.1171875" filter="url(#filter1204)" text-align="center" style="line-height:1.1" xml:space="preserve"><tspan x="38.824219" y="9.1171875" text-align="center">Transmission</tspan><tspan x="38.824219" y="22.317188" text-align="center">sborted</tspan></text> </g> <g stroke-width="3.77953" text-anchor="middle"> diff --git a/Documentation/networking/device_drivers/ethernet/3com/vortex.rst b/Documentation/networking/device_drivers/ethernet/3com/vortex.rst index e89e4192af88..a060f84c4f96 100644 --- a/Documentation/networking/device_drivers/ethernet/3com/vortex.rst +++ b/Documentation/networking/device_drivers/ethernet/3com/vortex.rst @@ -254,7 +254,7 @@ Media selection A number of the older NICs such as the 3c590 and 3c900 series have 10base2 and AUI interfaces. -Prior to January, 2001 this driver would autoeselect the 10base2 or AUI +Prior to January, 2001 this driver would autoselect the 10base2 or AUI port if it didn't detect activity on the 10baseT port. It would then get stuck on the 10base2 port and a driver reload was necessary to switch back to 10baseT. This behaviour could not be prevented with a diff --git a/Documentation/networking/device_drivers/ethernet/aquantia/atlantic.rst b/Documentation/networking/device_drivers/ethernet/aquantia/atlantic.rst index 595ddef1c8b3..099280a261be 100644 --- a/Documentation/networking/device_drivers/ethernet/aquantia/atlantic.rst +++ b/Documentation/networking/device_drivers/ethernet/aquantia/atlantic.rst @@ -270,7 +270,7 @@ RX flow rules (ntuple filters) ethtool -K ethX ntuple <on|off> - When disabling ntuple filters, all the user programed filters are + When disabling ntuple filters, all the user programmed filters are flushed from the driver cache and hardware. All needed filters must be re-added when ntuple is re-enabled. @@ -418,7 +418,7 @@ Default value: 0xFFFF 0 Disable interrupt throttling. 1 Enable interrupt throttling and use specified tx and rx rates. 0xFFFF Auto throttling mode. Driver will choose the best RX and TX - interrupt throtting settings based on link speed. + interrupt throttling settings based on link speed. ====== ============================================================== aq_itr_tx - TX interrupt throttle rate @@ -456,7 +456,7 @@ AQ_CFG_RX_PAGEORDER Default value: 0 -RX page order override. Thats a power of 2 number of RX pages allocated for +RX page order override. That's a power of 2 number of RX pages allocated for each descriptor. Received descriptor size is still limited by AQ_CFG_RX_FRAME_MAX. diff --git a/Documentation/networking/device_drivers/ethernet/freescale/dpaa2/mac-phy-support.rst b/Documentation/networking/device_drivers/ethernet/freescale/dpaa2/mac-phy-support.rst index 1d2f55feca24..e2a36d0d88ef 100644 --- a/Documentation/networking/device_drivers/ethernet/freescale/dpaa2/mac-phy-support.rst +++ b/Documentation/networking/device_drivers/ethernet/freescale/dpaa2/mac-phy-support.rst @@ -11,7 +11,7 @@ Overview -------- The DPAA2 MAC / PHY support consists of a set of APIs that help DPAA2 network -drivers (dpaa2-eth, dpaa2-ethsw) interract with the PHY library. +drivers (dpaa2-eth, dpaa2-ethsw) interact with the PHY library. DPAA2 Software Architecture --------------------------- diff --git a/Documentation/networking/device_drivers/ethernet/index.rst b/Documentation/networking/device_drivers/ethernet/index.rst index 5196905582c5..392969ac88ad 100644 --- a/Documentation/networking/device_drivers/ethernet/index.rst +++ b/Documentation/networking/device_drivers/ethernet/index.rst @@ -39,7 +39,7 @@ Contents: intel/ice marvell/octeontx2 marvell/octeon_ep - mellanox/mlx5 + mellanox/mlx5/index microsoft/netvsc neterion/s2io netronome/nfp diff --git a/Documentation/networking/device_drivers/ethernet/intel/ice.rst b/Documentation/networking/device_drivers/ethernet/intel/ice.rst index 1aa029d08cb1..5efea4dd1251 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/ice.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/ice.rst @@ -819,7 +819,7 @@ NAPI ---- This driver supports NAPI (Rx polling mode). For more information on NAPI, see -https://www.linuxfoundation.org/collaborate/workgroups/networking/napi +https://wiki.linuxfoundation.org/networking/napi MACVLAN diff --git a/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst b/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst index dd5cd69467be..5ba9015336e2 100644 --- a/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst +++ b/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst @@ -127,7 +127,7 @@ Type1: Type2: - RVU PF0 ie admin function creates these VFs and maps them to loopback block's channels. - A set of two VFs (VF0 & VF1, VF2 & VF3 .. so on) works as a pair ie pkts sent out of - VF0 will be received by VF1 and viceversa. + VF0 will be received by VF1 and vice versa. - These VFs can be used by applications or virtual machines to communicate between them without sending traffic outside. There is no switch present in HW, hence the support for loopback VFs. diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst deleted file mode 100644 index 6969652f593c..000000000000 --- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst +++ /dev/null @@ -1,746 +0,0 @@ -.. SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB - -================================================= -Mellanox ConnectX(R) mlx5 core VPI Network Driver -================================================= - -Copyright (c) 2019, Mellanox Technologies LTD. - -Contents -======== - -- `Enabling the driver and kconfig options`_ -- `Devlink info`_ -- `Devlink parameters`_ -- `Bridge offload`_ -- `mlx5 subfunction`_ -- `mlx5 function attributes`_ -- `Devlink health reporters`_ -- `mlx5 tracepoints`_ - -Enabling the driver and kconfig options -======================================= - -| mlx5 core is modular and most of the major mlx5 core driver features can be selected (compiled in/out) -| at build time via kernel Kconfig flags. -| Basic features, ethernet net device rx/tx offloads and XDP, are available with the most basic flags -| CONFIG_MLX5_CORE=y/m and CONFIG_MLX5_CORE_EN=y. -| For the list of advanced features, please see below. - -**CONFIG_MLX5_CORE=(y/m/n)** (module mlx5_core.ko) - -| The driver can be enabled by choosing CONFIG_MLX5_CORE=y/m in kernel config. -| This will provide mlx5 core driver for mlx5 ulps to interface with (mlx5e, mlx5_ib). - - -**CONFIG_MLX5_CORE_EN=(y/n)** - -| Choosing this option will allow basic ethernet netdevice support with all of the standard rx/tx offloads. -| mlx5e is the mlx5 ulp driver which provides netdevice kernel interface, when chosen, mlx5e will be -| built-in into mlx5_core.ko. - - -**CONFIG_MLX5_EN_ARFS=(y/n)** - -| Enables Hardware-accelerated receive flow steering (arfs) support, and ntuple filtering. -| https://community.mellanox.com/s/article/howto-configure-arfs-on-connectx-4 - - -**CONFIG_MLX5_EN_RXNFC=(y/n)** - -| Enables ethtool receive network flow classification, which allows user defined -| flow rules to direct traffic into arbitrary rx queue via ethtool set/get_rxnfc API. - - -**CONFIG_MLX5_CORE_EN_DCB=(y/n)**: - -| Enables `Data Center Bridging (DCB) Support <https://community.mellanox.com/s/article/howto-auto-config-pfc-and-ets-on-connectx-4-via-lldp-dcbx>`_. - - -**CONFIG_MLX5_MPFS=(y/n)** - -| Ethernet Multi-Physical Function Switch (MPFS) support in ConnectX NIC. -| MPFs is required for when `Multi-Host <http://www.mellanox.com/page/multihost>`_ configuration is enabled to allow passing -| user configured unicast MAC addresses to the requesting PF. - - -**CONFIG_MLX5_ESWITCH=(y/n)** - -| Ethernet SRIOV E-Switch support in ConnectX NIC. E-Switch provides internal SRIOV packet steering -| and switching for the enabled VFs and PF in two available modes: -| 1) `Legacy SRIOV mode (L2 mac vlan steering based) <https://community.mellanox.com/s/article/howto-configure-sr-iov-for-connectx-4-connectx-5-with-kvm--ethernet-x>`_. -| 2) `Switchdev mode (eswitch offloads) <https://www.mellanox.com/related-docs/prod_software/ASAP2_Hardware_Offloading_for_vSwitches_User_Manual_v4.4.pdf>`_. - - -**CONFIG_MLX5_CORE_IPOIB=(y/n)** - -| IPoIB offloads & acceleration support. -| Requires CONFIG_MLX5_CORE_EN to provide an accelerated interface for the rdma -| IPoIB ulp netdevice. - - -**CONFIG_MLX5_FPGA=(y/n)** - -| Build support for the Innova family of network cards by Mellanox Technologies. -| Innova network cards are comprised of a ConnectX chip and an FPGA chip on one board. -| If you select this option, the mlx5_core driver will include the Innova FPGA core and allow -| building sandbox-specific client drivers. - - -**CONFIG_MLX5_EN_IPSEC=(y/n)** - -| Enables `IPSec XFRM cryptography-offload acceleration <http://www.mellanox.com/related-docs/prod_software/Mellanox_Innova_IPsec_Ethernet_Adapter_Card_User_Manual.pdf>`_. - -**CONFIG_MLX5_EN_TLS=(y/n)** - -| TLS cryptography-offload acceleration. - - -**CONFIG_MLX5_INFINIBAND=(y/n/m)** (module mlx5_ib.ko) - -| Provides low-level InfiniBand/RDMA and `RoCE <https://community.mellanox.com/s/article/recommended-network-configuration-examples-for-roce-deployment>`_ support. - -**CONFIG_MLX5_SF=(y/n)** - -| Build support for subfunction. -| Subfunctons are more light weight than PCI SRIOV VFs. Choosing this option -| will enable support for creating subfunction devices. - -**External options** ( Choose if the corresponding mlx5 feature is required ) - -- CONFIG_PTP_1588_CLOCK: When chosen, mlx5 ptp support will be enabled -- CONFIG_VXLAN: When chosen, mlx5 vxlan support will be enabled. -- CONFIG_MLXFW: When chosen, mlx5 firmware flashing support will be enabled (via devlink and ethtool). - -Devlink info -============ - -The devlink info reports the running and stored firmware versions on device. -It also prints the device PSID which represents the HCA board type ID. - -User command example:: - - $ devlink dev info pci/0000:00:06.0 - pci/0000:00:06.0: - driver mlx5_core - versions: - fixed: - fw.psid MT_0000000009 - running: - fw.version 16.26.0100 - stored: - fw.version 16.26.0100 - -Devlink parameters -================== - -flow_steering_mode: Device flow steering mode ---------------------------------------------- -The flow steering mode parameter controls the flow steering mode of the driver. -Two modes are supported: -1. 'dmfs' - Device managed flow steering. -2. 'smfs' - Software/Driver managed flow steering. - -In DMFS mode, the HW steering entities are created and managed through the -Firmware. -In SMFS mode, the HW steering entities are created and managed though by -the driver directly into hardware without firmware intervention. - -SMFS mode is faster and provides better rule insertion rate compared to default DMFS mode. - -User command examples: - -- Set SMFS flow steering mode:: - - $ devlink dev param set pci/0000:06:00.0 name flow_steering_mode value "smfs" cmode runtime - -- Read device flow steering mode:: - - $ devlink dev param show pci/0000:06:00.0 name flow_steering_mode - pci/0000:06:00.0: - name flow_steering_mode type driver-specific - values: - cmode runtime value smfs - -enable_roce: RoCE enablement state ----------------------------------- -RoCE enablement state controls driver support for RoCE traffic. -When RoCE is disabled, there is no gid table, only raw ethernet QPs are supported and traffic on the well-known UDP RoCE port is handled as raw ethernet traffic. - -To change RoCE enablement state, a user must change the driverinit cmode value and run devlink reload. - -User command examples: - -- Disable RoCE:: - - $ devlink dev param set pci/0000:06:00.0 name enable_roce value false cmode driverinit - $ devlink dev reload pci/0000:06:00.0 - -- Read RoCE enablement state:: - - $ devlink dev param show pci/0000:06:00.0 name enable_roce - pci/0000:06:00.0: - name enable_roce type generic - values: - cmode driverinit value true - -esw_port_metadata: Eswitch port metadata state ----------------------------------------------- -When applicable, disabling eswitch metadata can increase packet rate -up to 20% depending on the use case and packet sizes. - -Eswitch port metadata state controls whether to internally tag packets with -metadata. Metadata tagging must be enabled for multi-port RoCE, failover -between representors and stacked devices. -By default metadata is enabled on the supported devices in E-switch. -Metadata is applicable only for E-switch in switchdev mode and -users may disable it when NONE of the below use cases will be in use: -1. HCA is in Dual/multi-port RoCE mode. -2. VF/SF representor bonding (Usually used for Live migration) -3. Stacked devices - -When metadata is disabled, the above use cases will fail to initialize if -users try to enable them. - -- Show eswitch port metadata:: - - $ devlink dev param show pci/0000:06:00.0 name esw_port_metadata - pci/0000:06:00.0: - name esw_port_metadata type driver-specific - values: - cmode runtime value true - -- Disable eswitch port metadata:: - - $ devlink dev param set pci/0000:06:00.0 name esw_port_metadata value false cmode runtime - -- Change eswitch mode to switchdev mode where after choosing the metadata value:: - - $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev - -Bridge offload -============== -The mlx5 driver implements support for offloading bridge rules when in switchdev -mode. Linux bridge FDBs are automatically offloaded when mlx5 switchdev -representor is attached to bridge. - -- Change device to switchdev mode:: - - $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev - -- Attach mlx5 switchdev representor 'enp8s0f0' to bridge netdev 'bridge1':: - - $ ip link set enp8s0f0 master bridge1 - -VLANs ------ -Following bridge VLAN functions are supported by mlx5: - -- VLAN filtering (including multiple VLANs per port):: - - $ ip link set bridge1 type bridge vlan_filtering 1 - $ bridge vlan add dev enp8s0f0 vid 2-3 - -- VLAN push on bridge ingress:: - - $ bridge vlan add dev enp8s0f0 vid 3 pvid - -- VLAN pop on bridge egress:: - - $ bridge vlan add dev enp8s0f0 vid 3 untagged - -mlx5 subfunction -================ -mlx5 supports subfunction management using devlink port (see :ref:`Documentation/networking/devlink/devlink-port.rst <devlink_port>`) interface. - -A subfunction has its own function capabilities and its own resources. This -means a subfunction has its own dedicated queues (txq, rxq, cq, eq). These -queues are neither shared nor stolen from the parent PCI function. - -When a subfunction is RDMA capable, it has its own QP1, GID table, and RDMA -resources neither shared nor stolen from the parent PCI function. - -A subfunction has a dedicated window in PCI BAR space that is not shared -with the other subfunctions or the parent PCI function. This ensures that all -devices (netdev, rdma, vdpa, etc.) of the subfunction accesses only assigned -PCI BAR space. - -A subfunction supports eswitch representation through which it supports tc -offloads. The user configures eswitch to send/receive packets from/to -the subfunction port. - -Subfunctions share PCI level resources such as PCI MSI-X IRQs with -other subfunctions and/or with its parent PCI function. - -Example mlx5 software, system, and device view:: - - _______ - | admin | - | user |---------- - |_______| | - | | - ____|____ __|______ _________________ - | | | | | | - | devlink | | tc tool | | user | - | tool | |_________| | applications | - |_________| | |_________________| - | | | | - | | | | Userspace - +---------|-------------|-------------------|----------|--------------------+ - | | +----------+ +----------+ Kernel - | | | netdev | | rdma dev | - | | +----------+ +----------+ - (devlink port add/del | ^ ^ - port function set) | | | - | | +---------------| - _____|___ | | _______|_______ - | | | | | mlx5 class | - | devlink | +------------+ | | drivers | - | kernel | | rep netdev | | |(mlx5_core,ib) | - |_________| +------------+ | |_______________| - | | | ^ - (devlink ops) | | (probe/remove) - _________|________ | | ____|________ - | subfunction | | +---------------+ | subfunction | - | management driver|----- | subfunction |---| driver | - | (mlx5_core) | | auxiliary dev | | (mlx5_core) | - |__________________| +---------------+ |_____________| - | ^ - (sf add/del, vhca events) | - | (device add/del) - _____|____ ____|________ - | | | subfunction | - | PCI NIC |--- activate/deactivate events--->| host driver | - |__________| | (mlx5_core) | - |_____________| - -Subfunction is created using devlink port interface. - -- Change device to switchdev mode:: - - $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev - -- Add a devlink port of subfunction flavour:: - - $ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88 - pci/0000:06:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false - function: - hw_addr 00:00:00:00:00:00 state inactive opstate detached - -- Show a devlink port of the subfunction:: - - $ devlink port show pci/0000:06:00.0/32768 - pci/0000:06:00.0/32768: type eth netdev enp6s0pf0sf88 flavour pcisf pfnum 0 sfnum 88 - function: - hw_addr 00:00:00:00:00:00 state inactive opstate detached - -- Delete a devlink port of subfunction after use:: - - $ devlink port del pci/0000:06:00.0/32768 - -mlx5 function attributes -======================== -The mlx5 driver provides a mechanism to setup PCI VF/SF function attributes in -a unified way for SmartNIC and non-SmartNIC. - -This is supported only when the eswitch mode is set to switchdev. Port function -configuration of the PCI VF/SF is supported through devlink eswitch port. - -Port function attributes should be set before PCI VF/SF is enumerated by the -driver. - -MAC address setup ------------------ -mlx5 driver support devlink port function attr mechanism to setup MAC -address. (refer to Documentation/networking/devlink/devlink-port.rst) - -RoCE capability setup ---------------------- -Not all mlx5 PCI devices/SFs require RoCE capability. - -When RoCE capability is disabled, it saves 1 Mbytes worth of system memory per -PCI devices/SF. - -mlx5 driver support devlink port function attr mechanism to setup RoCE -capability. (refer to Documentation/networking/devlink/devlink-port.rst) - -migratable capability setup ---------------------------- -User who wants mlx5 PCI VFs to be able to perform live migration need to -explicitly enable the VF migratable capability. - -mlx5 driver support devlink port function attr mechanism to setup migratable -capability. (refer to Documentation/networking/devlink/devlink-port.rst) - -SF state setup --------------- -To use the SF, the user must activate the SF using the SF function state -attribute. - -- Get the state of the SF identified by its unique devlink port index:: - - $ devlink port show ens2f0npf0sf88 - pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false - function: - hw_addr 00:00:00:00:88:88 state inactive opstate detached - -- Activate the function and verify its state is active:: - - $ devlink port function set ens2f0npf0sf88 state active - - $ devlink port show ens2f0npf0sf88 - pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false - function: - hw_addr 00:00:00:00:88:88 state active opstate detached - -Upon function activation, the PF driver instance gets the event from the device -that a particular SF was activated. It's the cue to put the device on bus, probe -it and instantiate the devlink instance and class specific auxiliary devices -for it. - -- Show the auxiliary device and port of the subfunction:: - - $ devlink dev show - devlink dev show auxiliary/mlx5_core.sf.4 - - $ devlink port show auxiliary/mlx5_core.sf.4/1 - auxiliary/mlx5_core.sf.4/1: type eth netdev p0sf88 flavour virtual port 0 splittable false - - $ rdma link show mlx5_0/1 - link mlx5_0/1 state ACTIVE physical_state LINK_UP netdev p0sf88 - - $ rdma dev show - 8: rocep6s0f1: node_type ca fw 16.29.0550 node_guid 248a:0703:00b3:d113 sys_image_guid 248a:0703:00b3:d112 - 13: mlx5_0: node_type ca fw 16.29.0550 node_guid 0000:00ff:fe00:8888 sys_image_guid 248a:0703:00b3:d112 - -- Subfunction auxiliary device and class device hierarchy:: - - mlx5_core.sf.4 - (subfunction auxiliary device) - /\ - / \ - / \ - / \ - / \ - mlx5_core.eth.4 mlx5_core.rdma.4 - (sf eth aux dev) (sf rdma aux dev) - | | - | | - p0sf88 mlx5_0 - (sf netdev) (sf rdma device) - -Additionally, the SF port also gets the event when the driver attaches to the -auxiliary device of the subfunction. This results in changing the operational -state of the function. This provides visibility to the user to decide when is it -safe to delete the SF port for graceful termination of the subfunction. - -- Show the SF port operational state:: - - $ devlink port show ens2f0npf0sf88 - pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false - function: - hw_addr 00:00:00:00:88:88 state active opstate attached - -Devlink health reporters -======================== - -tx reporter ------------ -The tx reporter is responsible for reporting and recovering of the following two error scenarios: - -- tx timeout - Report on kernel tx timeout detection. - Recover by searching lost interrupts. -- tx error completion - Report on error tx completion. - Recover by flushing the tx queue and reset it. - -tx reporter also support on demand diagnose callback, on which it provides -real time information of its send queues status. - -User commands examples: - -- Diagnose send queues status:: - - $ devlink health diagnose pci/0000:82:00.0 reporter tx - -NOTE: This command has valid output only when interface is up, otherwise the command has empty output. - -- Show number of tx errors indicated, number of recover flows ended successfully, - is autorecover enabled and graceful period from last recover:: - - $ devlink health show pci/0000:82:00.0 reporter tx - -rx reporter ------------ -The rx reporter is responsible for reporting and recovering of the following two error scenarios: - -- rx queues' initialization (population) timeout - Population of rx queues' descriptors on ring initialization is done - in napi context via triggering an irq. In case of a failure to get - the minimum amount of descriptors, a timeout would occur, and - descriptors could be recovered by polling the EQ (Event Queue). -- rx completions with errors (reported by HW on interrupt context) - Report on rx completion error. - Recover (if needed) by flushing the related queue and reset it. - -rx reporter also supports on demand diagnose callback, on which it -provides real time information of its receive queues' status. - -- Diagnose rx queues' status and corresponding completion queue:: - - $ devlink health diagnose pci/0000:82:00.0 reporter rx - -NOTE: This command has valid output only when interface is up. Otherwise, the command has empty output. - -- Show number of rx errors indicated, number of recover flows ended successfully, - is autorecover enabled, and graceful period from last recover:: - - $ devlink health show pci/0000:82:00.0 reporter rx - -fw reporter ------------ -The fw reporter implements `diagnose` and `dump` callbacks. -It follows symptoms of fw error such as fw syndrome by triggering -fw core dump and storing it into the dump buffer. -The fw reporter diagnose command can be triggered any time by the user to check -current fw status. - -User commands examples: - -- Check fw heath status:: - - $ devlink health diagnose pci/0000:82:00.0 reporter fw - -- Read FW core dump if already stored or trigger new one:: - - $ devlink health dump show pci/0000:82:00.0 reporter fw - -NOTE: This command can run only on the PF which has fw tracer ownership, -running it on other PF or any VF will return "Operation not permitted". - -fw fatal reporter ------------------ -The fw fatal reporter implements `dump` and `recover` callbacks. -It follows fatal errors indications by CR-space dump and recover flow. -The CR-space dump uses vsc interface which is valid even if the FW command -interface is not functional, which is the case in most FW fatal errors. -The recover function runs recover flow which reloads the driver and triggers fw -reset if needed. -On firmware error, the health buffer is dumped into the dmesg. The log -level is derived from the error's severity (given in health buffer). - -User commands examples: - -- Run fw recover flow manually:: - - $ devlink health recover pci/0000:82:00.0 reporter fw_fatal - -- Read FW CR-space dump if already stored or trigger new one:: - - $ devlink health dump show pci/0000:82:00.1 reporter fw_fatal - -NOTE: This command can run only on PF. - -mlx5 tracepoints -================ - -mlx5 driver provides internal tracepoints for tracking and debugging using -kernel tracepoints interfaces (refer to Documentation/trace/ftrace.rst). - -For the list of support mlx5 events, check `/sys/kernel/debug/tracing/events/mlx5/`. - -tc and eswitch offloads tracepoints: - -- mlx5e_configure_flower: trace flower filter actions and cookies offloaded to mlx5:: - - $ echo mlx5:mlx5e_configure_flower >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - tc-6535 [019] ...1 2672.404466: mlx5e_configure_flower: cookie=0000000067874a55 actions= REDIRECT - -- mlx5e_delete_flower: trace flower filter actions and cookies deleted from mlx5:: - - $ echo mlx5:mlx5e_delete_flower >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - tc-6569 [010] .N.1 2686.379075: mlx5e_delete_flower: cookie=0000000067874a55 actions= NULL - -- mlx5e_stats_flower: trace flower stats request:: - - $ echo mlx5:mlx5e_stats_flower >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - tc-6546 [010] ...1 2679.704889: mlx5e_stats_flower: cookie=0000000060eb3d6a bytes=0 packets=0 lastused=4295560217 - -- mlx5e_tc_update_neigh_used_value: trace tunnel rule neigh update value offloaded to mlx5:: - - $ echo mlx5:mlx5e_tc_update_neigh_used_value >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - kworker/u48:4-8806 [009] ...1 55117.882428: mlx5e_tc_update_neigh_used_value: netdev: ens1f0 IPv4: 1.1.1.10 IPv6: ::ffff:1.1.1.10 neigh_used=1 - -- mlx5e_rep_neigh_update: trace neigh update tasks scheduled due to neigh state change events:: - - $ echo mlx5:mlx5e_rep_neigh_update >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - kworker/u48:7-2221 [009] ...1 1475.387435: mlx5e_rep_neigh_update: netdev: ens1f0 MAC: 24:8a:07:9a:17:9a IPv4: 1.1.1.10 IPv6: ::ffff:1.1.1.10 neigh_connected=1 - -Bridge offloads tracepoints: - -- mlx5_esw_bridge_fdb_entry_init: trace bridge FDB entry offloaded to mlx5:: - - $ echo mlx5:mlx5_esw_bridge_fdb_entry_init >> set_event - $ cat /sys/kernel/debug/tracing/trace - ... - kworker/u20:9-2217 [003] ...1 318.582243: mlx5_esw_bridge_fdb_entry_init: net_device=enp8s0f0_0 addr=e4:fd:05:08:00:02 vid=0 flags=0 used=0 - -- mlx5_esw_bridge_fdb_entry_cleanup: trace bridge FDB entry deleted from mlx5:: - - $ echo mlx5:mlx5_esw_bridge_fdb_entry_cleanup >> set_event - $ cat /sys/kernel/debug/tracing/trace - ... - ip-2581 [005] ...1 318.629871: mlx5_esw_bridge_fdb_entry_cleanup: net_device=enp8s0f0_1 addr=e4:fd:05:08:00:03 vid=0 flags=0 used=16 - -- mlx5_esw_bridge_fdb_entry_refresh: trace bridge FDB entry offload refreshed in - mlx5:: - - $ echo mlx5:mlx5_esw_bridge_fdb_entry_refresh >> set_event - $ cat /sys/kernel/debug/tracing/trace - ... - kworker/u20:8-3849 [003] ...1 466716: mlx5_esw_bridge_fdb_entry_refresh: net_device=enp8s0f0_0 addr=e4:fd:05:08:00:02 vid=3 flags=0 used=0 - -- mlx5_esw_bridge_vlan_create: trace bridge VLAN object add on mlx5 - representor:: - - $ echo mlx5:mlx5_esw_bridge_vlan_create >> set_event - $ cat /sys/kernel/debug/tracing/trace - ... - ip-2560 [007] ...1 318.460258: mlx5_esw_bridge_vlan_create: vid=1 flags=6 - -- mlx5_esw_bridge_vlan_cleanup: trace bridge VLAN object delete from mlx5 - representor:: - - $ echo mlx5:mlx5_esw_bridge_vlan_cleanup >> set_event - $ cat /sys/kernel/debug/tracing/trace - ... - bridge-2582 [007] ...1 318.653496: mlx5_esw_bridge_vlan_cleanup: vid=2 flags=8 - -- mlx5_esw_bridge_vport_init: trace mlx5 vport assigned with bridge upper - device:: - - $ echo mlx5:mlx5_esw_bridge_vport_init >> set_event - $ cat /sys/kernel/debug/tracing/trace - ... - ip-2560 [007] ...1 318.458915: mlx5_esw_bridge_vport_init: vport_num=1 - -- mlx5_esw_bridge_vport_cleanup: trace mlx5 vport removed from bridge upper - device:: - - $ echo mlx5:mlx5_esw_bridge_vport_cleanup >> set_event - $ cat /sys/kernel/debug/tracing/trace - ... - ip-5387 [000] ...1 573713: mlx5_esw_bridge_vport_cleanup: vport_num=1 - -Eswitch QoS tracepoints: - -- mlx5_esw_vport_qos_create: trace creation of transmit scheduler arbiter for vport:: - - $ echo mlx5:mlx5_esw_vport_qos_create >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - <...>-23496 [018] .... 73136.838831: mlx5_esw_vport_qos_create: (0000:82:00.0) vport=2 tsar_ix=4 bw_share=0, max_rate=0 group=000000007b576bb3 - -- mlx5_esw_vport_qos_config: trace configuration of transmit scheduler arbiter for vport:: - - $ echo mlx5:mlx5_esw_vport_qos_config >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - <...>-26548 [023] .... 75754.223823: mlx5_esw_vport_qos_config: (0000:82:00.0) vport=1 tsar_ix=3 bw_share=34, max_rate=10000 group=000000007b576bb3 - -- mlx5_esw_vport_qos_destroy: trace deletion of transmit scheduler arbiter for vport:: - - $ echo mlx5:mlx5_esw_vport_qos_destroy >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - <...>-27418 [004] .... 76546.680901: mlx5_esw_vport_qos_destroy: (0000:82:00.0) vport=1 tsar_ix=3 - -- mlx5_esw_group_qos_create: trace creation of transmit scheduler arbiter for rate group:: - - $ echo mlx5:mlx5_esw_group_qos_create >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - <...>-26578 [008] .... 75776.022112: mlx5_esw_group_qos_create: (0000:82:00.0) group=000000008dac63ea tsar_ix=5 - -- mlx5_esw_group_qos_config: trace configuration of transmit scheduler arbiter for rate group:: - - $ echo mlx5:mlx5_esw_group_qos_config >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - <...>-27303 [020] .... 76461.455356: mlx5_esw_group_qos_config: (0000:82:00.0) group=000000008dac63ea tsar_ix=5 bw_share=100 max_rate=20000 - -- mlx5_esw_group_qos_destroy: trace deletion of transmit scheduler arbiter for group:: - - $ echo mlx5:mlx5_esw_group_qos_destroy >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - <...>-27418 [006] .... 76547.187258: mlx5_esw_group_qos_destroy: (0000:82:00.0) group=000000007b576bb3 tsar_ix=1 - -SF tracepoints: - -- mlx5_sf_add: trace addition of the SF port:: - - $ echo mlx5:mlx5_sf_add >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - devlink-9363 [031] ..... 24610.188722: mlx5_sf_add: (0000:06:00.0) port_index=32768 controller=0 hw_id=0x8000 sfnum=88 - -- mlx5_sf_free: trace freeing of the SF port:: - - $ echo mlx5:mlx5_sf_free >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - devlink-9830 [038] ..... 26300.404749: mlx5_sf_free: (0000:06:00.0) port_index=32768 controller=0 hw_id=0x8000 - -- mlx5_sf_hwc_alloc: trace allocating of the hardware SF context:: - - $ echo mlx5:mlx5_sf_hwc_alloc >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - devlink-9775 [031] ..... 26296.385259: mlx5_sf_hwc_alloc: (0000:06:00.0) controller=0 hw_id=0x8000 sfnum=88 - -- mlx5_sf_hwc_free: trace freeing of the hardware SF context:: - - $ echo mlx5:mlx5_sf_hwc_free >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - kworker/u128:3-9093 [046] ..... 24625.365771: mlx5_sf_hwc_free: (0000:06:00.0) hw_id=0x8000 - -- mlx5_sf_hwc_deferred_free : trace deferred freeing of the hardware SF context:: - - $ echo mlx5:mlx5_sf_hwc_deferred_free >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - devlink-9519 [046] ..... 24624.400271: mlx5_sf_hwc_deferred_free: (0000:06:00.0) hw_id=0x8000 - -- mlx5_sf_vhca_event: trace SF vhca event and state:: - - $ echo mlx5:mlx5_sf_vhca_event >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - kworker/u128:3-9093 [046] ..... 24625.365525: mlx5_sf_vhca_event: (0000:06:00.0) hw_id=0x8000 sfnum=88 vhca_state=1 - -- mlx5_sf_dev_add : trace SF device add event:: - - $ echo mlx5:mlx5_sf_dev_add>> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - kworker/u128:3-9093 [000] ..... 24616.524495: mlx5_sf_dev_add: (0000:06:00.0) sfdev=00000000fc5d96fd aux_id=4 hw_id=0x8000 sfnum=88 - -- mlx5_sf_dev_del : trace SF device delete event:: - - $ echo mlx5:mlx5_sf_dev_del >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - kworker/u128:3-9093 [044] ..... 24624.400749: mlx5_sf_dev_del: (0000:06:00.0) sfdev=00000000fc5d96fd aux_id=4 hw_id=0x8000 sfnum=88 diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst new file mode 100644 index 000000000000..4cd8e869762b --- /dev/null +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst @@ -0,0 +1,1302 @@ +.. SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +.. include:: <isonum.txt> + +================ +Ethtool counters +================ + +:Copyright: |copy| 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +Contents +======== + +- `Overview`_ +- `Groups`_ +- `Types`_ +- `Descriptions`_ + +Overview +======== + +There are several counter groups based on where the counter is being counted. In +addition, each group of counters may have different counter types. + +These counter groups are based on which component in a networking setup, +illustrated below, that they describe:: + + ---------------------------------------- + | | + ---------------------------------------- ---------------------------------------- | + | Hypervisor | | VM | | + | | | | | + | ------------------- --------------- | | ------------------- --------------- | | + | | Ethernet driver | | RDMA driver | | | | Ethernet driver | | RDMA driver | | | + | ------------------- --------------- | | ------------------- --------------- | | + | | | | | | | | | + | ------------------- | | ------------------- | | + | | | | | |-- + ---------------------------------------- ---------------------------------------- + | | + ------------- ----------------------------- + | | + ------ ------ ------ ------ ------ ------ ------ + -----| PF |----------------------| VF |-| VF |-| VF |----- --| PF |--- --| PF |--- --| PF |--- + | ------ ------ ------ ------ | | ------ | | ------ | | ------ | + | | | | | | | | + | | | | | | | | + | | | | | | | | + | eSwitch | | eSwitch | | eSwitch | | eSwitch | + ---------------------------------------------------------- ----------- ----------- ----------- + ------------------------------------------------------------------------------- + | | + | | + | Uplink (no counters) | + ------------------------------------------------------------------------------- + --------------------------------------------------------------- + | | + | | + | MPFS (no counters) | + --------------------------------------------------------------- + | + | + | Port + +Groups +====== + +Ring + Software counters populated by the driver stack. + +Netdev + An aggregation of software ring counters. + +vPort counters + Traffic counters and drops due to steering or no buffers. May indicate issues + with NIC. These counters include Ethernet traffic counters (including Raw + Ethernet) and RDMA/RoCE traffic counters. + +Physical port counters + Counters that collect statistics about the PFs and VFs. May indicate issues + with NIC, link, or network. This measuring point holds information on + standardized counters like IEEE 802.3, RFC2863, RFC 2819, RFC 3635 and + additional counters like flow control, FEC and more. Physical port counters + are not exposed to virtual machines. + +Priority Port Counters + A set of the physical port counters, per priority per port. + +Types +===== + +Counters are divided into three types. + +Traffic Informative Counters + Counters which count traffic. These counters can be used for load estimation + or for general debug. + +Traffic Acceleration Counters + Counters which count traffic that was accelerated by Mellanox driver or by + hardware. The counters are an additional layer to the informative counter set, + and the same traffic is counted in both informative and acceleration counters. + +.. [#accel] Traffic acceleration counter. + +Error Counters + Increment of these counters might indicate a problem. Each of these counters + has an explanation and correction action. + +Statistic can be fetched via the `ip link` or `ethtool` commands. `ethtool` +provides more detailed information.:: + + ip –s link show <if-name> + ethtool -S <if-name> + +Descriptions +============ + +XSK, PTP, and QoS counters that are similar to counters defined previously will +not be separately listed. For example, `ptp_tx[i]_packets` will not be +explicitly documented since `tx[i]_packets` describes the behavior of both +counters, except `ptp_tx[i]_packets` is only counted when precision time +protocol is used. + +Ring / Netdev Counter +---------------------------- +The following counters are available per ring or software port. + +These counters provide information on the amount of traffic that was accelerated +by the NIC. The counters are counting the accelerated traffic in addition to the +standard counters which counts it (i.e. accelerated traffic is counted twice). + +The counter names in the table below refers to both ring and port counters. The +notation for ring counters includes the [i] index without the braces. The +notation for port counters doesn't include the [i]. A counter name +`rx[i]_packets` will be printed as `rx0_packets` for ring 0 and `rx_packets` for +the software port. + +.. flat-table:: Ring / Software Port Counter Table + :widths: 2 3 1 + + * - Counter + - Description + - Type + + * - `rx[i]_packets` + - The number of packets received on ring i. + - Informative + + * - `rx[i]_bytes` + - The number of bytes received on ring i. + - Informative + + * - `tx[i]_packets` + - The number of packets transmitted on ring i. + - Informative + + * - `tx[i]_bytes` + - The number of bytes transmitted on ring i. + - Informative + + * - `tx[i]_recover` + - The number of times the SQ was recovered. + - Error + + * - `tx[i]_cqes` + - Number of CQEs events on SQ issued on ring i. + - Informative + + * - `tx[i]_cqe_err` + - The number of error CQEs encountered on the SQ for ring i. + - Error + + * - `tx[i]_tso_packets` + - The number of TSO packets transmitted on ring i [#accel]_. + - Acceleration + + * - `tx[i]_tso_bytes` + - The number of TSO bytes transmitted on ring i [#accel]_. + - Acceleration + + * - `tx[i]_tso_inner_packets` + - The number of TSO packets which are indicated to be carry internal + encapsulation transmitted on ring i [#accel]_. + - Acceleration + + * - `tx[i]_tso_inner_bytes` + - The number of TSO bytes which are indicated to be carry internal + encapsulation transmitted on ring i [#accel]_. + - Acceleration + + * - `rx[i]_gro_packets` + - Number of received packets processed using hardware-accelerated GRO. The + number of hardware GRO offloaded packets received on ring i. + - Acceleration + + * - `rx[i]_gro_bytes` + - Number of received bytes processed using hardware-accelerated GRO. The + number of hardware GRO offloaded bytes received on ring i. + - Acceleration + + * - `rx[i]_gro_skbs` + - The number of receive SKBs constructed while performing + hardware-accelerated GRO. + - Informative + + * - `rx[i]_gro_match_packets` + - Number of received packets processed using hardware-accelerated GRO that + met the flow table match criteria. + - Informative + + * - `rx[i]_gro_large_hds` + - Number of receive packets using hardware-accelerated GRO that have large + headers that require additional memory to be allocated. + - Informative + + * - `rx[i]_lro_packets` + - The number of LRO packets received on ring i [#accel]_. + - Acceleration + + * - `rx[i]_lro_bytes` + - The number of LRO bytes received on ring i [#accel]_. + - Acceleration + + * - `rx[i]_ecn_mark` + - The number of received packets where the ECN mark was turned on. + - Informative + + * - `rx_oversize_pkts_buffer` + - The number of dropped received packets due to length which arrived to RQ + and exceed software buffer size allocated by the device for incoming + traffic. It might imply that the device MTU is larger than the software + buffers size. + - Error + + * - `rx_oversize_pkts_sw_drop` + - Number of received packets dropped in software because the CQE data is + larger than the MTU size. + - Error + + * - `rx[i]_csum_unnecessary` + - Packets received with a `CHECKSUM_UNNECESSARY` on ring i [#accel]_. + - Acceleration + + * - `rx[i]_csum_unnecessary_inner` + - Packets received with inner encapsulation with a `CHECKSUM_UNNECESSARY` + on ring i [#accel]_. + - Acceleration + + * - `rx[i]_csum_none` + - Packets received with a `CHECKSUM_NONE` on ring i [#accel]_. + - Acceleration + + * - `rx[i]_csum_complete` + - Packets received with a `CHECKSUM_COMPLETE` on ring i [#accel]_. + - Acceleration + + * - `rx[i]_csum_complete_tail` + - Number of received packets that had checksum calculation computed, + potentially needed padding, and were able to do so with + `CHECKSUM_PARTIAL`. + - Informative + + * - `rx[i]_csum_complete_tail_slow` + - Number of received packets that need padding larger than eight bytes for + the checksum. + - Informative + + * - `tx[i]_csum_partial` + - Packets transmitted with a `CHECKSUM_PARTIAL` on ring i [#accel]_. + - Acceleration + + * - `tx[i]_csum_partial_inner` + - Packets transmitted with inner encapsulation with a `CHECKSUM_PARTIAL` on + ring i [#accel]_. + - Acceleration + + * - `tx[i]_csum_none` + - Packets transmitted with no hardware checksum acceleration on ring i. + - Informative + + * - `tx[i]_stopped` / `tx_queue_stopped` [#ring_global]_ + - Events where SQ was full on ring i. If this counter is increased, check + the amount of buffers allocated for transmission. + - Informative + + * - `tx[i]_wake` / `tx_queue_wake` [#ring_global]_ + - Events where SQ was full and has become not full on ring i. + - Informative + + * - `tx[i]_dropped` / `tx_queue_dropped` [#ring_global]_ + - Packets transmitted that were dropped due to DMA mapping failure on + ring i. If this counter is increased, check the amount of buffers + allocated for transmission. + - Error + + * - `tx[i]_nop` + - The number of nop WQEs (empty WQEs) inserted to the SQ (related to + ring i) due to the reach of the end of the cyclic buffer. When reaching + near to the end of cyclic buffer the driver may add those empty WQEs to + avoid handling a state the a WQE start in the end of the queue and ends + in the beginning of the queue. This is a normal condition. + - Informative + + * - `tx[i]_added_vlan_packets` + - The number of packets sent where vlan tag insertion was offloaded to the + hardware. + - Acceleration + + * - `rx[i]_removed_vlan_packets` + - The number of packets received where vlan tag stripping was offloaded to + the hardware. + - Acceleration + + * - `rx[i]_wqe_err` + - The number of wrong opcodes received on ring i. + - Error + + * - `rx[i]_mpwqe_frag` + - The number of WQEs that failed to allocate compound page and hence + fragmented MPWQE’s (Multi Packet WQEs) were used on ring i. If this + counter raise, it may suggest that there is no enough memory for large + pages, the driver allocated fragmented pages. This is not abnormal + condition. + - Informative + + * - `rx[i]_mpwqe_filler_cqes` + - The number of filler CQEs events that were issued on ring i. + - Informative + + * - `rx[i]_mpwqe_filler_strides` + - The number of strides consumed by filler CQEs on ring i. + - Informative + + * - `tx[i]_mpwqe_blks` + - The number of send blocks processed from Multi-Packet WQEs (mpwqe). + - Informative + + * - `tx[i]_mpwqe_pkts` + - The number of send packets processed from Multi-Packet WQEs (mpwqe). + - Informative + + * - `rx[i]_cqe_compress_blks` + - The number of receive blocks with CQE compression on ring i [#accel]_. + - Acceleration + + * - `rx[i]_cqe_compress_pkts` + - The number of receive packets with CQE compression on ring i [#accel]_. + - Acceleration + + * - `rx[i]_cache_reuse` + - The number of events of successful reuse of a page from a driver's + internal page cache. + - Acceleration + + * - `rx[i]_cache_full` + - The number of events of full internal page cache where driver can't put a + page back to the cache for recycling (page will be freed). + - Acceleration + + * - `rx[i]_cache_empty` + - The number of events where cache was empty - no page to give. Driver + shall allocate new page. + - Acceleration + + * - `rx[i]_cache_busy` + - The number of events where cache head was busy and cannot be recycled. + Driver allocated new page. + - Acceleration + + * - `rx[i]_cache_waive` + - The number of cache evacuation. This can occur due to page move to + another NUMA node or page was pfmemalloc-ed and should be freed as soon + as possible. + - Acceleration + + * - `rx[i]_arfs_err` + - Number of flow rules that failed to be added to the flow table. + - Error + + * - `rx[i]_recover` + - The number of times the RQ was recovered. + - Error + + * - `tx[i]_xmit_more` + - The number of packets sent with `xmit_more` indication set on the skbuff + (no doorbell). + - Acceleration + + * - `ch[i]_poll` + - The number of invocations of NAPI poll of channel i. + - Informative + + * - `ch[i]_arm` + - The number of times the NAPI poll function completed and armed the + completion queues on channel i. + - Informative + + * - `ch[i]_aff_change` + - The number of times the NAPI poll function explicitly stopped execution + on a CPU due to a change in affinity, on channel i. + - Informative + + * - `ch[i]_events` + - The number of hard interrupt events on the completion queues of channel i. + - Informative + + * - `ch[i]_eq_rearm` + - The number of times the EQ was recovered. + - Error + + * - `ch[i]_force_irq` + - Number of times NAPI is triggered by XSK wakeups by posting a NOP to + ICOSQ. + - Acceleration + + * - `rx[i]_congst_umr` + - The number of times an outstanding UMR request is delayed due to + congestion, on ring i. + - Informative + + * - `rx_pp_alloc_fast` + - Number of successful fast path allocations. + - Informative + + * - `rx_pp_alloc_slow` + - Number of slow path order-0 allocations. + - Informative + + * - `rx_pp_alloc_slow_high_order` + - Number of slow path high order allocations. + - Informative + + * - `rx_pp_alloc_empty` + - Counter is incremented when ptr ring is empty, so a slow path allocation + was forced. + - Informative + + * - `rx_pp_alloc_refill` + - Counter is incremented when an allocation which triggered a refill of the + cache. + - Informative + + * - `rx_pp_alloc_waive` + - Counter is incremented when pages obtained from the ptr ring that cannot + be added to the cache due to a NUMA mismatch. + - Informative + + * - `rx_pp_recycle_cached` + - Counter is incremented when recycling placed page in the page pool cache. + - Informative + + * - `rx_pp_recycle_cache_full` + - Counter is incremented when page pool cache was full. + - Informative + + * - `rx_pp_recycle_ring` + - Counter is incremented when page placed into the ptr ring. + - Informative + + * - `rx_pp_recycle_ring_full` + - Counter is incremented when page released from page pool because the ptr + ring was full. + - Informative + + * - `rx_pp_recycle_released_ref` + - Counter is incremented when page released (and not recycled) because + refcnt > 1. + - Informative + + * - `rx[i]_xsk_buff_alloc_err` + - The number of times allocating an skb or XSK buffer failed in the XSK RQ + context. + - Error + + * - `rx[i]_xsk_arfs_err` + - aRFS (accelerated Receive Flow Steering) does not occur in the XSK RQ + context, so this counter should never increment. + - Error + + * - `rx[i]_xdp_tx_xmit` + - The number of packets forwarded back to the port due to XDP program + `XDP_TX` action (bouncing). these packets are not counted by other + software counters. These packets are counted by physical port and vPort + counters. + - Informative + + * - `rx[i]_xdp_tx_mpwqe` + - Number of multi-packet WQEs transmitted by the netdev and `XDP_TX`-ed by + the netdev during the RQ context. + - Acceleration + + * - `rx[i]_xdp_tx_inlnw` + - Number of WQE data segments transmitted where the data could be inlined + in the WQE and then `XDP_TX`-ed during the RQ context. + - Acceleration + + * - `rx[i]_xdp_tx_nops` + - Number of NOP WQEBBs (WQE building blocks) received posted to the XDP SQ. + - Acceleration + + * - `rx[i]_xdp_tx_full` + - The number of packets that should have been forwarded back to the port + due to `XDP_TX` action but were dropped due to full tx queue. These packets + are not counted by other software counters. These packets are counted by + physical port and vPort counters. You may open more rx queues and spread + traffic rx over all queues and/or increase rx ring size. + - Error + + * - `rx[i]_xdp_tx_err` + - The number of times an `XDP_TX` error such as frame too long and frame + too short occurred on `XDP_TX` ring of RX ring. + - Error + + * - `rx[i]_xdp_tx_cqes` / `rx_xdp_tx_cqe` [#ring_global]_ + - The number of completions received on the CQ of the `XDP_TX` ring. + - Informative + + * - `rx[i]_xdp_drop` + - The number of packets dropped due to XDP program `XDP_DROP` action. these + packets are not counted by other software counters. These packets are + counted by physical port and vPort counters. + - Informative + + * - `rx[i]_xdp_redirect` + - The number of times an XDP redirect action was triggered on ring i. + - Acceleration + + * - `tx[i]_xdp_xmit` + - The number of packets redirected to the interface(due to XDP redirect). + These packets are not counted by other software counters. These packets + are counted by physical port and vPort counters. + - Informative + + * - `tx[i]_xdp_full` + - The number of packets redirected to the interface(due to XDP redirect), + but were dropped due to full tx queue. these packets are not counted by + other software counters. you may enlarge tx queues. + - Informative + + * - `tx[i]_xdp_mpwqe` + - Number of multi-packet WQEs offloaded onto the NIC that were + `XDP_REDIRECT`-ed from other netdevs. + - Acceleration + + * - `tx[i]_xdp_inlnw` + - Number of WQE data segments where the data could be inlined in the WQE + where the data segments were `XDP_REDIRECT`-ed from other netdevs. + - Acceleration + + * - `tx[i]_xdp_nops` + - Number of NOP WQEBBs (WQE building blocks) posted to the SQ that were + `XDP_REDIRECT`-ed from other netdevs. + - Acceleration + + * - `tx[i]_xdp_err` + - The number of packets redirected to the interface(due to XDP redirect) + but were dropped due to error such as frame too long and frame too short. + - Error + + * - `tx[i]_xdp_cqes` + - The number of completions received for packets redirected to the + interface(due to XDP redirect) on the CQ. + - Informative + + * - `tx[i]_xsk_xmit` + - The number of packets transmitted using XSK zerocopy functionality. + - Acceleration + + * - `tx[i]_xsk_mpwqe` + - Number of multi-packet WQEs offloaded onto the NIC that were + `XDP_REDIRECT`-ed from other netdevs. + - Acceleration + + * - `tx[i]_xsk_inlnw` + - Number of WQE data segments where the data could be inlined in the WQE + that are transmitted using XSK zerocopy. + - Acceleration + + * - `tx[i]_xsk_full` + - Number of times doorbell is rung in XSK zerocopy mode when SQ is full. + - Error + + * - `tx[i]_xsk_err` + - Number of errors that occurred in XSK zerocopy mode such as if the data + size is larger than the MTU size. + - Error + + * - `tx[i]_xsk_cqes` + - Number of CQEs processed in XSK zerocopy mode. + - Acceleration + + * - `tx_tls_ctx` + - Number of TLS TX HW offload contexts added to device for encryption. + - Acceleration + + * - `tx_tls_del` + - Number of TLS TX HW offload contexts removed from device (connection + closed). + - Acceleration + + * - `tx_tls_pool_alloc` + - Number of times a unit of work is successfully allocated in the TLS HW + offload pool. + - Acceleration + + * - `tx_tls_pool_free` + - Number of times a unit of work is freed in the TLS HW offload pool. + - Acceleration + + * - `rx_tls_ctx` + - Number of TLS RX HW offload contexts added to device for decryption. + - Acceleration + + * - `rx_tls_del` + - Number of TLS RX HW offload contexts deleted from device (connection has + finished). + - Acceleration + + * - `rx[i]_tls_decrypted_packets` + - Number of successfully decrypted RX packets which were part of a TLS + stream. + - Acceleration + + * - `rx[i]_tls_decrypted_bytes` + - Number of TLS payload bytes in RX packets which were successfully + decrypted. + - Acceleration + + * - `rx[i]_tls_resync_req_pkt` + - Number of received TLS packets with a resync request. + - Acceleration + + * - `rx[i]_tls_resync_req_start` + - Number of times the TLS async resync request was started. + - Acceleration + + * - `rx[i]_tls_resync_req_end` + - Number of times the TLS async resync request properly ended with + providing the HW tracked tcp-seq. + - Acceleration + + * - `rx[i]_tls_resync_req_skip` + - Number of times the TLS async resync request procedure was started but + not properly ended. + - Error + + * - `rx[i]_tls_resync_res_ok` + - Number of times the TLS resync response call to the driver was + successfully handled. + - Acceleration + + * - `rx[i]_tls_resync_res_retry` + - Number of times the TLS resync response call to the driver was + reattempted when ICOSQ is full. + - Error + + * - `rx[i]_tls_resync_res_skip` + - Number of times the TLS resync response call to the driver was terminated + unsuccessfully. + - Error + + * - `rx[i]_tls_err` + - Number of times when CQE TLS offload was problematic. + - Error + + * - `tx[i]_tls_encrypted_packets` + - The number of send packets that are TLS encrypted by the kernel. + - Acceleration + + * - `tx[i]_tls_encrypted_bytes` + - The number of send bytes that are TLS encrypted by the kernel. + - Acceleration + + * - `tx[i]_tls_ooo` + - Number of times out of order TLS SQE fragments were handled on ring i. + - Acceleration + + * - `tx[i]_tls_dump_packets` + - Number of TLS decrypted packets copied over from NIC over DMA. + - Acceleration + + * - `tx[i]_tls_dump_bytes` + - Number of TLS decrypted bytes copied over from NIC over DMA. + - Acceleration + + * - `tx[i]_tls_resync_bytes` + - Number of TLS bytes requested to be resynchronized in order to be + decrypted. + - Acceleration + + * - `tx[i]_tls_skip_no_sync_data` + - Number of TLS send data that can safely be skipped / do not need to be + decrypted. + - Acceleration + + * - `tx[i]_tls_drop_no_sync_data` + - Number of TLS send data that were dropped due to retransmission of TLS + data. + - Acceleration + + * - `ptp_cq[i]_abort` + - Number of times a CQE has to be skipped in precision time protocol due to + a skew between the port timestamp and CQE timestamp being greater than + 128 seconds. + - Error + + * - `ptp_cq[i]_abort_abs_diff_ns` + - Accumulation of time differences between the port timestamp and CQE + timestamp when the difference is greater than 128 seconds in precision + time protocol. + - Error + +.. [#ring_global] The corresponding ring and global counters do not share the + same name (i.e. do not follow the common naming scheme). + +vPort Counters +-------------- +Counters on the NIC port that is connected to a eSwitch. + +.. flat-table:: vPort Counter Table + :widths: 2 3 1 + + * - Counter + - Description + - Type + + * - `rx_vport_unicast_packets` + - Unicast packets received, steered to a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `rx_vport_unicast_bytes` + - Unicast bytes received, steered to a port including Raw Ethernet QP/DPDK + traffic, excluding RDMA traffic. + - Informative + + * - `tx_vport_unicast_packets` + - Unicast packets transmitted, steered from a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `tx_vport_unicast_bytes` + - Unicast bytes transmitted, steered from a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `rx_vport_multicast_packets` + - Multicast packets received, steered to a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `rx_vport_multicast_bytes` + - Multicast bytes received, steered to a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `tx_vport_multicast_packets` + - Multicast packets transmitted, steered from a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `tx_vport_multicast_bytes` + - Multicast bytes transmitted, steered from a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `rx_vport_broadcast_packets` + - Broadcast packets received, steered to a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `rx_vport_broadcast_bytes` + - Broadcast bytes received, steered to a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `tx_vport_broadcast_packets` + - Broadcast packets transmitted, steered from a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `tx_vport_broadcast_bytes` + - Broadcast bytes transmitted, steered from a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `rx_vport_rdma_unicast_packets` + - RDMA unicast packets received, steered to a port (counters counts + RoCE/UD/RC traffic) [#accel]_. + - Acceleration + + * - `rx_vport_rdma_unicast_bytes` + - RDMA unicast bytes received, steered to a port (counters counts + RoCE/UD/RC traffic) [#accel]_. + - Acceleration + + * - `tx_vport_rdma_unicast_packets` + - RDMA unicast packets transmitted, steered from a port (counters counts + RoCE/UD/RC traffic) [#accel]_. + - Acceleration + + * - `tx_vport_rdma_unicast_bytes` + - RDMA unicast bytes transmitted, steered from a port (counters counts + RoCE/UD/RC traffic) [#accel]_. + - Acceleration + + * - `rx_vport_rdma_multicast_packets` + - RDMA multicast packets received, steered to a port (counters counts + RoCE/UD/RC traffic) [#accel]_. + - Acceleration + + * - `rx_vport_rdma_multicast_bytes` + - RDMA multicast bytes received, steered to a port (counters counts + RoCE/UD/RC traffic) [#accel]_. + - Acceleration + + * - `tx_vport_rdma_multicast_packets` + - RDMA multicast packets transmitted, steered from a port (counters counts + RoCE/UD/RC traffic) [#accel]_. + - Acceleration + + * - `tx_vport_rdma_multicast_bytes` + - RDMA multicast bytes transmitted, steered from a port (counters counts + RoCE/UD/RC traffic) [#accel]_. + - Acceleration + + * - `rx_steer_missed_packets` + - Number of packets that was received by the NIC, however was discarded + because it did not match any flow in the NIC flow table. + - Error + + * - `rx_packets` + - Representor only: packets received, that were handled by the hypervisor. + - Informative + + * - `rx_bytes` + - Representor only: bytes received, that were handled by the hypervisor. + - Informative + + * - `tx_packets` + - Representor only: packets transmitted, that were handled by the + hypervisor. + - Informative + + * - `tx_bytes` + - Representor only: bytes transmitted, that were handled by the hypervisor. + - Informative + + * - `dev_internal_queue_oob` + - The number of dropped packets due to lack of receive WQEs for an internal + device RQ. + - Error + +Physical Port Counters +---------------------- +The physical port counters are the counters on the external port connecting the +adapter to the network. This measuring point holds information on standardized +counters like IEEE 802.3, RFC2863, RFC 2819, RFC 3635 and additional counters +like flow control, FEC and more. + +.. flat-table:: Physical Port Counter Table + :widths: 2 3 1 + + * - Counter + - Description + - Type + + * - `rx_packets_phy` + - The number of packets received on the physical port. This counter doesn’t + include packets that were discarded due to FCS, frame size and similar + errors. + - Informative + + * - `tx_packets_phy` + - The number of packets transmitted on the physical port. + - Informative + + * - `rx_bytes_phy` + - The number of bytes received on the physical port, including Ethernet + header and FCS. + - Informative + + * - `tx_bytes_phy` + - The number of bytes transmitted on the physical port. + - Informative + + * - `rx_multicast_phy` + - The number of multicast packets received on the physical port. + - Informative + + * - `tx_multicast_phy` + - The number of multicast packets transmitted on the physical port. + - Informative + + * - `rx_broadcast_phy` + - The number of broadcast packets received on the physical port. + - Informative + + * - `tx_broadcast_phy` + - The number of broadcast packets transmitted on the physical port. + - Informative + + * - `rx_crc_errors_phy` + - The number of dropped received packets due to FCS (Frame Check Sequence) + error on the physical port. If this counter is increased in high rate, + check the link quality using `rx_symbol_error_phy` and + `rx_corrected_bits_phy` counters below. + - Error + + * - `rx_in_range_len_errors_phy` + - The number of received packets dropped due to length/type errors on a + physical port. + - Error + + * - `rx_out_of_range_len_phy` + - The number of received packets dropped due to length greater than allowed + on a physical port. If this counter is increasing, it implies that the + peer connected to the adapter has a larger MTU configured. Using same MTU + configuration shall resolve this issue. + - Error + + * - `rx_oversize_pkts_phy` + - The number of dropped received packets due to length which exceed MTU + size on a physical port. If this counter is increasing, it implies that + the peer connected to the adapter has a larger MTU configured. Using same + MTU configuration shall resolve this issue. + - Error + + * - `rx_symbol_err_phy` + - The number of received packets dropped due to physical coding errors + (symbol errors) on a physical port. + - Error + + * - `rx_mac_control_phy` + - The number of MAC control packets received on the physical port. + - Informative + + * - `tx_mac_control_phy` + - The number of MAC control packets transmitted on the physical port. + - Informative + + * - `rx_pause_ctrl_phy` + - The number of link layer pause packets received on a physical port. If + this counter is increasing, it implies that the network is congested and + cannot absorb the traffic coming from to the adapter. + - Informative + + * - `tx_pause_ctrl_phy` + - The number of link layer pause packets transmitted on a physical port. If + this counter is increasing, it implies that the NIC is congested and + cannot absorb the traffic coming from the network. + - Informative + + * - `rx_unsupported_op_phy` + - The number of MAC control packets received with unsupported opcode on a + physical port. + - Error + + * - `rx_discards_phy` + - The number of received packets dropped due to lack of buffers on a + physical port. If this counter is increasing, it implies that the adapter + is congested and cannot absorb the traffic coming from the network. + - Error + + * - `tx_discards_phy` + - The number of packets which were discarded on transmission, even no + errors were detected. the drop might occur due to link in down state, + head of line drop, pause from the network, etc. + - Error + + * - `tx_errors_phy` + - The number of transmitted packets dropped due to a length which exceed + MTU size on a physical port. + - Error + + * - `rx_undersize_pkts_phy` + - The number of received packets dropped due to length which is shorter + than 64 bytes on a physical port. If this counter is increasing, it + implies that the peer connected to the adapter has a non-standard MTU + configured or malformed packet had arrived. + - Error + + * - `rx_fragments_phy` + - The number of received packets dropped due to a length which is shorter + than 64 bytes and has FCS error on a physical port. If this counter is + increasing, it implies that the peer connected to the adapter has a + non-standard MTU configured. + - Error + + * - `rx_jabbers_phy` + - The number of received packets d due to a length which is longer than 64 + bytes and had FCS error on a physical port. + - Error + + * - `rx_64_bytes_phy` + - The number of packets received on the physical port with size of 64 bytes. + - Informative + + * - `rx_65_to_127_bytes_phy` + - The number of packets received on the physical port with size of 65 to + 127 bytes. + - Informative + + * - `rx_128_to_255_bytes_phy` + - The number of packets received on the physical port with size of 128 to + 255 bytes. + - Informative + + * - `rx_256_to_511_bytes_phy` + - The number of packets received on the physical port with size of 256 to + 512 bytes. + - Informative + + * - `rx_512_to_1023_bytes_phy` + - The number of packets received on the physical port with size of 512 to + 1023 bytes. + - Informative + + * - `rx_1024_to_1518_bytes_phy` + - The number of packets received on the physical port with size of 1024 to + 1518 bytes. + - Informative + + * - `rx_1519_to_2047_bytes_phy` + - The number of packets received on the physical port with size of 1519 to + 2047 bytes. + - Informative + + * - `rx_2048_to_4095_bytes_phy` + - The number of packets received on the physical port with size of 2048 to + 4095 bytes. + - Informative + + * - `rx_4096_to_8191_bytes_phy` + - The number of packets received on the physical port with size of 4096 to + 8191 bytes. + - Informative + + * - `rx_8192_to_10239_bytes_phy` + - The number of packets received on the physical port with size of 8192 to + 10239 bytes. + - Informative + + * - `link_down_events_phy` + - The number of times where the link operative state changed to down. In + case this counter is increasing it may imply on port flapping. You may + need to replace the cable/transceiver. + - Error + + * - `rx_out_of_buffer` + - Number of times receive queue had no software buffers allocated for the + adapter's incoming traffic. + - Error + + * - `module_bus_stuck` + - The number of times that module's I\ :sup:`2`\C bus (data or clock) + short-wire was detected. You may need to replace the cable/transceiver. + - Error + + * - `module_high_temp` + - The number of times that the module temperature was too high. If this + issue persist, you may need to check the ambient temperature or replace + the cable/transceiver module. + - Error + + * - `module_bad_shorted` + - The number of times that the module cables were shorted. You may need to + replace the cable/transceiver module. + - Error + + * - `module_unplug` + - The number of times that module was ejected. + - Informative + + * - `rx_buffer_passed_thres_phy` + - The number of events where the port receive buffer was over 85% full. + - Informative + + * - `tx_pause_storm_warning_events` + - The number of times the device was sending pauses for a long period of + time. + - Informative + + * - `tx_pause_storm_error_events` + - The number of times the device was sending pauses for a long period of + time, reaching time out and disabling transmission of pause frames. on + the period where pause frames were disabled, drop could have been + occurred. + - Error + + * - `rx[i]_buff_alloc_err` + - Failed to allocate a buffer to received packet (or SKB) on ring i. + - Error + + * - `rx_bits_phy` + - This counter provides information on the total amount of traffic that + could have been received and can be used as a guideline to measure the + ratio of errored traffic in `rx_pcs_symbol_err_phy` and + `rx_corrected_bits_phy`. + - Informative + + * - `rx_pcs_symbol_err_phy` + - This counter counts the number of symbol errors that wasn’t corrected by + FEC correction algorithm or that FEC algorithm was not active on this + interface. If this counter is increasing, it implies that the link + between the NIC and the network is suffering from high BER, and that + traffic is lost. You may need to replace the cable/transceiver. The error + rate is the number of `rx_pcs_symbol_err_phy` divided by the number of + `rx_bits_phy` on a specific time frame. + - Error + + * - `rx_corrected_bits_phy` + - The number of corrected bits on this port according to active FEC + (RS/FC). If this counter is increasing, it implies that the link between + the NIC and the network is suffering from high BER. The corrected bit + rate is the number of `rx_corrected_bits_phy` divided by the number of + `rx_bits_phy` on a specific time frame. + - Error + + * - `rx_err_lane_[l]_phy` + - This counter counts the number of physical raw errors per lane l index. + The counter counts errors before FEC corrections. If this counter is + increasing, it implies that the link between the NIC and the network is + suffering from high BER, and that traffic might be lost. You may need to + replace the cable/transceiver. Please check in accordance with + `rx_corrected_bits_phy`. + - Error + + * - `rx_global_pause` + - The number of pause packets received on the physical port. If this + counter is increasing, it implies that the network is congested and + cannot absorb the traffic coming from the adapter. Note: This counter is + only enabled when global pause mode is enabled. + - Informative + + * - `rx_global_pause_duration` + - The duration of pause received (in microSec) on the physical port. The + counter represents the time the port did not send any traffic. If this + counter is increasing, it implies that the network is congested and + cannot absorb the traffic coming from the adapter. Note: This counter is + only enabled when global pause mode is enabled. + - Informative + + * - `tx_global_pause` + - The number of pause packets transmitted on a physical port. If this + counter is increasing, it implies that the adapter is congested and + cannot absorb the traffic coming from the network. Note: This counter is + only enabled when global pause mode is enabled. + - Informative + + * - `tx_global_pause_duration` + - The duration of pause transmitter (in microSec) on the physical port. + Note: This counter is only enabled when global pause mode is enabled. + - Informative + + * - `rx_global_pause_transition` + - The number of times a transition from Xoff to Xon on the physical port + has occurred. Note: This counter is only enabled when global pause mode + is enabled. + - Informative + + * - `rx_if_down_packets` + - The number of received packets that were dropped due to interface down. + - Informative + +Priority Port Counters +---------------------- +The following counters are physical port counters that are counted per L2 +priority (0-7). + +**Note:** `p` in the counter name represents the priority. + +.. flat-table:: Priority Port Counter Table + :widths: 2 3 1 + + * - Counter + - Description + - Type + + * - `rx_prio[p]_bytes` + - The number of bytes received with priority p on the physical port. + - Informative + + * - `rx_prio[p]_packets` + - The number of packets received with priority p on the physical port. + - Informative + + * - `tx_prio[p]_bytes` + - The number of bytes transmitted on priority p on the physical port. + - Informative + + * - `tx_prio[p]_packets` + - The number of packets transmitted on priority p on the physical port. + - Informative + + * - `rx_prio[p]_pause` + - The number of pause packets received with priority p on a physical port. + If this counter is increasing, it implies that the network is congested + and cannot absorb the traffic coming from the adapter. Note: This counter + is available only if PFC was enabled on priority p. + - Informative + + * - `rx_prio[p]_pause_duration` + - The duration of pause received (in microSec) on priority p on the + physical port. The counter represents the time the port did not send any + traffic on this priority. If this counter is increasing, it implies that + the network is congested and cannot absorb the traffic coming from the + adapter. Note: This counter is available only if PFC was enabled on + priority p. + - Informative + + * - `rx_prio[p]_pause_transition` + - The number of times a transition from Xoff to Xon on priority p on the + physical port has occurred. Note: This counter is available only if PFC + was enabled on priority p. + - Informative + + * - `tx_prio[p]_pause` + - The number of pause packets transmitted on priority p on a physical port. + If this counter is increasing, it implies that the adapter is congested + and cannot absorb the traffic coming from the network. Note: This counter + is available only if PFC was enabled on priority p. + - Informative + + * - `tx_prio[p]_pause_duration` + - The duration of pause transmitter (in microSec) on priority p on the + physical port. Note: This counter is available only if PFC was enabled on + priority p. + - Informative + + * - `rx_prio[p]_buf_discard` + - The number of packets discarded by device due to lack of per host receive + buffers. + - Informative + + * - `rx_prio[p]_cong_discard` + - The number of packets discarded by device due to per host congestion. + - Informative + + * - `rx_prio[p]_marked` + - The number of packets ecn marked by device due to per host congestion. + - Informative + + * - `rx_prio[p]_discards` + - The number of packets discarded by device due to lack of receive buffers. + - Informative + +Device Counters +--------------- +.. flat-table:: Device Counter Table + :widths: 2 3 1 + + * - Counter + - Description + - Type + + * - `rx_pci_signal_integrity` + - Counts physical layer PCIe signal integrity errors, the number of + transitions to recovery due to Framing errors and CRC (dlp and tlp). If + this counter is raising, try moving the adapter card to a different slot + to rule out a bad PCI slot. Validate that you are running with the latest + firmware available and latest server BIOS version. + - Error + + * - `tx_pci_signal_integrity` + - Counts physical layer PCIe signal integrity errors, the number of + transition to recovery initiated by the other side (moving to recovery + due to getting TS/EIEOS). If this counter is raising, try moving the + adapter card to a different slot to rule out a bad PCI slot. Validate + that you are running with the latest firmware available and latest server + BIOS version. + - Error + + * - `outbound_pci_buffer_overflow` + - The number of packets dropped due to pci buffer overflow. If this counter + is raising in high rate, it might indicate that the receive traffic rate + for a host is larger than the PCIe bus and therefore a congestion occurs. + - Informative + + * - `outbound_pci_stalled_rd` + - The percentage (in the range 0...100) of time within the last second that + the NIC had outbound non-posted reads requests but could not perform the + operation due to insufficient posted credits. + - Informative + + * - `outbound_pci_stalled_wr` + - The percentage (in the range 0...100) of time within the last second that + the NIC had outbound posted writes requests but could not perform the + operation due to insufficient posted credits. + - Informative + + * - `outbound_pci_stalled_rd_events` + - The number of seconds where `outbound_pci_stalled_rd` was above 30%. + - Informative + + * - `outbound_pci_stalled_wr_events` + - The number of seconds where `outbound_pci_stalled_wr` was above 30%. + - Informative + + * - `dev_out_of_buffer` + - The number of times the device owned queue had not enough buffers + allocated. + - Error diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst new file mode 100644 index 000000000000..9b5c40ba7f0d --- /dev/null +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst @@ -0,0 +1,224 @@ +.. SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +.. include:: <isonum.txt> + +======= +Devlink +======= + +:Copyright: |copy| 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +Contents +======== + +- `Info`_ +- `Parameters`_ +- `Health reporters`_ + +Info +==== + +The devlink info reports the running and stored firmware versions on device. +It also prints the device PSID which represents the HCA board type ID. + +User command example:: + + $ devlink dev info pci/0000:00:06.0 + pci/0000:00:06.0: + driver mlx5_core + versions: + fixed: + fw.psid MT_0000000009 + running: + fw.version 16.26.0100 + stored: + fw.version 16.26.0100 + +Parameters +========== + +flow_steering_mode: Device flow steering mode +--------------------------------------------- +The flow steering mode parameter controls the flow steering mode of the driver. +Two modes are supported: +1. 'dmfs' - Device managed flow steering. +2. 'smfs' - Software/Driver managed flow steering. + +In DMFS mode, the HW steering entities are created and managed through the +Firmware. +In SMFS mode, the HW steering entities are created and managed though by +the driver directly into hardware without firmware intervention. + +SMFS mode is faster and provides better rule insertion rate compared to default DMFS mode. + +User command examples: + +- Set SMFS flow steering mode:: + + $ devlink dev param set pci/0000:06:00.0 name flow_steering_mode value "smfs" cmode runtime + +- Read device flow steering mode:: + + $ devlink dev param show pci/0000:06:00.0 name flow_steering_mode + pci/0000:06:00.0: + name flow_steering_mode type driver-specific + values: + cmode runtime value smfs + +enable_roce: RoCE enablement state +---------------------------------- +If the device supports RoCE disablement, RoCE enablement state controls device +support for RoCE capability. Otherwise, the control occurs in the driver stack. +When RoCE is disabled at the driver level, only raw ethernet QPs are supported. + +To change RoCE enablement state, a user must change the driverinit cmode value +and run devlink reload. + +User command examples: + +- Disable RoCE:: + + $ devlink dev param set pci/0000:06:00.0 name enable_roce value false cmode driverinit + $ devlink dev reload pci/0000:06:00.0 + +- Read RoCE enablement state:: + + $ devlink dev param show pci/0000:06:00.0 name enable_roce + pci/0000:06:00.0: + name enable_roce type generic + values: + cmode driverinit value true + +esw_port_metadata: Eswitch port metadata state +---------------------------------------------- +When applicable, disabling eswitch metadata can increase packet rate +up to 20% depending on the use case and packet sizes. + +Eswitch port metadata state controls whether to internally tag packets with +metadata. Metadata tagging must be enabled for multi-port RoCE, failover +between representors and stacked devices. +By default metadata is enabled on the supported devices in E-switch. +Metadata is applicable only for E-switch in switchdev mode and +users may disable it when NONE of the below use cases will be in use: +1. HCA is in Dual/multi-port RoCE mode. +2. VF/SF representor bonding (Usually used for Live migration) +3. Stacked devices + +When metadata is disabled, the above use cases will fail to initialize if +users try to enable them. + +- Show eswitch port metadata:: + + $ devlink dev param show pci/0000:06:00.0 name esw_port_metadata + pci/0000:06:00.0: + name esw_port_metadata type driver-specific + values: + cmode runtime value true + +- Disable eswitch port metadata:: + + $ devlink dev param set pci/0000:06:00.0 name esw_port_metadata value false cmode runtime + +- Change eswitch mode to switchdev mode where after choosing the metadata value:: + + $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev + +Health reporters +================ + +tx reporter +----------- +The tx reporter is responsible for reporting and recovering of the following two error scenarios: + +- tx timeout + Report on kernel tx timeout detection. + Recover by searching lost interrupts. +- tx error completion + Report on error tx completion. + Recover by flushing the tx queue and reset it. + +tx reporter also support on demand diagnose callback, on which it provides +real time information of its send queues status. + +User commands examples: + +- Diagnose send queues status:: + + $ devlink health diagnose pci/0000:82:00.0 reporter tx + +NOTE: This command has valid output only when interface is up, otherwise the command has empty output. + +- Show number of tx errors indicated, number of recover flows ended successfully, + is autorecover enabled and graceful period from last recover:: + + $ devlink health show pci/0000:82:00.0 reporter tx + +rx reporter +----------- +The rx reporter is responsible for reporting and recovering of the following two error scenarios: + +- rx queues' initialization (population) timeout + Population of rx queues' descriptors on ring initialization is done + in napi context via triggering an irq. In case of a failure to get + the minimum amount of descriptors, a timeout would occur, and + descriptors could be recovered by polling the EQ (Event Queue). +- rx completions with errors (reported by HW on interrupt context) + Report on rx completion error. + Recover (if needed) by flushing the related queue and reset it. + +rx reporter also supports on demand diagnose callback, on which it +provides real time information of its receive queues' status. + +- Diagnose rx queues' status and corresponding completion queue:: + + $ devlink health diagnose pci/0000:82:00.0 reporter rx + +NOTE: This command has valid output only when interface is up. Otherwise, the command has empty output. + +- Show number of rx errors indicated, number of recover flows ended successfully, + is autorecover enabled, and graceful period from last recover:: + + $ devlink health show pci/0000:82:00.0 reporter rx + +fw reporter +----------- +The fw reporter implements `diagnose` and `dump` callbacks. +It follows symptoms of fw error such as fw syndrome by triggering +fw core dump and storing it into the dump buffer. +The fw reporter diagnose command can be triggered any time by the user to check +current fw status. + +User commands examples: + +- Check fw heath status:: + + $ devlink health diagnose pci/0000:82:00.0 reporter fw + +- Read FW core dump if already stored or trigger new one:: + + $ devlink health dump show pci/0000:82:00.0 reporter fw + +NOTE: This command can run only on the PF which has fw tracer ownership, +running it on other PF or any VF will return "Operation not permitted". + +fw fatal reporter +----------------- +The fw fatal reporter implements `dump` and `recover` callbacks. +It follows fatal errors indications by CR-space dump and recover flow. +The CR-space dump uses vsc interface which is valid even if the FW command +interface is not functional, which is the case in most FW fatal errors. +The recover function runs recover flow which reloads the driver and triggers fw +reset if needed. +On firmware error, the health buffer is dumped into the dmesg. The log +level is derived from the error's severity (given in health buffer). + +User commands examples: + +- Run fw recover flow manually:: + + $ devlink health recover pci/0000:82:00.0 reporter fw_fatal + +- Read FW CR-space dump if already stored or trigger new one:: + + $ devlink health dump show pci/0000:82:00.1 reporter fw_fatal + +NOTE: This command can run only on PF. diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/index.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/index.rst new file mode 100644 index 000000000000..3fdcd6b61ccf --- /dev/null +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/index.rst @@ -0,0 +1,26 @@ +.. SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +.. include:: <isonum.txt> + +Mellanox ConnectX(R) mlx5 core VPI Network Driver +================================================= + +:Copyright: |copy| 2019, Mellanox Technologies LTD. +:Copyright: |copy| 2020-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +Contents: + +.. toctree:: + :maxdepth: 2 + + kconfig + devlink + switchdev + tracepoints + counters + +.. only:: subproject and html + + Indices + ======= + + * :ref:`genindex` diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/kconfig.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/kconfig.rst new file mode 100644 index 000000000000..43b1f7e87ec4 --- /dev/null +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/kconfig.rst @@ -0,0 +1,168 @@ +.. SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +.. include:: <isonum.txt> + +======================================= +Enabling the driver and kconfig options +======================================= + +:Copyright: |copy| 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +| mlx5 core is modular and most of the major mlx5 core driver features can be selected (compiled in/out) +| at build time via kernel Kconfig flags. +| Basic features, ethernet net device rx/tx offloads and XDP, are available with the most basic flags +| CONFIG_MLX5_CORE=y/m and CONFIG_MLX5_CORE_EN=y. +| For the list of advanced features, please see below. + +**CONFIG_MLX5_BRIDGE=(y/n)** + +| Enable :ref:`Ethernet Bridging (BRIDGE) offloading support <mlx5_bridge_offload>`. +| This will provide the ability to add representors of mlx5 uplink and VF +| ports to Bridge and offloading rules for traffic between such ports. +| Supports VLANs (trunk and access modes). + + +**CONFIG_MLX5_CORE=(y/m/n)** (module mlx5_core.ko) + +| The driver can be enabled by choosing CONFIG_MLX5_CORE=y/m in kernel config. +| This will provide mlx5 core driver for mlx5 ulps to interface with (mlx5e, mlx5_ib). + + +**CONFIG_MLX5_CORE_EN=(y/n)** + +| Choosing this option will allow basic ethernet netdevice support with all of the standard rx/tx offloads. +| mlx5e is the mlx5 ulp driver which provides netdevice kernel interface, when chosen, mlx5e will be +| built-in into mlx5_core.ko. + + +**CONFIG_MLX5_CORE_EN_DCB=(y/n)**: + +| Enables `Data Center Bridging (DCB) Support <https://community.mellanox.com/s/article/howto-auto-config-pfc-and-ets-on-connectx-4-via-lldp-dcbx>`_. + + +**CONFIG_MLX5_CORE_IPOIB=(y/n)** + +| IPoIB offloads & acceleration support. +| Requires CONFIG_MLX5_CORE_EN to provide an accelerated interface for the rdma +| IPoIB ulp netdevice. + + +**CONFIG_MLX5_CLS_ACT=(y/n)** + +| Enables offload support for TC classifier action (NET_CLS_ACT). +| Works in both native NIC mode and Switchdev SRIOV mode. +| Flow-based classifiers, such as those registered through +| `tc-flower(8)`, are processed by the device, rather than the +| host. Actions that would then overwrite matching classification +| results would then be instant due to the offload. + + +**CONFIG_MLX5_EN_ARFS=(y/n)** + +| Enables Hardware-accelerated receive flow steering (arfs) support, and ntuple filtering. +| https://community.mellanox.com/s/article/howto-configure-arfs-on-connectx-4 + + +**CONFIG_MLX5_EN_IPSEC=(y/n)** + +| Enables `IPSec XFRM cryptography-offload acceleration <https://support.mellanox.com/s/article/ConnectX-6DX-Bluefield-2-IPsec-HW-Full-Offload-Configuration-Guide>`_. + + +**CONFIG_MLX5_EN_MACSEC=(y/n)** + +| Build support for MACsec cryptography-offload acceleration in the NIC. + + +**CONFIG_MLX5_EN_RXNFC=(y/n)** + +| Enables ethtool receive network flow classification, which allows user defined +| flow rules to direct traffic into arbitrary rx queue via ethtool set/get_rxnfc API. + + +**CONFIG_MLX5_EN_TLS=(y/n)** + +| TLS cryptography-offload acceleration. + + +**CONFIG_MLX5_ESWITCH=(y/n)** + +| Ethernet SRIOV E-Switch support in ConnectX NIC. E-Switch provides internal SRIOV packet steering +| and switching for the enabled VFs and PF in two available modes: +| 1) `Legacy SRIOV mode (L2 mac vlan steering based) <https://community.mellanox.com/s/article/howto-configure-sr-iov-for-connectx-4-connectx-5-with-kvm--ethernet-x>`_. +| 2) `Switchdev mode (eswitch offloads) <https://www.mellanox.com/related-docs/prod_software/ASAP2_Hardware_Offloading_for_vSwitches_User_Manual_v4.4.pdf>`_. + + +**CONFIG_MLX5_FPGA=(y/n)** + +| Build support for the Innova family of network cards by Mellanox Technologies. +| Innova network cards are comprised of a ConnectX chip and an FPGA chip on one board. +| If you select this option, the mlx5_core driver will include the Innova FPGA core and allow +| building sandbox-specific client drivers. + + +**CONFIG_MLX5_INFINIBAND=(y/n/m)** (module mlx5_ib.ko) + +| Provides low-level InfiniBand/RDMA and `RoCE <https://community.mellanox.com/s/article/recommended-network-configuration-examples-for-roce-deployment>`_ support. + + +**CONFIG_MLX5_MPFS=(y/n)** + +| Ethernet Multi-Physical Function Switch (MPFS) support in ConnectX NIC. +| MPFs is required for when `Multi-Host <http://www.mellanox.com/page/multihost>`_ configuration is enabled to allow passing +| user configured unicast MAC addresses to the requesting PF. + + +**CONFIG_MLX5_SF=(y/n)** + +| Build support for subfunction. +| Subfunctons are more light weight than PCI SRIOV VFs. Choosing this option +| will enable support for creating subfunction devices. + + +**CONFIG_MLX5_SF_MANAGER=(y/n)** + +| Build support for subfuction port in the NIC. A Mellanox subfunction +| port is managed through devlink. A subfunction supports RDMA, netdevice +| and vdpa device. It is similar to a SRIOV VF but it doesn't require +| SRIOV support. + + +**CONFIG_MLX5_SW_STEERING=(y/n)** + +| Build support for software-managed steering in the NIC. + + +**CONFIG_MLX5_TC_CT=(y/n)** + +| Support offloading connection tracking rules via tc ct action. + + +**CONFIG_MLX5_TC_SAMPLE=(y/n)** + +| Support offloading sample rules via tc sample action. + + +**CONFIG_MLX5_VDPA=(y/n)** + +| Support library for Mellanox VDPA drivers. Provides code that is +| common for all types of VDPA drivers. The following drivers are planned: +| net, block. + + +**CONFIG_MLX5_VDPA_NET=(y/n)** + +| VDPA network driver for ConnectX6 and newer. Provides offloading +| of virtio net datapath such that descriptors put on the ring will +| be executed by the hardware. It also supports a variety of stateless +| offloads depending on the actual device used and firmware version. + + +**CONFIG_MLX5_VFIO_PCI=(y/n)** + +| This provides migration support for MLX5 devices using the VFIO framework. + + +**External options** ( Choose if the corresponding mlx5 feature is required ) + +- CONFIG_MLXFW: When chosen, mlx5 firmware flashing support will be enabled (via devlink and ethtool). +- CONFIG_PTP_1588_CLOCK: When chosen, mlx5 ptp support will be enabled +- CONFIG_VXLAN: When chosen, mlx5 vxlan support will be enabled. diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/switchdev.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/switchdev.rst new file mode 100644 index 000000000000..01deedb71597 --- /dev/null +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/switchdev.rst @@ -0,0 +1,239 @@ +.. SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +.. include:: <isonum.txt> + +========= +Switchdev +========= + +:Copyright: |copy| 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +.. _mlx5_bridge_offload: + +Bridge offload +============== + +The mlx5 driver implements support for offloading bridge rules when in switchdev +mode. Linux bridge FDBs are automatically offloaded when mlx5 switchdev +representor is attached to bridge. + +- Change device to switchdev mode:: + + $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev + +- Attach mlx5 switchdev representor 'enp8s0f0' to bridge netdev 'bridge1':: + + $ ip link set enp8s0f0 master bridge1 + +VLANs +----- + +Following bridge VLAN functions are supported by mlx5: + +- VLAN filtering (including multiple VLANs per port):: + + $ ip link set bridge1 type bridge vlan_filtering 1 + $ bridge vlan add dev enp8s0f0 vid 2-3 + +- VLAN push on bridge ingress:: + + $ bridge vlan add dev enp8s0f0 vid 3 pvid + +- VLAN pop on bridge egress:: + + $ bridge vlan add dev enp8s0f0 vid 3 untagged + +Subfunction +=========== + +mlx5 supports subfunction management using devlink port (see :ref:`Documentation/networking/devlink/devlink-port.rst <devlink_port>`) interface. + +A subfunction has its own function capabilities and its own resources. This +means a subfunction has its own dedicated queues (txq, rxq, cq, eq). These +queues are neither shared nor stolen from the parent PCI function. + +When a subfunction is RDMA capable, it has its own QP1, GID table, and RDMA +resources neither shared nor stolen from the parent PCI function. + +A subfunction has a dedicated window in PCI BAR space that is not shared +with the other subfunctions or the parent PCI function. This ensures that all +devices (netdev, rdma, vdpa, etc.) of the subfunction accesses only assigned +PCI BAR space. + +A subfunction supports eswitch representation through which it supports tc +offloads. The user configures eswitch to send/receive packets from/to +the subfunction port. + +Subfunctions share PCI level resources such as PCI MSI-X IRQs with +other subfunctions and/or with its parent PCI function. + +Example mlx5 software, system, and device view:: + + _______ + | admin | + | user |---------- + |_______| | + | | + ____|____ __|______ _________________ + | | | | | | + | devlink | | tc tool | | user | + | tool | |_________| | applications | + |_________| | |_________________| + | | | | + | | | | Userspace + +---------|-------------|-------------------|----------|--------------------+ + | | +----------+ +----------+ Kernel + | | | netdev | | rdma dev | + | | +----------+ +----------+ + (devlink port add/del | ^ ^ + port function set) | | | + | | +---------------| + _____|___ | | _______|_______ + | | | | | mlx5 class | + | devlink | +------------+ | | drivers | + | kernel | | rep netdev | | |(mlx5_core,ib) | + |_________| +------------+ | |_______________| + | | | ^ + (devlink ops) | | (probe/remove) + _________|________ | | ____|________ + | subfunction | | +---------------+ | subfunction | + | management driver|----- | subfunction |---| driver | + | (mlx5_core) | | auxiliary dev | | (mlx5_core) | + |__________________| +---------------+ |_____________| + | ^ + (sf add/del, vhca events) | + | (device add/del) + _____|____ ____|________ + | | | subfunction | + | PCI NIC |--- activate/deactivate events--->| host driver | + |__________| | (mlx5_core) | + |_____________| + +Subfunction is created using devlink port interface. + +- Change device to switchdev mode:: + + $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev + +- Add a devlink port of subfunction flavour:: + + $ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88 + pci/0000:06:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false + function: + hw_addr 00:00:00:00:00:00 state inactive opstate detached + +- Show a devlink port of the subfunction:: + + $ devlink port show pci/0000:06:00.0/32768 + pci/0000:06:00.0/32768: type eth netdev enp6s0pf0sf88 flavour pcisf pfnum 0 sfnum 88 + function: + hw_addr 00:00:00:00:00:00 state inactive opstate detached + +- Delete a devlink port of subfunction after use:: + + $ devlink port del pci/0000:06:00.0/32768 + +Function attributes +=================== + +The mlx5 driver provides a mechanism to setup PCI VF/SF function attributes in +a unified way for SmartNIC and non-SmartNIC. + +This is supported only when the eswitch mode is set to switchdev. Port function +configuration of the PCI VF/SF is supported through devlink eswitch port. + +Port function attributes should be set before PCI VF/SF is enumerated by the +driver. + +MAC address setup +----------------- + +mlx5 driver support devlink port function attr mechanism to setup MAC +address. (refer to Documentation/networking/devlink/devlink-port.rst) + +RoCE capability setup +~~~~~~~~~~~~~~~~~~~~~ +Not all mlx5 PCI devices/SFs require RoCE capability. + +When RoCE capability is disabled, it saves 1 Mbytes worth of system memory per +PCI devices/SF. + +mlx5 driver support devlink port function attr mechanism to setup RoCE +capability. (refer to Documentation/networking/devlink/devlink-port.rst) + +migratable capability setup +~~~~~~~~~~~~~~~~~~~~~~~~~~~ +User who wants mlx5 PCI VFs to be able to perform live migration need to +explicitly enable the VF migratable capability. + +mlx5 driver support devlink port function attr mechanism to setup migratable +capability. (refer to Documentation/networking/devlink/devlink-port.rst) + +SF state setup +-------------- + +To use the SF, the user must activate the SF using the SF function state +attribute. + +- Get the state of the SF identified by its unique devlink port index:: + + $ devlink port show ens2f0npf0sf88 + pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false + function: + hw_addr 00:00:00:00:88:88 state inactive opstate detached + +- Activate the function and verify its state is active:: + + $ devlink port function set ens2f0npf0sf88 state active + + $ devlink port show ens2f0npf0sf88 + pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false + function: + hw_addr 00:00:00:00:88:88 state active opstate detached + +Upon function activation, the PF driver instance gets the event from the device +that a particular SF was activated. It's the cue to put the device on bus, probe +it and instantiate the devlink instance and class specific auxiliary devices +for it. + +- Show the auxiliary device and port of the subfunction:: + + $ devlink dev show + devlink dev show auxiliary/mlx5_core.sf.4 + + $ devlink port show auxiliary/mlx5_core.sf.4/1 + auxiliary/mlx5_core.sf.4/1: type eth netdev p0sf88 flavour virtual port 0 splittable false + + $ rdma link show mlx5_0/1 + link mlx5_0/1 state ACTIVE physical_state LINK_UP netdev p0sf88 + + $ rdma dev show + 8: rocep6s0f1: node_type ca fw 16.29.0550 node_guid 248a:0703:00b3:d113 sys_image_guid 248a:0703:00b3:d112 + 13: mlx5_0: node_type ca fw 16.29.0550 node_guid 0000:00ff:fe00:8888 sys_image_guid 248a:0703:00b3:d112 + +- Subfunction auxiliary device and class device hierarchy:: + + mlx5_core.sf.4 + (subfunction auxiliary device) + /\ + / \ + / \ + / \ + / \ + mlx5_core.eth.4 mlx5_core.rdma.4 + (sf eth aux dev) (sf rdma aux dev) + | | + | | + p0sf88 mlx5_0 + (sf netdev) (sf rdma device) + +Additionally, the SF port also gets the event when the driver attaches to the +auxiliary device of the subfunction. This results in changing the operational +state of the function. This provides visibility to the user to decide when is it +safe to delete the SF port for graceful termination of the subfunction. + +- Show the SF port operational state:: + + $ devlink port show ens2f0npf0sf88 + pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false + function: + hw_addr 00:00:00:00:88:88 state active opstate attached diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/tracepoints.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/tracepoints.rst new file mode 100644 index 000000000000..a9d3e123adc4 --- /dev/null +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/tracepoints.rst @@ -0,0 +1,229 @@ +.. SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +.. include:: <isonum.txt> + +=========== +Tracepoints +=========== + +:Copyright: |copy| 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +mlx5 driver provides internal tracepoints for tracking and debugging using +kernel tracepoints interfaces (refer to Documentation/trace/ftrace.rst). + +For the list of support mlx5 events, check `/sys/kernel/debug/tracing/events/mlx5/`. + +tc and eswitch offloads tracepoints: + +- mlx5e_configure_flower: trace flower filter actions and cookies offloaded to mlx5:: + + $ echo mlx5:mlx5e_configure_flower >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + tc-6535 [019] ...1 2672.404466: mlx5e_configure_flower: cookie=0000000067874a55 actions= REDIRECT + +- mlx5e_delete_flower: trace flower filter actions and cookies deleted from mlx5:: + + $ echo mlx5:mlx5e_delete_flower >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + tc-6569 [010] .N.1 2686.379075: mlx5e_delete_flower: cookie=0000000067874a55 actions= NULL + +- mlx5e_stats_flower: trace flower stats request:: + + $ echo mlx5:mlx5e_stats_flower >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + tc-6546 [010] ...1 2679.704889: mlx5e_stats_flower: cookie=0000000060eb3d6a bytes=0 packets=0 lastused=4295560217 + +- mlx5e_tc_update_neigh_used_value: trace tunnel rule neigh update value offloaded to mlx5:: + + $ echo mlx5:mlx5e_tc_update_neigh_used_value >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + kworker/u48:4-8806 [009] ...1 55117.882428: mlx5e_tc_update_neigh_used_value: netdev: ens1f0 IPv4: 1.1.1.10 IPv6: ::ffff:1.1.1.10 neigh_used=1 + +- mlx5e_rep_neigh_update: trace neigh update tasks scheduled due to neigh state change events:: + + $ echo mlx5:mlx5e_rep_neigh_update >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + kworker/u48:7-2221 [009] ...1 1475.387435: mlx5e_rep_neigh_update: netdev: ens1f0 MAC: 24:8a:07:9a:17:9a IPv4: 1.1.1.10 IPv6: ::ffff:1.1.1.10 neigh_connected=1 + +Bridge offloads tracepoints: + +- mlx5_esw_bridge_fdb_entry_init: trace bridge FDB entry offloaded to mlx5:: + + $ echo mlx5:mlx5_esw_bridge_fdb_entry_init >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + kworker/u20:9-2217 [003] ...1 318.582243: mlx5_esw_bridge_fdb_entry_init: net_device=enp8s0f0_0 addr=e4:fd:05:08:00:02 vid=0 flags=0 used=0 + +- mlx5_esw_bridge_fdb_entry_cleanup: trace bridge FDB entry deleted from mlx5:: + + $ echo mlx5:mlx5_esw_bridge_fdb_entry_cleanup >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + ip-2581 [005] ...1 318.629871: mlx5_esw_bridge_fdb_entry_cleanup: net_device=enp8s0f0_1 addr=e4:fd:05:08:00:03 vid=0 flags=0 used=16 + +- mlx5_esw_bridge_fdb_entry_refresh: trace bridge FDB entry offload refreshed in + mlx5:: + + $ echo mlx5:mlx5_esw_bridge_fdb_entry_refresh >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + kworker/u20:8-3849 [003] ...1 466716: mlx5_esw_bridge_fdb_entry_refresh: net_device=enp8s0f0_0 addr=e4:fd:05:08:00:02 vid=3 flags=0 used=0 + +- mlx5_esw_bridge_vlan_create: trace bridge VLAN object add on mlx5 + representor:: + + $ echo mlx5:mlx5_esw_bridge_vlan_create >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + ip-2560 [007] ...1 318.460258: mlx5_esw_bridge_vlan_create: vid=1 flags=6 + +- mlx5_esw_bridge_vlan_cleanup: trace bridge VLAN object delete from mlx5 + representor:: + + $ echo mlx5:mlx5_esw_bridge_vlan_cleanup >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + bridge-2582 [007] ...1 318.653496: mlx5_esw_bridge_vlan_cleanup: vid=2 flags=8 + +- mlx5_esw_bridge_vport_init: trace mlx5 vport assigned with bridge upper + device:: + + $ echo mlx5:mlx5_esw_bridge_vport_init >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + ip-2560 [007] ...1 318.458915: mlx5_esw_bridge_vport_init: vport_num=1 + +- mlx5_esw_bridge_vport_cleanup: trace mlx5 vport removed from bridge upper + device:: + + $ echo mlx5:mlx5_esw_bridge_vport_cleanup >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + ip-5387 [000] ...1 573713: mlx5_esw_bridge_vport_cleanup: vport_num=1 + +Eswitch QoS tracepoints: + +- mlx5_esw_vport_qos_create: trace creation of transmit scheduler arbiter for vport:: + + $ echo mlx5:mlx5_esw_vport_qos_create >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + <...>-23496 [018] .... 73136.838831: mlx5_esw_vport_qos_create: (0000:82:00.0) vport=2 tsar_ix=4 bw_share=0, max_rate=0 group=000000007b576bb3 + +- mlx5_esw_vport_qos_config: trace configuration of transmit scheduler arbiter for vport:: + + $ echo mlx5:mlx5_esw_vport_qos_config >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + <...>-26548 [023] .... 75754.223823: mlx5_esw_vport_qos_config: (0000:82:00.0) vport=1 tsar_ix=3 bw_share=34, max_rate=10000 group=000000007b576bb3 + +- mlx5_esw_vport_qos_destroy: trace deletion of transmit scheduler arbiter for vport:: + + $ echo mlx5:mlx5_esw_vport_qos_destroy >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + <...>-27418 [004] .... 76546.680901: mlx5_esw_vport_qos_destroy: (0000:82:00.0) vport=1 tsar_ix=3 + +- mlx5_esw_group_qos_create: trace creation of transmit scheduler arbiter for rate group:: + + $ echo mlx5:mlx5_esw_group_qos_create >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + <...>-26578 [008] .... 75776.022112: mlx5_esw_group_qos_create: (0000:82:00.0) group=000000008dac63ea tsar_ix=5 + +- mlx5_esw_group_qos_config: trace configuration of transmit scheduler arbiter for rate group:: + + $ echo mlx5:mlx5_esw_group_qos_config >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + <...>-27303 [020] .... 76461.455356: mlx5_esw_group_qos_config: (0000:82:00.0) group=000000008dac63ea tsar_ix=5 bw_share=100 max_rate=20000 + +- mlx5_esw_group_qos_destroy: trace deletion of transmit scheduler arbiter for group:: + + $ echo mlx5:mlx5_esw_group_qos_destroy >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + <...>-27418 [006] .... 76547.187258: mlx5_esw_group_qos_destroy: (0000:82:00.0) group=000000007b576bb3 tsar_ix=1 + +SF tracepoints: + +- mlx5_sf_add: trace addition of the SF port:: + + $ echo mlx5:mlx5_sf_add >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + devlink-9363 [031] ..... 24610.188722: mlx5_sf_add: (0000:06:00.0) port_index=32768 controller=0 hw_id=0x8000 sfnum=88 + +- mlx5_sf_free: trace freeing of the SF port:: + + $ echo mlx5:mlx5_sf_free >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + devlink-9830 [038] ..... 26300.404749: mlx5_sf_free: (0000:06:00.0) port_index=32768 controller=0 hw_id=0x8000 + +- mlx5_sf_activate: trace activation of the SF port:: + + $ echo mlx5:mlx5_sf_activate >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + devlink-29841 [008] ..... 3669.635095: mlx5_sf_activate: (0000:08:00.0) port_index=32768 controller=0 hw_id=0x8000 + +- mlx5_sf_deactivate: trace deactivation of the SF port:: + + $ echo mlx5:mlx5_sf_deactivate >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + devlink-29994 [008] ..... 4015.969467: mlx5_sf_deactivate: (0000:08:00.0) port_index=32768 controller=0 hw_id=0x8000 + +- mlx5_sf_hwc_alloc: trace allocating of the hardware SF context:: + + $ echo mlx5:mlx5_sf_hwc_alloc >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + devlink-9775 [031] ..... 26296.385259: mlx5_sf_hwc_alloc: (0000:06:00.0) controller=0 hw_id=0x8000 sfnum=88 + +- mlx5_sf_hwc_free: trace freeing of the hardware SF context:: + + $ echo mlx5:mlx5_sf_hwc_free >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + kworker/u128:3-9093 [046] ..... 24625.365771: mlx5_sf_hwc_free: (0000:06:00.0) hw_id=0x8000 + +- mlx5_sf_hwc_deferred_free: trace deferred freeing of the hardware SF context:: + + $ echo mlx5:mlx5_sf_hwc_deferred_free >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + devlink-9519 [046] ..... 24624.400271: mlx5_sf_hwc_deferred_free: (0000:06:00.0) hw_id=0x8000 + +- mlx5_sf_update_state: trace state updates for SF contexts:: + + $ echo mlx5:mlx5_sf_update_state >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + kworker/u20:3-29490 [009] ..... 4141.453530: mlx5_sf_update_state: (0000:08:00.0) port_index=32768 controller=0 hw_id=0x8000 state=2 + +- mlx5_sf_vhca_event: trace SF vhca event and state:: + + $ echo mlx5:mlx5_sf_vhca_event >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + kworker/u128:3-9093 [046] ..... 24625.365525: mlx5_sf_vhca_event: (0000:06:00.0) hw_id=0x8000 sfnum=88 vhca_state=1 + +- mlx5_sf_dev_add: trace SF device add event:: + + $ echo mlx5:mlx5_sf_dev_add>> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + kworker/u128:3-9093 [000] ..... 24616.524495: mlx5_sf_dev_add: (0000:06:00.0) sfdev=00000000fc5d96fd aux_id=4 hw_id=0x8000 sfnum=88 + +- mlx5_sf_dev_del: trace SF device delete event:: + + $ echo mlx5:mlx5_sf_dev_del >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + kworker/u128:3-9093 [044] ..... 24624.400749: mlx5_sf_dev_del: (0000:06:00.0) sfdev=00000000fc5d96fd aux_id=4 hw_id=0x8000 sfnum=88 diff --git a/Documentation/networking/device_drivers/ethernet/pensando/ionic.rst b/Documentation/networking/device_drivers/ethernet/pensando/ionic.rst index 0eabbc347d6c..6ec7d686efab 100644 --- a/Documentation/networking/device_drivers/ethernet/pensando/ionic.rst +++ b/Documentation/networking/device_drivers/ethernet/pensando/ionic.rst @@ -83,7 +83,7 @@ Configuring the Driver MTU --- -Jumbo frame support is available with a maximim size of 9194 bytes. +Jumbo frame support is available with a maximum size of 9194 bytes. Interrupt coalescing -------------------- diff --git a/Documentation/networking/device_drivers/ethernet/ti/am65_nuss_cpsw_switchdev.rst b/Documentation/networking/device_drivers/ethernet/ti/am65_nuss_cpsw_switchdev.rst index f24adfab6a1b..25fd9aa284e2 100644 --- a/Documentation/networking/device_drivers/ethernet/ti/am65_nuss_cpsw_switchdev.rst +++ b/Documentation/networking/device_drivers/ethernet/ti/am65_nuss_cpsw_switchdev.rst @@ -124,7 +124,7 @@ Multicast flooding ================== CPU port mcast_flooding is always on -Turning flooding on/off on swithch ports: +Turning flooding on/off on switch ports: bridge link set dev sw0p1 mcast_flood on/off Access and Trunk port diff --git a/Documentation/networking/device_drivers/ethernet/ti/cpsw_switchdev.rst b/Documentation/networking/device_drivers/ethernet/ti/cpsw_switchdev.rst index 1241ecac73bd..464dce938ed1 100644 --- a/Documentation/networking/device_drivers/ethernet/ti/cpsw_switchdev.rst +++ b/Documentation/networking/device_drivers/ethernet/ti/cpsw_switchdev.rst @@ -174,7 +174,7 @@ Multicast flooding ================== CPU port mcast_flooding is always on -Turning flooding on/off on swithch ports: +Turning flooding on/off on switch ports: bridge link set dev sw0p1 mcast_flood on/off Access and Trunk port diff --git a/Documentation/networking/device_drivers/ethernet/wangxun/txgbe.rst b/Documentation/networking/device_drivers/ethernet/wangxun/txgbe.rst index eaa87dbe8848..d052ef40fe36 100644 --- a/Documentation/networking/device_drivers/ethernet/wangxun/txgbe.rst +++ b/Documentation/networking/device_drivers/ethernet/wangxun/txgbe.rst @@ -16,5 +16,5 @@ Contents Support ======= -If you got any problem, contact Wangxun support team via support@trustnetic.com +If you got any problem, contact Wangxun support team via nic-support@net-swift.com and Cc: netdev. diff --git a/Documentation/networking/device_drivers/wwan/iosm.rst b/Documentation/networking/device_drivers/wwan/iosm.rst index aceb0223eb46..6f9e955af984 100644 --- a/Documentation/networking/device_drivers/wwan/iosm.rst +++ b/Documentation/networking/device_drivers/wwan/iosm.rst @@ -69,7 +69,7 @@ wwan0-X network device The IOSM driver exposes IP link interface "wwan0-X" of type "wwan" for IP traffic. Iproute network utility is used for creating "wwan0-X" network interface and for associating it with MBIM IP session. The Driver supports -upto 8 IP sessions for simultaneous IP communication. +up to 8 IP sessions for simultaneous IP communication. The userspace management application is responsible for creating new IP link prior to establishing MBIM IP session where the SessionId is greater than 0. diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst index 625efb3777d5..10f282c2117c 100644 --- a/Documentation/networking/devlink/ice.rst +++ b/Documentation/networking/devlink/ice.rst @@ -285,7 +285,7 @@ features are enabled after the hierarchy is exported, but before any changes are made. This feature is also dependent on switchdev being enabled in the system. -It's required bacause devlink-rate requires devlink-port objects to be +It's required because devlink-rate requires devlink-port objects to be present, and those objects are only created in switchdev mode. If the driver is set to the switchdev mode, it will export internal @@ -320,7 +320,7 @@ nodes and nodes with children also can't be deleted. * - ``tx_weight`` - allows for usage of Weighted Fair Queuing arbitration scheme among siblings. This arbitration scheme can be used simultaneously with - the strict priority. Range 1-200. Only relative values mater for + the strict priority. Range 1-200. Only relative values matter for arbitration. ``tx_priority`` and ``tx_weight`` can be used simultaneously. In that case diff --git a/Documentation/networking/devlink/netdevsim.rst b/Documentation/networking/devlink/netdevsim.rst index ec5e6d79b2e2..88482725422c 100644 --- a/Documentation/networking/devlink/netdevsim.rst +++ b/Documentation/networking/devlink/netdevsim.rst @@ -95,5 +95,5 @@ Driver-specific Traps * - ``fid_miss`` - ``exception`` - When a packet enters the device it is classified to a filtering - indentifier (FID) based on the ingress port and VLAN. This trap is used + identifier (FID) based on the ingress port and VLAN. This trap is used to trap packets for which a FID could not be found diff --git a/Documentation/networking/devlink/prestera.rst b/Documentation/networking/devlink/prestera.rst index 49409d1d3081..96b1124e614b 100644 --- a/Documentation/networking/devlink/prestera.rst +++ b/Documentation/networking/devlink/prestera.rst @@ -138,4 +138,4 @@ Driver-specific Traps - Drops packets with zero (0) IPV4 source address. * - ``met_red`` - ``drop`` - - Drops non-conforming packets (dropped by Ingress policer, metering drop), e.g. packet rate exceeded configured bandwith. + - Drops non-conforming packets (dropped by Ingress policer, metering drop), e.g. packet rate exceeded configured bandwidth. diff --git a/Documentation/networking/dsa/configuration.rst b/Documentation/networking/dsa/configuration.rst index 827701f8cbfe..d2934c40f0f1 100644 --- a/Documentation/networking/dsa/configuration.rst +++ b/Documentation/networking/dsa/configuration.rst @@ -5,7 +5,7 @@ DSA switch configuration from userspace ======================================= The DSA switch configuration is not integrated into the main userspace -network configuration suites by now and has to be performed manualy. +network configuration suites by now and has to be performed manually. .. _dsa-config-showcases: diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 1626e863eec9..d144e890961d 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -106,7 +106,7 @@ modifying a bitmap, the former changes the bit set in mask to values set in value and preserves the rest; the latter sets the bits set in the bitmap and clears the rest. -Compact form: nested (bitset) atrribute contents: +Compact form: nested (bitset) attribute contents: ============================ ====== ============================ ``ETHTOOL_A_BITSET_NOMASK`` flag no mask, only a list @@ -783,7 +783,7 @@ Kernel response contents: ``ETHTOOL_A_FEATURES_ACTIVE`` bitset diff old vs. new active ==================================== ====== ========================== -Request constains only one bitset which can be either value/mask pair (request +Request contains only one bitset which can be either value/mask pair (request to change specific feature bits and leave the rest) or only a value (request to set all features to specified set). @@ -1823,7 +1823,7 @@ aPLCATransmitOpportunityTimer. The valid range for this attribute is When set, the optional ``ETHTOOL_A_PLCA_BURST_CNT`` attribute indicates the configured number of extra packets that the node is allowed to send during a single transmit opportunity. By default, this attribute is 0, meaning that -the node can only send a sigle frame per TO. When greater than 0, the PLCA RS +the node can only send a single frame per TO. When greater than 0, the PLCA RS keeps the TO after any transmission, waiting for the MAC to send a new frame for up to aPLCABurstTimer BTs. This can only happen a number of times per PLCA cycle up to the value of this parameter. After that, the burst is over and the diff --git a/Documentation/networking/gtp.rst b/Documentation/networking/gtp.rst index 1563fb94b289..9a7835cc1437 100644 --- a/Documentation/networking/gtp.rst +++ b/Documentation/networking/gtp.rst @@ -162,7 +162,7 @@ Local GTP-U entity and tunnel identification GTP-U uses UDP for transporting PDU's. The receiving UDP port is 2152 for GTPv1-U and 3386 for GTPv0-U. -There is only one GTP-U entity (and therefor SGSN/GGSN/S-GW/PDN-GW +There is only one GTP-U entity (and therefore SGSN/GGSN/S-GW/PDN-GW instance) per IP address. Tunnel Endpoint Identifier (TEID) are unique per GTP-U entity. diff --git a/Documentation/networking/ieee802154.rst b/Documentation/networking/ieee802154.rst index f27856d77c8b..c652d383fe10 100644 --- a/Documentation/networking/ieee802154.rst +++ b/Documentation/networking/ieee802154.rst @@ -70,7 +70,7 @@ Like with WiFi, there are several types of devices implementing IEEE 802.15.4. exports a management (e.g. MLME) and data API. 2) 'SoftMAC' or just radio. These types of devices are just radio transceivers possibly with some kinds of acceleration like automatic CRC computation and -comparation, automagic ACK handling, address matching, etc. +comparison, automagic ACK handling, address matching, etc. Those types of devices require different approach to be hooked into Linux kernel. diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 4cc2fab58dea..87dd1c5283e6 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -50,7 +50,7 @@ ip_no_pmtu_disc - INTEGER Default: FALSE min_pmtu - INTEGER - default 552 - minimum Path MTU. Unless this is changed mannually, + default 552 - minimum Path MTU. Unless this is changed manually, each cached pmtu will never be lower than this setting. ip_forward_use_pmtu - BOOLEAN @@ -1592,6 +1592,14 @@ proxy_arp_pvlan - BOOLEAN Hewlett-Packard call it Source-Port filtering or port-isolation. Ericsson call it MAC-Forced Forwarding (RFC Draft). +proxy_delay - INTEGER + Delay proxy response. + + Delay response to a neighbor solicitation when proxy_arp + or proxy_ndp is enabled. A random value between [0, proxy_delay) + will be chosen, setting to zero means reply with no delay. + Value in jiffies. Defaults to 80. + shared_media - BOOLEAN Send(router) or accept(host) RFC1620 shared media redirects. Overrides secure_redirects. @@ -2078,7 +2086,7 @@ skip_notify_on_dev_down - BOOLEAN nexthop_compat_mode - BOOLEAN New nexthop API provides a means for managing nexthops independent of - prefixes. Backwards compatibilty with old route format is enabled by + prefixes. Backwards compatibility with old route format is enabled by default which means route dumps and notifications contain the new nexthop attribute but also the full, expanded nexthop definition. Further, updates or deletes of a nexthop configuration generate route @@ -2811,7 +2819,7 @@ pf_expose - INTEGER can be got via SCTP_GET_PEER_ADDR_INFO sockopt; When it's enabled, a SCTP_PEER_ADDR_CHANGE event will be sent for a transport becoming SCTP_PF state and a SCTP_PF-state transport info can be got via - SCTP_GET_PEER_ADDR_INFO sockopt; When it's diabled, no + SCTP_GET_PEER_ADDR_INFO sockopt; When it's disabled, no SCTP_PEER_ADDR_CHANGE event will be sent and it returns -EACCES when trying to get a SCTP_PF-state transport info via SCTP_GET_PEER_ADDR_INFO sockopt. diff --git a/Documentation/networking/ipvlan.rst b/Documentation/networking/ipvlan.rst index 0000c1d383bc..895d0ccfd596 100644 --- a/Documentation/networking/ipvlan.rst +++ b/Documentation/networking/ipvlan.rst @@ -61,7 +61,7 @@ e.g. IPvlan has two modes of operation - L2 and L3. For a given master device, you can select one of these two modes and all slaves on that master will operate in the same (selected) mode. The RX mode is almost identical except -that in L3 mode the slaves wont receive any multicast / broadcast traffic. +that in L3 mode the slaves won't receive any multicast / broadcast traffic. L3 mode is more restrictive since routing is controlled from the other (mostly) default namespace. diff --git a/Documentation/networking/j1939.rst b/Documentation/networking/j1939.rst index b705d2801e9c..e4bd7aa1f5aa 100644 --- a/Documentation/networking/j1939.rst +++ b/Documentation/networking/j1939.rst @@ -116,7 +116,7 @@ format, the Group Extension is set in the PS-field. ---------------------------------------- 23 ... 16 15 ... 8 ============== ======================== - F0h ... FFh GE (Group Extenstion) + F0h ... FFh GE (Group Extension) ============== ======================== On the other hand, when using PDU1 format, the PS-field contains a so-called diff --git a/Documentation/networking/net_failover.rst b/Documentation/networking/net_failover.rst index 3a662f2b4d6e..f4e1b4e07adc 100644 --- a/Documentation/networking/net_failover.rst +++ b/Documentation/networking/net_failover.rst @@ -90,7 +90,7 @@ virtio-net interface, and ens11 is the slave 'primary' VF passthrough interface. One point to note here is that some user space network configuration daemons like systemd-networkd, ifupdown, etc, do not understand the 'net_failover' device; and on the first boot, the VM might end up with both 'failover' device -and VF accquiring IP addresses (either same or different) from the DHCP server. +and VF acquiring IP addresses (either same or different) from the DHCP server. This will result in lack of connectivity to the VM. So some tweaks might be needed to these network configuration daemons to make sure that an IP is received only on the 'failover' device. diff --git a/Documentation/networking/netconsole.rst b/Documentation/networking/netconsole.rst index 1f5c4a04027c..dd0518e002f6 100644 --- a/Documentation/networking/netconsole.rst +++ b/Documentation/networking/netconsole.rst @@ -167,7 +167,7 @@ following format which is the same as /dev/kmsg:: Non printable characters in <message text> are escaped using "\xff" notation. If the message contains optional dictionary, verbatim -newline is used as the delimeter. +newline is used as the delimiter. If a message doesn't fit in certain number of bytes (currently 1000), the message is split into multiple fragments by netconsole. These diff --git a/Documentation/networking/page_pool.rst b/Documentation/networking/page_pool.rst index 5db8c263b0c6..30f1344e7cca 100644 --- a/Documentation/networking/page_pool.rst +++ b/Documentation/networking/page_pool.rst @@ -11,7 +11,7 @@ Basic use involves replacing alloc_pages() calls with the page_pool_alloc_pages() call. Drivers should use page_pool_dev_alloc_pages() replacing dev_alloc_pages(). -API keeps track of inflight pages, in order to let API user know +API keeps track of in-flight pages, in order to let API user know when it is safe to free a page_pool object. Thus, API users must run page_pool_release_page() when a page is leaving the page_pool or call page_pool_put_page() where appropriate in order to maintain correct @@ -19,7 +19,7 @@ accounting. API user must call page_pool_put_page() once on a page, as it will either recycle the page, or in case of refcnt > 1, it will -release the DMA mapping and inflight state accounting. +release the DMA mapping and in-flight state accounting. Architecture overview ===================== @@ -88,7 +88,7 @@ a page will cause no race conditions is enough. directly into the pool fast cache. * page_pool_release_page(): Unmap the page (if mapped) and account for it on - inflight counters. + in-flight counters. * page_pool_dev_alloc_pages(): Get a page from the page allocator or page_pool caches. diff --git a/Documentation/networking/phonet.rst b/Documentation/networking/phonet.rst index 8668dcbc5e6a..d705cc5b09fc 100644 --- a/Documentation/networking/phonet.rst +++ b/Documentation/networking/phonet.rst @@ -131,7 +131,7 @@ Phonet resources, as follow:: Subscription is similarly cancelled using the SIOCPNDELRESOURCE I/O control request, or when the socket is closed. -Note that no more than one socket can be subcribed to any given +Note that no more than one socket can be subscribed to any given resource at a time. If not, ioctl() will return EBUSY. diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst index d11329a08984..b7ac4c64cf67 100644 --- a/Documentation/networking/phy.rst +++ b/Documentation/networking/phy.rst @@ -315,7 +315,7 @@ Some of the interface modes are described below: only the port id, but also so-called "extensions". The only documented extension so-far in the specification is the inclusion of timestamps, for PTP-enabled PHYs. This mode isn't compatible with QSGMII, but offers the - same capabilities in terms of link speed and negociation. + same capabilities in terms of link speed and negotiation. ``PHY_INTERFACE_MODE_1000BASEKX`` This is 1000BASE-X as defined by IEEE 802.3 Clause 36 with Clause 73 diff --git a/Documentation/networking/regulatory.rst b/Documentation/networking/regulatory.rst index 16782a95b74a..5e42c8a175c3 100644 --- a/Documentation/networking/regulatory.rst +++ b/Documentation/networking/regulatory.rst @@ -66,7 +66,7 @@ An example:: iw reg set CR This will request the kernel to set the regulatory domain to -the specificied alpha2. The kernel in turn will then ask userspace +the specified alpha2. The kernel in turn will then ask userspace to provide a regulatory domain for the alpha2 specified by the user by sending a uevent. @@ -158,7 +158,7 @@ kmalloc() a structure big enough to hold your regulatory domain structure and you should then fill it with your data. Finally you simply call regulatory_hint() with the regulatory domain structure in it. -Bellow is a simple example, with a regulatory domain cached using the stack. +Below is a simple example, with a regulatory domain cached using the stack. Your implementation may vary (read EEPROM cache instead, for example). Example cache of some regulatory domain:: diff --git a/Documentation/networking/rxrpc.rst b/Documentation/networking/rxrpc.rst index e1af54424192..ec1323d92c96 100644 --- a/Documentation/networking/rxrpc.rst +++ b/Documentation/networking/rxrpc.rst @@ -1069,7 +1069,7 @@ The kernel interface functions are as follows: This value can be used to determine if the remote client has been restarted as it shouldn't change otherwise. - (#) Set the maxmimum lifespan on a call:: + (#) Set the maximum lifespan on a call:: void rxrpc_kernel_set_max_life(struct socket *sock, struct rxrpc_call *call, diff --git a/Documentation/networking/snmp_counter.rst b/Documentation/networking/snmp_counter.rst index 423d138b5ff3..213637474478 100644 --- a/Documentation/networking/snmp_counter.rst +++ b/Documentation/networking/snmp_counter.rst @@ -980,7 +980,7 @@ How many reply packets of the SYN cookies the TCP stack receives. The MSS decoded from the SYN cookie is invalid. When this counter is updated, the received packet won't be treated as a SYN cookie and the -TcpExtSyncookiesRecv counter wont be updated. +TcpExtSyncookiesRecv counter won't be updated. Challenge ACK ============= @@ -1681,7 +1681,7 @@ RST to nstat-b:: nstatuser@nstat-a:~$ sudo iptables -A INPUT -p tcp --sport 9000 -j DROP -Send 3 SYN repeatly to nstat-b:: +Send 3 SYN repeatedly to nstat-b:: nstatuser@nstat-a:~$ for i in {1..3}; do sudo tcpreplay -i ens3 /tmp/syn_fixcsum.pcap; done diff --git a/Documentation/networking/sysfs-tagging.rst b/Documentation/networking/sysfs-tagging.rst index 83647e10c207..65307130ab63 100644 --- a/Documentation/networking/sysfs-tagging.rst +++ b/Documentation/networking/sysfs-tagging.rst @@ -43,6 +43,6 @@ Users of this interface: - current_ns() which returns current's namespace - netlink_ns() which returns a socket's namespace - - initial_ns() which returns the initial namesapce + - initial_ns() which returns the initial namespace - call kobj_ns_exit() when an individual tag is no longer valid diff --git a/Documentation/userspace-api/netlink/genetlink-legacy.rst b/Documentation/userspace-api/netlink/genetlink-legacy.rst index 65cbbffee0bf..3bf0bcdf21d8 100644 --- a/Documentation/userspace-api/netlink/genetlink-legacy.rst +++ b/Documentation/userspace-api/netlink/genetlink-legacy.rst @@ -74,6 +74,88 @@ type. Inside the attr-index nest are the policy attributes. Modern Netlink families should have instead defined this as a flat structure, the nesting serves no good purpose here. +Operations +========== + +Enum (message ID) model +----------------------- + +unified +~~~~~~~ + +Modern families use the ``unified`` message ID model, which uses +a single enumeration for all messages within family. Requests and +responses share the same message ID. Notifications have separate +IDs from the same space. For example given the following list +of operations: + +.. code-block:: yaml + + - + name: a + value: 1 + do: ... + - + name: b + do: ... + - + name: c + value: 4 + notify: a + - + name: d + do: ... + +Requests and responses for operation ``a`` will have the ID of 1, +the requests and responses of ``b`` - 2 (since there is no explicit +``value`` it's previous operation ``+ 1``). Notification ``c`` will +use the ID of 4, operation ``d`` 5 etc. + +directional +~~~~~~~~~~~ + +The ``directional`` model splits the ID assignment by the direction of +the message. Messages from and to the kernel can't be confused with +each other so this conserves the ID space (at the cost of making +the programming more cumbersome). + +In this case ``value`` attribute should be specified in the ``request`` +``reply`` sections of the operations (if an operation has both ``do`` +and ``dump`` the IDs are shared, ``value`` should be set in ``do``). +For notifications the ``value`` is provided at the op level but it +only allocates a ``reply`` (i.e. a "from-kernel" ID). Let's look +at an example: + +.. code-block:: yaml + + - + name: a + do: + request: + value: 2 + attributes: ... + reply: + value: 1 + attributes: ... + - + name: b + notify: a + - + name: c + notify: a + value: 7 + - + name: d + do: ... + +In this case ``a`` will use 2 when sending the message to the kernel +and expects message with ID 1 in response. Notification ``b`` allocates +a "from-kernel" ID which is 2. ``c`` allocates "from-kernel" ID of 7. +If operation ``d`` does not set ``values`` explicitly in the spec +it will be allocated 3 for the request (``a`` is the previous operation +with a request section and the value of 2) and 8 for response (``c`` is +the previous operation in the "from-kernel" direction). + Other quirks (todo) =================== diff --git a/Documentation/userspace-api/netlink/index.rst b/Documentation/userspace-api/netlink/index.rst index be250110c8f6..26f3720cb3be 100644 --- a/Documentation/userspace-api/netlink/index.rst +++ b/Documentation/userspace-api/netlink/index.rst @@ -10,6 +10,7 @@ Netlink documentation for users. :maxdepth: 2 intro + intro-specs specs c-code-gen genetlink-legacy diff --git a/Documentation/userspace-api/netlink/intro-specs.rst b/Documentation/userspace-api/netlink/intro-specs.rst new file mode 100644 index 000000000000..a3b847eafff7 --- /dev/null +++ b/Documentation/userspace-api/netlink/intro-specs.rst @@ -0,0 +1,80 @@ +.. SPDX-License-Identifier: BSD-3-Clause + +===================================== +Using Netlink protocol specifications +===================================== + +This document is a quick starting guide for using Netlink protocol +specifications. For more detailed description of the specs see :doc:`specs`. + +Simple CLI +========== + +Kernel comes with a simple CLI tool which should be useful when +developing Netlink related code. The tool is implemented in Python +and can use a YAML specification to issue Netlink requests +to the kernel. Only Generic Netlink is supported. + +The tool is located at ``tools/net/ynl/cli.py``. It accepts +a handul of arguments, the most important ones are: + + - ``--spec`` - point to the spec file + - ``--do $name`` / ``--dump $name`` - issue request ``$name`` + - ``--json $attrs`` - provide attributes for the request + - ``--subscribe $group`` - receive notifications from ``$group`` + +YAML specs can be found under ``Documentation/netlink/specs/``. + +Example use:: + + $ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/ethtool.yaml \ + --do rings-get \ + --json '{"header":{"dev-index": 18}}' + {'header': {'dev-index': 18, 'dev-name': 'eni1np1'}, + 'rx': 0, + 'rx-jumbo': 0, + 'rx-jumbo-max': 4096, + 'rx-max': 4096, + 'rx-mini': 0, + 'rx-mini-max': 4096, + 'tx': 0, + 'tx-max': 4096, + 'tx-push': 0} + +The input arguments are parsed as JSON, while the output is only +Python-pretty-printed. This is because some Netlink types can't +be expressed as JSON directly. If such attributes are needed in +the input some hacking of the script will be necessary. + +The spec and Netlink internals are factored out as a standalone +library - it should be easy to write Python tools / tests reusing +code from ``cli.py``. + +Generating kernel code +====================== + +``tools/net/ynl/ynl-regen.sh`` scans the kernel tree in search of +auto-generated files which need to be updated. Using this tool is the easiest +way to generate / update auto-generated code. + +By default code is re-generated only if spec is newer than the source, +to force regeneration use ``-f``. + +``ynl-regen.sh`` searches for ``YNL-GEN`` in the contents of files +(note that it only scans files in the git index, that is only files +tracked by git!) For instance the ``fou_nl.c`` kernel source contains:: + + /* Documentation/netlink/specs/fou.yaml */ + /* YNL-GEN kernel source */ + +``ynl-regen.sh`` will find this marker and replace the file with +kernel source based on fou.yaml. + +The simplest way to generate a new file based on a spec is to add +the two marker lines like above to a file, add that file to git, +and run the regeneration tool. Grep the tree for ``YNL-GEN`` +to see other examples. + +The code generation itself is performed by ``tools/net/ynl/ynl-gen-c.py`` +but it takes a few arguments so calling it directly for each file +quickly becomes tedious. diff --git a/Documentation/userspace-api/netlink/specs.rst b/Documentation/userspace-api/netlink/specs.rst index 8394d74fc63a..6ffe8137cd90 100644 --- a/Documentation/userspace-api/netlink/specs.rst +++ b/Documentation/userspace-api/netlink/specs.rst @@ -21,6 +21,9 @@ Internally kernel uses the YAML specs to generate: YAML specifications can be found under ``Documentation/netlink/specs/`` +This document describes details of the schema. +See :doc:`intro-specs` for a practical starting guide. + Compatibility levels ==================== diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 9807b05a1b57..0a67cb738013 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -8070,9 +8070,13 @@ considering the state as complete. VMM needs to ensure that the dirty state is final and avoid missing dirty pages from another ioctl ordered after the bitmap collection. -NOTE: One example of using the backup bitmap is saving arm64 vgic/its -tables through KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_SAVE_TABLES} command on -KVM device "kvm-arm-vgic-its" when dirty ring is enabled. +NOTE: Multiple examples of using the backup bitmap: (1) save vgic/its +tables through command KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_SAVE_TABLES} on +KVM device "kvm-arm-vgic-its". (2) restore vgic/its tables through +command KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_RESTORE_TABLES} on KVM device +"kvm-arm-vgic-its". VGICv3 LPI pending status is restored. (3) save +vgic3 pending table through KVM_DEV_ARM_VGIC_{GRP_CTRL, SAVE_PENDING_TABLES} +command on KVM device "kvm-arm-vgic-v3". 8.30 KVM_CAP_XEN_HVM -------------------- diff --git a/Documentation/x86/amd-memory-encryption.rst b/Documentation/x86/amd-memory-encryption.rst index a1940ebe7be5..934310ce7258 100644 --- a/Documentation/x86/amd-memory-encryption.rst +++ b/Documentation/x86/amd-memory-encryption.rst @@ -95,3 +95,39 @@ by supplying mem_encrypt=on on the kernel command line. However, if BIOS does not enable SME, then Linux will not be able to activate memory encryption, even if configured to do so by default or the mem_encrypt=on command line parameter is specified. + +Secure Nested Paging (SNP) +========================== + +SEV-SNP introduces new features (SEV_FEATURES[1:63]) which can be enabled +by the hypervisor for security enhancements. Some of these features need +guest side implementation to function correctly. The below table lists the +expected guest behavior with various possible scenarios of guest/hypervisor +SNP feature support. + ++-----------------+---------------+---------------+------------------+ +| Feature Enabled | Guest needs | Guest has | Guest boot | +| by the HV | implementation| implementation| behaviour | ++=================+===============+===============+==================+ +| No | No | No | Boot | +| | | | | ++-----------------+---------------+---------------+------------------+ +| No | Yes | No | Boot | +| | | | | ++-----------------+---------------+---------------+------------------+ +| No | Yes | Yes | Boot | +| | | | | ++-----------------+---------------+---------------+------------------+ +| Yes | No | No | Boot with | +| | | | feature enabled | ++-----------------+---------------+---------------+------------------+ +| Yes | Yes | No | Graceful boot | +| | | | failure | ++-----------------+---------------+---------------+------------------+ +| Yes | Yes | Yes | Boot with | +| | | | feature enabled | ++-----------------+---------------+---------------+------------------+ + +More details in AMD64 APM[1] Vol 2: 15.34.10 SEV_STATUS MSR + +[1] https://www.amd.com/system/files/TechDocs/40332.pdf diff --git a/MAINTAINERS b/MAINTAINERS index cb30e6b85b57..f2bd469ffae5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1097,7 +1097,6 @@ S: Maintained F: drivers/dma/ptdma/ AMD SEATTLE DEVICE TREE SUPPORT -M: Brijesh Singh <brijeshkumar.singh@amd.com> M: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com> M: Tom Lendacky <thomas.lendacky@amd.com> S: Supported @@ -2212,6 +2211,9 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git X: drivers/media/i2c/ +F: arch/arm64/boot/dts/freescale/ +X: arch/arm64/boot/dts/freescale/fsl-* +X: arch/arm64/boot/dts/freescale/qoriq-* N: imx N: mxs @@ -2450,11 +2452,14 @@ F: drivers/rtc/rtc-mt7622.c ARM/Mediatek SoC support M: Matthias Brugger <matthias.bgg@gmail.com> +R: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> +L: linux-kernel@vger.kernel.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-mediatek@lists.infradead.org (moderated for non-subscribers) S: Maintained W: https://mtk.wiki.kernel.org/ -C: irc://chat.freenode.net/linux-mediatek +C: irc://irc.libera.chat/linux-mediatek +F: arch/arm/boot/dts/mt2* F: arch/arm/boot/dts/mt6* F: arch/arm/boot/dts/mt7* F: arch/arm/boot/dts/mt8* @@ -2462,7 +2467,7 @@ F: arch/arm/mach-mediatek/ F: arch/arm64/boot/dts/mediatek/ F: drivers/soc/mediatek/ N: mtk -N: mt[678] +N: mt[2678] K: mediatek ARM/Mediatek USB3 PHY DRIVER @@ -3766,7 +3771,6 @@ F: net/bluetooth/ BONDING DRIVER M: Jay Vosburgh <j.vosburgh@gmail.com> -M: Veaceslav Falico <vfalico@gmail.com> M: Andy Gospodarek <andy@greyhouse.net> L: netdev@vger.kernel.org S: Supported @@ -7893,7 +7897,11 @@ F: include/linux/extcon/ EXTRA BOOT CONFIG M: Masami Hiramatsu <mhiramat@kernel.org> +L: linux-kernel@vger.kernel.org +L: linux-trace-kernel@vger.kernel.org +Q: https://patchwork.kernel.org/project/linux-trace-kernel/list/ S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git F: Documentation/admin-guide/bootconfig.rst F: fs/proc/bootconfig.c F: include/linux/bootconfig.h @@ -8569,6 +8577,7 @@ F: kernel/trace/fgraph.c F: arch/*/*/*/*ftrace* F: arch/*/*/*ftrace* F: include/*/ftrace.h +F: samples/ftrace FUNGIBLE ETHERNET DRIVERS M: Dimitris Michailidis <dmichail@fungible.com> @@ -14161,6 +14170,7 @@ M: Peter Geis <pgwipeout@gmail.com> M: Frank <Frank.Sae@motor-comm.com> L: netdev@vger.kernel.org S: Maintained +F: Documentation/devicetree/bindings/net/motorcomm,yt8xxx.yaml F: drivers/net/phy/motorcomm.c MOXA SMARTIO/INDUSTIO/INTELLIO SERIAL CARD @@ -14605,7 +14615,6 @@ F: tools/testing/selftests/net/ipsec.c NETWORKING [IPv4/IPv6] M: "David S. Miller" <davem@davemloft.net> -M: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> M: David Ahern <dsahern@kernel.org> L: netdev@vger.kernel.org S: Maintained @@ -15155,6 +15164,7 @@ M: Colin Foster <colin.foster@in-advantage.com> S: Supported F: Documentation/devicetree/bindings/mfd/mscc,ocelot.yaml F: drivers/mfd/ocelot* +F: drivers/net/dsa/ocelot/ocelot_ext.c F: include/linux/mfd/ocelot.h OCXL (Open Coherent Accelerator Processor Interface OpenCAPI) DRIVER @@ -15669,7 +15679,7 @@ OPENRISC ARCHITECTURE M: Jonas Bonn <jonas@southpole.se> M: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> M: Stafford Horne <shorne@gmail.com> -L: openrisc@lists.librecores.org +L: linux-openrisc@vger.kernel.org S: Maintained W: http://openrisc.io T: git https://github.com/openrisc/linux.git @@ -17980,6 +17990,7 @@ M: Albert Ou <aou@eecs.berkeley.edu> L: linux-riscv@lists.infradead.org S: Supported Q: https://patchwork.kernel.org/project/linux-riscv/list/ +C: irc://irc.libera.chat/riscv P: Documentation/riscv/patch-acceptance.rst T: git git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux.git F: arch/riscv/ @@ -18701,9 +18712,9 @@ F: drivers/target/ F: include/target/ SCTP PROTOCOL -M: Vlad Yasevich <vyasevich@gmail.com> M: Neil Horman <nhorman@tuxdriver.com> M: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> +M: Xin Long <lucien.xin@gmail.com> L: linux-sctp@vger.kernel.org S: Maintained W: http://lksctp.sourceforge.net @@ -21741,6 +21752,7 @@ F: include/uapi/linux/uvcvideo.h USB WEBCAM GADGET M: Laurent Pinchart <laurent.pinchart@ideasonboard.com> +M: Daniel Scally <dan.scally@ideasonboard.com> L: linux-usb@vger.kernel.org S: Maintained F: drivers/usb/gadget/function/*uvc* @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 2 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc7 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 4067f5169144..955b0362cdfb 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -132,7 +132,7 @@ AFLAGS_NOWARN :=$(call as-option,-Wa$(comma)-mno-warn-deprecated,-Wa$(comma)-W) ifeq ($(CONFIG_THUMB2_KERNEL),y) CFLAGS_ISA :=-Wa,-mimplicit-it=always $(AFLAGS_NOWARN) -AFLAGS_ISA :=$(CFLAGS_ISA) -Wa$(comma)-mthumb -D__thumb2__=2 +AFLAGS_ISA :=$(CFLAGS_ISA) -Wa$(comma)-mthumb CFLAGS_ISA +=-mthumb else CFLAGS_ISA :=$(call cc-option,-marm,) $(AFLAGS_NOWARN) diff --git a/arch/arm/boot/dts/aspeed-bmc-ibm-bonnell.dts b/arch/arm/boot/dts/aspeed-bmc-ibm-bonnell.dts index d1971ddf06a5..7f755e5a4624 100644 --- a/arch/arm/boot/dts/aspeed-bmc-ibm-bonnell.dts +++ b/arch/arm/boot/dts/aspeed-bmc-ibm-bonnell.dts @@ -751,7 +751,7 @@ }; pca9849@75 { - compatible = "nxp,pca849"; + compatible = "nxp,pca9849"; reg = <0x75>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/imx7d-smegw01.dts b/arch/arm/boot/dts/imx7d-smegw01.dts index 546268b8d0b1..c0f00f5db11e 100644 --- a/arch/arm/boot/dts/imx7d-smegw01.dts +++ b/arch/arm/boot/dts/imx7d-smegw01.dts @@ -198,6 +198,7 @@ &usbotg2 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usbotg2>; + over-current-active-low; dr_mode = "host"; status = "okay"; }; @@ -374,7 +375,7 @@ pinctrl_usbotg2: usbotg2grp { fsl,pins = < - MX7D_PAD_UART3_RTS_B__USB_OTG2_OC 0x04 + MX7D_PAD_UART3_RTS_B__USB_OTG2_OC 0x5c >; }; diff --git a/arch/arm/boot/dts/nuvoton-wpcm450.dtsi b/arch/arm/boot/dts/nuvoton-wpcm450.dtsi index b637241316bb..fd671c7a1e5d 100644 --- a/arch/arm/boot/dts/nuvoton-wpcm450.dtsi +++ b/arch/arm/boot/dts/nuvoton-wpcm450.dtsi @@ -480,6 +480,7 @@ reg = <0xc8000000 0x1000>, <0xc0000000 0x4000000>; reg-names = "control", "memory"; clocks = <&clk 0>; + nuvoton,shm = <&shm>; status = "disabled"; }; diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile index 971e74546fb1..13e62c7c25dc 100644 --- a/arch/arm/crypto/Makefile +++ b/arch/arm/crypto/Makefile @@ -53,7 +53,12 @@ $(obj)/%-core.S: $(src)/%-armv4.pl clean-files += poly1305-core.S sha256-core.S sha512-core.S +aflags-thumb2-$(CONFIG_THUMB2_KERNEL) := -U__thumb2__ -D__thumb2__=1 + +AFLAGS_sha256-core.o += $(aflags-thumb2-y) +AFLAGS_sha512-core.o += $(aflags-thumb2-y) + # massage the perlasm code a bit so we only get the NEON routine if we need it poly1305-aflags-$(CONFIG_CPU_V7) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=5 poly1305-aflags-$(CONFIG_KERNEL_MODE_NEON) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=7 -AFLAGS_poly1305-core.o += $(poly1305-aflags-y) +AFLAGS_poly1305-core.o += $(poly1305-aflags-y) $(aflags-thumb2-y) diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index c1494a4dee25..53f2d8774fdb 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -161,7 +161,7 @@ void __init paging_init(const struct machine_desc *mdesc) mpu_setup(); /* allocate the zero page. */ - zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + zero_page = (void *)memblock_alloc(PAGE_SIZE, PAGE_SIZE); if (!zero_page) panic("%s: Failed to allocate %lu bytes align=0x%lx\n", __func__, PAGE_SIZE, PAGE_SIZE); diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index fa6999e24b07..e43f6d716b4b 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -6,6 +6,7 @@ * VM_EXEC */ #include <asm/asm-offsets.h> +#include <asm/pgtable.h> #include <asm/thread_info.h> #ifdef CONFIG_CPU_V7M diff --git a/arch/arm64/boot/dts/freescale/imx8dxl.dtsi b/arch/arm64/boot/dts/freescale/imx8dxl.dtsi index 0c64b9194621..214f21bd0cb4 100644 --- a/arch/arm64/boot/dts/freescale/imx8dxl.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8dxl.dtsi @@ -164,7 +164,7 @@ sc_pwrkey: keys { compatible = "fsl,imx8qxp-sc-key", "fsl,imx-sc-key"; - linux,keycode = <KEY_POWER>; + linux,keycodes = <KEY_POWER>; wakeup-source; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-data-modul-edm-sbc.dts b/arch/arm64/boot/dts/freescale/imx8mm-data-modul-edm-sbc.dts index 752f409a30b1..9889319d4f04 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-data-modul-edm-sbc.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-data-modul-edm-sbc.dts @@ -88,6 +88,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_watchdog_gpio>; compatible = "linux,wdt-gpio"; + always-running; gpios = <&gpio1 8 GPIO_ACTIVE_HIGH>; hw_algo = "level"; /* Reset triggers in 2..3 seconds */ diff --git a/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h b/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h index 83c8f715cd90..b1f11098d248 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h +++ b/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h @@ -602,7 +602,7 @@ #define MX8MM_IOMUXC_UART1_RXD_GPIO5_IO22 0x234 0x49C 0x000 0x5 0x0 #define MX8MM_IOMUXC_UART1_RXD_TPSMP_HDATA24 0x234 0x49C 0x000 0x7 0x0 #define MX8MM_IOMUXC_UART1_TXD_UART1_DCE_TX 0x238 0x4A0 0x000 0x0 0x0 -#define MX8MM_IOMUXC_UART1_TXD_UART1_DTE_RX 0x238 0x4A0 0x4F4 0x0 0x0 +#define MX8MM_IOMUXC_UART1_TXD_UART1_DTE_RX 0x238 0x4A0 0x4F4 0x0 0x1 #define MX8MM_IOMUXC_UART1_TXD_ECSPI3_MOSI 0x238 0x4A0 0x000 0x1 0x0 #define MX8MM_IOMUXC_UART1_TXD_GPIO5_IO23 0x238 0x4A0 0x000 0x5 0x0 #define MX8MM_IOMUXC_UART1_TXD_TPSMP_HDATA25 0x238 0x4A0 0x000 0x7 0x0 diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx-0x-rs232-rts.dtso b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx-0x-rs232-rts.dtso index 3ea73a6886ff..f6ad1a4b8b66 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx-0x-rs232-rts.dtso +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx-0x-rs232-rts.dtso @@ -33,7 +33,6 @@ pinctrl-0 = <&pinctrl_uart2>; rts-gpios = <&gpio5 29 GPIO_ACTIVE_LOW>; cts-gpios = <&gpio5 28 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx-0x-rs232-rts.dtso b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx-0x-rs232-rts.dtso index 2fa635e1c1a8..1f8ea20dfafc 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx-0x-rs232-rts.dtso +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx-0x-rs232-rts.dtso @@ -33,7 +33,6 @@ pinctrl-0 = <&pinctrl_uart2>; rts-gpios = <&gpio5 29 GPIO_ACTIVE_LOW>; cts-gpios = <&gpio5 28 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi index 244ef8d6cc68..7761d5671cb1 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi @@ -222,7 +222,6 @@ pinctrl-0 = <&pinctrl_uart3>, <&pinctrl_bten>; cts-gpios = <&gpio5 8 GPIO_ACTIVE_LOW>; rts-gpios = <&gpio5 9 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; bluetooth { diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts index 6433c205f8dd..64b366e83fa1 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts @@ -733,7 +733,6 @@ dtr-gpios = <&gpio1 14 GPIO_ACTIVE_LOW>; dsr-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>; dcd-gpios = <&gpio1 11 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; @@ -749,7 +748,6 @@ pinctrl-0 = <&pinctrl_uart3>, <&pinctrl_uart3_gpio>; cts-gpios = <&gpio4 10 GPIO_ACTIVE_LOW>; rts-gpios = <&gpio4 9 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; @@ -758,7 +756,6 @@ pinctrl-0 = <&pinctrl_uart4>, <&pinctrl_uart4_gpio>; cts-gpios = <&gpio5 11 GPIO_ACTIVE_LOW>; rts-gpios = <&gpio5 12 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7902.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7902.dts index 32872b0b1aaf..e8bc1fccc47b 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7902.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7902.dts @@ -664,7 +664,6 @@ pinctrl-0 = <&pinctrl_uart1>, <&pinctrl_uart1_gpio>; rts-gpios = <&gpio4 10 GPIO_ACTIVE_LOW>; cts-gpios = <&gpio4 24 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; @@ -681,7 +680,6 @@ pinctrl-0 = <&pinctrl_uart3>, <&pinctrl_uart3_gpio>; rts-gpios = <&gpio2 1 GPIO_ACTIVE_LOW>; cts-gpios = <&gpio2 0 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; bluetooth { @@ -699,7 +697,6 @@ dtr-gpios = <&gpio4 3 GPIO_ACTIVE_LOW>; dsr-gpios = <&gpio4 4 GPIO_ACTIVE_LOW>; dcd-gpios = <&gpio4 6 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts index 8ce562246a08..acc2ba8e00a8 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts @@ -581,7 +581,6 @@ dtr-gpios = <&gpio1 0 GPIO_ACTIVE_LOW>; dsr-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>; dcd-gpios = <&gpio3 24 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi index 0d454e0e2f7c..702d87621bb4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi @@ -98,6 +98,7 @@ off-on-delay = <500000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_reg_eth>; + regulator-always-on; regulator-boot-on; regulator-max-microvolt = <3300000>; regulator-min-microvolt = <3300000>; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-venice-gw7902.dts b/arch/arm64/boot/dts/freescale/imx8mn-venice-gw7902.dts index b9444e4a3d2d..7c12518dbc96 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-venice-gw7902.dts +++ b/arch/arm64/boot/dts/freescale/imx8mn-venice-gw7902.dts @@ -643,7 +643,6 @@ pinctrl-0 = <&pinctrl_uart3>, <&pinctrl_uart3_gpio>; rts-gpios = <&gpio2 1 GPIO_ACTIVE_LOW>; cts-gpios = <&gpio2 0 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; bluetooth { diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts index ceeca4966fc5..8eb7d5ee38da 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts @@ -623,7 +623,6 @@ pinctrl-0 = <&pinctrl_uart3>, <&pinctrl_uart3_gpio>; cts-gpios = <&gpio3 21 GPIO_ACTIVE_LOW>; rts-gpios = <&gpio3 22 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; bluetooth { diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 94a666dd1443..2642e9ce2819 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -2187,7 +2187,7 @@ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev, ((u64)ite->irq->intid << KVM_ITS_ITE_PINTID_SHIFT) | ite->collection->collection_id; val = cpu_to_le64(val); - return kvm_write_guest_lock(kvm, gpa, &val, ite_esz); + return vgic_write_guest_lock(kvm, gpa, &val, ite_esz); } /** @@ -2339,7 +2339,7 @@ static int vgic_its_save_dte(struct vgic_its *its, struct its_device *dev, (itt_addr_field << KVM_ITS_DTE_ITTADDR_SHIFT) | (dev->num_eventid_bits - 1)); val = cpu_to_le64(val); - return kvm_write_guest_lock(kvm, ptr, &val, dte_esz); + return vgic_write_guest_lock(kvm, ptr, &val, dte_esz); } /** @@ -2526,7 +2526,7 @@ static int vgic_its_save_cte(struct vgic_its *its, ((u64)collection->target_addr << KVM_ITS_CTE_RDBASE_SHIFT) | collection->collection_id); val = cpu_to_le64(val); - return kvm_write_guest_lock(its->dev->kvm, gpa, &val, esz); + return vgic_write_guest_lock(its->dev->kvm, gpa, &val, esz); } /* @@ -2607,7 +2607,7 @@ static int vgic_its_save_collection_table(struct vgic_its *its) */ val = 0; BUG_ON(cte_esz > sizeof(val)); - ret = kvm_write_guest_lock(its->dev->kvm, gpa, &val, cte_esz); + ret = vgic_write_guest_lock(its->dev->kvm, gpa, &val, cte_esz); return ret; } @@ -2743,7 +2743,6 @@ static int vgic_its_has_attr(struct kvm_device *dev, static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); - struct vgic_dist *dist = &kvm->arch.vgic; int ret = 0; if (attr == KVM_DEV_ARM_VGIC_CTRL_INIT) /* Nothing to do */ @@ -2763,9 +2762,7 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) vgic_its_reset(kvm, its); break; case KVM_DEV_ARM_ITS_SAVE_TABLES: - dist->save_its_tables_in_progress = true; ret = abi->save_tables(its); - dist->save_its_tables_in_progress = false; break; case KVM_DEV_ARM_ITS_RESTORE_TABLES: ret = abi->restore_tables(its); @@ -2792,7 +2789,7 @@ bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; - return dist->save_its_tables_in_progress; + return dist->table_write_in_progress; } static int vgic_its_set_attr(struct kvm_device *dev, diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 2624963cb95b..684bdfaad4a9 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -339,7 +339,7 @@ retry: if (status) { /* clear consumed data */ val &= ~(1 << bit_nr); - ret = kvm_write_guest_lock(kvm, ptr, &val, 1); + ret = vgic_write_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; } @@ -434,7 +434,7 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) else val &= ~(1 << bit_nr); - ret = kvm_write_guest_lock(kvm, ptr, &val, 1); + ret = vgic_write_guest_lock(kvm, ptr, &val, 1); if (ret) goto out; } diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index 23e280fa0a16..7f7f3c5ed85a 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -6,6 +6,7 @@ #define __KVM_ARM_VGIC_NEW_H__ #include <linux/irqchip/arm-gic-common.h> +#include <asm/kvm_mmu.h> #define PRODUCT_ID_KVM 0x4b /* ASCII code K */ #define IMPLEMENTER_ARM 0x43b @@ -131,6 +132,19 @@ static inline bool vgic_irq_is_multi_sgi(struct vgic_irq *irq) return vgic_irq_get_lr_count(irq) > 1; } +static inline int vgic_write_guest_lock(struct kvm *kvm, gpa_t gpa, + const void *data, unsigned long len) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + int ret; + + dist->table_write_in_progress = true; + ret = kvm_write_guest_lock(kvm, gpa, data, len); + dist->table_write_in_progress = false; + + return ret; +} + /* * This struct provides an intermediate representation of the fields contained * in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC diff --git a/arch/ia64/kernel/sys_ia64.c b/arch/ia64/kernel/sys_ia64.c index f6a502e8f02c..6e948d015332 100644 --- a/arch/ia64/kernel/sys_ia64.c +++ b/arch/ia64/kernel/sys_ia64.c @@ -170,6 +170,9 @@ ia64_mremap (unsigned long addr, unsigned long old_len, unsigned long new_len, u asmlinkage long ia64_clock_getres(const clockid_t which_clock, struct __kernel_timespec __user *tp) { + struct timespec64 rtn_tp; + s64 tick_ns; + /* * ia64's clock_gettime() syscall is implemented as a vdso call * fsys_clock_gettime(). Currently it handles only @@ -185,8 +188,8 @@ ia64_clock_getres(const clockid_t which_clock, struct __kernel_timespec __user * switch (which_clock) { case CLOCK_REALTIME: case CLOCK_MONOTONIC: - s64 tick_ns = DIV_ROUND_UP(NSEC_PER_SEC, local_cpu_data->itc_freq); - struct timespec64 rtn_tp = ns_to_timespec64(tick_ns); + tick_ns = DIV_ROUND_UP(NSEC_PER_SEC, local_cpu_data->itc_freq); + rtn_tp = ns_to_timespec64(tick_ns); return put_timespec64(&rtn_tp, tp); } diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index 4dfe1f49c5c8..6817892a2c58 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -1303,7 +1303,7 @@ static char iodc_dbuf[4096] __page_aligned_bss; */ int pdc_iodc_print(const unsigned char *str, unsigned count) { - unsigned int i; + unsigned int i, found = 0; unsigned long flags; count = min_t(unsigned int, count, sizeof(iodc_dbuf)); @@ -1315,6 +1315,7 @@ int pdc_iodc_print(const unsigned char *str, unsigned count) iodc_dbuf[i+0] = '\r'; iodc_dbuf[i+1] = '\n'; i += 2; + found = 1; goto print; default: iodc_dbuf[i] = str[i]; @@ -1330,7 +1331,7 @@ print: __pa(pdc_result), 0, __pa(iodc_dbuf), i, 0); spin_unlock_irqrestore(&pdc_lock, flags); - return i; + return i - found; } #if !defined(BOOTLOADER) diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index 69c62933e952..ceb45f51d52e 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -126,6 +126,12 @@ long arch_ptrace(struct task_struct *child, long request, unsigned long tmp; long ret = -EIO; + unsigned long user_regs_struct_size = sizeof(struct user_regs_struct); +#ifdef CONFIG_64BIT + if (is_compat_task()) + user_regs_struct_size /= 2; +#endif + switch (request) { /* Read the word at location addr in the USER area. For ptraced @@ -166,7 +172,7 @@ long arch_ptrace(struct task_struct *child, long request, addr >= sizeof(struct pt_regs)) break; if (addr == PT_IAOQ0 || addr == PT_IAOQ1) { - data |= 3; /* ensure userspace privilege */ + data |= PRIV_USER; /* ensure userspace privilege */ } if ((addr >= PT_GR1 && addr <= PT_GR31) || addr == PT_IAOQ0 || addr == PT_IAOQ1 || @@ -181,14 +187,14 @@ long arch_ptrace(struct task_struct *child, long request, return copy_regset_to_user(child, task_user_regset_view(current), REGSET_GENERAL, - 0, sizeof(struct user_regs_struct), + 0, user_regs_struct_size, datap); case PTRACE_SETREGS: /* Set all gp regs in the child. */ return copy_regset_from_user(child, task_user_regset_view(current), REGSET_GENERAL, - 0, sizeof(struct user_regs_struct), + 0, user_regs_struct_size, datap); case PTRACE_GETFPREGS: /* Get the child FPU state. */ @@ -285,7 +291,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, if (addr >= sizeof(struct pt_regs)) break; if (addr == PT_IAOQ0+4 || addr == PT_IAOQ1+4) { - data |= 3; /* ensure userspace privilege */ + data |= PRIV_USER; /* ensure userspace privilege */ } if (addr >= PT_FR0 && addr <= PT_FR31 + 4) { /* Special case, fp regs are 64 bits anyway */ @@ -302,6 +308,11 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, } } break; + case PTRACE_GETREGS: + case PTRACE_SETREGS: + case PTRACE_GETFPREGS: + case PTRACE_SETFPREGS: + return arch_ptrace(child, request, addr, data); default: ret = compat_ptrace_request(child, request, addr, data); @@ -484,7 +495,7 @@ static void set_reg(struct pt_regs *regs, int num, unsigned long val) case RI(iaoq[0]): case RI(iaoq[1]): /* set 2 lowest bits to ensure userspace privilege: */ - regs->iaoq[num - RI(iaoq[0])] = val | 3; + regs->iaoq[num - RI(iaoq[0])] = val | PRIV_USER; return; case RI(sar): regs->sar = val; return; diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h index dd39313242b4..d5cd16270c5d 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h @@ -97,6 +97,8 @@ static inline void tlb_flush(struct mmu_gather *tlb) { if (radix_enabled()) radix__tlb_flush(tlb); + + return hash__tlb_flush(tlb); } #ifdef CONFIG_SMP diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 77fa88c2aed0..eb6d094083fd 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -173,6 +173,15 @@ static inline notrace unsigned long irq_soft_mask_or_return(unsigned long mask) return flags; } +static inline notrace unsigned long irq_soft_mask_andc_return(unsigned long mask) +{ + unsigned long flags = irq_soft_mask_return(); + + irq_soft_mask_set(flags & ~mask); + + return flags; +} + static inline unsigned long arch_local_save_flags(void) { return irq_soft_mask_return(); @@ -192,7 +201,7 @@ static inline void arch_local_irq_enable(void) static inline unsigned long arch_local_irq_save(void) { - return irq_soft_mask_set_return(IRQS_DISABLED); + return irq_soft_mask_or_return(IRQS_DISABLED); } static inline bool arch_irqs_disabled_flags(unsigned long flags) @@ -331,10 +340,11 @@ bool power_pmu_wants_prompt_pmi(void); * is a different soft-masked interrupt pending that requires hard * masking. */ -static inline bool should_hard_irq_enable(void) +static inline bool should_hard_irq_enable(struct pt_regs *regs) { if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { - WARN_ON(irq_soft_mask_return() == IRQS_ENABLED); + WARN_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED); + WARN_ON(!(get_paca()->irq_happened & PACA_IRQ_HARD_DIS)); WARN_ON(mfmsr() & MSR_EE); } @@ -347,8 +357,17 @@ static inline bool should_hard_irq_enable(void) * * TODO: Add test for 64e */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !power_pmu_wants_prompt_pmi()) - return false; + if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) { + if (!power_pmu_wants_prompt_pmi()) + return false; + /* + * If PMIs are disabled then IRQs should be disabled as well, + * so we shouldn't see this condition, check for it just in + * case because we are about to enable PMIs. + */ + if (WARN_ON_ONCE(regs->softe & IRQS_PMI_DISABLED)) + return false; + } if (get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK) return false; @@ -358,18 +377,16 @@ static inline bool should_hard_irq_enable(void) /* * Do the hard enabling, only call this if should_hard_irq_enable is true. + * This allows PMI interrupts to profile irq handlers. */ static inline void do_hard_irq_enable(void) { - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { - WARN_ON(irq_soft_mask_return() == IRQS_ENABLED); - WARN_ON(get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK); - WARN_ON(mfmsr() & MSR_EE); - } /* - * This allows PMI interrupts (and watchdog soft-NMIs) through. - * There is no other reason to enable this way. + * Asynch interrupts come in with IRQS_ALL_DISABLED, + * PACA_IRQ_HARD_DIS, and MSR[EE]=0. */ + if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) + irq_soft_mask_andc_return(IRQS_PMI_DISABLED); get_paca()->irq_happened &= ~PACA_IRQ_HARD_DIS; __hard_irq_enable(); } @@ -452,7 +469,7 @@ static inline bool arch_irq_disabled_regs(struct pt_regs *regs) return !(regs->msr & MSR_EE); } -static __always_inline bool should_hard_irq_enable(void) +static __always_inline bool should_hard_irq_enable(struct pt_regs *regs) { return false; } diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c index f55c6fb34a3a..5712dd846263 100644 --- a/arch/powerpc/kernel/dbell.c +++ b/arch/powerpc/kernel/dbell.c @@ -27,7 +27,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception) ppc_msgsync(); - if (should_hard_irq_enable()) + if (should_hard_irq_enable(regs)) do_hard_irq_enable(); kvmppc_clear_host_ipi(smp_processor_id()); diff --git a/arch/powerpc/kernel/head_85xx.S b/arch/powerpc/kernel/head_85xx.S index d438ca74e96c..fdbee1093e2b 100644 --- a/arch/powerpc/kernel/head_85xx.S +++ b/arch/powerpc/kernel/head_85xx.S @@ -864,7 +864,7 @@ _GLOBAL(load_up_spe) * SPE unavailable trap from kernel - print a message, but let * the task use SPE in the kernel until it returns to user mode. */ -KernelSPE: +SYM_FUNC_START_LOCAL(KernelSPE) lwz r3,_MSR(r1) oris r3,r3,MSR_SPE@h stw r3,_MSR(r1) /* enable use of SPE after return */ @@ -881,6 +881,7 @@ KernelSPE: #endif .align 4,0 +SYM_FUNC_END(KernelSPE) #endif /* CONFIG_SPE */ /* diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index c5b9ce887483..c9535f2760b5 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -238,7 +238,7 @@ static void __do_irq(struct pt_regs *regs, unsigned long oldsp) irq = static_call(ppc_get_irq)(); /* We can hard enable interrupts now to allow perf interrupts */ - if (should_hard_irq_enable()) + if (should_hard_irq_enable(regs)) do_hard_irq_enable(); /* And finally process it */ diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index d68de3618741..e26eb6618ae5 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -515,7 +515,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) } /* Conditionally hard-enable interrupts. */ - if (should_hard_irq_enable()) { + if (should_hard_irq_enable(regs)) { /* * Ensure a positive value is written to the decrementer, or * else some CPUs will continue to take decrementer exceptions. diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index af8854f9eae3..52085751f5f4 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -989,10 +989,13 @@ unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image) * linux,drconf-usable-memory properties. Get an approximate on the * number of usable memory entries and use for FDT size estimation. */ - usm_entries = ((memblock_end_of_DRAM() / drmem_lmb_size()) + - (2 * (resource_size(&crashk_res) / drmem_lmb_size()))); - - extra_size = (unsigned int)(usm_entries * sizeof(u64)); + if (drmem_lmb_size()) { + usm_entries = ((memory_hotplug_max() / drmem_lmb_size()) + + (2 * (resource_size(&crashk_res) / drmem_lmb_size()))); + extra_size = (unsigned int)(usm_entries * sizeof(u64)); + } else { + extra_size = 0; + } /* * Get the number of CPU nodes in the current DT. This allows to diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 0dce93ccaadf..e89281d3ba28 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -912,16 +912,15 @@ static int kvmppc_handle_debug(struct kvm_vcpu *vcpu) static void kvmppc_fill_pt_regs(struct pt_regs *regs) { - ulong r1, ip, msr, lr; + ulong r1, msr, lr; asm("mr %0, 1" : "=r"(r1)); asm("mflr %0" : "=r"(lr)); asm("mfmsr %0" : "=r"(msr)); - asm("bl 1f; 1: mflr %0" : "=r"(ip)); memset(regs, 0, sizeof(*regs)); regs->gpr[1] = r1; - regs->nip = ip; + regs->nip = _THIS_IP_; regs->msr = msr; regs->link = lr; } diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index cac727b01799..26245aaf12b8 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -234,6 +234,14 @@ void radix__mark_rodata_ro(void) end = (unsigned long)__end_rodata; radix__change_memory_range(start, end, _PAGE_WRITE); + + for (start = PAGE_OFFSET; start < (unsigned long)_stext; start += PAGE_SIZE) { + end = start + PAGE_SIZE; + if (overlaps_interrupt_vector_text(start, end)) + radix__change_memory_range(start, end, _PAGE_WRITE); + else + break; + } } void radix__mark_initmem_nx(void) @@ -262,6 +270,22 @@ print_mapping(unsigned long start, unsigned long end, unsigned long size, bool e static unsigned long next_boundary(unsigned long addr, unsigned long end) { #ifdef CONFIG_STRICT_KERNEL_RWX + unsigned long stext_phys; + + stext_phys = __pa_symbol(_stext); + + // Relocatable kernel running at non-zero real address + if (stext_phys != 0) { + // The end of interrupts code at zero is a rodata boundary + unsigned long end_intr = __pa_symbol(__end_interrupts) - stext_phys; + if (addr < end_intr) + return end_intr; + + // Start of relocated kernel text is a rodata boundary + if (addr < stext_phys) + return stext_phys; + } + if (addr < __pa_symbol(__srwx_boundary)) return __pa_symbol(__srwx_boundary); #endif diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index 100e97daf76b..9d229ef7f86e 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -22,7 +22,7 @@ * Used to avoid races in counting the nest-pmu units during hotplug * register and unregister */ -static DEFINE_SPINLOCK(nest_init_lock); +static DEFINE_MUTEX(nest_init_lock); static DEFINE_PER_CPU(struct imc_pmu_ref *, local_nest_imc_refc); static struct imc_pmu **per_nest_pmu_arr; static cpumask_t nest_imc_cpumask; @@ -1629,7 +1629,7 @@ static void imc_common_mem_free(struct imc_pmu *pmu_ptr) static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr) { if (pmu_ptr->domain == IMC_DOMAIN_NEST) { - spin_lock(&nest_init_lock); + mutex_lock(&nest_init_lock); if (nest_pmus == 1) { cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE); kfree(nest_imc_refc); @@ -1639,7 +1639,7 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr) if (nest_pmus > 0) nest_pmus--; - spin_unlock(&nest_init_lock); + mutex_unlock(&nest_init_lock); } /* Free core_imc memory */ @@ -1796,11 +1796,11 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id * rest. To handle the cpuhotplug callback unregister, we track * the number of nest pmus in "nest_pmus". */ - spin_lock(&nest_init_lock); + mutex_lock(&nest_init_lock); if (nest_pmus == 0) { ret = init_nest_pmu_ref(); if (ret) { - spin_unlock(&nest_init_lock); + mutex_unlock(&nest_init_lock); kfree(per_nest_pmu_arr); per_nest_pmu_arr = NULL; goto err_free_mem; @@ -1808,7 +1808,7 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id /* Register for cpu hotplug notification. */ ret = nest_pmu_cpumask_init(); if (ret) { - spin_unlock(&nest_init_lock); + mutex_unlock(&nest_init_lock); kfree(nest_imc_refc); kfree(per_nest_pmu_arr); per_nest_pmu_arr = NULL; @@ -1816,7 +1816,7 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id } } nest_pmus++; - spin_unlock(&nest_init_lock); + mutex_unlock(&nest_init_lock); break; case IMC_DOMAIN_CORE: ret = core_imc_pmu_cpumask_init(); diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index faf2c2177094..82153960ac00 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -80,6 +80,9 @@ ifeq ($(CONFIG_PERF_EVENTS),y) KBUILD_CFLAGS += -fno-omit-frame-pointer endif +# Avoid generating .eh_frame sections. +KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables + KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax) KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax) diff --git a/arch/riscv/include/asm/alternative-macros.h b/arch/riscv/include/asm/alternative-macros.h index 7226e2462584..2c0f4c887289 100644 --- a/arch/riscv/include/asm/alternative-macros.h +++ b/arch/riscv/include/asm/alternative-macros.h @@ -46,7 +46,7 @@ .macro ALTERNATIVE_CFG_2 old_c, new_c_1, vendor_id_1, errata_id_1, enable_1, \ new_c_2, vendor_id_2, errata_id_2, enable_2 - ALTERNATIVE_CFG \old_c, \new_c_1, \vendor_id_1, \errata_id_1, \enable_1 + ALTERNATIVE_CFG "\old_c", "\new_c_1", \vendor_id_1, \errata_id_1, \enable_1 ALT_NEW_CONTENT \vendor_id_2, \errata_id_2, \enable_2, \new_c_2 .endm diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index 86328e3acb02..64ad1937e714 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -70,7 +70,6 @@ static_assert(RISCV_ISA_EXT_ID_MAX <= RISCV_ISA_EXT_MAX); */ enum riscv_isa_ext_key { RISCV_ISA_EXT_KEY_FPU, /* For 'F' and 'D' */ - RISCV_ISA_EXT_KEY_ZIHINTPAUSE, RISCV_ISA_EXT_KEY_SVINVAL, RISCV_ISA_EXT_KEY_MAX, }; @@ -91,8 +90,6 @@ static __always_inline int riscv_isa_ext2key(int num) return RISCV_ISA_EXT_KEY_FPU; case RISCV_ISA_EXT_d: return RISCV_ISA_EXT_KEY_FPU; - case RISCV_ISA_EXT_ZIHINTPAUSE: - return RISCV_ISA_EXT_KEY_ZIHINTPAUSE; case RISCV_ISA_EXT_SVINVAL: return RISCV_ISA_EXT_KEY_SVINVAL; default: diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h index fa70cfe507aa..14f5d27783b8 100644 --- a/arch/riscv/include/asm/vdso/processor.h +++ b/arch/riscv/include/asm/vdso/processor.h @@ -4,30 +4,26 @@ #ifndef __ASSEMBLY__ -#include <linux/jump_label.h> #include <asm/barrier.h> -#include <asm/hwcap.h> static inline void cpu_relax(void) { - if (!static_branch_likely(&riscv_isa_ext_keys[RISCV_ISA_EXT_KEY_ZIHINTPAUSE])) { #ifdef __riscv_muldiv - int dummy; - /* In lieu of a halt instruction, induce a long-latency stall. */ - __asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy)); + int dummy; + /* In lieu of a halt instruction, induce a long-latency stall. */ + __asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy)); #endif - } else { - /* - * Reduce instruction retirement. - * This assumes the PC changes. - */ -#ifdef CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE - __asm__ __volatile__ ("pause"); + +#ifdef __riscv_zihintpause + /* + * Reduce instruction retirement. + * This assumes the PC changes. + */ + __asm__ __volatile__ ("pause"); #else - /* Encoding of the pause instruction */ - __asm__ __volatile__ (".4byte 0x100000F"); + /* Encoding of the pause instruction */ + __asm__ __volatile__ (".4byte 0x100000F"); #endif - } barrier(); } diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index b865046e4dbb..4bf6c449d78b 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -326,7 +326,7 @@ clear_bss_done: call soc_early_init tail start_kernel -#if CONFIG_RISCV_BOOT_SPINWAIT +#ifdef CONFIG_RISCV_BOOT_SPINWAIT .Lsecondary_start: /* Set trap vector to spin forever to help debug */ la a3, .Lsecondary_park diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c index f21592d20306..41c7481afde3 100644 --- a/arch/riscv/kernel/probes/kprobes.c +++ b/arch/riscv/kernel/probes/kprobes.c @@ -48,6 +48,21 @@ static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs) post_kprobe_handler(p, kcb, regs); } +static bool __kprobes arch_check_kprobe(struct kprobe *p) +{ + unsigned long tmp = (unsigned long)p->addr - p->offset; + unsigned long addr = (unsigned long)p->addr; + + while (tmp <= addr) { + if (tmp == addr) + return true; + + tmp += GET_INSN_LENGTH(*(u16 *)tmp); + } + + return false; +} + int __kprobes arch_prepare_kprobe(struct kprobe *p) { unsigned long probe_addr = (unsigned long)p->addr; @@ -55,6 +70,9 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) if (probe_addr & 0x1) return -EILSEQ; + if (!arch_check_kprobe(p)) + return -EILSEQ; + /* copy instruction */ p->opcode = *p->addr; diff --git a/arch/riscv/kernel/probes/simulate-insn.c b/arch/riscv/kernel/probes/simulate-insn.c index d73e96f6ed7c..a20568bd1f1a 100644 --- a/arch/riscv/kernel/probes/simulate-insn.c +++ b/arch/riscv/kernel/probes/simulate-insn.c @@ -71,11 +71,11 @@ bool __kprobes simulate_jalr(u32 opcode, unsigned long addr, struct pt_regs *reg u32 rd_index = (opcode >> 7) & 0x1f; u32 rs1_index = (opcode >> 15) & 0x1f; - ret = rv_insn_reg_set_val(regs, rd_index, addr + 4); + ret = rv_insn_reg_get_val(regs, rs1_index, &base_addr); if (!ret) return ret; - ret = rv_insn_reg_get_val(regs, rs1_index, &base_addr); + ret = rv_insn_reg_set_val(regs, rd_index, addr + 4); if (!ret) return ret; diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 3373df413c88..ddb2afba6d25 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -39,7 +39,6 @@ static DECLARE_COMPLETION(cpu_running); void __init smp_prepare_boot_cpu(void) { - init_cpu_topology(); } void __init smp_prepare_cpus(unsigned int max_cpus) @@ -48,6 +47,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus) int ret; unsigned int curr_cpuid; + init_cpu_topology(); + curr_cpuid = smp_processor_id(); store_cpu_topology(curr_cpuid); numa_store_cpu_info(curr_cpuid); diff --git a/arch/s390/boot/decompressor.c b/arch/s390/boot/decompressor.c index 8dcd7af2911a..b519a1f045d8 100644 --- a/arch/s390/boot/decompressor.c +++ b/arch/s390/boot/decompressor.c @@ -80,6 +80,6 @@ void *decompress_kernel(void) void *output = (void *)decompress_offset; __decompress(_compressed_start, _compressed_end - _compressed_start, - NULL, NULL, output, 0, NULL, error); + NULL, NULL, output, vmlinux.image_size, NULL, error); return output; } diff --git a/arch/sh/include/asm/checksum_32.h b/arch/sh/include/asm/checksum_32.h index a6501b856f3e..2b5fa75b4651 100644 --- a/arch/sh/include/asm/checksum_32.h +++ b/arch/sh/include/asm/checksum_32.h @@ -7,6 +7,7 @@ */ #include <linux/in6.h> +#include <linux/uaccess.h> /* * computes the checksum of a memory block at buff, length len, diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S index 3161b9ccd2a5..b6276a3521d7 100644 --- a/arch/sh/kernel/vmlinux.lds.S +++ b/arch/sh/kernel/vmlinux.lds.S @@ -4,6 +4,7 @@ * Written by Niibe Yutaka and Paul Mundt */ OUTPUT_ARCH(sh) +#define RUNTIME_DISCARD_EXIT #include <asm/thread_info.h> #include <asm/cache.h> #include <asm/vmlinux.lds.h> diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 9cf07322875a..73ed982d4100 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -14,13 +14,13 @@ endif ifdef CONFIG_CC_IS_GCC RETPOLINE_CFLAGS := $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register) -RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch-cs-prefix) RETPOLINE_VDSO_CFLAGS := $(call cc-option,-mindirect-branch=thunk-inline -mindirect-branch-register) endif ifdef CONFIG_CC_IS_CLANG RETPOLINE_CFLAGS := -mretpoline-external-thunk RETPOLINE_VDSO_CFLAGS := -mretpoline endif +RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch-cs-prefix) ifdef CONFIG_RETHUNK RETHUNK_CFLAGS := -mfunction-return=thunk-extern diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index d4a314cc50d6..321a5011042d 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -180,6 +180,12 @@ void initialize_identity_maps(void *rmode) /* Load the new page-table. */ write_cr3(top_level_pgt); + + /* + * Now that the required page table mappings are established and a + * GHCB can be used, check for SNP guest/HV feature compatibility. + */ + snp_check_features(); } static pte_t *split_large_pmd(struct x86_mapping_info *info, diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 62208ec04ca4..20118fb7c53b 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -126,6 +126,7 @@ static inline void console_init(void) #ifdef CONFIG_AMD_MEM_ENCRYPT void sev_enable(struct boot_params *bp); +void snp_check_features(void); void sev_es_shutdown_ghcb(void); extern bool sev_es_check_ghcb_fault(unsigned long address); void snp_set_page_private(unsigned long paddr); @@ -143,6 +144,7 @@ static inline void sev_enable(struct boot_params *bp) if (bp) bp->cc_blob_address = 0; } +static inline void snp_check_features(void) { } static inline void sev_es_shutdown_ghcb(void) { } static inline bool sev_es_check_ghcb_fault(unsigned long address) { diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index c93930d5ccbd..d63ad8f99f83 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -208,6 +208,23 @@ void sev_es_shutdown_ghcb(void) error("Can't unmap GHCB page"); } +static void __noreturn sev_es_ghcb_terminate(struct ghcb *ghcb, unsigned int set, + unsigned int reason, u64 exit_info_2) +{ + u64 exit_info_1 = SVM_VMGEXIT_TERM_REASON(set, reason); + + vc_ghcb_invalidate(ghcb); + ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_TERM_REQUEST); + ghcb_set_sw_exit_info_1(ghcb, exit_info_1); + ghcb_set_sw_exit_info_2(ghcb, exit_info_2); + + sev_es_wr_ghcb_msr(__pa(ghcb)); + VMGEXIT(); + + while (true) + asm volatile("hlt\n" : : : "memory"); +} + bool sev_es_check_ghcb_fault(unsigned long address) { /* Check whether the fault was on the GHCB page */ @@ -270,6 +287,59 @@ static void enforce_vmpl0(void) sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0); } +/* + * SNP_FEATURES_IMPL_REQ is the mask of SNP features that will need + * guest side implementation for proper functioning of the guest. If any + * of these features are enabled in the hypervisor but are lacking guest + * side implementation, the behavior of the guest will be undefined. The + * guest could fail in non-obvious way making it difficult to debug. + * + * As the behavior of reserved feature bits is unknown to be on the + * safe side add them to the required features mask. + */ +#define SNP_FEATURES_IMPL_REQ (MSR_AMD64_SNP_VTOM | \ + MSR_AMD64_SNP_REFLECT_VC | \ + MSR_AMD64_SNP_RESTRICTED_INJ | \ + MSR_AMD64_SNP_ALT_INJ | \ + MSR_AMD64_SNP_DEBUG_SWAP | \ + MSR_AMD64_SNP_VMPL_SSS | \ + MSR_AMD64_SNP_SECURE_TSC | \ + MSR_AMD64_SNP_VMGEXIT_PARAM | \ + MSR_AMD64_SNP_VMSA_REG_PROTECTION | \ + MSR_AMD64_SNP_RESERVED_BIT13 | \ + MSR_AMD64_SNP_RESERVED_BIT15 | \ + MSR_AMD64_SNP_RESERVED_MASK) + +/* + * SNP_FEATURES_PRESENT is the mask of SNP features that are implemented + * by the guest kernel. As and when a new feature is implemented in the + * guest kernel, a corresponding bit should be added to the mask. + */ +#define SNP_FEATURES_PRESENT (0) + +void snp_check_features(void) +{ + u64 unsupported; + + if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + return; + + /* + * Terminate the boot if hypervisor has enabled any feature lacking + * guest side implementation. Pass on the unsupported features mask through + * EXIT_INFO_2 of the GHCB protocol so that those features can be reported + * as part of the guest boot failure. + */ + unsupported = sev_status & SNP_FEATURES_IMPL_REQ & ~SNP_FEATURES_PRESENT; + if (unsupported) { + if (ghcb_version < 2 || (!boot_ghcb && !early_setup_ghcb())) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); + + sev_es_ghcb_terminate(boot_ghcb, SEV_TERM_SET_GEN, + GHCB_SNP_UNSUPPORTED, unsupported); + } +} + void sev_enable(struct boot_params *bp) { unsigned int eax, ebx, ecx, edx; diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 65064d9f7fa6..8eb74cf386db 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -14,6 +14,7 @@ #include <asm/mmu.h> #include <asm/mpspec.h> #include <asm/x86_init.h> +#include <asm/cpufeature.h> #ifdef CONFIG_ACPI_APEI # include <asm/pgtable_types.h> @@ -63,6 +64,13 @@ extern int (*acpi_suspend_lowlevel)(void); /* Physical address to resume after wakeup */ unsigned long acpi_get_wakeup_address(void); +static inline bool acpi_skip_set_wakeup_address(void) +{ + return cpu_feature_enabled(X86_FEATURE_XENPV); +} + +#define acpi_skip_set_wakeup_address acpi_skip_set_wakeup_address + /* * Check if the CPU can handle C2 and deeper */ diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index b049d950612f..ca97442e8d49 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -39,7 +39,20 @@ static __always_inline unsigned long native_get_debugreg(int regno) asm("mov %%db6, %0" :"=r" (val)); break; case 7: - asm("mov %%db7, %0" :"=r" (val)); + /* + * Apply __FORCE_ORDER to DR7 reads to forbid re-ordering them + * with other code. + * + * This is needed because a DR7 access can cause a #VC exception + * when running under SEV-ES. Taking a #VC exception is not a + * safe thing to do just anywhere in the entry code and + * re-ordering might place the access into an unsafe location. + * + * This happened in the NMI handler, where the DR7 read was + * re-ordered to happen before the call to sev_es_ist_enter(), + * causing stack recursion. + */ + asm volatile("mov %%db7, %0" : "=r" (val) : __FORCE_ORDER); break; default: BUG(); @@ -66,7 +79,16 @@ static __always_inline void native_set_debugreg(int regno, unsigned long value) asm("mov %0, %%db6" ::"r" (value)); break; case 7: - asm("mov %0, %%db7" ::"r" (value)); + /* + * Apply __FORCE_ORDER to DR7 writes to forbid re-ordering them + * with other code. + * + * While is didn't happen with a DR7 write (see the DR7 read + * comment above which explains where it happened), add the + * __FORCE_ORDER here too to avoid similar problems in the + * future. + */ + asm volatile("mov %0, %%db7" ::"r" (value), __FORCE_ORDER); break; default: BUG(); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 37ff47552bcb..d3fe82c5d6b6 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -566,6 +566,26 @@ #define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) #define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT) +/* SNP feature bits enabled by the hypervisor */ +#define MSR_AMD64_SNP_VTOM BIT_ULL(3) +#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(4) +#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(5) +#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(6) +#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(7) +#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(8) +#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(9) +#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(10) +#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(11) +#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(12) +#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(14) +#define MSR_AMD64_SNP_VMSA_REG_PROTECTION BIT_ULL(16) +#define MSR_AMD64_SNP_SMT_PROTECTION BIT_ULL(17) + +/* SNP feature bits reserved for future use. */ +#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13) +#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15) +#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, 18) + #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f /* AMD Collaborative Processor Performance Control MSRs */ diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index f69c168391aa..80e1df482337 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -116,6 +116,12 @@ #define SVM_VMGEXIT_AP_CREATE 1 #define SVM_VMGEXIT_AP_DESTROY 2 #define SVM_VMGEXIT_HV_FEATURES 0x8000fffd +#define SVM_VMGEXIT_TERM_REQUEST 0x8000fffe +#define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code) \ + /* SW_EXITINFO1[3:0] */ \ + (((((u64)reason_set) & 0xf)) | \ + /* SW_EXITINFO1[11:4] */ \ + ((((u64)reason_code) & 0xff) << 4)) #define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff /* Exit code reserved for hypervisor/software use */ diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 3aa5304200c5..4d8aff05a509 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -114,6 +114,7 @@ static void make_8259A_irq(unsigned int irq) disable_irq_nosync(irq); io_apic_irqs &= ~(1<<irq); irq_set_chip_and_handler(irq, &i8259A_chip, handle_level_irq); + irq_set_status_flags(irq, IRQ_LEVEL); enable_irq(irq); lapic_assign_legacy_vector(irq, true); } diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index beb1bada1b0a..c683666876f1 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -65,8 +65,10 @@ void __init init_ISA_irqs(void) legacy_pic->init(0); - for (i = 0; i < nr_legacy_irqs(); i++) + for (i = 0; i < nr_legacy_irqs(); i++) { irq_set_chip_and_handler(i, chip, handle_level_irq); + irq_set_status_flags(i, IRQ_LEVEL); + } } void __init init_IRQ(void) diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index b94f727251b6..8babce71915f 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -392,6 +392,7 @@ static void xen_teardown_msi_irqs(struct pci_dev *dev) msi_for_each_desc(msidesc, &dev->dev, MSI_DESC_ASSOCIATED) { for (i = 0; i < msidesc->nvec_used; i++) xen_destroy_irq(msidesc->irq + i); + msidesc->irq = 0; } } @@ -433,6 +434,7 @@ static struct msi_domain_ops xen_pci_msi_domain_ops = { }; static struct msi_domain_info xen_pci_msi_domain_info = { + .flags = MSI_FLAG_PCI_MSIX | MSI_FLAG_FREE_MSI_DESCS | MSI_FLAG_DEV_SYSFS, .ops = &xen_pci_msi_domain_ops, }; diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 7d9b15f0dbd5..0fbde0fc0628 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -769,8 +769,8 @@ static void __bfq_bic_change_cgroup(struct bfq_data *bfqd, * request from the old cgroup. */ bfq_put_cooperator(sync_bfqq); - bfq_release_process_ref(bfqd, sync_bfqq); bic_set_bfqq(bic, NULL, true); + bfq_release_process_ref(bfqd, sync_bfqq); } } } diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index ccf2204477a5..380e9bda2e57 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5425,9 +5425,11 @@ static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio) bfqq = bic_to_bfqq(bic, false); if (bfqq) { - bfq_release_process_ref(bfqd, bfqq); + struct bfq_queue *old_bfqq = bfqq; + bfqq = bfq_get_queue(bfqd, bio, false, bic, true); bic_set_bfqq(bic, bfqq, false); + bfq_release_process_ref(bfqd, old_bfqq); } bfqq = bic_to_bfqq(bic, true); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 4c94a6560f62..9ac1efb053e0 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -2001,6 +2001,10 @@ void blk_cgroup_bio_start(struct bio *bio) struct blkg_iostat_set *bis; unsigned long flags; + /* Root-level stats are sourced from system-wide IO stats */ + if (!cgroup_parent(blkcg->css.cgroup)) + return; + cpu = get_cpu(); bis = per_cpu_ptr(bio->bi_blkg->iostat_cpu, cpu); flags = u64_stats_update_begin_irqsave(&bis->sync); diff --git a/block/blk-mq.c b/block/blk-mq.c index 9d463f7563bc..9c8dc70020bc 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -4069,8 +4069,9 @@ EXPORT_SYMBOL(blk_mq_init_queue); * blk_mq_destroy_queue - shutdown a request queue * @q: request queue to shutdown * - * This shuts down a request queue allocated by blk_mq_init_queue() and drops - * the initial reference. All future requests will failed with -ENODEV. + * This shuts down a request queue allocated by blk_mq_init_queue(). All future + * requests will be failed with -ENODEV. The caller is responsible for dropping + * the reference from blk_mq_init_queue() by calling blk_put_queue(). * * Context: can sleep */ diff --git a/certs/Makefile b/certs/Makefile index 9486ed924731..799ad7b9e68a 100644 --- a/certs/Makefile +++ b/certs/Makefile @@ -23,8 +23,8 @@ $(obj)/blacklist_hash_list: $(CONFIG_SYSTEM_BLACKLIST_HASH_LIST) FORCE targets += blacklist_hash_list quiet_cmd_extract_certs = CERT $@ - cmd_extract_certs = $(obj)/extract-cert $(extract-cert-in) $@ -extract-cert-in = $(or $(filter-out $(obj)/extract-cert, $(real-prereqs)),"") + cmd_extract_certs = $(obj)/extract-cert "$(extract-cert-in)" $@ +extract-cert-in = $(filter-out $(obj)/extract-cert, $(real-prereqs)) $(obj)/system_certificates.o: $(obj)/x509_certificate_list diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 0b557c0d405e..4ca667251272 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -60,13 +60,17 @@ static struct notifier_block tts_notifier = { .priority = 0, }; +#ifndef acpi_skip_set_wakeup_address +#define acpi_skip_set_wakeup_address() false +#endif + static int acpi_sleep_prepare(u32 acpi_state) { #ifdef CONFIG_ACPI_SLEEP unsigned long acpi_wakeup_address; /* do we have a wakeup address for S2 and S3? */ - if (acpi_state == ACPI_STATE_S3) { + if (acpi_state == ACPI_STATE_S3 && !acpi_skip_set_wakeup_address()) { acpi_wakeup_address = acpi_get_wakeup_address(); if (!acpi_wakeup_address) return -EFAULT; diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 65cec7bb6d96..a8c02608dde4 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -110,26 +110,6 @@ static bool nvidia_wmi_ec_supported(void) } #endif -static bool apple_gmux_backlight_present(void) -{ - struct acpi_device *adev; - struct device *dev; - - adev = acpi_dev_get_first_match_dev(GMUX_ACPI_HID, NULL, -1); - if (!adev) - return false; - - dev = acpi_get_first_physical_node(adev); - if (!dev) - return false; - - /* - * drivers/platform/x86/apple-gmux.c only supports old style - * Apple GMUX with an IO-resource. - */ - return pnp_get_resource(to_pnp_dev(dev), IORESOURCE_IO, 0) != NULL; -} - /* Force to use vendor driver when the ACPI device is known to be * buggy */ static int video_detect_force_vendor(const struct dmi_system_id *d) @@ -612,6 +592,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_native, + /* Asus U46E */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "U46E"), + }, + }, + { + .callback = video_detect_force_native, /* Asus UX303UB */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), @@ -620,6 +608,23 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_native, + /* HP EliteBook 8460p */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 8460p"), + }, + }, + { + .callback = video_detect_force_native, + /* HP Pavilion g6-1d80nr / B4U19UA */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion g6 Notebook PC"), + DMI_MATCH(DMI_PRODUCT_SKU, "B4U19UA"), + }, + }, + { + .callback = video_detect_force_native, /* Samsung N150P */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), @@ -766,6 +771,7 @@ static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native) { static DEFINE_MUTEX(init_mutex); static bool nvidia_wmi_ec_present; + static bool apple_gmux_present; static bool native_available; static bool init_done; static long video_caps; @@ -779,6 +785,7 @@ static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native) ACPI_UINT32_MAX, find_video, NULL, &video_caps, NULL); nvidia_wmi_ec_present = nvidia_wmi_ec_supported(); + apple_gmux_present = apple_gmux_detect(NULL, NULL); init_done = true; } if (native) @@ -800,7 +807,7 @@ static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native) if (nvidia_wmi_ec_present) return acpi_backlight_nvidia_wmi_ec; - if (apple_gmux_backlight_present()) + if (apple_gmux_present) return acpi_backlight_apple_gmux; /* Use ACPI video if available, except when native should be preferred. */ diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 884ae73b11ea..2ea572628b1c 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -3109,7 +3109,7 @@ int sata_down_spd_limit(struct ata_link *link, u32 spd_limit) */ if (spd > 1) mask &= (1 << (spd - 1)) - 1; - else + else if (link->sata_spd) return -EINVAL; /* were we already at the bottom? */ diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 17b677b5d3b2..6368b56eacf1 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -137,7 +137,7 @@ struct ublk_device { char *__queues; - unsigned short queue_size; + unsigned int queue_size; struct ublksrv_ctrl_dev_info dev_info; struct blk_mq_tag_set tag_set; @@ -2092,13 +2092,12 @@ static void __exit ublk_exit(void) struct ublk_device *ub; int id; - class_destroy(ublk_chr_class); - - misc_deregister(&ublk_misc); - idr_for_each_entry(&ublk_index_idr, ub, id) ublk_remove(ub); + class_destroy(ublk_chr_class); + misc_deregister(&ublk_misc); + idr_destroy(&ublk_index_idr); unregister_chrdev_region(ublk_chr_devt, UBLK_MINORS); } diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c index 3aa91aed3bf7..226e87b85116 100644 --- a/drivers/bus/sunxi-rsb.c +++ b/drivers/bus/sunxi-rsb.c @@ -857,7 +857,13 @@ static int __init sunxi_rsb_init(void) return ret; } - return platform_driver_register(&sunxi_rsb_driver); + ret = platform_driver_register(&sunxi_rsb_driver); + if (ret) { + bus_unregister(&sunxi_rsb_bus); + return ret; + } + + return 0; } module_init(sunxi_rsb_init); diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c index ad0849af42d7..13cde44c6086 100644 --- a/drivers/cxl/acpi.c +++ b/drivers/cxl/acpi.c @@ -736,4 +736,3 @@ module_exit(cxl_acpi_exit); MODULE_LICENSE("GPL v2"); MODULE_IMPORT_NS(CXL); MODULE_IMPORT_NS(ACPI); -MODULE_SOFTDEP("pre: cxl_pmem"); diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c index f3d2169b6731..c2e4b1093788 100644 --- a/drivers/cxl/core/pmem.c +++ b/drivers/cxl/core/pmem.c @@ -227,34 +227,16 @@ static struct cxl_nvdimm *cxl_nvdimm_alloc(struct cxl_nvdimm_bridge *cxl_nvb, return cxl_nvd; } -static void cxl_nvd_unregister(void *_cxl_nvd) +static void cxlmd_release_nvdimm(void *_cxlmd) { - struct cxl_nvdimm *cxl_nvd = _cxl_nvd; - struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_memdev *cxlmd = _cxlmd; + struct cxl_nvdimm *cxl_nvd = cxlmd->cxl_nvd; struct cxl_nvdimm_bridge *cxl_nvb = cxlmd->cxl_nvb; - /* - * Either the bridge is in ->remove() context under the device_lock(), - * or cxlmd_release_nvdimm() is cancelling the bridge's release action - * for @cxl_nvd and doing it itself (while manually holding the bridge - * lock). - */ - device_lock_assert(&cxl_nvb->dev); cxl_nvd->cxlmd = NULL; cxlmd->cxl_nvd = NULL; + cxlmd->cxl_nvb = NULL; device_unregister(&cxl_nvd->dev); -} - -static void cxlmd_release_nvdimm(void *_cxlmd) -{ - struct cxl_memdev *cxlmd = _cxlmd; - struct cxl_nvdimm_bridge *cxl_nvb = cxlmd->cxl_nvb; - - device_lock(&cxl_nvb->dev); - if (cxlmd->cxl_nvd) - devm_release_action(&cxl_nvb->dev, cxl_nvd_unregister, - cxlmd->cxl_nvd); - device_unlock(&cxl_nvb->dev); put_device(&cxl_nvb->dev); } @@ -293,22 +275,6 @@ int devm_cxl_add_nvdimm(struct cxl_memdev *cxlmd) dev_dbg(&cxlmd->dev, "register %s\n", dev_name(dev)); - /* - * The two actions below arrange for @cxl_nvd to be deleted when either - * the top-level PMEM bridge goes down, or the endpoint device goes - * through ->remove(). - */ - device_lock(&cxl_nvb->dev); - if (cxl_nvb->dev.driver) - rc = devm_add_action_or_reset(&cxl_nvb->dev, cxl_nvd_unregister, - cxl_nvd); - else - rc = -ENXIO; - device_unlock(&cxl_nvb->dev); - - if (rc) - goto err_alloc; - /* @cxlmd carries a reference on @cxl_nvb until cxlmd_release_nvdimm */ return devm_add_action_or_reset(&cxlmd->dev, cxlmd_release_nvdimm, cxlmd); diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 33083a522fd1..258004f34281 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -554,8 +554,11 @@ static bool cxl_report_and_clear(struct cxl_dev_state *cxlds) /* If multiple errors, log header points to first error from ctrl reg */ if (hweight32(status) > 1) { - addr = cxlds->regs.ras + CXL_RAS_CAP_CONTROL_OFFSET; - fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK, readl(addr))); + void __iomem *rcc_addr = + cxlds->regs.ras + CXL_RAS_CAP_CONTROL_OFFSET; + + fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK, + readl(rcc_addr))); } else { fe = status; } diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c index eedefebc4283..08bbbac9a6d0 100644 --- a/drivers/cxl/pmem.c +++ b/drivers/cxl/pmem.c @@ -225,11 +225,35 @@ static int cxl_pmem_ctl(struct nvdimm_bus_descriptor *nd_desc, return cxl_pmem_nvdimm_ctl(nvdimm, cmd, buf, buf_len); } +static int detach_nvdimm(struct device *dev, void *data) +{ + struct cxl_nvdimm *cxl_nvd; + bool release = false; + + if (!is_cxl_nvdimm(dev)) + return 0; + + device_lock(dev); + if (!dev->driver) + goto out; + + cxl_nvd = to_cxl_nvdimm(dev); + if (cxl_nvd->cxlmd && cxl_nvd->cxlmd->cxl_nvb == data) + release = true; +out: + device_unlock(dev); + if (release) + device_release_driver(dev); + return 0; +} + static void unregister_nvdimm_bus(void *_cxl_nvb) { struct cxl_nvdimm_bridge *cxl_nvb = _cxl_nvb; struct nvdimm_bus *nvdimm_bus = cxl_nvb->nvdimm_bus; + bus_for_each_dev(&cxl_bus_type, NULL, cxl_nvb, detach_nvdimm); + cxl_nvb->nvdimm_bus = NULL; nvdimm_bus_unregister(nvdimm_bus); } diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index 406b4e26f538..0de0482cd36e 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -167,7 +167,7 @@ struct dma_fence *dma_fence_allocate_private_stub(void) 0, 0); set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, - &dma_fence_stub.flags); + &fence->flags); dma_fence_signal(fence); diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index 9c89f7d53e99..958aa4662ccb 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -819,8 +819,10 @@ static int ioctl_send_response(struct client *client, union ioctl_arg *arg) r = container_of(resource, struct inbound_transaction_resource, resource); - if (is_fcp_request(r->request)) + if (is_fcp_request(r->request)) { + kfree(r->data); goto out; + } if (a->length != fw_get_response_length(r->request)) { ret = -EINVAL; diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index a2b0cbc8741c..1e0b016fdc2b 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -1007,6 +1007,8 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size) /* first try to find a slot in an existing linked list entry */ for (prsv = efi_memreserve_root->next; prsv; ) { rsv = memremap(prsv, sizeof(*rsv), MEMREMAP_WB); + if (!rsv) + return -ENOMEM; index = atomic_fetch_add_unless(&rsv->count, 1, rsv->size); if (index < rsv->size) { rsv->entry[index].base = addr; diff --git a/drivers/firmware/efi/memattr.c b/drivers/firmware/efi/memattr.c index 0a9aba5f9cef..f178b2984dfb 100644 --- a/drivers/firmware/efi/memattr.c +++ b/drivers/firmware/efi/memattr.c @@ -33,7 +33,7 @@ int __init efi_memattr_init(void) return -ENOMEM; } - if (tbl->version > 1) { + if (tbl->version > 2) { pr_warn("Unexpected EFI Memory Attributes table version %d\n", tbl->version); goto unmap; diff --git a/drivers/fpga/intel-m10-bmc-sec-update.c b/drivers/fpga/intel-m10-bmc-sec-update.c index 79d48852825e..03f1bd81c434 100644 --- a/drivers/fpga/intel-m10-bmc-sec-update.c +++ b/drivers/fpga/intel-m10-bmc-sec-update.c @@ -574,20 +574,27 @@ static int m10bmc_sec_probe(struct platform_device *pdev) len = scnprintf(buf, SEC_UPDATE_LEN_MAX, "secure-update%d", sec->fw_name_id); sec->fw_name = kmemdup_nul(buf, len, GFP_KERNEL); - if (!sec->fw_name) - return -ENOMEM; + if (!sec->fw_name) { + ret = -ENOMEM; + goto fw_name_fail; + } fwl = firmware_upload_register(THIS_MODULE, sec->dev, sec->fw_name, &m10bmc_ops, sec); if (IS_ERR(fwl)) { dev_err(sec->dev, "Firmware Upload driver failed to start\n"); - kfree(sec->fw_name); - xa_erase(&fw_upload_xa, sec->fw_name_id); - return PTR_ERR(fwl); + ret = PTR_ERR(fwl); + goto fw_uploader_fail; } sec->fwl = fwl; return 0; + +fw_uploader_fail: + kfree(sec->fw_name); +fw_name_fail: + xa_erase(&fw_upload_xa, sec->fw_name_id); + return ret; } static int m10bmc_sec_remove(struct platform_device *pdev) diff --git a/drivers/fpga/stratix10-soc.c b/drivers/fpga/stratix10-soc.c index 357cea58ec98..f7f01982a512 100644 --- a/drivers/fpga/stratix10-soc.c +++ b/drivers/fpga/stratix10-soc.c @@ -213,9 +213,9 @@ static int s10_ops_write_init(struct fpga_manager *mgr, /* Allocate buffers from the service layer's pool. */ for (i = 0; i < NUM_SVC_BUFS; i++) { kbuf = stratix10_svc_allocate_memory(priv->chan, SVC_BUF_SIZE); - if (!kbuf) { + if (IS_ERR(kbuf)) { s10_free_buffers(mgr); - ret = -ENOMEM; + ret = PTR_ERR(kbuf); goto init_done; } diff --git a/drivers/gpio/gpio-ep93xx.c b/drivers/gpio/gpio-ep93xx.c index 2e1779709113..6cedf46efec6 100644 --- a/drivers/gpio/gpio-ep93xx.c +++ b/drivers/gpio/gpio-ep93xx.c @@ -17,6 +17,7 @@ #include <linux/slab.h> #include <linux/gpio/driver.h> #include <linux/bitops.h> +#include <linux/seq_file.h> #define EP93XX_GPIO_F_INT_STATUS 0x5c #define EP93XX_GPIO_A_INT_STATUS 0xa0 @@ -40,7 +41,6 @@ #define EP93XX_GPIO_F_IRQ_BASE 80 struct ep93xx_gpio_irq_chip { - struct irq_chip ic; u8 irq_offset; u8 int_unmasked; u8 int_enabled; @@ -148,7 +148,7 @@ static void ep93xx_gpio_f_irq_handler(struct irq_desc *desc) */ struct irq_chip *irqchip = irq_desc_get_chip(desc); unsigned int irq = irq_desc_get_irq(desc); - int port_f_idx = ((irq + 1) & 7) ^ 4; /* {19..22,47..50} -> {0..7} */ + int port_f_idx = (irq & 7) ^ 4; /* {20..23,48..51} -> {0..7} */ int gpio_irq = EP93XX_GPIO_F_IRQ_BASE + port_f_idx; chained_irq_enter(irqchip, desc); @@ -185,6 +185,7 @@ static void ep93xx_gpio_irq_mask_ack(struct irq_data *d) ep93xx_gpio_update_int_params(epg, eic); writeb(port_mask, epg->base + eic->irq_offset + EP93XX_INT_EOI_OFFSET); + gpiochip_disable_irq(gc, irqd_to_hwirq(d)); } static void ep93xx_gpio_irq_mask(struct irq_data *d) @@ -195,6 +196,7 @@ static void ep93xx_gpio_irq_mask(struct irq_data *d) eic->int_unmasked &= ~BIT(d->irq & 7); ep93xx_gpio_update_int_params(epg, eic); + gpiochip_disable_irq(gc, irqd_to_hwirq(d)); } static void ep93xx_gpio_irq_unmask(struct irq_data *d) @@ -203,6 +205,7 @@ static void ep93xx_gpio_irq_unmask(struct irq_data *d) struct ep93xx_gpio_irq_chip *eic = to_ep93xx_gpio_irq_chip(gc); struct ep93xx_gpio *epg = gpiochip_get_data(gc); + gpiochip_enable_irq(gc, irqd_to_hwirq(d)); eic->int_unmasked |= BIT(d->irq & 7); ep93xx_gpio_update_int_params(epg, eic); } @@ -320,15 +323,25 @@ static int ep93xx_gpio_set_config(struct gpio_chip *gc, unsigned offset, return 0; } -static void ep93xx_init_irq_chip(struct device *dev, struct irq_chip *ic) +static void ep93xx_irq_print_chip(struct irq_data *data, struct seq_file *p) { - ic->irq_ack = ep93xx_gpio_irq_ack; - ic->irq_mask_ack = ep93xx_gpio_irq_mask_ack; - ic->irq_mask = ep93xx_gpio_irq_mask; - ic->irq_unmask = ep93xx_gpio_irq_unmask; - ic->irq_set_type = ep93xx_gpio_irq_type; + struct gpio_chip *gc = irq_data_get_irq_chip_data(data); + + seq_printf(p, dev_name(gc->parent)); } +static const struct irq_chip gpio_eic_irq_chip = { + .name = "ep93xx-gpio-eic", + .irq_ack = ep93xx_gpio_irq_ack, + .irq_mask = ep93xx_gpio_irq_mask, + .irq_unmask = ep93xx_gpio_irq_unmask, + .irq_mask_ack = ep93xx_gpio_irq_mask_ack, + .irq_set_type = ep93xx_gpio_irq_type, + .irq_print_chip = ep93xx_irq_print_chip, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + static int ep93xx_gpio_add_bank(struct ep93xx_gpio_chip *egc, struct platform_device *pdev, struct ep93xx_gpio *epg, @@ -350,8 +363,6 @@ static int ep93xx_gpio_add_bank(struct ep93xx_gpio_chip *egc, girq = &gc->irq; if (bank->has_irq || bank->has_hierarchical_irq) { - struct irq_chip *ic; - gc->set_config = ep93xx_gpio_set_config; egc->eic = devm_kcalloc(dev, 1, sizeof(*egc->eic), @@ -359,12 +370,7 @@ static int ep93xx_gpio_add_bank(struct ep93xx_gpio_chip *egc, if (!egc->eic) return -ENOMEM; egc->eic->irq_offset = bank->irq; - ic = &egc->eic->ic; - ic->name = devm_kasprintf(dev, GFP_KERNEL, "gpio-irq-%s", bank->label); - if (!ic->name) - return -ENOMEM; - ep93xx_init_irq_chip(dev, ic); - girq->chip = ic; + gpio_irq_chip_set_chip(girq, &gpio_eic_irq_chip); } if (bank->has_irq) { diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c index 6f673b2f2a1b..9d0cec4b82a3 100644 --- a/drivers/gpio/gpio-mxc.c +++ b/drivers/gpio/gpio-mxc.c @@ -249,10 +249,11 @@ static void mxc_flip_edge(struct mxc_gpio_port *port, u32 gpio) } else { pr_err("mxc: invalid configuration for GPIO %d: %x\n", gpio, edge); - return; + goto unlock; } writel(val | (edge << (bit << 1)), reg); +unlock: raw_spin_unlock_irqrestore(&port->gc.bgpio_lock, flags); } diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 9ef0f5641b52..17c53f484280 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -1104,7 +1104,8 @@ int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *name, in dev_dbg(&adev->dev, "IRQ %d already in use\n", irq); } - if (wake_capable) + /* avoid suspend issues with GPIOs when systems are using S3 */ + if (wake_capable && acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0) *wake_capable = info.wake_capable; return irq; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index b9b57a66e113..66eb102cd88f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -790,8 +790,8 @@ static void gfx_v11_0_read_wave_data(struct amdgpu_device *adev, uint32_t simd, * zero here */ WARN_ON(simd != 0); - /* type 2 wave data */ - dst[(*no_fields)++] = 2; + /* type 3 wave data */ + dst[(*no_fields)++] = 3; dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_STATUS); dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_PC_LO); dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_PC_HI); diff --git a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c index 95548c512f4f..077c53c6cc08 100644 --- a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c @@ -35,6 +35,7 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_0_imu.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_1_imu.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_2_imu.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_3_imu.bin"); +MODULE_FIRMWARE("amdgpu/gc_11_0_4_imu.bin"); static int imu_v11_0_init_microcode(struct amdgpu_device *adev) { diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 970b066b37bb..5dff79e8f301 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -40,6 +40,8 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_2_mes.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_2_mes1.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_3_mes.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_3_mes1.bin"); +MODULE_FIRMWARE("amdgpu/gc_11_0_4_mes.bin"); +MODULE_FIRMWARE("amdgpu/gc_11_0_4_mes1.bin"); static int mes_v11_0_hw_fini(void *handle); static int mes_v11_0_kiq_hw_init(struct amdgpu_device *adev); @@ -196,7 +198,6 @@ static int mes_v11_0_add_hw_queue(struct amdgpu_mes *mes, mes_add_queue_pkt.trap_handler_addr = input->tba_addr; mes_add_queue_pkt.tma_addr = input->tma_addr; mes_add_queue_pkt.is_kfd_process = input->is_kfd_process; - mes_add_queue_pkt.trap_en = 1; /* For KFD, gds_size is re-used for queue size (needed in MES for AQL queues) */ mes_add_queue_pkt.is_aql_queue = input->is_aql_queue; diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c index 15eb3658d70e..09fdcd20cb91 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c @@ -337,7 +337,13 @@ const struct nbio_hdp_flush_reg nbio_v4_3_hdp_flush_reg = { static void nbio_v4_3_init_registers(struct amdgpu_device *adev) { - return; + if (adev->ip_versions[NBIO_HWIP][0] == IP_VERSION(4, 3, 0)) { + uint32_t data; + + data = RREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF2_STRAP2); + data &= ~RCC_DEV0_EPF2_STRAP2__STRAP_NO_SOFT_RESET_DEV0_F2_MASK; + WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF2_STRAP2, data); + } } static u32 nbio_v4_3_get_rom_offset(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 5562670b7b52..9eff5f41df9d 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -640,7 +640,8 @@ static int soc21_common_early_init(void *handle) AMD_CG_SUPPORT_GFX_CGCG | AMD_CG_SUPPORT_GFX_CGLS | AMD_CG_SUPPORT_REPEATER_FGCG | - AMD_CG_SUPPORT_GFX_MGCG; + AMD_CG_SUPPORT_GFX_MGCG | + AMD_CG_SUPPORT_HDP_SD; adev->pg_flags = AMD_PG_SUPPORT_VCN | AMD_PG_SUPPORT_VCN_DPG | AMD_PG_SUPPORT_JPEG; 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 4d42033a703f..31bce529f685 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -4501,6 +4501,17 @@ DEVICE_ATTR_WO(s3_debug); static int dm_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_mode_info *mode_info = &adev->mode_info; + struct atom_context *ctx = mode_info->atom_context; + int index = GetIndexIntoMasterTable(DATA, Object_Header); + u16 data_offset; + + /* if there is no object header, skip DM */ + if (!amdgpu_atom_parse_data_header(ctx, index, NULL, NULL, NULL, &data_offset)) { + adev->harvest_ip_mask |= AMD_HARVEST_IP_DMU_MASK; + dev_info(adev->dev, "No object header, skipping DM\n"); + return -ENOENT; + } switch (adev->asic_type) { #if defined(CONFIG_DRM_AMD_DC_SI) @@ -8881,6 +8892,13 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm, if (!dm_old_crtc_state->stream) goto skip_modeset; + /* Unset freesync video if it was active before */ + if (dm_old_crtc_state->freesync_config.state == VRR_STATE_ACTIVE_FIXED) { + dm_new_crtc_state->freesync_config.state = VRR_STATE_INACTIVE; + dm_new_crtc_state->freesync_config.fixed_refresh_in_uhz = 0; + } + + /* Now check if we should set freesync video mode */ if (amdgpu_freesync_vid_mode && dm_new_crtc_state->stream && is_timing_unchanged_for_freesync(new_crtc_state, old_crtc_state)) { @@ -9497,6 +9515,8 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, bool lock_and_validation_needed = false; struct dm_crtc_state *dm_old_crtc_state, *dm_new_crtc_state; #if defined(CONFIG_DRM_AMD_DC_DCN) + struct drm_dp_mst_topology_mgr *mgr; + struct drm_dp_mst_topology_state *mst_state; struct dsc_mst_fairness_vars vars[MAX_PIPES]; #endif @@ -9745,6 +9765,28 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, lock_and_validation_needed = true; } +#if defined(CONFIG_DRM_AMD_DC_DCN) + /* set the slot info for each mst_state based on the link encoding format */ + for_each_new_mst_mgr_in_state(state, mgr, mst_state, i) { + struct amdgpu_dm_connector *aconnector; + struct drm_connector *connector; + struct drm_connector_list_iter iter; + u8 link_coding_cap; + + drm_connector_list_iter_begin(dev, &iter); + drm_for_each_connector_iter(connector, &iter) { + if (connector->index == mst_state->mgr->conn_base_id) { + aconnector = to_amdgpu_dm_connector(connector); + link_coding_cap = dc_link_dp_mst_decide_link_encoding_format(aconnector->dc_link); + drm_dp_mst_update_slots(mst_state, link_coding_cap); + + break; + } + } + drm_connector_list_iter_end(&iter); + } +#endif + /** * Streams and planes are reset when there are changes that affect * bandwidth. Anything that affects bandwidth needs to go through diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index 6994c9a1ed85..5cff56bb8f56 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -120,23 +120,50 @@ enum dc_edid_status dm_helpers_parse_edid_caps( } static void -fill_dc_mst_payload_table_from_drm(struct drm_dp_mst_topology_state *mst_state, - struct amdgpu_dm_connector *aconnector, +fill_dc_mst_payload_table_from_drm(struct dc_link *link, + bool enable, + struct drm_dp_mst_atomic_payload *target_payload, struct dc_dp_mst_stream_allocation_table *table) { struct dc_dp_mst_stream_allocation_table new_table = { 0 }; struct dc_dp_mst_stream_allocation *sa; - struct drm_dp_mst_atomic_payload *payload; + struct link_mst_stream_allocation_table copy_of_link_table = + link->mst_stream_alloc_table; + + int i; + int current_hw_table_stream_cnt = copy_of_link_table.stream_count; + struct link_mst_stream_allocation *dc_alloc; + + /* TODO: refactor to set link->mst_stream_alloc_table directly if possible.*/ + if (enable) { + dc_alloc = + ©_of_link_table.stream_allocations[current_hw_table_stream_cnt]; + dc_alloc->vcp_id = target_payload->vcpi; + dc_alloc->slot_count = target_payload->time_slots; + } else { + for (i = 0; i < copy_of_link_table.stream_count; i++) { + dc_alloc = + ©_of_link_table.stream_allocations[i]; + + if (dc_alloc->vcp_id == target_payload->vcpi) { + dc_alloc->vcp_id = 0; + dc_alloc->slot_count = 0; + break; + } + } + ASSERT(i != copy_of_link_table.stream_count); + } /* Fill payload info*/ - list_for_each_entry(payload, &mst_state->payloads, next) { - if (payload->delete) - continue; - - sa = &new_table.stream_allocations[new_table.stream_count]; - sa->slot_count = payload->time_slots; - sa->vcp_id = payload->vcpi; - new_table.stream_count++; + for (i = 0; i < MAX_CONTROLLER_NUM; i++) { + dc_alloc = + ©_of_link_table.stream_allocations[i]; + if (dc_alloc->vcp_id > 0 && dc_alloc->slot_count > 0) { + sa = &new_table.stream_allocations[new_table.stream_count]; + sa->slot_count = dc_alloc->slot_count; + sa->vcp_id = dc_alloc->vcp_id; + new_table.stream_count++; + } } /* Overwrite the old table */ @@ -185,7 +212,7 @@ bool dm_helpers_dp_mst_write_payload_allocation_table( * AUX message. The sequence is slot 1-63 allocated sequence for each * stream. AMD ASIC stream slot allocation should follow the same * sequence. copy DRM MST allocation to dc */ - fill_dc_mst_payload_table_from_drm(mst_state, aconnector, proposed_table); + fill_dc_mst_payload_table_from_drm(stream->link, enable, payload, proposed_table); return true; } 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 d7a044e79730..abdbd4352f6f 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 @@ -903,11 +903,6 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, if (IS_ERR(mst_state)) return PTR_ERR(mst_state); - mst_state->pbn_div = dm_mst_get_pbn_divider(dc_link); -#if defined(CONFIG_DRM_AMD_DC_DCN) - drm_dp_mst_update_slots(mst_state, dc_link_dp_mst_decide_link_encoding_format(dc_link)); -#endif - /* Set up params */ for (i = 0; i < dc_state->stream_count; i++) { struct dc_dsc_policy dsc_policy = {0}; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 342e906ae26e..c88f044666fe 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -3995,10 +3995,13 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx) struct fixed31_32 avg_time_slots_per_mtp = dc_fixpt_from_int(0); int i; bool mst_mode = (link->type == dc_connection_mst_branch); + /* adjust for drm changes*/ + bool update_drm_mst_state = true; const struct link_hwss *link_hwss = get_link_hwss(link, &pipe_ctx->link_res); const struct dc_link_settings empty_link_settings = {0}; DC_LOGGER_INIT(link->ctx->logger); + /* deallocate_mst_payload is called before disable link. When mode or * disable/enable monitor, new stream is created which is not in link * stream[] yet. For this, payload is not allocated yet, so de-alloc @@ -4014,7 +4017,7 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx) &empty_link_settings, avg_time_slots_per_mtp); - if (mst_mode) { + if (mst_mode || update_drm_mst_state) { /* when link is in mst mode, reply on mst manager to remove * payload */ @@ -4077,11 +4080,18 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx) stream->ctx, stream); + if (!update_drm_mst_state) + dm_helpers_dp_mst_send_payload_allocation( + stream->ctx, + stream, + false); + } + + if (update_drm_mst_state) dm_helpers_dp_mst_send_payload_allocation( stream->ctx, stream, false); - } return DC_OK; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c index f9ea1e86707f..79850a68f62a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c @@ -874,8 +874,9 @@ static const struct dc_plane_cap plane_cap = { }, // 6:1 downscaling ratio: 1000/6 = 166.666 + // 4:1 downscaling ratio for ARGB888 to prevent underflow during P010 playback: 1000/4 = 250 .max_downscale_factor = { - .argb8888 = 167, + .argb8888 = 250, .nv12 = 167, .fp16 = 167 }, @@ -1763,7 +1764,7 @@ static bool dcn314_resource_construct( pool->base.underlay_pipe_index = NO_UNDERLAY_PIPE; pool->base.pipe_count = pool->base.res_cap->num_timing_generator; pool->base.mpcc_count = pool->base.res_cap->num_timing_generator; - dc->caps.max_downscale_ratio = 600; + dc->caps.max_downscale_ratio = 400; dc->caps.i2c_speed_in_khz = 100; dc->caps.i2c_speed_in_khz_hdcp = 100; dc->caps.max_cursor_size = 256; diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c index dc4649458567..a4e9fd5307c6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c @@ -94,7 +94,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = { .get_vupdate_offset_from_vsync = dcn10_get_vupdate_offset_from_vsync, .calc_vupdate_position = dcn10_calc_vupdate_position, .apply_idle_power_optimizations = dcn32_apply_idle_power_optimizations, - .does_plane_fit_in_mall = dcn30_does_plane_fit_in_mall, + .does_plane_fit_in_mall = NULL, .set_backlight_level = dcn21_set_backlight_level, .set_abm_immediate_disable = dcn21_set_abm_immediate_disable, .hardware_release = dcn30_hardware_release, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c index 950669f2c10d..cb7c0c878423 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c @@ -3183,7 +3183,7 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman } else { v->MIN_DST_Y_NEXT_START[k] = v->VTotal[k] - v->VFrontPorch[k] + v->VTotal[k] - v->VActive[k] - v->VStartup[k]; } - v->MIN_DST_Y_NEXT_START[k] += dml_floor(4.0 * v->TSetup[k] / (double)v->HTotal[k] / v->PixelClock[k], 1.0) / 4.0; + v->MIN_DST_Y_NEXT_START[k] += dml_floor(4.0 * v->TSetup[k] / ((double)v->HTotal[k] / v->PixelClock[k]), 1.0) / 4.0; if (((v->VUpdateOffsetPix[k] + v->VUpdateWidthPix[k] + v->VReadyOffsetPix[k]) / v->HTotal[k]) <= (isInterlaceTiming ? dml_floor((v->VTotal[k] - v->VActive[k] - v->VFrontPorch[k] - v->VStartup[k]) / 2.0, 1.0) : diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c index 4a122925c3ae..92c18bfb98b3 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c @@ -532,6 +532,9 @@ enum dmub_status dmub_srv_hw_init(struct dmub_srv *dmub, if (dmub->hw_funcs.reset) dmub->hw_funcs.reset(dmub); + /* reset the cache of the last wptr as well now that hw is reset */ + dmub->inbox1_last_wptr = 0; + cw0.offset.quad_part = inst_fb->gpu_addr; cw0.region.base = DMUB_CW0_BASE; cw0.region.top = cw0.region.base + inst_fb->size - 1; @@ -649,6 +652,15 @@ enum dmub_status dmub_srv_hw_reset(struct dmub_srv *dmub) if (dmub->hw_funcs.reset) dmub->hw_funcs.reset(dmub); + /* mailboxes have been reset in hw, so reset the sw state as well */ + dmub->inbox1_last_wptr = 0; + dmub->inbox1_rb.wrpt = 0; + dmub->inbox1_rb.rptr = 0; + dmub->outbox0_rb.wrpt = 0; + dmub->outbox0_rb.rptr = 0; + dmub->outbox1_rb.wrpt = 0; + dmub->outbox1_rb.rptr = 0; + dmub->hw_init = false; return DMUB_STATUS_OK; diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 236657eece47..a9170360d7e8 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -2007,14 +2007,16 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_ gc_ver == IP_VERSION(10, 3, 0) || gc_ver == IP_VERSION(10, 1, 2) || gc_ver == IP_VERSION(11, 0, 0) || - gc_ver == IP_VERSION(11, 0, 2))) + gc_ver == IP_VERSION(11, 0, 2) || + gc_ver == IP_VERSION(11, 0, 3))) *states = ATTR_STATE_UNSUPPORTED; } else if (DEVICE_ATTR_IS(pp_dpm_dclk)) { if (!(gc_ver == IP_VERSION(10, 3, 1) || gc_ver == IP_VERSION(10, 3, 0) || gc_ver == IP_VERSION(10, 1, 2) || gc_ver == IP_VERSION(11, 0, 0) || - gc_ver == IP_VERSION(11, 0, 2))) + gc_ver == IP_VERSION(11, 0, 2) || + gc_ver == IP_VERSION(11, 0, 3))) *states = ATTR_STATE_UNSUPPORTED; } else if (DEVICE_ATTR_IS(pp_power_profile_mode)) { if (amdgpu_dpm_get_power_profile_mode(adev, NULL) == -EOPNOTSUPP) diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index ca3beb5d8f27..6ab155023592 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1500,6 +1500,20 @@ static int smu_disable_dpms(struct smu_context *smu) } /* + * For SMU 13.0.4/11, PMFW will handle the features disablement properly + * for gpu reset case. Driver involvement is unnecessary. + */ + if (amdgpu_in_reset(adev)) { + switch (adev->ip_versions[MP1_HWIP][0]) { + case IP_VERSION(13, 0, 4): + case IP_VERSION(13, 0, 11): + return 0; + default: + break; + } + } + + /* * For gpu reset, runpm and hibernation through BACO, * BACO feature has to be kept enabled. */ diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 4c20d17e7416..cf96c3f2affe 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -145,6 +145,7 @@ static struct cmn2asic_msg_mapping smu_v13_0_0_message_map[SMU_MSG_MAX_COUNT] = MSG_MAP(SetBadMemoryPagesRetiredFlagsPerChannel, PPSMC_MSG_SetBadMemoryPagesRetiredFlagsPerChannel, 0), MSG_MAP(AllowGpo, PPSMC_MSG_SetGpoAllow, 0), + MSG_MAP(AllowIHHostInterrupt, PPSMC_MSG_AllowIHHostInterrupt, 0), }; static struct cmn2asic_mapping smu_v13_0_0_clk_map[SMU_CLK_COUNT] = { diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c index a2f0860b20bb..d751820c6da6 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c @@ -193,6 +193,7 @@ static int snd_dw_hdmi_probe(struct platform_device *pdev) struct hdmi_codec_pdata pdata; struct platform_device *platform; + memset(&pdata, 0, sizeof(pdata)); pdata.ops = &dw_hdmi_i2s_ops; pdata.i2s = 1; pdata.max_i2s_channels = 8; diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c index 51a46689cda7..4ca37261584a 100644 --- a/drivers/gpu/drm/display/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c @@ -3372,6 +3372,9 @@ void drm_dp_remove_payload(struct drm_dp_mst_topology_mgr *mgr, mgr->payload_count--; mgr->next_start_slot -= payload->time_slots; + + if (payload->delete) + drm_dp_mst_put_port_malloc(payload->port); } EXPORT_SYMBOL(drm_dp_remove_payload); @@ -4327,7 +4330,6 @@ int drm_dp_atomic_release_time_slots(struct drm_atomic_state *state, drm_dbg_atomic(mgr->dev, "[MST PORT:%p] TU %d -> 0\n", port, payload->time_slots); if (!payload->delete) { - drm_dp_mst_put_port_malloc(port); payload->pbn = 0; payload->delete = true; topology_state->payload_mask &= ~BIT(payload->vcpi - 1); diff --git a/drivers/gpu/drm/drm_fbdev_generic.c b/drivers/gpu/drm/drm_fbdev_generic.c index ab8695669279..593aa3283792 100644 --- a/drivers/gpu/drm/drm_fbdev_generic.c +++ b/drivers/gpu/drm/drm_fbdev_generic.c @@ -171,11 +171,6 @@ static const struct fb_ops drm_fbdev_fb_ops = { .fb_imageblit = drm_fbdev_fb_imageblit, }; -static struct fb_deferred_io drm_fbdev_defio = { - .delay = HZ / 20, - .deferred_io = drm_fb_helper_deferred_io, -}; - /* * This function uses the client API to create a framebuffer backed by a dumb buffer. */ @@ -222,8 +217,14 @@ static int drm_fbdev_fb_probe(struct drm_fb_helper *fb_helper, return -ENOMEM; fbi->flags |= FBINFO_VIRTFB | FBINFO_READS_FAST; - fbi->fbdefio = &drm_fbdev_defio; - fb_deferred_io_init(fbi); + /* Set a default deferred I/O handler */ + fb_helper->fbdefio.delay = HZ / 20; + fb_helper->fbdefio.deferred_io = drm_fb_helper_deferred_io; + + fbi->fbdefio = &fb_helper->fbdefio; + ret = fb_deferred_io_init(fbi); + if (ret) + return ret; } else { /* buffer is mapped for HW framebuffer */ ret = drm_client_buffer_vmap(fb_helper->buffer, &map); diff --git a/drivers/gpu/drm/drm_vma_manager.c b/drivers/gpu/drm/drm_vma_manager.c index 7de37f8c68fd..83229a031af0 100644 --- a/drivers/gpu/drm/drm_vma_manager.c +++ b/drivers/gpu/drm/drm_vma_manager.c @@ -240,27 +240,8 @@ void drm_vma_offset_remove(struct drm_vma_offset_manager *mgr, } EXPORT_SYMBOL(drm_vma_offset_remove); -/** - * drm_vma_node_allow - Add open-file to list of allowed users - * @node: Node to modify - * @tag: Tag of file to remove - * - * Add @tag to the list of allowed open-files for this node. If @tag is - * already on this list, the ref-count is incremented. - * - * The list of allowed-users is preserved across drm_vma_offset_add() and - * drm_vma_offset_remove() calls. You may even call it if the node is currently - * not added to any offset-manager. - * - * You must remove all open-files the same number of times as you added them - * before destroying the node. Otherwise, you will leak memory. - * - * This is locked against concurrent access internally. - * - * RETURNS: - * 0 on success, negative error code on internal failure (out-of-mem) - */ -int drm_vma_node_allow(struct drm_vma_offset_node *node, struct drm_file *tag) +static int vma_node_allow(struct drm_vma_offset_node *node, + struct drm_file *tag, bool ref_counted) { struct rb_node **iter; struct rb_node *parent = NULL; @@ -282,7 +263,8 @@ int drm_vma_node_allow(struct drm_vma_offset_node *node, struct drm_file *tag) entry = rb_entry(*iter, struct drm_vma_offset_file, vm_rb); if (tag == entry->vm_tag) { - entry->vm_count++; + if (ref_counted) + entry->vm_count++; goto unlock; } else if (tag > entry->vm_tag) { iter = &(*iter)->rb_right; @@ -307,9 +289,59 @@ unlock: kfree(new); return ret; } + +/** + * drm_vma_node_allow - Add open-file to list of allowed users + * @node: Node to modify + * @tag: Tag of file to remove + * + * Add @tag to the list of allowed open-files for this node. If @tag is + * already on this list, the ref-count is incremented. + * + * The list of allowed-users is preserved across drm_vma_offset_add() and + * drm_vma_offset_remove() calls. You may even call it if the node is currently + * not added to any offset-manager. + * + * You must remove all open-files the same number of times as you added them + * before destroying the node. Otherwise, you will leak memory. + * + * This is locked against concurrent access internally. + * + * RETURNS: + * 0 on success, negative error code on internal failure (out-of-mem) + */ +int drm_vma_node_allow(struct drm_vma_offset_node *node, struct drm_file *tag) +{ + return vma_node_allow(node, tag, true); +} EXPORT_SYMBOL(drm_vma_node_allow); /** + * drm_vma_node_allow_once - Add open-file to list of allowed users + * @node: Node to modify + * @tag: Tag of file to remove + * + * Add @tag to the list of allowed open-files for this node. + * + * The list of allowed-users is preserved across drm_vma_offset_add() and + * drm_vma_offset_remove() calls. You may even call it if the node is currently + * not added to any offset-manager. + * + * This is not ref-counted unlike drm_vma_node_allow() hence drm_vma_node_revoke() + * should only be called once after this. + * + * This is locked against concurrent access internally. + * + * RETURNS: + * 0 on success, negative error code on internal failure (out-of-mem) + */ +int drm_vma_node_allow_once(struct drm_vma_offset_node *node, struct drm_file *tag) +{ + return vma_node_allow(node, tag, false); +} +EXPORT_SYMBOL(drm_vma_node_allow_once); + +/** * drm_vma_node_revoke - Remove open-file from list of allowed users * @node: Node to modify * @tag: Tag of file to remove diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index b74e36d76013..407a477939e5 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -1319,7 +1319,7 @@ static const struct intel_cdclk_vals adlp_cdclk_table[] = { { .refclk = 24000, .cdclk = 192000, .divider = 2, .ratio = 16 }, { .refclk = 24000, .cdclk = 312000, .divider = 2, .ratio = 26 }, { .refclk = 24000, .cdclk = 552000, .divider = 2, .ratio = 46 }, - { .refclk = 24400, .cdclk = 648000, .divider = 2, .ratio = 54 }, + { .refclk = 24000, .cdclk = 648000, .divider = 2, .ratio = 54 }, { .refclk = 38400, .cdclk = 179200, .divider = 3, .ratio = 14 }, { .refclk = 38400, .cdclk = 192000, .divider = 2, .ratio = 10 }, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 6250de9b9196..e4b78ab4773b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -1861,11 +1861,19 @@ static int get_ppgtt(struct drm_i915_file_private *file_priv, vm = ctx->vm; GEM_BUG_ON(!vm); + /* + * Get a reference for the allocated handle. Once the handle is + * visible in the vm_xa table, userspace could try to close it + * from under our feet, so we need to hold the extra reference + * first. + */ + i915_vm_get(vm); + err = xa_alloc(&file_priv->vm_xa, &id, vm, xa_limit_32b, GFP_KERNEL); - if (err) + if (err) { + i915_vm_put(vm); return err; - - i915_vm_get(vm); + } GEM_BUG_ON(id == 0); /* reserved for invalid/unassigned ppgtt */ args->value = id; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 0ad44f3868de..c7c252d4d366 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -697,7 +697,7 @@ insert: GEM_BUG_ON(lookup_mmo(obj, mmap_type) != mmo); out: if (file) - drm_vma_node_allow(&mmo->vma_node, file); + drm_vma_node_allow_once(&mmo->vma_node, file); return mmo; err: diff --git a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c index fd42b89b7162..bc21b1c2350a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c @@ -305,10 +305,6 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj, spin_unlock(&obj->vma.lock); obj->tiling_and_stride = tiling | stride; - i915_gem_object_unlock(obj); - - /* Force the fence to be reacquired for GTT access */ - i915_gem_object_release_mmap_gtt(obj); /* Try to preallocate memory required to save swizzling on put-pages */ if (i915_gem_object_needs_bit17_swizzle(obj)) { @@ -321,6 +317,11 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj, obj->bit_17 = NULL; } + i915_gem_object_unlock(obj); + + /* Force the fence to be reacquired for GTT access */ + i915_gem_object_release_mmap_gtt(obj); + return 0; } diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index e94365b08f1e..2aa63ec521b8 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -528,7 +528,7 @@ retry: return rq; } -struct i915_request *intel_context_find_active_request(struct intel_context *ce) +struct i915_request *intel_context_get_active_request(struct intel_context *ce) { struct intel_context *parent = intel_context_to_parent(ce); struct i915_request *rq, *active = NULL; @@ -552,6 +552,8 @@ struct i915_request *intel_context_find_active_request(struct intel_context *ce) active = rq; } + if (active) + active = i915_request_get_rcu(active); spin_unlock_irqrestore(&parent->guc_state.lock, flags); return active; diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h index fb62b7b8cbcd..0a8d553da3f4 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.h +++ b/drivers/gpu/drm/i915/gt/intel_context.h @@ -268,8 +268,7 @@ int intel_context_prepare_remote_request(struct intel_context *ce, struct i915_request *intel_context_create_request(struct intel_context *ce); -struct i915_request * -intel_context_find_active_request(struct intel_context *ce); +struct i915_request *intel_context_get_active_request(struct intel_context *ce); static inline bool intel_context_is_barrier(const struct intel_context *ce) { diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h index cbc8b857d5f7..7a4504ea35c3 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine.h +++ b/drivers/gpu/drm/i915/gt/intel_engine.h @@ -248,8 +248,8 @@ void intel_engine_dump_active_requests(struct list_head *requests, ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine, ktime_t *now); -struct i915_request * -intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine); +void intel_engine_get_hung_entity(struct intel_engine_cs *engine, + struct intel_context **ce, struct i915_request **rq); u32 intel_engine_context_size(struct intel_gt *gt, u8 class); struct intel_context * diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index c33e0d72d670..d37931e16fd9 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -2094,17 +2094,6 @@ static void print_request_ring(struct drm_printer *m, struct i915_request *rq) } } -static unsigned long list_count(struct list_head *list) -{ - struct list_head *pos; - unsigned long count = 0; - - list_for_each(pos, list) - count++; - - return count; -} - static unsigned long read_ul(void *p, size_t x) { return *(unsigned long *)(p + x); @@ -2196,11 +2185,11 @@ void intel_engine_dump_active_requests(struct list_head *requests, } } -static void engine_dump_active_requests(struct intel_engine_cs *engine, struct drm_printer *m) +static void engine_dump_active_requests(struct intel_engine_cs *engine, + struct drm_printer *m) { + struct intel_context *hung_ce = NULL; struct i915_request *hung_rq = NULL; - struct intel_context *ce; - bool guc; /* * No need for an engine->irq_seqno_barrier() before the seqno reads. @@ -2209,27 +2198,22 @@ static void engine_dump_active_requests(struct intel_engine_cs *engine, struct d * But the intention here is just to report an instantaneous snapshot * so that's fine. */ - lockdep_assert_held(&engine->sched_engine->lock); + intel_engine_get_hung_entity(engine, &hung_ce, &hung_rq); drm_printf(m, "\tRequests:\n"); - guc = intel_uc_uses_guc_submission(&engine->gt->uc); - if (guc) { - ce = intel_engine_get_hung_context(engine); - if (ce) - hung_rq = intel_context_find_active_request(ce); - } else { - hung_rq = intel_engine_execlist_find_hung_request(engine); - } - if (hung_rq) engine_dump_request(hung_rq, m, "\t\thung"); + else if (hung_ce) + drm_printf(m, "\t\tGot hung ce but no hung rq!\n"); - if (guc) + if (intel_uc_uses_guc_submission(&engine->gt->uc)) intel_guc_dump_active_requests(engine, hung_rq, m); else - intel_engine_dump_active_requests(&engine->sched_engine->requests, - hung_rq, m); + intel_execlists_dump_active_requests(engine, hung_rq, m); + + if (hung_rq) + i915_request_put(hung_rq); } void intel_engine_dump(struct intel_engine_cs *engine, @@ -2239,7 +2223,6 @@ void intel_engine_dump(struct intel_engine_cs *engine, struct i915_gpu_error * const error = &engine->i915->gpu_error; struct i915_request *rq; intel_wakeref_t wakeref; - unsigned long flags; ktime_t dummy; if (header) { @@ -2276,13 +2259,8 @@ void intel_engine_dump(struct intel_engine_cs *engine, i915_reset_count(error)); print_properties(engine, m); - spin_lock_irqsave(&engine->sched_engine->lock, flags); engine_dump_active_requests(engine, m); - drm_printf(m, "\tOn hold?: %lu\n", - list_count(&engine->sched_engine->hold)); - spin_unlock_irqrestore(&engine->sched_engine->lock, flags); - drm_printf(m, "\tMMIO base: 0x%08x\n", engine->mmio_base); wakeref = intel_runtime_pm_get_if_in_use(engine->uncore->rpm); if (wakeref) { @@ -2328,8 +2306,7 @@ intel_engine_create_virtual(struct intel_engine_cs **siblings, return siblings[0]->cops->create_virtual(siblings, count, flags); } -struct i915_request * -intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine) +static struct i915_request *engine_execlist_find_hung_request(struct intel_engine_cs *engine) { struct i915_request *request, *active = NULL; @@ -2381,6 +2358,33 @@ intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine) return active; } +void intel_engine_get_hung_entity(struct intel_engine_cs *engine, + struct intel_context **ce, struct i915_request **rq) +{ + unsigned long flags; + + *ce = intel_engine_get_hung_context(engine); + if (*ce) { + intel_engine_clear_hung_context(engine); + + *rq = intel_context_get_active_request(*ce); + return; + } + + /* + * Getting here with GuC enabled means it is a forced error capture + * with no actual hang. So, no need to attempt the execlist search. + */ + if (intel_uc_uses_guc_submission(&engine->gt->uc)) + return; + + spin_lock_irqsave(&engine->sched_engine->lock, flags); + *rq = engine_execlist_find_hung_request(engine); + if (*rq) + *rq = i915_request_get_rcu(*rq); + spin_unlock_irqrestore(&engine->sched_engine->lock, flags); +} + void xehp_enable_ccs_engines(struct intel_engine_cs *engine) { /* diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 2daffa7c7dfd..21cb5b69d82e 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -4148,6 +4148,33 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine, spin_unlock_irqrestore(&sched_engine->lock, flags); } +static unsigned long list_count(struct list_head *list) +{ + struct list_head *pos; + unsigned long count = 0; + + list_for_each(pos, list) + count++; + + return count; +} + +void intel_execlists_dump_active_requests(struct intel_engine_cs *engine, + struct i915_request *hung_rq, + struct drm_printer *m) +{ + unsigned long flags; + + spin_lock_irqsave(&engine->sched_engine->lock, flags); + + intel_engine_dump_active_requests(&engine->sched_engine->requests, hung_rq, m); + + drm_printf(m, "\tOn hold?: %lu\n", + list_count(&engine->sched_engine->hold)); + + spin_unlock_irqrestore(&engine->sched_engine->lock, flags); +} + #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftest_execlists.c" #endif diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h index a1aa92c983a5..d2c7d45ea062 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h @@ -32,6 +32,10 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine, int indent), unsigned int max); +void intel_execlists_dump_active_requests(struct intel_engine_cs *engine, + struct i915_request *hung_rq, + struct drm_printer *m); + bool intel_engine_in_execlists_submission_mode(const struct intel_engine_cs *engine); diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 7771a19008c6..bbeeb6dde7ae 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -288,39 +288,6 @@ static const u8 dg2_xcs_offsets[] = { END }; -static const u8 mtl_xcs_offsets[] = { - NOP(1), - LRI(13, POSTED), - REG16(0x244), - REG(0x034), - REG(0x030), - REG(0x038), - REG(0x03c), - REG(0x168), - REG(0x140), - REG(0x110), - REG(0x1c0), - REG(0x1c4), - REG(0x1c8), - REG(0x180), - REG16(0x2b4), - NOP(4), - - NOP(1), - LRI(9, POSTED), - REG16(0x3a8), - REG16(0x28c), - REG16(0x288), - REG16(0x284), - REG16(0x280), - REG16(0x27c), - REG16(0x278), - REG16(0x274), - REG16(0x270), - - END -}; - static const u8 gen8_rcs_offsets[] = { NOP(1), LRI(14, POSTED), @@ -739,9 +706,7 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine) else return gen8_rcs_offsets; } else { - if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 70)) - return mtl_xcs_offsets; - else if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55)) + if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55)) return dg2_xcs_offsets; else if (GRAPHICS_VER(engine->i915) >= 12) return gen12_xcs_offsets; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 0a42f1807f52..c10977cb06b9 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1702,7 +1702,7 @@ static void __guc_reset_context(struct intel_context *ce, intel_engine_mask_t st goto next_context; guilty = false; - rq = intel_context_find_active_request(ce); + rq = intel_context_get_active_request(ce); if (!rq) { head = ce->ring->tail; goto out_replay; @@ -1715,6 +1715,7 @@ static void __guc_reset_context(struct intel_context *ce, intel_engine_mask_t st head = intel_ring_wrap(ce->ring, rq->head); __i915_request_reset(rq, guilty); + i915_request_put(rq); out_replay: guc_reset_state(ce, head, guilty); next_context: @@ -4817,6 +4818,8 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine) xa_lock_irqsave(&guc->context_lookup, flags); xa_for_each(&guc->context_lookup, index, ce) { + bool found; + if (!kref_get_unless_zero(&ce->ref)) continue; @@ -4833,10 +4836,18 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine) goto next; } + found = false; + spin_lock(&ce->guc_state.lock); list_for_each_entry(rq, &ce->guc_state.requests, sched.link) { if (i915_test_request_state(rq) != I915_REQUEST_ACTIVE) continue; + found = true; + break; + } + spin_unlock(&ce->guc_state.lock); + + if (found) { intel_engine_set_hung_context(engine, ce); /* Can only cope with one hang at a time... */ @@ -4844,6 +4855,7 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine) xa_lock(&guc->context_lookup); goto done; } + next: intel_context_put(ce); xa_lock(&guc->context_lookup); diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 9d5d5a397b64..b20bd6365615 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1596,43 +1596,20 @@ capture_engine(struct intel_engine_cs *engine, { struct intel_engine_capture_vma *capture = NULL; struct intel_engine_coredump *ee; - struct intel_context *ce; + struct intel_context *ce = NULL; struct i915_request *rq = NULL; - unsigned long flags; ee = intel_engine_coredump_alloc(engine, ALLOW_FAIL, dump_flags); if (!ee) return NULL; - ce = intel_engine_get_hung_context(engine); - if (ce) { - intel_engine_clear_hung_context(engine); - rq = intel_context_find_active_request(ce); - if (!rq || !i915_request_started(rq)) - goto no_request_capture; - } else { - /* - * Getting here with GuC enabled means it is a forced error capture - * with no actual hang. So, no need to attempt the execlist search. - */ - if (!intel_uc_uses_guc_submission(&engine->gt->uc)) { - spin_lock_irqsave(&engine->sched_engine->lock, flags); - rq = intel_engine_execlist_find_hung_request(engine); - spin_unlock_irqrestore(&engine->sched_engine->lock, - flags); - } - } - if (rq) - rq = i915_request_get_rcu(rq); - - if (!rq) + intel_engine_get_hung_entity(engine, &ce, &rq); + if (!rq || !i915_request_started(rq)) goto no_request_capture; capture = intel_engine_coredump_add_request(ee, rq, ATOMIC_MAYFAIL); - if (!capture) { - i915_request_put(rq); + if (!capture) goto no_request_capture; - } if (dump_flags & CORE_DUMP_FLAG_IS_GUC_CAPTURE) intel_guc_capture_get_matching_node(engine->gt, ee, ce); @@ -1642,6 +1619,8 @@ capture_engine(struct intel_engine_cs *engine, return ee; no_request_capture: + if (rq) + i915_request_put(rq); kfree(ee); return NULL; } diff --git a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c index 310fb83c527e..2990dd4d4a0d 100644 --- a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c +++ b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c @@ -28,8 +28,7 @@ struct intel_engine_cs *intel_selftest_find_any_engine(struct intel_gt *gt) int intel_selftest_modify_policy(struct intel_engine_cs *engine, struct intel_selftest_saved_policy *saved, - u32 modify_type) - + enum selftest_scheduler_modify modify_type) { int err; diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h index 40768373cdd9..c5a4f49ee206 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h @@ -97,6 +97,7 @@ int gp100_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct n int gp102_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **); int gp10b_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **); int gv100_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **); +int tu102_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **); int ga100_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **); int ga102_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **); diff --git a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c index fcf2a002f6cb..91fb494d4009 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c @@ -151,6 +151,9 @@ nvkm_firmware_mem_page(struct nvkm_memory *memory) static enum nvkm_memory_target nvkm_firmware_mem_target(struct nvkm_memory *memory) { + if (nvkm_firmware_mem(memory)->device->func->tegra) + return NVKM_MEM_TARGET_NCOH; + return NVKM_MEM_TARGET_HOST; } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index 364fea320cb3..1c81e5b34d29 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -2405,7 +2405,7 @@ nv162_chipset = { .bus = { 0x00000001, gf100_bus_new }, .devinit = { 0x00000001, tu102_devinit_new }, .fault = { 0x00000001, tu102_fault_new }, - .fb = { 0x00000001, gv100_fb_new }, + .fb = { 0x00000001, tu102_fb_new }, .fuse = { 0x00000001, gm107_fuse_new }, .gpio = { 0x00000001, gk104_gpio_new }, .gsp = { 0x00000001, gv100_gsp_new }, @@ -2440,7 +2440,7 @@ nv164_chipset = { .bus = { 0x00000001, gf100_bus_new }, .devinit = { 0x00000001, tu102_devinit_new }, .fault = { 0x00000001, tu102_fault_new }, - .fb = { 0x00000001, gv100_fb_new }, + .fb = { 0x00000001, tu102_fb_new }, .fuse = { 0x00000001, gm107_fuse_new }, .gpio = { 0x00000001, gk104_gpio_new }, .gsp = { 0x00000001, gv100_gsp_new }, @@ -2475,7 +2475,7 @@ nv166_chipset = { .bus = { 0x00000001, gf100_bus_new }, .devinit = { 0x00000001, tu102_devinit_new }, .fault = { 0x00000001, tu102_fault_new }, - .fb = { 0x00000001, gv100_fb_new }, + .fb = { 0x00000001, tu102_fb_new }, .fuse = { 0x00000001, gm107_fuse_new }, .gpio = { 0x00000001, gk104_gpio_new }, .gsp = { 0x00000001, gv100_gsp_new }, @@ -2510,7 +2510,7 @@ nv167_chipset = { .bus = { 0x00000001, gf100_bus_new }, .devinit = { 0x00000001, tu102_devinit_new }, .fault = { 0x00000001, tu102_fault_new }, - .fb = { 0x00000001, gv100_fb_new }, + .fb = { 0x00000001, tu102_fb_new }, .fuse = { 0x00000001, gm107_fuse_new }, .gpio = { 0x00000001, gk104_gpio_new }, .gsp = { 0x00000001, gv100_gsp_new }, @@ -2545,7 +2545,7 @@ nv168_chipset = { .bus = { 0x00000001, gf100_bus_new }, .devinit = { 0x00000001, tu102_devinit_new }, .fault = { 0x00000001, tu102_fault_new }, - .fb = { 0x00000001, gv100_fb_new }, + .fb = { 0x00000001, tu102_fb_new }, .fuse = { 0x00000001, gm107_fuse_new }, .gpio = { 0x00000001, gk104_gpio_new }, .gsp = { 0x00000001, gv100_gsp_new }, diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c b/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c index 393ade9f7e6c..b7da3ab44c27 100644 --- a/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c +++ b/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c @@ -48,6 +48,16 @@ gm200_flcn_pio_dmem_rd(struct nvkm_falcon *falcon, u8 port, const u8 *img, int l img += 4; len -= 4; } + + /* Sigh. Tegra PMU FW's init message... */ + if (len) { + u32 data = nvkm_falcon_rd32(falcon, 0x1c4 + (port * 8)); + + while (len--) { + *(u8 *)img++ = data & 0xff; + data >>= 8; + } + } } static void @@ -64,6 +74,8 @@ gm200_flcn_pio_dmem_wr(struct nvkm_falcon *falcon, u8 port, const u8 *img, int l img += 4; len -= 4; } + + WARN_ON(len); } static void @@ -74,7 +86,7 @@ gm200_flcn_pio_dmem_wr_init(struct nvkm_falcon *falcon, u8 port, bool sec, u32 d const struct nvkm_falcon_func_pio gm200_flcn_dmem_pio = { - .min = 4, + .min = 1, .max = 0x100, .wr_init = gm200_flcn_pio_dmem_wr_init, .wr = gm200_flcn_pio_dmem_wr, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c index 634f64f88fc8..81a1ad2c88a7 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c @@ -65,10 +65,33 @@ tu102_devinit_pll_set(struct nvkm_devinit *init, u32 type, u32 freq) return ret; } +static int +tu102_devinit_wait(struct nvkm_device *device) +{ + unsigned timeout = 50 + 2000; + + do { + if (nvkm_rd32(device, 0x118128) & 0x00000001) { + if ((nvkm_rd32(device, 0x118234) & 0x000000ff) == 0xff) + return 0; + } + + usleep_range(1000, 2000); + } while (timeout--); + + return -ETIMEDOUT; +} + int tu102_devinit_post(struct nvkm_devinit *base, bool post) { struct nv50_devinit *init = nv50_devinit(base); + int ret; + + ret = tu102_devinit_wait(init->base.subdev.device); + if (ret) + return ret; + gm200_devinit_preos(init, post); return 0; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild index 5d0bab8ecb43..6ba5120a2ebe 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild @@ -32,6 +32,7 @@ nvkm-y += nvkm/subdev/fb/gp100.o nvkm-y += nvkm/subdev/fb/gp102.o nvkm-y += nvkm/subdev/fb/gp10b.o nvkm-y += nvkm/subdev/fb/gv100.o +nvkm-y += nvkm/subdev/fb/tu102.o nvkm-y += nvkm/subdev/fb/ga100.o nvkm-y += nvkm/subdev/fb/ga102.o diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c index 8b7c8ea5e8a5..5a21b0ae4595 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c @@ -40,12 +40,6 @@ ga102_fb_vpr_scrub(struct nvkm_fb *fb) return ret; } -static bool -ga102_fb_vpr_scrub_required(struct nvkm_fb *fb) -{ - return (nvkm_rd32(fb->subdev.device, 0x1fa80c) & 0x00000010) != 0; -} - static const struct nvkm_fb_func ga102_fb = { .dtor = gf100_fb_dtor, @@ -56,7 +50,7 @@ ga102_fb = { .sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init, .ram_new = ga102_ram_new, .default_bigpage = 16, - .vpr.scrub_required = ga102_fb_vpr_scrub_required, + .vpr.scrub_required = tu102_fb_vpr_scrub_required, .vpr.scrub = ga102_fb_vpr_scrub, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c index 1f0126437c1a..0e3c0a8f5d71 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c @@ -49,8 +49,3 @@ gv100_fb_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, s } MODULE_FIRMWARE("nvidia/gv100/nvdec/scrubber.bin"); -MODULE_FIRMWARE("nvidia/tu102/nvdec/scrubber.bin"); -MODULE_FIRMWARE("nvidia/tu104/nvdec/scrubber.bin"); -MODULE_FIRMWARE("nvidia/tu106/nvdec/scrubber.bin"); -MODULE_FIRMWARE("nvidia/tu116/nvdec/scrubber.bin"); -MODULE_FIRMWARE("nvidia/tu117/nvdec/scrubber.bin"); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h index ac03eac0f261..f517751f94ac 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h @@ -89,4 +89,6 @@ bool gp102_fb_vpr_scrub_required(struct nvkm_fb *); int gp102_fb_vpr_scrub(struct nvkm_fb *); int gv100_fb_init_page(struct nvkm_fb *); + +bool tu102_fb_vpr_scrub_required(struct nvkm_fb *); #endif diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/tu102.c new file mode 100644 index 000000000000..be82af0364ee --- /dev/null +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/tu102.c @@ -0,0 +1,55 @@ +/* + * Copyright 2018 Red Hat Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ +#include "gf100.h" +#include "ram.h" + +bool +tu102_fb_vpr_scrub_required(struct nvkm_fb *fb) +{ + return (nvkm_rd32(fb->subdev.device, 0x1fa80c) & 0x00000010) != 0; +} + +static const struct nvkm_fb_func +tu102_fb = { + .dtor = gf100_fb_dtor, + .oneinit = gf100_fb_oneinit, + .init = gm200_fb_init, + .init_page = gv100_fb_init_page, + .init_unkn = gp100_fb_init_unkn, + .sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init, + .vpr.scrub_required = tu102_fb_vpr_scrub_required, + .vpr.scrub = gp102_fb_vpr_scrub, + .ram_new = gp100_ram_new, + .default_bigpage = 16, +}; + +int +tu102_fb_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, struct nvkm_fb **pfb) +{ + return gp102_fb_new_(&tu102_fb, device, type, inst, pfb); +} + +MODULE_FIRMWARE("nvidia/tu102/nvdec/scrubber.bin"); +MODULE_FIRMWARE("nvidia/tu104/nvdec/scrubber.bin"); +MODULE_FIRMWARE("nvidia/tu106/nvdec/scrubber.bin"); +MODULE_FIRMWARE("nvidia/tu116/nvdec/scrubber.bin"); +MODULE_FIRMWARE("nvidia/tu117/nvdec/scrubber.bin"); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c index a72403777329..2ed04da3621d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c @@ -225,7 +225,7 @@ gm20b_pmu_init(struct nvkm_pmu *pmu) pmu->initmsg_received = false; - nvkm_falcon_load_dmem(falcon, &args, addr_args, sizeof(args), 0); + nvkm_falcon_pio_wr(falcon, (u8 *)&args, 0, 0, DMEM, addr_args, sizeof(args), 0, false); nvkm_falcon_start(falcon); return 0; } diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c index 857a2f0420d7..c924f1124ebc 100644 --- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c +++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c @@ -1193,14 +1193,11 @@ static int boe_panel_enter_sleep_mode(struct boe_panel *boe) return 0; } -static int boe_panel_unprepare(struct drm_panel *panel) +static int boe_panel_disable(struct drm_panel *panel) { struct boe_panel *boe = to_boe_panel(panel); int ret; - if (!boe->prepared) - return 0; - ret = boe_panel_enter_sleep_mode(boe); if (ret < 0) { dev_err(panel->dev, "failed to set panel off: %d\n", ret); @@ -1209,6 +1206,16 @@ static int boe_panel_unprepare(struct drm_panel *panel) msleep(150); + return 0; +} + +static int boe_panel_unprepare(struct drm_panel *panel) +{ + struct boe_panel *boe = to_boe_panel(panel); + + if (!boe->prepared) + return 0; + if (boe->desc->discharge_on_disable) { regulator_disable(boe->avee); regulator_disable(boe->avdd); @@ -1528,6 +1535,7 @@ static enum drm_panel_orientation boe_panel_get_orientation(struct drm_panel *pa } static const struct drm_panel_funcs boe_panel_funcs = { + .disable = boe_panel_disable, .unprepare = boe_panel_unprepare, .prepare = boe_panel_prepare, .enable = boe_panel_enable, diff --git a/drivers/gpu/drm/solomon/ssd130x.c b/drivers/gpu/drm/solomon/ssd130x.c index 53464afc2b9a..91f69e62430b 100644 --- a/drivers/gpu/drm/solomon/ssd130x.c +++ b/drivers/gpu/drm/solomon/ssd130x.c @@ -656,18 +656,8 @@ static const struct drm_crtc_helper_funcs ssd130x_crtc_helper_funcs = { .atomic_check = drm_crtc_helper_atomic_check, }; -static void ssd130x_crtc_reset(struct drm_crtc *crtc) -{ - struct drm_device *drm = crtc->dev; - struct ssd130x_device *ssd130x = drm_to_ssd130x(drm); - - ssd130x_init(ssd130x); - - drm_atomic_helper_crtc_reset(crtc); -} - static const struct drm_crtc_funcs ssd130x_crtc_funcs = { - .reset = ssd130x_crtc_reset, + .reset = drm_atomic_helper_crtc_reset, .destroy = drm_crtc_cleanup, .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, @@ -686,6 +676,12 @@ static void ssd130x_encoder_helper_atomic_enable(struct drm_encoder *encoder, if (ret) return; + ret = ssd130x_init(ssd130x); + if (ret) { + ssd130x_power_off(ssd130x); + return; + } + ssd130x_write_cmd(ssd130x, 1, SSD130X_DISPLAY_ON); backlight_enable(ssd130x->bl_dev); diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 12a00d644b61..55744216392b 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -3018,7 +3018,8 @@ static int vc4_hdmi_cec_init(struct vc4_hdmi *vc4_hdmi) } vc4_hdmi->cec_adap = cec_allocate_adapter(&vc4_hdmi_cec_adap_ops, - vc4_hdmi, "vc4", + vc4_hdmi, + vc4_hdmi->variant->card_name, CEC_CAP_DEFAULTS | CEC_CAP_CONNECTOR_INFO, 1); ret = PTR_ERR_OR_ZERO(vc4_hdmi->cec_adap); diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_client.c b/drivers/hid/amd-sfh-hid/amd_sfh_client.c index 1fb0f7105fb2..c751d12f5df8 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_client.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_client.c @@ -227,6 +227,7 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata) cl_data->num_hid_devices = amd_mp2_get_sensor_num(privdata, &cl_data->sensor_idx[0]); if (cl_data->num_hid_devices == 0) return -ENODEV; + cl_data->is_any_sensor_enabled = false; INIT_DELAYED_WORK(&cl_data->work, amd_sfh_work); INIT_DELAYED_WORK(&cl_data->work_buffer, amd_sfh_work_buffer); @@ -287,6 +288,7 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata) status = amd_sfh_wait_for_response (privdata, cl_data->sensor_idx[i], SENSOR_ENABLED); if (status == SENSOR_ENABLED) { + cl_data->is_any_sensor_enabled = true; cl_data->sensor_sts[i] = SENSOR_ENABLED; rc = amdtp_hid_probe(cl_data->cur_hid_dev, cl_data); if (rc) { @@ -301,19 +303,26 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata) cl_data->sensor_sts[i]); goto cleanup; } + } else { + cl_data->sensor_sts[i] = SENSOR_DISABLED; + dev_dbg(dev, "sid 0x%x (%s) status 0x%x\n", + cl_data->sensor_idx[i], + get_sensor_name(cl_data->sensor_idx[i]), + cl_data->sensor_sts[i]); } dev_dbg(dev, "sid 0x%x (%s) status 0x%x\n", cl_data->sensor_idx[i], get_sensor_name(cl_data->sensor_idx[i]), cl_data->sensor_sts[i]); } - if (mp2_ops->discovery_status && mp2_ops->discovery_status(privdata) == 0) { + if (!cl_data->is_any_sensor_enabled || + (mp2_ops->discovery_status && mp2_ops->discovery_status(privdata) == 0)) { amd_sfh_hid_client_deinit(privdata); for (i = 0; i < cl_data->num_hid_devices; i++) { devm_kfree(dev, cl_data->feature_report[i]); devm_kfree(dev, in_data->input_report[i]); devm_kfree(dev, cl_data->report_descr[i]); } - dev_warn(dev, "Failed to discover, sensors not enabled\n"); + dev_warn(dev, "Failed to discover, sensors not enabled is %d\n", cl_data->is_any_sensor_enabled); return -EOPNOTSUPP; } schedule_delayed_work(&cl_data->work_buffer, msecs_to_jiffies(AMD_SFH_IDLE_LOOP)); diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_hid.h b/drivers/hid/amd-sfh-hid/amd_sfh_hid.h index 3754fb423e3a..528036892c9d 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_hid.h +++ b/drivers/hid/amd-sfh-hid/amd_sfh_hid.h @@ -32,6 +32,7 @@ struct amd_input_data { struct amdtp_cl_data { u8 init_done; u32 cur_hid_dev; + bool is_any_sensor_enabled; u32 hid_dev_count; u32 num_hid_devices; struct device_info *hid_devices; diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 3e1803592bd4..5c72aef3d3dd 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1202,6 +1202,7 @@ int hid_open_report(struct hid_device *device) __u8 *end; __u8 *next; int ret; + int i; static int (*dispatch_type[])(struct hid_parser *parser, struct hid_item *item) = { hid_parser_main, @@ -1252,6 +1253,8 @@ int hid_open_report(struct hid_device *device) goto err; } device->collection_size = HID_DEFAULT_NUM_COLLECTIONS; + for (i = 0; i < HID_DEFAULT_NUM_COLLECTIONS; i++) + device->collection[i].parent_idx = -1; ret = -EINVAL; while ((next = fetch_item(start, end, &item)) != NULL) { diff --git a/drivers/hid/hid-elecom.c b/drivers/hid/hid-elecom.c index e59e9911fc37..4fa45ee77503 100644 --- a/drivers/hid/hid-elecom.c +++ b/drivers/hid/hid-elecom.c @@ -12,6 +12,7 @@ * Copyright (c) 2017 Alex Manoussakis <amanou@gnu.org> * Copyright (c) 2017 Tomasz Kramkowski <tk@the-tk.com> * Copyright (c) 2020 YOSHIOKA Takuma <lo48576@hard-wi.red> + * Copyright (c) 2022 Takahiro Fujii <fujii@xaxxi.net> */ /* @@ -89,7 +90,7 @@ static __u8 *elecom_report_fixup(struct hid_device *hdev, __u8 *rdesc, case USB_DEVICE_ID_ELECOM_M_DT1URBK: case USB_DEVICE_ID_ELECOM_M_DT1DRBK: case USB_DEVICE_ID_ELECOM_M_HT1URBK: - case USB_DEVICE_ID_ELECOM_M_HT1DRBK: + case USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D: /* * Report descriptor format: * 12: button bit count @@ -99,6 +100,16 @@ static __u8 *elecom_report_fixup(struct hid_device *hdev, __u8 *rdesc, */ mouse_button_fixup(hdev, rdesc, *rsize, 12, 30, 14, 20, 8); break; + case USB_DEVICE_ID_ELECOM_M_HT1DRBK_011C: + /* + * Report descriptor format: + * 22: button bit count + * 30: padding bit count + * 24: button report size + * 16: button usage maximum + */ + mouse_button_fixup(hdev, rdesc, *rsize, 22, 30, 24, 16, 8); + break; } return rdesc; } @@ -112,7 +123,8 @@ static const struct hid_device_id elecom_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1URBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1DRBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1URBK) }, - { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK_011C) }, { } }; MODULE_DEVICE_TABLE(hid, elecom_devices); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 0f8c11842a3a..9e36b4cd905e 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -413,6 +413,8 @@ #define I2C_DEVICE_ID_HP_ENVY_X360_15T_DR100 0x29CF #define I2C_DEVICE_ID_HP_ENVY_X360_EU0009NV 0x2CF9 #define I2C_DEVICE_ID_HP_SPECTRE_X360_15 0x2817 +#define I2C_DEVICE_ID_HP_SPECTRE_X360_13_AW0020NG 0x29DF +#define I2C_DEVICE_ID_ASUS_TP420IA_TOUCHSCREEN 0x2BC8 #define USB_DEVICE_ID_ASUS_UX550VE_TOUCHSCREEN 0x2544 #define USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN 0x2706 #define I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN 0x261A @@ -428,7 +430,8 @@ #define USB_DEVICE_ID_ELECOM_M_DT1URBK 0x00fe #define USB_DEVICE_ID_ELECOM_M_DT1DRBK 0x00ff #define USB_DEVICE_ID_ELECOM_M_HT1URBK 0x010c -#define USB_DEVICE_ID_ELECOM_M_HT1DRBK 0x010d +#define USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D 0x010d +#define USB_DEVICE_ID_ELECOM_M_HT1DRBK_011C 0x011c #define USB_VENDOR_ID_DREAM_CHEEKY 0x1d34 #define USB_DEVICE_ID_DREAM_CHEEKY_WN 0x0004 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 9b59e436df0a..77c8c49852b5 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -370,6 +370,8 @@ static const struct hid_device_id hid_battery_quirks[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_DINOVO_EDGE_KBD), HID_BATTERY_QUIRK_IGNORE }, + { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_ASUS_TP420IA_TOUCHSCREEN), + HID_BATTERY_QUIRK_IGNORE }, { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN), HID_BATTERY_QUIRK_IGNORE }, { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550VE_TOUCHSCREEN), @@ -384,6 +386,8 @@ static const struct hid_device_id hid_battery_quirks[] = { HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_15), HID_BATTERY_QUIRK_IGNORE }, + { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_13_AW0020NG), + HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN), HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_SURFACE_GO2_TOUCHSCREEN), diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index abf2c95e4d0b..9c1ee8e91e0c 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -3978,7 +3978,8 @@ static void hidpp_connect_event(struct hidpp_device *hidpp) } hidpp_initialize_battery(hidpp); - hidpp_initialize_hires_scroll(hidpp); + if (!hid_is_usb(hidpp->hid_dev)) + hidpp_initialize_hires_scroll(hidpp); /* forward current battery state */ if (hidpp->capabilities & HIDPP_CAPABILITY_HIDPP10_BATTERY) { diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index be3ad02573de..5bc91f68b374 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -393,7 +393,8 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1URBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1DRBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1URBK) }, - { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK_011C) }, #endif #if IS_ENABLED(CONFIG_HID_ELO) { HID_USB_DEVICE(USB_VENDOR_ID_ELO, 0x0009) }, diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index cbe43e2567a7..64ac5bdee3a6 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -1963,7 +1963,7 @@ static void hv_balloon_debugfs_init(struct hv_dynmem_device *b) static void hv_balloon_debugfs_exit(struct hv_dynmem_device *b) { - debugfs_remove(debugfs_lookup("hv-balloon", NULL)); + debugfs_lookup_and_remove("hv-balloon", NULL); } #else diff --git a/drivers/i2c/busses/i2c-axxia.c b/drivers/i2c/busses/i2c-axxia.c index bdf3b50de8ad..c1c74ce08407 100644 --- a/drivers/i2c/busses/i2c-axxia.c +++ b/drivers/i2c/busses/i2c-axxia.c @@ -118,7 +118,7 @@ #define SDA_HOLD_TIME 0x90 /** - * axxia_i2c_dev - I2C device context + * struct axxia_i2c_dev - I2C device context * @base: pointer to register struct * @msg: pointer to current message * @msg_r: pointer to current read message (sequence transfer) diff --git a/drivers/i2c/busses/i2c-designware-common.c b/drivers/i2c/busses/i2c-designware-common.c index a3240ece55b2..581e02cc979a 100644 --- a/drivers/i2c/busses/i2c-designware-common.c +++ b/drivers/i2c/busses/i2c-designware-common.c @@ -351,7 +351,8 @@ u32 i2c_dw_scl_hcnt(u32 ic_clk, u32 tSYMBOL, u32 tf, int cond, int offset) * * If your hardware is free from tHD;STA issue, try this one. */ - return DIV_ROUND_CLOSEST(ic_clk * tSYMBOL, MICRO) - 8 + offset; + return DIV_ROUND_CLOSEST_ULL((u64)ic_clk * tSYMBOL, MICRO) - + 8 + offset; else /* * Conditional expression: @@ -367,7 +368,8 @@ u32 i2c_dw_scl_hcnt(u32 ic_clk, u32 tSYMBOL, u32 tf, int cond, int offset) * The reason why we need to take into account "tf" here, * is the same as described in i2c_dw_scl_lcnt(). */ - return DIV_ROUND_CLOSEST(ic_clk * (tSYMBOL + tf), MICRO) - 3 + offset; + return DIV_ROUND_CLOSEST_ULL((u64)ic_clk * (tSYMBOL + tf), MICRO) - + 3 + offset; } u32 i2c_dw_scl_lcnt(u32 ic_clk, u32 tLOW, u32 tf, int offset) @@ -383,7 +385,8 @@ u32 i2c_dw_scl_lcnt(u32 ic_clk, u32 tLOW, u32 tf, int offset) * account the fall time of SCL signal (tf). Default tf value * should be 0.3 us, for safety. */ - return DIV_ROUND_CLOSEST(ic_clk * (tLOW + tf), MICRO) - 1 + offset; + return DIV_ROUND_CLOSEST_ULL((u64)ic_clk * (tLOW + tf), MICRO) - + 1 + offset; } int i2c_dw_set_sda_hold(struct dw_i2c_dev *dev) diff --git a/drivers/i2c/busses/i2c-designware-pcidrv.c b/drivers/i2c/busses/i2c-designware-pcidrv.c index e499f96506c5..782fe1ef3ca1 100644 --- a/drivers/i2c/busses/i2c-designware-pcidrv.c +++ b/drivers/i2c/busses/i2c-designware-pcidrv.c @@ -396,6 +396,8 @@ static const struct pci_device_id i2_designware_pci_ids[] = { { PCI_VDEVICE(ATI, 0x73a4), navi_amd }, { PCI_VDEVICE(ATI, 0x73e4), navi_amd }, { PCI_VDEVICE(ATI, 0x73c4), navi_amd }, + { PCI_VDEVICE(ATI, 0x7444), navi_amd }, + { PCI_VDEVICE(ATI, 0x7464), navi_amd }, { 0,} }; MODULE_DEVICE_TABLE(pci, i2_designware_pci_ids); diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c index ba043b547393..74182db03a88 100644 --- a/drivers/i2c/busses/i2c-designware-platdrv.c +++ b/drivers/i2c/busses/i2c-designware-platdrv.c @@ -351,13 +351,11 @@ static int dw_i2c_plat_probe(struct platform_device *pdev) if (dev->flags & ACCESS_NO_IRQ_SUSPEND) { dev_pm_set_driver_flags(&pdev->dev, - DPM_FLAG_SMART_PREPARE | - DPM_FLAG_MAY_SKIP_RESUME); + DPM_FLAG_SMART_PREPARE); } else { dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_SMART_PREPARE | - DPM_FLAG_SMART_SUSPEND | - DPM_FLAG_MAY_SKIP_RESUME); + DPM_FLAG_SMART_SUSPEND); } device_enable_async_suspend(&pdev->dev); @@ -419,21 +417,8 @@ static int dw_i2c_plat_prepare(struct device *dev) */ return !has_acpi_companion(dev); } - -static void dw_i2c_plat_complete(struct device *dev) -{ - /* - * The device can only be in runtime suspend at this point if it has not - * been resumed throughout the ending system suspend/resume cycle, so if - * the platform firmware might mess up with it, request the runtime PM - * framework to resume it. - */ - if (pm_runtime_suspended(dev) && pm_resume_via_firmware()) - pm_request_resume(dev); -} #else #define dw_i2c_plat_prepare NULL -#define dw_i2c_plat_complete NULL #endif #ifdef CONFIG_PM @@ -483,7 +468,6 @@ static int __maybe_unused dw_i2c_plat_resume(struct device *dev) static const struct dev_pm_ops dw_i2c_dev_pm_ops = { .prepare = dw_i2c_plat_prepare, - .complete = dw_i2c_plat_complete, SET_LATE_SYSTEM_SLEEP_PM_OPS(dw_i2c_plat_suspend, dw_i2c_plat_resume) SET_RUNTIME_PM_OPS(dw_i2c_plat_runtime_suspend, dw_i2c_plat_runtime_resume, NULL) }; diff --git a/drivers/i2c/busses/i2c-mxs.c b/drivers/i2c/busses/i2c-mxs.c index 5af5cffc444e..d113bed79545 100644 --- a/drivers/i2c/busses/i2c-mxs.c +++ b/drivers/i2c/busses/i2c-mxs.c @@ -826,8 +826,8 @@ static int mxs_i2c_probe(struct platform_device *pdev) /* Setup the DMA */ i2c->dmach = dma_request_chan(dev, "rx-tx"); if (IS_ERR(i2c->dmach)) { - dev_err(dev, "Failed to request dma\n"); - return PTR_ERR(i2c->dmach); + return dev_err_probe(dev, PTR_ERR(i2c->dmach), + "Failed to request dma\n"); } platform_set_drvdata(pdev, i2c); diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c index d1658ed76562..b31cf4f18f85 100644 --- a/drivers/i2c/busses/i2c-rk3x.c +++ b/drivers/i2c/busses/i2c-rk3x.c @@ -80,7 +80,7 @@ enum { #define DEFAULT_SCL_RATE (100 * 1000) /* Hz */ /** - * struct i2c_spec_values: + * struct i2c_spec_values - I2C specification values for various modes * @min_hold_start_ns: min hold time (repeated) START condition * @min_low_ns: min LOW period of the SCL clock * @min_high_ns: min HIGH period of the SCL cloc @@ -136,7 +136,7 @@ static const struct i2c_spec_values fast_mode_plus_spec = { }; /** - * struct rk3x_i2c_calced_timings: + * struct rk3x_i2c_calced_timings - calculated V1 timings * @div_low: Divider output for low * @div_high: Divider output for high * @tuning: Used to adjust setup/hold data time, @@ -159,7 +159,7 @@ enum rk3x_i2c_state { }; /** - * struct rk3x_i2c_soc_data: + * struct rk3x_i2c_soc_data - SOC-specific data * @grf_offset: offset inside the grf regmap for setting the i2c type * @calc_timings: Callback function for i2c timing information calculated */ @@ -239,7 +239,8 @@ static inline void rk3x_i2c_clean_ipd(struct rk3x_i2c *i2c) } /** - * Generate a START condition, which triggers a REG_INT_START interrupt. + * rk3x_i2c_start - Generate a START condition, which triggers a REG_INT_START interrupt. + * @i2c: target controller data */ static void rk3x_i2c_start(struct rk3x_i2c *i2c) { @@ -258,8 +259,8 @@ static void rk3x_i2c_start(struct rk3x_i2c *i2c) } /** - * Generate a STOP condition, which triggers a REG_INT_STOP interrupt. - * + * rk3x_i2c_stop - Generate a STOP condition, which triggers a REG_INT_STOP interrupt. + * @i2c: target controller data * @error: Error code to return in rk3x_i2c_xfer */ static void rk3x_i2c_stop(struct rk3x_i2c *i2c, int error) @@ -298,7 +299,8 @@ static void rk3x_i2c_stop(struct rk3x_i2c *i2c, int error) } /** - * Setup a read according to i2c->msg + * rk3x_i2c_prepare_read - Setup a read according to i2c->msg + * @i2c: target controller data */ static void rk3x_i2c_prepare_read(struct rk3x_i2c *i2c) { @@ -329,7 +331,8 @@ static void rk3x_i2c_prepare_read(struct rk3x_i2c *i2c) } /** - * Fill the transmit buffer with data from i2c->msg + * rk3x_i2c_fill_transmit_buf - Fill the transmit buffer with data from i2c->msg + * @i2c: target controller data */ static void rk3x_i2c_fill_transmit_buf(struct rk3x_i2c *i2c) { @@ -532,11 +535,10 @@ out: } /** - * Get timing values of I2C specification - * + * rk3x_i2c_get_spec - Get timing values of I2C specification * @speed: Desired SCL frequency * - * Returns: Matched i2c spec values. + * Return: Matched i2c_spec_values. */ static const struct i2c_spec_values *rk3x_i2c_get_spec(unsigned int speed) { @@ -549,13 +551,12 @@ static const struct i2c_spec_values *rk3x_i2c_get_spec(unsigned int speed) } /** - * Calculate divider values for desired SCL frequency - * + * rk3x_i2c_v0_calc_timings - Calculate divider values for desired SCL frequency * @clk_rate: I2C input clock rate * @t: Known I2C timing information * @t_calc: Caculated rk3x private timings that would be written into regs * - * Returns: 0 on success, -EINVAL if the goal SCL rate is too slow. In that case + * Return: %0 on success, -%EINVAL if the goal SCL rate is too slow. In that case * a best-effort divider value is returned in divs. If the target rate is * too high, we silently use the highest possible rate. */ @@ -710,13 +711,12 @@ static int rk3x_i2c_v0_calc_timings(unsigned long clk_rate, } /** - * Calculate timing values for desired SCL frequency - * + * rk3x_i2c_v1_calc_timings - Calculate timing values for desired SCL frequency * @clk_rate: I2C input clock rate * @t: Known I2C timing information * @t_calc: Caculated rk3x private timings that would be written into regs * - * Returns: 0 on success, -EINVAL if the goal SCL rate is too slow. In that case + * Return: %0 on success, -%EINVAL if the goal SCL rate is too slow. In that case * a best-effort divider value is returned in divs. If the target rate is * too high, we silently use the highest possible rate. * The following formulas are v1's method to calculate timings. @@ -960,14 +960,14 @@ static int rk3x_i2c_clk_notifier_cb(struct notifier_block *nb, unsigned long } /** - * Setup I2C registers for an I2C operation specified by msgs, num. - * - * Must be called with i2c->lock held. - * + * rk3x_i2c_setup - Setup I2C registers for an I2C operation specified by msgs, num. + * @i2c: target controller data * @msgs: I2C msgs to process * @num: Number of msgs * - * returns: Number of I2C msgs processed or negative in case of error + * Must be called with i2c->lock held. + * + * Return: Number of I2C msgs processed or negative in case of error */ static int rk3x_i2c_setup(struct rk3x_i2c *i2c, struct i2c_msg *msgs, int num) { diff --git a/drivers/iio/accel/hid-sensor-accel-3d.c b/drivers/iio/accel/hid-sensor-accel-3d.c index a2def6f9380a..5eac7ea19993 100644 --- a/drivers/iio/accel/hid-sensor-accel-3d.c +++ b/drivers/iio/accel/hid-sensor-accel-3d.c @@ -280,6 +280,7 @@ static int accel_3d_capture_sample(struct hid_sensor_hub_device *hsdev, hid_sensor_convert_timestamp( &accel_state->common_attributes, *(int64_t *)raw_data); + ret = 0; break; default: break; diff --git a/drivers/iio/adc/berlin2-adc.c b/drivers/iio/adc/berlin2-adc.c index 3d2e8b4db61a..a4e7c7eff5ac 100644 --- a/drivers/iio/adc/berlin2-adc.c +++ b/drivers/iio/adc/berlin2-adc.c @@ -298,8 +298,10 @@ static int berlin2_adc_probe(struct platform_device *pdev) int ret; indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*priv)); - if (!indio_dev) + if (!indio_dev) { + of_node_put(parent_np); return -ENOMEM; + } priv = iio_priv(indio_dev); diff --git a/drivers/iio/adc/imx8qxp-adc.c b/drivers/iio/adc/imx8qxp-adc.c index 36777b827165..f5a0fc9e64c5 100644 --- a/drivers/iio/adc/imx8qxp-adc.c +++ b/drivers/iio/adc/imx8qxp-adc.c @@ -86,6 +86,8 @@ #define IMX8QXP_ADC_TIMEOUT msecs_to_jiffies(100) +#define IMX8QXP_ADC_MAX_FIFO_SIZE 16 + struct imx8qxp_adc { struct device *dev; void __iomem *regs; @@ -95,6 +97,7 @@ struct imx8qxp_adc { /* Serialise ADC channel reads */ struct mutex lock; struct completion completion; + u32 fifo[IMX8QXP_ADC_MAX_FIFO_SIZE]; }; #define IMX8QXP_ADC_CHAN(_idx) { \ @@ -238,8 +241,7 @@ static int imx8qxp_adc_read_raw(struct iio_dev *indio_dev, return ret; } - *val = FIELD_GET(IMX8QXP_ADC_RESFIFO_VAL_MASK, - readl(adc->regs + IMX8QXP_ADR_ADC_RESFIFO)); + *val = adc->fifo[0]; mutex_unlock(&adc->lock); return IIO_VAL_INT; @@ -265,10 +267,15 @@ static irqreturn_t imx8qxp_adc_isr(int irq, void *dev_id) { struct imx8qxp_adc *adc = dev_id; u32 fifo_count; + int i; fifo_count = FIELD_GET(IMX8QXP_ADC_FCTRL_FCOUNT_MASK, readl(adc->regs + IMX8QXP_ADR_ADC_FCTRL)); + for (i = 0; i < fifo_count; i++) + adc->fifo[i] = FIELD_GET(IMX8QXP_ADC_RESFIFO_VAL_MASK, + readl_relaxed(adc->regs + IMX8QXP_ADR_ADC_RESFIFO)); + if (fifo_count) complete(&adc->completion); diff --git a/drivers/iio/adc/stm32-dfsdm-adc.c b/drivers/iio/adc/stm32-dfsdm-adc.c index 6d21ea84fa82..a428bdb567d5 100644 --- a/drivers/iio/adc/stm32-dfsdm-adc.c +++ b/drivers/iio/adc/stm32-dfsdm-adc.c @@ -1520,6 +1520,7 @@ static const struct of_device_id stm32_dfsdm_adc_match[] = { }, {} }; +MODULE_DEVICE_TABLE(of, stm32_dfsdm_adc_match); static int stm32_dfsdm_adc_probe(struct platform_device *pdev) { diff --git a/drivers/iio/adc/twl6030-gpadc.c b/drivers/iio/adc/twl6030-gpadc.c index f53e8558b560..32873fb5f367 100644 --- a/drivers/iio/adc/twl6030-gpadc.c +++ b/drivers/iio/adc/twl6030-gpadc.c @@ -57,6 +57,18 @@ #define TWL6030_GPADCS BIT(1) #define TWL6030_GPADCR BIT(0) +#define USB_VBUS_CTRL_SET 0x04 +#define USB_ID_CTRL_SET 0x06 + +#define TWL6030_MISC1 0xE4 +#define VBUS_MEAS 0x01 +#define ID_MEAS 0x01 + +#define VAC_MEAS 0x04 +#define VBAT_MEAS 0x02 +#define BB_MEAS 0x01 + + /** * struct twl6030_chnl_calib - channel calibration * @gain: slope coefficient for ideal curve @@ -927,6 +939,26 @@ static int twl6030_gpadc_probe(struct platform_device *pdev) return ret; } + ret = twl_i2c_write_u8(TWL_MODULE_USB, VBUS_MEAS, USB_VBUS_CTRL_SET); + if (ret < 0) { + dev_err(dev, "failed to wire up inputs\n"); + return ret; + } + + ret = twl_i2c_write_u8(TWL_MODULE_USB, ID_MEAS, USB_ID_CTRL_SET); + if (ret < 0) { + dev_err(dev, "failed to wire up inputs\n"); + return ret; + } + + ret = twl_i2c_write_u8(TWL6030_MODULE_ID0, + VBAT_MEAS | BB_MEAS | VAC_MEAS, + TWL6030_MISC1); + if (ret < 0) { + dev_err(dev, "failed to wire up inputs\n"); + return ret; + } + indio_dev->name = DRIVER_NAME; indio_dev->info = &twl6030_gpadc_iio_info; indio_dev->modes = INDIO_DIRECT_MODE; diff --git a/drivers/iio/adc/xilinx-ams.c b/drivers/iio/adc/xilinx-ams.c index 5b4bdf3a26bb..a507d2e17079 100644 --- a/drivers/iio/adc/xilinx-ams.c +++ b/drivers/iio/adc/xilinx-ams.c @@ -1329,7 +1329,7 @@ static int ams_parse_firmware(struct iio_dev *indio_dev) dev_channels = devm_krealloc(dev, ams_channels, dev_size, GFP_KERNEL); if (!dev_channels) - ret = -ENOMEM; + return -ENOMEM; indio_dev->channels = dev_channels; indio_dev->num_channels = num_channels; diff --git a/drivers/iio/gyro/hid-sensor-gyro-3d.c b/drivers/iio/gyro/hid-sensor-gyro-3d.c index 8f0ad022c7f1..698c50da1f10 100644 --- a/drivers/iio/gyro/hid-sensor-gyro-3d.c +++ b/drivers/iio/gyro/hid-sensor-gyro-3d.c @@ -231,6 +231,7 @@ static int gyro_3d_capture_sample(struct hid_sensor_hub_device *hsdev, gyro_state->timestamp = hid_sensor_convert_timestamp(&gyro_state->common_attributes, *(s64 *)raw_data); + ret = 0; break; default: break; diff --git a/drivers/iio/imu/fxos8700_core.c b/drivers/iio/imu/fxos8700_core.c index 423cfe526f2a..6d189c4b9ff9 100644 --- a/drivers/iio/imu/fxos8700_core.c +++ b/drivers/iio/imu/fxos8700_core.c @@ -10,6 +10,7 @@ #include <linux/regmap.h> #include <linux/acpi.h> #include <linux/bitops.h> +#include <linux/bitfield.h> #include <linux/iio/iio.h> #include <linux/iio/sysfs.h> @@ -144,9 +145,8 @@ #define FXOS8700_NVM_DATA_BNK0 0xa7 /* Bit definitions for FXOS8700_CTRL_REG1 */ -#define FXOS8700_CTRL_ODR_MSK 0x38 #define FXOS8700_CTRL_ODR_MAX 0x00 -#define FXOS8700_CTRL_ODR_MIN GENMASK(4, 3) +#define FXOS8700_CTRL_ODR_MSK GENMASK(5, 3) /* Bit definitions for FXOS8700_M_CTRL_REG1 */ #define FXOS8700_HMS_MASK GENMASK(1, 0) @@ -320,7 +320,7 @@ static enum fxos8700_sensor fxos8700_to_sensor(enum iio_chan_type iio_type) switch (iio_type) { case IIO_ACCEL: return FXOS8700_ACCEL; - case IIO_ANGL_VEL: + case IIO_MAGN: return FXOS8700_MAGN; default: return -EINVAL; @@ -345,15 +345,35 @@ static int fxos8700_set_active_mode(struct fxos8700_data *data, static int fxos8700_set_scale(struct fxos8700_data *data, enum fxos8700_sensor t, int uscale) { - int i; + int i, ret, val; + bool active_mode; static const int scale_num = ARRAY_SIZE(fxos8700_accel_scale); struct device *dev = regmap_get_device(data->regmap); if (t == FXOS8700_MAGN) { - dev_err(dev, "Magnetometer scale is locked at 1200uT\n"); + dev_err(dev, "Magnetometer scale is locked at 0.001Gs\n"); return -EINVAL; } + /* + * When device is in active mode, it failed to set an ACCEL + * full-scale range(2g/4g/8g) in FXOS8700_XYZ_DATA_CFG. + * This is not align with the datasheet, but it is a fxos8700 + * chip behavier. Set the device in standby mode before setting + * an ACCEL full-scale range. + */ + ret = regmap_read(data->regmap, FXOS8700_CTRL_REG1, &val); + if (ret) + return ret; + + active_mode = val & FXOS8700_ACTIVE; + if (active_mode) { + ret = regmap_write(data->regmap, FXOS8700_CTRL_REG1, + val & ~FXOS8700_ACTIVE); + if (ret) + return ret; + } + for (i = 0; i < scale_num; i++) if (fxos8700_accel_scale[i].uscale == uscale) break; @@ -361,8 +381,12 @@ static int fxos8700_set_scale(struct fxos8700_data *data, if (i == scale_num) return -EINVAL; - return regmap_write(data->regmap, FXOS8700_XYZ_DATA_CFG, + ret = regmap_write(data->regmap, FXOS8700_XYZ_DATA_CFG, fxos8700_accel_scale[i].bits); + if (ret) + return ret; + return regmap_write(data->regmap, FXOS8700_CTRL_REG1, + active_mode); } static int fxos8700_get_scale(struct fxos8700_data *data, @@ -372,7 +396,7 @@ static int fxos8700_get_scale(struct fxos8700_data *data, static const int scale_num = ARRAY_SIZE(fxos8700_accel_scale); if (t == FXOS8700_MAGN) { - *uscale = 1200; /* Magnetometer is locked at 1200uT */ + *uscale = 1000; /* Magnetometer is locked at 0.001Gs */ return 0; } @@ -394,22 +418,61 @@ static int fxos8700_get_data(struct fxos8700_data *data, int chan_type, int axis, int *val) { u8 base, reg; + s16 tmp; int ret; - enum fxos8700_sensor type = fxos8700_to_sensor(chan_type); - base = type ? FXOS8700_OUT_X_MSB : FXOS8700_M_OUT_X_MSB; + /* + * Different register base addresses varies with channel types. + * This bug hasn't been noticed before because using an enum is + * really hard to read. Use an a switch statement to take over that. + */ + switch (chan_type) { + case IIO_ACCEL: + base = FXOS8700_OUT_X_MSB; + break; + case IIO_MAGN: + base = FXOS8700_M_OUT_X_MSB; + break; + default: + return -EINVAL; + } /* Block read 6 bytes of device output registers to avoid data loss */ ret = regmap_bulk_read(data->regmap, base, data->buf, - FXOS8700_DATA_BUF_SIZE); + sizeof(data->buf)); if (ret) return ret; /* Convert axis to buffer index */ reg = axis - IIO_MOD_X; + /* + * Convert to native endianness. The accel data and magn data + * are signed, so a forced type conversion is needed. + */ + tmp = be16_to_cpu(data->buf[reg]); + + /* + * ACCEL output data registers contain the X-axis, Y-axis, and Z-axis + * 14-bit left-justified sample data and MAGN output data registers + * contain the X-axis, Y-axis, and Z-axis 16-bit sample data. Apply + * a signed 2 bits right shift to the readback raw data from ACCEL + * output data register and keep that from MAGN sensor as the origin. + * Value should be extended to 32 bit. + */ + switch (chan_type) { + case IIO_ACCEL: + tmp = tmp >> 2; + break; + case IIO_MAGN: + /* Nothing to do */ + break; + default: + return -EINVAL; + } + /* Convert to native endianness */ - *val = sign_extend32(be16_to_cpu(data->buf[reg]), 15); + *val = sign_extend32(tmp, 15); return 0; } @@ -445,10 +508,9 @@ static int fxos8700_set_odr(struct fxos8700_data *data, enum fxos8700_sensor t, if (i >= odr_num) return -EINVAL; - return regmap_update_bits(data->regmap, - FXOS8700_CTRL_REG1, - FXOS8700_CTRL_ODR_MSK + FXOS8700_ACTIVE, - fxos8700_odr[i].bits << 3 | active_mode); + val &= ~FXOS8700_CTRL_ODR_MSK; + val |= FIELD_PREP(FXOS8700_CTRL_ODR_MSK, fxos8700_odr[i].bits) | FXOS8700_ACTIVE; + return regmap_write(data->regmap, FXOS8700_CTRL_REG1, val); } static int fxos8700_get_odr(struct fxos8700_data *data, enum fxos8700_sensor t, @@ -461,7 +523,7 @@ static int fxos8700_get_odr(struct fxos8700_data *data, enum fxos8700_sensor t, if (ret) return ret; - val &= FXOS8700_CTRL_ODR_MSK; + val = FIELD_GET(FXOS8700_CTRL_ODR_MSK, val); for (i = 0; i < odr_num; i++) if (val == fxos8700_odr[i].bits) @@ -526,7 +588,7 @@ static IIO_CONST_ATTR(in_accel_sampling_frequency_available, static IIO_CONST_ATTR(in_magn_sampling_frequency_available, "1.5625 6.25 12.5 50 100 200 400 800"); static IIO_CONST_ATTR(in_accel_scale_available, "0.000244 0.000488 0.000976"); -static IIO_CONST_ATTR(in_magn_scale_available, "0.000001200"); +static IIO_CONST_ATTR(in_magn_scale_available, "0.001000"); static struct attribute *fxos8700_attrs[] = { &iio_const_attr_in_accel_sampling_frequency_available.dev_attr.attr, @@ -592,14 +654,19 @@ static int fxos8700_chip_init(struct fxos8700_data *data, bool use_spi) if (ret) return ret; - /* Max ODR (800Hz individual or 400Hz hybrid), active mode */ - ret = regmap_write(data->regmap, FXOS8700_CTRL_REG1, - FXOS8700_CTRL_ODR_MAX | FXOS8700_ACTIVE); + /* + * Set max full-scale range (+/-8G) for ACCEL sensor in chip + * initialization then activate the device. + */ + ret = regmap_write(data->regmap, FXOS8700_XYZ_DATA_CFG, MODE_8G); if (ret) return ret; - /* Set for max full-scale range (+/-8G) */ - return regmap_write(data->regmap, FXOS8700_XYZ_DATA_CFG, MODE_8G); + /* Max ODR (800Hz individual or 400Hz hybrid), active mode */ + return regmap_update_bits(data->regmap, FXOS8700_CTRL_REG1, + FXOS8700_CTRL_ODR_MSK | FXOS8700_ACTIVE, + FIELD_PREP(FXOS8700_CTRL_ODR_MSK, FXOS8700_CTRL_ODR_MAX) | + FXOS8700_ACTIVE); } static void fxos8700_chip_uninit(void *data) diff --git a/drivers/iio/imu/st_lsm6dsx/Kconfig b/drivers/iio/imu/st_lsm6dsx/Kconfig index f6660847fb58..8c16cdacf2f2 100644 --- a/drivers/iio/imu/st_lsm6dsx/Kconfig +++ b/drivers/iio/imu/st_lsm6dsx/Kconfig @@ -4,6 +4,7 @@ config IIO_ST_LSM6DSX tristate "ST_LSM6DSx driver for STM 6-axis IMU MEMS sensors" depends on (I2C || SPI || I3C) select IIO_BUFFER + select IIO_TRIGGERED_BUFFER select IIO_KFIFO_BUF select IIO_ST_LSM6DSX_I2C if (I2C) select IIO_ST_LSM6DSX_SPI if (SPI_MASTER) diff --git a/drivers/iio/light/cm32181.c b/drivers/iio/light/cm32181.c index 001055d09750..b1674a5bfa36 100644 --- a/drivers/iio/light/cm32181.c +++ b/drivers/iio/light/cm32181.c @@ -440,6 +440,8 @@ static int cm32181_probe(struct i2c_client *client) if (!indio_dev) return -ENOMEM; + i2c_set_clientdata(client, indio_dev); + /* * Some ACPI systems list 2 I2C resources for the CM3218 sensor, the * SMBus Alert Response Address (ARA, 0x0c) and the actual I2C address. @@ -460,8 +462,6 @@ static int cm32181_probe(struct i2c_client *client) return PTR_ERR(client); } - i2c_set_clientdata(client, indio_dev); - cm32181 = iio_priv(indio_dev); cm32181->client = client; cm32181->dev = dev; @@ -490,7 +490,8 @@ static int cm32181_probe(struct i2c_client *client) static int cm32181_suspend(struct device *dev) { - struct i2c_client *client = to_i2c_client(dev); + struct cm32181_chip *cm32181 = iio_priv(dev_get_drvdata(dev)); + struct i2c_client *client = cm32181->client; return i2c_smbus_write_word_data(client, CM32181_REG_ADDR_CMD, CM32181_CMD_ALS_DISABLE); @@ -498,8 +499,8 @@ static int cm32181_suspend(struct device *dev) static int cm32181_resume(struct device *dev) { - struct i2c_client *client = to_i2c_client(dev); struct cm32181_chip *cm32181 = iio_priv(dev_get_drvdata(dev)); + struct i2c_client *client = cm32181->client; return i2c_smbus_write_word_data(client, CM32181_REG_ADDR_CMD, cm32181->conf_regs[CM32181_REG_ADDR_CMD]); diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h index 785c37cae3c0..5a2baf49ecaa 100644 --- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h +++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h @@ -89,13 +89,6 @@ struct bnxt_re_ring_attr { u8 mode; }; -struct bnxt_re_work { - struct work_struct work; - unsigned long event; - struct bnxt_re_dev *rdev; - struct net_device *vlan_dev; -}; - struct bnxt_re_sqp_entries { struct bnxt_qplib_sge sge; u64 wrid; @@ -132,10 +125,10 @@ struct bnxt_re_dev { #define BNXT_RE_FLAG_ERR_DEVICE_DETACHED 17 #define BNXT_RE_FLAG_ISSUE_ROCE_STATS 29 struct net_device *netdev; + struct notifier_block nb; unsigned int version, major, minor; struct bnxt_qplib_chip_ctx *chip_ctx; struct bnxt_en_dev *en_dev; - struct bnxt_msix_entry msix_entries[BNXT_RE_MAX_MSIX]; int num_msix; int id; @@ -194,5 +187,4 @@ static inline struct device *rdev_to_dev(struct bnxt_re_dev *rdev) return &rdev->ibdev.dev; return NULL; } - #endif diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 8c0c80a8d338..c5867e78f231 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -48,6 +48,7 @@ #include <net/ipv6.h> #include <net/addrconf.h> #include <linux/if_ether.h> +#include <linux/auxiliary_bus.h> #include <rdma/ib_verbs.h> #include <rdma/ib_user_verbs.h> @@ -74,14 +75,14 @@ MODULE_DESCRIPTION(BNXT_RE_DESC " Driver"); MODULE_LICENSE("Dual BSD/GPL"); /* globals */ -static struct list_head bnxt_re_dev_list = LIST_HEAD_INIT(bnxt_re_dev_list); -/* Mutex to protect the list of bnxt_re devices added */ -static DEFINE_MUTEX(bnxt_re_dev_lock); -static struct workqueue_struct *bnxt_re_wq; -static void bnxt_re_remove_device(struct bnxt_re_dev *rdev); -static void bnxt_re_dealloc_driver(struct ib_device *ib_dev); +static DEFINE_MUTEX(bnxt_re_mutex); + static void bnxt_re_stop_irq(void *handle); static void bnxt_re_dev_stop(struct bnxt_re_dev *rdev); +static int bnxt_re_netdev_event(struct notifier_block *notifier, + unsigned long event, void *ptr); +static struct bnxt_re_dev *bnxt_re_from_netdev(struct net_device *netdev); +static void bnxt_re_dev_uninit(struct bnxt_re_dev *rdev); static void bnxt_re_set_drv_mode(struct bnxt_re_dev *rdev, u8 mode) { @@ -111,16 +112,14 @@ static int bnxt_re_setup_chip_ctx(struct bnxt_re_dev *rdev, u8 wqe_mode) { struct bnxt_qplib_chip_ctx *chip_ctx; struct bnxt_en_dev *en_dev; - struct bnxt *bp; en_dev = rdev->en_dev; - bp = netdev_priv(en_dev->net); chip_ctx = kzalloc(sizeof(*chip_ctx), GFP_KERNEL); if (!chip_ctx) return -ENOMEM; - chip_ctx->chip_num = bp->chip_num; - chip_ctx->hw_stats_size = bp->hw_ring_stats_size; + chip_ctx->chip_num = en_dev->chip_num; + chip_ctx->hw_stats_size = en_dev->hw_ring_stats_size; rdev->chip_ctx = chip_ctx; /* rest members to follow eventually */ @@ -128,7 +127,7 @@ static int bnxt_re_setup_chip_ctx(struct bnxt_re_dev *rdev, u8 wqe_mode) rdev->qplib_res.cctx = rdev->chip_ctx; rdev->rcfw.res = &rdev->qplib_res; rdev->qplib_res.dattr = &rdev->dev_attr; - rdev->qplib_res.is_vf = BNXT_VF(bp); + rdev->qplib_res.is_vf = BNXT_EN_VF(en_dev); bnxt_re_set_drv_mode(rdev, wqe_mode); if (bnxt_qplib_determine_atomics(en_dev->pdev)) @@ -141,10 +140,7 @@ static int bnxt_re_setup_chip_ctx(struct bnxt_re_dev *rdev, u8 wqe_mode) static void bnxt_re_get_sriov_func_type(struct bnxt_re_dev *rdev) { - struct bnxt *bp; - - bp = netdev_priv(rdev->en_dev->net); - if (BNXT_VF(bp)) + if (BNXT_EN_VF(rdev->en_dev)) rdev->is_virtfn = 1; } @@ -225,56 +221,12 @@ static void bnxt_re_set_resource_limits(struct bnxt_re_dev *rdev) bnxt_re_limit_vf_res(&rdev->qplib_ctx, num_vfs); } -/* for handling bnxt_en callbacks later */ -static void bnxt_re_stop(void *p) -{ - struct bnxt_re_dev *rdev = p; - struct bnxt *bp; - - if (!rdev) - return; - ASSERT_RTNL(); - - /* L2 driver invokes this callback during device error/crash or device - * reset. Current RoCE driver doesn't recover the device in case of - * error. Handle the error by dispatching fatal events to all qps - * ie. by calling bnxt_re_dev_stop and release the MSIx vectors as - * L2 driver want to modify the MSIx table. - */ - bp = netdev_priv(rdev->netdev); - - ibdev_info(&rdev->ibdev, "Handle device stop call from L2 driver"); - /* Check the current device state from L2 structure and move the - * device to detached state if FW_FATAL_COND is set. - * This prevents more commands to HW during clean-up, - * in case the device is already in error. - */ - if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) - set_bit(ERR_DEVICE_DETACHED, &rdev->rcfw.cmdq.flags); - - bnxt_re_dev_stop(rdev); - bnxt_re_stop_irq(rdev); - /* Move the device states to detached and avoid sending any more - * commands to HW - */ - set_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags); - set_bit(ERR_DEVICE_DETACHED, &rdev->rcfw.cmdq.flags); -} - -static void bnxt_re_start(void *p) -{ -} - -static void bnxt_re_sriov_config(void *p, int num_vfs) +static void bnxt_re_vf_res_config(struct bnxt_re_dev *rdev) { - struct bnxt_re_dev *rdev = p; - - if (!rdev) - return; if (test_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags)) return; - rdev->num_vfs = num_vfs; + rdev->num_vfs = pci_sriov_get_totalvfs(rdev->en_dev->pdev); if (!bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)) { bnxt_re_set_resource_limits(rdev); bnxt_qplib_set_func_resources(&rdev->qplib_res, &rdev->rcfw, @@ -282,16 +234,14 @@ static void bnxt_re_sriov_config(void *p, int num_vfs) } } -static void bnxt_re_shutdown(void *p) +static void bnxt_re_shutdown(struct auxiliary_device *adev) { - struct bnxt_re_dev *rdev = p; + struct bnxt_re_dev *rdev = auxiliary_get_drvdata(adev); if (!rdev) return; - ASSERT_RTNL(); - /* Release the MSIx vectors before queuing unregister */ - bnxt_re_stop_irq(rdev); - ib_unregister_device_queued(&rdev->ibdev); + ib_unregister_device(&rdev->ibdev); + bnxt_re_dev_uninit(rdev); } static void bnxt_re_stop_irq(void *handle) @@ -312,7 +262,7 @@ static void bnxt_re_stop_irq(void *handle) static void bnxt_re_start_irq(void *handle, struct bnxt_msix_entry *ent) { struct bnxt_re_dev *rdev = (struct bnxt_re_dev *)handle; - struct bnxt_msix_entry *msix_ent = rdev->msix_entries; + struct bnxt_msix_entry *msix_ent = rdev->en_dev->msix_entries; struct bnxt_qplib_rcfw *rcfw = &rdev->rcfw; struct bnxt_qplib_nq *nq; int indx, rc; @@ -331,7 +281,7 @@ static void bnxt_re_start_irq(void *handle, struct bnxt_msix_entry *ent) * in device sctructure. */ for (indx = 0; indx < rdev->num_msix; indx++) - rdev->msix_entries[indx].vector = ent[indx].vector; + rdev->en_dev->msix_entries[indx].vector = ent[indx].vector; bnxt_qplib_rcfw_start_irq(rcfw, msix_ent[BNXT_RE_AEQ_IDX].vector, false); @@ -346,93 +296,22 @@ static void bnxt_re_start_irq(void *handle, struct bnxt_msix_entry *ent) } static struct bnxt_ulp_ops bnxt_re_ulp_ops = { - .ulp_async_notifier = NULL, - .ulp_stop = bnxt_re_stop, - .ulp_start = bnxt_re_start, - .ulp_sriov_config = bnxt_re_sriov_config, - .ulp_shutdown = bnxt_re_shutdown, .ulp_irq_stop = bnxt_re_stop_irq, .ulp_irq_restart = bnxt_re_start_irq }; /* RoCE -> Net driver */ -/* Driver registration routines used to let the networking driver (bnxt_en) - * to know that the RoCE driver is now installed - */ -static int bnxt_re_unregister_netdev(struct bnxt_re_dev *rdev) -{ - struct bnxt_en_dev *en_dev; - int rc; - - if (!rdev) - return -EINVAL; - - en_dev = rdev->en_dev; - - rc = en_dev->en_ops->bnxt_unregister_device(rdev->en_dev, - BNXT_ROCE_ULP); - return rc; -} - static int bnxt_re_register_netdev(struct bnxt_re_dev *rdev) { struct bnxt_en_dev *en_dev; int rc = 0; - if (!rdev) - return -EINVAL; - en_dev = rdev->en_dev; - rc = en_dev->en_ops->bnxt_register_device(en_dev, BNXT_ROCE_ULP, - &bnxt_re_ulp_ops, rdev); - rdev->qplib_res.pdev = rdev->en_dev->pdev; - return rc; -} - -static int bnxt_re_free_msix(struct bnxt_re_dev *rdev) -{ - struct bnxt_en_dev *en_dev; - int rc; - - if (!rdev) - return -EINVAL; - - en_dev = rdev->en_dev; - - - rc = en_dev->en_ops->bnxt_free_msix(rdev->en_dev, BNXT_ROCE_ULP); - - return rc; -} - -static int bnxt_re_request_msix(struct bnxt_re_dev *rdev) -{ - int rc = 0, num_msix_want = BNXT_RE_MAX_MSIX, num_msix_got; - struct bnxt_en_dev *en_dev; - - if (!rdev) - return -EINVAL; - - en_dev = rdev->en_dev; - - num_msix_want = min_t(u32, BNXT_RE_MAX_MSIX, num_online_cpus()); - - num_msix_got = en_dev->en_ops->bnxt_request_msix(en_dev, BNXT_ROCE_ULP, - rdev->msix_entries, - num_msix_want); - if (num_msix_got < BNXT_RE_MIN_MSIX) { - rc = -EINVAL; - goto done; - } - if (num_msix_got != num_msix_want) { - ibdev_warn(&rdev->ibdev, - "Requested %d MSI-X vectors, got %d\n", - num_msix_want, num_msix_got); - } - rdev->num_msix = num_msix_got; -done: + rc = bnxt_register_dev(en_dev, &bnxt_re_ulp_ops, rdev); + if (!rc) + rdev->qplib_res.pdev = rdev->en_dev->pdev; return rc; } @@ -458,12 +337,17 @@ static void bnxt_re_fill_fw_msg(struct bnxt_fw_msg *fw_msg, void *msg, static int bnxt_re_net_ring_free(struct bnxt_re_dev *rdev, u16 fw_ring_id, int type) { - struct bnxt_en_dev *en_dev = rdev->en_dev; + struct bnxt_en_dev *en_dev; struct hwrm_ring_free_input req = {0}; struct hwrm_ring_free_output resp; struct bnxt_fw_msg fw_msg; int rc = -EINVAL; + if (!rdev) + return rc; + + en_dev = rdev->en_dev; + if (!en_dev) return rc; @@ -477,7 +361,7 @@ static int bnxt_re_net_ring_free(struct bnxt_re_dev *rdev, req.ring_id = cpu_to_le16(fw_ring_id); bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp, sizeof(resp), DFLT_HWRM_CMD_TIMEOUT); - rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg); + rc = bnxt_send_msg(en_dev, &fw_msg); if (rc) ibdev_err(&rdev->ibdev, "Failed to free HW ring:%d :%#x", req.ring_id, rc); @@ -514,7 +398,7 @@ static int bnxt_re_net_ring_alloc(struct bnxt_re_dev *rdev, req.int_mode = ring_attr->mode; bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp, sizeof(resp), DFLT_HWRM_CMD_TIMEOUT); - rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg); + rc = bnxt_send_msg(en_dev, &fw_msg); if (!rc) *fw_ring_id = le16_to_cpu(resp.ring_id); @@ -542,7 +426,7 @@ static int bnxt_re_net_stats_ctx_free(struct bnxt_re_dev *rdev, req.stat_ctx_id = cpu_to_le32(fw_stats_ctx_id); bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp, sizeof(resp), DFLT_HWRM_CMD_TIMEOUT); - rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg); + rc = bnxt_send_msg(en_dev, &fw_msg); if (rc) ibdev_err(&rdev->ibdev, "Failed to free HW stats context %#x", rc); @@ -575,7 +459,7 @@ static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev, req.stat_ctx_flags = STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE; bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp, sizeof(resp), DFLT_HWRM_CMD_TIMEOUT); - rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg); + rc = bnxt_send_msg(en_dev, &fw_msg); if (!rc) *fw_stats_ctx_id = le32_to_cpu(resp.stat_ctx_id); @@ -584,21 +468,6 @@ static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev, /* Device */ -static bool is_bnxt_re_dev(struct net_device *netdev) -{ - struct ethtool_drvinfo drvinfo; - - if (netdev->ethtool_ops && netdev->ethtool_ops->get_drvinfo) { - memset(&drvinfo, 0, sizeof(drvinfo)); - netdev->ethtool_ops->get_drvinfo(netdev, &drvinfo); - - if (strcmp(drvinfo.driver, "bnxt_en")) - return false; - return true; - } - return false; -} - static struct bnxt_re_dev *bnxt_re_from_netdev(struct net_device *netdev) { struct ib_device *ibdev = @@ -609,31 +478,6 @@ static struct bnxt_re_dev *bnxt_re_from_netdev(struct net_device *netdev) return container_of(ibdev, struct bnxt_re_dev, ibdev); } -static struct bnxt_en_dev *bnxt_re_dev_probe(struct net_device *netdev) -{ - struct bnxt_en_dev *en_dev; - struct pci_dev *pdev; - - en_dev = bnxt_ulp_probe(netdev); - if (IS_ERR(en_dev)) - return en_dev; - - pdev = en_dev->pdev; - if (!pdev) - return ERR_PTR(-EINVAL); - - if (!(en_dev->flags & BNXT_EN_FLAG_ROCE_CAP)) { - dev_info(&pdev->dev, - "%s: probe error: RoCE is not supported on this device", - ROCE_DRV_MODULE_NAME); - return ERR_PTR(-ENODEV); - } - - dev_hold(netdev); - - return en_dev; -} - static ssize_t hw_rev_show(struct device *device, struct device_attribute *attr, char *buf) { @@ -679,7 +523,6 @@ static const struct ib_device_ops bnxt_re_dev_ops = { .create_qp = bnxt_re_create_qp, .create_srq = bnxt_re_create_srq, .create_user_ah = bnxt_re_create_ah, - .dealloc_driver = bnxt_re_dealloc_driver, .dealloc_pd = bnxt_re_dealloc_pd, .dealloc_ucontext = bnxt_re_dealloc_ucontext, .del_gid = bnxt_re_del_gid, @@ -744,18 +587,7 @@ static int bnxt_re_register_ib(struct bnxt_re_dev *rdev) return ib_register_device(ibdev, "bnxt_re%d", &rdev->en_dev->pdev->dev); } -static void bnxt_re_dev_remove(struct bnxt_re_dev *rdev) -{ - dev_put(rdev->netdev); - rdev->netdev = NULL; - mutex_lock(&bnxt_re_dev_lock); - list_del_rcu(&rdev->list); - mutex_unlock(&bnxt_re_dev_lock); - - synchronize_rcu(); -} - -static struct bnxt_re_dev *bnxt_re_dev_add(struct net_device *netdev, +static struct bnxt_re_dev *bnxt_re_dev_add(struct bnxt_aux_priv *aux_priv, struct bnxt_en_dev *en_dev) { struct bnxt_re_dev *rdev; @@ -768,8 +600,8 @@ static struct bnxt_re_dev *bnxt_re_dev_add(struct net_device *netdev, return NULL; } /* Default values */ - rdev->netdev = netdev; - dev_hold(rdev->netdev); + rdev->nb.notifier_call = NULL; + rdev->netdev = en_dev->net; rdev->en_dev = en_dev; rdev->id = rdev->en_dev->pdev->devfn; INIT_LIST_HEAD(&rdev->qp_list); @@ -784,9 +616,6 @@ static struct bnxt_re_dev *bnxt_re_dev_add(struct net_device *netdev, rdev->cosq[0] = 0xFFFF; rdev->cosq[1] = 0xFFFF; - mutex_lock(&bnxt_re_dev_lock); - list_add_tail_rcu(&rdev->list, &bnxt_re_dev_list); - mutex_unlock(&bnxt_re_dev_lock); return rdev; } @@ -930,7 +759,7 @@ static u32 bnxt_re_get_nqdb_offset(struct bnxt_re_dev *rdev, u16 indx) return bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx) ? (rdev->is_virtfn ? BNXT_RE_GEN_P5_VF_NQ_DB : BNXT_RE_GEN_P5_PF_NQ_DB) : - rdev->msix_entries[indx].db_offset; + rdev->en_dev->msix_entries[indx].db_offset; } static void bnxt_re_cleanup_res(struct bnxt_re_dev *rdev) @@ -955,7 +784,7 @@ static int bnxt_re_init_res(struct bnxt_re_dev *rdev) for (i = 1; i < rdev->num_msix ; i++) { db_offt = bnxt_re_get_nqdb_offset(rdev, i); rc = bnxt_qplib_enable_nq(rdev->en_dev->pdev, &rdev->nq[i - 1], - i - 1, rdev->msix_entries[i].vector, + i - 1, rdev->en_dev->msix_entries[i].vector, db_offt, &bnxt_re_cqn_handler, &bnxt_re_srqn_handler); if (rc) { @@ -1042,7 +871,7 @@ static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev) rattr.type = type; rattr.mode = RING_ALLOC_REQ_INT_MODE_MSIX; rattr.depth = BNXT_QPLIB_NQE_MAX_CNT - 1; - rattr.lrid = rdev->msix_entries[i + 1].ring_idx; + rattr.lrid = rdev->en_dev->msix_entries[i + 1].ring_idx; rc = bnxt_re_net_ring_alloc(rdev, &rattr, &nq->ring_id); if (rc) { ibdev_err(&rdev->ibdev, @@ -1095,7 +924,6 @@ static int bnxt_re_query_hwrm_pri2cos(struct bnxt_re_dev *rdev, u8 dir, u64 *cid_map) { struct hwrm_queue_pri2cos_qcfg_input req = {0}; - struct bnxt *bp = netdev_priv(rdev->netdev); struct hwrm_queue_pri2cos_qcfg_output resp; struct bnxt_en_dev *en_dev = rdev->en_dev; struct bnxt_fw_msg fw_msg; @@ -1112,11 +940,11 @@ static int bnxt_re_query_hwrm_pri2cos(struct bnxt_re_dev *rdev, u8 dir, flags |= (dir & 0x01); flags |= HWRM_QUEUE_PRI2COS_QCFG_INPUT_FLAGS_IVLAN; req.flags = cpu_to_le32(flags); - req.port_id = bp->pf.port_id; + req.port_id = en_dev->pf_port_id; bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp, sizeof(resp), DFLT_HWRM_CMD_TIMEOUT); - rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg); + rc = bnxt_send_msg(en_dev, &fw_msg); if (rc) return rc; @@ -1299,7 +1127,7 @@ static void bnxt_re_query_hwrm_intf_version(struct bnxt_re_dev *rdev) req.hwrm_intf_upd = HWRM_VERSION_UPDATE; bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp, sizeof(resp), DFLT_HWRM_CMD_TIMEOUT); - rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg); + rc = bnxt_send_msg(en_dev, &fw_msg); if (rc) { ibdev_err(&rdev->ibdev, "Failed to query HW version, rc = 0x%x", rc); @@ -1323,7 +1151,7 @@ static int bnxt_re_ib_init(struct bnxt_re_dev *rdev) pr_err("Failed to register with IB: %#x\n", rc); return rc; } - dev_info(rdev_to_dev(rdev), "Device registered successfully"); + dev_info(rdev_to_dev(rdev), "Device registered with IB successfully"); ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed, &rdev->active_width); set_bit(BNXT_RE_FLAG_ISSUE_ROCE_STATS, &rdev->flags); @@ -1362,20 +1190,12 @@ static void bnxt_re_dev_uninit(struct bnxt_re_dev *rdev) bnxt_re_net_ring_free(rdev, rdev->rcfw.creq.ring_id, type); bnxt_qplib_free_rcfw_channel(&rdev->rcfw); } - if (test_and_clear_bit(BNXT_RE_FLAG_GOT_MSIX, &rdev->flags)) { - rc = bnxt_re_free_msix(rdev); - if (rc) - ibdev_warn(&rdev->ibdev, - "Failed to free MSI-X vectors: %#x", rc); - } + if (test_and_clear_bit(BNXT_RE_FLAG_GOT_MSIX, &rdev->flags)) + rdev->num_msix = 0; bnxt_re_destroy_chip_ctx(rdev); - if (test_and_clear_bit(BNXT_RE_FLAG_NETDEV_REGISTERED, &rdev->flags)) { - rc = bnxt_re_unregister_netdev(rdev); - if (rc) - ibdev_warn(&rdev->ibdev, - "Failed to unregister with netdev: %#x", rc); - } + if (test_and_clear_bit(BNXT_RE_FLAG_NETDEV_REGISTERED, &rdev->flags)) + bnxt_unregister_dev(rdev->en_dev); } /* worker thread for polling periodic events. Now used for QoS programming*/ @@ -1416,13 +1236,15 @@ static int bnxt_re_dev_init(struct bnxt_re_dev *rdev, u8 wqe_mode) /* Check whether VF or PF */ bnxt_re_get_sriov_func_type(rdev); - rc = bnxt_re_request_msix(rdev); - if (rc) { + if (!rdev->en_dev->ulp_tbl->msix_requested) { ibdev_err(&rdev->ibdev, "Failed to get MSI-X vectors: %#x\n", rc); rc = -EINVAL; goto fail; } + ibdev_dbg(&rdev->ibdev, "Got %d MSI-X vectors\n", + rdev->en_dev->ulp_tbl->msix_requested); + rdev->num_msix = rdev->en_dev->ulp_tbl->msix_requested; set_bit(BNXT_RE_FLAG_GOT_MSIX, &rdev->flags); bnxt_re_query_hwrm_intf_version(rdev); @@ -1446,14 +1268,14 @@ static int bnxt_re_dev_init(struct bnxt_re_dev *rdev, u8 wqe_mode) rattr.type = type; rattr.mode = RING_ALLOC_REQ_INT_MODE_MSIX; rattr.depth = BNXT_QPLIB_CREQE_MAX_CNT - 1; - rattr.lrid = rdev->msix_entries[BNXT_RE_AEQ_IDX].ring_idx; + rattr.lrid = rdev->en_dev->msix_entries[BNXT_RE_AEQ_IDX].ring_idx; rc = bnxt_re_net_ring_alloc(rdev, &rattr, &creq->ring_id); if (rc) { ibdev_err(&rdev->ibdev, "Failed to allocate CREQ: %#x\n", rc); goto free_rcfw; } db_offt = bnxt_re_get_nqdb_offset(rdev, BNXT_RE_AEQ_IDX); - vid = rdev->msix_entries[BNXT_RE_AEQ_IDX].vector; + vid = rdev->en_dev->msix_entries[BNXT_RE_AEQ_IDX].vector; rc = bnxt_qplib_enable_rcfw_channel(&rdev->rcfw, vid, db_offt, rdev->is_virtfn, &bnxt_re_aeq_handler); @@ -1521,6 +1343,11 @@ static int bnxt_re_dev_init(struct bnxt_re_dev *rdev, u8 wqe_mode) INIT_DELAYED_WORK(&rdev->worker, bnxt_re_worker); set_bit(BNXT_RE_FLAG_QOS_WORK_REG, &rdev->flags); schedule_delayed_work(&rdev->worker, msecs_to_jiffies(30000)); + /* + * Use the total VF count since the actual VF count may not be + * available at this point. + */ + bnxt_re_vf_res_config(rdev); } return 0; @@ -1541,135 +1368,43 @@ fail: return rc; } -static void bnxt_re_dev_unreg(struct bnxt_re_dev *rdev) -{ - struct net_device *netdev = rdev->netdev; - - bnxt_re_dev_remove(rdev); - - if (netdev) - dev_put(netdev); -} - -static int bnxt_re_dev_reg(struct bnxt_re_dev **rdev, struct net_device *netdev) +static int bnxt_re_add_device(struct auxiliary_device *adev, u8 wqe_mode) { + struct bnxt_aux_priv *aux_priv = + container_of(adev, struct bnxt_aux_priv, aux_dev); struct bnxt_en_dev *en_dev; + struct bnxt_re_dev *rdev; int rc = 0; - if (!is_bnxt_re_dev(netdev)) - return -ENODEV; + /* en_dev should never be NULL as long as adev and aux_dev are valid. */ + en_dev = aux_priv->edev; - en_dev = bnxt_re_dev_probe(netdev); - if (IS_ERR(en_dev)) { - if (en_dev != ERR_PTR(-ENODEV)) - ibdev_err(&(*rdev)->ibdev, "%s: Failed to probe\n", - ROCE_DRV_MODULE_NAME); - rc = PTR_ERR(en_dev); - goto exit; - } - *rdev = bnxt_re_dev_add(netdev, en_dev); - if (!*rdev) { + rdev = bnxt_re_dev_add(aux_priv, en_dev); + if (!rdev || !rdev_to_dev(rdev)) { rc = -ENOMEM; - dev_put(netdev); goto exit; } -exit: - return rc; -} -static void bnxt_re_remove_device(struct bnxt_re_dev *rdev) -{ - bnxt_re_dev_uninit(rdev); - pci_dev_put(rdev->en_dev->pdev); - bnxt_re_dev_unreg(rdev); -} - -static int bnxt_re_add_device(struct bnxt_re_dev **rdev, - struct net_device *netdev, u8 wqe_mode) -{ - int rc; - - rc = bnxt_re_dev_reg(rdev, netdev); - if (rc == -ENODEV) - return rc; - if (rc) { - pr_err("Failed to register with the device %s: %#x\n", - netdev->name, rc); - return rc; - } + rc = bnxt_re_dev_init(rdev, wqe_mode); + if (rc) + goto re_dev_dealloc; - pci_dev_get((*rdev)->en_dev->pdev); - rc = bnxt_re_dev_init(*rdev, wqe_mode); + rc = bnxt_re_ib_init(rdev); if (rc) { - pci_dev_put((*rdev)->en_dev->pdev); - bnxt_re_dev_unreg(*rdev); + pr_err("Failed to register with IB: %s", + aux_priv->aux_dev.name); + goto re_dev_uninit; } + auxiliary_set_drvdata(adev, rdev); - return rc; -} - -static void bnxt_re_dealloc_driver(struct ib_device *ib_dev) -{ - struct bnxt_re_dev *rdev = - container_of(ib_dev, struct bnxt_re_dev, ibdev); - - dev_info(rdev_to_dev(rdev), "Unregistering Device"); - - rtnl_lock(); - bnxt_re_remove_device(rdev); - rtnl_unlock(); -} - -/* Handle all deferred netevents tasks */ -static void bnxt_re_task(struct work_struct *work) -{ - struct bnxt_re_work *re_work; - struct bnxt_re_dev *rdev; - int rc = 0; - - re_work = container_of(work, struct bnxt_re_work, work); - rdev = re_work->rdev; - - if (re_work->event == NETDEV_REGISTER) { - rc = bnxt_re_ib_init(rdev); - if (rc) { - ibdev_err(&rdev->ibdev, - "Failed to register with IB: %#x", rc); - rtnl_lock(); - bnxt_re_remove_device(rdev); - rtnl_unlock(); - goto exit; - } - goto exit; - } - - if (!ib_device_try_get(&rdev->ibdev)) - goto exit; + return 0; - switch (re_work->event) { - case NETDEV_UP: - bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, - IB_EVENT_PORT_ACTIVE); - break; - case NETDEV_DOWN: - bnxt_re_dev_stop(rdev); - break; - case NETDEV_CHANGE: - if (!netif_carrier_ok(rdev->netdev)) - bnxt_re_dev_stop(rdev); - else if (netif_carrier_ok(rdev->netdev)) - bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, - IB_EVENT_PORT_ACTIVE); - ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed, - &rdev->active_width); - break; - default: - break; - } - ib_device_put(&rdev->ibdev); +re_dev_uninit: + bnxt_re_dev_uninit(rdev); +re_dev_dealloc: + ib_dealloc_device(&rdev->ibdev); exit: - put_device(&rdev->ibdev.dev); - kfree(re_work); + return rc; } /* @@ -1690,109 +1425,189 @@ static int bnxt_re_netdev_event(struct notifier_block *notifier, unsigned long event, void *ptr) { struct net_device *real_dev, *netdev = netdev_notifier_info_to_dev(ptr); - struct bnxt_re_work *re_work; struct bnxt_re_dev *rdev; - int rc = 0; - bool sch_work = false; - bool release = true; real_dev = rdma_vlan_dev_real_dev(netdev); if (!real_dev) real_dev = netdev; - rdev = bnxt_re_from_netdev(real_dev); - if (!rdev && event != NETDEV_REGISTER) - return NOTIFY_OK; - if (real_dev != netdev) goto exit; - switch (event) { - case NETDEV_REGISTER: - if (rdev) - break; - rc = bnxt_re_add_device(&rdev, real_dev, - BNXT_QPLIB_WQE_MODE_STATIC); - if (!rc) - sch_work = true; - release = false; - break; + rdev = bnxt_re_from_netdev(real_dev); + if (!rdev) + return NOTIFY_DONE; - case NETDEV_UNREGISTER: - ib_unregister_device_queued(&rdev->ibdev); - break; + switch (event) { + case NETDEV_UP: + case NETDEV_DOWN: + case NETDEV_CHANGE: + bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, + netif_carrier_ok(real_dev) ? + IB_EVENT_PORT_ACTIVE : + IB_EVENT_PORT_ERR); + break; default: - sch_work = true; break; } - if (sch_work) { - /* Allocate for the deferred task */ - re_work = kzalloc(sizeof(*re_work), GFP_KERNEL); - if (re_work) { - get_device(&rdev->ibdev.dev); - re_work->rdev = rdev; - re_work->event = event; - re_work->vlan_dev = (real_dev == netdev ? - NULL : netdev); - INIT_WORK(&re_work->work, bnxt_re_task); - queue_work(bnxt_re_wq, &re_work->work); - } - } - + ib_device_put(&rdev->ibdev); exit: - if (rdev && release) - ib_device_put(&rdev->ibdev); return NOTIFY_DONE; } -static struct notifier_block bnxt_re_netdev_notifier = { - .notifier_call = bnxt_re_netdev_event -}; +#define BNXT_ADEV_NAME "bnxt_en" -static int __init bnxt_re_mod_init(void) +static void bnxt_re_remove(struct auxiliary_device *adev) { - int rc = 0; + struct bnxt_re_dev *rdev = auxiliary_get_drvdata(adev); - pr_info("%s: %s", ROCE_DRV_MODULE_NAME, version); + if (!rdev) + return; - bnxt_re_wq = create_singlethread_workqueue("bnxt_re"); - if (!bnxt_re_wq) - return -ENOMEM; + mutex_lock(&bnxt_re_mutex); + if (rdev->nb.notifier_call) { + unregister_netdevice_notifier(&rdev->nb); + rdev->nb.notifier_call = NULL; + } else { + /* If notifier is null, we should have already done a + * clean up before coming here. + */ + goto skip_remove; + } + + ib_unregister_device(&rdev->ibdev); + ib_dealloc_device(&rdev->ibdev); + bnxt_re_dev_uninit(rdev); +skip_remove: + mutex_unlock(&bnxt_re_mutex); +} + +static int bnxt_re_probe(struct auxiliary_device *adev, + const struct auxiliary_device_id *id) +{ + struct bnxt_re_dev *rdev; + int rc; - INIT_LIST_HEAD(&bnxt_re_dev_list); + mutex_lock(&bnxt_re_mutex); + rc = bnxt_re_add_device(adev, BNXT_QPLIB_WQE_MODE_STATIC); + if (rc) { + mutex_unlock(&bnxt_re_mutex); + return rc; + } + + rdev = auxiliary_get_drvdata(adev); - rc = register_netdevice_notifier(&bnxt_re_netdev_notifier); + rdev->nb.notifier_call = bnxt_re_netdev_event; + rc = register_netdevice_notifier(&rdev->nb); if (rc) { + rdev->nb.notifier_call = NULL; pr_err("%s: Cannot register to netdevice_notifier", ROCE_DRV_MODULE_NAME); - goto err_netdev; + goto err; } + + mutex_unlock(&bnxt_re_mutex); return 0; -err_netdev: - destroy_workqueue(bnxt_re_wq); +err: + mutex_unlock(&bnxt_re_mutex); + bnxt_re_remove(adev); return rc; } -static void __exit bnxt_re_mod_exit(void) +static int bnxt_re_suspend(struct auxiliary_device *adev, pm_message_t state) { - struct bnxt_re_dev *rdev; + struct bnxt_re_dev *rdev = auxiliary_get_drvdata(adev); - unregister_netdevice_notifier(&bnxt_re_netdev_notifier); - if (bnxt_re_wq) - destroy_workqueue(bnxt_re_wq); - list_for_each_entry(rdev, &bnxt_re_dev_list, list) { - /* VF device removal should be called before the removal - * of PF device. Queue VFs unregister first, so that VFs - * shall be removed before the PF during the call of - * ib_unregister_driver. - */ - if (rdev->is_virtfn) - ib_unregister_device(&rdev->ibdev); + if (!rdev) + return 0; + + mutex_lock(&bnxt_re_mutex); + /* L2 driver may invoke this callback during device error/crash or device + * reset. Current RoCE driver doesn't recover the device in case of + * error. Handle the error by dispatching fatal events to all qps + * ie. by calling bnxt_re_dev_stop and release the MSIx vectors as + * L2 driver want to modify the MSIx table. + */ + + ibdev_info(&rdev->ibdev, "Handle device suspend call"); + /* Check the current device state from bnxt_en_dev and move the + * device to detached state if FW_FATAL_COND is set. + * This prevents more commands to HW during clean-up, + * in case the device is already in error. + */ + if (test_bit(BNXT_STATE_FW_FATAL_COND, &rdev->en_dev->en_state)) + set_bit(ERR_DEVICE_DETACHED, &rdev->rcfw.cmdq.flags); + + bnxt_re_dev_stop(rdev); + bnxt_re_stop_irq(rdev); + /* Move the device states to detached and avoid sending any more + * commands to HW + */ + set_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags); + set_bit(ERR_DEVICE_DETACHED, &rdev->rcfw.cmdq.flags); + mutex_unlock(&bnxt_re_mutex); + + return 0; +} + +static int bnxt_re_resume(struct auxiliary_device *adev) +{ + struct bnxt_re_dev *rdev = auxiliary_get_drvdata(adev); + + if (!rdev) + return 0; + + mutex_lock(&bnxt_re_mutex); + /* L2 driver may invoke this callback during device recovery, resume. + * reset. Current RoCE driver doesn't recover the device in case of + * error. Handle the error by dispatching fatal events to all qps + * ie. by calling bnxt_re_dev_stop and release the MSIx vectors as + * L2 driver want to modify the MSIx table. + */ + + ibdev_info(&rdev->ibdev, "Handle device resume call"); + mutex_unlock(&bnxt_re_mutex); + + return 0; +} + +static const struct auxiliary_device_id bnxt_re_id_table[] = { + { .name = BNXT_ADEV_NAME ".rdma", }, + {}, +}; + +MODULE_DEVICE_TABLE(auxiliary, bnxt_re_id_table); + +static struct auxiliary_driver bnxt_re_driver = { + .name = "rdma", + .probe = bnxt_re_probe, + .remove = bnxt_re_remove, + .shutdown = bnxt_re_shutdown, + .suspend = bnxt_re_suspend, + .resume = bnxt_re_resume, + .id_table = bnxt_re_id_table, +}; + +static int __init bnxt_re_mod_init(void) +{ + int rc = 0; + + pr_info("%s: %s", ROCE_DRV_MODULE_NAME, version); + rc = auxiliary_driver_register(&bnxt_re_driver); + if (rc) { + pr_err("%s: Failed to register auxiliary driver\n", + ROCE_DRV_MODULE_NAME); + return rc; } - ib_unregister_driver(RDMA_DRIVER_BNXT_RE); + return 0; +} + +static void __exit bnxt_re_mod_exit(void) +{ + auxiliary_driver_unregister(&bnxt_re_driver); } module_init(bnxt_re_mod_init); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index c669ef6e47e7..dc32e4518a28 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -3012,26 +3012,63 @@ static void mlx5_eth_lag_cleanup(struct mlx5_ib_dev *dev) } } -static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u32 port_num) +static void mlx5_netdev_notifier_register(struct mlx5_roce *roce, + struct net_device *netdev) { int err; - dev->port[port_num].roce.nb.notifier_call = mlx5_netdev_event; - err = register_netdevice_notifier(&dev->port[port_num].roce.nb); - if (err) { - dev->port[port_num].roce.nb.notifier_call = NULL; - return err; - } + if (roce->tracking_netdev) + return; + roce->tracking_netdev = netdev; + roce->nb.notifier_call = mlx5_netdev_event; + err = register_netdevice_notifier_dev_net(netdev, &roce->nb, &roce->nn); + WARN_ON(err); +} - return 0; +static void mlx5_netdev_notifier_unregister(struct mlx5_roce *roce) +{ + if (!roce->tracking_netdev) + return; + unregister_netdevice_notifier_dev_net(roce->tracking_netdev, &roce->nb, + &roce->nn); + roce->tracking_netdev = NULL; } -static void mlx5_remove_netdev_notifier(struct mlx5_ib_dev *dev, u32 port_num) +static int mlx5e_mdev_notifier_event(struct notifier_block *nb, + unsigned long event, void *data) { - if (dev->port[port_num].roce.nb.notifier_call) { - unregister_netdevice_notifier(&dev->port[port_num].roce.nb); - dev->port[port_num].roce.nb.notifier_call = NULL; + struct mlx5_roce *roce = container_of(nb, struct mlx5_roce, mdev_nb); + struct net_device *netdev = data; + + switch (event) { + case MLX5_DRIVER_EVENT_UPLINK_NETDEV: + if (netdev) + mlx5_netdev_notifier_register(roce, netdev); + else + mlx5_netdev_notifier_unregister(roce); + break; + default: + return NOTIFY_DONE; } + + return NOTIFY_OK; +} + +static void mlx5_mdev_netdev_track(struct mlx5_ib_dev *dev, u32 port_num) +{ + struct mlx5_roce *roce = &dev->port[port_num].roce; + + roce->mdev_nb.notifier_call = mlx5e_mdev_notifier_event; + mlx5_blocking_notifier_register(dev->mdev, &roce->mdev_nb); + mlx5_core_uplink_netdev_event_replay(dev->mdev); +} + +static void mlx5_mdev_netdev_untrack(struct mlx5_ib_dev *dev, u32 port_num) +{ + struct mlx5_roce *roce = &dev->port[port_num].roce; + + mlx5_blocking_notifier_unregister(dev->mdev, &roce->mdev_nb); + mlx5_netdev_notifier_unregister(roce); } static int mlx5_enable_eth(struct mlx5_ib_dev *dev) @@ -3138,7 +3175,7 @@ static void mlx5_ib_unbind_slave_port(struct mlx5_ib_dev *ibdev, if (mpi->mdev_events.notifier_call) mlx5_notifier_unregister(mpi->mdev, &mpi->mdev_events); mpi->mdev_events.notifier_call = NULL; - mlx5_remove_netdev_notifier(ibdev, port_num); + mlx5_mdev_netdev_untrack(ibdev, port_num); spin_lock(&port->mp.mpi_lock); comps = mpi->mdev_refcnt; @@ -3196,12 +3233,7 @@ static bool mlx5_ib_bind_slave_port(struct mlx5_ib_dev *ibdev, if (err) goto unbind; - err = mlx5_add_netdev_notifier(ibdev, port_num); - if (err) { - mlx5_ib_err(ibdev, "failed adding netdev notifier for port %u\n", - port_num + 1); - goto unbind; - } + mlx5_mdev_netdev_track(ibdev, port_num); mpi->mdev_events.notifier_call = mlx5_ib_event_slave_port; mlx5_notifier_register(mpi->mdev, &mpi->mdev_events); @@ -3909,9 +3941,7 @@ static int mlx5_ib_roce_init(struct mlx5_ib_dev *dev) port_num = mlx5_core_native_port_num(dev->mdev) - 1; /* Register only for native ports */ - err = mlx5_add_netdev_notifier(dev, port_num); - if (err) - return err; + mlx5_mdev_netdev_track(dev, port_num); err = mlx5_enable_eth(dev); if (err) @@ -3920,7 +3950,7 @@ static int mlx5_ib_roce_init(struct mlx5_ib_dev *dev) return 0; cleanup: - mlx5_remove_netdev_notifier(dev, port_num); + mlx5_mdev_netdev_untrack(dev, port_num); return err; } @@ -3938,7 +3968,7 @@ static void mlx5_ib_roce_cleanup(struct mlx5_ib_dev *dev) mlx5_disable_eth(dev); port_num = mlx5_core_native_port_num(dev->mdev) - 1; - mlx5_remove_netdev_notifier(dev, port_num); + mlx5_mdev_netdev_untrack(dev, port_num); } } diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 8b91babdd4c0..7394e7f36ba7 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -832,6 +832,9 @@ struct mlx5_roce { rwlock_t netdev_lock; struct net_device *netdev; struct notifier_block nb; + struct netdev_net_notifier nn; + struct notifier_block mdev_nb; + struct net_device *tracking_netdev; atomic_t tx_port_affinity; enum ib_port_state last_port_state; struct mlx5_ib_dev *dev; diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index b0f776448a1c..fa021af8506e 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -192,7 +192,6 @@ static const char * const smbus_pnp_ids[] = { "SYN3221", /* HP 15-ay000 */ "SYN323d", /* HP Spectre X360 13-w013dx */ "SYN3257", /* HP Envy 13-ad105ng */ - "SYN3286", /* HP Laptop 15-da3001TU */ NULL }; diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h index 46f8a694291e..efc61736099b 100644 --- a/drivers/input/serio/i8042-acpipnpio.h +++ b/drivers/input/serio/i8042-acpipnpio.h @@ -1240,6 +1240,13 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { }, { .matches = { + DMI_MATCH(DMI_BOARD_NAME, "PCX0DX"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "X170SM"), }, .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | diff --git a/drivers/md/bcache/bcache_ondisk.h b/drivers/md/bcache/bcache_ondisk.h index 97413586195b..f96034e0ba4f 100644 --- a/drivers/md/bcache/bcache_ondisk.h +++ b/drivers/md/bcache/bcache_ondisk.h @@ -106,7 +106,8 @@ static inline unsigned long bkey_bytes(const struct bkey *k) return bkey_u64s(k) * sizeof(__u64); } -#define bkey_copy(_dest, _src) memcpy(_dest, _src, bkey_bytes(_src)) +#define bkey_copy(_dest, _src) unsafe_memcpy(_dest, _src, bkey_bytes(_src), \ + /* bkey is always padded */) static inline void bkey_copy_key(struct bkey *dest, const struct bkey *src) { diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index e5da469a4235..c182c21de2e8 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -149,7 +149,8 @@ add: bytes, GFP_KERNEL); if (!i) return -ENOMEM; - memcpy(&i->j, j, bytes); + unsafe_memcpy(&i->j, j, bytes, + /* "bytes" was calculated by set_bytes() above */); /* Add to the location after 'where' points to */ list_add(&i->list, where); ret = 1; diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index fc3758a5bc1c..53e495223ea0 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -2149,8 +2149,6 @@ int vb2_core_streamon(struct vb2_queue *q, unsigned int type) if (ret) return ret; - q->streaming = 1; - /* * Tell driver to start streaming provided sufficient buffers * are available. @@ -2161,12 +2159,13 @@ int vb2_core_streamon(struct vb2_queue *q, unsigned int type) goto unprepare; } + q->streaming = 1; + dprintk(q, 3, "successful\n"); return 0; unprepare: call_void_qop(q, unprepare_streaming, q); - q->streaming = 0; return ret; } EXPORT_SYMBOL_GPL(vb2_core_streamon); diff --git a/drivers/media/v4l2-core/v4l2-ctrls-api.c b/drivers/media/v4l2-core/v4l2-ctrls-api.c index 3d3b6dc24ca6..002ea6588edf 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-api.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-api.c @@ -150,8 +150,8 @@ static int user_to_new(struct v4l2_ext_control *c, struct v4l2_ctrl *ctrl) * then return an error. */ if (strlen(ctrl->p_new.p_char) == ctrl->maximum && last) - ctrl->is_new = 1; return -ERANGE; + ctrl->is_new = 1; } return ret; default: diff --git a/drivers/mfd/ocelot-core.c b/drivers/mfd/ocelot-core.c index 1816d52c65c5..b0ff05c1759f 100644 --- a/drivers/mfd/ocelot-core.c +++ b/drivers/mfd/ocelot-core.c @@ -34,16 +34,49 @@ #define VSC7512_MIIM0_RES_START 0x7107009c #define VSC7512_MIIM1_RES_START 0x710700c0 -#define VSC7512_MIIM_RES_SIZE 0x024 +#define VSC7512_MIIM_RES_SIZE 0x00000024 #define VSC7512_PHY_RES_START 0x710700f0 -#define VSC7512_PHY_RES_SIZE 0x004 +#define VSC7512_PHY_RES_SIZE 0x00000004 #define VSC7512_GPIO_RES_START 0x71070034 -#define VSC7512_GPIO_RES_SIZE 0x06c +#define VSC7512_GPIO_RES_SIZE 0x0000006c #define VSC7512_SIO_CTRL_RES_START 0x710700f8 -#define VSC7512_SIO_CTRL_RES_SIZE 0x100 +#define VSC7512_SIO_CTRL_RES_SIZE 0x00000100 + +#define VSC7512_ANA_RES_START 0x71880000 +#define VSC7512_ANA_RES_SIZE 0x00010000 + +#define VSC7512_QS_RES_START 0x71080000 +#define VSC7512_QS_RES_SIZE 0x00000100 + +#define VSC7512_QSYS_RES_START 0x71800000 +#define VSC7512_QSYS_RES_SIZE 0x00200000 + +#define VSC7512_REW_RES_START 0x71030000 +#define VSC7512_REW_RES_SIZE 0x00010000 + +#define VSC7512_SYS_RES_START 0x71010000 +#define VSC7512_SYS_RES_SIZE 0x00010000 + +#define VSC7512_S0_RES_START 0x71040000 +#define VSC7512_S1_RES_START 0x71050000 +#define VSC7512_S2_RES_START 0x71060000 +#define VCAP_RES_SIZE 0x00000400 + +#define VSC7512_PORT_0_RES_START 0x711e0000 +#define VSC7512_PORT_1_RES_START 0x711f0000 +#define VSC7512_PORT_2_RES_START 0x71200000 +#define VSC7512_PORT_3_RES_START 0x71210000 +#define VSC7512_PORT_4_RES_START 0x71220000 +#define VSC7512_PORT_5_RES_START 0x71230000 +#define VSC7512_PORT_6_RES_START 0x71240000 +#define VSC7512_PORT_7_RES_START 0x71250000 +#define VSC7512_PORT_8_RES_START 0x71260000 +#define VSC7512_PORT_9_RES_START 0x71270000 +#define VSC7512_PORT_10_RES_START 0x71280000 +#define VSC7512_PORT_RES_SIZE 0x00010000 #define VSC7512_GCB_RST_SLEEP_US 100 #define VSC7512_GCB_RST_TIMEOUT_US 100000 @@ -96,6 +129,28 @@ static const struct resource vsc7512_sgpio_resources[] = { DEFINE_RES_REG_NAMED(VSC7512_SIO_CTRL_RES_START, VSC7512_SIO_CTRL_RES_SIZE, "gcb_sio"), }; +static const struct resource vsc7512_switch_resources[] = { + DEFINE_RES_REG_NAMED(VSC7512_ANA_RES_START, VSC7512_ANA_RES_SIZE, "ana"), + DEFINE_RES_REG_NAMED(VSC7512_QS_RES_START, VSC7512_QS_RES_SIZE, "qs"), + DEFINE_RES_REG_NAMED(VSC7512_QSYS_RES_START, VSC7512_QSYS_RES_SIZE, "qsys"), + DEFINE_RES_REG_NAMED(VSC7512_REW_RES_START, VSC7512_REW_RES_SIZE, "rew"), + DEFINE_RES_REG_NAMED(VSC7512_SYS_RES_START, VSC7512_SYS_RES_SIZE, "sys"), + DEFINE_RES_REG_NAMED(VSC7512_S0_RES_START, VCAP_RES_SIZE, "s0"), + DEFINE_RES_REG_NAMED(VSC7512_S1_RES_START, VCAP_RES_SIZE, "s1"), + DEFINE_RES_REG_NAMED(VSC7512_S2_RES_START, VCAP_RES_SIZE, "s2"), + DEFINE_RES_REG_NAMED(VSC7512_PORT_0_RES_START, VSC7512_PORT_RES_SIZE, "port0"), + DEFINE_RES_REG_NAMED(VSC7512_PORT_1_RES_START, VSC7512_PORT_RES_SIZE, "port1"), + DEFINE_RES_REG_NAMED(VSC7512_PORT_2_RES_START, VSC7512_PORT_RES_SIZE, "port2"), + DEFINE_RES_REG_NAMED(VSC7512_PORT_3_RES_START, VSC7512_PORT_RES_SIZE, "port3"), + DEFINE_RES_REG_NAMED(VSC7512_PORT_4_RES_START, VSC7512_PORT_RES_SIZE, "port4"), + DEFINE_RES_REG_NAMED(VSC7512_PORT_5_RES_START, VSC7512_PORT_RES_SIZE, "port5"), + DEFINE_RES_REG_NAMED(VSC7512_PORT_6_RES_START, VSC7512_PORT_RES_SIZE, "port6"), + DEFINE_RES_REG_NAMED(VSC7512_PORT_7_RES_START, VSC7512_PORT_RES_SIZE, "port7"), + DEFINE_RES_REG_NAMED(VSC7512_PORT_8_RES_START, VSC7512_PORT_RES_SIZE, "port8"), + DEFINE_RES_REG_NAMED(VSC7512_PORT_9_RES_START, VSC7512_PORT_RES_SIZE, "port9"), + DEFINE_RES_REG_NAMED(VSC7512_PORT_10_RES_START, VSC7512_PORT_RES_SIZE, "port10") +}; + static const struct mfd_cell vsc7512_devs[] = { { .name = "ocelot-pinctrl", @@ -121,6 +176,11 @@ static const struct mfd_cell vsc7512_devs[] = { .use_of_reg = true, .num_resources = ARRAY_SIZE(vsc7512_miim1_resources), .resources = vsc7512_miim1_resources, + }, { + .name = "ocelot-switch", + .of_compatible = "mscc,vsc7512-switch", + .num_resources = ARRAY_SIZE(vsc7512_switch_resources), + .resources = vsc7512_switch_resources, }, }; diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c index 4f9b4a18c74c..594094526648 100644 --- a/drivers/net/bonding/bond_debugfs.c +++ b/drivers/net/bonding/bond_debugfs.c @@ -76,7 +76,7 @@ void bond_debug_reregister(struct bonding *bond) d = debugfs_rename(bonding_debug_root, bond->debug_dir, bonding_debug_root, bond->dev->name); - if (d) { + if (!IS_ERR(d)) { bond->debug_dir = d; } else { netdev_warn(bond->dev, "failed to reregister, so just unregister old one\n"); diff --git a/drivers/net/can/dev/bittiming.c b/drivers/net/can/dev/bittiming.c index 7ae80763c960..0b93900b1dfa 100644 --- a/drivers/net/can/dev/bittiming.c +++ b/drivers/net/can/dev/bittiming.c @@ -6,25 +6,81 @@ #include <linux/can/dev.h> +void can_sjw_set_default(struct can_bittiming *bt) +{ + if (bt->sjw) + return; + + /* If user space provides no sjw, use sane default of phase_seg2 / 2 */ + bt->sjw = max(1U, min(bt->phase_seg1, bt->phase_seg2 / 2)); +} + +int can_sjw_check(const struct net_device *dev, const struct can_bittiming *bt, + const struct can_bittiming_const *btc, struct netlink_ext_ack *extack) +{ + if (bt->sjw > btc->sjw_max) { + NL_SET_ERR_MSG_FMT(extack, "sjw: %u greater than max sjw: %u", + bt->sjw, btc->sjw_max); + return -EINVAL; + } + + if (bt->sjw > bt->phase_seg1) { + NL_SET_ERR_MSG_FMT(extack, + "sjw: %u greater than phase-seg1: %u", + bt->sjw, bt->phase_seg1); + return -EINVAL; + } + + if (bt->sjw > bt->phase_seg2) { + NL_SET_ERR_MSG_FMT(extack, + "sjw: %u greater than phase-seg2: %u", + bt->sjw, bt->phase_seg2); + return -EINVAL; + } + + return 0; +} + /* Checks the validity of the specified bit-timing parameters prop_seg, * phase_seg1, phase_seg2 and sjw and tries to determine the bitrate * prescaler value brp. You can find more information in the header * file linux/can/netlink.h. */ static int can_fixup_bittiming(const struct net_device *dev, struct can_bittiming *bt, - const struct can_bittiming_const *btc) + const struct can_bittiming_const *btc, + struct netlink_ext_ack *extack) { + const unsigned int tseg1 = bt->prop_seg + bt->phase_seg1; const struct can_priv *priv = netdev_priv(dev); - unsigned int tseg1, alltseg; u64 brp64; + int err; - tseg1 = bt->prop_seg + bt->phase_seg1; - if (!bt->sjw) - bt->sjw = 1; - if (bt->sjw > btc->sjw_max || - tseg1 < btc->tseg1_min || tseg1 > btc->tseg1_max || - bt->phase_seg2 < btc->tseg2_min || bt->phase_seg2 > btc->tseg2_max) - return -ERANGE; + if (tseg1 < btc->tseg1_min) { + NL_SET_ERR_MSG_FMT(extack, "prop-seg + phase-seg1: %u less than tseg1-min: %u", + tseg1, btc->tseg1_min); + return -EINVAL; + } + if (tseg1 > btc->tseg1_max) { + NL_SET_ERR_MSG_FMT(extack, "prop-seg + phase-seg1: %u greater than tseg1-max: %u", + tseg1, btc->tseg1_max); + return -EINVAL; + } + if (bt->phase_seg2 < btc->tseg2_min) { + NL_SET_ERR_MSG_FMT(extack, "phase-seg2: %u less than tseg2-min: %u", + bt->phase_seg2, btc->tseg2_min); + return -EINVAL; + } + if (bt->phase_seg2 > btc->tseg2_max) { + NL_SET_ERR_MSG_FMT(extack, "phase-seg2: %u greater than tseg2-max: %u", + bt->phase_seg2, btc->tseg2_max); + return -EINVAL; + } + + can_sjw_set_default(bt); + + err = can_sjw_check(dev, bt, btc, extack); + if (err) + return err; brp64 = (u64)priv->clock.freq * (u64)bt->tq; if (btc->brp_inc > 1) @@ -35,12 +91,21 @@ static int can_fixup_bittiming(const struct net_device *dev, struct can_bittimin brp64 *= btc->brp_inc; bt->brp = (u32)brp64; - if (bt->brp < btc->brp_min || bt->brp > btc->brp_max) + if (bt->brp < btc->brp_min) { + NL_SET_ERR_MSG_FMT(extack, "resulting brp: %u less than brp-min: %u", + bt->brp, btc->brp_min); + return -EINVAL; + } + if (bt->brp > btc->brp_max) { + NL_SET_ERR_MSG_FMT(extack, "resulting brp: %u greater than brp-max: %u", + bt->brp, btc->brp_max); return -EINVAL; + } - alltseg = bt->prop_seg + bt->phase_seg1 + bt->phase_seg2 + 1; - bt->bitrate = priv->clock.freq / (bt->brp * alltseg); - bt->sample_point = ((tseg1 + 1) * 1000) / alltseg; + bt->bitrate = priv->clock.freq / (bt->brp * can_bit_time(bt)); + bt->sample_point = ((CAN_SYNC_SEG + tseg1) * 1000) / can_bit_time(bt); + bt->tq = DIV_U64_ROUND_CLOSEST(mul_u32_u32(bt->brp, NSEC_PER_SEC), + priv->clock.freq); return 0; } @@ -49,7 +114,8 @@ static int can_fixup_bittiming(const struct net_device *dev, struct can_bittimin static int can_validate_bitrate(const struct net_device *dev, const struct can_bittiming *bt, const u32 *bitrate_const, - const unsigned int bitrate_const_cnt) + const unsigned int bitrate_const_cnt, + struct netlink_ext_ack *extack) { unsigned int i; @@ -58,30 +124,30 @@ can_validate_bitrate(const struct net_device *dev, const struct can_bittiming *b return 0; } + NL_SET_ERR_MSG_FMT(extack, "bitrate %u bps not supported", + bt->brp); + return -EINVAL; } int can_get_bittiming(const struct net_device *dev, struct can_bittiming *bt, const struct can_bittiming_const *btc, const u32 *bitrate_const, - const unsigned int bitrate_const_cnt) + const unsigned int bitrate_const_cnt, + struct netlink_ext_ack *extack) { - int err; - /* Depending on the given can_bittiming parameter structure the CAN * timing parameters are calculated based on the provided bitrate OR * alternatively the CAN timing parameters (tq, prop_seg, etc.) are * provided directly which are then checked and fixed up. */ if (!bt->tq && bt->bitrate && btc) - err = can_calc_bittiming(dev, bt, btc); - else if (bt->tq && !bt->bitrate && btc) - err = can_fixup_bittiming(dev, bt, btc); - else if (!bt->tq && bt->bitrate && bitrate_const) - err = can_validate_bitrate(dev, bt, bitrate_const, - bitrate_const_cnt); - else - err = -EINVAL; - - return err; + return can_calc_bittiming(dev, bt, btc, extack); + if (bt->tq && !bt->bitrate && btc) + return can_fixup_bittiming(dev, bt, btc, extack); + if (!bt->tq && bt->bitrate && bitrate_const) + return can_validate_bitrate(dev, bt, bitrate_const, + bitrate_const_cnt, extack); + + return -EINVAL; } diff --git a/drivers/net/can/dev/calc_bittiming.c b/drivers/net/can/dev/calc_bittiming.c index d3caa040614d..3809c148fb88 100644 --- a/drivers/net/can/dev/calc_bittiming.c +++ b/drivers/net/can/dev/calc_bittiming.c @@ -63,7 +63,7 @@ can_update_sample_point(const struct can_bittiming_const *btc, } int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, - const struct can_bittiming_const *btc) + const struct can_bittiming_const *btc, struct netlink_ext_ack *extack) { struct can_priv *priv = netdev_priv(dev); unsigned int bitrate; /* current bitrate */ @@ -76,6 +76,7 @@ int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, unsigned int best_brp = 0; /* current best value for brp */ unsigned int brp, tsegall, tseg, tseg1 = 0, tseg2 = 0; u64 v64; + int err; /* Use CiA recommended sample points */ if (bt->sample_point) { @@ -133,13 +134,14 @@ int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, do_div(v64, bt->bitrate); bitrate_error = (u32)v64; if (bitrate_error > CAN_CALC_MAX_ERROR) { - netdev_err(dev, - "bitrate error %d.%d%% too high\n", - bitrate_error / 10, bitrate_error % 10); - return -EDOM; + NL_SET_ERR_MSG_FMT(extack, + "bitrate error: %u.%u%% too high", + bitrate_error / 10, bitrate_error % 10); + return -EINVAL; } - netdev_warn(dev, "bitrate error %d.%d%%\n", - bitrate_error / 10, bitrate_error % 10); + NL_SET_ERR_MSG_FMT(extack, + "bitrate error: %u.%u%%", + bitrate_error / 10, bitrate_error % 10); } /* real sample point */ @@ -154,23 +156,17 @@ int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, bt->phase_seg1 = tseg1 - bt->prop_seg; bt->phase_seg2 = tseg2; - /* check for sjw user settings */ - if (!bt->sjw || !btc->sjw_max) { - bt->sjw = 1; - } else { - /* bt->sjw is at least 1 -> sanitize upper bound to sjw_max */ - if (bt->sjw > btc->sjw_max) - bt->sjw = btc->sjw_max; - /* bt->sjw must not be higher than tseg2 */ - if (tseg2 < bt->sjw) - bt->sjw = tseg2; - } + can_sjw_set_default(bt); + + err = can_sjw_check(dev, bt, btc, extack); + if (err) + return err; bt->brp = best_brp; /* real bitrate */ bt->bitrate = priv->clock.freq / - (bt->brp * (CAN_SYNC_SEG + tseg1 + tseg2)); + (bt->brp * can_bit_time(bt)); return 0; } diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c index c1956b1e9faf..7f9334a8af50 100644 --- a/drivers/net/can/dev/dev.c +++ b/drivers/net/can/dev/dev.c @@ -498,6 +498,18 @@ static int can_get_termination(struct net_device *ndev) return 0; } +static bool +can_bittiming_const_valid(const struct can_bittiming_const *btc) +{ + if (!btc) + return true; + + if (!btc->sjw_max) + return false; + + return true; +} + /* Register the CAN network device */ int register_candev(struct net_device *dev) { @@ -518,6 +530,15 @@ int register_candev(struct net_device *dev) if (!priv->data_bitrate_const != !priv->data_bitrate_const_cnt) return -EINVAL; + /* We only support either fixed bit rates or bit timing const. */ + if ((priv->bitrate_const || priv->data_bitrate_const) && + (priv->bittiming_const || priv->data_bittiming_const)) + return -EINVAL; + + if (!can_bittiming_const_valid(priv->bittiming_const) || + !can_bittiming_const_valid(priv->data_bittiming_const)) + return -EINVAL; + if (!priv->termination_const) { err = can_get_termination(dev); if (err) diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index 8efa22d9f214..036d85ef07f5 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -36,10 +36,24 @@ static const struct nla_policy can_tdc_policy[IFLA_CAN_TDC_MAX + 1] = { [IFLA_CAN_TDC_TDCF] = { .type = NLA_U32 }, }; +static int can_validate_bittiming(const struct can_bittiming *bt, + struct netlink_ext_ack *extack) +{ + /* sample point is in one-tenth of a percent */ + if (bt->sample_point >= 1000) { + NL_SET_ERR_MSG(extack, "sample point must be between 0 and 100%"); + + return -EINVAL; + } + + return 0; +} + static int can_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { bool is_can_fd = false; + int err; /* Make sure that valid CAN FD configurations always consist of * - nominal/arbitration bittiming @@ -51,6 +65,15 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[], if (!data) return 0; + if (data[IFLA_CAN_BITTIMING]) { + struct can_bittiming bt; + + memcpy(&bt, nla_data(data[IFLA_CAN_BITTIMING]), sizeof(bt)); + err = can_validate_bittiming(&bt, extack); + if (err) + return err; + } + if (data[IFLA_CAN_CTRLMODE]) { struct can_ctrlmode *cm = nla_data(data[IFLA_CAN_CTRLMODE]); u32 tdc_flags = cm->flags & CAN_CTRLMODE_TDC_MASK; @@ -71,7 +94,6 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[], */ if (data[IFLA_CAN_TDC]) { struct nlattr *tb_tdc[IFLA_CAN_TDC_MAX + 1]; - int err; err = nla_parse_nested(tb_tdc, IFLA_CAN_TDC_MAX, data[IFLA_CAN_TDC], @@ -102,6 +124,15 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[], return -EOPNOTSUPP; } + if (data[IFLA_CAN_DATA_BITTIMING]) { + struct can_bittiming bt; + + memcpy(&bt, nla_data(data[IFLA_CAN_DATA_BITTIMING]), sizeof(bt)); + err = can_validate_bittiming(&bt, extack); + if (err) + return err; + } + return 0; } @@ -184,13 +215,15 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], err = can_get_bittiming(dev, &bt, priv->bittiming_const, priv->bitrate_const, - priv->bitrate_const_cnt); + priv->bitrate_const_cnt, + extack); if (err) return err; if (priv->bitrate_max && bt.bitrate > priv->bitrate_max) { - netdev_err(dev, "arbitration bitrate surpasses transceiver capabilities of %d bps\n", - priv->bitrate_max); + NL_SET_ERR_MSG_FMT(extack, + "arbitration bitrate %u bps surpasses transceiver capabilities of %u bps", + bt.bitrate, priv->bitrate_max); return -EINVAL; } @@ -288,13 +321,15 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], err = can_get_bittiming(dev, &dbt, priv->data_bittiming_const, priv->data_bitrate_const, - priv->data_bitrate_const_cnt); + priv->data_bitrate_const_cnt, + extack); if (err) return err; if (priv->bitrate_max && dbt.bitrate > priv->bitrate_max) { - netdev_err(dev, "canfd data bitrate surpasses transceiver capabilities of %d bps\n", - priv->bitrate_max); + NL_SET_ERR_MSG_FMT(extack, + "CANFD data bitrate %u bps surpasses transceiver capabilities of %u bps", + dbt.bitrate, priv->bitrate_max); return -EINVAL; } diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c index f6fa7157b99b..ef4e1b9a9e1e 100644 --- a/drivers/net/can/rcar/rcar_canfd.c +++ b/drivers/net/can/rcar/rcar_canfd.c @@ -21,23 +21,23 @@ * wherever it is modified to a readable name. */ -#include <linux/module.h> -#include <linux/moduleparam.h> -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/interrupt.h> +#include <linux/bitmap.h> +#include <linux/bitops.h> +#include <linux/can/dev.h> +#include <linux/clk.h> #include <linux/errno.h> #include <linux/ethtool.h> +#include <linux/interrupt.h> +#include <linux/iopoll.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/moduleparam.h> #include <linux/netdevice.h> -#include <linux/platform_device.h> -#include <linux/can/dev.h> -#include <linux/clk.h> #include <linux/of.h> #include <linux/of_device.h> -#include <linux/bitmap.h> -#include <linux/bitops.h> -#include <linux/iopoll.h> +#include <linux/platform_device.h> #include <linux/reset.h> +#include <linux/types.h> #define RCANFD_DRV_NAME "rcar_canfd" @@ -82,8 +82,8 @@ #define RCANFD_GERFL_DEF BIT(0) #define RCANFD_GERFL_ERR(gpriv, x) \ - ((x) & (reg_v3u(gpriv, RCANFD_GERFL_EEF0_7, \ - RCANFD_GERFL_EEF(0) | RCANFD_GERFL_EEF(1)) | \ + ((x) & (reg_gen4(gpriv, RCANFD_GERFL_EEF0_7, \ + RCANFD_GERFL_EEF(0) | RCANFD_GERFL_EEF(1)) | \ RCANFD_GERFL_MES | \ ((gpriv)->fdmode ? RCANFD_GERFL_CMPOF : 0))) @@ -91,16 +91,16 @@ /* RSCFDnCFDGAFLCFG0 / RSCFDnGAFLCFG0 */ #define RCANFD_GAFLCFG_SETRNC(gpriv, n, x) \ - (((x) & reg_v3u(gpriv, 0x1ff, 0xff)) << \ - (reg_v3u(gpriv, 16, 24) - (n) * reg_v3u(gpriv, 16, 8))) + (((x) & reg_gen4(gpriv, 0x1ff, 0xff)) << \ + (reg_gen4(gpriv, 16, 24) - ((n) & 1) * reg_gen4(gpriv, 16, 8))) #define RCANFD_GAFLCFG_GETRNC(gpriv, n, x) \ - (((x) >> (reg_v3u(gpriv, 16, 24) - (n) * reg_v3u(gpriv, 16, 8))) & \ - reg_v3u(gpriv, 0x1ff, 0xff)) + (((x) >> (reg_gen4(gpriv, 16, 24) - ((n) & 1) * reg_gen4(gpriv, 16, 8))) & \ + reg_gen4(gpriv, 0x1ff, 0xff)) /* RSCFDnCFDGAFLECTR / RSCFDnGAFLECTR */ #define RCANFD_GAFLECTR_AFLDAE BIT(8) -#define RCANFD_GAFLECTR_AFLPN(gpriv, x) ((x) & reg_v3u(gpriv, 0x7f, 0x1f)) +#define RCANFD_GAFLECTR_AFLPN(gpriv, x) ((x) & reg_gen4(gpriv, 0x7f, 0x1f)) /* RSCFDnCFDGAFLIDj / RSCFDnGAFLIDj */ #define RCANFD_GAFLID_GAFLLB BIT(29) @@ -118,13 +118,13 @@ /* RSCFDnCFDCmNCFG - CAN FD only */ #define RCANFD_NCFG_NTSEG2(gpriv, x) \ - (((x) & reg_v3u(gpriv, 0x7f, 0x1f)) << reg_v3u(gpriv, 25, 24)) + (((x) & reg_gen4(gpriv, 0x7f, 0x1f)) << reg_gen4(gpriv, 25, 24)) #define RCANFD_NCFG_NTSEG1(gpriv, x) \ - (((x) & reg_v3u(gpriv, 0xff, 0x7f)) << reg_v3u(gpriv, 17, 16)) + (((x) & reg_gen4(gpriv, 0xff, 0x7f)) << reg_gen4(gpriv, 17, 16)) #define RCANFD_NCFG_NSJW(gpriv, x) \ - (((x) & reg_v3u(gpriv, 0x7f, 0x1f)) << reg_v3u(gpriv, 10, 11)) + (((x) & reg_gen4(gpriv, 0x7f, 0x1f)) << reg_gen4(gpriv, 10, 11)) #define RCANFD_NCFG_NBRP(x) (((x) & 0x3ff) << 0) @@ -186,19 +186,19 @@ #define RCANFD_CERFL_ERR(x) ((x) & (0x7fff)) /* above bits 14:0 */ /* RSCFDnCFDCmDCFG */ -#define RCANFD_DCFG_DSJW(x) (((x) & 0x7) << 24) +#define RCANFD_DCFG_DSJW(gpriv, x) (((x) & reg_gen4(gpriv, 0xf, 0x7)) << 24) #define RCANFD_DCFG_DTSEG2(gpriv, x) \ - (((x) & reg_v3u(gpriv, 0x0f, 0x7)) << reg_v3u(gpriv, 16, 20)) + (((x) & reg_gen4(gpriv, 0x0f, 0x7)) << reg_gen4(gpriv, 16, 20)) #define RCANFD_DCFG_DTSEG1(gpriv, x) \ - (((x) & reg_v3u(gpriv, 0x1f, 0xf)) << reg_v3u(gpriv, 8, 16)) + (((x) & reg_gen4(gpriv, 0x1f, 0xf)) << reg_gen4(gpriv, 8, 16)) #define RCANFD_DCFG_DBRP(x) (((x) & 0xff) << 0) /* RSCFDnCFDCmFDCFG */ -#define RCANFD_FDCFG_CLOE BIT(30) -#define RCANFD_FDCFG_FDOE BIT(28) +#define RCANFD_GEN4_FDCFG_CLOE BIT(30) +#define RCANFD_GEN4_FDCFG_FDOE BIT(28) #define RCANFD_FDCFG_TDCE BIT(9) #define RCANFD_FDCFG_TDCOC BIT(8) #define RCANFD_FDCFG_TDCO(x) (((x) & 0x7f) >> 16) @@ -233,10 +233,11 @@ /* Common FIFO bits */ /* RSCFDnCFDCFCCk */ -#define RCANFD_CFCC_CFTML(gpriv, x) (((x) & 0xf) << reg_v3u(gpriv, 16, 20)) -#define RCANFD_CFCC_CFM(gpriv, x) (((x) & 0x3) << reg_v3u(gpriv, 8, 16)) +#define RCANFD_CFCC_CFTML(gpriv, x) \ + (((x) & reg_gen4(gpriv, 0x1f, 0xf)) << reg_gen4(gpriv, 16, 20)) +#define RCANFD_CFCC_CFM(gpriv, x) (((x) & 0x3) << reg_gen4(gpriv, 8, 16)) #define RCANFD_CFCC_CFIM BIT(12) -#define RCANFD_CFCC_CFDC(gpriv, x) (((x) & 0x7) << reg_v3u(gpriv, 21, 8)) +#define RCANFD_CFCC_CFDC(gpriv, x) (((x) & 0x7) << reg_gen4(gpriv, 21, 8)) #define RCANFD_CFCC_CFPLS(x) (((x) & 0x7) << 4) #define RCANFD_CFCC_CFTXIE BIT(2) #define RCANFD_CFCC_CFE BIT(0) @@ -304,7 +305,7 @@ #define RCANFD_RMND(y) (0x00a8 + (0x04 * (y))) /* RSCFDnCFDRFCCx / RSCFDnRFCCx */ -#define RCANFD_RFCC(gpriv, x) (reg_v3u(gpriv, 0x00c0, 0x00b8) + (0x04 * (x))) +#define RCANFD_RFCC(gpriv, x) (reg_gen4(gpriv, 0x00c0, 0x00b8) + (0x04 * (x))) /* RSCFDnCFDRFSTSx / RSCFDnRFSTSx */ #define RCANFD_RFSTS(gpriv, x) (RCANFD_RFCC(gpriv, x) + 0x20) /* RSCFDnCFDRFPCTRx / RSCFDnRFPCTRx */ @@ -314,13 +315,13 @@ /* RSCFDnCFDCFCCx / RSCFDnCFCCx */ #define RCANFD_CFCC(gpriv, ch, idx) \ - (reg_v3u(gpriv, 0x0120, 0x0118) + (0x0c * (ch)) + (0x04 * (idx))) + (reg_gen4(gpriv, 0x0120, 0x0118) + (0x0c * (ch)) + (0x04 * (idx))) /* RSCFDnCFDCFSTSx / RSCFDnCFSTSx */ #define RCANFD_CFSTS(gpriv, ch, idx) \ - (reg_v3u(gpriv, 0x01e0, 0x0178) + (0x0c * (ch)) + (0x04 * (idx))) + (reg_gen4(gpriv, 0x01e0, 0x0178) + (0x0c * (ch)) + (0x04 * (idx))) /* RSCFDnCFDCFPCTRx / RSCFDnCFPCTRx */ #define RCANFD_CFPCTR(gpriv, ch, idx) \ - (reg_v3u(gpriv, 0x0240, 0x01d8) + (0x0c * (ch)) + (0x04 * (idx))) + (reg_gen4(gpriv, 0x0240, 0x01d8) + (0x0c * (ch)) + (0x04 * (idx))) /* RSCFDnCFDFESTS / RSCFDnFESTS */ #define RCANFD_FESTS (0x0238) @@ -428,16 +429,15 @@ /* RSCFDnRPGACCr */ #define RCANFD_C_RPGACC(r) (0x1900 + (0x04 * (r))) -/* R-Car V3U Classical and CAN FD mode specific register map */ -#define RCANFD_V3U_CFDCFG (0x1314) -#define RCANFD_V3U_DCFG(m) (0x1400 + (0x20 * (m))) +/* R-Car Gen4 Classical and CAN FD mode specific register map */ +#define RCANFD_GEN4_FDCFG(m) (0x1404 + (0x20 * (m))) -#define RCANFD_V3U_GAFL_OFFSET (0x1800) +#define RCANFD_GEN4_GAFL_OFFSET (0x1800) /* CAN FD mode specific register map */ /* RSCFDnCFDCmXXX -> RCANFD_F_XXX(m) */ -#define RCANFD_F_DCFG(m) (0x0500 + (0x20 * (m))) +#define RCANFD_F_DCFG(gpriv, m) (reg_gen4(gpriv, 0x1400, 0x0500) + (0x20 * (m))) #define RCANFD_F_CFDCFG(m) (0x0504 + (0x20 * (m))) #define RCANFD_F_CFDCTR(m) (0x0508 + (0x20 * (m))) #define RCANFD_F_CFDSTS(m) (0x050c + (0x20 * (m))) @@ -453,7 +453,7 @@ #define RCANFD_F_RMDF(q, b) (0x200c + (0x04 * (b)) + (0x20 * (q))) /* RSCFDnCFDRFXXx -> RCANFD_F_RFXX(x) */ -#define RCANFD_F_RFOFFSET(gpriv) reg_v3u(gpriv, 0x6000, 0x3000) +#define RCANFD_F_RFOFFSET(gpriv) reg_gen4(gpriv, 0x6000, 0x3000) #define RCANFD_F_RFID(gpriv, x) (RCANFD_F_RFOFFSET(gpriv) + (0x80 * (x))) #define RCANFD_F_RFPTR(gpriv, x) (RCANFD_F_RFOFFSET(gpriv) + 0x04 + (0x80 * (x))) #define RCANFD_F_RFFDSTS(gpriv, x) (RCANFD_F_RFOFFSET(gpriv) + 0x08 + (0x80 * (x))) @@ -461,7 +461,7 @@ (RCANFD_F_RFOFFSET(gpriv) + 0x0c + (0x80 * (x)) + (0x04 * (df))) /* RSCFDnCFDCFXXk -> RCANFD_F_CFXX(ch, k) */ -#define RCANFD_F_CFOFFSET(gpriv) reg_v3u(gpriv, 0x6400, 0x3400) +#define RCANFD_F_CFOFFSET(gpriv) reg_gen4(gpriv, 0x6400, 0x3400) #define RCANFD_F_CFID(gpriv, ch, idx) \ (RCANFD_F_CFOFFSET(gpriv) + (0x180 * (ch)) + (0x80 * (idx))) @@ -597,28 +597,28 @@ static const struct rcar_canfd_hw_info rcar_gen3_hw_info = { .shared_global_irqs = 1, }; +static const struct rcar_canfd_hw_info rcar_gen4_hw_info = { + .max_channels = 8, + .postdiv = 2, + .shared_global_irqs = 1, +}; + static const struct rcar_canfd_hw_info rzg2l_hw_info = { .max_channels = 2, .postdiv = 1, .multi_channel_irqs = 1, }; -static const struct rcar_canfd_hw_info r8a779a0_hw_info = { - .max_channels = 8, - .postdiv = 2, - .shared_global_irqs = 1, -}; - /* Helper functions */ -static inline bool is_v3u(struct rcar_canfd_global *gpriv) +static inline bool is_gen4(struct rcar_canfd_global *gpriv) { - return gpriv->info == &r8a779a0_hw_info; + return gpriv->info == &rcar_gen4_hw_info; } -static inline u32 reg_v3u(struct rcar_canfd_global *gpriv, - u32 v3u, u32 not_v3u) +static inline u32 reg_gen4(struct rcar_canfd_global *gpriv, + u32 gen4, u32 not_gen4) { - return is_v3u(gpriv) ? v3u : not_v3u; + return is_gen4(gpriv) ? gen4 : not_gen4; } static inline void rcar_canfd_update(u32 mask, u32 val, u32 __iomem *reg) @@ -688,13 +688,14 @@ static void rcar_canfd_tx_failure_cleanup(struct net_device *ndev) static void rcar_canfd_set_mode(struct rcar_canfd_global *gpriv) { - if (is_v3u(gpriv)) { - if (gpriv->fdmode) - rcar_canfd_set_bit(gpriv->base, RCANFD_V3U_CFDCFG, - RCANFD_FDCFG_FDOE); - else - rcar_canfd_set_bit(gpriv->base, RCANFD_V3U_CFDCFG, - RCANFD_FDCFG_CLOE); + if (is_gen4(gpriv)) { + u32 ch, val = gpriv->fdmode ? RCANFD_GEN4_FDCFG_FDOE + : RCANFD_GEN4_FDCFG_CLOE; + + for_each_set_bit(ch, &gpriv->channels_mask, + gpriv->info->max_channels) + rcar_canfd_set_bit(gpriv->base, RCANFD_GEN4_FDCFG(ch), + val); } else { if (gpriv->fdmode) rcar_canfd_set_bit(gpriv->base, RCANFD_GRMCFG, @@ -814,8 +815,8 @@ static void rcar_canfd_configure_afl_rules(struct rcar_canfd_global *gpriv, /* Write number of rules for channel */ rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLCFG(ch), RCANFD_GAFLCFG_SETRNC(gpriv, ch, num_rules)); - if (is_v3u(gpriv)) - offset = RCANFD_V3U_GAFL_OFFSET; + if (is_gen4(gpriv)) + offset = RCANFD_GEN4_GAFL_OFFSET; else if (gpriv->fdmode) offset = RCANFD_F_GAFL_OFFSET; else @@ -1343,17 +1344,14 @@ static void rcar_canfd_set_bittiming(struct net_device *dev) tseg2 = dbt->phase_seg2 - 1; cfg = (RCANFD_DCFG_DTSEG1(gpriv, tseg1) | RCANFD_DCFG_DBRP(brp) | - RCANFD_DCFG_DSJW(sjw) | RCANFD_DCFG_DTSEG2(gpriv, tseg2)); + RCANFD_DCFG_DSJW(gpriv, sjw) | RCANFD_DCFG_DTSEG2(gpriv, tseg2)); - if (is_v3u(gpriv)) - rcar_canfd_write(priv->base, RCANFD_V3U_DCFG(ch), cfg); - else - rcar_canfd_write(priv->base, RCANFD_F_DCFG(ch), cfg); + rcar_canfd_write(priv->base, RCANFD_F_DCFG(gpriv, ch), cfg); netdev_dbg(priv->ndev, "drate: brp %u, sjw %u, tseg1 %u, tseg2 %u\n", brp, sjw, tseg1, tseg2); } else { /* Classical CAN only mode */ - if (is_v3u(gpriv)) { + if (is_gen4(gpriv)) { cfg = (RCANFD_NCFG_NTSEG1(gpriv, tseg1) | RCANFD_NCFG_NBRP(brp) | RCANFD_NCFG_NSJW(gpriv, sjw) | @@ -1510,7 +1508,7 @@ static netdev_tx_t rcar_canfd_start_xmit(struct sk_buff *skb, dlc = RCANFD_CFPTR_CFDLC(can_fd_len2dlc(cf->len)); - if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) || is_v3u(gpriv)) { + if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) || is_gen4(gpriv)) { rcar_canfd_write(priv->base, RCANFD_F_CFID(gpriv, ch, RCANFD_CFFIFO_IDX), id); rcar_canfd_write(priv->base, @@ -1569,7 +1567,7 @@ static void rcar_canfd_rx_pkt(struct rcar_canfd_channel *priv) u32 ch = priv->channel; u32 ridx = ch + RCANFD_RFFIFO_IDX; - if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) || is_v3u(gpriv)) { + if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) || is_gen4(gpriv)) { id = rcar_canfd_read(priv->base, RCANFD_F_RFID(gpriv, ridx)); dlc = rcar_canfd_read(priv->base, RCANFD_F_RFPTR(gpriv, ridx)); @@ -1620,7 +1618,7 @@ static void rcar_canfd_rx_pkt(struct rcar_canfd_channel *priv) cf->len = can_cc_dlc2len(RCANFD_RFPTR_RFDLC(dlc)); if (id & RCANFD_RFID_RFRTR) cf->can_id |= CAN_RTR_FLAG; - else if (is_v3u(gpriv)) + else if (is_gen4(gpriv)) rcar_canfd_get_data(priv, cf, RCANFD_F_RFDF(gpriv, ridx, 0)); else rcar_canfd_get_data(priv, cf, RCANFD_C_RFDF(ridx, 0)); @@ -1717,13 +1715,14 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch, { const struct rcar_canfd_hw_info *info = gpriv->info; struct platform_device *pdev = gpriv->pdev; + struct device *dev = &pdev->dev; struct rcar_canfd_channel *priv; struct net_device *ndev; int err = -ENODEV; ndev = alloc_candev(sizeof(*priv), RCANFD_FIFO_DEPTH); if (!ndev) { - dev_err(&pdev->dev, "alloc_candev() failed\n"); + dev_err(dev, "alloc_candev() failed\n"); return -ENOMEM; } priv = netdev_priv(ndev); @@ -1736,7 +1735,7 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch, priv->channel = ch; priv->gpriv = gpriv; priv->can.clock.freq = fcan_freq; - dev_info(&pdev->dev, "can_clk rate is %u\n", priv->can.clock.freq); + dev_info(dev, "can_clk rate is %u\n", priv->can.clock.freq); if (info->multi_channel_irqs) { char *irq_name; @@ -1755,31 +1754,31 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch, goto fail; } - irq_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, - "canfd.ch%d_err", ch); + irq_name = devm_kasprintf(dev, GFP_KERNEL, "canfd.ch%d_err", + ch); if (!irq_name) { err = -ENOMEM; goto fail; } - err = devm_request_irq(&pdev->dev, err_irq, + err = devm_request_irq(dev, err_irq, rcar_canfd_channel_err_interrupt, 0, irq_name, priv); if (err) { - dev_err(&pdev->dev, "devm_request_irq CH Err(%d) failed, error %d\n", + dev_err(dev, "devm_request_irq CH Err(%d) failed, error %d\n", err_irq, err); goto fail; } - irq_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, - "canfd.ch%d_trx", ch); + irq_name = devm_kasprintf(dev, GFP_KERNEL, "canfd.ch%d_trx", + ch); if (!irq_name) { err = -ENOMEM; goto fail; } - err = devm_request_irq(&pdev->dev, tx_irq, + err = devm_request_irq(dev, tx_irq, rcar_canfd_channel_tx_interrupt, 0, irq_name, priv); if (err) { - dev_err(&pdev->dev, "devm_request_irq Tx (%d) failed, error %d\n", + dev_err(dev, "devm_request_irq Tx (%d) failed, error %d\n", tx_irq, err); goto fail; } @@ -1803,7 +1802,7 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch, priv->can.do_set_mode = rcar_canfd_do_set_mode; priv->can.do_get_berr_counter = rcar_canfd_get_berr_counter; - SET_NETDEV_DEV(ndev, &pdev->dev); + SET_NETDEV_DEV(ndev, dev); netif_napi_add_weight(ndev, &priv->napi, rcar_canfd_rx_poll, RCANFD_NAPI_WEIGHT); @@ -1811,11 +1810,10 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch, gpriv->ch[priv->channel] = priv; err = register_candev(ndev); if (err) { - dev_err(&pdev->dev, - "register_candev() failed, error %d\n", err); + dev_err(dev, "register_candev() failed, error %d\n", err); goto fail_candev; } - dev_info(&pdev->dev, "device registered (channel %u)\n", priv->channel); + dev_info(dev, "device registered (channel %u)\n", priv->channel); return 0; fail_candev: @@ -1839,6 +1837,7 @@ static void rcar_canfd_channel_remove(struct rcar_canfd_global *gpriv, u32 ch) static int rcar_canfd_probe(struct platform_device *pdev) { const struct rcar_canfd_hw_info *info; + struct device *dev = &pdev->dev; void __iomem *addr; u32 sts, ch, fcan_freq; struct rcar_canfd_global *gpriv; @@ -1850,14 +1849,14 @@ static int rcar_canfd_probe(struct platform_device *pdev) char name[9] = "channelX"; int i; - info = of_device_get_match_data(&pdev->dev); + info = of_device_get_match_data(dev); - if (of_property_read_bool(pdev->dev.of_node, "renesas,no-can-fd")) + if (of_property_read_bool(dev->of_node, "renesas,no-can-fd")) fdmode = false; /* Classical CAN only mode */ for (i = 0; i < info->max_channels; ++i) { name[7] = '0' + i; - of_child = of_get_child_by_name(pdev->dev.of_node, name); + of_child = of_get_child_by_name(dev->of_node, name); if (of_child && of_device_is_available(of_child)) channels_mask |= BIT(i); of_node_put(of_child); @@ -1890,7 +1889,7 @@ static int rcar_canfd_probe(struct platform_device *pdev) } /* Global controller context */ - gpriv = devm_kzalloc(&pdev->dev, sizeof(*gpriv), GFP_KERNEL); + gpriv = devm_kzalloc(dev, sizeof(*gpriv), GFP_KERNEL); if (!gpriv) return -ENOMEM; @@ -1899,32 +1898,30 @@ static int rcar_canfd_probe(struct platform_device *pdev) gpriv->fdmode = fdmode; gpriv->info = info; - gpriv->rstc1 = devm_reset_control_get_optional_exclusive(&pdev->dev, - "rstp_n"); + gpriv->rstc1 = devm_reset_control_get_optional_exclusive(dev, "rstp_n"); if (IS_ERR(gpriv->rstc1)) - return dev_err_probe(&pdev->dev, PTR_ERR(gpriv->rstc1), + return dev_err_probe(dev, PTR_ERR(gpriv->rstc1), "failed to get rstp_n\n"); - gpriv->rstc2 = devm_reset_control_get_optional_exclusive(&pdev->dev, - "rstc_n"); + gpriv->rstc2 = devm_reset_control_get_optional_exclusive(dev, "rstc_n"); if (IS_ERR(gpriv->rstc2)) - return dev_err_probe(&pdev->dev, PTR_ERR(gpriv->rstc2), + return dev_err_probe(dev, PTR_ERR(gpriv->rstc2), "failed to get rstc_n\n"); /* Peripheral clock */ - gpriv->clkp = devm_clk_get(&pdev->dev, "fck"); + gpriv->clkp = devm_clk_get(dev, "fck"); if (IS_ERR(gpriv->clkp)) - return dev_err_probe(&pdev->dev, PTR_ERR(gpriv->clkp), + return dev_err_probe(dev, PTR_ERR(gpriv->clkp), "cannot get peripheral clock\n"); /* fCAN clock: Pick External clock. If not available fallback to * CANFD clock */ - gpriv->can_clk = devm_clk_get(&pdev->dev, "can_clk"); + gpriv->can_clk = devm_clk_get(dev, "can_clk"); if (IS_ERR(gpriv->can_clk) || (clk_get_rate(gpriv->can_clk) == 0)) { - gpriv->can_clk = devm_clk_get(&pdev->dev, "canfd"); + gpriv->can_clk = devm_clk_get(dev, "canfd"); if (IS_ERR(gpriv->can_clk)) - return dev_err_probe(&pdev->dev, PTR_ERR(gpriv->can_clk), + return dev_err_probe(dev, PTR_ERR(gpriv->can_clk), "cannot get canfd clock\n"); gpriv->fcan = RCANFD_CANFDCLK; @@ -1947,39 +1944,38 @@ static int rcar_canfd_probe(struct platform_device *pdev) /* Request IRQ that's common for both channels */ if (info->shared_global_irqs) { - err = devm_request_irq(&pdev->dev, ch_irq, + err = devm_request_irq(dev, ch_irq, rcar_canfd_channel_interrupt, 0, "canfd.ch_int", gpriv); if (err) { - dev_err(&pdev->dev, "devm_request_irq(%d) failed, error %d\n", + dev_err(dev, "devm_request_irq(%d) failed, error %d\n", ch_irq, err); goto fail_dev; } - err = devm_request_irq(&pdev->dev, g_irq, - rcar_canfd_global_interrupt, 0, - "canfd.g_int", gpriv); + err = devm_request_irq(dev, g_irq, rcar_canfd_global_interrupt, + 0, "canfd.g_int", gpriv); if (err) { - dev_err(&pdev->dev, "devm_request_irq(%d) failed, error %d\n", + dev_err(dev, "devm_request_irq(%d) failed, error %d\n", g_irq, err); goto fail_dev; } } else { - err = devm_request_irq(&pdev->dev, g_recc_irq, + err = devm_request_irq(dev, g_recc_irq, rcar_canfd_global_receive_fifo_interrupt, 0, "canfd.g_recc", gpriv); if (err) { - dev_err(&pdev->dev, "devm_request_irq(%d) failed, error %d\n", + dev_err(dev, "devm_request_irq(%d) failed, error %d\n", g_recc_irq, err); goto fail_dev; } - err = devm_request_irq(&pdev->dev, g_err_irq, + err = devm_request_irq(dev, g_err_irq, rcar_canfd_global_err_interrupt, 0, "canfd.g_err", gpriv); if (err) { - dev_err(&pdev->dev, "devm_request_irq(%d) failed, error %d\n", + dev_err(dev, "devm_request_irq(%d) failed, error %d\n", g_err_irq, err); goto fail_dev; } @@ -1997,14 +1993,14 @@ static int rcar_canfd_probe(struct platform_device *pdev) /* Enable peripheral clock for register access */ err = clk_prepare_enable(gpriv->clkp); if (err) { - dev_err(&pdev->dev, - "failed to enable peripheral clock, error %d\n", err); + dev_err(dev, "failed to enable peripheral clock, error %d\n", + err); goto fail_reset; } err = rcar_canfd_reset_controller(gpriv); if (err) { - dev_err(&pdev->dev, "reset controller failed\n"); + dev_err(dev, "reset controller failed\n"); goto fail_clk; } @@ -2034,7 +2030,7 @@ static int rcar_canfd_probe(struct platform_device *pdev) err = readl_poll_timeout((gpriv->base + RCANFD_GSTS), sts, !(sts & RCANFD_GSTS_GNOPM), 2, 500000); if (err) { - dev_err(&pdev->dev, "global operational mode failed\n"); + dev_err(dev, "global operational mode failed\n"); goto fail_mode; } @@ -2045,7 +2041,7 @@ static int rcar_canfd_probe(struct platform_device *pdev) } platform_set_drvdata(pdev, gpriv); - dev_info(&pdev->dev, "global operational state (clk %d, fdmode %d)\n", + dev_info(dev, "global operational state (clk %d, fdmode %d)\n", gpriv->fcan, gpriv->fdmode); return 0; @@ -2099,9 +2095,10 @@ static SIMPLE_DEV_PM_OPS(rcar_canfd_pm_ops, rcar_canfd_suspend, rcar_canfd_resume); static const __maybe_unused struct of_device_id rcar_canfd_of_table[] = { + { .compatible = "renesas,r8a779a0-canfd", .data = &rcar_gen4_hw_info }, { .compatible = "renesas,rcar-gen3-canfd", .data = &rcar_gen3_hw_info }, + { .compatible = "renesas,rcar-gen4-canfd", .data = &rcar_gen4_hw_info }, { .compatible = "renesas,rzg2l-canfd", .data = &rzg2l_hw_info }, - { .compatible = "renesas,r8a779a0-canfd", .data = &r8a779a0_hw_info }, { } }; diff --git a/drivers/net/can/sja1000/ems_pci.c b/drivers/net/can/sja1000/ems_pci.c index 4ab91759a5c6..c56e27223e5f 100644 --- a/drivers/net/can/sja1000/ems_pci.c +++ b/drivers/net/can/sja1000/ems_pci.c @@ -3,6 +3,7 @@ * Copyright (C) 2007 Wolfgang Grandegger <wg@grandegger.com> * Copyright (C) 2008 Markus Plessing <plessing@ems-wuensche.com> * Copyright (C) 2008 Sebastian Haas <haas@ems-wuensche.com> + * Copyright (C) 2023 EMS Dr. Thomas Wuensche */ #include <linux/kernel.h> @@ -19,12 +20,14 @@ #define DRV_NAME "ems_pci" -MODULE_AUTHOR("Sebastian Haas <haas@ems-wuenche.com>"); +MODULE_AUTHOR("Sebastian Haas <support@ems-wuensche.com>"); +MODULE_AUTHOR("Gerhard Uttenthaler <uttenthaler@ems-wuensche.com>"); MODULE_DESCRIPTION("Socket-CAN driver for EMS CPC-PCI/PCIe/104P CAN cards"); MODULE_LICENSE("GPL v2"); #define EMS_PCI_V1_MAX_CHAN 2 #define EMS_PCI_V2_MAX_CHAN 4 +#define EMS_PCI_V3_MAX_CHAN 4 #define EMS_PCI_MAX_CHAN EMS_PCI_V2_MAX_CHAN struct ems_pci_card { @@ -40,8 +43,7 @@ struct ems_pci_card { #define EMS_PCI_CAN_CLOCK (16000000 / 2) -/* - * Register definitions and descriptions are from LinCAN 0.3.3. +/* Register definitions and descriptions are from LinCAN 0.3.3. * * PSB4610 PITA-2 bridge control registers */ @@ -52,8 +54,7 @@ struct ems_pci_card { #define PITA2_MISC 0x1c /* Miscellaneous Register */ #define PITA2_MISC_CONFIG 0x04000000 /* Multiplexed parallel interface */ -/* - * Register definitions for the PLX 9030 +/* Register definitions for the PLX 9030 */ #define PLX_ICSR 0x4c /* Interrupt Control/Status register */ #define PLX_ICSR_LINTI1_ENA 0x0001 /* LINTi1 Enable */ @@ -62,8 +63,16 @@ struct ems_pci_card { #define PLX_ICSR_ENA_CLR (PLX_ICSR_LINTI1_ENA | PLX_ICSR_PCIINT_ENA | \ PLX_ICSR_LINTI1_CLR) -/* - * The board configuration is probably following: +/* Register definitions for the ASIX99100 + */ +#define ASIX_LINTSR 0x28 /* Interrupt Control/Status register */ +#define ASIX_LINTSR_INT0AC BIT(0) /* Writing 1 enables or clears interrupt */ + +#define ASIX_LIEMR 0x24 /* Local Interrupt Enable / Miscellaneous Register */ +#define ASIX_LIEMR_L0EINTEN BIT(16) /* Local INT0 input assertion enable */ +#define ASIX_LIEMR_LRST BIT(14) /* Local Reset assert */ + +/* The board configuration is probably following: * RX1 is connected to ground. * TX1 is not connected. * CLKO is not connected. @@ -72,23 +81,40 @@ struct ems_pci_card { */ #define EMS_PCI_OCR (OCR_TX0_PUSHPULL | OCR_TX1_PUSHPULL) -/* - * In the CDR register, you should set CBP to 1. +/* In the CDR register, you should set CBP to 1. * You will probably also want to set the clock divider value to 7 * (meaning direct oscillator output) because the second SJA1000 chip * is driven by the first one CLKOUT output. */ #define EMS_PCI_CDR (CDR_CBP | CDR_CLKOUT_MASK) -#define EMS_PCI_V1_BASE_BAR 1 -#define EMS_PCI_V1_CONF_SIZE 4096 /* size of PITA control area */ -#define EMS_PCI_V2_BASE_BAR 2 -#define EMS_PCI_V2_CONF_SIZE 128 /* size of PLX control area */ -#define EMS_PCI_CAN_BASE_OFFSET 0x400 /* offset where the controllers starts */ -#define EMS_PCI_CAN_CTRL_SIZE 0x200 /* memory size for each controller */ +#define EMS_PCI_V1_BASE_BAR 1 +#define EMS_PCI_V1_CONF_BAR 0 +#define EMS_PCI_V1_CONF_SIZE 4096 /* size of PITA control area */ +#define EMS_PCI_V1_CAN_BASE_OFFSET 0x400 /* offset where the controllers start */ +#define EMS_PCI_V1_CAN_CTRL_SIZE 0x200 /* memory size for each controller */ + +#define EMS_PCI_V2_BASE_BAR 2 +#define EMS_PCI_V2_CONF_BAR 0 +#define EMS_PCI_V2_CONF_SIZE 128 /* size of PLX control area */ +#define EMS_PCI_V2_CAN_BASE_OFFSET 0x400 /* offset where the controllers start */ +#define EMS_PCI_V2_CAN_CTRL_SIZE 0x200 /* memory size for each controller */ + +#define EMS_PCI_V3_BASE_BAR 0 +#define EMS_PCI_V3_CONF_BAR 5 +#define EMS_PCI_V3_CONF_SIZE 128 /* size of ASIX control area */ +#define EMS_PCI_V3_CAN_BASE_OFFSET 0x00 /* offset where the controllers starts */ +#define EMS_PCI_V3_CAN_CTRL_SIZE 0x100 /* memory size for each controller */ #define EMS_PCI_BASE_SIZE 4096 /* size of controller area */ +#ifndef PCI_VENDOR_ID_ASIX +#define PCI_VENDOR_ID_ASIX 0x125b +#define PCI_DEVICE_ID_ASIX_9110 0x9110 +#define PCI_SUBVENDOR_ID_ASIX 0xa000 +#endif +#define PCI_SUBDEVICE_ID_EMS 0x4010 + static const struct pci_device_id ems_pci_tbl[] = { /* CPC-PCI v1 */ {PCI_VENDOR_ID_SIEMENS, 0x2104, PCI_ANY_ID, PCI_ANY_ID,}, @@ -96,12 +122,13 @@ static const struct pci_device_id ems_pci_tbl[] = { {PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9030, PCI_VENDOR_ID_PLX, 0x4000}, /* CPC-104P v2 */ {PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9030, PCI_VENDOR_ID_PLX, 0x4002}, + /* CPC-PCIe v3 */ + {PCI_VENDOR_ID_ASIX, PCI_DEVICE_ID_ASIX_9110, PCI_SUBVENDOR_ID_ASIX, PCI_SUBDEVICE_ID_EMS}, {0,} }; MODULE_DEVICE_TABLE(pci, ems_pci_tbl); -/* - * Helper to read internal registers from card logic (not CAN) +/* Helper to read internal registers from card logic (not CAN) */ static u8 ems_pci_v1_readb(struct ems_pci_card *card, unsigned int port) { @@ -146,8 +173,25 @@ static void ems_pci_v2_post_irq(const struct sja1000_priv *priv) writel(PLX_ICSR_ENA_CLR, card->conf_addr + PLX_ICSR); } -/* - * Check if a CAN controller is present at the specified location +static u8 ems_pci_v3_read_reg(const struct sja1000_priv *priv, int port) +{ + return readb(priv->reg_base + port); +} + +static void ems_pci_v3_write_reg(const struct sja1000_priv *priv, + int port, u8 val) +{ + writeb(val, priv->reg_base + port); +} + +static void ems_pci_v3_post_irq(const struct sja1000_priv *priv) +{ + struct ems_pci_card *card = (struct ems_pci_card *)priv->priv; + + writel(ASIX_LINTSR_INT0AC, card->conf_addr + ASIX_LINTSR); +} + +/* Check if a CAN controller is present at the specified location * by trying to set 'em into the PeliCAN mode */ static inline int ems_pci_check_chan(const struct sja1000_priv *priv) @@ -185,10 +229,10 @@ static void ems_pci_del_card(struct pci_dev *pdev) free_sja1000dev(dev); } - if (card->base_addr != NULL) + if (card->base_addr) pci_iounmap(card->pci_dev, card->base_addr); - if (card->conf_addr != NULL) + if (card->conf_addr) pci_iounmap(card->pci_dev, card->conf_addr); kfree(card); @@ -202,8 +246,7 @@ static void ems_pci_card_reset(struct ems_pci_card *card) writeb(0, card->base_addr); } -/* - * Probe PCI device for EMS CAN signature and register each available +/* Probe PCI device for EMS CAN signature and register each available * CAN channel to SJA1000 Socket-CAN subsystem. */ static int ems_pci_add_card(struct pci_dev *pdev, @@ -212,7 +255,7 @@ static int ems_pci_add_card(struct pci_dev *pdev, struct sja1000_priv *priv; struct net_device *dev; struct ems_pci_card *card; - int max_chan, conf_size, base_bar; + int max_chan, conf_size, base_bar, conf_bar; int err, i; /* Enabling PCI device */ @@ -222,8 +265,8 @@ static int ems_pci_add_card(struct pci_dev *pdev, } /* Allocating card structures to hold addresses, ... */ - card = kzalloc(sizeof(struct ems_pci_card), GFP_KERNEL); - if (card == NULL) { + card = kzalloc(sizeof(*card), GFP_KERNEL); + if (!card) { pci_disable_device(pdev); return -ENOMEM; } @@ -234,27 +277,35 @@ static int ems_pci_add_card(struct pci_dev *pdev, card->channels = 0; - if (pdev->vendor == PCI_VENDOR_ID_PLX) { + if (pdev->vendor == PCI_VENDOR_ID_ASIX) { + card->version = 3; /* CPC-PCI v3 */ + max_chan = EMS_PCI_V3_MAX_CHAN; + base_bar = EMS_PCI_V3_BASE_BAR; + conf_bar = EMS_PCI_V3_CONF_BAR; + conf_size = EMS_PCI_V3_CONF_SIZE; + } else if (pdev->vendor == PCI_VENDOR_ID_PLX) { card->version = 2; /* CPC-PCI v2 */ max_chan = EMS_PCI_V2_MAX_CHAN; base_bar = EMS_PCI_V2_BASE_BAR; + conf_bar = EMS_PCI_V2_CONF_BAR; conf_size = EMS_PCI_V2_CONF_SIZE; } else { card->version = 1; /* CPC-PCI v1 */ max_chan = EMS_PCI_V1_MAX_CHAN; base_bar = EMS_PCI_V1_BASE_BAR; + conf_bar = EMS_PCI_V1_CONF_BAR; conf_size = EMS_PCI_V1_CONF_SIZE; } /* Remap configuration space and controller memory area */ - card->conf_addr = pci_iomap(pdev, 0, conf_size); - if (card->conf_addr == NULL) { + card->conf_addr = pci_iomap(pdev, conf_bar, conf_size); + if (!card->conf_addr) { err = -ENOMEM; goto failure_cleanup; } card->base_addr = pci_iomap(pdev, base_bar, EMS_PCI_BASE_SIZE); - if (card->base_addr == NULL) { + if (!card->base_addr) { err = -ENOMEM; goto failure_cleanup; } @@ -276,12 +327,20 @@ static int ems_pci_add_card(struct pci_dev *pdev, } } + if (card->version == 3) { + /* ASIX chip asserts local reset to CAN controllers + * after bootup until it is deasserted + */ + writel(readl(card->conf_addr + ASIX_LIEMR) & ~ASIX_LIEMR_LRST, + card->conf_addr + ASIX_LIEMR); + } + ems_pci_card_reset(card); /* Detect available channels */ for (i = 0; i < max_chan; i++) { dev = alloc_sja1000dev(0); - if (dev == NULL) { + if (!dev) { err = -ENOMEM; goto failure_cleanup; } @@ -292,16 +351,25 @@ static int ems_pci_add_card(struct pci_dev *pdev, priv->irq_flags = IRQF_SHARED; dev->irq = pdev->irq; - priv->reg_base = card->base_addr + EMS_PCI_CAN_BASE_OFFSET - + (i * EMS_PCI_CAN_CTRL_SIZE); + if (card->version == 1) { priv->read_reg = ems_pci_v1_read_reg; priv->write_reg = ems_pci_v1_write_reg; priv->post_irq = ems_pci_v1_post_irq; - } else { + priv->reg_base = card->base_addr + EMS_PCI_V1_CAN_BASE_OFFSET + + (i * EMS_PCI_V1_CAN_CTRL_SIZE); + } else if (card->version == 2) { priv->read_reg = ems_pci_v2_read_reg; priv->write_reg = ems_pci_v2_write_reg; priv->post_irq = ems_pci_v2_post_irq; + priv->reg_base = card->base_addr + EMS_PCI_V2_CAN_BASE_OFFSET + + (i * EMS_PCI_V2_CAN_CTRL_SIZE); + } else { + priv->read_reg = ems_pci_v3_read_reg; + priv->write_reg = ems_pci_v3_write_reg; + priv->post_irq = ems_pci_v3_post_irq; + priv->reg_base = card->base_addr + EMS_PCI_V3_CAN_BASE_OFFSET + + (i * EMS_PCI_V3_CAN_CTRL_SIZE); } /* Check if channel is present */ @@ -313,20 +381,28 @@ static int ems_pci_add_card(struct pci_dev *pdev, SET_NETDEV_DEV(dev, &pdev->dev); dev->dev_id = i; - if (card->version == 1) + if (card->version == 1) { /* reset int flag of pita */ writel(PITA2_ICR_INT0_EN | PITA2_ICR_INT0, card->conf_addr + PITA2_ICR); - else + } else if (card->version == 2) { /* enable IRQ in PLX 9030 */ writel(PLX_ICSR_ENA_CLR, card->conf_addr + PLX_ICSR); + } else { + /* Enable IRQ in AX99100 */ + writel(ASIX_LINTSR_INT0AC, card->conf_addr + ASIX_LINTSR); + /* Enable local INT0 input enable */ + writel(readl(card->conf_addr + ASIX_LIEMR) | ASIX_LIEMR_L0EINTEN, + card->conf_addr + ASIX_LIEMR); + } /* Register SJA1000 device */ err = register_sja1000dev(dev); if (err) { - dev_err(&pdev->dev, "Registering device failed " - "(err=%d)\n", err); + dev_err(&pdev->dev, + "Registering device failed: %pe\n", + ERR_PTR(err)); free_sja1000dev(dev); goto failure_cleanup; } @@ -334,7 +410,7 @@ static int ems_pci_add_card(struct pci_dev *pdev, card->channels++; dev_info(&pdev->dev, "Channel #%d at 0x%p, irq %d\n", - i + 1, priv->reg_base, dev->irq); + i + 1, priv->reg_base, dev->irq); } else { free_sja1000dev(dev); } diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ethtool.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ethtool.c index 3585f02575df..57eeb066a945 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ethtool.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ethtool.c @@ -48,6 +48,7 @@ mcp251xfd_ring_set_ringparam(struct net_device *ndev, priv->rx_obj_num = layout.cur_rx; priv->rx_obj_num_coalesce_irq = layout.rx_coalesce; priv->tx->obj_num = layout.cur_tx; + priv->tx_obj_num_coalesce_irq = layout.tx_coalesce; return 0; } diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c index bf3f0f150199..bfe4caa0c99d 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c @@ -30,11 +30,23 @@ mcp251xfd_cmd_prepare_write_reg(const struct mcp251xfd_priv *priv, last_byte = mcp251xfd_last_byte_set(mask); len = last_byte - first_byte + 1; - data = mcp251xfd_spi_cmd_write(priv, write_reg_buf, reg + first_byte); + data = mcp251xfd_spi_cmd_write(priv, write_reg_buf, reg + first_byte, len); val_le32 = cpu_to_le32(val >> BITS_PER_BYTE * first_byte); memcpy(data, &val_le32, len); - if (priv->devtype_data.quirks & MCP251XFD_QUIRK_CRC_REG) { + if (!(priv->devtype_data.quirks & MCP251XFD_QUIRK_CRC_REG)) { + len += sizeof(write_reg_buf->nocrc.cmd); + } else if (len == 1) { + u16 crc; + + /* CRC */ + len += sizeof(write_reg_buf->safe.cmd); + crc = mcp251xfd_crc16_compute(&write_reg_buf->safe, len); + put_unaligned_be16(crc, (void *)write_reg_buf + len); + + /* Total length */ + len += sizeof(write_reg_buf->safe.crc); + } else { u16 crc; mcp251xfd_spi_cmd_crc_set_len_in_reg(&write_reg_buf->crc.cmd, @@ -46,8 +58,6 @@ mcp251xfd_cmd_prepare_write_reg(const struct mcp251xfd_priv *priv, /* Total length */ len += sizeof(write_reg_buf->crc.crc); - } else { - len += sizeof(write_reg_buf->nocrc.cmd); } return len; diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h index 2b0309fedfac..7024ff0cc2c0 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h @@ -504,6 +504,11 @@ union mcp251xfd_write_reg_buf { u8 data[4]; __be16 crc; } crc; + struct __packed { + struct mcp251xfd_buf_cmd cmd; + u8 data[1]; + __be16 crc; + } safe; } ____cacheline_aligned; struct mcp251xfd_tx_obj { @@ -759,6 +764,13 @@ mcp251xfd_spi_cmd_write_crc_set_addr(struct mcp251xfd_buf_cmd_crc *cmd, } static inline void +mcp251xfd_spi_cmd_write_safe_set_addr(struct mcp251xfd_buf_cmd *cmd, + u16 addr) +{ + cmd->cmd = cpu_to_be16(MCP251XFD_SPI_INSTRUCTION_WRITE_CRC_SAFE | addr); +} + +static inline void mcp251xfd_spi_cmd_write_crc(struct mcp251xfd_buf_cmd_crc *cmd, u16 addr, u16 len) { @@ -769,14 +781,20 @@ mcp251xfd_spi_cmd_write_crc(struct mcp251xfd_buf_cmd_crc *cmd, static inline u8 * mcp251xfd_spi_cmd_write(const struct mcp251xfd_priv *priv, union mcp251xfd_write_reg_buf *write_reg_buf, - u16 addr) + u16 addr, u8 len) { u8 *data; if (priv->devtype_data.quirks & MCP251XFD_QUIRK_CRC_REG) { - mcp251xfd_spi_cmd_write_crc_set_addr(&write_reg_buf->crc.cmd, - addr); - data = write_reg_buf->crc.data; + if (len == 1) { + mcp251xfd_spi_cmd_write_safe_set_addr(&write_reg_buf->safe.cmd, + addr); + data = write_reg_buf->safe.data; + } else { + mcp251xfd_spi_cmd_write_crc_set_addr(&write_reg_buf->crc.cmd, + addr); + data = write_reg_buf->crc.data; + } } else { mcp251xfd_spi_cmd_write_nocrc(&write_reg_buf->nocrc.cmd, addr); diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c index 687dd542f7f6..b211b6e283a2 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb.c @@ -9,10 +9,11 @@ * Many thanks to Klaus Hitschler <klaus.hitschler@gmx.de> */ #include <asm/unaligned.h> + +#include <linux/ethtool.h> +#include <linux/module.h> #include <linux/netdevice.h> #include <linux/usb.h> -#include <linux/module.h> -#include <linux/ethtool.h> #include <linux/can.h> #include <linux/can/dev.h> @@ -381,23 +382,42 @@ static int pcan_usb_get_serial(struct peak_usb_device *dev, u32 *serial_number) } /* - * read device id from device + * read can channel id from device */ -static int pcan_usb_get_device_id(struct peak_usb_device *dev, u32 *device_id) +static int pcan_usb_get_can_channel_id(struct peak_usb_device *dev, u32 *can_ch_id) { u8 args[PCAN_USB_CMD_ARGS_LEN]; int err; err = pcan_usb_wait_rsp(dev, PCAN_USB_CMD_DEVID, PCAN_USB_GET, args); if (err) - netdev_err(dev->netdev, "getting device id failure: %d\n", err); + netdev_err(dev->netdev, "getting can channel id failure: %d\n", err); else - *device_id = args[0]; + *can_ch_id = args[0]; return err; } +/* set a new CAN channel id in the flash memory of the device */ +static int pcan_usb_set_can_channel_id(struct peak_usb_device *dev, u32 can_ch_id) +{ + u8 args[PCAN_USB_CMD_ARGS_LEN]; + + /* this kind of device supports 8-bit values only */ + if (can_ch_id > U8_MAX) + return -EINVAL; + + /* during the flash process the device disconnects during ~1.25 s.: + * prohibit access when interface is UP + */ + if (dev->netdev->flags & IFF_UP) + return -EBUSY; + + args[0] = can_ch_id; + return pcan_usb_send_cmd(dev, PCAN_USB_CMD_DEVID, PCAN_USB_SET, args); +} + /* * update current time ref with received timestamp */ @@ -963,9 +983,18 @@ static int pcan_usb_set_phys_id(struct net_device *netdev, return err; } +/* This device only handles 8-bit CAN channel id. */ +static int pcan_usb_get_eeprom_len(struct net_device *netdev) +{ + return sizeof(u8); +} + static const struct ethtool_ops pcan_usb_ethtool_ops = { .set_phys_id = pcan_usb_set_phys_id, .get_ts_info = pcan_get_ts_info, + .get_eeprom_len = pcan_usb_get_eeprom_len, + .get_eeprom = peak_usb_get_eeprom, + .set_eeprom = peak_usb_set_eeprom, }; /* @@ -1017,7 +1046,8 @@ const struct peak_usb_adapter pcan_usb = { .dev_init = pcan_usb_init, .dev_set_bus = pcan_usb_write_mode, .dev_set_bittiming = pcan_usb_set_bittiming, - .dev_get_device_id = pcan_usb_get_device_id, + .dev_get_can_channel_id = pcan_usb_get_can_channel_id, + .dev_set_can_channel_id = pcan_usb_set_can_channel_id, .dev_decode_buf = pcan_usb_decode_buf, .dev_encode_msg = pcan_usb_encode_msg, .dev_start = pcan_usb_start, diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index 1d996d3320fe..d881e1d30183 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -8,13 +8,15 @@ * * Many thanks to Klaus Hitschler <klaus.hitschler@gmx.de> */ +#include <linux/device.h> +#include <linux/ethtool.h> #include <linux/init.h> -#include <linux/signal.h> -#include <linux/slab.h> #include <linux/module.h> #include <linux/netdevice.h> +#include <linux/signal.h> +#include <linux/slab.h> +#include <linux/sysfs.h> #include <linux/usb.h> -#include <linux/ethtool.h> #include <linux/can.h> #include <linux/can/dev.h> @@ -53,6 +55,26 @@ static const struct usb_device_id peak_usb_table[] = { MODULE_DEVICE_TABLE(usb, peak_usb_table); +static ssize_t can_channel_id_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + struct peak_usb_device *peak_dev = netdev_priv(netdev); + + return sysfs_emit(buf, "%08X\n", peak_dev->can_channel_id); +} +static DEVICE_ATTR_RO(can_channel_id); + +/* mutable to avoid cast in attribute_group */ +static struct attribute *peak_usb_sysfs_attrs[] = { + &dev_attr_can_channel_id.attr, + NULL, +}; + +static const struct attribute_group peak_usb_sysfs_group = { + .name = "peak_usb", + .attrs = peak_usb_sysfs_attrs, +}; + /* * dump memory */ @@ -808,6 +830,86 @@ static const struct net_device_ops peak_usb_netdev_ops = { .ndo_change_mtu = can_change_mtu, }; +/* CAN-USB devices generally handle 32-bit CAN channel IDs. + * In case one doesn't, then it have to overload this function. + */ +int peak_usb_get_eeprom_len(struct net_device *netdev) +{ + return sizeof(u32); +} + +/* Every CAN-USB device exports the dev_get_can_channel_id() operation. It is used + * here to fill the data buffer with the user defined CAN channel ID. + */ +int peak_usb_get_eeprom(struct net_device *netdev, + struct ethtool_eeprom *eeprom, u8 *data) +{ + struct peak_usb_device *dev = netdev_priv(netdev); + u32 ch_id; + __le32 ch_id_le; + int err; + + err = dev->adapter->dev_get_can_channel_id(dev, &ch_id); + if (err) + return err; + + /* ethtool operates on individual bytes. The byte order of the CAN + * channel id in memory depends on the kernel architecture. We + * convert the CAN channel id back to the native byte order of the PEAK + * device itself to ensure that the order is consistent for all + * host architectures. + */ + ch_id_le = cpu_to_le32(ch_id); + memcpy(data, (u8 *)&ch_id_le + eeprom->offset, eeprom->len); + + /* update cached value */ + dev->can_channel_id = ch_id; + return err; +} + +/* Every CAN-USB device exports the dev_get_can_channel_id()/dev_set_can_channel_id() + * operations. They are used here to set the new user defined CAN channel ID. + */ +int peak_usb_set_eeprom(struct net_device *netdev, + struct ethtool_eeprom *eeprom, u8 *data) +{ + struct peak_usb_device *dev = netdev_priv(netdev); + u32 ch_id; + __le32 ch_id_le; + int err; + + /* first, read the current user defined CAN channel ID */ + err = dev->adapter->dev_get_can_channel_id(dev, &ch_id); + if (err) { + netdev_err(netdev, "Failed to init CAN channel id (err %d)\n", err); + return err; + } + + /* do update the value with user given bytes. + * ethtool operates on individual bytes. The byte order of the CAN + * channel ID in memory depends on the kernel architecture. We + * convert the CAN channel ID back to the native byte order of the PEAK + * device itself to ensure that the order is consistent for all + * host architectures. + */ + ch_id_le = cpu_to_le32(ch_id); + memcpy((u8 *)&ch_id_le + eeprom->offset, data, eeprom->len); + ch_id = le32_to_cpu(ch_id_le); + + /* flash the new value now */ + err = dev->adapter->dev_set_can_channel_id(dev, ch_id); + if (err) { + netdev_err(netdev, "Failed to write new CAN channel id (err %d)\n", + err); + return err; + } + + /* update cached value with the new one */ + dev->can_channel_id = ch_id; + + return 0; +} + int pcan_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) { info->so_timestamping = @@ -881,6 +983,9 @@ static int peak_usb_create_dev(const struct peak_usb_adapter *peak_usb_adapter, /* add ethtool support */ netdev->ethtool_ops = peak_usb_adapter->ethtool_ops; + /* register peak_usb sysfs files */ + netdev->sysfs_groups[0] = &peak_usb_sysfs_group; + init_usb_anchor(&dev->rx_submitted); init_usb_anchor(&dev->tx_submitted); @@ -921,12 +1026,11 @@ static int peak_usb_create_dev(const struct peak_usb_adapter *peak_usb_adapter, goto adap_dev_free; } - /* get device number early */ - if (dev->adapter->dev_get_device_id) - dev->adapter->dev_get_device_id(dev, &dev->device_number); + /* get CAN channel id early */ + dev->adapter->dev_get_can_channel_id(dev, &dev->can_channel_id); - netdev_info(netdev, "attached to %s channel %u (device %u)\n", - peak_usb_adapter->name, ctrl_idx, dev->device_number); + netdev_info(netdev, "attached to %s channel %u (device 0x%08X)\n", + peak_usb_adapter->name, ctrl_idx, dev->can_channel_id); return 0; @@ -964,7 +1068,7 @@ static void peak_usb_disconnect(struct usb_interface *intf) dev->state &= ~PCAN_USB_STATE_CONNECTED; strscpy(name, netdev->name, IFNAMSIZ); - unregister_netdev(netdev); + unregister_candev(netdev); kfree(dev->cmd_buf); dev->next_siblings = NULL; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.h b/drivers/net/can/usb/peak_usb/pcan_usb_core.h index f6bdd8b3f290..980e315186cf 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.h +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.h @@ -60,7 +60,8 @@ struct peak_usb_adapter { int (*dev_set_data_bittiming)(struct peak_usb_device *dev, struct can_bittiming *bt); int (*dev_set_bus)(struct peak_usb_device *dev, u8 onoff); - int (*dev_get_device_id)(struct peak_usb_device *dev, u32 *device_id); + int (*dev_get_can_channel_id)(struct peak_usb_device *dev, u32 *can_ch_id); + int (*dev_set_can_channel_id)(struct peak_usb_device *dev, u32 can_ch_id); int (*dev_decode_buf)(struct peak_usb_device *dev, struct urb *urb); int (*dev_encode_msg)(struct peak_usb_device *dev, struct sk_buff *skb, u8 *obuf, size_t *size); @@ -122,7 +123,8 @@ struct peak_usb_device { u8 *cmd_buf; struct usb_anchor rx_submitted; - u32 device_number; + /* equivalent to the device ID in the Windows API */ + u32 can_channel_id; u8 device_rev; u8 ep_msg_in; @@ -147,4 +149,10 @@ void peak_usb_async_complete(struct urb *urb); void peak_usb_restart_complete(struct peak_usb_device *dev); int pcan_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info); +/* common 32-bit CAN channel ID ethtool management */ +int peak_usb_get_eeprom_len(struct net_device *netdev); +int peak_usb_get_eeprom(struct net_device *netdev, + struct ethtool_eeprom *eeprom, u8 *data); +int peak_usb_set_eeprom(struct net_device *netdev, + struct ethtool_eeprom *eeprom, u8 *data); #endif diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c index 2ea1500df393..4d85b29a17b7 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c @@ -4,10 +4,10 @@ * * Copyright (C) 2013-2014 Stephane Grosjean <s.grosjean@peak-system.com> */ +#include <linux/ethtool.h> +#include <linux/module.h> #include <linux/netdevice.h> #include <linux/usb.h> -#include <linux/module.h> -#include <linux/ethtool.h> #include <linux/can.h> #include <linux/can/dev.h> @@ -147,6 +147,15 @@ struct __packed pcan_ufd_ovr_msg { u8 unused[3]; }; +#define PCAN_UFD_CMD_DEVID_SET 0x81 + +struct __packed pcan_ufd_device_id { + __le16 opcode_channel; + + u16 unused; + __le32 device_id; +}; + static inline int pufd_omsg_get_channel(struct pcan_ufd_ovr_msg *om) { return om->channel & 0xf; @@ -234,6 +243,15 @@ static int pcan_usb_fd_send_cmd(struct peak_usb_device *dev, void *cmd_tail) return err; } +static int pcan_usb_fd_read_fwinfo(struct peak_usb_device *dev, + struct pcan_ufd_fw_info *fw_info) +{ + return pcan_usb_pro_send_req(dev, PCAN_USBPRO_REQ_INFO, + PCAN_USBPRO_INFO_FW, + fw_info, + sizeof(*fw_info)); +} + /* build the commands list in the given buffer, to enter operational mode */ static int pcan_usb_fd_build_restart_cmd(struct peak_usb_device *dev, u8 *buf) { @@ -434,6 +452,34 @@ static int pcan_usb_fd_set_bittiming_fast(struct peak_usb_device *dev, return pcan_usb_fd_send_cmd(dev, ++cmd); } +/* read user CAN channel id from device */ +static int pcan_usb_fd_get_can_channel_id(struct peak_usb_device *dev, + u32 *can_ch_id) +{ + int err; + struct pcan_usb_fd_if *usb_if = pcan_usb_fd_dev_if(dev); + + err = pcan_usb_fd_read_fwinfo(dev, &usb_if->fw_info); + if (err) + return err; + + *can_ch_id = le32_to_cpu(usb_if->fw_info.dev_id[dev->ctrl_idx]); + return err; +} + +/* set a new CAN channel id in the flash memory of the device */ +static int pcan_usb_fd_set_can_channel_id(struct peak_usb_device *dev, u32 can_ch_id) +{ + struct pcan_ufd_device_id *cmd = pcan_usb_fd_cmd_buffer(dev); + + cmd->opcode_channel = pucan_cmd_opcode_channel(dev->ctrl_idx, + PCAN_UFD_CMD_DEVID_SET); + cmd->device_id = cpu_to_le32(can_ch_id); + + /* send the command */ + return pcan_usb_fd_send_cmd(dev, ++cmd); +} + /* handle restart but in asynchronously way * (uses PCAN-USB Pro code to complete asynchronous request) */ @@ -907,10 +953,7 @@ static int pcan_usb_fd_init(struct peak_usb_device *dev) fw_info = &pdev->usb_if->fw_info; - err = pcan_usb_pro_send_req(dev, PCAN_USBPRO_REQ_INFO, - PCAN_USBPRO_INFO_FW, - fw_info, - sizeof(*fw_info)); + err = pcan_usb_fd_read_fwinfo(dev, fw_info); if (err) { dev_err(dev->netdev->dev.parent, "unable to read %s firmware info (err %d)\n", @@ -972,7 +1015,7 @@ static int pcan_usb_fd_init(struct peak_usb_device *dev) } pdev->usb_if->dev[dev->ctrl_idx] = dev; - dev->device_number = + dev->can_channel_id = le32_to_cpu(pdev->usb_if->fw_info.dev_id[dev->ctrl_idx]); /* if vendor rsp is of type 2, then it contains EP numbers to @@ -1081,6 +1124,9 @@ static int pcan_usb_fd_set_phys_id(struct net_device *netdev, static const struct ethtool_ops pcan_usb_fd_ethtool_ops = { .set_phys_id = pcan_usb_fd_set_phys_id, .get_ts_info = pcan_get_ts_info, + .get_eeprom_len = peak_usb_get_eeprom_len, + .get_eeprom = peak_usb_get_eeprom, + .set_eeprom = peak_usb_set_eeprom, }; /* describes the PCAN-USB FD adapter */ @@ -1148,6 +1194,8 @@ const struct peak_usb_adapter pcan_usb_fd = { .dev_set_bus = pcan_usb_fd_set_bus, .dev_set_bittiming = pcan_usb_fd_set_bittiming_slow, .dev_set_data_bittiming = pcan_usb_fd_set_bittiming_fast, + .dev_get_can_channel_id = pcan_usb_fd_get_can_channel_id, + .dev_set_can_channel_id = pcan_usb_fd_set_can_channel_id, .dev_decode_buf = pcan_usb_fd_decode_buf, .dev_start = pcan_usb_fd_start, .dev_stop = pcan_usb_fd_stop, @@ -1222,6 +1270,8 @@ const struct peak_usb_adapter pcan_usb_chip = { .dev_set_bus = pcan_usb_fd_set_bus, .dev_set_bittiming = pcan_usb_fd_set_bittiming_slow, .dev_set_data_bittiming = pcan_usb_fd_set_bittiming_fast, + .dev_get_can_channel_id = pcan_usb_fd_get_can_channel_id, + .dev_set_can_channel_id = pcan_usb_fd_set_can_channel_id, .dev_decode_buf = pcan_usb_fd_decode_buf, .dev_start = pcan_usb_fd_start, .dev_stop = pcan_usb_fd_stop, @@ -1296,6 +1346,8 @@ const struct peak_usb_adapter pcan_usb_pro_fd = { .dev_set_bus = pcan_usb_fd_set_bus, .dev_set_bittiming = pcan_usb_fd_set_bittiming_slow, .dev_set_data_bittiming = pcan_usb_fd_set_bittiming_fast, + .dev_get_can_channel_id = pcan_usb_fd_get_can_channel_id, + .dev_set_can_channel_id = pcan_usb_fd_set_can_channel_id, .dev_decode_buf = pcan_usb_fd_decode_buf, .dev_start = pcan_usb_fd_start, .dev_stop = pcan_usb_fd_stop, @@ -1370,6 +1422,8 @@ const struct peak_usb_adapter pcan_usb_x6 = { .dev_set_bus = pcan_usb_fd_set_bus, .dev_set_bittiming = pcan_usb_fd_set_bittiming_slow, .dev_set_data_bittiming = pcan_usb_fd_set_bittiming_fast, + .dev_get_can_channel_id = pcan_usb_fd_get_can_channel_id, + .dev_set_can_channel_id = pcan_usb_fd_set_can_channel_id, .dev_decode_buf = pcan_usb_fd_decode_buf, .dev_start = pcan_usb_fd_start, .dev_stop = pcan_usb_fd_stop, diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c index 5d8f6a40bb2c..f736196383ac 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c @@ -6,10 +6,10 @@ * Copyright (C) 2003-2011 PEAK System-Technik GmbH * Copyright (C) 2011-2012 Stephane Grosjean <s.grosjean@peak-system.com> */ +#include <linux/ethtool.h> +#include <linux/module.h> #include <linux/netdevice.h> #include <linux/usb.h> -#include <linux/module.h> -#include <linux/ethtool.h> #include <linux/can.h> #include <linux/can/dev.h> @@ -76,6 +76,7 @@ static u16 pcan_usb_pro_sizeof_rec[256] = { [PCAN_USBPRO_SETFILTR] = sizeof(struct pcan_usb_pro_filter), [PCAN_USBPRO_SETTS] = sizeof(struct pcan_usb_pro_setts), [PCAN_USBPRO_GETDEVID] = sizeof(struct pcan_usb_pro_devid), + [PCAN_USBPRO_SETDEVID] = sizeof(struct pcan_usb_pro_devid), [PCAN_USBPRO_SETLED] = sizeof(struct pcan_usb_pro_setled), [PCAN_USBPRO_RXMSG8] = sizeof(struct pcan_usb_pro_rxmsg), [PCAN_USBPRO_RXMSG4] = sizeof(struct pcan_usb_pro_rxmsg) - 4, @@ -149,6 +150,7 @@ static int pcan_msg_add_rec(struct pcan_usb_pro_msg *pm, int id, ...) case PCAN_USBPRO_SETBTR: case PCAN_USBPRO_GETDEVID: + case PCAN_USBPRO_SETDEVID: *pc++ = va_arg(ap, int); pc += 2; *(__le32 *)pc = cpu_to_le32(va_arg(ap, u32)); @@ -419,8 +421,8 @@ static int pcan_usb_pro_set_led(struct peak_usb_device *dev, u8 mode, return pcan_usb_pro_send_cmd(dev, &um); } -static int pcan_usb_pro_get_device_id(struct peak_usb_device *dev, - u32 *device_id) +static int pcan_usb_pro_get_can_channel_id(struct peak_usb_device *dev, + u32 *can_ch_id) { struct pcan_usb_pro_devid *pdn; struct pcan_usb_pro_msg um; @@ -439,11 +441,23 @@ static int pcan_usb_pro_get_device_id(struct peak_usb_device *dev, return err; pdn = (struct pcan_usb_pro_devid *)pc; - *device_id = le32_to_cpu(pdn->dev_num); + *can_ch_id = le32_to_cpu(pdn->dev_num); return err; } +static int pcan_usb_pro_set_can_channel_id(struct peak_usb_device *dev, + u32 can_ch_id) +{ + struct pcan_usb_pro_msg um; + + pcan_msg_init_empty(&um, dev->cmd_buf, PCAN_USB_MAX_CMD_LEN); + pcan_msg_add_rec(&um, PCAN_USBPRO_SETDEVID, dev->ctrl_idx, + can_ch_id); + + return pcan_usb_pro_send_cmd(dev, &um); +} + static int pcan_usb_pro_set_bittiming(struct peak_usb_device *dev, struct can_bittiming *bt) { @@ -1023,6 +1037,9 @@ static int pcan_usb_pro_set_phys_id(struct net_device *netdev, static const struct ethtool_ops pcan_usb_pro_ethtool_ops = { .set_phys_id = pcan_usb_pro_set_phys_id, .get_ts_info = pcan_get_ts_info, + .get_eeprom_len = peak_usb_get_eeprom_len, + .get_eeprom = peak_usb_get_eeprom, + .set_eeprom = peak_usb_set_eeprom, }; /* @@ -1076,7 +1093,8 @@ const struct peak_usb_adapter pcan_usb_pro = { .dev_free = pcan_usb_pro_free, .dev_set_bus = pcan_usb_pro_set_bus, .dev_set_bittiming = pcan_usb_pro_set_bittiming, - .dev_get_device_id = pcan_usb_pro_get_device_id, + .dev_get_can_channel_id = pcan_usb_pro_get_can_channel_id, + .dev_set_can_channel_id = pcan_usb_pro_set_can_channel_id, .dev_decode_buf = pcan_usb_pro_decode_buf, .dev_encode_msg = pcan_usb_pro_encode_msg, .dev_start = pcan_usb_pro_start, diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.h b/drivers/net/can/usb/peak_usb/pcan_usb_pro.h index a34e0fc021c9..28e740af905d 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.h +++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.h @@ -62,6 +62,7 @@ struct __packed pcan_usb_pro_fwinfo { #define PCAN_USBPRO_SETBTR 0x02 #define PCAN_USBPRO_SETBUSACT 0x04 #define PCAN_USBPRO_SETSILENT 0x05 +#define PCAN_USBPRO_SETDEVID 0x06 #define PCAN_USBPRO_SETFILTR 0x0a #define PCAN_USBPRO_SETTS 0x10 #define PCAN_USBPRO_GETDEVID 0x12 diff --git a/drivers/net/dsa/microchip/Kconfig b/drivers/net/dsa/microchip/Kconfig index 0546c573668a..394ca8678d2b 100644 --- a/drivers/net/dsa/microchip/Kconfig +++ b/drivers/net/dsa/microchip/Kconfig @@ -11,7 +11,6 @@ menuconfig NET_DSA_MICROCHIP_KSZ_COMMON config NET_DSA_MICROCHIP_KSZ9477_I2C tristate "KSZ series I2C connected switch driver" depends on NET_DSA_MICROCHIP_KSZ_COMMON && I2C - depends on PTP_1588_CLOCK_OPTIONAL select REGMAP_I2C help Select to enable support for registering switches configured through I2C. @@ -19,7 +18,6 @@ config NET_DSA_MICROCHIP_KSZ9477_I2C config NET_DSA_MICROCHIP_KSZ_SPI tristate "KSZ series SPI connected switch driver" depends on NET_DSA_MICROCHIP_KSZ_COMMON && SPI - depends on PTP_1588_CLOCK_OPTIONAL select REGMAP_SPI help Select to enable support for registering switches configured through SPI. @@ -27,6 +25,7 @@ config NET_DSA_MICROCHIP_KSZ_SPI config NET_DSA_MICROCHIP_KSZ_PTP bool "Support for the PTP clock on the KSZ9563/LAN937x Ethernet Switch" depends on NET_DSA_MICROCHIP_KSZ_COMMON && PTP_1588_CLOCK + depends on NET_DSA_MICROCHIP_KSZ_COMMON=m || PTP_1588_CLOCK=y help Select to enable support for timestamping & PTP clock manipulation in KSZ8563/KSZ9563/LAN937x series of switches. KSZ9563/KSZ8563 supports diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 616b21c90d05..3a15015bc409 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1302,14 +1302,26 @@ mt7530_port_set_vlan_aware(struct dsa_switch *ds, int port) if (!priv->ports[port].pvid) mt7530_rmw(priv, MT7530_PVC_P(port), ACC_FRM_MASK, MT7530_VLAN_ACC_TAGGED); - } - /* 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 | PVC_EG_TAG_MASK, - VLAN_ATTR(MT7530_VLAN_USER) | - PVC_EG_TAG(MT7530_VLAN_EG_DISABLED)); + /* 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 | PVC_EG_TAG_MASK, + VLAN_ATTR(MT7530_VLAN_USER) | + PVC_EG_TAG(MT7530_VLAN_EG_DISABLED)); + } else { + /* Also set CPU ports to the "user" VLAN port attribute, to + * allow VLAN classification, but keep the EG_TAG attribute as + * "consistent" (i.o.w. don't change its value) for packets + * received by the switch from the CPU, so that tagged packets + * are forwarded to user ports as tagged, and untagged as + * untagged. + */ + mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK, + VLAN_ATTR(MT7530_VLAN_USER)); + } } static void diff --git a/drivers/net/dsa/ocelot/Kconfig b/drivers/net/dsa/ocelot/Kconfig index 60f1f7ada465..640725524d0c 100644 --- a/drivers/net/dsa/ocelot/Kconfig +++ b/drivers/net/dsa/ocelot/Kconfig @@ -8,6 +8,26 @@ config NET_DSA_MSCC_FELIX_DSA_LIB Its name comes from the first hardware chip to make use of it (VSC9959), code named Felix. +config NET_DSA_MSCC_OCELOT_EXT + tristate "Ocelot External Ethernet switch support" + depends on NET_DSA && SPI + depends on NET_VENDOR_MICROSEMI + select MDIO_MSCC_MIIM + select MFD_OCELOT_CORE + select MSCC_OCELOT_SWITCH_LIB + select NET_DSA_MSCC_FELIX_DSA_LIB + select NET_DSA_TAG_OCELOT_8021Q + select NET_DSA_TAG_OCELOT + help + This driver supports the VSC7511, VSC7512, VSC7513 and VSC7514 chips + when controlled through SPI. + + The Ocelot switch family is a set of multi-port networking chips. All + of these chips have the ability to be controlled externally through + SPI or PCIe interfaces. + + Say "Y" here to enable external control to these chips. + config NET_DSA_MSCC_FELIX tristate "Ocelot / Felix Ethernet switch support" depends on NET_DSA && PCI diff --git a/drivers/net/dsa/ocelot/Makefile b/drivers/net/dsa/ocelot/Makefile index fd7dde570d4e..ead868a293e3 100644 --- a/drivers/net/dsa/ocelot/Makefile +++ b/drivers/net/dsa/ocelot/Makefile @@ -1,8 +1,10 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_NET_DSA_MSCC_FELIX_DSA_LIB) += mscc_felix_dsa_lib.o obj-$(CONFIG_NET_DSA_MSCC_FELIX) += mscc_felix.o +obj-$(CONFIG_NET_DSA_MSCC_OCELOT_EXT) += mscc_ocelot_ext.o obj-$(CONFIG_NET_DSA_MSCC_SEVILLE) += mscc_seville.o mscc_felix_dsa_lib-objs := felix.o mscc_felix-objs := felix_vsc9959.o +mscc_ocelot_ext-objs := ocelot_ext.o mscc_seville-objs := seville_vsc9953.o diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index f57b4095b793..d4cc9e60f369 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1075,9 +1075,12 @@ static void felix_phylink_mac_link_down(struct dsa_switch *ds, int port, phy_interface_t interface) { struct ocelot *ocelot = ds->priv; + struct felix *felix; + + felix = ocelot_to_felix(ocelot); ocelot_phylink_mac_link_down(ocelot, port, link_an_mode, interface, - FELIX_MAC_QUIRKS); + felix->info->quirks); } static void felix_phylink_mac_link_up(struct dsa_switch *ds, int port, @@ -1092,7 +1095,7 @@ static void felix_phylink_mac_link_up(struct dsa_switch *ds, int port, ocelot_phylink_mac_link_up(ocelot, port, phydev, link_an_mode, interface, speed, duplex, tx_pause, rx_pause, - FELIX_MAC_QUIRKS); + felix->info->quirks); if (felix->info->port_sched_speed_set) felix->info->port_sched_speed_set(ocelot, port, speed); @@ -1270,10 +1273,15 @@ static int felix_parse_ports_node(struct felix *felix, err = felix_validate_phy_mode(felix, port, phy_mode); if (err < 0) { - dev_err(dev, "Unsupported PHY mode %s on port %d\n", - phy_modes(phy_mode), port); + dev_info(dev, "Unsupported PHY mode %s on port %d\n", + phy_modes(phy_mode), port); of_node_put(child); - return err; + + /* Leave port_phy_modes[port] = 0, which is also + * PHY_INTERFACE_MODE_NA. This will perform a + * best-effort to bring up as many ports as possible. + */ + continue; } port_phy_modes[port] = phy_mode; @@ -1312,6 +1320,13 @@ static struct regmap *felix_request_regmap_by_name(struct felix *felix, struct resource res; int i; + /* In an MFD configuration, regmaps are registered directly to the + * parent device before the child devices are probed, so there is no + * need to initialize a new one. + */ + if (!felix->info->resources) + return dev_get_regmap(ocelot->dev->parent, resource_name); + for (i = 0; i < felix->info->num_resources; i++) { if (strcmp(resource_name, felix->info->resources[i].name)) continue; diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h index be22d6ccd7c8..d5d0b30c0b75 100644 --- a/drivers/net/dsa/ocelot/felix.h +++ b/drivers/net/dsa/ocelot/felix.h @@ -7,6 +7,7 @@ #define ocelot_to_felix(o) container_of((o), struct felix, ocelot) #define FELIX_MAC_QUIRKS OCELOT_QUIRK_PCS_PERFORMS_RATE_ADAPTATION +#define OCELOT_PORT_MODE_NONE 0 #define OCELOT_PORT_MODE_INTERNAL BIT(0) #define OCELOT_PORT_MODE_SGMII BIT(1) #define OCELOT_PORT_MODE_QSGMII BIT(2) @@ -36,6 +37,7 @@ struct felix_info { u16 vcap_pol_base2; u16 vcap_pol_max2; const struct ptp_clock_info *ptp_caps; + unsigned long quirks; /* Some Ocelot switches are integrated into the SoC without the * extraction IRQ line connected to the ARM GIC. By enabling this diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 43dc8ed4854d..354aa3dbfde7 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -2593,6 +2593,7 @@ static const struct felix_info felix_info_vsc9959 = { .num_mact_rows = 2048, .num_ports = VSC9959_NUM_PORTS, .num_tx_queues = OCELOT_NUM_TC, + .quirks = FELIX_MAC_QUIRKS, .quirk_no_xtr_irq = true, .ptp_caps = &vsc9959_ptp_caps, .mdio_bus_alloc = vsc9959_mdio_bus_alloc, diff --git a/drivers/net/dsa/ocelot/ocelot_ext.c b/drivers/net/dsa/ocelot/ocelot_ext.c new file mode 100644 index 000000000000..14efa6387bd7 --- /dev/null +++ b/drivers/net/dsa/ocelot/ocelot_ext.c @@ -0,0 +1,163 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright 2021-2022 Innovative Advantage Inc. + */ + +#include <linux/mfd/ocelot.h> +#include <linux/phylink.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <soc/mscc/ocelot.h> +#include <soc/mscc/vsc7514_regs.h> +#include "felix.h" + +#define VSC7514_NUM_PORTS 11 + +#define OCELOT_PORT_MODE_SERDES (OCELOT_PORT_MODE_SGMII | \ + OCELOT_PORT_MODE_QSGMII) + +static const u32 vsc7512_port_modes[VSC7514_NUM_PORTS] = { + OCELOT_PORT_MODE_INTERNAL, + OCELOT_PORT_MODE_INTERNAL, + OCELOT_PORT_MODE_INTERNAL, + OCELOT_PORT_MODE_INTERNAL, + OCELOT_PORT_MODE_NONE, + OCELOT_PORT_MODE_NONE, + OCELOT_PORT_MODE_NONE, + OCELOT_PORT_MODE_NONE, + OCELOT_PORT_MODE_NONE, + OCELOT_PORT_MODE_NONE, + OCELOT_PORT_MODE_NONE, +}; + +static const struct ocelot_ops ocelot_ext_ops = { + .reset = ocelot_reset, + .wm_enc = ocelot_wm_enc, + .wm_dec = ocelot_wm_dec, + .wm_stat = ocelot_wm_stat, + .port_to_netdev = felix_port_to_netdev, + .netdev_to_port = felix_netdev_to_port, +}; + +static const char * const vsc7512_resource_names[TARGET_MAX] = { + [SYS] = "sys", + [REW] = "rew", + [S0] = "s0", + [S1] = "s1", + [S2] = "s2", + [QS] = "qs", + [QSYS] = "qsys", + [ANA] = "ana", +}; + +static const struct felix_info vsc7512_info = { + .resource_names = vsc7512_resource_names, + .regfields = vsc7514_regfields, + .map = vsc7514_regmap, + .ops = &ocelot_ext_ops, + .vcap = vsc7514_vcap_props, + .num_mact_rows = 1024, + .num_ports = VSC7514_NUM_PORTS, + .num_tx_queues = OCELOT_NUM_TC, + .port_modes = vsc7512_port_modes, +}; + +static int ocelot_ext_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct dsa_switch *ds; + struct ocelot *ocelot; + struct felix *felix; + int err; + + felix = kzalloc(sizeof(*felix), GFP_KERNEL); + if (!felix) + return -ENOMEM; + + dev_set_drvdata(dev, felix); + + ocelot = &felix->ocelot; + ocelot->dev = dev; + + ocelot->num_flooding_pgids = 1; + + felix->info = &vsc7512_info; + + ds = kzalloc(sizeof(*ds), GFP_KERNEL); + if (!ds) { + err = -ENOMEM; + dev_err_probe(dev, err, "Failed to allocate DSA switch\n"); + goto err_free_felix; + } + + ds->dev = dev; + ds->num_ports = felix->info->num_ports; + ds->num_tx_queues = felix->info->num_tx_queues; + + ds->ops = &felix_switch_ops; + ds->priv = ocelot; + felix->ds = ds; + felix->tag_proto = DSA_TAG_PROTO_OCELOT; + + err = dsa_register_switch(ds); + if (err) { + dev_err_probe(dev, err, "Failed to register DSA switch\n"); + goto err_free_ds; + } + + return 0; + +err_free_ds: + kfree(ds); +err_free_felix: + kfree(felix); + return err; +} + +static int ocelot_ext_remove(struct platform_device *pdev) +{ + struct felix *felix = dev_get_drvdata(&pdev->dev); + + if (!felix) + return 0; + + dsa_unregister_switch(felix->ds); + + kfree(felix->ds); + kfree(felix); + + return 0; +} + +static void ocelot_ext_shutdown(struct platform_device *pdev) +{ + struct felix *felix = dev_get_drvdata(&pdev->dev); + + if (!felix) + return; + + dsa_switch_shutdown(felix->ds); + + dev_set_drvdata(&pdev->dev, NULL); +} + +static const struct of_device_id ocelot_ext_switch_of_match[] = { + { .compatible = "mscc,vsc7512-switch" }, + { }, +}; +MODULE_DEVICE_TABLE(of, ocelot_ext_switch_of_match); + +static struct platform_driver ocelot_ext_switch_driver = { + .driver = { + .name = "ocelot-switch", + .of_match_table = of_match_ptr(ocelot_ext_switch_of_match), + }, + .probe = ocelot_ext_probe, + .remove = ocelot_ext_remove, + .shutdown = ocelot_ext_shutdown, +}; +module_platform_driver(ocelot_ext_switch_driver); + +MODULE_DESCRIPTION("External Ocelot Switch driver"); +MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS(MFD_OCELOT); diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c index 88ed3a2e487a..287b64b788db 100644 --- a/drivers/net/dsa/ocelot/seville_vsc9953.c +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -971,6 +971,7 @@ static const struct felix_info seville_info_vsc9953 = { .vcap_pol_max = VSC9953_VCAP_POLICER_MAX, .vcap_pol_base2 = VSC9953_VCAP_POLICER_BASE2, .vcap_pol_max2 = VSC9953_VCAP_POLICER_MAX2, + .quirks = FELIX_MAC_QUIRKS, .num_mact_rows = 2048, .num_ports = VSC9953_NUM_PORTS, .num_tx_queues = OCELOT_NUM_TC, diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h index 3fd9728f817f..3b70f6737633 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h @@ -1285,6 +1285,22 @@ #define MDIO_PMA_RX_CTRL1 0x8051 #endif +#ifndef MDIO_PMA_RX_LSTS +#define MDIO_PMA_RX_LSTS 0x018020 +#endif + +#ifndef MDIO_PMA_RX_EQ_CTRL4 +#define MDIO_PMA_RX_EQ_CTRL4 0x0001805C +#endif + +#ifndef MDIO_PMA_MP_MISC_STS +#define MDIO_PMA_MP_MISC_STS 0x0078 +#endif + +#ifndef MDIO_PMA_PHY_RX_EQ_CEU +#define MDIO_PMA_PHY_RX_EQ_CEU 0x1800E +#endif + #ifndef MDIO_PCS_DIG_CTRL #define MDIO_PCS_DIG_CTRL 0x8000 #endif @@ -1395,6 +1411,28 @@ #define XGBE_PMA_RX_RST_0_RESET_ON 0x10 #define XGBE_PMA_RX_RST_0_RESET_OFF 0x00 +#define XGBE_PMA_RX_SIG_DET_0_MASK BIT(4) +#define XGBE_PMA_RX_SIG_DET_0_ENABLE BIT(4) +#define XGBE_PMA_RX_SIG_DET_0_DISABLE 0x0000 + +#define XGBE_PMA_RX_VALID_0_MASK BIT(12) +#define XGBE_PMA_RX_VALID_0_ENABLE BIT(12) +#define XGBE_PMA_RX_VALID_0_DISABLE 0x0000 + +#define XGBE_PMA_RX_AD_REQ_MASK BIT(12) +#define XGBE_PMA_RX_AD_REQ_ENABLE BIT(12) +#define XGBE_PMA_RX_AD_REQ_DISABLE 0x0000 + +#define XGBE_PMA_RX_ADPT_ACK_MASK BIT(12) +#define XGBE_PMA_RX_ADPT_ACK BIT(12) + +#define XGBE_PMA_CFF_UPDTM1_VLD BIT(8) +#define XGBE_PMA_CFF_UPDT0_VLD BIT(9) +#define XGBE_PMA_CFF_UPDT1_VLD BIT(10) +#define XGBE_PMA_CFF_UPDT_MASK (XGBE_PMA_CFF_UPDTM1_VLD |\ + XGBE_PMA_CFF_UPDT0_VLD | \ + XGBE_PMA_CFF_UPDT1_VLD) + #define XGBE_PMA_PLL_CTRL_MASK BIT(15) #define XGBE_PMA_PLL_CTRL_ENABLE BIT(15) #define XGBE_PMA_PLL_CTRL_DISABLE 0x0000 diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index f4683d53e58c..16e7fb2c0dae 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -388,6 +388,10 @@ struct xgbe_phy_data { static DEFINE_MUTEX(xgbe_phy_comm_lock); static enum xgbe_an_mode xgbe_phy_an_mode(struct xgbe_prv_data *pdata); +static void xgbe_phy_rrc(struct xgbe_prv_data *pdata); +static void xgbe_phy_perform_ratechange(struct xgbe_prv_data *pdata, + enum xgbe_mb_cmd cmd, + enum xgbe_mb_subcmd sub_cmd); static int xgbe_phy_i2c_xfer(struct xgbe_prv_data *pdata, struct xgbe_i2c_op *i2c_op) @@ -1882,6 +1886,9 @@ static void xgbe_phy_an_advertising(struct xgbe_prv_data *pdata, if (phy_data->phydev && (phy_data->phydev->speed == SPEED_10000)) XGBE_SET_ADV(dlks, 10000baseKR_Full); + else if (phy_data->phydev && + (phy_data->phydev->speed == SPEED_2500)) + XGBE_SET_ADV(dlks, 2500baseX_Full); else XGBE_SET_ADV(dlks, 1000baseKX_Full); break; @@ -2035,6 +2042,93 @@ static void xgbe_phy_set_redrv_mode(struct xgbe_prv_data *pdata) xgbe_phy_put_comm_ownership(pdata); } +#define MAX_RX_ADAPT_RETRIES 1 +#define XGBE_PMA_RX_VAL_SIG_MASK (XGBE_PMA_RX_SIG_DET_0_MASK | \ + XGBE_PMA_RX_VALID_0_MASK) + +static void xgbe_set_rx_adap_mode(struct xgbe_prv_data *pdata, + enum xgbe_mode mode) +{ + if (pdata->rx_adapt_retries++ >= MAX_RX_ADAPT_RETRIES) { + pdata->rx_adapt_retries = 0; + return; + } + + xgbe_phy_perform_ratechange(pdata, + mode == XGBE_MODE_KR ? + XGBE_MB_CMD_SET_10G_KR : + XGBE_MB_CMD_SET_10G_SFI, + XGBE_MB_SUBCMD_RX_ADAP); +} + +static void xgbe_rx_adaptation(struct xgbe_prv_data *pdata) +{ + struct xgbe_phy_data *phy_data = pdata->phy_data; + unsigned int reg; + + /* step 2: force PCS to send RX_ADAPT Req to PHY */ + XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_RX_EQ_CTRL4, + XGBE_PMA_RX_AD_REQ_MASK, XGBE_PMA_RX_AD_REQ_ENABLE); + + /* Step 3: Wait for RX_ADAPT ACK from the PHY */ + msleep(200); + + /* Software polls for coefficient update command (given by local PHY) */ + reg = XMDIO_READ(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_PHY_RX_EQ_CEU); + + /* Clear the RX_AD_REQ bit */ + XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_RX_EQ_CTRL4, + XGBE_PMA_RX_AD_REQ_MASK, XGBE_PMA_RX_AD_REQ_DISABLE); + + /* Check if coefficient update command is set */ + if ((reg & XGBE_PMA_CFF_UPDT_MASK) != XGBE_PMA_CFF_UPDT_MASK) + goto set_mode; + + /* Step 4: Check for Block lock */ + + /* Link status is latched low, so read once to clear + * and then read again to get current state + */ + reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1); + reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1); + if (reg & MDIO_STAT1_LSTATUS) { + /* If the block lock is found, update the helpers + * and declare the link up + */ + netif_dbg(pdata, link, pdata->netdev, "Block_lock done"); + pdata->rx_adapt_done = true; + pdata->mode_set = false; + return; + } + +set_mode: + xgbe_set_rx_adap_mode(pdata, phy_data->cur_mode); +} + +static void xgbe_phy_rx_adaptation(struct xgbe_prv_data *pdata) +{ + unsigned int reg; + +rx_adapt_reinit: + reg = XMDIO_READ_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_RX_LSTS, + XGBE_PMA_RX_VAL_SIG_MASK); + + /* step 1: Check for RX_VALID && LF_SIGDET */ + if ((reg & XGBE_PMA_RX_VAL_SIG_MASK) != XGBE_PMA_RX_VAL_SIG_MASK) { + netif_dbg(pdata, link, pdata->netdev, + "RX_VALID or LF_SIGDET is unset, issue rrc"); + xgbe_phy_rrc(pdata); + if (pdata->rx_adapt_retries++ >= MAX_RX_ADAPT_RETRIES) { + pdata->rx_adapt_retries = 0; + return; + } + goto rx_adapt_reinit; + } + + /* perform rx adaptation */ + xgbe_rx_adaptation(pdata); +} + static void xgbe_phy_rx_reset(struct xgbe_prv_data *pdata) { int reg; @@ -2100,7 +2194,7 @@ static void xgbe_phy_perform_ratechange(struct xgbe_prv_data *pdata, wait = XGBE_RATECHANGE_COUNT; while (wait--) { if (!XP_IOREAD_BITS(pdata, XP_DRIVER_INT_RO, STATUS)) - goto reenable_pll; + goto do_rx_adaptation; usleep_range(1000, 2000); } @@ -2110,6 +2204,20 @@ static void xgbe_phy_perform_ratechange(struct xgbe_prv_data *pdata, /* Reset on error */ xgbe_phy_rx_reset(pdata); + goto reenable_pll; + +do_rx_adaptation: + if (pdata->en_rx_adap && sub_cmd == XGBE_MB_SUBCMD_RX_ADAP && + (cmd == XGBE_MB_CMD_SET_10G_KR || cmd == XGBE_MB_CMD_SET_10G_SFI)) { + netif_dbg(pdata, link, pdata->netdev, + "Enabling RX adaptation\n"); + pdata->mode_set = true; + xgbe_phy_rx_adaptation(pdata); + /* return from here to avoid enabling PLL ctrl + * during adaptation phase + */ + return; + } reenable_pll: /* Enable PLL re-initialization, not needed for PHY Power Off and RRC cmds */ @@ -2138,6 +2246,31 @@ static void xgbe_phy_power_off(struct xgbe_prv_data *pdata) netif_dbg(pdata, link, pdata->netdev, "phy powered off\n"); } +static bool enable_rx_adap(struct xgbe_prv_data *pdata, enum xgbe_mode mode) +{ + struct xgbe_phy_data *phy_data = pdata->phy_data; + unsigned int ver; + + /* Rx-Adaptation is not supported on older platforms(< 0x30H) */ + ver = XGMAC_GET_BITS(pdata->hw_feat.version, MAC_VR, SNPSVER); + if (ver < 0x30) + return false; + + /* Re-driver models 4223 && 4227 do not support Rx-Adaptation */ + if (phy_data->redrv && + (phy_data->redrv_model == XGBE_PHY_REDRV_MODEL_4223 || + phy_data->redrv_model == XGBE_PHY_REDRV_MODEL_4227)) + return false; + + /* 10G KR mode with AN does not support Rx-Adaptation */ + if (mode == XGBE_MODE_KR && + phy_data->port_mode != XGBE_PORT_MODE_BACKPLANE_NO_AUTONEG) + return false; + + pdata->en_rx_adap = 1; + return true; +} + static void xgbe_phy_sfi_mode(struct xgbe_prv_data *pdata) { struct xgbe_phy_data *phy_data = pdata->phy_data; @@ -2146,7 +2279,12 @@ static void xgbe_phy_sfi_mode(struct xgbe_prv_data *pdata) /* 10G/SFI */ if (phy_data->sfp_cable != XGBE_SFP_CABLE_PASSIVE) { + pdata->en_rx_adap = 0; xgbe_phy_perform_ratechange(pdata, XGBE_MB_CMD_SET_10G_SFI, XGBE_MB_SUBCMD_ACTIVE); + } else if ((phy_data->sfp_cable == XGBE_SFP_CABLE_PASSIVE) && + (enable_rx_adap(pdata, XGBE_MODE_SFI))) { + xgbe_phy_perform_ratechange(pdata, XGBE_MB_CMD_SET_10G_SFI, + XGBE_MB_SUBCMD_RX_ADAP); } else { if (phy_data->sfp_cable_len <= 1) xgbe_phy_perform_ratechange(pdata, XGBE_MB_CMD_SET_10G_SFI, @@ -2227,7 +2365,12 @@ static void xgbe_phy_kr_mode(struct xgbe_prv_data *pdata) xgbe_phy_set_redrv_mode(pdata); /* 10G/KR */ - xgbe_phy_perform_ratechange(pdata, XGBE_MB_CMD_SET_10G_KR, XGBE_MB_SUBCMD_NONE); + if (enable_rx_adap(pdata, XGBE_MODE_KR)) + xgbe_phy_perform_ratechange(pdata, XGBE_MB_CMD_SET_10G_KR, + XGBE_MB_SUBCMD_RX_ADAP); + else + xgbe_phy_perform_ratechange(pdata, XGBE_MB_CMD_SET_10G_KR, + XGBE_MB_SUBCMD_NONE); phy_data->cur_mode = XGBE_MODE_KR; @@ -2282,9 +2425,11 @@ static enum xgbe_mode xgbe_phy_switch_baset_mode(struct xgbe_prv_data *pdata) case XGBE_MODE_SGMII_100: case XGBE_MODE_SGMII_1000: return XGBE_MODE_KR; + case XGBE_MODE_KX_2500: + return XGBE_MODE_SGMII_1000; case XGBE_MODE_KR: default: - return XGBE_MODE_SGMII_1000; + return XGBE_MODE_KX_2500; } } @@ -2644,7 +2789,8 @@ static bool xgbe_phy_valid_speed_baset_mode(struct xgbe_prv_data *pdata, case SPEED_1000: return true; case SPEED_2500: - return (phy_data->port_mode == XGBE_PORT_MODE_NBASE_T); + return ((phy_data->port_mode == XGBE_PORT_MODE_10GBASE_T) || + (phy_data->port_mode == XGBE_PORT_MODE_NBASE_T)); case SPEED_10000: return (phy_data->port_mode == XGBE_PORT_MODE_10GBASE_T); default: @@ -2737,8 +2883,11 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart) return 0; } - if (phy_data->sfp_mod_absent || phy_data->sfp_rx_los) + if (phy_data->sfp_mod_absent || phy_data->sfp_rx_los) { + if (pdata->en_rx_adap) + pdata->rx_adapt_done = false; return 0; + } } if (phy_data->phydev) { @@ -2760,7 +2909,29 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart) */ reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1); reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1); - if (reg & MDIO_STAT1_LSTATUS) + + if (pdata->en_rx_adap) { + /* if the link is available and adaptation is done, + * declare link up + */ + if ((reg & MDIO_STAT1_LSTATUS) && pdata->rx_adapt_done) + return 1; + /* If either link is not available or adaptation is not done, + * retrigger the adaptation logic. (if the mode is not set, + * then issue mailbox command first) + */ + if (pdata->mode_set) { + xgbe_phy_rx_adaptation(pdata); + } else { + pdata->rx_adapt_done = false; + xgbe_phy_set_mode(pdata, phy_data->cur_mode); + } + + /* check again for the link and adaptation status */ + reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1); + if ((reg & MDIO_STAT1_LSTATUS) && pdata->rx_adapt_done) + return 1; + } else if (reg & MDIO_STAT1_LSTATUS) return 1; if (pdata->phy.autoneg == AUTONEG_ENABLE && @@ -3024,6 +3195,7 @@ static bool xgbe_phy_port_mode_mismatch(struct xgbe_prv_data *pdata) if ((phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10) || (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) || (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) || + (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_2500) || (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000)) return false; break; @@ -3474,6 +3646,10 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata) XGBE_SET_SUP(lks, 1000baseT_Full); phy_data->start_mode = XGBE_MODE_SGMII_1000; } + if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_2500) { + XGBE_SET_SUP(lks, 2500baseT_Full); + phy_data->start_mode = XGBE_MODE_KX_2500; + } if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000) { XGBE_SET_SUP(lks, 10000baseT_Full); phy_data->start_mode = XGBE_MODE_KR; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index 16e73df3e9b9..ad136ed493ed 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -625,6 +625,7 @@ enum xgbe_mb_cmd { enum xgbe_mb_subcmd { XGBE_MB_SUBCMD_NONE = 0, + XGBE_MB_SUBCMD_RX_ADAP, /* 10GbE SFP subcommands */ XGBE_MB_SUBCMD_ACTIVE = 0, @@ -1316,6 +1317,10 @@ struct xgbe_prv_data { bool debugfs_an_cdr_workaround; bool debugfs_an_cdr_track_early; + bool en_rx_adap; + int rx_adapt_retries; + bool rx_adapt_done; + bool mode_set; }; /* Function prototypes*/ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index 77609dc0a08d..0b2a52199914 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -21,6 +21,7 @@ #include <linux/ip.h> #include <linux/udp.h> #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include <linux/filter.h> MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index f4ca0c6c0f51..948586bf1b5b 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -213,6 +213,7 @@ config BNXT select NET_DEVLINK select PAGE_POOL select DIMLIB + select AUXILIARY_BUS help This driver supports Broadcom NetXtreme-C/E 10/25/40/50 gigabit Ethernet cards. To compile this driver as a module, choose M here: diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index b751dc8486dc..392ec09a1d8a 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -196,28 +196,6 @@ static int b44_wait_bit(struct b44 *bp, unsigned long reg, return 0; } -static inline void __b44_cam_read(struct b44 *bp, unsigned char *data, int index) -{ - u32 val; - - bw32(bp, B44_CAM_CTRL, (CAM_CTRL_READ | - (index << CAM_CTRL_INDEX_SHIFT))); - - b44_wait_bit(bp, B44_CAM_CTRL, CAM_CTRL_BUSY, 100, 1); - - val = br32(bp, B44_CAM_DATA_LO); - - data[2] = (val >> 24) & 0xFF; - data[3] = (val >> 16) & 0xFF; - data[4] = (val >> 8) & 0xFF; - data[5] = (val >> 0) & 0xFF; - - val = br32(bp, B44_CAM_DATA_HI); - - data[0] = (val >> 8) & 0xFF; - data[1] = (val >> 0) & 0xFF; -} - static inline void __b44_cam_write(struct b44 *bp, const unsigned char *data, int index) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index a1b4356dfb6c..ab5dfb3a4081 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2414,7 +2414,6 @@ static int bnxt_async_event_process(struct bnxt *bp, } bnxt_queue_sp_work(bp); async_event_process_exit: - bnxt_ulp_async_events(bp, cmpl); return 0; } @@ -5538,7 +5537,7 @@ vnic_mru: #endif if ((bp->flags & BNXT_FLAG_STRIP_VLAN) || def_vlan) req->flags |= cpu_to_le32(VNIC_CFG_REQ_FLAGS_VLAN_STRIP_MODE); - if (!vnic_id && bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP)) + if (!vnic_id && bnxt_ulp_registered(bp->edev)) req->flags |= cpu_to_le32(bnxt_get_roce_vnic_mode(bp)); return hwrm_req_send(bp, req); @@ -13181,6 +13180,8 @@ static void bnxt_remove_one(struct pci_dev *pdev) if (BNXT_PF(bp)) bnxt_sriov_disable(bp); + bnxt_rdma_aux_device_uninit(bp); + bnxt_ptp_clear(bp); pci_disable_pcie_error_reporting(pdev); unregister_netdev(dev); @@ -13779,11 +13780,13 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) bnxt_dl_fw_reporters_create(bp); + bnxt_rdma_aux_device_init(bp); + bnxt_print_device_info(bp); pci_save_state(pdev); - return 0; + return 0; init_err_cleanup: bnxt_dl_unregister(bp); init_err_dl: @@ -13827,7 +13830,6 @@ static void bnxt_shutdown(struct pci_dev *pdev) if (netif_running(dev)) dev_close(dev); - bnxt_ulp_shutdown(bp); bnxt_clear_int_mode(bp); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 5163ef4a49ea..dcb09fbe4007 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -24,6 +24,7 @@ #include <linux/interrupt.h> #include <linux/rhashtable.h> #include <linux/crash_dump.h> +#include <linux/auxiliary_bus.h> #include <net/devlink.h> #include <net/dst_metadata.h> #include <net/xdp.h> @@ -1631,6 +1632,12 @@ struct bnxt_fw_health { #define BNXT_FW_IF_RETRY 10 #define BNXT_FW_SLOT_RESET_RETRY 4 +struct bnxt_aux_priv { + struct auxiliary_device aux_dev; + struct bnxt_en_dev *edev; + int id; +}; + enum board_idx { BCM57301, BCM57302, @@ -1852,6 +1859,7 @@ struct bnxt { #define BNXT_CHIP_P4_PLUS(bp) \ (BNXT_CHIP_P4(bp) || BNXT_CHIP_P5(bp)) + struct bnxt_aux_priv *aux_priv; struct bnxt_en_dev *edev; struct bnxt_napi **bnapi; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 26913dc816d3..8b3e7697390f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -1303,7 +1303,6 @@ int bnxt_dl_register(struct bnxt *bp) if (rc) goto err_dl_port_unreg; - devlink_set_features(dl, DEVLINK_F_RELOAD); out: devlink_register(dl); return 0; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index a4cba7cb2783..3ed3a2b3b3a9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -749,7 +749,6 @@ int bnxt_cfg_hw_sriov(struct bnxt *bp, int *num_vfs, bool reset) *num_vfs = rc; } - bnxt_ulp_sriov_cfg(bp, *num_vfs); return 0; } @@ -823,10 +822,8 @@ static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs) goto err_out2; rc = pci_enable_sriov(bp->pdev, *num_vfs); - if (rc) { - bnxt_ulp_sriov_cfg(bp, 0); + if (rc) goto err_out2; - } return 0; @@ -872,8 +869,6 @@ void bnxt_sriov_disable(struct bnxt *bp) rtnl_lock(); bnxt_restore_pf_fw_resources(bp); rtnl_unlock(); - - bnxt_ulp_sriov_cfg(bp, 0); } int bnxt_sriov_configure(struct pci_dev *pdev, int num_vfs) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index 2e54bf4fc7a7..d4cc9c371e7b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -19,89 +19,26 @@ #include <linux/irq.h> #include <asm/byteorder.h> #include <linux/bitmap.h> +#include <linux/auxiliary_bus.h> #include "bnxt_hsi.h" #include "bnxt.h" #include "bnxt_hwrm.h" #include "bnxt_ulp.h" -static int bnxt_register_dev(struct bnxt_en_dev *edev, unsigned int ulp_id, - struct bnxt_ulp_ops *ulp_ops, void *handle) -{ - struct net_device *dev = edev->net; - struct bnxt *bp = netdev_priv(dev); - struct bnxt_ulp *ulp; - - ASSERT_RTNL(); - if (ulp_id >= BNXT_MAX_ULP) - return -EINVAL; - - ulp = &edev->ulp_tbl[ulp_id]; - if (rcu_access_pointer(ulp->ulp_ops)) { - netdev_err(bp->dev, "ulp id %d already registered\n", ulp_id); - return -EBUSY; - } - if (ulp_id == BNXT_ROCE_ULP) { - unsigned int max_stat_ctxs; - - max_stat_ctxs = bnxt_get_max_func_stat_ctxs(bp); - if (max_stat_ctxs <= BNXT_MIN_ROCE_STAT_CTXS || - bp->cp_nr_rings == max_stat_ctxs) - return -ENOMEM; - } - - atomic_set(&ulp->ref_count, 0); - ulp->handle = handle; - rcu_assign_pointer(ulp->ulp_ops, ulp_ops); - - if (ulp_id == BNXT_ROCE_ULP) { - if (test_bit(BNXT_STATE_OPEN, &bp->state)) - bnxt_hwrm_vnic_cfg(bp, 0); - } - - return 0; -} - -static int bnxt_unregister_dev(struct bnxt_en_dev *edev, unsigned int ulp_id) -{ - struct net_device *dev = edev->net; - struct bnxt *bp = netdev_priv(dev); - struct bnxt_ulp *ulp; - int i = 0; - - ASSERT_RTNL(); - if (ulp_id >= BNXT_MAX_ULP) - return -EINVAL; - - ulp = &edev->ulp_tbl[ulp_id]; - if (!rcu_access_pointer(ulp->ulp_ops)) { - netdev_err(bp->dev, "ulp id %d not registered\n", ulp_id); - return -EINVAL; - } - if (ulp_id == BNXT_ROCE_ULP && ulp->msix_requested) - edev->en_ops->bnxt_free_msix(edev, ulp_id); - - if (ulp->max_async_event_id) - bnxt_hwrm_func_drv_rgtr(bp, NULL, 0, true); - - RCU_INIT_POINTER(ulp->ulp_ops, NULL); - synchronize_rcu(); - ulp->max_async_event_id = 0; - ulp->async_events_bmap = NULL; - while (atomic_read(&ulp->ref_count) != 0 && i < 10) { - msleep(100); - i++; - } - return 0; -} +static DEFINE_IDA(bnxt_aux_dev_ids); static void bnxt_fill_msix_vecs(struct bnxt *bp, struct bnxt_msix_entry *ent) { struct bnxt_en_dev *edev = bp->edev; int num_msix, idx, i; - num_msix = edev->ulp_tbl[BNXT_ROCE_ULP].msix_requested; - idx = edev->ulp_tbl[BNXT_ROCE_ULP].msix_base; + if (!edev->ulp_tbl->msix_requested) { + netdev_warn(bp->dev, "Requested MSI-X vectors insufficient\n"); + return; + } + num_msix = edev->ulp_tbl->msix_requested; + idx = edev->ulp_tbl->msix_base; for (i = 0; i < num_msix; i++) { ent[i].vector = bp->irq_tbl[idx + i].vector; ent[i].ring_idx = idx + i; @@ -115,125 +52,95 @@ static void bnxt_fill_msix_vecs(struct bnxt *bp, struct bnxt_msix_entry *ent) } } -static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, unsigned int ulp_id, - struct bnxt_msix_entry *ent, int num_msix) +int bnxt_register_dev(struct bnxt_en_dev *edev, + struct bnxt_ulp_ops *ulp_ops, + void *handle) { struct net_device *dev = edev->net; struct bnxt *bp = netdev_priv(dev); - struct bnxt_hw_resc *hw_resc; - int max_idx, max_cp_rings; - int avail_msix, idx; - int total_vecs; - int rc = 0; - - ASSERT_RTNL(); - if (ulp_id != BNXT_ROCE_ULP) - return -EINVAL; - - if (!(bp->flags & BNXT_FLAG_USING_MSIX)) - return -ENODEV; + unsigned int max_stat_ctxs; + struct bnxt_ulp *ulp; - if (edev->ulp_tbl[ulp_id].msix_requested) - return -EAGAIN; + max_stat_ctxs = bnxt_get_max_func_stat_ctxs(bp); + if (max_stat_ctxs <= BNXT_MIN_ROCE_STAT_CTXS || + bp->cp_nr_rings == max_stat_ctxs) + return -ENOMEM; - max_cp_rings = bnxt_get_max_func_cp_rings(bp); - avail_msix = bnxt_get_avail_msix(bp, num_msix); - if (!avail_msix) + ulp = edev->ulp_tbl; + if (!ulp) return -ENOMEM; - if (avail_msix > num_msix) - avail_msix = num_msix; - - if (BNXT_NEW_RM(bp)) { - idx = bp->cp_nr_rings; - } else { - max_idx = min_t(int, bp->total_irqs, max_cp_rings); - idx = max_idx - avail_msix; - } - edev->ulp_tbl[ulp_id].msix_base = idx; - edev->ulp_tbl[ulp_id].msix_requested = avail_msix; - hw_resc = &bp->hw_resc; - total_vecs = idx + avail_msix; - if (bp->total_irqs < total_vecs || - (BNXT_NEW_RM(bp) && hw_resc->resv_irqs < total_vecs)) { - if (netif_running(dev)) { - bnxt_close_nic(bp, true, false); - rc = bnxt_open_nic(bp, true, false); - } else { - rc = bnxt_reserve_rings(bp, true); - } - } - if (rc) { - edev->ulp_tbl[ulp_id].msix_requested = 0; - return -EAGAIN; - } - if (BNXT_NEW_RM(bp)) { - int resv_msix; + ulp->handle = handle; + rcu_assign_pointer(ulp->ulp_ops, ulp_ops); + + if (test_bit(BNXT_STATE_OPEN, &bp->state)) + bnxt_hwrm_vnic_cfg(bp, 0); - resv_msix = hw_resc->resv_irqs - bp->cp_nr_rings; - avail_msix = min_t(int, resv_msix, avail_msix); - edev->ulp_tbl[ulp_id].msix_requested = avail_msix; - } - bnxt_fill_msix_vecs(bp, ent); + bnxt_fill_msix_vecs(bp, bp->edev->msix_entries); edev->flags |= BNXT_EN_FLAG_MSIX_REQUESTED; - return avail_msix; + return 0; } +EXPORT_SYMBOL(bnxt_register_dev); -static int bnxt_free_msix_vecs(struct bnxt_en_dev *edev, unsigned int ulp_id) +void bnxt_unregister_dev(struct bnxt_en_dev *edev) { struct net_device *dev = edev->net; struct bnxt *bp = netdev_priv(dev); + struct bnxt_ulp *ulp; + int i = 0; - ASSERT_RTNL(); - if (ulp_id != BNXT_ROCE_ULP) - return -EINVAL; + ulp = edev->ulp_tbl; + if (ulp->msix_requested) + edev->flags &= ~BNXT_EN_FLAG_MSIX_REQUESTED; - if (!(edev->flags & BNXT_EN_FLAG_MSIX_REQUESTED)) - return 0; + if (ulp->max_async_event_id) + bnxt_hwrm_func_drv_rgtr(bp, NULL, 0, true); - edev->ulp_tbl[ulp_id].msix_requested = 0; - edev->flags &= ~BNXT_EN_FLAG_MSIX_REQUESTED; - if (netif_running(dev) && !(edev->flags & BNXT_EN_FLAG_ULP_STOPPED)) { - bnxt_close_nic(bp, true, false); - bnxt_open_nic(bp, true, false); + RCU_INIT_POINTER(ulp->ulp_ops, NULL); + synchronize_rcu(); + ulp->max_async_event_id = 0; + ulp->async_events_bmap = NULL; + while (atomic_read(&ulp->ref_count) != 0 && i < 10) { + msleep(100); + i++; } - return 0; + return; } +EXPORT_SYMBOL(bnxt_unregister_dev); int bnxt_get_ulp_msix_num(struct bnxt *bp) { - if (bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP)) { - struct bnxt_en_dev *edev = bp->edev; + u32 roce_msix = BNXT_VF(bp) ? + BNXT_MAX_VF_ROCE_MSIX : BNXT_MAX_ROCE_MSIX; - return edev->ulp_tbl[BNXT_ROCE_ULP].msix_requested; - } - return 0; + return ((bp->flags & BNXT_FLAG_ROCE_CAP) ? + min_t(u32, roce_msix, num_online_cpus()) : 0); } int bnxt_get_ulp_msix_base(struct bnxt *bp) { - if (bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP)) { + if (bnxt_ulp_registered(bp->edev)) { struct bnxt_en_dev *edev = bp->edev; - if (edev->ulp_tbl[BNXT_ROCE_ULP].msix_requested) - return edev->ulp_tbl[BNXT_ROCE_ULP].msix_base; + if (edev->ulp_tbl->msix_requested) + return edev->ulp_tbl->msix_base; } return 0; } int bnxt_get_ulp_stat_ctxs(struct bnxt *bp) { - if (bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP)) { + if (bnxt_ulp_registered(bp->edev)) { struct bnxt_en_dev *edev = bp->edev; - if (edev->ulp_tbl[BNXT_ROCE_ULP].msix_requested) + if (edev->ulp_tbl->msix_requested) return BNXT_MIN_ROCE_STAT_CTXS; } return 0; } -static int bnxt_send_msg(struct bnxt_en_dev *edev, unsigned int ulp_id, +int bnxt_send_msg(struct bnxt_en_dev *edev, struct bnxt_fw_msg *fw_msg) { struct net_device *dev = edev->net; @@ -243,7 +150,7 @@ static int bnxt_send_msg(struct bnxt_en_dev *edev, unsigned int ulp_id, u32 resp_len; int rc; - if (ulp_id != BNXT_ROCE_ULP && bp->fw_reset_state) + if (bp->fw_reset_state) return -EBUSY; rc = hwrm_req_init(bp, req, 0 /* don't care */); @@ -267,42 +174,36 @@ static int bnxt_send_msg(struct bnxt_en_dev *edev, unsigned int ulp_id, hwrm_req_drop(bp, req); return rc; } - -static void bnxt_ulp_get(struct bnxt_ulp *ulp) -{ - atomic_inc(&ulp->ref_count); -} - -static void bnxt_ulp_put(struct bnxt_ulp *ulp) -{ - atomic_dec(&ulp->ref_count); -} +EXPORT_SYMBOL(bnxt_send_msg); void bnxt_ulp_stop(struct bnxt *bp) { + struct bnxt_aux_priv *aux_priv = bp->aux_priv; struct bnxt_en_dev *edev = bp->edev; - struct bnxt_ulp_ops *ops; - int i; if (!edev) return; edev->flags |= BNXT_EN_FLAG_ULP_STOPPED; - for (i = 0; i < BNXT_MAX_ULP; i++) { - struct bnxt_ulp *ulp = &edev->ulp_tbl[i]; + if (aux_priv) { + struct auxiliary_device *adev; - ops = rtnl_dereference(ulp->ulp_ops); - if (!ops || !ops->ulp_stop) - continue; - ops->ulp_stop(ulp->handle); + adev = &aux_priv->aux_dev; + if (adev->dev.driver) { + struct auxiliary_driver *adrv; + pm_message_t pm = {}; + + adrv = to_auxiliary_drv(adev->dev.driver); + edev->en_state = bp->state; + adrv->suspend(adev, pm); + } } } void bnxt_ulp_start(struct bnxt *bp, int err) { + struct bnxt_aux_priv *aux_priv = bp->aux_priv; struct bnxt_en_dev *edev = bp->edev; - struct bnxt_ulp_ops *ops; - int i; if (!edev) return; @@ -312,58 +213,19 @@ void bnxt_ulp_start(struct bnxt *bp, int err) if (err) return; - for (i = 0; i < BNXT_MAX_ULP; i++) { - struct bnxt_ulp *ulp = &edev->ulp_tbl[i]; - - ops = rtnl_dereference(ulp->ulp_ops); - if (!ops || !ops->ulp_start) - continue; - ops->ulp_start(ulp->handle); - } -} - -void bnxt_ulp_sriov_cfg(struct bnxt *bp, int num_vfs) -{ - struct bnxt_en_dev *edev = bp->edev; - struct bnxt_ulp_ops *ops; - int i; - - if (!edev) - return; + if (aux_priv) { + struct auxiliary_device *adev; - for (i = 0; i < BNXT_MAX_ULP; i++) { - struct bnxt_ulp *ulp = &edev->ulp_tbl[i]; + adev = &aux_priv->aux_dev; + if (adev->dev.driver) { + struct auxiliary_driver *adrv; - rcu_read_lock(); - ops = rcu_dereference(ulp->ulp_ops); - if (!ops || !ops->ulp_sriov_config) { - rcu_read_unlock(); - continue; + adrv = to_auxiliary_drv(adev->dev.driver); + edev->en_state = bp->state; + adrv->resume(adev); } - bnxt_ulp_get(ulp); - rcu_read_unlock(); - ops->ulp_sriov_config(ulp->handle, num_vfs); - bnxt_ulp_put(ulp); } -} -void bnxt_ulp_shutdown(struct bnxt *bp) -{ - struct bnxt_en_dev *edev = bp->edev; - struct bnxt_ulp_ops *ops; - int i; - - if (!edev) - return; - - for (i = 0; i < BNXT_MAX_ULP; i++) { - struct bnxt_ulp *ulp = &edev->ulp_tbl[i]; - - ops = rtnl_dereference(ulp->ulp_ops); - if (!ops || !ops->ulp_shutdown) - continue; - ops->ulp_shutdown(ulp->handle); - } } void bnxt_ulp_irq_stop(struct bnxt *bp) @@ -374,8 +236,8 @@ void bnxt_ulp_irq_stop(struct bnxt *bp) if (!edev || !(edev->flags & BNXT_EN_FLAG_MSIX_REQUESTED)) return; - if (bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP)) { - struct bnxt_ulp *ulp = &edev->ulp_tbl[BNXT_ROCE_ULP]; + if (bnxt_ulp_registered(bp->edev)) { + struct bnxt_ulp *ulp = edev->ulp_tbl; if (!ulp->msix_requested) return; @@ -395,8 +257,8 @@ void bnxt_ulp_irq_restart(struct bnxt *bp, int err) if (!edev || !(edev->flags & BNXT_EN_FLAG_MSIX_REQUESTED)) return; - if (bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP)) { - struct bnxt_ulp *ulp = &edev->ulp_tbl[BNXT_ROCE_ULP]; + if (bnxt_ulp_registered(bp->edev)) { + struct bnxt_ulp *ulp = edev->ulp_tbl; struct bnxt_msix_entry *ent = NULL; if (!ulp->msix_requested) @@ -418,46 +280,15 @@ void bnxt_ulp_irq_restart(struct bnxt *bp, int err) } } -void bnxt_ulp_async_events(struct bnxt *bp, struct hwrm_async_event_cmpl *cmpl) -{ - u16 event_id = le16_to_cpu(cmpl->event_id); - struct bnxt_en_dev *edev = bp->edev; - struct bnxt_ulp_ops *ops; - int i; - - if (!edev) - return; - - rcu_read_lock(); - for (i = 0; i < BNXT_MAX_ULP; i++) { - struct bnxt_ulp *ulp = &edev->ulp_tbl[i]; - - ops = rcu_dereference(ulp->ulp_ops); - if (!ops || !ops->ulp_async_notifier) - continue; - if (!ulp->async_events_bmap || - event_id > ulp->max_async_event_id) - continue; - - /* Read max_async_event_id first before testing the bitmap. */ - smp_rmb(); - if (test_bit(event_id, ulp->async_events_bmap)) - ops->ulp_async_notifier(ulp->handle, cmpl); - } - rcu_read_unlock(); -} - -static int bnxt_register_async_events(struct bnxt_en_dev *edev, unsigned int ulp_id, - unsigned long *events_bmap, u16 max_id) +int bnxt_register_async_events(struct bnxt_en_dev *edev, + unsigned long *events_bmap, + u16 max_id) { struct net_device *dev = edev->net; struct bnxt *bp = netdev_priv(dev); struct bnxt_ulp *ulp; - if (ulp_id >= BNXT_MAX_ULP) - return -EINVAL; - - ulp = &edev->ulp_tbl[ulp_id]; + ulp = edev->ulp_tbl; ulp->async_events_bmap = events_bmap; /* Make sure bnxt_ulp_async_events() sees this order */ smp_wmb(); @@ -465,38 +296,121 @@ static int bnxt_register_async_events(struct bnxt_en_dev *edev, unsigned int ulp bnxt_hwrm_func_drv_rgtr(bp, events_bmap, max_id + 1, true); return 0; } +EXPORT_SYMBOL(bnxt_register_async_events); -static const struct bnxt_en_ops bnxt_en_ops_tbl = { - .bnxt_register_device = bnxt_register_dev, - .bnxt_unregister_device = bnxt_unregister_dev, - .bnxt_request_msix = bnxt_req_msix_vecs, - .bnxt_free_msix = bnxt_free_msix_vecs, - .bnxt_send_fw_msg = bnxt_send_msg, - .bnxt_register_fw_async_events = bnxt_register_async_events, -}; +void bnxt_rdma_aux_device_uninit(struct bnxt *bp) +{ + struct bnxt_aux_priv *aux_priv; + struct auxiliary_device *adev; + + /* Skip if no auxiliary device init was done. */ + if (!(bp->flags & BNXT_FLAG_ROCE_CAP)) + return; + + aux_priv = bp->aux_priv; + adev = &aux_priv->aux_dev; + auxiliary_device_delete(adev); + auxiliary_device_uninit(adev); +} -struct bnxt_en_dev *bnxt_ulp_probe(struct net_device *dev) +static void bnxt_aux_dev_release(struct device *dev) { - struct bnxt *bp = netdev_priv(dev); - struct bnxt_en_dev *edev; + struct bnxt_aux_priv *aux_priv = + container_of(dev, struct bnxt_aux_priv, aux_dev.dev); + + ida_free(&bnxt_aux_dev_ids, aux_priv->id); + kfree(aux_priv->edev->ulp_tbl); + kfree(aux_priv->edev); + kfree(aux_priv); +} + +static void bnxt_set_edev_info(struct bnxt_en_dev *edev, struct bnxt *bp) +{ + edev->net = bp->dev; + edev->pdev = bp->pdev; + edev->l2_db_size = bp->db_size; + edev->l2_db_size_nc = bp->db_size; - edev = bp->edev; - if (!edev) { - edev = kzalloc(sizeof(*edev), GFP_KERNEL); - if (!edev) - return ERR_PTR(-ENOMEM); - edev->en_ops = &bnxt_en_ops_tbl; - edev->net = dev; - edev->pdev = bp->pdev; - edev->l2_db_size = bp->db_size; - edev->l2_db_size_nc = bp->db_size; - bp->edev = edev; - } - edev->flags &= ~BNXT_EN_FLAG_ROCE_CAP; if (bp->flags & BNXT_FLAG_ROCEV1_CAP) edev->flags |= BNXT_EN_FLAG_ROCEV1_CAP; if (bp->flags & BNXT_FLAG_ROCEV2_CAP) edev->flags |= BNXT_EN_FLAG_ROCEV2_CAP; - return bp->edev; + if (bp->flags & BNXT_FLAG_VF) + edev->flags |= BNXT_EN_FLAG_VF; + + edev->chip_num = bp->chip_num; + edev->hw_ring_stats_size = bp->hw_ring_stats_size; + edev->pf_port_id = bp->pf.port_id; + edev->en_state = bp->state; + + edev->ulp_tbl->msix_requested = bnxt_get_ulp_msix_num(bp); +} + +void bnxt_rdma_aux_device_init(struct bnxt *bp) +{ + struct auxiliary_device *aux_dev; + struct bnxt_aux_priv *aux_priv; + struct bnxt_en_dev *edev; + struct bnxt_ulp *ulp; + int rc; + + if (!(bp->flags & BNXT_FLAG_ROCE_CAP)) + return; + + bp->aux_priv = kzalloc(sizeof(*bp->aux_priv), GFP_KERNEL); + if (!bp->aux_priv) + goto exit; + + bp->aux_priv->id = ida_alloc(&bnxt_aux_dev_ids, GFP_KERNEL); + if (bp->aux_priv->id < 0) { + netdev_warn(bp->dev, + "ida alloc failed for ROCE auxiliary device\n"); + kfree(bp->aux_priv); + goto exit; + } + + aux_priv = bp->aux_priv; + aux_dev = &aux_priv->aux_dev; + aux_dev->id = aux_priv->id; + aux_dev->name = "rdma"; + aux_dev->dev.parent = &bp->pdev->dev; + aux_dev->dev.release = bnxt_aux_dev_release; + + rc = auxiliary_device_init(aux_dev); + if (rc) { + ida_free(&bnxt_aux_dev_ids, bp->aux_priv->id); + kfree(bp->aux_priv); + goto exit; + } + + /* From this point, all cleanup will happen via the .release callback & + * any error unwinding will need to include a call to + * auxiliary_device_uninit. + */ + edev = kzalloc(sizeof(*edev), GFP_KERNEL); + if (!edev) + goto aux_dev_uninit; + + ulp = kzalloc(sizeof(*ulp), GFP_KERNEL); + if (!ulp) + goto aux_dev_uninit; + + edev->ulp_tbl = ulp; + aux_priv->edev = edev; + bp->edev = edev; + bnxt_set_edev_info(edev, bp); + + rc = auxiliary_device_add(aux_dev); + if (rc) { + netdev_warn(bp->dev, + "Failed to add auxiliary device for ROCE\n"); + goto aux_dev_uninit; + } + + return; + +aux_dev_uninit: + auxiliary_device_uninit(aux_dev); +exit: + bp->flags &= ~BNXT_FLAG_ROCE_CAP; } -EXPORT_SYMBOL(bnxt_ulp_probe); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h index 42b50abc3e91..80cbc4b6130a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h @@ -15,6 +15,8 @@ #define BNXT_MIN_ROCE_CP_RINGS 2 #define BNXT_MIN_ROCE_STAT_CTXS 1 +#define BNXT_MAX_ROCE_MSIX 9 +#define BNXT_MAX_VF_ROCE_MSIX 2 struct hwrm_async_event_cmpl; struct bnxt; @@ -26,12 +28,6 @@ struct bnxt_msix_entry { }; struct bnxt_ulp_ops { - /* async_notifier() cannot sleep (in BH context) */ - void (*ulp_async_notifier)(void *, struct hwrm_async_event_cmpl *); - void (*ulp_stop)(void *); - void (*ulp_start)(void *); - void (*ulp_sriov_config)(void *, int); - void (*ulp_shutdown)(void *); void (*ulp_irq_stop)(void *); void (*ulp_irq_restart)(void *, struct bnxt_msix_entry *); }; @@ -57,6 +53,7 @@ struct bnxt_ulp { struct bnxt_en_dev { struct net_device *net; struct pci_dev *pdev; + struct bnxt_msix_entry msix_entries[BNXT_MAX_ROCE_MSIX]; u32 flags; #define BNXT_EN_FLAG_ROCEV1_CAP 0x1 #define BNXT_EN_FLAG_ROCEV2_CAP 0x2 @@ -64,8 +61,10 @@ struct bnxt_en_dev { BNXT_EN_FLAG_ROCEV2_CAP) #define BNXT_EN_FLAG_MSIX_REQUESTED 0x4 #define BNXT_EN_FLAG_ULP_STOPPED 0x8 - const struct bnxt_en_ops *en_ops; - struct bnxt_ulp ulp_tbl[BNXT_MAX_ULP]; + #define BNXT_EN_FLAG_VF 0x10 +#define BNXT_EN_VF(edev) ((edev)->flags & BNXT_EN_FLAG_VF) + + struct bnxt_ulp *ulp_tbl; int l2_db_size; /* Doorbell BAR size in * bytes mapped by L2 * driver. @@ -74,24 +73,19 @@ struct bnxt_en_dev { * bytes mapped as non- * cacheable. */ + u16 chip_num; + u16 hw_ring_stats_size; + u16 pf_port_id; + unsigned long en_state; /* Could be checked in + * RoCE driver suspend + * mode only. Will be + * updated in resume. + */ }; -struct bnxt_en_ops { - int (*bnxt_register_device)(struct bnxt_en_dev *, unsigned int, - struct bnxt_ulp_ops *, void *); - int (*bnxt_unregister_device)(struct bnxt_en_dev *, unsigned int); - int (*bnxt_request_msix)(struct bnxt_en_dev *, unsigned int, - struct bnxt_msix_entry *, int); - int (*bnxt_free_msix)(struct bnxt_en_dev *, unsigned int); - int (*bnxt_send_fw_msg)(struct bnxt_en_dev *, unsigned int, - struct bnxt_fw_msg *); - int (*bnxt_register_fw_async_events)(struct bnxt_en_dev *, unsigned int, - unsigned long *, u16); -}; - -static inline bool bnxt_ulp_registered(struct bnxt_en_dev *edev, int ulp_id) +static inline bool bnxt_ulp_registered(struct bnxt_en_dev *edev) { - if (edev && rcu_access_pointer(edev->ulp_tbl[ulp_id].ulp_ops)) + if (edev && edev->ulp_tbl) return true; return false; } @@ -102,10 +96,15 @@ int bnxt_get_ulp_stat_ctxs(struct bnxt *bp); void bnxt_ulp_stop(struct bnxt *bp); void bnxt_ulp_start(struct bnxt *bp, int err); void bnxt_ulp_sriov_cfg(struct bnxt *bp, int num_vfs); -void bnxt_ulp_shutdown(struct bnxt *bp); void bnxt_ulp_irq_stop(struct bnxt *bp); void bnxt_ulp_irq_restart(struct bnxt *bp, int err); void bnxt_ulp_async_events(struct bnxt *bp, struct hwrm_async_event_cmpl *cmpl); -struct bnxt_en_dev *bnxt_ulp_probe(struct net_device *dev); - +void bnxt_rdma_aux_device_uninit(struct bnxt *bp); +void bnxt_rdma_aux_device_init(struct bnxt *bp); +int bnxt_register_dev(struct bnxt_en_dev *edev, struct bnxt_ulp_ops *ulp_ops, + void *handle); +void bnxt_unregister_dev(struct bnxt_en_dev *edev); +int bnxt_send_msg(struct bnxt_en_dev *edev, struct bnxt_fw_msg *fw_msg); +int bnxt_register_async_events(struct bnxt_en_dev *edev, + unsigned long *events_bmap, u16 max_id); #endif diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 21973046b12b..d937daa8ee88 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -2316,6 +2316,14 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring, __func__, p_index, ring->c_index, ring->read_ptr, dma_length_status); + if (unlikely(len > RX_BUF_LENGTH)) { + netif_err(priv, rx_status, dev, "oversized packet\n"); + dev->stats.rx_length_errors++; + dev->stats.rx_errors++; + dev_kfree_skb_any(skb); + goto next; + } + if (unlikely(!(dma_flag & DMA_EOP) || !(dma_flag & DMA_SOP))) { netif_err(priv, rx_status, dev, "dropping fragmented packet!\n"); diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 41964fd02452..6e141a8bbf43 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -4684,25 +4684,26 @@ static int init_reset_optional(struct platform_device *pdev) if (ret) return dev_err_probe(&pdev->dev, ret, "failed to init SGMII PHY\n"); - } - ret = zynqmp_pm_is_function_supported(PM_IOCTL, IOCTL_SET_GEM_CONFIG); - if (!ret) { - u32 pm_info[2]; + ret = zynqmp_pm_is_function_supported(PM_IOCTL, IOCTL_SET_GEM_CONFIG); + if (!ret) { + u32 pm_info[2]; + + ret = of_property_read_u32_array(pdev->dev.of_node, "power-domains", + pm_info, ARRAY_SIZE(pm_info)); + if (ret) { + dev_err(&pdev->dev, "Failed to read power management information\n"); + goto err_out_phy_exit; + } + ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_FIXED, 0); + if (ret) + goto err_out_phy_exit; - ret = of_property_read_u32_array(pdev->dev.of_node, "power-domains", - pm_info, ARRAY_SIZE(pm_info)); - if (ret) { - dev_err(&pdev->dev, "Failed to read power management information\n"); - goto err_out_phy_exit; + ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_SGMII_MODE, 1); + if (ret) + goto err_out_phy_exit; } - ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_FIXED, 0); - if (ret) - goto err_out_phy_exit; - ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_SGMII_MODE, 1); - if (ret) - goto err_out_phy_exit; } /* Fully reset controller at hardware level if mapped in device tree */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h index be96f1dc0372..d4a862a9fd7d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h @@ -4,7 +4,7 @@ #ifndef __CXGB4_TC_MQPRIO_H__ #define __CXGB4_TC_MQPRIO_H__ -#include <net/pkt_cls.h> +#include <net/pkt_sched.h> #define CXGB4_EOSW_TXQ_DEFAULT_DESC_NUM 128 diff --git a/drivers/net/ethernet/engleder/tsnep_tc.c b/drivers/net/ethernet/engleder/tsnep_tc.c index c4c6e1357317..d083e6684f12 100644 --- a/drivers/net/ethernet/engleder/tsnep_tc.c +++ b/drivers/net/ethernet/engleder/tsnep_tc.c @@ -403,12 +403,33 @@ static int tsnep_taprio(struct tsnep_adapter *adapter, return 0; } +static int tsnep_tc_query_caps(struct tsnep_adapter *adapter, + struct tc_query_caps_base *base) +{ + switch (base->type) { + case TC_SETUP_QDISC_TAPRIO: { + struct tc_taprio_caps *caps = base->caps; + + if (!adapter->gate_control) + return -EOPNOTSUPP; + + caps->gate_mask_per_txq = true; + + return 0; + } + default: + return -EOPNOTSUPP; + } +} + int tsnep_tc_setup(struct net_device *netdev, enum tc_setup_type type, void *type_data) { struct tsnep_adapter *adapter = netdev_priv(netdev); switch (type) { + case TC_QUERY_CAPS: + return tsnep_tc_query_caps(adapter, type_data); case TC_SETUP_QDISC_TAPRIO: return tsnep_taprio(adapter, type_data); default: diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 159ae740ba3c..2fc712b24d12 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -28,11 +28,9 @@ EXPORT_SYMBOL_GPL(enetc_port_mac_wr); static int enetc_num_stack_tx_queues(struct enetc_ndev_priv *priv) { int num_tx_rings = priv->num_tx_rings; - int i; - for (i = 0; i < priv->num_rx_rings; i++) - if (priv->rx_ring[i]->xdp.prog) - return num_tx_rings - num_possible_cpus(); + if (priv->xdp_prog) + return num_tx_rings - num_possible_cpus(); return num_tx_rings; } @@ -2456,7 +2454,6 @@ int enetc_open(struct net_device *ndev) { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_bdr_resource *tx_res, *rx_res; - int num_stack_tx_queues; bool extended; int err; @@ -2482,16 +2479,6 @@ int enetc_open(struct net_device *ndev) goto err_alloc_rx; } - num_stack_tx_queues = enetc_num_stack_tx_queues(priv); - - err = netif_set_real_num_tx_queues(ndev, num_stack_tx_queues); - if (err) - goto err_set_queues; - - err = netif_set_real_num_rx_queues(ndev, priv->num_rx_rings); - if (err) - goto err_set_queues; - enetc_tx_onestep_tstamp_init(priv); enetc_assign_tx_resources(priv, tx_res); enetc_assign_rx_resources(priv, rx_res); @@ -2500,8 +2487,6 @@ int enetc_open(struct net_device *ndev) return 0; -err_set_queues: - enetc_free_rx_resources(rx_res, priv->num_rx_rings); err_alloc_rx: enetc_free_tx_resources(tx_res, priv->num_tx_rings); err_alloc_tx: @@ -2576,8 +2561,11 @@ static int enetc_reconfigure(struct enetc_ndev_priv *priv, bool extended, * without reconfiguration. */ if (!netif_running(priv->ndev)) { - if (cb) - cb(priv, ctx); + if (cb) { + err = cb(priv, ctx); + if (err) + return err; + } return 0; } @@ -2598,8 +2586,11 @@ static int enetc_reconfigure(struct enetc_ndev_priv *priv, bool extended, enetc_free_rxtx_rings(priv); /* Interface is down, run optional callback now */ - if (cb) - cb(priv, ctx); + if (cb) { + err = cb(priv, ctx); + if (err) + goto out_restart; + } enetc_assign_tx_resources(priv, tx_res); enetc_assign_rx_resources(priv, rx_res); @@ -2608,76 +2599,123 @@ static int enetc_reconfigure(struct enetc_ndev_priv *priv, bool extended, return 0; +out_restart: + enetc_setup_bdrs(priv, extended); + enetc_start(priv->ndev); + enetc_free_rx_resources(rx_res, priv->num_rx_rings); out_free_tx_res: enetc_free_tx_resources(tx_res, priv->num_tx_rings); out: return err; } -int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) +static void enetc_debug_tx_ring_prios(struct enetc_ndev_priv *priv) +{ + int i; + + for (i = 0; i < priv->num_tx_rings; i++) + netdev_dbg(priv->ndev, "TX ring %d prio %d\n", i, + priv->tx_ring[i]->prio); +} + +static void enetc_reset_tc_mqprio(struct net_device *ndev) { struct enetc_ndev_priv *priv = netdev_priv(ndev); - struct tc_mqprio_qopt *mqprio = type_data; struct enetc_hw *hw = &priv->si->hw; struct enetc_bdr *tx_ring; int num_stack_tx_queues; - u8 num_tc; int i; num_stack_tx_queues = enetc_num_stack_tx_queues(priv); - mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; - num_tc = mqprio->num_tc; - if (!num_tc) { - netdev_reset_tc(ndev); - netif_set_real_num_tx_queues(ndev, num_stack_tx_queues); + netdev_reset_tc(ndev); + netif_set_real_num_tx_queues(ndev, num_stack_tx_queues); + priv->min_num_stack_tx_queues = num_possible_cpus(); - /* Reset all ring priorities to 0 */ - for (i = 0; i < priv->num_tx_rings; i++) { - tx_ring = priv->tx_ring[i]; - tx_ring->prio = 0; - enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); - } + /* Reset all ring priorities to 0 */ + for (i = 0; i < priv->num_tx_rings; i++) { + tx_ring = priv->tx_ring[i]; + tx_ring->prio = 0; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); + } + + enetc_debug_tx_ring_prios(priv); +} + +int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) +{ + struct enetc_ndev_priv *priv = netdev_priv(ndev); + struct tc_mqprio_qopt *mqprio = type_data; + struct enetc_hw *hw = &priv->si->hw; + int num_stack_tx_queues = 0; + u8 num_tc = mqprio->num_tc; + struct enetc_bdr *tx_ring; + int offset, count; + int err, tc, q; + if (!num_tc) { + enetc_reset_tc_mqprio(ndev); return 0; } - /* Check if we have enough BD rings available to accommodate all TCs */ - if (num_tc > num_stack_tx_queues) { - netdev_err(ndev, "Max %d traffic classes supported\n", - priv->num_tx_rings); - return -EINVAL; - } + err = netdev_set_num_tc(ndev, num_tc); + if (err) + return err; - /* For the moment, we use only one BD ring per TC. - * - * Configure num_tc BD rings with increasing priorities. - */ - for (i = 0; i < num_tc; i++) { - tx_ring = priv->tx_ring[i]; - tx_ring->prio = i; - enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); + for (tc = 0; tc < num_tc; tc++) { + offset = mqprio->offset[tc]; + count = mqprio->count[tc]; + num_stack_tx_queues += count; + + err = netdev_set_tc_queue(ndev, tc, count, offset); + if (err) + goto err_reset_tc; + + for (q = offset; q < offset + count; q++) { + tx_ring = priv->tx_ring[q]; + /* The prio_tc_map is skb_tx_hash()'s way of selecting + * between TX queues based on skb->priority. As such, + * there's nothing to offload based on it. + * Make the mqprio "traffic class" be the priority of + * this ring group, and leave the Tx IPV to traffic + * class mapping as its default mapping value of 1:1. + */ + tx_ring->prio = tc; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); + } } - /* Reset the number of netdev queues based on the TC count */ - netif_set_real_num_tx_queues(ndev, num_tc); + err = netif_set_real_num_tx_queues(ndev, num_stack_tx_queues); + if (err) + goto err_reset_tc; - netdev_set_num_tc(ndev, num_tc); + priv->min_num_stack_tx_queues = num_stack_tx_queues; - /* Each TC is associated with one netdev queue */ - for (i = 0; i < num_tc; i++) - netdev_set_tc_queue(ndev, i, 1, i); + enetc_debug_tx_ring_prios(priv); return 0; + +err_reset_tc: + enetc_reset_tc_mqprio(ndev); + return err; } EXPORT_SYMBOL_GPL(enetc_setup_tc_mqprio); static int enetc_reconfigure_xdp_cb(struct enetc_ndev_priv *priv, void *ctx) { struct bpf_prog *old_prog, *prog = ctx; - int i; + int num_stack_tx_queues; + int err, i; old_prog = xchg(&priv->xdp_prog, prog); + + num_stack_tx_queues = enetc_num_stack_tx_queues(priv); + err = netif_set_real_num_tx_queues(priv->ndev, num_stack_tx_queues); + if (err) { + xchg(&priv->xdp_prog, old_prog); + return err; + } + if (old_prog) bpf_prog_put(old_prog); @@ -2698,9 +2736,20 @@ static int enetc_reconfigure_xdp_cb(struct enetc_ndev_priv *priv, void *ctx) static int enetc_setup_xdp_prog(struct net_device *ndev, struct bpf_prog *prog, struct netlink_ext_ack *extack) { + int num_xdp_tx_queues = prog ? num_possible_cpus() : 0; struct enetc_ndev_priv *priv = netdev_priv(ndev); bool extended; + if (priv->min_num_stack_tx_queues + num_xdp_tx_queues > + priv->num_tx_rings) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "Reserving %d XDP TXQs does not leave a minimum of %d TXQs for network stack (total %d available)", + num_xdp_tx_queues, + priv->min_num_stack_tx_queues, + priv->num_tx_rings); + return -EBUSY; + } + extended = !!(priv->active_offloads & ENETC_F_RX_TSTAMP); /* The buffer layout is changing, so we need to drain the old @@ -2898,6 +2947,7 @@ EXPORT_SYMBOL_GPL(enetc_ioctl); int enetc_alloc_msix(struct enetc_ndev_priv *priv) { struct pci_dev *pdev = priv->si->pdev; + int num_stack_tx_queues; int first_xdp_tx_ring; int i, n, err, nvec; int v_tx_rings; @@ -2974,6 +3024,17 @@ int enetc_alloc_msix(struct enetc_ndev_priv *priv) } } + num_stack_tx_queues = enetc_num_stack_tx_queues(priv); + + err = netif_set_real_num_tx_queues(priv->ndev, num_stack_tx_queues); + if (err) + goto fail; + + err = netif_set_real_num_rx_queues(priv->ndev, priv->num_rx_rings); + if (err) + goto fail; + + priv->min_num_stack_tx_queues = num_possible_cpus(); first_xdp_tx_ring = priv->num_tx_rings - num_possible_cpus(); priv->xdp_tx_ring = &priv->tx_ring[first_xdp_tx_ring]; diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index 1fe8dfd6b6d4..8010f31cd10d 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -314,7 +314,6 @@ struct psfp_cap { }; #define ENETC_F_TX_TSTAMP_MASK 0xff -/* TODO: more hardware offloads */ enum enetc_active_offloads { /* 8 bits reserved for TX timestamp types (hwtstamp_tx_types) */ ENETC_F_TX_TSTAMP = BIT(0), @@ -323,6 +322,7 @@ enum enetc_active_offloads { ENETC_F_RX_TSTAMP = BIT(8), ENETC_F_QBV = BIT(9), ENETC_F_QCI = BIT(10), + ENETC_F_QBU = BIT(11), }; enum enetc_flags_bit { @@ -369,6 +369,9 @@ struct enetc_ndev_priv { struct psfp_cap psfp_cap; + /* Minimum number of TX queues required by the network stack */ + unsigned int min_num_stack_tx_queues; + struct phylink *phylink; int ic_mode; u32 tx_ictt; @@ -379,6 +382,11 @@ struct enetc_ndev_priv { struct work_struct tx_onestep_tstamp; struct sk_buff_head tx_skbs; + + /* Serialize access to MAC Merge state between ethtool requests + * and link state updates + */ + struct mutex mm_lock; }; /* Messaging */ @@ -424,6 +432,7 @@ int enetc_xdp_xmit(struct net_device *ndev, int num_frames, /* ethtool */ void enetc_set_ethtool_ops(struct net_device *ndev); +void enetc_mm_link_state_update(struct enetc_ndev_priv *priv, bool link); /* control buffer descriptor ring (CBDR) */ int enetc_setup_cbdr(struct device *dev, struct enetc_hw *hw, int bd_count, diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c index 05e2bad609c6..bca68edfbe9c 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) /* Copyright 2017-2019 NXP */ +#include <linux/ethtool_netlink.h> #include <linux/net_tstamp.h> #include <linux/module.h> #include "enetc.h" @@ -299,14 +300,32 @@ static void enetc_get_ethtool_stats(struct net_device *ndev, data[o++] = enetc_port_rd(hw, enetc_port_counters[i].reg); } +static void enetc_pause_stats(struct enetc_hw *hw, int mac, + struct ethtool_pause_stats *pause_stats) +{ + pause_stats->tx_pause_frames = enetc_port_rd(hw, ENETC_PM_TXPF(mac)); + pause_stats->rx_pause_frames = enetc_port_rd(hw, ENETC_PM_RXPF(mac)); +} + static void enetc_get_pause_stats(struct net_device *ndev, struct ethtool_pause_stats *pause_stats) { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_hw *hw = &priv->si->hw; + struct enetc_si *si = priv->si; - pause_stats->tx_pause_frames = enetc_port_rd(hw, ENETC_PM_TXPF(0)); - pause_stats->rx_pause_frames = enetc_port_rd(hw, ENETC_PM_RXPF(0)); + switch (pause_stats->src) { + case ETHTOOL_MAC_STATS_SRC_EMAC: + enetc_pause_stats(hw, 0, pause_stats); + break; + case ETHTOOL_MAC_STATS_SRC_PMAC: + if (si->hw_features & ENETC_SI_F_QBU) + enetc_pause_stats(hw, 1, pause_stats); + break; + case ETHTOOL_MAC_STATS_SRC_AGGREGATE: + ethtool_aggregate_pause_stats(ndev, pause_stats); + break; + } } static void enetc_mac_stats(struct enetc_hw *hw, int mac, @@ -383,8 +402,20 @@ static void enetc_get_eth_mac_stats(struct net_device *ndev, { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_hw *hw = &priv->si->hw; + struct enetc_si *si = priv->si; - enetc_mac_stats(hw, 0, mac_stats); + switch (mac_stats->src) { + case ETHTOOL_MAC_STATS_SRC_EMAC: + enetc_mac_stats(hw, 0, mac_stats); + break; + case ETHTOOL_MAC_STATS_SRC_PMAC: + if (si->hw_features & ENETC_SI_F_QBU) + enetc_mac_stats(hw, 1, mac_stats); + break; + case ETHTOOL_MAC_STATS_SRC_AGGREGATE: + ethtool_aggregate_mac_stats(ndev, mac_stats); + break; + } } static void enetc_get_eth_ctrl_stats(struct net_device *ndev, @@ -392,8 +423,20 @@ static void enetc_get_eth_ctrl_stats(struct net_device *ndev, { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_hw *hw = &priv->si->hw; + struct enetc_si *si = priv->si; - enetc_ctrl_stats(hw, 0, ctrl_stats); + switch (ctrl_stats->src) { + case ETHTOOL_MAC_STATS_SRC_EMAC: + enetc_ctrl_stats(hw, 0, ctrl_stats); + break; + case ETHTOOL_MAC_STATS_SRC_PMAC: + if (si->hw_features & ENETC_SI_F_QBU) + enetc_ctrl_stats(hw, 1, ctrl_stats); + break; + case ETHTOOL_MAC_STATS_SRC_AGGREGATE: + ethtool_aggregate_ctrl_stats(ndev, ctrl_stats); + break; + } } static void enetc_get_rmon_stats(struct net_device *ndev, @@ -402,8 +445,20 @@ static void enetc_get_rmon_stats(struct net_device *ndev, { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_hw *hw = &priv->si->hw; + struct enetc_si *si = priv->si; - enetc_rmon_stats(hw, 0, rmon_stats, ranges); + switch (rmon_stats->src) { + case ETHTOOL_MAC_STATS_SRC_EMAC: + enetc_rmon_stats(hw, 0, rmon_stats, ranges); + break; + case ETHTOOL_MAC_STATS_SRC_PMAC: + if (si->hw_features & ENETC_SI_F_QBU) + enetc_rmon_stats(hw, 1, rmon_stats, ranges); + break; + case ETHTOOL_MAC_STATS_SRC_AGGREGATE: + ethtool_aggregate_rmon_stats(ndev, rmon_stats); + break; + } } #define ENETC_RSSHASH_L3 (RXH_L2DA | RXH_VLAN | RXH_L3_PROTO | RXH_IP_SRC | \ @@ -863,6 +918,166 @@ static int enetc_set_link_ksettings(struct net_device *dev, return phylink_ethtool_ksettings_set(priv->phylink, cmd); } +static void enetc_get_mm_stats(struct net_device *ndev, + struct ethtool_mm_stats *s) +{ + struct enetc_ndev_priv *priv = netdev_priv(ndev); + struct enetc_hw *hw = &priv->si->hw; + struct enetc_si *si = priv->si; + + if (!(si->hw_features & ENETC_SI_F_QBU)) + return; + + s->MACMergeFrameAssErrorCount = enetc_port_rd(hw, ENETC_MMFAECR); + s->MACMergeFrameSmdErrorCount = enetc_port_rd(hw, ENETC_MMFSECR); + s->MACMergeFrameAssOkCount = enetc_port_rd(hw, ENETC_MMFAOCR); + s->MACMergeFragCountRx = enetc_port_rd(hw, ENETC_MMFCRXR); + s->MACMergeFragCountTx = enetc_port_rd(hw, ENETC_MMFCTXR); + s->MACMergeHoldCount = enetc_port_rd(hw, ENETC_MMHCR); +} + +static int enetc_get_mm(struct net_device *ndev, struct ethtool_mm_state *state) +{ + struct enetc_ndev_priv *priv = netdev_priv(ndev); + struct enetc_si *si = priv->si; + struct enetc_hw *hw = &si->hw; + u32 lafs, rafs, val; + + if (!(si->hw_features & ENETC_SI_F_QBU)) + return -EOPNOTSUPP; + + mutex_lock(&priv->mm_lock); + + val = enetc_port_rd(hw, ENETC_PFPMR); + state->pmac_enabled = !!(val & ENETC_PFPMR_PMACE); + + val = enetc_port_rd(hw, ENETC_MMCSR); + + switch (ENETC_MMCSR_GET_VSTS(val)) { + case 0: + state->verify_status = ETHTOOL_MM_VERIFY_STATUS_DISABLED; + break; + case 2: + state->verify_status = ETHTOOL_MM_VERIFY_STATUS_VERIFYING; + break; + case 3: + state->verify_status = ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED; + break; + case 4: + state->verify_status = ETHTOOL_MM_VERIFY_STATUS_FAILED; + break; + case 5: + default: + state->verify_status = ETHTOOL_MM_VERIFY_STATUS_UNKNOWN; + break; + } + + rafs = ENETC_MMCSR_GET_RAFS(val); + state->tx_min_frag_size = ethtool_mm_frag_size_add_to_min(rafs); + lafs = ENETC_MMCSR_GET_LAFS(val); + state->rx_min_frag_size = ethtool_mm_frag_size_add_to_min(lafs); + state->tx_enabled = !!(val & ENETC_MMCSR_LPE); /* mirror of MMCSR_ME */ + state->tx_active = !!(val & ENETC_MMCSR_LPA); + state->verify_enabled = !(val & ENETC_MMCSR_VDIS); + state->verify_time = ENETC_MMCSR_GET_VT(val); + /* A verifyTime of 128 ms would exceed the 7 bit width + * of the ENETC_MMCSR_VT field + */ + state->max_verify_time = 127; + + mutex_unlock(&priv->mm_lock); + + return 0; +} + +static int enetc_set_mm(struct net_device *ndev, struct ethtool_mm_cfg *cfg, + struct netlink_ext_ack *extack) +{ + struct enetc_ndev_priv *priv = netdev_priv(ndev); + struct enetc_hw *hw = &priv->si->hw; + struct enetc_si *si = priv->si; + u32 val, add_frag_size; + int err; + + if (!(si->hw_features & ENETC_SI_F_QBU)) + return -EOPNOTSUPP; + + err = ethtool_mm_frag_size_min_to_add(cfg->tx_min_frag_size, + &add_frag_size, extack); + if (err) + return err; + + mutex_lock(&priv->mm_lock); + + val = enetc_port_rd(hw, ENETC_PFPMR); + if (cfg->pmac_enabled) + val |= ENETC_PFPMR_PMACE; + else + val &= ~ENETC_PFPMR_PMACE; + enetc_port_wr(hw, ENETC_PFPMR, val); + + val = enetc_port_rd(hw, ENETC_MMCSR); + + if (cfg->verify_enabled) + val &= ~ENETC_MMCSR_VDIS; + else + val |= ENETC_MMCSR_VDIS; + + if (cfg->tx_enabled) + priv->active_offloads |= ENETC_F_QBU; + else + priv->active_offloads &= ~ENETC_F_QBU; + + /* If link is up, enable MAC Merge right away */ + if (!!(priv->active_offloads & ENETC_F_QBU) && + !(val & ENETC_MMCSR_LINK_FAIL)) + val |= ENETC_MMCSR_ME; + + val &= ~ENETC_MMCSR_VT_MASK; + val |= ENETC_MMCSR_VT(cfg->verify_time); + + val &= ~ENETC_MMCSR_RAFS_MASK; + val |= ENETC_MMCSR_RAFS(add_frag_size); + + enetc_port_wr(hw, ENETC_MMCSR, val); + + mutex_unlock(&priv->mm_lock); + + return 0; +} + +/* When the link is lost, the verification state machine goes to the FAILED + * state and doesn't restart on its own after a new link up event. + * According to 802.3 Figure 99-8 - Verify state diagram, the LINK_FAIL bit + * should have been sufficient to re-trigger verification, but for ENETC it + * doesn't. As a workaround, we need to toggle the Merge Enable bit to + * re-trigger verification when link comes up. + */ +void enetc_mm_link_state_update(struct enetc_ndev_priv *priv, bool link) +{ + struct enetc_hw *hw = &priv->si->hw; + u32 val; + + mutex_lock(&priv->mm_lock); + + val = enetc_port_rd(hw, ENETC_MMCSR); + + if (link) { + val &= ~ENETC_MMCSR_LINK_FAIL; + if (priv->active_offloads & ENETC_F_QBU) + val |= ENETC_MMCSR_ME; + } else { + val |= ENETC_MMCSR_LINK_FAIL; + if (priv->active_offloads & ENETC_F_QBU) + val &= ~ENETC_MMCSR_ME; + } + + enetc_port_wr(hw, ENETC_MMCSR, val); + + mutex_unlock(&priv->mm_lock); +} +EXPORT_SYMBOL_GPL(enetc_mm_link_state_update); + static const struct ethtool_ops enetc_pf_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES | @@ -893,6 +1108,9 @@ static const struct ethtool_ops enetc_pf_ethtool_ops = { .set_wol = enetc_set_wol, .get_pauseparam = enetc_get_pauseparam, .set_pauseparam = enetc_set_pauseparam, + .get_mm = enetc_get_mm, + .set_mm = enetc_set_mm, + .get_mm_stats = enetc_get_mm_stats, }; static const struct ethtool_ops enetc_vf_ethtool_ops = { diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 041df7d0ae81..de2e0ee8cdcb 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -222,7 +222,30 @@ enum enetc_bdr_type {TX, RX}; #define ENETC_PSIVHFR0(n) (0x1e00 + (n) * 8) /* n = SI index */ #define ENETC_PSIVHFR1(n) (0x1e04 + (n) * 8) /* n = SI index */ #define ENETC_MMCSR 0x1f00 -#define ENETC_MMCSR_ME BIT(16) +#define ENETC_MMCSR_LINK_FAIL BIT(31) +#define ENETC_MMCSR_VT_MASK GENMASK(29, 23) /* Verify Time */ +#define ENETC_MMCSR_VT(x) (((x) << 23) & ENETC_MMCSR_VT_MASK) +#define ENETC_MMCSR_GET_VT(x) (((x) & ENETC_MMCSR_VT_MASK) >> 23) +#define ENETC_MMCSR_TXSTS_MASK GENMASK(22, 21) /* Merge Status */ +#define ENETC_MMCSR_GET_TXSTS(x) (((x) & ENETC_MMCSR_TXSTS_MASK) >> 21) +#define ENETC_MMCSR_VSTS_MASK GENMASK(20, 18) /* Verify Status */ +#define ENETC_MMCSR_GET_VSTS(x) (((x) & ENETC_MMCSR_VSTS_MASK) >> 18) +#define ENETC_MMCSR_VDIS BIT(17) /* Verify Disabled */ +#define ENETC_MMCSR_ME BIT(16) /* Merge Enabled */ +#define ENETC_MMCSR_RAFS_MASK GENMASK(9, 8) /* Remote Additional Fragment Size */ +#define ENETC_MMCSR_RAFS(x) (((x) << 8) & ENETC_MMCSR_RAFS_MASK) +#define ENETC_MMCSR_GET_RAFS(x) (((x) & ENETC_MMCSR_RAFS_MASK) >> 8) +#define ENETC_MMCSR_LAFS_MASK GENMASK(4, 3) /* Local Additional Fragment Size */ +#define ENETC_MMCSR_GET_LAFS(x) (((x) & ENETC_MMCSR_LAFS_MASK) >> 3) +#define ENETC_MMCSR_LPA BIT(2) /* Local Preemption Active */ +#define ENETC_MMCSR_LPE BIT(1) /* Local Preemption Enabled */ +#define ENETC_MMCSR_LPS BIT(0) /* Local Preemption Supported */ +#define ENETC_MMFAECR 0x1f08 +#define ENETC_MMFSECR 0x1f0c +#define ENETC_MMFAOCR 0x1f10 +#define ENETC_MMFCRXR 0x1f14 +#define ENETC_MMFCTXR 0x1f18 +#define ENETC_MMHCR 0x1f1c #define ENETC_PTCMSDUR(n) (0x2020 + (n) * 4) /* n = TC index [0..7] */ #define ENETC_PMAC_OFFSET 0x1000 diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 6b54071d4ecc..7cd22d370caa 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -1086,6 +1086,9 @@ static void enetc_pl_mac_link_up(struct phylink_config *config, enetc_port_mac_wr(si, ENETC_PM0_CMD_CFG, cmd_cfg); enetc_mac_enable(si, true); + + if (si->hw_features & ENETC_SI_F_QBU) + enetc_mm_link_state_update(priv, true); } static void enetc_pl_mac_link_down(struct phylink_config *config, @@ -1093,8 +1096,15 @@ static void enetc_pl_mac_link_down(struct phylink_config *config, phy_interface_t interface) { struct enetc_pf *pf = phylink_to_enetc_pf(config); + struct enetc_si *si = pf->si; + struct enetc_ndev_priv *priv; - enetc_mac_enable(pf->si, false); + priv = netdev_priv(si->ndev); + + if (si->hw_features & ENETC_SI_F_QBU) + enetc_mm_link_state_update(priv, false); + + enetc_mac_enable(si, false); } static const struct phylink_mac_ops enetc_mac_phylink_ops = { @@ -1287,6 +1297,8 @@ static int enetc_pf_probe(struct pci_dev *pdev, priv = netdev_priv(ndev); + mutex_init(&priv->mm_lock); + enetc_init_si_rings_params(priv); err = enetc_alloc_si_resources(priv); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index fcebb54224c0..130ebf6853e6 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -136,29 +136,21 @@ int enetc_setup_tc_taprio(struct net_device *ndev, void *type_data) { struct tc_taprio_qopt_offload *taprio = type_data; struct enetc_ndev_priv *priv = netdev_priv(ndev); - struct enetc_hw *hw = &priv->si->hw; - struct enetc_bdr *tx_ring; - int err; - int i; + int err, i; /* TSD and Qbv are mutually exclusive in hardware */ for (i = 0; i < priv->num_tx_rings; i++) if (priv->tx_ring[i]->tsd_enable) return -EBUSY; - for (i = 0; i < priv->num_tx_rings; i++) { - tx_ring = priv->tx_ring[i]; - tx_ring->prio = taprio->enable ? i : 0; - enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); - } + err = enetc_setup_tc_mqprio(ndev, &taprio->mqprio); + if (err) + return err; err = enetc_setup_taprio(ndev, taprio); if (err) { - for (i = 0; i < priv->num_tx_rings; i++) { - tx_ring = priv->tx_ring[i]; - tx_ring->prio = taprio->enable ? 0 : i; - enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); - } + taprio->mqprio.qopt.num_tc = 0; + enetc_setup_tc_mqprio(ndev, &taprio->mqprio); } return err; @@ -1611,6 +1603,13 @@ int enetc_qos_query_caps(struct net_device *ndev, void *type_data) struct enetc_si *si = priv->si; switch (base->type) { + case TC_SETUP_QDISC_MQPRIO: { + struct tc_mqprio_caps *caps = base->caps; + + caps->validate_queue_counts = true; + + return 0; + } case TC_SETUP_QDISC_TAPRIO: { struct tc_taprio_caps *caps = base->caps; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 5ff45b1a74a5..c73e25f8995e 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -56,12 +56,12 @@ #include <linux/fec.h> #include <linux/of.h> #include <linux/of_device.h> -#include <linux/of_gpio.h> #include <linux/of_mdio.h> #include <linux/of_net.h> #include <linux/regulator/consumer.h> #include <linux/if_vlan.h> #include <linux/pinctrl/consumer.h> +#include <linux/gpio/consumer.h> #include <linux/prefetch.h> #include <linux/mfd/syscon.h> #include <linux/regmap.h> @@ -4035,10 +4035,10 @@ free_queue_mem: #ifdef CONFIG_OF static int fec_reset_phy(struct platform_device *pdev) { - int err, phy_reset; - bool active_high = false; + struct gpio_desc *phy_reset; int msec = 1, phy_post_delay = 0; struct device_node *np = pdev->dev.of_node; + int err; if (!np) return 0; @@ -4048,33 +4048,26 @@ static int fec_reset_phy(struct platform_device *pdev) if (!err && msec > 1000) msec = 1; - phy_reset = of_get_named_gpio(np, "phy-reset-gpios", 0); - if (phy_reset == -EPROBE_DEFER) - return phy_reset; - else if (!gpio_is_valid(phy_reset)) - return 0; - err = of_property_read_u32(np, "phy-reset-post-delay", &phy_post_delay); /* valid reset duration should be less than 1s */ if (!err && phy_post_delay > 1000) return -EINVAL; - active_high = of_property_read_bool(np, "phy-reset-active-high"); + phy_reset = devm_gpiod_get_optional(&pdev->dev, "phy-reset", + GPIOD_OUT_HIGH); + if (IS_ERR(phy_reset)) + return dev_err_probe(&pdev->dev, PTR_ERR(phy_reset), + "failed to get phy-reset-gpios\n"); - err = devm_gpio_request_one(&pdev->dev, phy_reset, - active_high ? GPIOF_OUT_INIT_HIGH : GPIOF_OUT_INIT_LOW, - "phy-reset"); - if (err) { - dev_err(&pdev->dev, "failed to get phy-reset-gpios: %d\n", err); - return err; - } + if (!phy_reset) + return 0; if (msec > 20) msleep(msec); else usleep_range(msec * 1000, msec * 1000 + 1000); - gpio_set_value_cansleep(phy_reset, !active_high); + gpiod_set_value_cansleep(phy_reset, 0); if (!phy_post_delay) return 0; diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index 9349f841bd06..587ad81a2dc3 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -1055,6 +1055,9 @@ static struct phylink_pcs *memac_pcs_create(struct device_node *mac_node, return ERR_PTR(-EPROBE_DEFER); pcs = lynx_pcs_create(mdiodev); + if (!pcs) + mdio_device_free(mdiodev); + return pcs; } diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 5b40f9c53196..07111c241e0e 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -327,7 +327,6 @@ static int gve_napi_poll_dqo(struct napi_struct *napi, int budget) static int gve_alloc_notify_blocks(struct gve_priv *priv) { int num_vecs_requested = priv->num_ntfy_blks + 1; - char *name = priv->dev->name; unsigned int active_cpus; int vecs_enabled; int i, j; @@ -371,8 +370,8 @@ static int gve_alloc_notify_blocks(struct gve_priv *priv) active_cpus = min_t(int, priv->num_ntfy_blks / 2, num_online_cpus()); /* Setup Management Vector - the last vector */ - snprintf(priv->mgmt_msix_name, sizeof(priv->mgmt_msix_name), "%s-mgmnt", - name); + snprintf(priv->mgmt_msix_name, sizeof(priv->mgmt_msix_name), "gve-mgmnt@pci:%s", + pci_name(priv->pdev)); err = request_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector, gve_mgmnt_intr, 0, priv->mgmt_msix_name, priv); if (err) { @@ -401,8 +400,8 @@ static int gve_alloc_notify_blocks(struct gve_priv *priv) struct gve_notify_block *block = &priv->ntfy_blocks[i]; int msix_idx = i; - snprintf(block->name, sizeof(block->name), "%s-ntfy-block.%d", - name, i); + snprintf(block->name, sizeof(block->name), "gve-ntfy-blk%d@pci:%s", + i, pci_name(priv->pdev)); block->priv = priv; err = request_irq(priv->msix_vectors[msix_idx].vector, gve_is_gqi(priv) ? gve_intr : gve_intr_dqo, diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 17137de9338c..40f4306449eb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -32,6 +32,7 @@ #include <linux/pkt_sched.h> #include <linux/types.h> #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #define HNAE3_MOD_VERSION "1.0" diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index b4c4fb873568..25be7f8ac7cd 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -20,6 +20,7 @@ #include <net/gro.h> #include <net/ip6_checksum.h> #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include <net/tcp.h> #include <net/vxlan.h> #include <net/geneve.h> diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c index 3d3b69605423..9a939c0b217f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c @@ -114,7 +114,6 @@ int hclge_devlink_init(struct hclge_dev *hdev) priv->hdev = hdev; hdev->devlink = devlink; - devlink_set_features(devlink, DEVLINK_F_RELOAD); devlink_register(devlink); return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c index a6c3c5e8f0ab..1b535142c65a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c @@ -116,7 +116,6 @@ int hclgevf_devlink_init(struct hclgevf_dev *hdev) priv->hdev = hdev; hdev->devlink = devlink; - devlink_set_features(devlink, DEVLINK_F_RELOAD); devlink_register(devlink); return 0; } diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index e19a6bb3f444..146ca1d8031b 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -250,10 +250,11 @@ static void ibmvnic_set_affinity(struct ibmvnic_adapter *adapter) struct ibmvnic_sub_crq_queue **rxqs = adapter->rx_scrq; struct ibmvnic_sub_crq_queue **txqs = adapter->tx_scrq; struct ibmvnic_sub_crq_queue *queue; - int num_rxqs = adapter->num_active_rx_scrqs; - int num_txqs = adapter->num_active_tx_scrqs; + int num_rxqs = adapter->num_active_rx_scrqs, i_rxqs = 0; + int num_txqs = adapter->num_active_tx_scrqs, i_txqs = 0; int total_queues, stride, stragglers, i; unsigned int num_cpu, cpu; + bool is_rx_queue; int rc = 0; netdev_dbg(adapter->netdev, "%s: Setting irq affinity hints", __func__); @@ -273,14 +274,24 @@ static void ibmvnic_set_affinity(struct ibmvnic_adapter *adapter) /* next available cpu to assign irq to */ cpu = cpumask_next(-1, cpu_online_mask); - for (i = 0; i < num_txqs; i++) { - queue = txqs[i]; + for (i = 0; i < total_queues; i++) { + is_rx_queue = false; + /* balance core load by alternating rx and tx assignments + * ex: TX0 -> RX0 -> TX1 -> RX1 etc. + */ + if ((i % 2 == 1 && i_rxqs < num_rxqs) || i_txqs == num_txqs) { + queue = rxqs[i_rxqs++]; + is_rx_queue = true; + } else { + queue = txqs[i_txqs++]; + } + rc = ibmvnic_set_queue_affinity(queue, &cpu, &stragglers, stride); if (rc) goto out; - if (!queue) + if (!queue || is_rx_queue) continue; rc = __netif_set_xps_queue(adapter->netdev, @@ -291,14 +302,6 @@ static void ibmvnic_set_affinity(struct ibmvnic_adapter *adapter) __func__, i, rc); } - for (i = 0; i < num_rxqs; i++) { - queue = rxqs[i]; - rc = ibmvnic_set_queue_affinity(queue, &cpu, &stragglers, - stride); - if (rc) - goto out; - } - out: if (rc) { netdev_warn(adapter->netdev, diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 04acd1a992fa..e1eb1de88bf9 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -7418,9 +7418,6 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_pci_reg; - /* AER (Advanced Error Reporting) hooks */ - pci_enable_pcie_error_reporting(pdev); - pci_set_master(pdev); /* PCI config space info */ err = pci_save_state(pdev); @@ -7708,7 +7705,6 @@ err_flashmap: err_ioremap: free_netdev(netdev); err_alloc_etherdev: - pci_disable_pcie_error_reporting(pdev); pci_release_mem_regions(pdev); err_pci_reg: err_dma: @@ -7775,9 +7771,6 @@ static void e1000_remove(struct pci_dev *pdev) free_netdev(netdev); - /* AER disable */ - pci_disable_pcie_error_reporting(pdev); - pci_disable_device(pdev); } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index b473cb7d7c57..027d721feb18 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -2127,8 +2127,6 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_pci_reg; } - pci_enable_pcie_error_reporting(pdev); - pci_set_master(pdev); pci_save_state(pdev); @@ -2227,7 +2225,6 @@ err_sw_init: err_ioremap: free_netdev(netdev); err_alloc_netdev: - pci_disable_pcie_error_reporting(pdev); pci_release_mem_regions(pdev); err_pci_reg: err_dma: @@ -2281,8 +2278,6 @@ static void fm10k_remove(struct pci_dev *pdev) pci_release_mem_regions(pdev); - pci_disable_pcie_error_reporting(pdev); - pci_disable_device(pdev); } diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 60e351665c70..38c341b9f368 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -33,6 +33,7 @@ #include <linux/net_tstamp.h> #include <linux/ptp_clock_kernel.h> #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include <net/tc_act/tc_gact.h> #include <net/tc_act/tc_mirred.h> #include <net/udp_tunnel.h> diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 8a79cc18c428..3ee00c3bc319 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -15595,7 +15595,6 @@ err_switch_setup: timer_shutdown_sync(&pf->service_timer); i40e_shutdown_adminq(hw); iounmap(hw->hw_addr); - pci_disable_pcie_error_reporting(pf->pdev); pci_release_mem_regions(pf->pdev); pci_disable_device(pf->pdev); kfree(pf); @@ -15666,7 +15665,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_pci_reg; } - pci_enable_pcie_error_reporting(pdev); pci_set_master(pdev); /* Now that we have a PCI connection, we need to do the @@ -16224,7 +16222,6 @@ err_pf_reset: err_ioremap: kfree(pf); err_pf_alloc: - pci_disable_pcie_error_reporting(pdev); pci_release_mem_regions(pdev); err_pci_reg: err_dma: @@ -16372,7 +16369,6 @@ unmap: kfree(pf); pci_release_mem_regions(pdev); - pci_disable_pcie_error_reporting(pdev); pci_disable_device(pdev); } diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 23bc000e77b8..232bc61d9eee 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -30,6 +30,7 @@ #include <linux/jiffies.h> #include <net/ip6_checksum.h> #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include <net/udp.h> #include <net/tc_act/tc_gact.h> #include <net/tc_act/tc_mirred.h> diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 2c4480b20db3..3273aeb8fa67 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -4868,8 +4868,6 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_pci_reg; } - pci_enable_pcie_error_reporting(pdev); - pci_set_master(pdev); netdev = alloc_etherdev_mq(sizeof(struct iavf_adapter), @@ -4957,7 +4955,6 @@ err_ioremap: err_alloc_wq: free_netdev(netdev); err_alloc_etherdev: - pci_disable_pcie_error_reporting(pdev); pci_release_regions(pdev); err_pci_reg: err_dma: @@ -5175,8 +5172,6 @@ static void iavf_remove(struct pci_dev *pdev) free_netdev(netdev); - pci_disable_pcie_error_reporting(pdev); - pci_disable_device(pdev); } diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index ae93ae488bc2..7bd50e49312c 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -41,6 +41,7 @@ #include <linux/dim.h> #include <linux/gnss.h> #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include <net/tc_act/tc_mirred.h> #include <net/tc_act/tc_gact.h> #include <net/ip.h> @@ -353,7 +354,6 @@ struct ice_vsi { struct ice_vf *vf; /* VF associated with this VSI */ - u16 ethtype; /* Ethernet protocol for pause frame */ u16 num_gfltr; u16 num_bfltr; @@ -880,7 +880,7 @@ void ice_set_ethtool_repr_ops(struct net_device *netdev); void ice_set_ethtool_safe_mode_ops(struct net_device *netdev); u16 ice_get_avail_txq_count(struct ice_pf *pf); u16 ice_get_avail_rxq_count(struct ice_pf *pf); -int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx); +int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked); void ice_update_vsi_stats(struct ice_vsi *vsi); void ice_update_pf_stats(struct ice_pf *pf); void @@ -889,7 +889,7 @@ ice_fetch_u64_stats_per_ring(struct u64_stats_sync *syncp, int ice_up(struct ice_vsi *vsi); int ice_down(struct ice_vsi *vsi); int ice_down_up(struct ice_vsi *vsi); -int ice_vsi_cfg(struct ice_vsi *vsi); +int ice_vsi_cfg_lan(struct ice_vsi *vsi); struct ice_vsi *ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi); int ice_vsi_determine_xdp_res(struct ice_vsi *vsi); int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog); @@ -907,6 +907,7 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup); int ice_plug_aux_dev(struct ice_pf *pf); void ice_unplug_aux_dev(struct ice_pf *pf); int ice_init_rdma(struct ice_pf *pf); +void ice_deinit_rdma(struct ice_pf *pf); const char *ice_aq_str(enum ice_aq_err aq_err); bool ice_is_wol_supported(struct ice_hw *hw); void ice_fdir_del_all_fltrs(struct ice_vsi *vsi); @@ -931,6 +932,8 @@ int ice_open(struct net_device *netdev); int ice_open_internal(struct net_device *netdev); int ice_stop(struct net_device *netdev); void ice_service_task_schedule(struct ice_pf *pf); +int ice_load(struct ice_pf *pf); +void ice_unload(struct ice_pf *pf); /** * ice_set_rdma_cap - enable RDMA support diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index f5842ff42bc7..1b79bb0a4fcd 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1088,8 +1088,10 @@ int ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_cqinit; - hw->port_info = devm_kzalloc(ice_hw_to_dev(hw), - sizeof(*hw->port_info), GFP_KERNEL); + if (!hw->port_info) + hw->port_info = devm_kzalloc(ice_hw_to_dev(hw), + sizeof(*hw->port_info), + GFP_KERNEL); if (!hw->port_info) { status = -ENOMEM; goto err_unroll_cqinit; @@ -1217,11 +1219,6 @@ void ice_deinit_hw(struct ice_hw *hw) ice_free_hw_tbls(hw); mutex_destroy(&hw->tnl_lock); - if (hw->port_info) { - devm_kfree(ice_hw_to_dev(hw), hw->port_info); - hw->port_info = NULL; - } - /* Attempt to disable FW logging before shutting down control queues */ ice_cfg_fw_log(hw, false); ice_destroy_all_ctrlq(hw); @@ -5537,7 +5534,7 @@ bool ice_fw_supports_report_dflt_cfg(struct ice_hw *hw) * returned by the firmware is a 16 bit * value, but is indexed * by [fls(speed) - 1] */ -static const u32 ice_aq_to_link_speed[15] = { +static const u32 ice_aq_to_link_speed[] = { SPEED_10, /* BIT(0) */ SPEED_100, SPEED_1000, @@ -5549,10 +5546,6 @@ static const u32 ice_aq_to_link_speed[15] = { SPEED_40000, SPEED_50000, SPEED_100000, /* BIT(10) */ - 0, - 0, - 0, - 0 /* BIT(14) */ }; /** @@ -5563,5 +5556,8 @@ static const u32 ice_aq_to_link_speed[15] = { */ u32 ice_get_link_speed(u16 index) { + if (index >= ARRAY_SIZE(ice_aq_to_link_speed)) + return 0; + return ice_aq_to_link_speed[index]; } diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index a97b137e21c0..c6d4926f0fcf 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -441,7 +441,7 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked) goto out; } - ice_pf_dcb_recfg(pf); + ice_pf_dcb_recfg(pf, false); out: /* enable previously downed VSIs */ @@ -731,12 +731,13 @@ static int ice_dcb_noncontig_cfg(struct ice_pf *pf) /** * ice_pf_dcb_recfg - Reconfigure all VEBs and VSIs * @pf: pointer to the PF struct + * @locked: is adev device lock held * * Assumed caller has already disabled all VSIs before * calling this function. Reconfiguring DCB based on * local_dcbx_cfg. */ -void ice_pf_dcb_recfg(struct ice_pf *pf) +void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked) { struct ice_dcbx_cfg *dcbcfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; struct iidc_event *event; @@ -783,14 +784,16 @@ void ice_pf_dcb_recfg(struct ice_pf *pf) if (vsi->type == ICE_VSI_PF) ice_dcbnl_set_all(vsi); } - /* Notify the AUX drivers that TC change is finished */ - event = kzalloc(sizeof(*event), GFP_KERNEL); - if (!event) - return; - - set_bit(IIDC_EVENT_AFTER_TC_CHANGE, event->type); - ice_send_event_to_aux(pf, event); - kfree(event); + if (!locked) { + /* Notify the AUX drivers that TC change is finished */ + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (!event) + return; + + set_bit(IIDC_EVENT_AFTER_TC_CHANGE, event->type); + ice_send_event_to_aux(pf, event); + kfree(event); + } } /** @@ -1078,7 +1081,7 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, } /* changes in configuration update VSI */ - ice_pf_dcb_recfg(pf); + ice_pf_dcb_recfg(pf, false); /* enable previously downed VSIs */ ice_dcb_ena_dis_vsi(pf, true, true); diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h index 4c421c842a13..800879a88c5e 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h @@ -23,7 +23,7 @@ u8 ice_dcb_get_tc(struct ice_vsi *vsi, int queue_index); int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked); int ice_dcb_bwchk(struct ice_pf *pf, struct ice_dcbx_cfg *dcbcfg); -void ice_pf_dcb_recfg(struct ice_pf *pf); +void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked); void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi); int ice_init_pf_dcb(struct ice_pf *pf, bool locked); void ice_update_dcb_stats(struct ice_pf *pf); @@ -128,7 +128,7 @@ static inline u8 ice_get_pfc_mode(struct ice_pf *pf) return 0; } -static inline void ice_pf_dcb_recfg(struct ice_pf *pf) { } +static inline void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked) { } static inline void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi) { } static inline void ice_update_dcb_stats(struct ice_pf *pf) { } static inline void diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index ce753d23aba9..63acb7b96053 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -371,10 +371,7 @@ out_free_ctx: /** * ice_devlink_reload_empr_start - Start EMP reset to activate new firmware - * @devlink: pointer to the devlink instance to reload - * @netns_change: if true, the network namespace is changing - * @action: the action to perform. Must be DEVLINK_RELOAD_ACTION_FW_ACTIVATE - * @limit: limits on what reload should do, such as not resetting + * @pf: pointer to the pf instance * @extack: netlink extended ACK structure * * Allow user to activate new Embedded Management Processor firmware by @@ -387,12 +384,9 @@ out_free_ctx: * any source. */ static int -ice_devlink_reload_empr_start(struct devlink *devlink, bool netns_change, - enum devlink_reload_action action, - enum devlink_reload_limit limit, +ice_devlink_reload_empr_start(struct ice_pf *pf, struct netlink_ext_ack *extack) { - struct ice_pf *pf = devlink_priv(devlink); struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; u8 pending; @@ -431,11 +425,51 @@ ice_devlink_reload_empr_start(struct devlink *devlink, bool netns_change, } /** + * ice_devlink_reload_down - prepare for reload + * @devlink: pointer to the devlink instance to reload + * @netns_change: if true, the network namespace is changing + * @action: the action to perform + * @limit: limits on what reload should do, such as not resetting + * @extack: netlink extended ACK structure + */ +static int +ice_devlink_reload_down(struct devlink *devlink, bool netns_change, + enum devlink_reload_action action, + enum devlink_reload_limit limit, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_priv(devlink); + + switch (action) { + case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: + if (ice_is_eswitch_mode_switchdev(pf)) { + NL_SET_ERR_MSG_MOD(extack, + "Go to legacy mode before doing reinit\n"); + return -EOPNOTSUPP; + } + if (ice_is_adq_active(pf)) { + NL_SET_ERR_MSG_MOD(extack, + "Turn off ADQ before doing reinit\n"); + return -EOPNOTSUPP; + } + if (ice_has_vfs(pf)) { + NL_SET_ERR_MSG_MOD(extack, + "Remove all VFs before doing reinit\n"); + return -EOPNOTSUPP; + } + ice_unload(pf); + return 0; + case DEVLINK_RELOAD_ACTION_FW_ACTIVATE: + return ice_devlink_reload_empr_start(pf, extack); + default: + WARN_ON(1); + return -EOPNOTSUPP; + } +} + +/** * ice_devlink_reload_empr_finish - Wait for EMP reset to finish - * @devlink: pointer to the devlink instance reloading - * @action: the action requested - * @limit: limits imposed by userspace, such as not resetting - * @actions_performed: on return, indicate what actions actually performed + * @pf: pointer to the pf instance * @extack: netlink extended ACK structure * * Wait for driver to finish rebuilding after EMP reset is completed. This @@ -443,17 +477,11 @@ ice_devlink_reload_empr_start(struct devlink *devlink, bool netns_change, * for the driver's rebuild to complete. */ static int -ice_devlink_reload_empr_finish(struct devlink *devlink, - enum devlink_reload_action action, - enum devlink_reload_limit limit, - u32 *actions_performed, +ice_devlink_reload_empr_finish(struct ice_pf *pf, struct netlink_ext_ack *extack) { - struct ice_pf *pf = devlink_priv(devlink); int err; - *actions_performed = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE); - err = ice_wait_for_reset(pf, 60 * HZ); if (err) { NL_SET_ERR_MSG_MOD(extack, "Device still resetting after 1 minute"); @@ -1192,12 +1220,43 @@ static int ice_devlink_set_parent(struct devlink_rate *devlink_rate, return status; } +/** + * ice_devlink_reload_up - do reload up after reinit + * @devlink: pointer to the devlink instance reloading + * @action: the action requested + * @limit: limits imposed by userspace, such as not resetting + * @actions_performed: on return, indicate what actions actually performed + * @extack: netlink extended ACK structure + */ +static int +ice_devlink_reload_up(struct devlink *devlink, + enum devlink_reload_action action, + enum devlink_reload_limit limit, + u32 *actions_performed, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_priv(devlink); + + switch (action) { + case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: + *actions_performed = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT); + return ice_load(pf); + case DEVLINK_RELOAD_ACTION_FW_ACTIVATE: + *actions_performed = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE); + return ice_devlink_reload_empr_finish(pf, extack); + default: + WARN_ON(1); + return -EOPNOTSUPP; + } +} + static const struct devlink_ops ice_devlink_ops = { .supported_flash_update_params = DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK, - .reload_actions = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE), + .reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) | + BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE), /* The ice driver currently does not support driver reinit */ - .reload_down = ice_devlink_reload_empr_start, - .reload_up = ice_devlink_reload_empr_finish, + .reload_down = ice_devlink_reload_down, + .reload_up = ice_devlink_reload_up, .port_split = ice_devlink_port_split, .port_unsplit = ice_devlink_port_unsplit, .eswitch_mode_get = ice_eswitch_mode_get, @@ -1376,7 +1435,6 @@ void ice_devlink_register(struct ice_pf *pf) { struct devlink *devlink = priv_to_devlink(pf); - devlink_set_features(devlink, DEVLINK_F_RELOAD); devlink_register(devlink); } diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index f9f15acae90a..f6dd3f8fd936 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -71,17 +71,17 @@ void ice_eswitch_replay_vf_mac_rule(struct ice_vf *vf) if (!ice_is_switchdev_running(vf->pf)) return; - if (is_valid_ether_addr(vf->hw_lan_addr.addr)) { + if (is_valid_ether_addr(vf->hw_lan_addr)) { err = ice_eswitch_add_vf_mac_rule(vf->pf, vf, - vf->hw_lan_addr.addr); + vf->hw_lan_addr); if (err) { dev_err(ice_pf_to_dev(vf->pf), "Failed to add MAC %pM for VF %d\n, error %d\n", - vf->hw_lan_addr.addr, vf->vf_id, err); + vf->hw_lan_addr, vf->vf_id, err); return; } vf->num_mac++; - ether_addr_copy(vf->dev_lan_addr.addr, vf->hw_lan_addr.addr); + ether_addr_copy(vf->dev_lan_addr, vf->hw_lan_addr); } } @@ -237,7 +237,7 @@ ice_eswitch_release_reprs(struct ice_pf *pf, struct ice_vsi *ctrl_vsi) ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof); metadata_dst_free(vf->repr->dst); vf->repr->dst = NULL; - ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr.addr, + ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, ICE_FWD_TO_VSI); netif_napi_del(&vf->repr->q_vector->napi); @@ -265,14 +265,14 @@ static int ice_eswitch_setup_reprs(struct ice_pf *pf) GFP_KERNEL); if (!vf->repr->dst) { ice_fltr_add_mac_and_broadcast(vsi, - vf->hw_lan_addr.addr, + vf->hw_lan_addr, ICE_FWD_TO_VSI); goto err; } if (ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof)) { ice_fltr_add_mac_and_broadcast(vsi, - vf->hw_lan_addr.addr, + vf->hw_lan_addr, ICE_FWD_TO_VSI); metadata_dst_free(vf->repr->dst); vf->repr->dst = NULL; @@ -281,7 +281,7 @@ static int ice_eswitch_setup_reprs(struct ice_pf *pf) if (ice_vsi_add_vlan_zero(vsi)) { ice_fltr_add_mac_and_broadcast(vsi, - vf->hw_lan_addr.addr, + vf->hw_lan_addr, ICE_FWD_TO_VSI); metadata_dst_free(vf->repr->dst); vf->repr->dst = NULL; @@ -338,7 +338,7 @@ void ice_eswitch_update_repr(struct ice_vsi *vsi) ret = ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof); if (ret) { - ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr.addr, ICE_FWD_TO_VSI); + ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, ICE_FWD_TO_VSI); dev_err(ice_pf_to_dev(pf), "Failed to update VF %d port representor", vsi->vf->vf_id); } @@ -425,7 +425,13 @@ static void ice_eswitch_release_env(struct ice_pf *pf) static struct ice_vsi * ice_eswitch_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) { - return ice_vsi_setup(pf, pi, ICE_VSI_SWITCHDEV_CTRL, NULL, NULL); + struct ice_vsi_cfg_params params = {}; + + params.type = ICE_VSI_SWITCHDEV_CTRL; + params.pi = pi; + params.flags = ICE_VSI_FLAG_INIT; + + return ice_vsi_setup(pf, ¶ms); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 1adbcb4786c2..b360bd8f1599 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -656,7 +656,7 @@ static int ice_lbtest_prepare_rings(struct ice_vsi *vsi) if (status) goto err_setup_rx_ring; - status = ice_vsi_cfg(vsi); + status = ice_vsi_cfg_lan(vsi); if (status) goto err_setup_rx_ring; @@ -3658,7 +3658,9 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch) struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; int new_rx = 0, new_tx = 0; + bool locked = false; u32 curr_combined; + int ret = 0; /* do not support changing channels in Safe Mode */ if (ice_is_safe_mode(pf)) { @@ -3722,15 +3724,33 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch) return -EINVAL; } - ice_vsi_recfg_qs(vsi, new_rx, new_tx); + if (pf->adev) { + mutex_lock(&pf->adev_mutex); + device_lock(&pf->adev->dev); + locked = true; + if (pf->adev->dev.driver) { + netdev_err(dev, "Cannot change channels when RDMA is active\n"); + ret = -EBUSY; + goto adev_unlock; + } + } + + ice_vsi_recfg_qs(vsi, new_rx, new_tx, locked); - if (!netif_is_rxfh_configured(dev)) - return ice_vsi_set_dflt_rss_lut(vsi, new_rx); + if (!netif_is_rxfh_configured(dev)) { + ret = ice_vsi_set_dflt_rss_lut(vsi, new_rx); + goto adev_unlock; + } /* Update rss_size due to change in Rx queues */ vsi->rss_size = ice_get_valid_rss_size(&pf->hw, new_rx); - return 0; +adev_unlock: + if (locked) { + device_unlock(&pf->adev->dev); + mutex_unlock(&pf->adev_mutex); + } + return ret; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.c b/drivers/net/ethernet/intel/ice/ice_fltr.c index 40e678cfb507..aff7a141c30d 100644 --- a/drivers/net/ethernet/intel/ice/ice_fltr.c +++ b/drivers/net/ethernet/intel/ice/ice_fltr.c @@ -208,6 +208,11 @@ static int ice_fltr_remove_eth_list(struct ice_vsi *vsi, struct list_head *list) void ice_fltr_remove_all(struct ice_vsi *vsi) { ice_remove_vsi_fltr(&vsi->back->hw, vsi->idx); + /* sync netdev filters if exist */ + if (vsi->netdev) { + __dev_uc_unsync(vsi->netdev, NULL); + __dev_mc_unsync(vsi->netdev, NULL); + } } /** diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c index 895c32bcc8b5..e6bc2285071e 100644 --- a/drivers/net/ethernet/intel/ice/ice_idc.c +++ b/drivers/net/ethernet/intel/ice/ice_idc.c @@ -6,6 +6,8 @@ #include "ice_lib.h" #include "ice_dcb_lib.h" +static DEFINE_XARRAY_ALLOC1(ice_aux_id); + /** * ice_get_auxiliary_drv - retrieve iidc_auxiliary_drv struct * @pf: pointer to PF struct @@ -246,6 +248,17 @@ static int ice_reserve_rdma_qvector(struct ice_pf *pf) } /** + * ice_free_rdma_qvector - free vector resources reserved for RDMA driver + * @pf: board private structure to initialize + */ +static void ice_free_rdma_qvector(struct ice_pf *pf) +{ + pf->num_avail_sw_msix -= pf->num_rdma_msix; + ice_free_res(pf->irq_tracker, pf->rdma_base_vector, + ICE_RES_RDMA_VEC_ID); +} + +/** * ice_adev_release - function to be mapped to AUX dev's release op * @dev: pointer to device to free */ @@ -331,12 +344,48 @@ int ice_init_rdma(struct ice_pf *pf) struct device *dev = &pf->pdev->dev; int ret; + if (!ice_is_rdma_ena(pf)) { + dev_warn(dev, "RDMA is not supported on this device\n"); + return 0; + } + + ret = xa_alloc(&ice_aux_id, &pf->aux_idx, NULL, XA_LIMIT(1, INT_MAX), + GFP_KERNEL); + if (ret) { + dev_err(dev, "Failed to allocate device ID for AUX driver\n"); + return -ENOMEM; + } + /* Reserve vector resources */ ret = ice_reserve_rdma_qvector(pf); if (ret < 0) { dev_err(dev, "failed to reserve vectors for RDMA\n"); - return ret; + goto err_reserve_rdma_qvector; } pf->rdma_mode |= IIDC_RDMA_PROTOCOL_ROCEV2; - return ice_plug_aux_dev(pf); + ret = ice_plug_aux_dev(pf); + if (ret) + goto err_plug_aux_dev; + return 0; + +err_plug_aux_dev: + ice_free_rdma_qvector(pf); +err_reserve_rdma_qvector: + pf->adev = NULL; + xa_erase(&ice_aux_id, pf->aux_idx); + return ret; +} + +/** + * ice_deinit_rdma - deinitialize RDMA on PF + * @pf: ptr to ice_pf + */ +void ice_deinit_rdma(struct ice_pf *pf) +{ + if (!ice_is_rdma_ena(pf)) + return; + + ice_unplug_aux_dev(pf); + ice_free_rdma_qvector(pf); + xa_erase(&ice_aux_id, pf->aux_idx); } diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 4a35479bd7dd..37fe639712e6 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -166,14 +166,14 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi) /** * ice_vsi_set_num_qs - Set number of queues, descriptors and vectors for a VSI * @vsi: the VSI being configured - * @vf: the VF associated with this VSI, if any * * Return 0 on success and a negative value on error */ -static void ice_vsi_set_num_qs(struct ice_vsi *vsi, struct ice_vf *vf) +static void ice_vsi_set_num_qs(struct ice_vsi *vsi) { enum ice_vsi_type vsi_type = vsi->type; struct ice_pf *pf = vsi->back; + struct ice_vf *vf = vsi->vf; if (WARN_ON(vsi_type == ICE_VSI_VF && !vf)) return; @@ -282,10 +282,10 @@ static int ice_get_free_slot(void *array, int size, int curr) } /** - * ice_vsi_delete - delete a VSI from the switch + * ice_vsi_delete_from_hw - delete a VSI from the switch * @vsi: pointer to VSI being removed */ -void ice_vsi_delete(struct ice_vsi *vsi) +static void ice_vsi_delete_from_hw(struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; struct ice_vsi_ctx *ctxt; @@ -348,47 +348,144 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi) } /** - * ice_vsi_clear - clean up and deallocate the provided VSI + * ice_vsi_free_stats - Free the ring statistics structures + * @vsi: VSI pointer + */ +static void ice_vsi_free_stats(struct ice_vsi *vsi) +{ + struct ice_vsi_stats *vsi_stat; + struct ice_pf *pf = vsi->back; + int i; + + if (vsi->type == ICE_VSI_CHNL) + return; + if (!pf->vsi_stats) + return; + + vsi_stat = pf->vsi_stats[vsi->idx]; + if (!vsi_stat) + return; + + ice_for_each_alloc_txq(vsi, i) { + if (vsi_stat->tx_ring_stats[i]) { + kfree_rcu(vsi_stat->tx_ring_stats[i], rcu); + WRITE_ONCE(vsi_stat->tx_ring_stats[i], NULL); + } + } + + ice_for_each_alloc_rxq(vsi, i) { + if (vsi_stat->rx_ring_stats[i]) { + kfree_rcu(vsi_stat->rx_ring_stats[i], rcu); + WRITE_ONCE(vsi_stat->rx_ring_stats[i], NULL); + } + } + + kfree(vsi_stat->tx_ring_stats); + kfree(vsi_stat->rx_ring_stats); + kfree(vsi_stat); + pf->vsi_stats[vsi->idx] = NULL; +} + +/** + * ice_vsi_alloc_ring_stats - Allocates Tx and Rx ring stats for the VSI + * @vsi: VSI which is having stats allocated + */ +static int ice_vsi_alloc_ring_stats(struct ice_vsi *vsi) +{ + struct ice_ring_stats **tx_ring_stats; + struct ice_ring_stats **rx_ring_stats; + struct ice_vsi_stats *vsi_stats; + struct ice_pf *pf = vsi->back; + u16 i; + + vsi_stats = pf->vsi_stats[vsi->idx]; + tx_ring_stats = vsi_stats->tx_ring_stats; + rx_ring_stats = vsi_stats->rx_ring_stats; + + /* Allocate Tx ring stats */ + ice_for_each_alloc_txq(vsi, i) { + struct ice_ring_stats *ring_stats; + struct ice_tx_ring *ring; + + ring = vsi->tx_rings[i]; + ring_stats = tx_ring_stats[i]; + + if (!ring_stats) { + ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL); + if (!ring_stats) + goto err_out; + + WRITE_ONCE(tx_ring_stats[i], ring_stats); + } + + ring->ring_stats = ring_stats; + } + + /* Allocate Rx ring stats */ + ice_for_each_alloc_rxq(vsi, i) { + struct ice_ring_stats *ring_stats; + struct ice_rx_ring *ring; + + ring = vsi->rx_rings[i]; + ring_stats = rx_ring_stats[i]; + + if (!ring_stats) { + ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL); + if (!ring_stats) + goto err_out; + + WRITE_ONCE(rx_ring_stats[i], ring_stats); + } + + ring->ring_stats = ring_stats; + } + + return 0; + +err_out: + ice_vsi_free_stats(vsi); + return -ENOMEM; +} + +/** + * ice_vsi_free - clean up and deallocate the provided VSI * @vsi: pointer to VSI being cleared * * This deallocates the VSI's queue resources, removes it from the PF's * VSI array if necessary, and deallocates the VSI - * - * Returns 0 on success, negative on failure */ -int ice_vsi_clear(struct ice_vsi *vsi) +static void ice_vsi_free(struct ice_vsi *vsi) { struct ice_pf *pf = NULL; struct device *dev; - if (!vsi) - return 0; - - if (!vsi->back) - return -EINVAL; + if (!vsi || !vsi->back) + return; pf = vsi->back; dev = ice_pf_to_dev(pf); if (!pf->vsi[vsi->idx] || pf->vsi[vsi->idx] != vsi) { dev_dbg(dev, "vsi does not exist at pf->vsi[%d]\n", vsi->idx); - return -EINVAL; + return; } mutex_lock(&pf->sw_mutex); /* updates the PF for this cleared VSI */ pf->vsi[vsi->idx] = NULL; - if (vsi->idx < pf->next_vsi && vsi->type != ICE_VSI_CTRL) - pf->next_vsi = vsi->idx; - if (vsi->idx < pf->next_vsi && vsi->type == ICE_VSI_CTRL && vsi->vf) - pf->next_vsi = vsi->idx; + pf->next_vsi = vsi->idx; + ice_vsi_free_stats(vsi); ice_vsi_free_arrays(vsi); mutex_unlock(&pf->sw_mutex); devm_kfree(dev, vsi); +} - return 0; +void ice_vsi_delete(struct ice_vsi *vsi) +{ + ice_vsi_delete_from_hw(vsi); + ice_vsi_free(vsi); } /** @@ -461,6 +558,10 @@ static int ice_vsi_alloc_stat_arrays(struct ice_vsi *vsi) if (!pf->vsi_stats) return -ENOENT; + if (pf->vsi_stats[vsi->idx]) + /* realloc will happen in rebuild path */ + return 0; + vsi_stat = kzalloc(sizeof(*vsi_stat), GFP_KERNEL); if (!vsi_stat) return -ENOMEM; @@ -491,128 +592,92 @@ err_alloc_tx: } /** - * ice_vsi_alloc - Allocates the next available struct VSI in the PF - * @pf: board private structure - * @vsi_type: type of VSI + * ice_vsi_alloc_def - set default values for already allocated VSI + * @vsi: ptr to VSI * @ch: ptr to channel - * @vf: VF for ICE_VSI_VF and ICE_VSI_CTRL - * - * The VF pointer is used for ICE_VSI_VF and ICE_VSI_CTRL. For ICE_VSI_CTRL, - * it may be NULL in the case there is no association with a VF. For - * ICE_VSI_VF the VF pointer *must not* be NULL. - * - * returns a pointer to a VSI on success, NULL on failure. */ -static struct ice_vsi * -ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, - struct ice_channel *ch, struct ice_vf *vf) +static int +ice_vsi_alloc_def(struct ice_vsi *vsi, struct ice_channel *ch) { - struct device *dev = ice_pf_to_dev(pf); - struct ice_vsi *vsi = NULL; - - if (WARN_ON(vsi_type == ICE_VSI_VF && !vf)) - return NULL; - - /* Need to protect the allocation of the VSIs at the PF level */ - mutex_lock(&pf->sw_mutex); - - /* If we have already allocated our maximum number of VSIs, - * pf->next_vsi will be ICE_NO_VSI. If not, pf->next_vsi index - * is available to be populated - */ - if (pf->next_vsi == ICE_NO_VSI) { - dev_dbg(dev, "out of VSI slots!\n"); - goto unlock_pf; + if (vsi->type != ICE_VSI_CHNL) { + ice_vsi_set_num_qs(vsi); + if (ice_vsi_alloc_arrays(vsi)) + return -ENOMEM; } - vsi = devm_kzalloc(dev, sizeof(*vsi), GFP_KERNEL); - if (!vsi) - goto unlock_pf; - - vsi->type = vsi_type; - vsi->back = pf; - set_bit(ICE_VSI_DOWN, vsi->state); - - if (vsi_type == ICE_VSI_VF) - ice_vsi_set_num_qs(vsi, vf); - else if (vsi_type != ICE_VSI_CHNL) - ice_vsi_set_num_qs(vsi, NULL); - switch (vsi->type) { case ICE_VSI_SWITCHDEV_CTRL: - if (ice_vsi_alloc_arrays(vsi)) - goto err_rings; - /* Setup eswitch MSIX irq handler for VSI */ vsi->irq_handler = ice_eswitch_msix_clean_rings; break; case ICE_VSI_PF: - if (ice_vsi_alloc_arrays(vsi)) - goto err_rings; - /* Setup default MSIX irq handler for VSI */ vsi->irq_handler = ice_msix_clean_rings; break; case ICE_VSI_CTRL: - if (ice_vsi_alloc_arrays(vsi)) - goto err_rings; - /* Setup ctrl VSI MSIX irq handler */ vsi->irq_handler = ice_msix_clean_ctrl_vsi; - - /* For the PF control VSI this is NULL, for the VF control VSI - * this will be the first VF to allocate it. - */ - vsi->vf = vf; - break; - case ICE_VSI_VF: - if (ice_vsi_alloc_arrays(vsi)) - goto err_rings; - vsi->vf = vf; break; case ICE_VSI_CHNL: if (!ch) - goto err_rings; + return -EINVAL; + vsi->num_rxq = ch->num_rxq; vsi->num_txq = ch->num_txq; vsi->next_base_q = ch->base_q; break; - case ICE_VSI_LB: - if (ice_vsi_alloc_arrays(vsi)) - goto err_rings; + case ICE_VSI_VF: break; default: - dev_warn(dev, "Unknown VSI type %d\n", vsi->type); - goto unlock_pf; + ice_vsi_free_arrays(vsi); + return -EINVAL; } - if (vsi->type == ICE_VSI_CTRL && !vf) { - /* Use the last VSI slot as the index for PF control VSI */ - vsi->idx = pf->num_alloc_vsi - 1; - pf->ctrl_vsi_idx = vsi->idx; - pf->vsi[vsi->idx] = vsi; - } else { - /* fill slot and make note of the index */ - vsi->idx = pf->next_vsi; - pf->vsi[pf->next_vsi] = vsi; + return 0; +} - /* prepare pf->next_vsi for next use */ - pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi, - pf->next_vsi); +/** + * ice_vsi_alloc - Allocates the next available struct VSI in the PF + * @pf: board private structure + * + * Reserves a VSI index from the PF and allocates an empty VSI structure + * without a type. The VSI structure must later be initialized by calling + * ice_vsi_cfg(). + * + * returns a pointer to a VSI on success, NULL on failure. + */ +static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + struct ice_vsi *vsi = NULL; + + /* Need to protect the allocation of the VSIs at the PF level */ + mutex_lock(&pf->sw_mutex); + + /* If we have already allocated our maximum number of VSIs, + * pf->next_vsi will be ICE_NO_VSI. If not, pf->next_vsi index + * is available to be populated + */ + if (pf->next_vsi == ICE_NO_VSI) { + dev_dbg(dev, "out of VSI slots!\n"); + goto unlock_pf; } - if (vsi->type == ICE_VSI_CTRL && vf) - vf->ctrl_vsi_idx = vsi->idx; + vsi = devm_kzalloc(dev, sizeof(*vsi), GFP_KERNEL); + if (!vsi) + goto unlock_pf; - /* allocate memory for Tx/Rx ring stat pointers */ - if (ice_vsi_alloc_stat_arrays(vsi)) - goto err_rings; + vsi->back = pf; + set_bit(ICE_VSI_DOWN, vsi->state); - goto unlock_pf; + /* fill slot and make note of the index */ + vsi->idx = pf->next_vsi; + pf->vsi[pf->next_vsi] = vsi; + + /* prepare pf->next_vsi for next use */ + pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi, + pf->next_vsi); -err_rings: - devm_kfree(dev, vsi); - vsi = NULL; unlock_pf: mutex_unlock(&pf->sw_mutex); return vsi; @@ -1177,12 +1242,15 @@ ice_chnl_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) /** * ice_vsi_init - Create and initialize a VSI * @vsi: the VSI being configured - * @init_vsi: is this call creating a VSI + * @vsi_flags: VSI configuration flags + * + * Set ICE_FLAG_VSI_INIT to initialize a new VSI context, clear it to + * reconfigure an existing context. * * This initializes a VSI context depending on the VSI type to be added and * passes it down to the add_vsi aq command to create a new VSI. */ -static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) +static int ice_vsi_init(struct ice_vsi *vsi, u32 vsi_flags) { struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; @@ -1244,7 +1312,7 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) /* if updating VSI context, make sure to set valid_section: * to indicate which section of VSI context being updated */ - if (!init_vsi) + if (!(vsi_flags & ICE_VSI_FLAG_INIT)) ctxt->info.valid_sections |= cpu_to_le16(ICE_AQ_VSI_PROP_Q_OPT_VALID); } @@ -1257,7 +1325,8 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) if (ret) goto out; - if (!init_vsi) /* means VSI being updated */ + if (!(vsi_flags & ICE_VSI_FLAG_INIT)) + /* means VSI being updated */ /* must to indicate which section of VSI context are * being modified */ @@ -1272,7 +1341,7 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID); } - if (init_vsi) { + if (vsi_flags & ICE_VSI_FLAG_INIT) { ret = ice_add_vsi(hw, vsi->idx, ctxt, NULL); if (ret) { dev_err(dev, "Add VSI failed, err %d\n", ret); @@ -1436,7 +1505,7 @@ static int ice_get_vf_ctrl_res(struct ice_pf *pf, struct ice_vsi *vsi) * ice_vsi_setup_vector_base - Set up the base vector for the given VSI * @vsi: ptr to the VSI * - * This should only be called after ice_vsi_alloc() which allocates the + * This should only be called after ice_vsi_alloc_def() which allocates the * corresponding SW VSI structure and initializes num_queue_pairs for the * newly allocated VSI. * @@ -1584,106 +1653,6 @@ err_out: } /** - * ice_vsi_free_stats - Free the ring statistics structures - * @vsi: VSI pointer - */ -static void ice_vsi_free_stats(struct ice_vsi *vsi) -{ - struct ice_vsi_stats *vsi_stat; - struct ice_pf *pf = vsi->back; - int i; - - if (vsi->type == ICE_VSI_CHNL) - return; - if (!pf->vsi_stats) - return; - - vsi_stat = pf->vsi_stats[vsi->idx]; - if (!vsi_stat) - return; - - ice_for_each_alloc_txq(vsi, i) { - if (vsi_stat->tx_ring_stats[i]) { - kfree_rcu(vsi_stat->tx_ring_stats[i], rcu); - WRITE_ONCE(vsi_stat->tx_ring_stats[i], NULL); - } - } - - ice_for_each_alloc_rxq(vsi, i) { - if (vsi_stat->rx_ring_stats[i]) { - kfree_rcu(vsi_stat->rx_ring_stats[i], rcu); - WRITE_ONCE(vsi_stat->rx_ring_stats[i], NULL); - } - } - - kfree(vsi_stat->tx_ring_stats); - kfree(vsi_stat->rx_ring_stats); - kfree(vsi_stat); - pf->vsi_stats[vsi->idx] = NULL; -} - -/** - * ice_vsi_alloc_ring_stats - Allocates Tx and Rx ring stats for the VSI - * @vsi: VSI which is having stats allocated - */ -static int ice_vsi_alloc_ring_stats(struct ice_vsi *vsi) -{ - struct ice_ring_stats **tx_ring_stats; - struct ice_ring_stats **rx_ring_stats; - struct ice_vsi_stats *vsi_stats; - struct ice_pf *pf = vsi->back; - u16 i; - - vsi_stats = pf->vsi_stats[vsi->idx]; - tx_ring_stats = vsi_stats->tx_ring_stats; - rx_ring_stats = vsi_stats->rx_ring_stats; - - /* Allocate Tx ring stats */ - ice_for_each_alloc_txq(vsi, i) { - struct ice_ring_stats *ring_stats; - struct ice_tx_ring *ring; - - ring = vsi->tx_rings[i]; - ring_stats = tx_ring_stats[i]; - - if (!ring_stats) { - ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL); - if (!ring_stats) - goto err_out; - - WRITE_ONCE(tx_ring_stats[i], ring_stats); - } - - ring->ring_stats = ring_stats; - } - - /* Allocate Rx ring stats */ - ice_for_each_alloc_rxq(vsi, i) { - struct ice_ring_stats *ring_stats; - struct ice_rx_ring *ring; - - ring = vsi->rx_rings[i]; - ring_stats = rx_ring_stats[i]; - - if (!ring_stats) { - ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL); - if (!ring_stats) - goto err_out; - - WRITE_ONCE(rx_ring_stats[i], ring_stats); - } - - ring->ring_stats = ring_stats; - } - - return 0; - -err_out: - ice_vsi_free_stats(vsi); - return -ENOMEM; -} - -/** * ice_vsi_manage_rss_lut - disable/enable RSS * @vsi: the VSI being changed * @ena: boolean value indicating if this is an enable or disable request @@ -2641,54 +2610,97 @@ static void ice_set_agg_vsi(struct ice_vsi *vsi) } /** - * ice_vsi_setup - Set up a VSI by a given type - * @pf: board private structure - * @pi: pointer to the port_info instance - * @vsi_type: VSI type - * @vf: pointer to VF to which this VSI connects. This field is used primarily - * for the ICE_VSI_VF type. Other VSI types should pass NULL. - * @ch: ptr to channel - * - * This allocates the sw VSI structure and its queue resources. + * ice_free_vf_ctrl_res - Free the VF control VSI resource + * @pf: pointer to PF structure + * @vsi: the VSI to free resources for * - * Returns pointer to the successfully allocated and configured VSI sw struct on - * success, NULL on failure. + * Check if the VF control VSI resource is still in use. If no VF is using it + * any more, release the VSI resource. Otherwise, leave it to be cleaned up + * once no other VF uses it. */ -struct ice_vsi * -ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, - enum ice_vsi_type vsi_type, struct ice_vf *vf, - struct ice_channel *ch) +static void ice_free_vf_ctrl_res(struct ice_pf *pf, struct ice_vsi *vsi) +{ + struct ice_vf *vf; + unsigned int bkt; + + rcu_read_lock(); + ice_for_each_vf_rcu(pf, bkt, vf) { + if (vf != vsi->vf && vf->ctrl_vsi_idx != ICE_NO_VSI) { + rcu_read_unlock(); + return; + } + } + rcu_read_unlock(); + + /* No other VFs left that have control VSI. It is now safe to reclaim + * SW interrupts back to the common pool. + */ + ice_free_res(pf->irq_tracker, vsi->base_vector, + ICE_RES_VF_CTRL_VEC_ID); + pf->num_avail_sw_msix += vsi->num_q_vectors; +} + +static int ice_vsi_cfg_tc_lan(struct ice_pf *pf, struct ice_vsi *vsi) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct device *dev = ice_pf_to_dev(pf); - struct ice_vsi *vsi; int ret, i; - if (vsi_type == ICE_VSI_CHNL) - vsi = ice_vsi_alloc(pf, vsi_type, ch, NULL); - else if (vsi_type == ICE_VSI_VF || vsi_type == ICE_VSI_CTRL) - vsi = ice_vsi_alloc(pf, vsi_type, NULL, vf); - else - vsi = ice_vsi_alloc(pf, vsi_type, NULL, NULL); + /* configure VSI nodes based on number of queues and TC's */ + ice_for_each_traffic_class(i) { + if (!(vsi->tc_cfg.ena_tc & BIT(i))) + continue; - if (!vsi) { - dev_err(dev, "could not allocate VSI\n"); - return NULL; + if (vsi->type == ICE_VSI_CHNL) { + if (!vsi->alloc_txq && vsi->num_txq) + max_txqs[i] = vsi->num_txq; + else + max_txqs[i] = pf->num_lan_tx; + } else { + max_txqs[i] = vsi->alloc_txq; + } } - vsi->port_info = pi; + dev_dbg(dev, "vsi->tc_cfg.ena_tc = %d\n", vsi->tc_cfg.ena_tc); + ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, + max_txqs); + if (ret) { + dev_err(dev, "VSI %d failed lan queue config, error %d\n", + vsi->vsi_num, ret); + return ret; + } + + return 0; +} + +/** + * ice_vsi_cfg_def - configure default VSI based on the type + * @vsi: pointer to VSI + * @params: the parameters to configure this VSI with + */ +static int +ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) +{ + struct device *dev = ice_pf_to_dev(vsi->back); + struct ice_pf *pf = vsi->back; + int ret; + vsi->vsw = pf->first_sw; - if (vsi->type == ICE_VSI_PF) - vsi->ethtype = ETH_P_PAUSE; + + ret = ice_vsi_alloc_def(vsi, params->ch); + if (ret) + return ret; + + /* allocate memory for Tx/Rx ring stat pointers */ + if (ice_vsi_alloc_stat_arrays(vsi)) + goto unroll_vsi_alloc; ice_alloc_fd_res(vsi); - if (vsi_type != ICE_VSI_CHNL) { - if (ice_vsi_get_qs(vsi)) { - dev_err(dev, "Failed to allocate queues. vsi->idx = %d\n", - vsi->idx); - goto unroll_vsi_alloc; - } + if (ice_vsi_get_qs(vsi)) { + dev_err(dev, "Failed to allocate queues. vsi->idx = %d\n", + vsi->idx); + goto unroll_vsi_alloc_stat; } /* set RSS capabilities */ @@ -2698,7 +2710,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, ice_vsi_set_tc_cfg(vsi); /* create the VSI */ - ret = ice_vsi_init(vsi, true); + ret = ice_vsi_init(vsi, params->flags); if (ret) goto unroll_get_qs; @@ -2729,6 +2741,14 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, goto unroll_vector_base; ice_vsi_map_rings_to_vectors(vsi); + if (ice_is_xdp_ena_vsi(vsi)) { + ret = ice_vsi_determine_xdp_res(vsi); + if (ret) + goto unroll_vector_base; + ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog); + if (ret) + goto unroll_vector_base; + } /* ICE_VSI_CTRL does not need RSS so skip RSS processing */ if (vsi->type != ICE_VSI_CTRL) @@ -2793,30 +2813,156 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, goto unroll_vsi_init; } - /* configure VSI nodes based on number of queues and TC's */ - ice_for_each_traffic_class(i) { - if (!(vsi->tc_cfg.ena_tc & BIT(i))) - continue; + return 0; - if (vsi->type == ICE_VSI_CHNL) { - if (!vsi->alloc_txq && vsi->num_txq) - max_txqs[i] = vsi->num_txq; - else - max_txqs[i] = pf->num_lan_tx; +unroll_vector_base: + /* reclaim SW interrupts back to the common pool */ + ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx); + pf->num_avail_sw_msix += vsi->num_q_vectors; +unroll_alloc_q_vector: + ice_vsi_free_q_vectors(vsi); +unroll_vsi_init: + ice_vsi_delete_from_hw(vsi); +unroll_get_qs: + ice_vsi_put_qs(vsi); +unroll_vsi_alloc_stat: + ice_vsi_free_stats(vsi); +unroll_vsi_alloc: + ice_vsi_free_arrays(vsi); + return ret; +} + +/** + * ice_vsi_cfg - configure a previously allocated VSI + * @vsi: pointer to VSI + * @params: parameters used to configure this VSI + */ +int ice_vsi_cfg(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) +{ + struct ice_pf *pf = vsi->back; + int ret; + + if (WARN_ON(params->type == ICE_VSI_VF && !params->vf)) + return -EINVAL; + + vsi->type = params->type; + vsi->port_info = params->pi; + + /* For VSIs which don't have a connected VF, this will be NULL */ + vsi->vf = params->vf; + + ret = ice_vsi_cfg_def(vsi, params); + if (ret) + return ret; + + ret = ice_vsi_cfg_tc_lan(vsi->back, vsi); + if (ret) + ice_vsi_decfg(vsi); + + if (vsi->type == ICE_VSI_CTRL) { + if (vsi->vf) { + WARN_ON(vsi->vf->ctrl_vsi_idx != ICE_NO_VSI); + vsi->vf->ctrl_vsi_idx = vsi->idx; } else { - max_txqs[i] = vsi->alloc_txq; + WARN_ON(pf->ctrl_vsi_idx != ICE_NO_VSI); + pf->ctrl_vsi_idx = vsi->idx; } } - dev_dbg(dev, "vsi->tc_cfg.ena_tc = %d\n", vsi->tc_cfg.ena_tc); - ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, - max_txqs); - if (ret) { - dev_err(dev, "VSI %d failed lan queue config, error %d\n", - vsi->vsi_num, ret); - goto unroll_clear_rings; + return ret; +} + +/** + * ice_vsi_decfg - remove all VSI configuration + * @vsi: pointer to VSI + */ +void ice_vsi_decfg(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + int err; + + /* The Rx rule will only exist to remove if the LLDP FW + * engine is currently stopped + */ + if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF && + !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags)) + ice_cfg_sw_lldp(vsi, false, false); + + ice_fltr_remove_all(vsi); + ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); + err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); + if (err) + dev_err(ice_pf_to_dev(pf), "Failed to remove RDMA scheduler config for VSI %u, err %d\n", + vsi->vsi_num, err); + + if (ice_is_xdp_ena_vsi(vsi)) + /* return value check can be skipped here, it always returns + * 0 if reset is in progress + */ + ice_destroy_xdp_rings(vsi); + + ice_vsi_clear_rings(vsi); + ice_vsi_free_q_vectors(vsi); + ice_vsi_put_qs(vsi); + ice_vsi_free_arrays(vsi); + + /* SR-IOV determines needed MSIX resources all at once instead of per + * VSI since when VFs are spawned we know how many VFs there are and how + * many interrupts each VF needs. SR-IOV MSIX resources are also + * cleared in the same manner. + */ + if (vsi->type == ICE_VSI_CTRL && vsi->vf) { + ice_free_vf_ctrl_res(pf, vsi); + } else if (vsi->type != ICE_VSI_VF) { + /* reclaim SW interrupts back to the common pool */ + ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx); + pf->num_avail_sw_msix += vsi->num_q_vectors; + vsi->base_vector = 0; + } + + if (vsi->type == ICE_VSI_VF && + vsi->agg_node && vsi->agg_node->valid) + vsi->agg_node->num_vsis--; + if (vsi->agg_node) { + vsi->agg_node->valid = false; + vsi->agg_node->agg_id = 0; + } +} + +/** + * ice_vsi_setup - Set up a VSI by a given type + * @pf: board private structure + * @params: parameters to use when creating the VSI + * + * This allocates the sw VSI structure and its queue resources. + * + * Returns pointer to the successfully allocated and configured VSI sw struct on + * success, NULL on failure. + */ +struct ice_vsi * +ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params) +{ + struct device *dev = ice_pf_to_dev(pf); + struct ice_vsi *vsi; + int ret; + + /* ice_vsi_setup can only initialize a new VSI, and we must have + * a port_info structure for it. + */ + if (WARN_ON(!(params->flags & ICE_VSI_FLAG_INIT)) || + WARN_ON(!params->pi)) + return NULL; + + vsi = ice_vsi_alloc(pf); + if (!vsi) { + dev_err(dev, "could not allocate VSI\n"); + return NULL; } + ret = ice_vsi_cfg(vsi, params); + if (ret) + goto err_vsi_cfg; + /* Add switch rule to drop all Tx Flow Control Frames, of look up * type ETHERTYPE from VSIs, and restrict malicious VF from sending * out PAUSE or PFC frames. If enabled, FW can still send FC frames. @@ -2826,34 +2972,21 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, * be dropped so that VFs cannot send LLDP packets to reconfig DCB * settings in the HW. */ - if (!ice_is_safe_mode(pf)) - if (vsi->type == ICE_VSI_PF) { - ice_fltr_add_eth(vsi, ETH_P_PAUSE, ICE_FLTR_TX, - ICE_DROP_PACKET); - ice_cfg_sw_lldp(vsi, true, true); - } + if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF) { + ice_fltr_add_eth(vsi, ETH_P_PAUSE, ICE_FLTR_TX, + ICE_DROP_PACKET); + ice_cfg_sw_lldp(vsi, true, true); + } if (!vsi->agg_node) ice_set_agg_vsi(vsi); + return vsi; -unroll_clear_rings: - ice_vsi_clear_rings(vsi); -unroll_vector_base: - /* reclaim SW interrupts back to the common pool */ - ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx); - pf->num_avail_sw_msix += vsi->num_q_vectors; -unroll_alloc_q_vector: - ice_vsi_free_q_vectors(vsi); -unroll_vsi_init: - ice_vsi_free_stats(vsi); - ice_vsi_delete(vsi); -unroll_get_qs: - ice_vsi_put_qs(vsi); -unroll_vsi_alloc: - if (vsi_type == ICE_VSI_VF) +err_vsi_cfg: + if (params->type == ICE_VSI_VF) ice_enable_lag(pf->lag); - ice_vsi_clear(vsi); + ice_vsi_free(vsi); return NULL; } @@ -3117,37 +3250,6 @@ void ice_napi_del(struct ice_vsi *vsi) } /** - * ice_free_vf_ctrl_res - Free the VF control VSI resource - * @pf: pointer to PF structure - * @vsi: the VSI to free resources for - * - * Check if the VF control VSI resource is still in use. If no VF is using it - * any more, release the VSI resource. Otherwise, leave it to be cleaned up - * once no other VF uses it. - */ -static void ice_free_vf_ctrl_res(struct ice_pf *pf, struct ice_vsi *vsi) -{ - struct ice_vf *vf; - unsigned int bkt; - - rcu_read_lock(); - ice_for_each_vf_rcu(pf, bkt, vf) { - if (vf != vsi->vf && vf->ctrl_vsi_idx != ICE_NO_VSI) { - rcu_read_unlock(); - return; - } - } - rcu_read_unlock(); - - /* No other VFs left that have control VSI. It is now safe to reclaim - * SW interrupts back to the common pool. - */ - ice_free_res(pf->irq_tracker, vsi->base_vector, - ICE_RES_VF_CTRL_VEC_ID); - pf->num_avail_sw_msix += vsi->num_q_vectors; -} - -/** * ice_vsi_release - Delete a VSI and free its resources * @vsi: the VSI being removed * @@ -3156,7 +3258,6 @@ static void ice_free_vf_ctrl_res(struct ice_pf *pf, struct ice_vsi *vsi) int ice_vsi_release(struct ice_vsi *vsi) { struct ice_pf *pf; - int err; if (!vsi->back) return -ENODEV; @@ -3174,50 +3275,14 @@ int ice_vsi_release(struct ice_vsi *vsi) clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); } + if (vsi->type == ICE_VSI_PF) + ice_devlink_destroy_pf_port(pf); + if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) ice_rss_clean(vsi); - /* Disable VSI and free resources */ - if (vsi->type != ICE_VSI_LB) - ice_vsi_dis_irq(vsi); ice_vsi_close(vsi); - - /* SR-IOV determines needed MSIX resources all at once instead of per - * VSI since when VFs are spawned we know how many VFs there are and how - * many interrupts each VF needs. SR-IOV MSIX resources are also - * cleared in the same manner. - */ - if (vsi->type == ICE_VSI_CTRL && vsi->vf) { - ice_free_vf_ctrl_res(pf, vsi); - } else if (vsi->type != ICE_VSI_VF) { - /* reclaim SW interrupts back to the common pool */ - ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx); - pf->num_avail_sw_msix += vsi->num_q_vectors; - } - - if (!ice_is_safe_mode(pf)) { - if (vsi->type == ICE_VSI_PF) { - ice_fltr_remove_eth(vsi, ETH_P_PAUSE, ICE_FLTR_TX, - ICE_DROP_PACKET); - ice_cfg_sw_lldp(vsi, true, false); - /* The Rx rule will only exist to remove if the LLDP FW - * engine is currently stopped - */ - if (!test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags)) - ice_cfg_sw_lldp(vsi, false, false); - } - } - - if (ice_is_vsi_dflt_vsi(vsi)) - ice_clear_dflt_vsi(vsi); - ice_fltr_remove_all(vsi); - ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); - err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); - if (err) - dev_err(ice_pf_to_dev(vsi->back), "Failed to remove RDMA scheduler config for VSI %u, err %d\n", - vsi->vsi_num, err); - ice_vsi_delete(vsi); - ice_vsi_free_q_vectors(vsi); + ice_vsi_decfg(vsi); if (vsi->netdev) { if (test_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state)) { @@ -3231,19 +3296,12 @@ int ice_vsi_release(struct ice_vsi *vsi) } } - if (vsi->type == ICE_VSI_VF && - vsi->agg_node && vsi->agg_node->valid) - vsi->agg_node->num_vsis--; - ice_vsi_clear_rings(vsi); - ice_vsi_free_stats(vsi); - ice_vsi_put_qs(vsi); - /* retain SW VSI data structure since it is needed to unregister and * free VSI netdev when PF is not in reset recovery pending state,\ * for ex: during rmmod. */ if (!ice_is_reset_in_progress(pf->state)) - ice_vsi_clear(vsi); + ice_vsi_delete(vsi); return 0; } @@ -3406,29 +3464,31 @@ ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi, int prev_txq, int prev_rxq) /** * ice_vsi_rebuild - Rebuild VSI after reset * @vsi: VSI to be rebuild - * @init_vsi: is this an initialization or a reconfigure of the VSI + * @vsi_flags: flags used for VSI rebuild flow + * + * Set vsi_flags to ICE_VSI_FLAG_INIT to initialize a new VSI, or + * ICE_VSI_FLAG_NO_INIT to rebuild an existing VSI in hardware. * * Returns 0 on success and negative value on failure */ -int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) +int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags) { - u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; + struct ice_vsi_cfg_params params = {}; struct ice_coalesce_stored *coalesce; - int ret, i, prev_txq, prev_rxq; + int ret, prev_txq, prev_rxq; int prev_num_q_vectors = 0; - enum ice_vsi_type vtype; struct ice_pf *pf; if (!vsi) return -EINVAL; + params = ice_vsi_to_params(vsi); + params.flags = vsi_flags; + pf = vsi->back; - vtype = vsi->type; - if (WARN_ON(vtype == ICE_VSI_VF && !vsi->vf)) + if (WARN_ON(vsi->type == ICE_VSI_VF && !vsi->vf)) return -EINVAL; - ice_vsi_init_vlan_ops(vsi); - coalesce = kcalloc(vsi->num_q_vectors, sizeof(struct ice_coalesce_stored), GFP_KERNEL); if (!coalesce) @@ -3439,188 +3499,33 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) prev_txq = vsi->num_txq; prev_rxq = vsi->num_rxq; - ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); - ret = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); + ice_vsi_decfg(vsi); + ret = ice_vsi_cfg_def(vsi, ¶ms); if (ret) - dev_err(ice_pf_to_dev(vsi->back), "Failed to remove RDMA scheduler config for VSI %u, err %d\n", - vsi->vsi_num, ret); - ice_vsi_free_q_vectors(vsi); - - /* SR-IOV determines needed MSIX resources all at once instead of per - * VSI since when VFs are spawned we know how many VFs there are and how - * many interrupts each VF needs. SR-IOV MSIX resources are also - * cleared in the same manner. - */ - if (vtype != ICE_VSI_VF) { - /* reclaim SW interrupts back to the common pool */ - ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx); - pf->num_avail_sw_msix += vsi->num_q_vectors; - vsi->base_vector = 0; - } - - if (ice_is_xdp_ena_vsi(vsi)) - /* return value check can be skipped here, it always returns - * 0 if reset is in progress - */ - ice_destroy_xdp_rings(vsi); - ice_vsi_put_qs(vsi); - ice_vsi_clear_rings(vsi); - ice_vsi_free_arrays(vsi); - if (vtype == ICE_VSI_VF) - ice_vsi_set_num_qs(vsi, vsi->vf); - else - ice_vsi_set_num_qs(vsi, NULL); - - ret = ice_vsi_alloc_arrays(vsi); - if (ret < 0) - goto err_vsi; - - ice_vsi_get_qs(vsi); - - ice_alloc_fd_res(vsi); - ice_vsi_set_tc_cfg(vsi); - - /* Initialize VSI struct elements and create VSI in FW */ - ret = ice_vsi_init(vsi, init_vsi); - if (ret < 0) - goto err_vsi; - - switch (vtype) { - case ICE_VSI_CTRL: - case ICE_VSI_SWITCHDEV_CTRL: - case ICE_VSI_PF: - ret = ice_vsi_alloc_q_vectors(vsi); - if (ret) - goto err_rings; - - ret = ice_vsi_setup_vector_base(vsi); - if (ret) - goto err_vectors; - - ret = ice_vsi_set_q_vectors_reg_idx(vsi); - if (ret) - goto err_vectors; - - ret = ice_vsi_alloc_rings(vsi); - if (ret) - goto err_vectors; - - ret = ice_vsi_alloc_ring_stats(vsi); - if (ret) - goto err_vectors; - - ice_vsi_map_rings_to_vectors(vsi); - - vsi->stat_offsets_loaded = false; - if (ice_is_xdp_ena_vsi(vsi)) { - ret = ice_vsi_determine_xdp_res(vsi); - if (ret) - goto err_vectors; - ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog); - if (ret) - goto err_vectors; - } - /* ICE_VSI_CTRL does not need RSS so skip RSS processing */ - if (vtype != ICE_VSI_CTRL) - /* Do not exit if configuring RSS had an issue, at - * least receive traffic on first queue. Hence no - * need to capture return value - */ - if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) - ice_vsi_cfg_rss_lut_key(vsi); - - /* disable or enable CRC stripping */ - if (vsi->netdev) - ice_vsi_cfg_crc_strip(vsi, !!(vsi->netdev->features & - NETIF_F_RXFCS)); - - break; - case ICE_VSI_VF: - ret = ice_vsi_alloc_q_vectors(vsi); - if (ret) - goto err_rings; - - ret = ice_vsi_set_q_vectors_reg_idx(vsi); - if (ret) - goto err_vectors; - - ret = ice_vsi_alloc_rings(vsi); - if (ret) - goto err_vectors; - - ret = ice_vsi_alloc_ring_stats(vsi); - if (ret) - goto err_vectors; - - vsi->stat_offsets_loaded = false; - break; - case ICE_VSI_CHNL: - if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { - ice_vsi_cfg_rss_lut_key(vsi); - ice_vsi_set_rss_flow_fld(vsi); - } - break; - default: - break; - } - - /* configure VSI nodes based on number of queues and TC's */ - for (i = 0; i < vsi->tc_cfg.numtc; i++) { - /* configure VSI nodes based on number of queues and TC's. - * ADQ creates VSIs for each TC/Channel but doesn't - * allocate queues instead it reconfigures the PF queues - * as per the TC command. So max_txqs should point to the - * PF Tx queues. - */ - if (vtype == ICE_VSI_CHNL) - max_txqs[i] = pf->num_lan_tx; - else - max_txqs[i] = vsi->alloc_txq; - - if (ice_is_xdp_ena_vsi(vsi)) - max_txqs[i] += vsi->num_xdp_txq; - } - - if (test_bit(ICE_FLAG_TC_MQPRIO, pf->flags)) - /* If MQPRIO is set, means channel code path, hence for main - * VSI's, use TC as 1 - */ - ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, 1, max_txqs); - else - ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, - vsi->tc_cfg.ena_tc, max_txqs); + goto err_vsi_cfg; + ret = ice_vsi_cfg_tc_lan(pf, vsi); if (ret) { - dev_err(ice_pf_to_dev(pf), "VSI %d failed lan queue config, error %d\n", - vsi->vsi_num, ret); - if (init_vsi) { + if (vsi_flags & ICE_VSI_FLAG_INIT) { ret = -EIO; - goto err_vectors; + goto err_vsi_cfg_tc_lan; } else { + kfree(coalesce); return ice_schedule_reset(pf, ICE_RESET_PFR); } } if (ice_vsi_realloc_stat_arrays(vsi, prev_txq, prev_rxq)) - goto err_vectors; + goto err_vsi_cfg_tc_lan; ice_vsi_rebuild_set_coalesce(vsi, coalesce, prev_num_q_vectors); kfree(coalesce); return 0; -err_vectors: - ice_vsi_free_q_vectors(vsi); -err_rings: - if (vsi->netdev) { - vsi->current_netdev_flags = 0; - unregister_netdev(vsi->netdev); - free_netdev(vsi->netdev); - vsi->netdev = NULL; - } -err_vsi: - ice_vsi_clear(vsi); - set_bit(ICE_RESET_FAILED, pf->state); +err_vsi_cfg_tc_lan: + ice_vsi_decfg(vsi); +err_vsi_cfg: kfree(coalesce); return ret; } diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index dcdf69a693e9..75221478f2dc 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -7,6 +7,47 @@ #include "ice.h" #include "ice_vlan.h" +/* Flags used for VSI configuration and rebuild */ +#define ICE_VSI_FLAG_INIT BIT(0) +#define ICE_VSI_FLAG_NO_INIT 0 + +/** + * struct ice_vsi_cfg_params - VSI configuration parameters + * @pi: pointer to the port_info instance for the VSI + * @ch: pointer to the channel structure for the VSI, may be NULL + * @vf: pointer to the VF associated with this VSI, may be NULL + * @type: the type of VSI to configure + * @flags: VSI flags used for rebuild and configuration + * + * Parameter structure used when configuring a new VSI. + */ +struct ice_vsi_cfg_params { + struct ice_port_info *pi; + struct ice_channel *ch; + struct ice_vf *vf; + enum ice_vsi_type type; + u32 flags; +}; + +/** + * ice_vsi_to_params - Get parameters for an existing VSI + * @vsi: the VSI to get parameters for + * + * Fill a parameter structure for reconfiguring a VSI with its current + * parameters, such as during a rebuild operation. + */ +static inline struct ice_vsi_cfg_params ice_vsi_to_params(struct ice_vsi *vsi) +{ + struct ice_vsi_cfg_params params = {}; + + params.pi = vsi->port_info; + params.ch = vsi->ch; + params.vf = vsi->vf; + params.type = vsi->type; + + return params; +} + const char *ice_vsi_type_str(enum ice_vsi_type vsi_type); bool ice_pf_state_is_nominal(struct ice_pf *pf); @@ -42,7 +83,6 @@ void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create); int ice_set_link(struct ice_vsi *vsi, bool ena); void ice_vsi_delete(struct ice_vsi *vsi); -int ice_vsi_clear(struct ice_vsi *vsi); int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc); @@ -51,9 +91,7 @@ int ice_vsi_cfg_rss_lut_key(struct ice_vsi *vsi); void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc); struct ice_vsi * -ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, - enum ice_vsi_type vsi_type, struct ice_vf *vf, - struct ice_channel *ch); +ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params); void ice_napi_del(struct ice_vsi *vsi); @@ -63,6 +101,7 @@ void ice_vsi_close(struct ice_vsi *vsi); int ice_ena_vsi(struct ice_vsi *vsi, bool locked); +void ice_vsi_decfg(struct ice_vsi *vsi); void ice_dis_vsi(struct ice_vsi *vsi, bool locked); int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id); @@ -70,7 +109,8 @@ int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id); int ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id); -int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi); +int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags); +int ice_vsi_cfg(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params); bool ice_is_reset_in_progress(unsigned long *state); int ice_wait_for_reset(struct ice_pf *pf, unsigned long timeout); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 074b0e6d0e2d..0712c1055aea 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -45,7 +45,6 @@ MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all), hw debug_mask (0x8XXXX MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all)"); #endif /* !CONFIG_DYNAMIC_DEBUG */ -static DEFINE_IDA(ice_aux_ida); DEFINE_STATIC_KEY_FALSE(ice_xdp_locking_key); EXPORT_SYMBOL(ice_xdp_locking_key); @@ -539,7 +538,7 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type) /* Disable VFs until reset is completed */ mutex_lock(&pf->vfs.table_lock); ice_for_each_vf(pf, bkt, vf) - ice_set_vf_state_qs_dis(vf); + ice_set_vf_state_dis(vf); mutex_unlock(&pf->vfs.table_lock); if (ice_is_eswitch_mode_switchdev(pf)) { @@ -3440,55 +3439,6 @@ static void ice_set_netdev_features(struct net_device *netdev) } /** - * ice_cfg_netdev - Allocate, configure and register a netdev - * @vsi: the VSI associated with the new netdev - * - * Returns 0 on success, negative value on failure - */ -static int ice_cfg_netdev(struct ice_vsi *vsi) -{ - struct ice_netdev_priv *np; - struct net_device *netdev; - u8 mac_addr[ETH_ALEN]; - - netdev = alloc_etherdev_mqs(sizeof(*np), vsi->alloc_txq, - vsi->alloc_rxq); - if (!netdev) - return -ENOMEM; - - set_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); - vsi->netdev = netdev; - np = netdev_priv(netdev); - np->vsi = vsi; - - ice_set_netdev_features(netdev); - netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | - NETDEV_XDP_ACT_XSK_ZEROCOPY; - - ice_set_ops(netdev); - - if (vsi->type == ICE_VSI_PF) { - SET_NETDEV_DEV(netdev, ice_pf_to_dev(vsi->back)); - ether_addr_copy(mac_addr, vsi->port_info->mac.perm_addr); - eth_hw_addr_set(netdev, mac_addr); - ether_addr_copy(netdev->perm_addr, mac_addr); - } - - netdev->priv_flags |= IFF_UNICAST_FLT; - - /* Setup netdev TC information */ - ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc); - - /* setup watchdog timeout value to be 5 second */ - netdev->watchdog_timeo = 5 * HZ; - - netdev->min_mtu = ETH_MIN_MTU; - netdev->max_mtu = ICE_MAX_MTU; - - return 0; -} - -/** * ice_fill_rss_lut - Fill the RSS lookup table with default values * @lut: Lookup table * @rss_table_size: Lookup table size @@ -3513,14 +3463,27 @@ void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size) static struct ice_vsi * ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) { - return ice_vsi_setup(pf, pi, ICE_VSI_PF, NULL, NULL); + struct ice_vsi_cfg_params params = {}; + + params.type = ICE_VSI_PF; + params.pi = pi; + params.flags = ICE_VSI_FLAG_INIT; + + return ice_vsi_setup(pf, ¶ms); } static struct ice_vsi * ice_chnl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, struct ice_channel *ch) { - return ice_vsi_setup(pf, pi, ICE_VSI_CHNL, NULL, ch); + struct ice_vsi_cfg_params params = {}; + + params.type = ICE_VSI_CHNL; + params.pi = pi; + params.ch = ch; + params.flags = ICE_VSI_FLAG_INIT; + + return ice_vsi_setup(pf, ¶ms); } /** @@ -3534,7 +3497,13 @@ ice_chnl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, static struct ice_vsi * ice_ctrl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) { - return ice_vsi_setup(pf, pi, ICE_VSI_CTRL, NULL, NULL); + struct ice_vsi_cfg_params params = {}; + + params.type = ICE_VSI_CTRL; + params.pi = pi; + params.flags = ICE_VSI_FLAG_INIT; + + return ice_vsi_setup(pf, ¶ms); } /** @@ -3548,7 +3517,13 @@ ice_ctrl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) struct ice_vsi * ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) { - return ice_vsi_setup(pf, pi, ICE_VSI_LB, NULL, NULL); + struct ice_vsi_cfg_params params = {}; + + params.type = ICE_VSI_LB; + params.pi = pi; + params.flags = ICE_VSI_FLAG_INIT; + + return ice_vsi_setup(pf, ¶ms); } /** @@ -3708,20 +3683,6 @@ static void ice_tc_indir_block_unregister(struct ice_vsi *vsi) } /** - * ice_tc_indir_block_remove - clean indirect TC block notifications - * @pf: PF structure - */ -static void ice_tc_indir_block_remove(struct ice_pf *pf) -{ - struct ice_vsi *pf_vsi = ice_get_main_vsi(pf); - - if (!pf_vsi) - return; - - ice_tc_indir_block_unregister(pf_vsi); -} - -/** * ice_tc_indir_block_register - Register TC indirect block notifications * @vsi: VSI struct which has the netdev * @@ -3741,76 +3702,6 @@ static int ice_tc_indir_block_register(struct ice_vsi *vsi) } /** - * ice_setup_pf_sw - Setup the HW switch on startup or after reset - * @pf: board private structure - * - * Returns 0 on success, negative value on failure - */ -static int ice_setup_pf_sw(struct ice_pf *pf) -{ - struct device *dev = ice_pf_to_dev(pf); - bool dvm = ice_is_dvm_ena(&pf->hw); - struct ice_vsi *vsi; - int status; - - if (ice_is_reset_in_progress(pf->state)) - return -EBUSY; - - status = ice_aq_set_port_params(pf->hw.port_info, dvm, NULL); - if (status) - return -EIO; - - vsi = ice_pf_vsi_setup(pf, pf->hw.port_info); - if (!vsi) - return -ENOMEM; - - /* init channel list */ - INIT_LIST_HEAD(&vsi->ch_list); - - status = ice_cfg_netdev(vsi); - if (status) - goto unroll_vsi_setup; - /* netdev has to be configured before setting frame size */ - ice_vsi_cfg_frame_size(vsi); - - /* init indirect block notifications */ - status = ice_tc_indir_block_register(vsi); - if (status) { - dev_err(dev, "Failed to register netdev notifier\n"); - goto unroll_cfg_netdev; - } - - /* Setup DCB netlink interface */ - ice_dcbnl_setup(vsi); - - /* registering the NAPI handler requires both the queues and - * netdev to be created, which are done in ice_pf_vsi_setup() - * and ice_cfg_netdev() respectively - */ - ice_napi_add(vsi); - - status = ice_init_mac_fltr(pf); - if (status) - goto unroll_napi_add; - - return 0; - -unroll_napi_add: - ice_tc_indir_block_unregister(vsi); -unroll_cfg_netdev: - ice_napi_del(vsi); - if (vsi->netdev) { - clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); - free_netdev(vsi->netdev); - vsi->netdev = NULL; - } - -unroll_vsi_setup: - ice_vsi_release(vsi); - return status; -} - -/** * ice_get_avail_q_count - Get count of queues in use * @pf_qmap: bitmap to get queue use count from * @lock: pointer to a mutex that protects access to pf_qmap @@ -4211,12 +4102,13 @@ bool ice_is_wol_supported(struct ice_hw *hw) * @vsi: VSI being changed * @new_rx: new number of Rx queues * @new_tx: new number of Tx queues + * @locked: is adev device_lock held * * Only change the number of queues if new_tx, or new_rx is non-0. * * Returns 0 on success. */ -int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx) +int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked) { struct ice_pf *pf = vsi->back; int err = 0, timeout = 50; @@ -4238,14 +4130,14 @@ int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx) /* set for the next time the netdev is started */ if (!netif_running(vsi->netdev)) { - ice_vsi_rebuild(vsi, false); + ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT); dev_dbg(ice_pf_to_dev(pf), "Link is down, queue count change happens when link is brought up\n"); goto done; } ice_vsi_close(vsi); - ice_vsi_rebuild(vsi, false); - ice_pf_dcb_recfg(pf); + ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT); + ice_pf_dcb_recfg(pf, locked); ice_vsi_open(vsi); done: clear_bit(ICE_CFG_BUSY, pf->state); @@ -4507,6 +4399,23 @@ err_vsi_open: return err; } +static void ice_deinit_fdir(struct ice_pf *pf) +{ + struct ice_vsi *vsi = ice_get_ctrl_vsi(pf); + + if (!vsi) + return; + + ice_vsi_manage_fdir(vsi, false); + ice_vsi_release(vsi); + if (pf->ctrl_vsi_idx != ICE_NO_VSI) { + pf->vsi[pf->ctrl_vsi_idx] = NULL; + pf->ctrl_vsi_idx = ICE_NO_VSI; + } + + mutex_destroy(&(&pf->hw)->fdir_fltr_lock); +} + /** * ice_get_opt_fw_name - return optional firmware file name or NULL * @pf: pointer to the PF instance @@ -4607,116 +4516,173 @@ static void ice_print_wake_reason(struct ice_pf *pf) /** * ice_register_netdev - register netdev - * @pf: pointer to the PF struct + * @vsi: pointer to the VSI struct */ -static int ice_register_netdev(struct ice_pf *pf) +static int ice_register_netdev(struct ice_vsi *vsi) { - struct ice_vsi *vsi; - int err = 0; + int err; - vsi = ice_get_main_vsi(pf); if (!vsi || !vsi->netdev) return -EIO; err = register_netdev(vsi->netdev); if (err) - goto err_register_netdev; + return err; set_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); netif_carrier_off(vsi->netdev); netif_tx_stop_all_queues(vsi->netdev); return 0; -err_register_netdev: - free_netdev(vsi->netdev); - vsi->netdev = NULL; - clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); - return err; +} + +static void ice_unregister_netdev(struct ice_vsi *vsi) +{ + if (!vsi || !vsi->netdev) + return; + + unregister_netdev(vsi->netdev); + clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); } /** - * ice_probe - Device initialization routine - * @pdev: PCI device information struct - * @ent: entry in ice_pci_tbl + * ice_cfg_netdev - Allocate, configure and register a netdev + * @vsi: the VSI associated with the new netdev * - * Returns 0 on success, negative on failure + * Returns 0 on success, negative value on failure */ -static int -ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) +static int ice_cfg_netdev(struct ice_vsi *vsi) { - struct device *dev = &pdev->dev; - struct ice_vsi *vsi; - struct ice_pf *pf; - struct ice_hw *hw; - int i, err; + struct ice_netdev_priv *np; + struct net_device *netdev; + u8 mac_addr[ETH_ALEN]; - if (pdev->is_virtfn) { - dev_err(dev, "can't probe a virtual function\n"); - return -EINVAL; + netdev = alloc_etherdev_mqs(sizeof(*np), vsi->alloc_txq, + vsi->alloc_rxq); + if (!netdev) + return -ENOMEM; + + set_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); + vsi->netdev = netdev; + np = netdev_priv(netdev); + np->vsi = vsi; + + ice_set_netdev_features(netdev); + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_XSK_ZEROCOPY; + ice_set_ops(netdev); + + if (vsi->type == ICE_VSI_PF) { + SET_NETDEV_DEV(netdev, ice_pf_to_dev(vsi->back)); + ether_addr_copy(mac_addr, vsi->port_info->mac.perm_addr); + eth_hw_addr_set(netdev, mac_addr); } - /* this driver uses devres, see - * Documentation/driver-api/driver-model/devres.rst - */ - err = pcim_enable_device(pdev); + netdev->priv_flags |= IFF_UNICAST_FLT; + + /* Setup netdev TC information */ + ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc); + + netdev->max_mtu = ICE_MAX_MTU; + + return 0; +} + +static void ice_decfg_netdev(struct ice_vsi *vsi) +{ + clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); + free_netdev(vsi->netdev); + vsi->netdev = NULL; +} + +static int ice_start_eth(struct ice_vsi *vsi) +{ + int err; + + err = ice_init_mac_fltr(vsi->back); if (err) return err; - err = pcim_iomap_regions(pdev, BIT(ICE_BAR0), dev_driver_string(dev)); - if (err) { - dev_err(dev, "BAR0 I/O map error %d\n", err); - return err; - } + rtnl_lock(); + err = ice_vsi_open(vsi); + rtnl_unlock(); - pf = ice_allocate_pf(dev); - if (!pf) - return -ENOMEM; + return err; +} - /* initialize Auxiliary index to invalid value */ - pf->aux_idx = -1; +static int ice_init_eth(struct ice_pf *pf) +{ + struct ice_vsi *vsi = ice_get_main_vsi(pf); + int err; - /* set up for high or low DMA */ - err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); - if (err) { - dev_err(dev, "DMA configuration failed: 0x%x\n", err); + if (!vsi) + return -EINVAL; + + /* init channel list */ + INIT_LIST_HEAD(&vsi->ch_list); + + err = ice_cfg_netdev(vsi); + if (err) return err; - } + /* Setup DCB netlink interface */ + ice_dcbnl_setup(vsi); - pci_enable_pcie_error_reporting(pdev); - pci_set_master(pdev); + err = ice_init_mac_fltr(pf); + if (err) + goto err_init_mac_fltr; - pf->pdev = pdev; - pci_set_drvdata(pdev, pf); - set_bit(ICE_DOWN, pf->state); - /* Disable service task until DOWN bit is cleared */ - set_bit(ICE_SERVICE_DIS, pf->state); + err = ice_devlink_create_pf_port(pf); + if (err) + goto err_devlink_create_pf_port; - hw = &pf->hw; - hw->hw_addr = pcim_iomap_table(pdev)[ICE_BAR0]; - pci_save_state(pdev); + SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port); - hw->back = pf; - hw->vendor_id = pdev->vendor; - hw->device_id = pdev->device; - pci_read_config_byte(pdev, PCI_REVISION_ID, &hw->revision_id); - hw->subsystem_vendor_id = pdev->subsystem_vendor; - hw->subsystem_device_id = pdev->subsystem_device; - hw->bus.device = PCI_SLOT(pdev->devfn); - hw->bus.func = PCI_FUNC(pdev->devfn); - ice_set_ctrlq_len(hw); + err = ice_register_netdev(vsi); + if (err) + goto err_register_netdev; - pf->msg_enable = netif_msg_init(debug, ICE_DFLT_NETIF_M); + err = ice_tc_indir_block_register(vsi); + if (err) + goto err_tc_indir_block_register; -#ifndef CONFIG_DYNAMIC_DEBUG - if (debug < -1) - hw->debug_mask = debug; -#endif + ice_napi_add(vsi); + + return 0; + +err_tc_indir_block_register: + ice_unregister_netdev(vsi); +err_register_netdev: + ice_devlink_destroy_pf_port(pf); +err_devlink_create_pf_port: +err_init_mac_fltr: + ice_decfg_netdev(vsi); + return err; +} + +static void ice_deinit_eth(struct ice_pf *pf) +{ + struct ice_vsi *vsi = ice_get_main_vsi(pf); + + if (!vsi) + return; + + ice_vsi_close(vsi); + ice_unregister_netdev(vsi); + ice_devlink_destroy_pf_port(pf); + ice_tc_indir_block_unregister(vsi); + ice_decfg_netdev(vsi); +} + +static int ice_init_dev(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw *hw = &pf->hw; + int err; err = ice_init_hw(hw); if (err) { dev_err(dev, "ice_init_hw failed: %d\n", err); - err = -EIO; - goto err_exit_unroll; + return err; } ice_init_feature_support(pf); @@ -4739,62 +4705,31 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) err = ice_init_pf(pf); if (err) { dev_err(dev, "ice_init_pf failed: %d\n", err); - goto err_init_pf_unroll; + goto err_init_pf; } - ice_devlink_init_regions(pf); - pf->hw.udp_tunnel_nic.set_port = ice_udp_tunnel_set_port; pf->hw.udp_tunnel_nic.unset_port = ice_udp_tunnel_unset_port; pf->hw.udp_tunnel_nic.flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP; pf->hw.udp_tunnel_nic.shared = &pf->hw.udp_tunnel_shared; - i = 0; if (pf->hw.tnl.valid_count[TNL_VXLAN]) { - pf->hw.udp_tunnel_nic.tables[i].n_entries = + pf->hw.udp_tunnel_nic.tables[0].n_entries = pf->hw.tnl.valid_count[TNL_VXLAN]; - pf->hw.udp_tunnel_nic.tables[i].tunnel_types = + pf->hw.udp_tunnel_nic.tables[0].tunnel_types = UDP_TUNNEL_TYPE_VXLAN; - i++; } if (pf->hw.tnl.valid_count[TNL_GENEVE]) { - pf->hw.udp_tunnel_nic.tables[i].n_entries = + pf->hw.udp_tunnel_nic.tables[1].n_entries = pf->hw.tnl.valid_count[TNL_GENEVE]; - pf->hw.udp_tunnel_nic.tables[i].tunnel_types = + pf->hw.udp_tunnel_nic.tables[1].tunnel_types = UDP_TUNNEL_TYPE_GENEVE; - i++; - } - - pf->num_alloc_vsi = hw->func_caps.guar_num_vsi; - if (!pf->num_alloc_vsi) { - err = -EIO; - goto err_init_pf_unroll; - } - if (pf->num_alloc_vsi > UDP_TUNNEL_NIC_MAX_SHARING_DEVICES) { - dev_warn(&pf->pdev->dev, - "limiting the VSI count due to UDP tunnel limitation %d > %d\n", - pf->num_alloc_vsi, UDP_TUNNEL_NIC_MAX_SHARING_DEVICES); - pf->num_alloc_vsi = UDP_TUNNEL_NIC_MAX_SHARING_DEVICES; - } - - pf->vsi = devm_kcalloc(dev, pf->num_alloc_vsi, sizeof(*pf->vsi), - GFP_KERNEL); - if (!pf->vsi) { - err = -ENOMEM; - goto err_init_pf_unroll; - } - - pf->vsi_stats = devm_kcalloc(dev, pf->num_alloc_vsi, - sizeof(*pf->vsi_stats), GFP_KERNEL); - if (!pf->vsi_stats) { - err = -ENOMEM; - goto err_init_vsi_unroll; } err = ice_init_interrupt_scheme(pf); if (err) { dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err); err = -EIO; - goto err_init_vsi_stats_unroll; + goto err_init_interrupt_scheme; } /* In case of MSIX we are going to setup the misc vector right here @@ -4805,49 +4740,94 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) err = ice_req_irq_msix_misc(pf); if (err) { dev_err(dev, "setup of misc vector failed: %d\n", err); - goto err_init_interrupt_unroll; + goto err_req_irq_msix_misc; } - /* create switch struct for the switch element created by FW on boot */ - pf->first_sw = devm_kzalloc(dev, sizeof(*pf->first_sw), GFP_KERNEL); - if (!pf->first_sw) { - err = -ENOMEM; - goto err_msix_misc_unroll; - } + return 0; - if (hw->evb_veb) - pf->first_sw->bridge_mode = BRIDGE_MODE_VEB; - else - pf->first_sw->bridge_mode = BRIDGE_MODE_VEPA; +err_req_irq_msix_misc: + ice_clear_interrupt_scheme(pf); +err_init_interrupt_scheme: + ice_deinit_pf(pf); +err_init_pf: + ice_deinit_hw(hw); + return err; +} - pf->first_sw->pf = pf; +static void ice_deinit_dev(struct ice_pf *pf) +{ + ice_free_irq_msix_misc(pf); + ice_clear_interrupt_scheme(pf); + ice_deinit_pf(pf); + ice_deinit_hw(&pf->hw); +} - /* record the sw_id available for later use */ - pf->first_sw->sw_id = hw->port_info->sw_id; +static void ice_init_features(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); - err = ice_setup_pf_sw(pf); - if (err) { - dev_err(dev, "probe failed due to setup PF switch: %d\n", err); - goto err_alloc_sw_unroll; - } + if (ice_is_safe_mode(pf)) + return; - clear_bit(ICE_SERVICE_DIS, pf->state); + /* initialize DDP driven features */ + if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) + ice_ptp_init(pf); - /* tell the firmware we are up */ - err = ice_send_version(pf); - if (err) { - dev_err(dev, "probe failed sending driver version %s. error: %d\n", - UTS_RELEASE, err); - goto err_send_version_unroll; + if (ice_is_feature_supported(pf, ICE_F_GNSS)) + ice_gnss_init(pf); + + /* Note: Flow director init failure is non-fatal to load */ + if (ice_init_fdir(pf)) + dev_err(dev, "could not initialize flow director\n"); + + /* Note: DCB init failure is non-fatal to load */ + if (ice_init_pf_dcb(pf, false)) { + clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); + clear_bit(ICE_FLAG_DCB_ENA, pf->flags); + } else { + ice_cfg_lldp_mib_change(&pf->hw, true); } - /* since everything is good, start the service timer */ - mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period)); + if (ice_init_lag(pf)) + dev_warn(dev, "Failed to init link aggregation support\n"); +} + +static void ice_deinit_features(struct ice_pf *pf) +{ + ice_deinit_lag(pf); + if (test_bit(ICE_FLAG_DCB_CAPABLE, pf->flags)) + ice_cfg_lldp_mib_change(&pf->hw, false); + ice_deinit_fdir(pf); + if (ice_is_feature_supported(pf, ICE_F_GNSS)) + ice_gnss_exit(pf); + if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) + ice_ptp_release(pf); +} + +static void ice_init_wakeup(struct ice_pf *pf) +{ + /* Save wakeup reason register for later use */ + pf->wakeup_reason = rd32(&pf->hw, PFPM_WUS); + + /* check for a power management event */ + ice_print_wake_reason(pf); + + /* clear wake status, all bits */ + wr32(&pf->hw, PFPM_WUS, U32_MAX); + + /* Disable WoL at init, wait for user to enable */ + device_set_wakeup_enable(ice_pf_to_dev(pf), false); +} + +static int ice_init_link(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; err = ice_init_link_events(pf->hw.port_info); if (err) { dev_err(dev, "ice_init_link_events failed: %d\n", err); - goto err_send_version_unroll; + return err; } /* not a fatal error if this fails */ @@ -4883,123 +4863,350 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) set_bit(ICE_FLAG_NO_MEDIA, pf->flags); } - ice_verify_cacheline_size(pf); + return err; +} - /* Save wakeup reason register for later use */ - pf->wakeup_reason = rd32(hw, PFPM_WUS); +static int ice_init_pf_sw(struct ice_pf *pf) +{ + bool dvm = ice_is_dvm_ena(&pf->hw); + struct ice_vsi *vsi; + int err; - /* check for a power management event */ - ice_print_wake_reason(pf); + /* create switch struct for the switch element created by FW on boot */ + pf->first_sw = kzalloc(sizeof(*pf->first_sw), GFP_KERNEL); + if (!pf->first_sw) + return -ENOMEM; - /* clear wake status, all bits */ - wr32(hw, PFPM_WUS, U32_MAX); + if (pf->hw.evb_veb) + pf->first_sw->bridge_mode = BRIDGE_MODE_VEB; + else + pf->first_sw->bridge_mode = BRIDGE_MODE_VEPA; - /* Disable WoL at init, wait for user to enable */ - device_set_wakeup_enable(dev, false); + pf->first_sw->pf = pf; - if (ice_is_safe_mode(pf)) { - ice_set_safe_mode_vlan_cfg(pf); - goto probe_done; + /* record the sw_id available for later use */ + pf->first_sw->sw_id = pf->hw.port_info->sw_id; + + err = ice_aq_set_port_params(pf->hw.port_info, dvm, NULL); + if (err) + goto err_aq_set_port_params; + + vsi = ice_pf_vsi_setup(pf, pf->hw.port_info); + if (!vsi) { + err = -ENOMEM; + goto err_pf_vsi_setup; } - /* initialize DDP driven features */ - if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) - ice_ptp_init(pf); + return 0; - if (ice_is_feature_supported(pf, ICE_F_GNSS)) - ice_gnss_init(pf); +err_pf_vsi_setup: +err_aq_set_port_params: + kfree(pf->first_sw); + return err; +} - /* Note: Flow director init failure is non-fatal to load */ - if (ice_init_fdir(pf)) - dev_err(dev, "could not initialize flow director\n"); +static void ice_deinit_pf_sw(struct ice_pf *pf) +{ + struct ice_vsi *vsi = ice_get_main_vsi(pf); - /* Note: DCB init failure is non-fatal to load */ - if (ice_init_pf_dcb(pf, false)) { - clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); - clear_bit(ICE_FLAG_DCB_ENA, pf->flags); - } else { - ice_cfg_lldp_mib_change(&pf->hw, true); + if (!vsi) + return; + + ice_vsi_release(vsi); + kfree(pf->first_sw); +} + +static int ice_alloc_vsis(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + + pf->num_alloc_vsi = pf->hw.func_caps.guar_num_vsi; + if (!pf->num_alloc_vsi) + return -EIO; + + if (pf->num_alloc_vsi > UDP_TUNNEL_NIC_MAX_SHARING_DEVICES) { + dev_warn(dev, + "limiting the VSI count due to UDP tunnel limitation %d > %d\n", + pf->num_alloc_vsi, UDP_TUNNEL_NIC_MAX_SHARING_DEVICES); + pf->num_alloc_vsi = UDP_TUNNEL_NIC_MAX_SHARING_DEVICES; } - if (ice_init_lag(pf)) - dev_warn(dev, "Failed to init link aggregation support\n"); + pf->vsi = devm_kcalloc(dev, pf->num_alloc_vsi, sizeof(*pf->vsi), + GFP_KERNEL); + if (!pf->vsi) + return -ENOMEM; - /* print PCI link speed and width */ - pcie_print_link_status(pf->pdev); + pf->vsi_stats = devm_kcalloc(dev, pf->num_alloc_vsi, + sizeof(*pf->vsi_stats), GFP_KERNEL); + if (!pf->vsi_stats) { + devm_kfree(dev, pf->vsi); + return -ENOMEM; + } -probe_done: - err = ice_devlink_create_pf_port(pf); + return 0; +} + +static void ice_dealloc_vsis(struct ice_pf *pf) +{ + devm_kfree(ice_pf_to_dev(pf), pf->vsi_stats); + pf->vsi_stats = NULL; + + pf->num_alloc_vsi = 0; + devm_kfree(ice_pf_to_dev(pf), pf->vsi); + pf->vsi = NULL; +} + +static int ice_init_devlink(struct ice_pf *pf) +{ + int err; + + err = ice_devlink_register_params(pf); if (err) - goto err_create_pf_port; + return err; - vsi = ice_get_main_vsi(pf); - if (!vsi || !vsi->netdev) { - err = -EINVAL; - goto err_netdev_reg; - } + ice_devlink_init_regions(pf); + ice_devlink_register(pf); - SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port); + return 0; +} - err = ice_register_netdev(pf); +static void ice_deinit_devlink(struct ice_pf *pf) +{ + ice_devlink_unregister(pf); + ice_devlink_destroy_regions(pf); + ice_devlink_unregister_params(pf); +} + +static int ice_init(struct ice_pf *pf) +{ + int err; + + err = ice_init_dev(pf); if (err) - goto err_netdev_reg; + return err; - err = ice_devlink_register_params(pf); + err = ice_alloc_vsis(pf); if (err) - goto err_netdev_reg; + goto err_alloc_vsis; + + err = ice_init_pf_sw(pf); + if (err) + goto err_init_pf_sw; + + ice_init_wakeup(pf); + + err = ice_init_link(pf); + if (err) + goto err_init_link; + + err = ice_send_version(pf); + if (err) + goto err_init_link; + + ice_verify_cacheline_size(pf); + + if (ice_is_safe_mode(pf)) + ice_set_safe_mode_vlan_cfg(pf); + else + /* print PCI link speed and width */ + pcie_print_link_status(pf->pdev); /* ready to go, so clear down state bit */ clear_bit(ICE_DOWN, pf->state); - if (ice_is_rdma_ena(pf)) { - pf->aux_idx = ida_alloc(&ice_aux_ida, GFP_KERNEL); - if (pf->aux_idx < 0) { - dev_err(dev, "Failed to allocate device ID for AUX driver\n"); - err = -ENOMEM; - goto err_devlink_reg_param; - } + clear_bit(ICE_SERVICE_DIS, pf->state); - err = ice_init_rdma(pf); - if (err) { - dev_err(dev, "Failed to initialize RDMA: %d\n", err); - err = -EIO; - goto err_init_aux_unroll; - } - } else { - dev_warn(dev, "RDMA is not supported on this device\n"); - } + /* since everything is good, start the service timer */ + mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period)); - ice_devlink_register(pf); return 0; -err_init_aux_unroll: - pf->adev = NULL; - ida_free(&ice_aux_ida, pf->aux_idx); -err_devlink_reg_param: - ice_devlink_unregister_params(pf); -err_netdev_reg: - ice_devlink_destroy_pf_port(pf); -err_create_pf_port: -err_send_version_unroll: - ice_vsi_release_all(pf); -err_alloc_sw_unroll: +err_init_link: + ice_deinit_pf_sw(pf); +err_init_pf_sw: + ice_dealloc_vsis(pf); +err_alloc_vsis: + ice_deinit_dev(pf); + return err; +} + +static void ice_deinit(struct ice_pf *pf) +{ set_bit(ICE_SERVICE_DIS, pf->state); set_bit(ICE_DOWN, pf->state); - devm_kfree(dev, pf->first_sw); -err_msix_misc_unroll: - ice_free_irq_msix_misc(pf); -err_init_interrupt_unroll: - ice_clear_interrupt_scheme(pf); -err_init_vsi_stats_unroll: - devm_kfree(dev, pf->vsi_stats); - pf->vsi_stats = NULL; -err_init_vsi_unroll: - devm_kfree(dev, pf->vsi); -err_init_pf_unroll: - ice_deinit_pf(pf); - ice_devlink_destroy_regions(pf); - ice_deinit_hw(hw); -err_exit_unroll: - pci_disable_pcie_error_reporting(pdev); + + ice_deinit_pf_sw(pf); + ice_dealloc_vsis(pf); + ice_deinit_dev(pf); +} + +/** + * ice_load - load pf by init hw and starting VSI + * @pf: pointer to the pf instance + */ +int ice_load(struct ice_pf *pf) +{ + struct ice_vsi_cfg_params params = {}; + struct ice_vsi *vsi; + int err; + + err = ice_reset(&pf->hw, ICE_RESET_PFR); + if (err) + return err; + + err = ice_init_dev(pf); + if (err) + return err; + + vsi = ice_get_main_vsi(pf); + + params = ice_vsi_to_params(vsi); + params.flags = ICE_VSI_FLAG_INIT; + + err = ice_vsi_cfg(vsi, ¶ms); + if (err) + goto err_vsi_cfg; + + err = ice_start_eth(ice_get_main_vsi(pf)); + if (err) + goto err_start_eth; + + err = ice_init_rdma(pf); + if (err) + goto err_init_rdma; + + ice_init_features(pf); + ice_service_task_restart(pf); + + clear_bit(ICE_DOWN, pf->state); + + return 0; + +err_init_rdma: + ice_vsi_close(ice_get_main_vsi(pf)); +err_start_eth: + ice_vsi_decfg(ice_get_main_vsi(pf)); +err_vsi_cfg: + ice_deinit_dev(pf); + return err; +} + +/** + * ice_unload - unload pf by stopping VSI and deinit hw + * @pf: pointer to the pf instance + */ +void ice_unload(struct ice_pf *pf) +{ + ice_deinit_features(pf); + ice_deinit_rdma(pf); + ice_vsi_close(ice_get_main_vsi(pf)); + ice_vsi_decfg(ice_get_main_vsi(pf)); + ice_deinit_dev(pf); +} + +/** + * ice_probe - Device initialization routine + * @pdev: PCI device information struct + * @ent: entry in ice_pci_tbl + * + * Returns 0 on success, negative on failure + */ +static int +ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) +{ + struct device *dev = &pdev->dev; + struct ice_pf *pf; + struct ice_hw *hw; + int err; + + if (pdev->is_virtfn) { + dev_err(dev, "can't probe a virtual function\n"); + return -EINVAL; + } + + /* this driver uses devres, see + * Documentation/driver-api/driver-model/devres.rst + */ + err = pcim_enable_device(pdev); + if (err) + return err; + + err = pcim_iomap_regions(pdev, BIT(ICE_BAR0), dev_driver_string(dev)); + if (err) { + dev_err(dev, "BAR0 I/O map error %d\n", err); + return err; + } + + pf = ice_allocate_pf(dev); + if (!pf) + return -ENOMEM; + + /* initialize Auxiliary index to invalid value */ + pf->aux_idx = -1; + + /* set up for high or low DMA */ + err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); + if (err) { + dev_err(dev, "DMA configuration failed: 0x%x\n", err); + return err; + } + + pci_set_master(pdev); + + pf->pdev = pdev; + pci_set_drvdata(pdev, pf); + set_bit(ICE_DOWN, pf->state); + /* Disable service task until DOWN bit is cleared */ + set_bit(ICE_SERVICE_DIS, pf->state); + + hw = &pf->hw; + hw->hw_addr = pcim_iomap_table(pdev)[ICE_BAR0]; + pci_save_state(pdev); + + hw->back = pf; + hw->port_info = NULL; + hw->vendor_id = pdev->vendor; + hw->device_id = pdev->device; + pci_read_config_byte(pdev, PCI_REVISION_ID, &hw->revision_id); + hw->subsystem_vendor_id = pdev->subsystem_vendor; + hw->subsystem_device_id = pdev->subsystem_device; + hw->bus.device = PCI_SLOT(pdev->devfn); + hw->bus.func = PCI_FUNC(pdev->devfn); + ice_set_ctrlq_len(hw); + + pf->msg_enable = netif_msg_init(debug, ICE_DFLT_NETIF_M); + +#ifndef CONFIG_DYNAMIC_DEBUG + if (debug < -1) + hw->debug_mask = debug; +#endif + + err = ice_init(pf); + if (err) + goto err_init; + + err = ice_init_eth(pf); + if (err) + goto err_init_eth; + + err = ice_init_rdma(pf); + if (err) + goto err_init_rdma; + + err = ice_init_devlink(pf); + if (err) + goto err_init_devlink; + + ice_init_features(pf); + + return 0; + +err_init_devlink: + ice_deinit_rdma(pf); +err_init_rdma: + ice_deinit_eth(pf); +err_init_eth: + ice_deinit(pf); +err_init: pci_disable_device(pdev); return err; } @@ -5072,66 +5279,42 @@ static void ice_setup_mc_magic_wake(struct ice_pf *pf) static void ice_remove(struct pci_dev *pdev) { struct ice_pf *pf = pci_get_drvdata(pdev); - struct ice_hw *hw; int i; - hw = &pf->hw; - - ice_devlink_unregister(pf); for (i = 0; i < ICE_MAX_RESET_WAIT; i++) { if (!ice_is_reset_in_progress(pf->state)) break; msleep(100); } - ice_tc_indir_block_remove(pf); - if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) { set_bit(ICE_VF_RESETS_DISABLED, pf->state); ice_free_vfs(pf); } ice_service_task_stop(pf); - ice_aq_cancel_waiting_tasks(pf); - ice_unplug_aux_dev(pf); - if (pf->aux_idx >= 0) - ida_free(&ice_aux_ida, pf->aux_idx); - ice_devlink_unregister_params(pf); set_bit(ICE_DOWN, pf->state); - ice_deinit_lag(pf); - if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) - ice_ptp_release(pf); - if (ice_is_feature_supported(pf, ICE_F_GNSS)) - ice_gnss_exit(pf); if (!ice_is_safe_mode(pf)) ice_remove_arfs(pf); - ice_setup_mc_magic_wake(pf); + ice_deinit_features(pf); + ice_deinit_devlink(pf); + ice_deinit_rdma(pf); + ice_deinit_eth(pf); + ice_deinit(pf); + ice_vsi_release_all(pf); - mutex_destroy(&hw->fdir_fltr_lock); - ice_devlink_destroy_pf_port(pf); + + ice_setup_mc_magic_wake(pf); ice_set_wake(pf); - ice_free_irq_msix_misc(pf); - ice_for_each_vsi(pf, i) { - if (!pf->vsi[i]) - continue; - ice_vsi_free_q_vectors(pf->vsi[i]); - } - devm_kfree(&pdev->dev, pf->vsi_stats); - pf->vsi_stats = NULL; - ice_deinit_pf(pf); - ice_devlink_destroy_regions(pf); - ice_deinit_hw(hw); /* Issue a PFR as part of the prescribed driver unload flow. Do not * do it via ice_schedule_reset() since there is no need to rebuild * and the service task is already stopped. */ - ice_reset(hw, ICE_RESET_PFR); + ice_reset(&pf->hw, ICE_RESET_PFR); pci_wait_for_pending_transaction(pdev); - ice_clear_interrupt_scheme(pf); - pci_disable_pcie_error_reporting(pdev); pci_disable_device(pdev); } @@ -5559,7 +5742,7 @@ static int __init ice_module_init(void) pr_info("%s\n", ice_driver_string); pr_info("%s\n", ice_copyright); - ice_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, KBUILD_MODNAME); + ice_wq = alloc_workqueue("%s", 0, 0, KBUILD_MODNAME); if (!ice_wq) { pr_err("Failed to create workqueue\n"); return -ENOMEM; @@ -6165,12 +6348,12 @@ static int ice_vsi_vlan_setup(struct ice_vsi *vsi) } /** - * ice_vsi_cfg - Setup the VSI + * ice_vsi_cfg_lan - Setup the VSI lan related config * @vsi: the VSI being configured * * Return 0 on success and negative value on error */ -int ice_vsi_cfg(struct ice_vsi *vsi) +int ice_vsi_cfg_lan(struct ice_vsi *vsi) { int err; @@ -6386,7 +6569,7 @@ int ice_up(struct ice_vsi *vsi) { int err; - err = ice_vsi_cfg(vsi); + err = ice_vsi_cfg_lan(vsi); if (!err) err = ice_up_complete(vsi); @@ -6954,7 +7137,7 @@ int ice_vsi_open_ctrl(struct ice_vsi *vsi) if (err) goto err_setup_rx; - err = ice_vsi_cfg(vsi); + err = ice_vsi_cfg_lan(vsi); if (err) goto err_setup_rx; @@ -7008,7 +7191,7 @@ int ice_vsi_open(struct ice_vsi *vsi) if (err) goto err_setup_rx; - err = ice_vsi_cfg(vsi); + err = ice_vsi_cfg_lan(vsi); if (err) goto err_setup_rx; @@ -7093,7 +7276,7 @@ static int ice_vsi_rebuild_by_type(struct ice_pf *pf, enum ice_vsi_type type) continue; /* rebuild the VSI */ - err = ice_vsi_rebuild(vsi, true); + err = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_INIT); if (err) { dev_err(dev, "rebuild VSI failed, err %d, VSI index %d, type %s\n", err, vsi->idx, ice_vsi_type_str(type)); @@ -8434,12 +8617,9 @@ static void ice_remove_q_channels(struct ice_vsi *vsi, bool rem_fltr) /* clear the VSI from scheduler tree */ ice_rm_vsi_lan_cfg(ch->ch_vsi->port_info, ch->ch_vsi->idx); - /* Delete VSI from FW */ + /* Delete VSI from FW, PF and HW VSI arrays */ ice_vsi_delete(ch->ch_vsi); - /* Delete VSI from PF and HW VSI arrays */ - ice_vsi_clear(ch->ch_vsi); - /* free the channel */ kfree(ch); } @@ -8498,7 +8678,7 @@ static int ice_rebuild_channels(struct ice_pf *pf) type = vsi->type; /* rebuild ADQ VSI */ - err = ice_vsi_rebuild(vsi, true); + err = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_INIT); if (err) { dev_err(dev, "VSI (type:%s) at index %d rebuild failed, err %d\n", ice_vsi_type_str(type), vsi->idx, err); @@ -8730,14 +8910,14 @@ config_tcf: cur_rxq = vsi->num_rxq; /* proceed with rebuild main VSI using correct number of queues */ - ret = ice_vsi_rebuild(vsi, false); + ret = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT); if (ret) { /* fallback to current number of queues */ dev_info(dev, "Rebuild failed with new queues, try with current number of queues\n"); vsi->req_txq = cur_txq; vsi->req_rxq = cur_rxq; clear_bit(ICE_RESET_FAILED, pf->state); - if (ice_vsi_rebuild(vsi, false)) { + if (ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT)) { dev_err(dev, "Rebuild of main VSI failed again\n"); return ret; } diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 3ba1408c56a9..96a64c25e2ef 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -41,21 +41,6 @@ static void ice_free_vf_entries(struct ice_pf *pf) } /** - * ice_vf_vsi_release - invalidate the VF's VSI after freeing it - * @vf: invalidate this VF's VSI after freeing it - */ -static void ice_vf_vsi_release(struct ice_vf *vf) -{ - struct ice_vsi *vsi = ice_get_vf_vsi(vf); - - if (WARN_ON(!vsi)) - return; - - ice_vsi_release(vsi); - ice_vf_invalidate_vsi(vf); -} - -/** * ice_free_vf_res - Free a VF's resources * @vf: pointer to the VF info */ @@ -248,11 +233,16 @@ void ice_free_vfs(struct ice_pf *pf) */ static struct ice_vsi *ice_vf_vsi_setup(struct ice_vf *vf) { - struct ice_port_info *pi = ice_vf_get_port_info(vf); + struct ice_vsi_cfg_params params = {}; struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; - vsi = ice_vsi_setup(pf, pi, ICE_VSI_VF, vf, NULL); + params.type = ICE_VSI_VF; + params.pi = ice_vf_get_port_info(vf); + params.vf = vf; + params.flags = ICE_VSI_FLAG_INIT; + + vsi = ice_vsi_setup(pf, ¶ms); if (!vsi) { dev_err(ice_pf_to_dev(pf), "Failed to create VF VSI\n"); @@ -583,51 +573,19 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs) */ static int ice_init_vf_vsi_res(struct ice_vf *vf) { - struct ice_vsi_vlan_ops *vlan_ops; struct ice_pf *pf = vf->pf; - u8 broadcast[ETH_ALEN]; struct ice_vsi *vsi; - struct device *dev; int err; vf->first_vector_idx = ice_calc_vf_first_vector_idx(pf, vf); - dev = ice_pf_to_dev(pf); vsi = ice_vf_vsi_setup(vf); if (!vsi) return -ENOMEM; - err = ice_vsi_add_vlan_zero(vsi); - if (err) { - dev_warn(dev, "Failed to add VLAN 0 filter for VF %d\n", - vf->vf_id); - goto release_vsi; - } - - vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); - err = vlan_ops->ena_rx_filtering(vsi); - if (err) { - dev_warn(dev, "Failed to enable Rx VLAN filtering for VF %d\n", - vf->vf_id); - goto release_vsi; - } - - eth_broadcast_addr(broadcast); - err = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI); - if (err) { - dev_err(dev, "Failed to add broadcast MAC filter for VF %d, error %d\n", - vf->vf_id, err); - goto release_vsi; - } - - err = ice_vsi_apply_spoofchk(vsi, vf->spoofchk); - if (err) { - dev_warn(dev, "Failed to initialize spoofchk setting for VF %d\n", - vf->vf_id); + err = ice_vf_init_host_cfg(vf, vsi); + if (err) goto release_vsi; - } - - vf->num_mac = 1; return 0; @@ -697,6 +655,21 @@ static void ice_sriov_free_vf(struct ice_vf *vf) } /** + * ice_sriov_clear_reset_state - clears VF Reset status register + * @vf: the vf to configure + */ +static void ice_sriov_clear_reset_state(struct ice_vf *vf) +{ + struct ice_hw *hw = &vf->pf->hw; + + /* Clear the reset status register so that VF immediately sees that + * the device is resetting, even if hardware hasn't yet gotten around + * to clearing VFGEN_RSTAT for us. + */ + wr32(hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_INPROGRESS); +} + +/** * ice_sriov_clear_mbx_register - clears SRIOV VF's mailbox registers * @vf: the vf to configure */ @@ -799,23 +772,19 @@ static void ice_sriov_clear_reset_trigger(struct ice_vf *vf) } /** - * ice_sriov_vsi_rebuild - release and rebuild VF's VSI - * @vf: VF to release and setup the VSI for + * ice_sriov_create_vsi - Create a new VSI for a VF + * @vf: VF to create the VSI for * - * This is only called when a single VF is being reset (i.e. VFR, VFLR, host VF - * configuration change, etc.). + * This is called by ice_vf_recreate_vsi to create the new VSI after the old + * VSI has been released. */ -static int ice_sriov_vsi_rebuild(struct ice_vf *vf) +static int ice_sriov_create_vsi(struct ice_vf *vf) { - struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; - ice_vf_vsi_release(vf); - if (!ice_vf_vsi_setup(vf)) { - dev_err(ice_pf_to_dev(pf), - "Failed to release and setup the VF%u's VSI\n", - vf->vf_id); + vsi = ice_vf_vsi_setup(vf); + if (!vsi) return -ENOMEM; - } return 0; } @@ -826,8 +795,6 @@ static int ice_sriov_vsi_rebuild(struct ice_vf *vf) */ static void ice_sriov_post_vsi_rebuild(struct ice_vf *vf) { - ice_vf_rebuild_host_cfg(vf); - ice_vf_set_initialized(vf); ice_ena_vf_mappings(vf); wr32(&vf->pf->hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_VFACTIVE); } @@ -835,11 +802,13 @@ static void ice_sriov_post_vsi_rebuild(struct ice_vf *vf) static const struct ice_vf_ops ice_sriov_vf_ops = { .reset_type = ICE_VF_RESET, .free = ice_sriov_free_vf, + .clear_reset_state = ice_sriov_clear_reset_state, .clear_mbx_register = ice_sriov_clear_mbx_register, .trigger_reset_register = ice_sriov_trigger_reset_register, .poll_reset_status = ice_sriov_poll_reset_status, .clear_reset_trigger = ice_sriov_clear_reset_trigger, - .vsi_rebuild = ice_sriov_vsi_rebuild, + .irq_close = NULL, + .create_vsi = ice_sriov_create_vsi, .post_vsi_rebuild = ice_sriov_post_vsi_rebuild, }; @@ -879,21 +848,9 @@ static int ice_create_vf_entries(struct ice_pf *pf, u16 num_vfs) /* set sriov vf ops for VFs created during SRIOV flow */ vf->vf_ops = &ice_sriov_vf_ops; - vf->vf_sw_id = pf->first_sw; - /* assign default capabilities */ - vf->spoofchk = true; - vf->num_vf_qs = pf->vfs.num_qps_per; - ice_vc_set_default_allowlist(vf); - - /* ctrl_vsi_idx will be set to a valid value only when VF - * creates its first fdir rule. - */ - ice_vf_ctrl_invalidate_vsi(vf); - ice_vf_fdir_init(vf); - - ice_virtchnl_set_dflt_ops(vf); + ice_initialize_vf_entry(vf); - mutex_init(&vf->cfg_lock); + vf->vf_sw_id = pf->first_sw; hash_add_rcu(vfs->table, &vf->entry, vf_id); } @@ -1285,7 +1242,7 @@ ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi) goto out_put_vf; ivi->vf = vf_id; - ether_addr_copy(ivi->mac, vf->hw_lan_addr.addr); + ether_addr_copy(ivi->mac, vf->hw_lan_addr); /* VF configuration for VLAN and applicable QoS */ ivi->vlan = ice_vf_get_port_vlan_id(vf); @@ -1333,8 +1290,8 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) return -EINVAL; /* nothing left to do, unicast MAC already set */ - if (ether_addr_equal(vf->dev_lan_addr.addr, mac) && - ether_addr_equal(vf->hw_lan_addr.addr, mac)) { + if (ether_addr_equal(vf->dev_lan_addr, mac) && + ether_addr_equal(vf->hw_lan_addr, mac)) { ret = 0; goto out_put_vf; } @@ -1348,8 +1305,8 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) /* VF is notified of its new MAC via the PF's response to the * VIRTCHNL_OP_GET_VF_RESOURCES message after the VF has been reset */ - ether_addr_copy(vf->dev_lan_addr.addr, mac); - ether_addr_copy(vf->hw_lan_addr.addr, mac); + ether_addr_copy(vf->dev_lan_addr, mac); + ether_addr_copy(vf->hw_lan_addr, mac); if (is_zero_ether_addr(mac)) { /* VF will send VIRTCHNL_OP_ADD_ETH_ADDR message with its MAC */ vf->pf_set_mac = false; @@ -1750,7 +1707,7 @@ void ice_print_vf_rx_mdd_event(struct ice_vf *vf) dev_info(dev, "%d Rx Malicious Driver Detection events detected on PF %d VF %d MAC %pM. mdd-auto-reset-vfs=%s\n", vf->mdd_rx_events.count, pf->hw.pf_id, vf->vf_id, - vf->dev_lan_addr.addr, + vf->dev_lan_addr, test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags) ? "on" : "off"); } @@ -1794,7 +1751,7 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf) dev_info(dev, "%d Tx Malicious Driver Detection events detected on PF %d VF %d MAC %pM.\n", vf->mdd_tx_events.count, hw->pf_id, vf->vf_id, - vf->dev_lan_addr.addr); + vf->dev_lan_addr); } } mutex_unlock(&pf->vfs.table_lock); @@ -1884,7 +1841,7 @@ ice_is_malicious_vf(struct ice_pf *pf, struct ice_rq_event_info *event, if (pf_vsi) dev_warn(dev, "VF MAC %pM on PF MAC %pM is generating asynchronous messages and may be overflowing the PF message queue. Please see the Adapter User Guide for more information\n", - &vf->dev_lan_addr.addr[0], + &vf->dev_lan_addr[0], pf_vsi->netdev->dev_addr); } } diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 9b762f7972ce..61f844d22512 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -5420,7 +5420,7 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, */ status = ice_add_special_words(rinfo, lkup_exts, ice_is_dvm_ena(hw)); if (status) - goto err_free_lkup_exts; + goto err_unroll; /* Group match words into recipes using preferred recipe grouping * criteria. diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index 80706f7330f4..6b48cbc049c6 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -1688,7 +1688,7 @@ ice_tc_forward_to_queue(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr, struct ice_vsi *ch_vsi = NULL; u16 queue = act->rx_queue; - if (queue > vsi->num_rxq) { + if (queue >= vsi->num_rxq) { NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because specified queue is invalid"); return -EINVAL; diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 375eb6493f0f..0e57bd1b85fd 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -237,16 +237,49 @@ static void ice_vf_clear_counters(struct ice_vf *vf) */ static void ice_vf_pre_vsi_rebuild(struct ice_vf *vf) { + /* Close any IRQ mapping now */ + if (vf->vf_ops->irq_close) + vf->vf_ops->irq_close(vf); + ice_vf_clear_counters(vf); vf->vf_ops->clear_reset_trigger(vf); } /** + * ice_vf_recreate_vsi - Release and re-create the VF's VSI + * @vf: VF to recreate the VSI for + * + * This is only called when a single VF is being reset (i.e. VVF, VFLR, host + * VF configuration change, etc) + * + * It releases and then re-creates a new VSI. + */ +static int ice_vf_recreate_vsi(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + int err; + + ice_vf_vsi_release(vf); + + err = vf->vf_ops->create_vsi(vf); + if (err) { + dev_err(ice_pf_to_dev(pf), + "Failed to recreate the VF%u's VSI, error %d\n", + vf->vf_id, err); + return err; + } + + return 0; +} + +/** * ice_vf_rebuild_vsi - rebuild the VF's VSI * @vf: VF to rebuild the VSI for * * This is only called when all VF(s) are being reset (i.e. PCIe Reset on the * host, PFR, CORER, etc.). + * + * It reprograms the VSI configuration back into hardware. */ static int ice_vf_rebuild_vsi(struct ice_vf *vf) { @@ -256,7 +289,7 @@ static int ice_vf_rebuild_vsi(struct ice_vf *vf) if (WARN_ON(!vsi)) return -EINVAL; - if (ice_vsi_rebuild(vsi, true)) { + if (ice_vsi_rebuild(vsi, ICE_VSI_FLAG_INIT)) { dev_err(ice_pf_to_dev(pf), "failed to rebuild VF %d VSI\n", vf->vf_id); return -EIO; @@ -271,6 +304,21 @@ static int ice_vf_rebuild_vsi(struct ice_vf *vf) } /** + * ice_vf_post_vsi_rebuild - Reset tasks that occur after VSI rebuild + * @vf: the VF being reset + * + * Perform reset tasks which must occur after the VSI has been re-created or + * rebuilt during a VF reset. + */ +static void ice_vf_post_vsi_rebuild(struct ice_vf *vf) +{ + ice_vf_rebuild_host_cfg(vf); + ice_vf_set_initialized(vf); + + vf->vf_ops->post_vsi_rebuild(vf); +} + +/** * ice_is_any_vf_in_unicast_promisc - check if any VF(s) * are in unicast promiscuous mode * @pf: PF structure for accessing VF(s) @@ -495,7 +543,7 @@ void ice_reset_all_vfs(struct ice_pf *pf) ice_vf_pre_vsi_rebuild(vf); ice_vf_rebuild_vsi(vf); - vf->vf_ops->post_vsi_rebuild(vf); + ice_vf_post_vsi_rebuild(vf); mutex_unlock(&vf->cfg_lock); } @@ -639,14 +687,14 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) ice_vf_pre_vsi_rebuild(vf); - if (vf->vf_ops->vsi_rebuild(vf)) { + if (ice_vf_recreate_vsi(vf)) { dev_err(dev, "Failed to release and setup the VF%u's VSI\n", vf->vf_id); err = -EFAULT; goto out_unlock; } - vf->vf_ops->post_vsi_rebuild(vf); + ice_vf_post_vsi_rebuild(vf); vsi = ice_get_vf_vsi(vf); if (WARN_ON(!vsi)) { err = -EINVAL; @@ -673,7 +721,7 @@ out_unlock: * ice_set_vf_state_qs_dis - Set VF queues state to disabled * @vf: pointer to the VF structure */ -void ice_set_vf_state_qs_dis(struct ice_vf *vf) +static void ice_set_vf_state_qs_dis(struct ice_vf *vf) { /* Clear Rx/Tx enabled queues flag */ bitmap_zero(vf->txq_ena, ICE_MAX_RSS_QS_PER_VF); @@ -681,9 +729,45 @@ void ice_set_vf_state_qs_dis(struct ice_vf *vf) clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states); } +/** + * ice_set_vf_state_dis - Set VF state to disabled + * @vf: pointer to the VF structure + */ +void ice_set_vf_state_dis(struct ice_vf *vf) +{ + ice_set_vf_state_qs_dis(vf); + vf->vf_ops->clear_reset_state(vf); +} + /* Private functions only accessed from other virtualization files */ /** + * ice_initialize_vf_entry - Initialize a VF entry + * @vf: pointer to the VF structure + */ +void ice_initialize_vf_entry(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + struct ice_vfs *vfs; + + vfs = &pf->vfs; + + /* assign default capabilities */ + vf->spoofchk = true; + vf->num_vf_qs = vfs->num_qps_per; + ice_vc_set_default_allowlist(vf); + ice_virtchnl_set_dflt_ops(vf); + + /* ctrl_vsi_idx will be set to a valid value only when iAVF + * creates its first fdir rule. + */ + ice_vf_ctrl_invalidate_vsi(vf); + ice_vf_fdir_init(vf); + + mutex_init(&vf->cfg_lock); +} + +/** * ice_dis_vf_qs - Disable the VF queues * @vf: pointer to the VF structure */ @@ -924,18 +1008,18 @@ static int ice_vf_rebuild_host_mac_cfg(struct ice_vf *vf) vf->num_mac++; - if (is_valid_ether_addr(vf->hw_lan_addr.addr)) { - status = ice_fltr_add_mac(vsi, vf->hw_lan_addr.addr, + if (is_valid_ether_addr(vf->hw_lan_addr)) { + status = ice_fltr_add_mac(vsi, vf->hw_lan_addr, ICE_FWD_TO_VSI); if (status) { dev_err(dev, "failed to add default unicast MAC filter %pM for VF %u, error %d\n", - &vf->hw_lan_addr.addr[0], vf->vf_id, + &vf->hw_lan_addr[0], vf->vf_id, status); return status; } vf->num_mac++; - ether_addr_copy(vf->dev_lan_addr.addr, vf->hw_lan_addr.addr); + ether_addr_copy(vf->dev_lan_addr, vf->hw_lan_addr); } return 0; @@ -1115,11 +1199,16 @@ void ice_vf_ctrl_vsi_release(struct ice_vf *vf) */ struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf) { - struct ice_port_info *pi = ice_vf_get_port_info(vf); + struct ice_vsi_cfg_params params = {}; struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; - vsi = ice_vsi_setup(pf, pi, ICE_VSI_CTRL, vf, NULL); + params.type = ICE_VSI_CTRL; + params.pi = ice_vf_get_port_info(vf); + params.vf = vf; + params.flags = ICE_VSI_FLAG_INIT; + + vsi = ice_vsi_setup(pf, ¶ms); if (!vsi) { dev_err(ice_pf_to_dev(pf), "Failed to create VF control VSI\n"); ice_vf_ctrl_invalidate_vsi(vf); @@ -1129,6 +1218,60 @@ struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf) } /** + * ice_vf_init_host_cfg - Initialize host admin configuration + * @vf: VF to initialize + * @vsi: the VSI created at initialization + * + * Initialize the VF host configuration. Called during VF creation to setup + * VLAN 0, add the VF VSI broadcast filter, and setup spoof checking. It + * should only be called during VF creation. + */ +int ice_vf_init_host_cfg(struct ice_vf *vf, struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops; + struct ice_pf *pf = vf->pf; + u8 broadcast[ETH_ALEN]; + struct device *dev; + int err; + + dev = ice_pf_to_dev(pf); + + err = ice_vsi_add_vlan_zero(vsi); + if (err) { + dev_warn(dev, "Failed to add VLAN 0 filter for VF %d\n", + vf->vf_id); + return err; + } + + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + err = vlan_ops->ena_rx_filtering(vsi); + if (err) { + dev_warn(dev, "Failed to enable Rx VLAN filtering for VF %d\n", + vf->vf_id); + return err; + } + + eth_broadcast_addr(broadcast); + err = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI); + if (err) { + dev_err(dev, "Failed to add broadcast MAC filter for VF %d, status %d\n", + vf->vf_id, err); + return err; + } + + vf->num_mac = 1; + + err = ice_vsi_apply_spoofchk(vsi, vf->spoofchk); + if (err) { + dev_warn(dev, "Failed to initialize spoofchk setting for VF %d\n", + vf->vf_id); + return err; + } + + return 0; +} + +/** * ice_vf_invalidate_vsi - invalidate vsi_idx/vsi_num to remove VSI access * @vf: VF to remove access to VSI for */ @@ -1139,6 +1282,24 @@ void ice_vf_invalidate_vsi(struct ice_vf *vf) } /** + * ice_vf_vsi_release - Release the VF VSI and invalidate indexes + * @vf: pointer to the VF structure + * + * Release the VF associated with this VSI and then invalidate the VSI + * indexes. + */ +void ice_vf_vsi_release(struct ice_vf *vf) +{ + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + + if (WARN_ON(!vsi)) + return; + + ice_vsi_release(vsi); + ice_vf_invalidate_vsi(vf); +} + +/** * ice_vf_set_initialized - VF is ready for VIRTCHNL communication * @vf: VF to set in initialized state * diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index 52bd9a3816bf..ef30f05b5d02 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -56,11 +56,13 @@ struct ice_mdd_vf_events { struct ice_vf_ops { enum ice_disq_rst_src reset_type; void (*free)(struct ice_vf *vf); + void (*clear_reset_state)(struct ice_vf *vf); void (*clear_mbx_register)(struct ice_vf *vf); void (*trigger_reset_register)(struct ice_vf *vf, bool is_vflr); bool (*poll_reset_status)(struct ice_vf *vf); void (*clear_reset_trigger)(struct ice_vf *vf); - int (*vsi_rebuild)(struct ice_vf *vf); + void (*irq_close)(struct ice_vf *vf); + int (*create_vsi)(struct ice_vf *vf); void (*post_vsi_rebuild)(struct ice_vf *vf); }; @@ -96,8 +98,8 @@ struct ice_vf { struct ice_sw *vf_sw_id; /* switch ID the VF VSIs connect to */ struct virtchnl_version_info vf_ver; u32 driver_caps; /* reported by VF driver */ - struct virtchnl_ether_addr dev_lan_addr; - struct virtchnl_ether_addr hw_lan_addr; + u8 dev_lan_addr[ETH_ALEN]; + u8 hw_lan_addr[ETH_ALEN]; struct ice_time_mac legacy_last_added_umac; DECLARE_BITMAP(txq_ena, ICE_MAX_RSS_QS_PER_VF); DECLARE_BITMAP(rxq_ena, ICE_MAX_RSS_QS_PER_VF); @@ -213,7 +215,7 @@ u16 ice_get_num_vfs(struct ice_pf *pf); struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf); bool ice_is_vf_disabled(struct ice_vf *vf); int ice_check_vf_ready_for_cfg(struct ice_vf *vf); -void ice_set_vf_state_qs_dis(struct ice_vf *vf); +void ice_set_vf_state_dis(struct ice_vf *vf); bool ice_is_any_vf_in_unicast_promisc(struct ice_pf *pf); void ice_vf_get_promisc_masks(struct ice_vf *vf, struct ice_vsi *vsi, @@ -259,7 +261,7 @@ static inline int ice_check_vf_ready_for_cfg(struct ice_vf *vf) return -EOPNOTSUPP; } -static inline void ice_set_vf_state_qs_dis(struct ice_vf *vf) +static inline void ice_set_vf_state_dis(struct ice_vf *vf) { } diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h index 9c8ef2b01f0f..6f3293b793b5 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h @@ -23,6 +23,7 @@ #warning "Only include ice_vf_lib_private.h in CONFIG_PCI_IOV virtualization files" #endif +void ice_initialize_vf_entry(struct ice_vf *vf); void ice_dis_vf_qs(struct ice_vf *vf); int ice_check_vf_init(struct ice_vf *vf); enum virtchnl_status_code ice_err_to_virt_err(int err); @@ -35,7 +36,9 @@ void ice_vf_rebuild_host_cfg(struct ice_vf *vf); void ice_vf_ctrl_invalidate_vsi(struct ice_vf *vf); void ice_vf_ctrl_vsi_release(struct ice_vf *vf); struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf); +int ice_vf_init_host_cfg(struct ice_vf *vf, struct ice_vsi *vsi); void ice_vf_invalidate_vsi(struct ice_vf *vf); +void ice_vf_vsi_release(struct ice_vf *vf); void ice_vf_set_initialized(struct ice_vf *vf); #endif /* _ICE_VF_LIB_PRIVATE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c index d4a4001b6e5d..f56fa94ff3d0 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c @@ -39,7 +39,7 @@ ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, return ice_sq_send_cmd(hw, &hw->mailboxq, &desc, msg, msglen, cd); } -static const u32 ice_legacy_aq_to_vc_speed[15] = { +static const u32 ice_legacy_aq_to_vc_speed[] = { VIRTCHNL_LINK_SPEED_100MB, /* BIT(0) */ VIRTCHNL_LINK_SPEED_100MB, VIRTCHNL_LINK_SPEED_1GB, @@ -51,10 +51,6 @@ static const u32 ice_legacy_aq_to_vc_speed[15] = { VIRTCHNL_LINK_SPEED_40GB, VIRTCHNL_LINK_SPEED_40GB, VIRTCHNL_LINK_SPEED_40GB, - VIRTCHNL_LINK_SPEED_UNKNOWN, - VIRTCHNL_LINK_SPEED_UNKNOWN, - VIRTCHNL_LINK_SPEED_UNKNOWN, - VIRTCHNL_LINK_SPEED_UNKNOWN /* BIT(14) */ }; /** @@ -71,21 +67,20 @@ static const u32 ice_legacy_aq_to_vc_speed[15] = { */ u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed) { - u32 speed; + /* convert a BIT() value into an array index */ + u32 index = fls(link_speed) - 1; - if (adv_link_support) { - /* convert a BIT() value into an array index */ - speed = ice_get_link_speed(fls(link_speed) - 1); - } else { + if (adv_link_support) + return ice_get_link_speed(index); + else if (index < ARRAY_SIZE(ice_legacy_aq_to_vc_speed)) /* Virtchnl speeds are not defined for every speed supported in * the hardware. To maintain compatibility with older AVF * drivers, while reporting the speed the new speed values are * resolved to the closest known virtchnl speeds */ - speed = ice_legacy_aq_to_vc_speed[fls(link_speed) - 1]; - } + return ice_legacy_aq_to_vc_speed[index]; - return speed; + return VIRTCHNL_LINK_SPEED_UNKNOWN; } /* The mailbox overflow detection algorithm helps to check if there diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c index 5ecc0ee9a78e..b1ffb81893d4 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c @@ -44,13 +44,17 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) /* outer VLAN ops regardless of port VLAN config */ vlan_ops->add_vlan = ice_vsi_add_vlan; - vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering; vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; if (ice_vf_is_port_vlan_ena(vf)) { /* setup outer VLAN ops */ vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; + /* all Rx traffic should be in the domain of the + * assigned port VLAN, so prevent disabling Rx VLAN + * filtering + */ + vlan_ops->dis_rx_filtering = noop_vlan; vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering; @@ -63,6 +67,9 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; } else { + vlan_ops->dis_rx_filtering = + ice_vsi_dis_rx_vlan_filtering; + if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) vlan_ops->ena_rx_filtering = noop_vlan; else @@ -96,7 +103,14 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan; vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering; + /* all Rx traffic should be in the domain of the + * assigned port VLAN, so prevent disabling Rx VLAN + * filtering + */ + vlan_ops->dis_rx_filtering = noop_vlan; } else { + vlan_ops->dis_rx_filtering = + ice_vsi_dis_rx_vlan_filtering; if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) vlan_ops->ena_rx_filtering = noop_vlan; else diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index dab3cd5d300e..e24e3f5017ca 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -507,7 +507,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vfres->vsi_res[0].vsi_type = VIRTCHNL_VSI_SRIOV; vfres->vsi_res[0].num_queue_pairs = vsi->num_txq; ether_addr_copy(vfres->vsi_res[0].default_mac_addr, - vf->hw_lan_addr.addr); + vf->hw_lan_addr); /* match guest capabilities */ vf->driver_caps = vfres->vf_cap_flags; @@ -1802,10 +1802,10 @@ ice_vfhw_mac_add(struct ice_vf *vf, struct virtchnl_ether_addr *vc_ether_addr) * was correctly specified over VIRTCHNL */ if ((ice_is_vc_addr_legacy(vc_ether_addr) && - is_zero_ether_addr(vf->hw_lan_addr.addr)) || + is_zero_ether_addr(vf->hw_lan_addr)) || ice_is_vc_addr_primary(vc_ether_addr)) { - ether_addr_copy(vf->dev_lan_addr.addr, mac_addr); - ether_addr_copy(vf->hw_lan_addr.addr, mac_addr); + ether_addr_copy(vf->dev_lan_addr, mac_addr); + ether_addr_copy(vf->hw_lan_addr, mac_addr); } /* hardware and device MACs are already set, but its possible that the @@ -1836,7 +1836,7 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, int ret; /* device MAC already added */ - if (ether_addr_equal(mac_addr, vf->dev_lan_addr.addr)) + if (ether_addr_equal(mac_addr, vf->dev_lan_addr)) return 0; if (is_unicast_ether_addr(mac_addr) && !ice_can_vf_change_mac(vf)) { @@ -1891,8 +1891,8 @@ ice_update_legacy_cached_mac(struct ice_vf *vf, ice_is_legacy_umac_expired(&vf->legacy_last_added_umac)) return; - ether_addr_copy(vf->dev_lan_addr.addr, vf->legacy_last_added_umac.addr); - ether_addr_copy(vf->hw_lan_addr.addr, vf->legacy_last_added_umac.addr); + ether_addr_copy(vf->dev_lan_addr, vf->legacy_last_added_umac.addr); + ether_addr_copy(vf->hw_lan_addr, vf->legacy_last_added_umac.addr); } /** @@ -1906,15 +1906,15 @@ ice_vfhw_mac_del(struct ice_vf *vf, struct virtchnl_ether_addr *vc_ether_addr) u8 *mac_addr = vc_ether_addr->addr; if (!is_valid_ether_addr(mac_addr) || - !ether_addr_equal(vf->dev_lan_addr.addr, mac_addr)) + !ether_addr_equal(vf->dev_lan_addr, mac_addr)) return; /* allow the device MAC to be repopulated in the add flow and don't - * clear the hardware MAC (i.e. hw_lan_addr.addr) here as that is meant + * clear the hardware MAC (i.e. hw_lan_addr) here as that is meant * to be persistent on VM reboot and across driver unload/load, which * won't work if we clear the hardware MAC here */ - eth_zero_addr(vf->dev_lan_addr.addr); + eth_zero_addr(vf->dev_lan_addr); ice_update_legacy_cached_mac(vf, vc_ether_addr); } @@ -1934,7 +1934,7 @@ ice_vc_del_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, int status; if (!ice_can_vf_change_mac(vf) && - ether_addr_equal(vf->dev_lan_addr.addr, mac_addr)) + ether_addr_equal(vf->dev_lan_addr, mac_addr)) return 0; status = ice_fltr_remove_mac(vsi, mac_addr, ICE_FWD_TO_VSI); @@ -3733,7 +3733,7 @@ static int ice_vc_repr_add_mac(struct ice_vf *vf, u8 *msg) int result; if (!is_unicast_ether_addr(mac_addr) || - ether_addr_equal(mac_addr, vf->hw_lan_addr.addr)) + ether_addr_equal(mac_addr, vf->hw_lan_addr)) continue; if (vf->pf_set_mac) { diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c index c6a58343d81d..e6ef6b303222 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -113,7 +113,7 @@ ice_vc_fdir_param_check(struct ice_vf *vf, u16 vsi_id) if (!ice_vc_isvalid_vsi_id(vf, vsi_id)) return -EINVAL; - if (!pf->vsi[vf->lan_vsi_idx]) + if (!ice_get_vf_vsi(vf)) return -EINVAL; return 0; @@ -494,7 +494,7 @@ ice_vc_fdir_rem_prof(struct ice_vf *vf, enum ice_fltr_ptype flow, int tun) vf_prof = fdir->fdir_prof[flow]; - vf_vsi = pf->vsi[vf->lan_vsi_idx]; + vf_vsi = ice_get_vf_vsi(vf); if (!vf_vsi) { dev_dbg(dev, "NULL vf %d vsi pointer\n", vf->vf_id); return; @@ -572,7 +572,7 @@ ice_vc_fdir_write_flow_prof(struct ice_vf *vf, enum ice_fltr_ptype flow, pf = vf->pf; dev = ice_pf_to_dev(pf); hw = &pf->hw; - vf_vsi = pf->vsi[vf->lan_vsi_idx]; + vf_vsi = ice_get_vf_vsi(vf); if (!vf_vsi) return -EINVAL; @@ -1205,7 +1205,7 @@ static int ice_vc_fdir_write_fltr(struct ice_vf *vf, pf = vf->pf; dev = ice_pf_to_dev(pf); hw = &pf->hw; - vsi = pf->vsi[vf->lan_vsi_idx]; + vsi = ice_get_vf_vsi(vf); if (!vsi) { dev_dbg(dev, "Invalid vsi for VF %d\n", vf->vf_id); return -EINVAL; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 0e11a082f7a1..087c950fea0b 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2810,6 +2810,22 @@ static int igb_offload_txtime(struct igb_adapter *adapter, return 0; } +static int igb_tc_query_caps(struct igb_adapter *adapter, + struct tc_query_caps_base *base) +{ + switch (base->type) { + case TC_SETUP_QDISC_TAPRIO: { + struct tc_taprio_caps *caps = base->caps; + + caps->broken_mqprio = true; + + return 0; + } + default: + return -EOPNOTSUPP; + } +} + static LIST_HEAD(igb_block_cb_list); static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type, @@ -2818,6 +2834,8 @@ static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type, struct igb_adapter *adapter = netdev_priv(dev); switch (type) { + case TC_QUERY_CAPS: + return igb_tc_query_caps(adapter, type_data); case TC_SETUP_QDISC_CBS: return igb_offload_cbs(adapter, type_data); case TC_SETUP_BLOCK: @@ -3200,8 +3218,6 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_pci_reg; - pci_enable_pcie_error_reporting(pdev); - pci_set_master(pdev); pci_save_state(pdev); @@ -3633,7 +3649,6 @@ err_sw_init: err_ioremap: free_netdev(netdev); err_alloc_etherdev: - pci_disable_pcie_error_reporting(pdev); pci_release_mem_regions(pdev); err_pci_reg: err_dma: @@ -3844,8 +3859,6 @@ static void igb_remove(struct pci_dev *pdev) kfree(adapter->shadow_vfta); free_netdev(netdev); - pci_disable_pcie_error_reporting(pdev); - pci_disable_device(pdev); } diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 8b572cd2c350..2928a6c73692 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -2942,7 +2942,9 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) if (tx_buffer->next_to_watch && time_after(jiffies, tx_buffer->time_stamp + (adapter->tx_timeout_factor * HZ)) && - !(rd32(IGC_STATUS) & IGC_STATUS_TXOFF)) { + !(rd32(IGC_STATUS) & IGC_STATUS_TXOFF) && + (rd32(IGC_TDH(tx_ring->reg_idx)) != + readl(tx_ring->tail))) { /* detected Tx unit hang */ netdev_err(tx_ring->netdev, "Detected Tx Unit Hang\n" @@ -5069,6 +5071,24 @@ static int igc_change_mtu(struct net_device *netdev, int new_mtu) } /** + * igc_tx_timeout - Respond to a Tx Hang + * @netdev: network interface device structure + * @txqueue: queue number that timed out + **/ +static void igc_tx_timeout(struct net_device *netdev, + unsigned int __always_unused txqueue) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + struct igc_hw *hw = &adapter->hw; + + /* Do the reset outside of interrupt context */ + adapter->tx_timeout_count++; + schedule_work(&adapter->reset_task); + wr32(IGC_EICS, + (adapter->eims_enable_mask & ~adapter->eims_other)); +} + +/** * igc_get_stats64 - Get System Network Statistics * @netdev: network interface device structure * @stats: rtnl_link_stats64 pointer @@ -5495,7 +5515,7 @@ static void igc_watchdog_task(struct work_struct *work) case SPEED_100: case SPEED_1000: case SPEED_2500: - adapter->tx_timeout_factor = 7; + adapter->tx_timeout_factor = 1; break; } @@ -6205,12 +6225,35 @@ static int igc_tsn_enable_cbs(struct igc_adapter *adapter, return igc_tsn_offload_apply(adapter); } +static int igc_tc_query_caps(struct igc_adapter *adapter, + struct tc_query_caps_base *base) +{ + struct igc_hw *hw = &adapter->hw; + + switch (base->type) { + case TC_SETUP_QDISC_TAPRIO: { + struct tc_taprio_caps *caps = base->caps; + + caps->broken_mqprio = true; + + if (hw->mac.type == igc_i225) + caps->gate_mask_per_txq = true; + + return 0; + } + default: + return -EOPNOTSUPP; + } +} + 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_QUERY_CAPS: + return igc_tc_query_caps(adapter, type_data); case TC_SETUP_QDISC_TAPRIO: return igc_tsn_enable_qbv_scheduling(adapter, type_data); @@ -6324,6 +6367,7 @@ static const struct net_device_ops igc_netdev_ops = { .ndo_set_rx_mode = igc_set_rx_mode, .ndo_set_mac_address = igc_set_mac, .ndo_change_mtu = igc_change_mtu, + .ndo_tx_timeout = igc_tx_timeout, .ndo_get_stats64 = igc_get_stats64, .ndo_fix_features = igc_fix_features, .ndo_set_features = igc_set_features, @@ -6434,8 +6478,6 @@ static int igc_probe(struct pci_dev *pdev, if (err) goto err_pci_reg; - pci_enable_pcie_error_reporting(pdev); - err = pci_enable_ptm(pdev, NULL); if (err < 0) dev_info(&pdev->dev, "PCIe PTM not supported by PCIe bus/controller\n"); @@ -6643,7 +6685,6 @@ err_sw_init: err_ioremap: free_netdev(netdev); err_alloc_etherdev: - pci_disable_pcie_error_reporting(pdev); pci_release_mem_regions(pdev); err_pci_reg: err_dma: @@ -6691,8 +6732,6 @@ static void igc_remove(struct pci_dev *pdev) free_netdev(netdev); - pci_disable_pcie_error_reporting(pdev); - pci_disable_device(pdev); } diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index c34734d432e0..4e10ced736db 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -417,10 +417,12 @@ static int igc_ptp_verify_pin(struct ptp_clock_info *ptp, unsigned int pin, * * We need to convert the system time value stored in the RX/TXSTMP registers * into a hwtstamp which can be used by the upper level timestamping functions. + * + * Returns 0 on success. **/ -static void igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter, - struct skb_shared_hwtstamps *hwtstamps, - u64 systim) +static int igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter, + struct skb_shared_hwtstamps *hwtstamps, + u64 systim) { switch (adapter->hw.mac.type) { case igc_i225: @@ -430,8 +432,9 @@ static void igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter, systim & 0xFFFFFFFF); break; default: - break; + return -EINVAL; } + return 0; } /** @@ -652,7 +655,8 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) regval = rd32(IGC_TXSTMPL); regval |= (u64)rd32(IGC_TXSTMPH) << 32; - igc_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval); + if (igc_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval)) + return; switch (adapter->link_speed) { case SPEED_10: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index af4c12b6059f..a3aaf051f9f1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -10812,8 +10812,6 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_pci_reg; } - pci_enable_pcie_error_reporting(pdev); - pci_set_master(pdev); pci_save_state(pdev); @@ -11244,7 +11242,6 @@ err_ioremap: disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state); free_netdev(netdev); err_alloc_etherdev: - pci_disable_pcie_error_reporting(pdev); pci_release_mem_regions(pdev); err_pci_reg: err_dma: @@ -11333,8 +11330,6 @@ static void ixgbe_remove(struct pci_dev *pdev) disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state); free_netdev(netdev); - pci_disable_pcie_error_reporting(pdev); - if (disable_dev) pci_disable_device(pdev); } diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index dc2989103a77..1cb4f59c0050 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -38,7 +38,7 @@ #include <net/ipv6.h> #include <net/tso.h> #include <net/page_pool.h> -#include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include <linux/bpf_trace.h> /* Registers */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c index bda1a6fa2ec4..e4407f09c9d3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c @@ -1500,6 +1500,9 @@ static const struct devlink_param rvu_af_dl_params[] = { BIT(DEVLINK_PARAM_CMODE_RUNTIME), rvu_af_dl_dwrr_mtu_get, rvu_af_dl_dwrr_mtu_set, rvu_af_dl_dwrr_mtu_validate), +}; + +static const struct devlink_param rvu_af_dl_param_exact_match[] = { DEVLINK_PARAM_DRIVER(RVU_AF_DEVLINK_PARAM_ID_NPC_EXACT_FEATURE_DISABLE, "npc_exact_feature_disable", DEVLINK_PARAM_TYPE_STRING, BIT(DEVLINK_PARAM_CMODE_RUNTIME), @@ -1556,7 +1559,6 @@ int rvu_register_dl(struct rvu *rvu) { struct rvu_devlink *rvu_dl; struct devlink *dl; - size_t size; int err; dl = devlink_alloc(&rvu_devlink_ops, sizeof(struct rvu_devlink), @@ -1578,21 +1580,32 @@ int rvu_register_dl(struct rvu *rvu) goto err_dl_health; } + err = devlink_params_register(dl, rvu_af_dl_params, ARRAY_SIZE(rvu_af_dl_params)); + if (err) { + dev_err(rvu->dev, + "devlink params register failed with error %d", err); + goto err_dl_health; + } + /* Register exact match devlink only for CN10K-B */ - size = ARRAY_SIZE(rvu_af_dl_params); if (!rvu_npc_exact_has_match_table(rvu)) - size -= 1; + goto done; - err = devlink_params_register(dl, rvu_af_dl_params, size); + err = devlink_params_register(dl, rvu_af_dl_param_exact_match, + ARRAY_SIZE(rvu_af_dl_param_exact_match)); if (err) { dev_err(rvu->dev, - "devlink params register failed with error %d", err); - goto err_dl_health; + "devlink exact match params register failed with error %d", err); + goto err_dl_exact_match; } +done: devlink_register(dl); return 0; +err_dl_exact_match: + devlink_params_unregister(dl, rvu_af_dl_params, ARRAY_SIZE(rvu_af_dl_params)); + err_dl_health: rvu_health_reporters_destroy(rvu); devlink_free(dl); @@ -1605,8 +1618,14 @@ void rvu_unregister_dl(struct rvu *rvu) struct devlink *dl = rvu_dl->dl; devlink_unregister(dl); - devlink_params_unregister(dl, rvu_af_dl_params, - ARRAY_SIZE(rvu_af_dl_params)); + + devlink_params_unregister(dl, rvu_af_dl_params, ARRAY_SIZE(rvu_af_dl_params)); + + /* Unregister exact match devlink only for CN10K-B */ + if (rvu_npc_exact_has_match_table(rvu)) + devlink_params_unregister(dl, rvu_af_dl_param_exact_match, + ARRAY_SIZE(rvu_af_dl_param_exact_match)); + rvu_health_reporters_destroy(rvu); devlink_free(dl); } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c index f69102d20c90..20ebb9c95c73 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c @@ -200,10 +200,8 @@ void npc_config_secret_key(struct rvu *rvu, int blkaddr) struct rvu_hwinfo *hw = rvu->hw; u8 intf; - if (!hwcap->npc_hash_extract) { - dev_info(rvu->dev, "HW does not support secret key configuration\n"); + if (!hwcap->npc_hash_extract) return; - } for (intf = 0; intf < hw->npc_intfs; intf++) { rvu_write64(rvu, blkaddr, NPC_AF_INTFX_SECRET_KEY0(intf), @@ -221,10 +219,8 @@ void npc_program_mkex_hash(struct rvu *rvu, int blkaddr) struct rvu_hwinfo *hw = rvu->hw; u8 intf; - if (!hwcap->npc_hash_extract) { - dev_dbg(rvu->dev, "Field hash extract feature is not supported\n"); + if (!hwcap->npc_hash_extract) return; - } for (intf = 0; intf < hw->npc_intfs; intf++) { npc_program_mkex_hash_rx(rvu, blkaddr, intf); @@ -1853,19 +1849,13 @@ int rvu_npc_exact_init(struct rvu *rvu) /* Check exact match feature is supported */ npc_const3 = rvu_read64(rvu, blkaddr, NPC_AF_CONST3); - if (!(npc_const3 & BIT_ULL(62))) { - dev_info(rvu->dev, "%s: No support for exact match support\n", - __func__); + if (!(npc_const3 & BIT_ULL(62))) return 0; - } /* Check if kex profile has enabled EXACT match nibble */ cfg = rvu_read64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_RX)); - if (!(cfg & NPC_EXACT_NIBBLE_HIT)) { - dev_info(rvu->dev, "%s: NPC exact match nibble not enabled in KEX profile\n", - __func__); + if (!(cfg & NPC_EXACT_NIBBLE_HIT)) return 0; - } /* Set capability to true */ rvu->hw->cap.npc_exact_match_enabled = true; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index ac54b6f2bb5c..14be6ea51b88 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -1621,8 +1621,8 @@ static struct page_pool *mtk_create_page_pool(struct mtk_eth *eth, if (IS_ERR(pp)) return pp; - err = __xdp_rxq_info_reg(xdp_q, ð->dummy_dev, eth->rx_napi.napi_id, - id, PAGE_SIZE); + err = __xdp_rxq_info_reg(xdp_q, ð->dummy_dev, id, + eth->rx_napi.napi_id, PAGE_SIZE); if (err < 0) goto err_free_pp; @@ -1921,7 +1921,9 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, while (done < budget) { unsigned int pktlen, *rxdcsum; + bool has_hwaccel_tag = false; struct net_device *netdev; + u16 vlan_proto, vlan_tci; dma_addr_t dma_addr; u32 hash, reason; int mac = 0; @@ -2061,27 +2063,29 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) { if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) { - if (trxd.rxd3 & RX_DMA_VTAG_V2) - __vlan_hwaccel_put_tag(skb, - htons(RX_DMA_VPID(trxd.rxd4)), - RX_DMA_VID(trxd.rxd4)); + if (trxd.rxd3 & RX_DMA_VTAG_V2) { + vlan_proto = RX_DMA_VPID(trxd.rxd4); + vlan_tci = RX_DMA_VID(trxd.rxd4); + has_hwaccel_tag = true; + } } else if (trxd.rxd2 & RX_DMA_VTAG) { - __vlan_hwaccel_put_tag(skb, htons(RX_DMA_VPID(trxd.rxd3)), - RX_DMA_VID(trxd.rxd3)); + vlan_proto = RX_DMA_VPID(trxd.rxd3); + vlan_tci = RX_DMA_VID(trxd.rxd3); + has_hwaccel_tag = true; } } /* When using VLAN untagging in combination with DSA, the * hardware treats the MTK special tag as a VLAN and untags it. */ - if (skb_vlan_tag_present(skb) && netdev_uses_dsa(netdev)) { - unsigned int port = ntohs(skb->vlan_proto) & GENMASK(2, 0); + if (has_hwaccel_tag && netdev_uses_dsa(netdev)) { + unsigned int port = vlan_proto & GENMASK(2, 0); if (port < ARRAY_SIZE(eth->dsa_meta) && eth->dsa_meta[port]) skb_dst_set_noref(skb, ð->dsa_meta[port]->dst); - - __vlan_hwaccel_clear_tag(skb); + } else if (has_hwaccel_tag) { + __vlan_hwaccel_put_tag(skb, htons(vlan_proto), vlan_tci); } skb_record_rx_queue(skb, 0); @@ -3177,7 +3181,7 @@ static void mtk_gdm_config(struct mtk_eth *eth, u32 config) val |= config; - if (!i && eth->netdev[0] && netdev_uses_dsa(eth->netdev[0])) + if (eth->netdev[i] && netdev_uses_dsa(eth->netdev[i])) val |= MTK_GDMA_SPECIAL_TAG; mtk_w32(eth, val, MTK_GDMA_FWD_CFG(i)); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index dff0e3ad2de6..afc9d52e79bf 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -533,7 +533,7 @@ #define SGMII_SPEED_10 FIELD_PREP(SGMII_SPEED_MASK, 0) #define SGMII_SPEED_100 FIELD_PREP(SGMII_SPEED_MASK, 1) #define SGMII_SPEED_1000 FIELD_PREP(SGMII_SPEED_MASK, 2) -#define SGMII_DUPLEX_FULL BIT(4) +#define SGMII_DUPLEX_HALF BIT(4) #define SGMII_IF_MODE_BIT5 BIT(5) #define SGMII_REMOTE_FAULT_DIS BIT(8) #define SGMII_CODE_SYNC_SET_VAL BIT(9) @@ -1066,11 +1066,13 @@ struct mtk_soc_data { * @regmap: The register map pointing at the range used to setup * SGMII modes * @ana_rgc3: The offset refers to register ANA_RGC3 related to regmap + * @interface: Currently configured interface mode * @pcs: Phylink PCS structure */ struct mtk_pcs { struct regmap *regmap; u32 ana_rgc3; + phy_interface_t interface; struct phylink_pcs pcs; }; diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c index 451a87b1bc20..6883eb34cd8b 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe.c @@ -615,8 +615,7 @@ mtk_foe_entry_commit_subflow(struct mtk_ppe *ppe, struct mtk_flow_entry *entry, u32 ib1_mask = mtk_get_ib1_pkt_type_mask(ppe->eth) | MTK_FOE_IB1_UDP; int type; - flow_info = kzalloc(offsetof(struct mtk_flow_entry, l2_data.end), - GFP_ATOMIC); + flow_info = kzalloc(sizeof(*flow_info), GFP_ATOMIC); if (!flow_info) return; diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.h b/drivers/net/ethernet/mediatek/mtk_ppe.h index 16b02e1d4649..5e8bc48252b1 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.h +++ b/drivers/net/ethernet/mediatek/mtk_ppe.h @@ -279,7 +279,6 @@ struct mtk_flow_entry { struct { struct mtk_flow_entry *base_flow; struct hlist_node list; - struct {} end; } l2_data; }; struct rhash_head node; diff --git a/drivers/net/ethernet/mediatek/mtk_sgmii.c b/drivers/net/ethernet/mediatek/mtk_sgmii.c index 5c286f2c9418..bb00de1003ac 100644 --- a/drivers/net/ethernet/mediatek/mtk_sgmii.c +++ b/drivers/net/ethernet/mediatek/mtk_sgmii.c @@ -43,11 +43,6 @@ static int mtk_pcs_config(struct phylink_pcs *pcs, unsigned int mode, int advertise, link_timer; bool changed, use_an; - if (interface == PHY_INTERFACE_MODE_2500BASEX) - rgc3 = RG_PHY_SPEED_3_125G; - else - rgc3 = 0; - advertise = phylink_mii_c22_pcs_encode_advertisement(interface, advertising); if (advertise < 0) @@ -88,9 +83,22 @@ static int mtk_pcs_config(struct phylink_pcs *pcs, unsigned int mode, bmcr = 0; } - /* Configure the underlying interface speed */ - regmap_update_bits(mpcs->regmap, mpcs->ana_rgc3, - RG_PHY_SPEED_3_125G, rgc3); + if (mpcs->interface != interface) { + /* PHYA power down */ + regmap_update_bits(mpcs->regmap, SGMSYS_QPHY_PWR_STATE_CTRL, + SGMII_PHYA_PWD, SGMII_PHYA_PWD); + + if (interface == PHY_INTERFACE_MODE_2500BASEX) + rgc3 = RG_PHY_SPEED_3_125G; + else + rgc3 = 0; + + /* Configure the underlying interface speed */ + regmap_update_bits(mpcs->regmap, mpcs->ana_rgc3, + RG_PHY_SPEED_3_125G, rgc3); + + mpcs->interface = interface; + } /* Update the advertisement, noting whether it has changed */ regmap_update_bits_check(mpcs->regmap, SGMSYS_PCS_ADVERTISE, @@ -108,9 +116,17 @@ static int mtk_pcs_config(struct phylink_pcs *pcs, unsigned int mode, regmap_update_bits(mpcs->regmap, SGMSYS_PCS_CONTROL_1, SGMII_AN_RESTART | SGMII_AN_ENABLE, bmcr); - /* Release PHYA power down state */ - regmap_update_bits(mpcs->regmap, SGMSYS_QPHY_PWR_STATE_CTRL, - SGMII_PHYA_PWD, 0); + /* Release PHYA power down state + * Only removing bit SGMII_PHYA_PWD isn't enough. + * There are cases when the SGMII_PHYA_PWD register contains 0x9 which + * prevents SGMII from working. The SGMII still shows link but no traffic + * can flow. Writing 0x0 to the PHYA_PWD register fix the issue. 0x0 was + * taken from a good working state of the SGMII interface. + * Unknown how much the QPHY needs but it is racy without a sleep. + * Tested on mt7622 & mt7986. + */ + usleep_range(50, 100); + regmap_write(mpcs->regmap, SGMSYS_QPHY_PWR_STATE_CTRL, 0); return changed; } @@ -138,11 +154,11 @@ static void mtk_pcs_link_up(struct phylink_pcs *pcs, unsigned int mode, else sgm_mode = SGMII_SPEED_1000; - if (duplex == DUPLEX_FULL) - sgm_mode |= SGMII_DUPLEX_FULL; + if (duplex != DUPLEX_FULL) + sgm_mode |= SGMII_DUPLEX_HALF; regmap_update_bits(mpcs->regmap, SGMSYS_SGMII_MODE, - SGMII_DUPLEX_FULL | SGMII_SPEED_MASK, + SGMII_DUPLEX_HALF | SGMII_SPEED_MASK, sgm_mode); } } @@ -171,6 +187,8 @@ int mtk_sgmii_init(struct mtk_sgmii *ss, struct device_node *r, u32 ana_rgc3) return PTR_ERR(ss->pcs[i].regmap); ss->pcs[i].pcs.ops = &mtk_pcs_ops; + ss->pcs[i].pcs.poll = true; + ss->pcs[i].interface = PHY_INTERFACE_MODE_NA; } return 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 6152f77dcfd8..277738c50c56 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -4031,7 +4031,6 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) goto err_params_unregister; pci_save_state(pdev); - devlink_set_features(devlink, DEVLINK_F_RELOAD); devl_unlock(devlink); devlink_register(devlink); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 382d02f6619c..b00e33ed05e9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -104,6 +104,7 @@ static bool mlx5_cmd_is_throttle_opcode(u16 op) case MLX5_CMD_OP_DESTROY_GENERAL_OBJECT: case MLX5_CMD_OP_MODIFY_GENERAL_OBJECT: case MLX5_CMD_OP_QUERY_GENERAL_OBJECT: + case MLX5_CMD_OP_SYNC_CRYPTO: return true; } return false; @@ -523,6 +524,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_QUERY_VHCA_MIGRATION_STATE: case MLX5_CMD_OP_SAVE_VHCA_STATE: case MLX5_CMD_OP_LOAD_VHCA_STATE: + case MLX5_CMD_OP_SYNC_CRYPTO: *status = MLX5_DRIVER_STATUS_ABORTED; *synd = MLX5_DRIVER_SYND; return -ENOLINK; @@ -725,6 +727,7 @@ const char *mlx5_command_str(int command) MLX5_COMMAND_STR_CASE(QUERY_VHCA_MIGRATION_STATE); MLX5_COMMAND_STR_CASE(SAVE_VHCA_STATE); MLX5_COMMAND_STR_CASE(LOAD_VHCA_STATE); + MLX5_COMMAND_STR_CASE(SYNC_CRYPTO); default: return "unknown command opcode"; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index 3e232a65a0c3..bb95b40d25eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -245,8 +245,9 @@ void mlx5_pages_debugfs_init(struct mlx5_core_dev *dev) pages = dev->priv.dbg.pages_debugfs; debugfs_create_u32("fw_pages_total", 0400, pages, &dev->priv.fw_pages); - debugfs_create_u32("fw_pages_vfs", 0400, pages, &dev->priv.vfs_pages); - debugfs_create_u32("fw_pages_host_pf", 0400, pages, &dev->priv.host_pf_pages); + debugfs_create_u32("fw_pages_vfs", 0400, pages, &dev->priv.page_counters[MLX5_VF]); + debugfs_create_u32("fw_pages_sfs", 0400, pages, &dev->priv.page_counters[MLX5_SF]); + debugfs_create_u32("fw_pages_host_pf", 0400, pages, &dev->priv.page_counters[MLX5_HOST_PF]); debugfs_create_u32("fw_pages_alloc_failed", 0400, pages, &dev->priv.fw_pages_alloc_failed); debugfs_create_u32("fw_pages_give_dropped", 0400, pages, &dev->priv.give_pages_dropped); debugfs_create_u32("fw_pages_reclaim_discard", 0400, pages, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index 95a69544a685..b742e04deec1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -156,6 +156,11 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change, return -EOPNOTSUPP; } + if (mlx5_core_is_mp_slave(dev)) { + NL_SET_ERR_MSG_MOD(extack, "reload is unsupported for multi port slave"); + return -EOPNOTSUPP; + } + if (pci_num_vf(pdev)) { NL_SET_ERR_MSG_MOD(extack, "reload while VFs are present is unfavorable"); } @@ -263,9 +268,10 @@ static int mlx5_devlink_trap_action_set(struct devlink *devlink, struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_priv(devlink); + struct mlx5_devlink_trap_event_ctx trap_event_ctx; enum devlink_trap_action action_orig; struct mlx5_devlink_trap *dl_trap; - int err = 0; + int err; if (is_mdev_switchdev_mode(dev)) { NL_SET_ERR_MSG_MOD(extack, "Devlink traps can't be set in switchdev mode"); @@ -275,26 +281,25 @@ static int mlx5_devlink_trap_action_set(struct devlink *devlink, dl_trap = mlx5_find_trap_by_id(dev, trap->id); if (!dl_trap) { mlx5_core_err(dev, "Devlink trap: Set action on invalid trap id 0x%x", trap->id); - err = -EINVAL; - goto out; + return -EINVAL; } - if (action != DEVLINK_TRAP_ACTION_DROP && action != DEVLINK_TRAP_ACTION_TRAP) { - err = -EOPNOTSUPP; - goto out; - } + if (action != DEVLINK_TRAP_ACTION_DROP && action != DEVLINK_TRAP_ACTION_TRAP) + return -EOPNOTSUPP; if (action == dl_trap->trap.action) - goto out; + return 0; action_orig = dl_trap->trap.action; dl_trap->trap.action = action; + trap_event_ctx.trap = &dl_trap->trap; + trap_event_ctx.err = 0; err = mlx5_blocking_notifier_call_chain(dev, MLX5_DRIVER_EVENT_TYPE_TRAP, - &dl_trap->trap); - if (err) + &trap_event_ctx); + if (err == NOTIFY_BAD) dl_trap->trap.action = action_orig; -out: - return err; + + return trap_event_ctx.err; } static const struct devlink_ops mlx5_devlink_ops = { @@ -744,7 +749,6 @@ void mlx5_devlink_traps_unregister(struct devlink *devlink) int mlx5_devlink_params_register(struct devlink *devlink) { - struct mlx5_core_dev *dev = devlink_priv(devlink); int err; err = devl_params_register(devlink, mlx5_devlink_params, @@ -762,9 +766,6 @@ int mlx5_devlink_params_register(struct devlink *devlink) if (err) goto max_uc_list_err; - if (!mlx5_core_is_mp_slave(dev)) - devlink_set_features(devlink, DEVLINK_F_RELOAD); - return 0; max_uc_list_err: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h index 1c1b62ee84bb..b561107e0df1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h @@ -24,6 +24,11 @@ struct mlx5_devlink_trap { struct list_head list; }; +struct mlx5_devlink_trap_event_ctx { + struct mlx5_trap_ctx *trap; + int err; +}; + struct mlx5_core_dev; void mlx5_devlink_trap_report(struct mlx5_core_dev *dev, int trap_id, struct sk_buff *skb, struct devlink_port *dl_port); 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 21831386b26e..f40497823e65 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -64,6 +64,7 @@ static int mlx5_query_mtrc_caps(struct mlx5_fw_tracer *tracer) MLX5_GET(mtrc_cap, out, num_string_trace); tracer->str_db.num_string_db = MLX5_GET(mtrc_cap, out, num_string_db); tracer->owner = !!MLX5_GET(mtrc_cap, out, trace_owner); + tracer->str_db.loaded = false; for (i = 0; i < tracer->str_db.num_string_db; i++) { mtrc_cap_sp = MLX5_ADDR_OF(mtrc_cap, out, string_db_param[i]); @@ -233,6 +234,8 @@ static int mlx5_fw_tracer_allocate_strings_db(struct mlx5_fw_tracer *tracer) int i; for (i = 0; i < num_string_db; i++) { + if (!string_db_size_out[i]) + continue; tracer->str_db.buffer[i] = kzalloc(string_db_size_out[i], GFP_KERNEL); if (!tracer->str_db.buffer[i]) goto free_strings_db; @@ -278,6 +281,8 @@ static void mlx5_tracer_read_strings_db(struct work_struct *work) } for (i = 0; i < num_string_db; i++) { + if (!tracer->str_db.size_out[i]) + continue; offset = 0; MLX5_SET(mtrc_stdb, in, string_db_index, i); num_of_reads = tracer->str_db.size_out[i] / @@ -384,6 +389,8 @@ static struct tracer_string_format *mlx5_tracer_get_string(struct mlx5_fw_tracer str_ptr = tracer_event->string_event.string_param; for (i = 0; i < tracer->str_db.num_string_db; i++) { + if (!tracer->str_db.size_out[i]) + continue; if (str_ptr > tracer->str_db.base_address_out[i] && str_ptr < tracer->str_db.base_address_out[i] + tracer->str_db.size_out[i]) { @@ -459,6 +466,7 @@ static void poll_trace(struct mlx5_fw_tracer *tracer, tracer_event->event_id = MLX5_GET(tracer_event, trace, event_id); tracer_event->lost_event = MLX5_GET(tracer_event, trace, lost); + tracer_event->out = trace; switch (tracer_event->event_id) { case TRACER_EVENT_TYPE_TIMESTAMP: @@ -581,6 +589,26 @@ void mlx5_tracer_print_trace(struct tracer_string_format *str_frmt, mlx5_tracer_clean_message(str_frmt); } +static int mlx5_tracer_handle_raw_string(struct mlx5_fw_tracer *tracer, + struct tracer_event *tracer_event) +{ + struct tracer_string_format *cur_string; + + cur_string = mlx5_tracer_message_insert(tracer, tracer_event); + if (!cur_string) + return -1; + + cur_string->event_id = tracer_event->event_id; + cur_string->timestamp = tracer_event->string_event.timestamp; + cur_string->lost = tracer_event->lost_event; + cur_string->string = "0x%08x%08x"; + cur_string->num_of_params = 2; + cur_string->params[0] = upper_32_bits(*tracer_event->out); + cur_string->params[1] = lower_32_bits(*tracer_event->out); + list_add_tail(&cur_string->list, &tracer->ready_strings_list); + return 0; +} + static int mlx5_tracer_handle_string_trace(struct mlx5_fw_tracer *tracer, struct tracer_event *tracer_event) { @@ -589,7 +617,7 @@ static int mlx5_tracer_handle_string_trace(struct mlx5_fw_tracer *tracer, if (tracer_event->string_event.tdsn == 0) { cur_string = mlx5_tracer_get_string(tracer, tracer_event); if (!cur_string) - return -1; + return mlx5_tracer_handle_raw_string(tracer, tracer_event); cur_string->num_of_params = mlx5_tracer_get_num_of_params(cur_string->string); cur_string->last_param_num = 0; @@ -602,9 +630,9 @@ static int mlx5_tracer_handle_string_trace(struct mlx5_fw_tracer *tracer, } else { cur_string = mlx5_tracer_message_get(tracer, tracer_event); if (!cur_string) { - pr_debug("%s Got string event for unknown string tdsm: %d\n", + pr_debug("%s Got string event for unknown string tmsn: %d\n", __func__, tracer_event->string_event.tmsn); - return -1; + return mlx5_tracer_handle_raw_string(tracer, tracer_event); } cur_string->last_param_num += 1; if (cur_string->last_param_num > TRACER_MAX_PARAMS) { @@ -756,6 +784,7 @@ static int mlx5_fw_tracer_set_mtrc_conf(struct mlx5_fw_tracer *tracer) if (err) mlx5_core_warn(dev, "FWTracer: Failed to set tracer configurations %d\n", err); + tracer->buff.consumer_index = 0; return err; } @@ -820,7 +849,6 @@ static void mlx5_fw_tracer_ownership_change(struct work_struct *work) mlx5_core_dbg(tracer->dev, "FWTracer: ownership changed, current=(%d)\n", tracer->owner); if (tracer->owner) { tracer->owner = false; - tracer->buff.consumer_index = 0; return; } @@ -930,6 +958,14 @@ unlock: return err; } +static void mlx5_fw_tracer_update_db(struct work_struct *work) +{ + struct mlx5_fw_tracer *tracer = + container_of(work, struct mlx5_fw_tracer, update_db_work); + + mlx5_fw_tracer_reload(tracer); +} + /* Create software resources (Buffers, etc ..) */ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev) { @@ -957,6 +993,8 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev) INIT_WORK(&tracer->ownership_change_work, mlx5_fw_tracer_ownership_change); INIT_WORK(&tracer->read_fw_strings_work, mlx5_tracer_read_strings_db); INIT_WORK(&tracer->handle_traces_work, mlx5_fw_tracer_handle_traces); + INIT_WORK(&tracer->update_db_work, mlx5_fw_tracer_update_db); + mutex_init(&tracer->state_lock); err = mlx5_query_mtrc_caps(tracer); @@ -1003,11 +1041,15 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer) if (IS_ERR_OR_NULL(tracer)) return 0; - dev = tracer->dev; - if (!tracer->str_db.loaded) queue_work(tracer->work_queue, &tracer->read_fw_strings_work); + mutex_lock(&tracer->state_lock); + if (test_and_set_bit(MLX5_TRACER_STATE_UP, &tracer->state)) + goto unlock; + + dev = tracer->dev; + err = mlx5_core_alloc_pd(dev, &tracer->buff.pdn); if (err) { mlx5_core_warn(dev, "FWTracer: Failed to allocate PD %d\n", err); @@ -1028,6 +1070,8 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer) mlx5_core_warn(dev, "FWTracer: Failed to start tracer %d\n", err); goto err_notifier_unregister; } +unlock: + mutex_unlock(&tracer->state_lock); return 0; err_notifier_unregister: @@ -1037,6 +1081,7 @@ err_dealloc_pd: mlx5_core_dealloc_pd(dev, tracer->buff.pdn); err_cancel_work: cancel_work_sync(&tracer->read_fw_strings_work); + mutex_unlock(&tracer->state_lock); return err; } @@ -1046,17 +1091,27 @@ void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer) if (IS_ERR_OR_NULL(tracer)) return; + mutex_lock(&tracer->state_lock); + if (!test_and_clear_bit(MLX5_TRACER_STATE_UP, &tracer->state)) + goto unlock; + mlx5_core_dbg(tracer->dev, "FWTracer: Cleanup, is owner ? (%d)\n", tracer->owner); mlx5_eq_notifier_unregister(tracer->dev, &tracer->nb); cancel_work_sync(&tracer->ownership_change_work); cancel_work_sync(&tracer->handle_traces_work); + /* It is valid to get here from update_db_work. Hence, don't wait for + * update_db_work to finished. + */ + cancel_work(&tracer->update_db_work); if (tracer->owner) mlx5_fw_tracer_ownership_release(tracer); mlx5_core_destroy_mkey(tracer->dev, tracer->buff.mkey); mlx5_core_dealloc_pd(tracer->dev, tracer->buff.pdn); +unlock: + mutex_unlock(&tracer->state_lock); } /* Free software resources (Buffers, etc ..) */ @@ -1073,6 +1128,7 @@ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer) mlx5_fw_tracer_clean_saved_traces_array(tracer); mlx5_fw_tracer_free_strings_db(tracer); mlx5_fw_tracer_destroy_log_buf(tracer); + mutex_destroy(&tracer->state_lock); destroy_workqueue(tracer->work_queue); kvfree(tracer); } @@ -1082,6 +1138,8 @@ static int mlx5_fw_tracer_recreate_strings_db(struct mlx5_fw_tracer *tracer) struct mlx5_core_dev *dev; int err; + if (test_and_set_bit(MLX5_TRACER_RECREATE_DB, &tracer->state)) + return 0; cancel_work_sync(&tracer->read_fw_strings_work); mlx5_fw_tracer_clean_ready_list(tracer); mlx5_fw_tracer_clean_print_hash(tracer); @@ -1092,17 +1150,18 @@ static int mlx5_fw_tracer_recreate_strings_db(struct mlx5_fw_tracer *tracer) err = mlx5_query_mtrc_caps(tracer); if (err) { mlx5_core_dbg(dev, "FWTracer: Failed to query capabilities %d\n", err); - return err; + goto out; } err = mlx5_fw_tracer_allocate_strings_db(tracer); if (err) { mlx5_core_warn(dev, "FWTracer: Allocate strings DB failed %d\n", err); - return err; + goto out; } mlx5_fw_tracer_init_saved_traces_array(tracer); - - return 0; +out: + clear_bit(MLX5_TRACER_RECREATE_DB, &tracer->state); + return err; } int mlx5_fw_tracer_reload(struct mlx5_fw_tracer *tracer) @@ -1142,6 +1201,9 @@ static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void case MLX5_TRACER_SUBTYPE_TRACES_AVAILABLE: queue_work(tracer->work_queue, &tracer->handle_traces_work); break; + case MLX5_TRACER_SUBTYPE_STRINGS_DB_UPDATE: + queue_work(tracer->work_queue, &tracer->update_db_work); + break; default: mlx5_core_dbg(dev, "FWTracer: Event with unrecognized subtype: sub_type %d\n", eqe->sub_type); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h index 4762b55b0b0e..5c548bb74f07 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h @@ -63,6 +63,11 @@ struct mlx5_fw_trace_data { char msg[TRACE_STR_MSG]; }; +enum mlx5_fw_tracer_state { + MLX5_TRACER_STATE_UP = BIT(0), + MLX5_TRACER_RECREATE_DB = BIT(1), +}; + struct mlx5_fw_tracer { struct mlx5_core_dev *dev; struct mlx5_nb nb; @@ -104,6 +109,9 @@ struct mlx5_fw_tracer { struct work_struct handle_traces_work; struct hlist_head hash[MESSAGE_HASH_SIZE]; struct list_head ready_strings_list; + struct work_struct update_db_work; + struct mutex state_lock; /* Synchronize update work with reload flows */ + unsigned long state; }; struct tracer_string_format { @@ -158,6 +166,7 @@ struct tracer_event { struct tracer_string_event string_event; struct tracer_timestamp_event timestamp_event; }; + u64 *out; }; struct mlx5_ifc_tracer_event_bits { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c index b70e36025d92..9a3878f9e582 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c @@ -95,7 +95,7 @@ void mlx5_ec_cleanup(struct mlx5_core_dev *dev) mlx5_host_pf_cleanup(dev); - err = mlx5_wait_for_pages(dev, &dev->priv.host_pf_pages); + err = mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_HOST_PF]); if (err) mlx5_core_warn(dev, "Timeout reclaiming external host PF pages err(%d)\n", err); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 6f8723cc6874..125c7cb7d839 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -454,6 +454,7 @@ struct mlx5e_txqsq { struct mlx5_clock *clock; struct net_device *netdev; struct mlx5_core_dev *mdev; + struct mlx5e_channel *channel; struct mlx5e_priv *priv; /* control path */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c index 57f4b1b50421..7ac1ad9c46de 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c @@ -314,11 +314,11 @@ static int port_set_buffer(struct mlx5e_priv *priv, err = port_update_shared_buffer(priv->mdev, current_headroom_size, new_headroom_size); if (err) - return err; + goto out; err = port_update_pool_cfg(priv->mdev, port_buffer); if (err) - return err; + goto out; err = mlx5e_port_set_pbmc(mdev, in); out: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index 8469e9c38670..9a1bc93b7dc6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -771,8 +771,8 @@ void mlx5e_ptp_activate_channel(struct mlx5e_ptp *c) if (test_bit(MLX5E_PTP_STATE_RX, c->state)) { mlx5e_ptp_rx_set_fs(c->priv); mlx5e_activate_rq(&c->rq); - mlx5e_trigger_napi_sched(&c->napi); } + mlx5e_trigger_napi_sched(&c->napi); } void mlx5e_ptp_deactivate_channel(struct mlx5e_ptp *c) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c index 8099a21e674c..ce85b48d327d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c @@ -438,10 +438,6 @@ static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb, switch (event) { case SWITCHDEV_FDB_ADD_TO_BRIDGE: - /* only handle the event on native eswtich of representor */ - if (!mlx5_esw_bridge_is_local(dev, rep, esw)) - break; - fdb_info = container_of(info, struct switchdev_notifier_fdb_info, info); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index b195dbbf6c90..41e356d9d785 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -81,6 +81,10 @@ static int mlx5e_tx_reporter_err_cqe_recover(void *ctx) sq->stats->recover++; clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state); mlx5e_activate_txqsq(sq); + if (sq->channel) + mlx5e_trigger_napi_icosq(sq->channel); + else + mlx5e_trigger_napi_sched(sq->cq.napi); return 0; out: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c index 78c427b38048..c095a12346de 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c @@ -232,9 +232,9 @@ parse_mirred(struct mlx5e_tc_act_parse_state *parse_state, parse_state->ifindexes[if_count] = out_dev->ifindex; parse_state->if_count++; is_uplink_rep = mlx5e_eswitch_uplink_rep(out_dev); - err = mlx5_lag_do_mirred(priv->mdev, out_dev); - if (err) - return err; + + if (mlx5_lag_mpesw_do_mirred(priv->mdev, out_dev, extack)) + return -EOPNOTSUPP; out_dev = get_fdb_out_dev(uplink_dev, out_dev); if (!out_dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c index b86ac604d0c2..2e0d88b513aa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c @@ -44,19 +44,17 @@ parse_tc_vlan_action(struct mlx5e_priv *priv, return -EOPNOTSUPP; } + if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, vlan_idx)) { + NL_SET_ERR_MSG_MOD(extack, "firmware vlan actions is not supported"); + return -EOPNOTSUPP; + } + switch (act->id) { case FLOW_ACTION_VLAN_POP: - if (vlan_idx) { - if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, - MLX5_FS_VLAN_DEPTH)) { - NL_SET_ERR_MSG_MOD(extack, "vlan pop action is not supported"); - return -EOPNOTSUPP; - } - + if (vlan_idx) *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2; - } else { + else *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP; - } break; case FLOW_ACTION_VLAN_PUSH: attr->vlan_vid[vlan_idx] = act->vlan.vid; @@ -65,25 +63,10 @@ parse_tc_vlan_action(struct mlx5e_priv *priv, if (!attr->vlan_proto[vlan_idx]) attr->vlan_proto[vlan_idx] = htons(ETH_P_8021Q); - if (vlan_idx) { - if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, - MLX5_FS_VLAN_DEPTH)) { - NL_SET_ERR_MSG_MOD(extack, - "vlan push action is not supported for vlan depth > 1"); - return -EOPNOTSUPP; - } - + if (vlan_idx) *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2; - } else { - if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, 1) && - (act->vlan.proto != htons(ETH_P_8021Q) || - act->vlan.prio)) { - NL_SET_ERR_MSG_MOD(extack, "vlan push action is not supported"); - return -EOPNOTSUPP; - } - + else *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH; - } break; case FLOW_ACTION_VLAN_POP_ETH: parse_state->eth_pop = true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c index 7758a425bfa8..8218c892b161 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c @@ -204,13 +204,15 @@ mlx5e_flow_meter_create_aso_obj(struct mlx5e_flow_meters *flow_meters, int *obj_ u32 in[MLX5_ST_SZ_DW(create_flow_meter_aso_obj_in)] = {}; u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)]; struct mlx5_core_dev *mdev = flow_meters->mdev; - void *obj; + void *obj, *param; int err; MLX5_SET(general_obj_in_cmd_hdr, in, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT); MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_GENERAL_OBJECT_TYPES_FLOW_METER_ASO); - MLX5_SET(general_obj_in_cmd_hdr, in, log_obj_range, flow_meters->log_granularity); + param = MLX5_ADDR_OF(general_obj_in_cmd_hdr, in, op_param); + MLX5_SET(general_obj_create_param, param, log_obj_range, + flow_meters->log_granularity); obj = MLX5_ADDR_OF(create_flow_meter_aso_obj_in, in, flow_meter_aso_obj); MLX5_SET(flow_meter_aso_obj, obj, meter_aso_access_pd, flow_meters->pdn); 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 313df8232db7..193562c14c44 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -1073,12 +1073,16 @@ mlx5_tc_ct_block_flow_offload_add(struct mlx5_ct_ft *ft, struct mlx5_tc_ct_priv *ct_priv = ft->ct_priv; struct flow_action_entry *meta_action; unsigned long cookie = flow->cookie; + enum ip_conntrack_info ctinfo; struct mlx5_ct_entry *entry; int err; meta_action = mlx5_tc_ct_get_ct_metadata_action(flow_rule); if (!meta_action) return -EOPNOTSUPP; + ctinfo = meta_action->ct_metadata.cookie & NFCT_INFOMASK; + if (ctinfo == IP_CT_NEW) + return -EOPNOTSUPP; spin_lock_bh(&ct_priv->ht_lock); entry = rhashtable_lookup_fast(&ft->ct_entries_ht, &cookie, cts_ht_params); 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 e84c3400ba1d..7b0d3de0ec6c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -158,6 +158,11 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry, attrs->family = x->props.family; attrs->type = x->xso.type; attrs->reqid = x->props.reqid; + attrs->upspec.dport = ntohs(x->sel.dport); + attrs->upspec.dport_mask = ntohs(x->sel.dport_mask); + attrs->upspec.sport = ntohs(x->sel.sport); + attrs->upspec.sport_mask = ntohs(x->sel.sport_mask); + attrs->upspec.proto = x->sel.proto; mlx5e_ipsec_init_limits(sa_entry, attrs); } @@ -221,6 +226,13 @@ static int mlx5e_xfrm_validate_state(struct mlx5_core_dev *mdev, NL_SET_ERR_MSG_MOD(extack, "Cannot offload xfrm states with geniv other than seqiv"); return -EINVAL; } + + if (x->sel.proto != IPPROTO_IP && + (x->sel.proto != IPPROTO_UDP || x->xso.dir != XFRM_DEV_OFFLOAD_OUT)) { + NL_SET_ERR_MSG_MOD(extack, "Device does not support upper protocol other than UDP, and only Tx direction"); + return -EINVAL; + } + switch (x->xso.type) { case XFRM_DEV_OFFLOAD_CRYPTO: if (!(mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_CRYPTO)) { @@ -517,6 +529,12 @@ static int mlx5e_xfrm_validate_policy(struct xfrm_policy *x, return -EINVAL; } + if (x->selector.proto != IPPROTO_IP && + (x->selector.proto != IPPROTO_UDP || x->xdo.dir != XFRM_DEV_OFFLOAD_OUT)) { + NL_SET_ERR_MSG_MOD(extack, "Device does not support upper protocol other than UDP, and only Tx direction"); + return -EINVAL; + } + return 0; } @@ -537,6 +555,11 @@ mlx5e_ipsec_build_accel_pol_attrs(struct mlx5e_ipsec_pol_entry *pol_entry, attrs->action = x->action; attrs->type = XFRM_DEV_OFFLOAD_PACKET; attrs->reqid = x->xfrm_vec[0].reqid; + attrs->upspec.dport = ntohs(sel->dport); + attrs->upspec.dport_mask = ntohs(sel->dport_mask); + attrs->upspec.sport = ntohs(sel->sport); + attrs->upspec.sport_mask = ntohs(sel->sport_mask); + attrs->upspec.proto = sel->proto; } static int mlx5e_xfrm_add_policy(struct xfrm_policy *x, 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 8bed9c361075..b387adca9c20 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h @@ -52,6 +52,14 @@ struct aes_gcm_keymat { u32 aes_key[256 / 32]; }; +struct upspec { + u16 dport; + u16 dport_mask; + u16 sport; + u16 sport_mask; + u8 proto; +}; + struct mlx5_accel_esp_xfrm_attrs { u32 esn; u32 spi; @@ -68,6 +76,7 @@ struct mlx5_accel_esp_xfrm_attrs { __be32 a6[4]; } daddr; + struct upspec upspec; u8 dir : 2; u8 esn_overlap : 1; u8 esn_trigger : 1; @@ -181,6 +190,7 @@ struct mlx5_accel_pol_xfrm_attrs { __be32 a6[4]; } daddr; + struct upspec upspec; u8 family; u8 action; u8 type : 2; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index 9f19f4b59a70..5da6fe68eea6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -467,6 +467,27 @@ static void setup_fte_reg_c0(struct mlx5_flow_spec *spec, u32 reqid) misc_parameters_2.metadata_reg_c_0, reqid); } +static void setup_fte_upper_proto_match(struct mlx5_flow_spec *spec, struct upspec *upspec) +{ + if (upspec->proto != IPPROTO_UDP) + return; + + spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS; + MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, spec->match_criteria, ip_protocol); + MLX5_SET(fte_match_set_lyr_2_4, spec->match_value, ip_protocol, upspec->proto); + if (upspec->dport) { + MLX5_SET(fte_match_set_lyr_2_4, spec->match_criteria, udp_dport, + upspec->dport_mask); + MLX5_SET(fte_match_set_lyr_2_4, spec->match_value, udp_dport, upspec->dport); + } + + if (upspec->sport) { + MLX5_SET(fte_match_set_lyr_2_4, spec->match_criteria, udp_dport, + upspec->sport_mask); + MLX5_SET(fte_match_set_lyr_2_4, spec->match_value, udp_dport, upspec->sport); + } +} + static int setup_modify_header(struct mlx5_core_dev *mdev, u32 val, u8 dir, struct mlx5_flow_act *flow_act) { @@ -654,6 +675,7 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6); setup_fte_no_frags(spec); + setup_fte_upper_proto_match(spec, &attrs->upspec); switch (attrs->type) { case XFRM_DEV_OFFLOAD_CRYPTO: @@ -728,6 +750,7 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry) setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6); setup_fte_no_frags(spec); + setup_fte_upper_proto_match(spec, &attrs->upspec); err = setup_modify_header(mdev, attrs->reqid, XFRM_DEV_OFFLOAD_OUT, &flow_act); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index 2461462b7b99..7fb3835befbd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -4,7 +4,7 @@ #include "mlx5_core.h" #include "en.h" #include "ipsec.h" -#include "lib/mlx5.h" +#include "lib/crypto.h" enum { MLX5_IPSEC_ASO_REMOVE_FLOW_PKT_CNT_OFFSET, @@ -92,7 +92,6 @@ static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn, MLX5_SET(ipsec_aso, aso_ctx, remove_flow_pkt_cnt, lower_32_bits(attrs->hard_packet_limit)); MLX5_SET(ipsec_aso, aso_ctx, hard_lft_arm, 1); - MLX5_SET(ipsec_aso, aso_ctx, remove_flow_enable, 1); } if (attrs->soft_packet_limit != XFRM_INF) { @@ -329,8 +328,7 @@ static void mlx5e_ipsec_handle_event(struct work_struct *_work) if (attrs->soft_packet_limit != XFRM_INF) if (!MLX5_GET(ipsec_aso, aso->ctx, soft_lft_arm) || - !MLX5_GET(ipsec_aso, aso->ctx, hard_lft_arm) || - !MLX5_GET(ipsec_aso, aso->ctx, remove_flow_enable)) + !MLX5_GET(ipsec_aso, aso->ctx, hard_lft_arm)) xfrm_state_check_expire(sa_entry->x); unlock: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c index eb5b09f81dec..cf704f106b7c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c @@ -4,16 +4,16 @@ #include <linux/debugfs.h> #include "en.h" #include "lib/mlx5.h" +#include "lib/crypto.h" #include "en_accel/ktls.h" #include "en_accel/ktls_utils.h" #include "en_accel/fs_tcp.h" -int mlx5_ktls_create_key(struct mlx5_core_dev *mdev, - struct tls_crypto_info *crypto_info, - u32 *p_key_id) +struct mlx5_crypto_dek *mlx5_ktls_create_key(struct mlx5_crypto_dek_pool *dek_pool, + struct tls_crypto_info *crypto_info) { + const void *key; u32 sz_bytes; - void *key; switch (crypto_info->cipher_type) { case TLS_CIPHER_AES_GCM_128: { @@ -33,17 +33,16 @@ int mlx5_ktls_create_key(struct mlx5_core_dev *mdev, break; } default: - return -EINVAL; + return ERR_PTR(-EINVAL); } - return mlx5_create_encryption_key(mdev, key, sz_bytes, - MLX5_ACCEL_OBJ_TLS_KEY, - p_key_id); + return mlx5_crypto_dek_create(dek_pool, key, sz_bytes); } -void mlx5_ktls_destroy_key(struct mlx5_core_dev *mdev, u32 key_id) +void mlx5_ktls_destroy_key(struct mlx5_crypto_dek_pool *dek_pool, + struct mlx5_crypto_dek *dek) { - mlx5_destroy_encryption_key(mdev, key_id); + mlx5_crypto_dek_destroy(dek_pool, dek); } static int mlx5e_ktls_add(struct net_device *netdev, struct sock *sk, @@ -189,6 +188,7 @@ static void mlx5e_tls_debugfs_init(struct mlx5e_tls *tls, int mlx5e_ktls_init(struct mlx5e_priv *priv) { + struct mlx5_crypto_dek_pool *dek_pool; struct mlx5e_tls *tls; if (!mlx5e_is_ktls_device(priv->mdev)) @@ -197,9 +197,15 @@ int mlx5e_ktls_init(struct mlx5e_priv *priv) tls = kzalloc(sizeof(*tls), GFP_KERNEL); if (!tls) return -ENOMEM; + tls->mdev = priv->mdev; + dek_pool = mlx5_crypto_dek_pool_create(priv->mdev, MLX5_ACCEL_OBJ_TLS_KEY); + if (IS_ERR(dek_pool)) { + kfree(tls); + return PTR_ERR(dek_pool); + } + tls->dek_pool = dek_pool; priv->tls = tls; - priv->tls->mdev = priv->mdev; mlx5e_tls_debugfs_init(tls, priv->dfs_root); @@ -216,6 +222,7 @@ void mlx5e_ktls_cleanup(struct mlx5e_priv *priv) debugfs_remove_recursive(tls->debugfs.dfs); tls->debugfs.dfs = NULL; + mlx5_crypto_dek_pool_destroy(tls->dek_pool); kfree(priv->tls); priv->tls = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h index fccf995ee16d..f11075e67658 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h @@ -10,10 +10,12 @@ #include "en.h" #ifdef CONFIG_MLX5_EN_TLS -int mlx5_ktls_create_key(struct mlx5_core_dev *mdev, - struct tls_crypto_info *crypto_info, - u32 *p_key_id); -void mlx5_ktls_destroy_key(struct mlx5_core_dev *mdev, u32 key_id); +#include "lib/crypto.h" + +struct mlx5_crypto_dek *mlx5_ktls_create_key(struct mlx5_crypto_dek_pool *dek_pool, + struct tls_crypto_info *crypto_info); +void mlx5_ktls_destroy_key(struct mlx5_crypto_dek_pool *dek_pool, + struct mlx5_crypto_dek *dek); static inline bool mlx5e_is_ktls_device(struct mlx5_core_dev *mdev) { @@ -83,6 +85,7 @@ struct mlx5e_tls { struct mlx5e_tls_sw_stats sw_stats; struct workqueue_struct *rx_wq; struct mlx5e_tls_tx_pool *tx_pool; + struct mlx5_crypto_dek_pool *dek_pool; struct mlx5e_tls_debugfs debugfs; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c index 3e54834747ce..4be770443b0c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c @@ -50,7 +50,7 @@ struct mlx5e_ktls_offload_context_rx { struct mlx5e_tls_sw_stats *sw_stats; struct completion add_ctx; struct mlx5e_tir tir; - u32 key_id; + struct mlx5_crypto_dek *dek; u32 rxq; DECLARE_BITMAP(flags, MLX5E_NUM_PRIV_RX_FLAGS); @@ -148,7 +148,8 @@ post_static_params(struct mlx5e_icosq *sq, wqe = MLX5E_TLS_FETCH_SET_STATIC_PARAMS_WQE(sq, pi); mlx5e_ktls_build_static_params(wqe, sq->pc, sq->sqn, &priv_rx->crypto_info, mlx5e_tir_get_tirn(&priv_rx->tir), - priv_rx->key_id, priv_rx->resync.seq, false, + mlx5_crypto_dek_get_id(priv_rx->dek), + priv_rx->resync.seq, false, TLS_OFFLOAD_CTX_DIR_RX); wi = (struct mlx5e_icosq_wqe_info) { .wqe_type = MLX5E_ICOSQ_WQE_UMR_TLS, @@ -610,20 +611,22 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk, struct mlx5e_ktls_offload_context_rx *priv_rx; struct mlx5e_ktls_rx_resync_ctx *resync; struct tls_context *tls_ctx; - struct mlx5_core_dev *mdev; + struct mlx5_crypto_dek *dek; struct mlx5e_priv *priv; int rxq, err; tls_ctx = tls_get_ctx(sk); priv = netdev_priv(netdev); - mdev = priv->mdev; priv_rx = kzalloc(sizeof(*priv_rx), GFP_KERNEL); if (unlikely(!priv_rx)) return -ENOMEM; - err = mlx5_ktls_create_key(mdev, crypto_info, &priv_rx->key_id); - if (err) + dek = mlx5_ktls_create_key(priv->tls->dek_pool, crypto_info); + if (IS_ERR(dek)) { + err = PTR_ERR(dek); goto err_create_key; + } + priv_rx->dek = dek; INIT_LIST_HEAD(&priv_rx->list); spin_lock_init(&priv_rx->lock); @@ -673,7 +676,7 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk, err_post_wqes: mlx5e_tir_destroy(&priv_rx->tir); err_create_tir: - mlx5_ktls_destroy_key(mdev, priv_rx->key_id); + mlx5_ktls_destroy_key(priv->tls->dek_pool, priv_rx->dek); err_create_key: kfree(priv_rx); return err; @@ -683,11 +686,9 @@ void mlx5e_ktls_del_rx(struct net_device *netdev, struct tls_context *tls_ctx) { struct mlx5e_ktls_offload_context_rx *priv_rx; struct mlx5e_ktls_rx_resync_ctx *resync; - struct mlx5_core_dev *mdev; struct mlx5e_priv *priv; priv = netdev_priv(netdev); - mdev = priv->mdev; priv_rx = mlx5e_get_ktls_rx_priv_ctx(tls_ctx); set_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags); @@ -707,7 +708,7 @@ void mlx5e_ktls_del_rx(struct net_device *netdev, struct tls_context *tls_ctx) mlx5e_accel_fs_del_sk(priv_rx->rule.rule); mlx5e_tir_destroy(&priv_rx->tir); - mlx5_ktls_destroy_key(mdev, priv_rx->key_id); + mlx5_ktls_destroy_key(priv->tls->dek_pool, priv_rx->dek); /* priv_rx should normally be freed here, but if there is an outstanding * GET_PSV, deallocation will be delayed until the CQE for GET_PSV is * processed. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index 6db27062b765..60b3e08a1028 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -98,7 +98,7 @@ struct mlx5e_ktls_offload_context_tx { struct tls_offload_context_tx *tx_ctx; struct mlx5_core_dev *mdev; struct mlx5e_tls_sw_stats *sw_stats; - u32 key_id; + struct mlx5_crypto_dek *dek; u8 create_err : 1; }; @@ -457,6 +457,7 @@ int mlx5e_ktls_add_tx(struct net_device *netdev, struct sock *sk, struct mlx5e_ktls_offload_context_tx *priv_tx; struct mlx5e_tls_tx_pool *pool; struct tls_context *tls_ctx; + struct mlx5_crypto_dek *dek; struct mlx5e_priv *priv; int err; @@ -468,9 +469,12 @@ int mlx5e_ktls_add_tx(struct net_device *netdev, struct sock *sk, if (IS_ERR(priv_tx)) return PTR_ERR(priv_tx); - err = mlx5_ktls_create_key(pool->mdev, crypto_info, &priv_tx->key_id); - if (err) + dek = mlx5_ktls_create_key(priv->tls->dek_pool, crypto_info); + if (IS_ERR(dek)) { + err = PTR_ERR(dek); goto err_create_key; + } + priv_tx->dek = dek; priv_tx->expected_seq = start_offload_tcp_sn; switch (crypto_info->cipher_type) { @@ -512,7 +516,7 @@ void mlx5e_ktls_del_tx(struct net_device *netdev, struct tls_context *tls_ctx) pool = priv->tls->tx_pool; atomic64_inc(&priv_tx->sw_stats->tx_tls_del); - mlx5_ktls_destroy_key(priv_tx->mdev, priv_tx->key_id); + mlx5_ktls_destroy_key(priv->tls->dek_pool, priv_tx->dek); pool_push(pool, priv_tx); } @@ -551,8 +555,9 @@ post_static_params(struct mlx5e_txqsq *sq, pi = mlx5e_txqsq_get_next_pi(sq, num_wqebbs); wqe = MLX5E_TLS_FETCH_SET_STATIC_PARAMS_WQE(sq, pi); mlx5e_ktls_build_static_params(wqe, sq->pc, sq->sqn, &priv_tx->crypto_info, - priv_tx->tisn, priv_tx->key_id, 0, fence, - TLS_OFFLOAD_CTX_DIR_TX); + priv_tx->tisn, + mlx5_crypto_dek_get_id(priv_tx->dek), + 0, fence, TLS_OFFLOAD_CTX_DIR_TX); tx_fill_wi(sq, pi, num_wqebbs, 0, NULL); sq->pc += num_wqebbs; } @@ -894,8 +899,6 @@ static void mlx5e_tls_tx_debugfs_init(struct mlx5e_tls *tls, return; tls->debugfs.dfs_tx = debugfs_create_dir("tx", dfs_root); - if (!tls->debugfs.dfs_tx) - return; debugfs_create_size_t("pool_size", 0400, tls->debugfs.dfs_tx, &tls->tx_pool->size); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index 7f6b940830b3..08d0929e8260 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -7,7 +7,7 @@ #include "en.h" #include "lib/aso.h" -#include "lib/mlx5.h" +#include "lib/crypto.h" #include "en_accel/macsec.h" #include "en_accel/macsec_fs.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 68f19324db93..4c9a3210600c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -31,6 +31,7 @@ */ #include "en.h" +#include "lib/crypto.h" /* mlx5e global resources should be placed in this file. * Global resources are common to all the netdevices created on the same nic. @@ -104,6 +105,13 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev) INIT_LIST_HEAD(&res->td.tirs_list); mutex_init(&res->td.list_lock); + mdev->mlx5e_res.dek_priv = mlx5_crypto_dek_init(mdev); + if (IS_ERR(mdev->mlx5e_res.dek_priv)) { + mlx5_core_err(mdev, "crypto dek init failed, %ld\n", + PTR_ERR(mdev->mlx5e_res.dek_priv)); + mdev->mlx5e_res.dek_priv = NULL; + } + return 0; err_destroy_mkey: @@ -119,6 +127,8 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev) { struct mlx5e_hw_objs *res = &mdev->mlx5e_res.hw_objs; + mlx5_crypto_dek_cleanup(mdev->mlx5e_res.dek_priv); + mdev->mlx5e_res.dek_priv = NULL; mlx5_free_bfreg(mdev, &res->bfreg); mlx5_core_destroy_mkey(mdev, res->mkey); mlx5_core_dealloc_transport_domain(mdev, res->td.tdn); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 7298fe782e9e..05796f8b1d7c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -450,7 +450,7 @@ void mlx5e_enable_cvlan_filter(struct mlx5e_flow_steering *fs, bool promisc) void mlx5e_disable_cvlan_filter(struct mlx5e_flow_steering *fs, bool promisc) { - if (fs->vlan->cvlan_filter_disabled) + if (!fs->vlan || fs->vlan->cvlan_filter_disabled) return; fs->vlan->cvlan_filter_disabled = true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index e4996ef04d86..ec81d935262f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -39,6 +39,7 @@ #include <linux/if_bridge.h> #include <linux/filter.h> #include <net/page_pool.h> +#include <net/pkt_sched.h> #include <net/xdp_sock_drv.h> #include "eswitch.h" #include "en.h" @@ -180,17 +181,21 @@ static void mlx5e_disable_async_events(struct mlx5e_priv *priv) static int blocking_event(struct notifier_block *nb, unsigned long event, void *data) { struct mlx5e_priv *priv = container_of(nb, struct mlx5e_priv, blocking_events_nb); + struct mlx5_devlink_trap_event_ctx *trap_event_ctx = data; int err; switch (event) { case MLX5_DRIVER_EVENT_TYPE_TRAP: - err = mlx5e_handle_trap_event(priv, data); + err = mlx5e_handle_trap_event(priv, trap_event_ctx->trap); + if (err) { + trap_event_ctx->err = err; + return NOTIFY_BAD; + } break; default: - netdev_warn(priv->netdev, "Sync event: Unknown event %ld\n", event); - err = -EINVAL; + return NOTIFY_DONE; } - return err; + return NOTIFY_OK; } static void mlx5e_enable_blocking_events(struct mlx5e_priv *priv) @@ -592,7 +597,8 @@ static int mlx5e_init_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *param rq->ix = c->ix; rq->channel = c; rq->mdev = mdev; - rq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); + rq->hw_mtu = + MLX5E_SW2HW_MTU(params, params->sw_mtu) - ETH_FCS_LEN * !params->scatter_fcs_en; rq->xdpsq = &c->rq_xdpsq; rq->stats = &c->priv->channel_stats[c->ix]->rq; rq->ptp_cyc2time = mlx5_rq_ts_translator(mdev); @@ -1015,35 +1021,6 @@ int mlx5e_flush_rq(struct mlx5e_rq *rq, int curr_state) return mlx5e_rq_to_ready(rq, curr_state); } -static int mlx5e_modify_rq_scatter_fcs(struct mlx5e_rq *rq, bool enable) -{ - struct mlx5_core_dev *mdev = rq->mdev; - - void *in; - void *rqc; - int inlen; - int err; - - inlen = MLX5_ST_SZ_BYTES(modify_rq_in); - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) - return -ENOMEM; - - rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx); - - MLX5_SET(modify_rq_in, in, rq_state, MLX5_RQC_STATE_RDY); - MLX5_SET64(modify_rq_in, in, modify_bitmask, - MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_SCATTER_FCS); - MLX5_SET(rqc, rqc, scatter_fcs, enable); - MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RDY); - - err = mlx5_core_modify_rq(mdev, rq->rqn, in); - - kvfree(in); - - return err; -} - static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd) { struct mlx5_core_dev *mdev = rq->mdev; @@ -1470,6 +1447,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, sq->mkey_be = c->mkey_be; sq->netdev = c->netdev; sq->mdev = c->mdev; + sq->channel = c; sq->priv = c->priv; sq->ch_ix = c->ix; sq->txq_ix = txq_ix; @@ -2482,8 +2460,6 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c) mlx5e_activate_xsk(c); else mlx5e_activate_rq(&c->rq); - - mlx5e_trigger_napi_icosq(c); } static void mlx5e_deactivate_channel(struct mlx5e_channel *c) @@ -2575,13 +2551,19 @@ err_free: return err; } -static void mlx5e_activate_channels(struct mlx5e_channels *chs) +static void mlx5e_activate_channels(struct mlx5e_priv *priv, struct mlx5e_channels *chs) { int i; for (i = 0; i < chs->num; i++) mlx5e_activate_channel(chs->c[i]); + if (priv->htb) + mlx5e_qos_activate_queues(priv); + + for (i = 0; i < chs->num; i++) + mlx5e_trigger_napi_icosq(chs->c[i]); + if (chs->ptp) mlx5e_ptp_activate_channel(chs->ptp); } @@ -2888,9 +2870,7 @@ out: void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) { mlx5e_build_txq_maps(priv); - mlx5e_activate_channels(&priv->channels); - if (priv->htb) - mlx5e_qos_activate_queues(priv); + mlx5e_activate_channels(priv, &priv->channels); mlx5e_xdp_tx_enable(priv); /* dev_watchdog() wants all TX queues to be started when the carrier is @@ -2998,32 +2978,37 @@ int mlx5e_safe_switch_params(struct mlx5e_priv *priv, mlx5e_fp_preactivate preactivate, void *context, bool reset) { - struct mlx5e_channels new_chs = {}; + struct mlx5e_channels *new_chs; int err; reset &= test_bit(MLX5E_STATE_OPENED, &priv->state); if (!reset) return mlx5e_switch_priv_params(priv, params, preactivate, context); - new_chs.params = *params; + new_chs = kzalloc(sizeof(*new_chs), GFP_KERNEL); + if (!new_chs) + return -ENOMEM; + new_chs->params = *params; - mlx5e_selq_prepare_params(&priv->selq, &new_chs.params); + mlx5e_selq_prepare_params(&priv->selq, &new_chs->params); - err = mlx5e_open_channels(priv, &new_chs); + err = mlx5e_open_channels(priv, new_chs); if (err) goto err_cancel_selq; - err = mlx5e_switch_priv_channels(priv, &new_chs, preactivate, context); + err = mlx5e_switch_priv_channels(priv, new_chs, preactivate, context); if (err) goto err_close; + kfree(new_chs); return 0; err_close: - mlx5e_close_channels(&new_chs); + mlx5e_close_channels(new_chs); err_cancel_selq: mlx5e_selq_cancel(&priv->selq); + kfree(new_chs); return err; } @@ -3315,20 +3300,6 @@ static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv) mlx5e_destroy_tises(priv); } -static int mlx5e_modify_channels_scatter_fcs(struct mlx5e_channels *chs, bool enable) -{ - int err = 0; - int i; - - for (i = 0; i < chs->num; i++) { - err = mlx5e_modify_rq_scatter_fcs(&chs->c[i]->rq, enable); - if (err) - return err; - } - - return 0; -} - static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd) { int err; @@ -3904,41 +3875,27 @@ static int mlx5e_set_rx_port_ts(struct mlx5_core_dev *mdev, bool enable) return mlx5_set_ports_check(mdev, in, sizeof(in)); } +static int mlx5e_set_rx_port_ts_wrap(struct mlx5e_priv *priv, void *ctx) +{ + struct mlx5_core_dev *mdev = priv->mdev; + bool enable = *(bool *)ctx; + + return mlx5e_set_rx_port_ts(mdev, enable); +} + static int set_feature_rx_fcs(struct net_device *netdev, bool enable) { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_channels *chs = &priv->channels; - struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5e_params new_params; int err; mutex_lock(&priv->state_lock); - if (enable) { - err = mlx5e_set_rx_port_ts(mdev, false); - if (err) - goto out; - - chs->params.scatter_fcs_en = true; - err = mlx5e_modify_channels_scatter_fcs(chs, true); - if (err) { - chs->params.scatter_fcs_en = false; - mlx5e_set_rx_port_ts(mdev, true); - } - } else { - chs->params.scatter_fcs_en = false; - err = mlx5e_modify_channels_scatter_fcs(chs, false); - if (err) { - chs->params.scatter_fcs_en = true; - goto out; - } - err = mlx5e_set_rx_port_ts(mdev, true); - if (err) { - mlx5_core_warn(mdev, "Failed to set RX port timestamp %d\n", err); - err = 0; - } - } - -out: + new_params = chs->params; + new_params.scatter_fcs_en = enable; + err = mlx5e_safe_switch_params(priv, &new_params, mlx5e_set_rx_port_ts_wrap, + &new_params.scatter_fcs_en, true); mutex_unlock(&priv->state_lock); return err; } @@ -4075,6 +4032,10 @@ static netdev_features_t mlx5e_fix_uplink_rep_features(struct net_device *netdev if (netdev->features & NETIF_F_GRO_HW) netdev_warn(netdev, "Disabling HW_GRO, not supported in switchdev mode\n"); + features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; + if (netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER) + netdev_warn(netdev, "Disabling HW_VLAN CTAG FILTERING, not supported in switchdev mode\n"); + return features; } @@ -5986,7 +5947,7 @@ static int mlx5e_probe(struct auxiliary_device *adev, } mlx5e_dcbnl_init_app(priv); - mlx5_uplink_netdev_set(mdev, netdev); + mlx5_core_uplink_netdev_set(mdev, netdev); mlx5e_params_print_info(mdev, &priv->channels.params); return 0; @@ -6010,6 +5971,7 @@ static void mlx5e_remove(struct auxiliary_device *adev) struct mlx5e_priv *priv = mlx5e_dev->priv; pm_message_t state = {}; + mlx5_core_uplink_netdev_set(priv->mdev, NULL); mlx5e_dcbnl_delete_app(priv); unregister_netdev(priv->netdev); mlx5e_suspend(adev, state); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 4e6f5caf8ab6..e2ec80ebde58 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1124,8 +1124,6 @@ static void mlx5e_tc_debugfs_init(struct mlx5e_tc_table *tc, return; tc->dfs_root = debugfs_create_dir("tc", dfs_root); - if (!tc->dfs_root) - return; debugfs_create_file("hairpin_num_queues", 0644, tc->dfs_root, &tc->hairpin_params, &fops_hairpin_queues); @@ -1884,7 +1882,6 @@ post_process_attr(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr, struct netlink_ext_ack *extack) { - struct mlx5_eswitch *esw = flow->priv->mdev->priv.eswitch; bool vf_tun; int err = 0; @@ -1896,12 +1893,6 @@ post_process_attr(struct mlx5e_tc_flow *flow, if (err) goto err_out; - if (mlx5e_is_eswitch_flow(flow)) { - err = mlx5_eswitch_add_vlan_action(esw, attr); - if (err) - goto err_out; - } - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { err = mlx5e_tc_attach_mod_hdr(flow->priv, flow, attr); if (err) @@ -2105,8 +2096,6 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, if (mlx5_flow_has_geneve_opt(flow)) mlx5_geneve_tlv_option_del(priv->mdev->geneve); - mlx5_eswitch_del_vlan_action(esw, attr); - if (flow->decap_route) mlx5e_detach_decap_route(priv, flow); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 9b44557e7271..66ec7932f008 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -817,9 +817,12 @@ static void comp_irqs_release(struct mlx5_core_dev *dev) static int comp_irqs_request(struct mlx5_core_dev *dev) { struct mlx5_eq_table *table = dev->priv.eq_table; + const struct cpumask *prev = cpu_none_mask; + const struct cpumask *mask; int ncomp_eqs = table->num_comp_eqs; u16 *cpus; int ret; + int cpu; int i; ncomp_eqs = table->num_comp_eqs; @@ -838,8 +841,19 @@ static int comp_irqs_request(struct mlx5_core_dev *dev) ret = -ENOMEM; goto free_irqs; } - for (i = 0; i < ncomp_eqs; i++) - cpus[i] = cpumask_local_spread(i, dev->priv.numa_node); + + i = 0; + rcu_read_lock(); + for_each_numa_hop_mask(mask, dev->priv.numa_node) { + for_each_cpu_andnot(cpu, mask, prev) { + cpus[i] = cpu; + if (++i == ncomp_eqs) + goto spread_done; + } + prev = mask; + } +spread_done: + rcu_read_unlock(); ret = mlx5_irqs_request_vectors(dev, cpus, ncomp_eqs, table->comp_irqs); kfree(cpus); if (ret < 0) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index b176648d1343..3cdcb0e0b20f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -1715,7 +1715,7 @@ void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16 struct mlx5_esw_bridge *bridge; port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads); - if (!port || port->flags & MLX5_ESW_BRIDGE_PORT_FLAG_PEER) + if (!port) return; bridge = port->bridge; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 5b5a215a7dc5..fd03f076551b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -222,7 +222,6 @@ struct mlx5_eswitch_fdb { struct mlx5_flow_handle **send_to_vport_meta_rules; struct mlx5_flow_handle *miss_rule_uni; struct mlx5_flow_handle *miss_rule_multi; - int vlan_push_pop_refcount; struct mlx5_fs_chains *esw_chains_priv; struct { @@ -520,10 +519,6 @@ int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable, struct netlink_ext_ack *extack); void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type); -int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, - struct mlx5_flow_attr *attr); -int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw, - struct mlx5_flow_attr *attr); int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw, u16 vport, u16 vlan, u8 qos, u8 set_flags); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 3a82e385544d..8fb09143e9e8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -579,16 +579,16 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, if (esw->mode != MLX5_ESWITCH_OFFLOADS) return ERR_PTR(-EOPNOTSUPP); + if (!mlx5_eswitch_vlan_actions_supported(esw->dev, 1)) + return ERR_PTR(-EOPNOTSUPP); + dest = kcalloc(MLX5_MAX_FLOW_FWD_VPORTS + 1, sizeof(*dest), GFP_KERNEL); if (!dest) return ERR_PTR(-ENOMEM); flow_act.action = attr->action; - /* if per flow vlan pop/push is emulated, don't set that into the firmware */ - if (!mlx5_eswitch_vlan_actions_supported(esw->dev, 1)) - flow_act.action &= ~(MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH | - MLX5_FLOW_CONTEXT_ACTION_VLAN_POP); - else if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) { + + if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) { flow_act.vlan[0].ethtype = ntohs(esw_attr->vlan_proto[0]); flow_act.vlan[0].vid = esw_attr->vlan_vid[0]; flow_act.vlan[0].prio = esw_attr->vlan_prio[0]; @@ -829,204 +829,6 @@ mlx5_eswitch_del_fwd_rule(struct mlx5_eswitch *esw, __mlx5_eswitch_del_rule(esw, rule, attr, true); } -static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val) -{ - struct mlx5_eswitch_rep *rep; - unsigned long i; - int err = 0; - - esw_debug(esw->dev, "%s applying global %s policy\n", __func__, val ? "pop" : "none"); - mlx5_esw_for_each_host_func_vport(esw, i, rep, esw->esw_funcs.num_vfs) { - if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED) - continue; - - err = __mlx5_eswitch_set_vport_vlan(esw, rep->vport, 0, 0, val); - if (err) - goto out; - } - -out: - return err; -} - -static struct mlx5_eswitch_rep * -esw_vlan_action_get_vport(struct mlx5_esw_flow_attr *attr, bool push, bool pop) -{ - struct mlx5_eswitch_rep *in_rep, *out_rep, *vport = NULL; - - in_rep = attr->in_rep; - out_rep = attr->dests[0].rep; - - if (push) - vport = in_rep; - else if (pop) - vport = out_rep; - else - vport = in_rep; - - return vport; -} - -static int esw_add_vlan_action_check(struct mlx5_esw_flow_attr *attr, - bool push, bool pop, bool fwd) -{ - struct mlx5_eswitch_rep *in_rep, *out_rep; - - if ((push || pop) && !fwd) - goto out_notsupp; - - in_rep = attr->in_rep; - out_rep = attr->dests[0].rep; - - if (push && in_rep->vport == MLX5_VPORT_UPLINK) - goto out_notsupp; - - if (pop && out_rep->vport == MLX5_VPORT_UPLINK) - goto out_notsupp; - - /* vport has vlan push configured, can't offload VF --> wire rules w.o it */ - if (!push && !pop && fwd) - if (in_rep->vlan && out_rep->vport == MLX5_VPORT_UPLINK) - goto out_notsupp; - - /* protects against (1) setting rules with different vlans to push and - * (2) setting rules w.o vlans (attr->vlan = 0) && w. vlans to push (!= 0) - */ - if (push && in_rep->vlan_refcount && (in_rep->vlan != attr->vlan_vid[0])) - goto out_notsupp; - - return 0; - -out_notsupp: - return -EOPNOTSUPP; -} - -int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, - struct mlx5_flow_attr *attr) -{ - struct offloads_fdb *offloads = &esw->fdb_table.offloads; - struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; - struct mlx5_eswitch_rep *vport = NULL; - bool push, pop, fwd; - int err = 0; - - /* nop if we're on the vlan push/pop non emulation mode */ - if (mlx5_eswitch_vlan_actions_supported(esw->dev, 1)) - return 0; - - push = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH); - pop = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP); - fwd = !!((attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) && - !attr->dest_chain); - - mutex_lock(&esw->state_lock); - - err = esw_add_vlan_action_check(esw_attr, push, pop, fwd); - if (err) - goto unlock; - - attr->flags &= ~MLX5_ATTR_FLAG_VLAN_HANDLED; - - vport = esw_vlan_action_get_vport(esw_attr, push, pop); - - if (!push && !pop && fwd) { - /* tracks VF --> wire rules without vlan push action */ - if (esw_attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) { - vport->vlan_refcount++; - attr->flags |= MLX5_ATTR_FLAG_VLAN_HANDLED; - } - - goto unlock; - } - - if (!push && !pop) - goto unlock; - - if (!(offloads->vlan_push_pop_refcount)) { - /* it's the 1st vlan rule, apply global vlan pop policy */ - err = esw_set_global_vlan_pop(esw, SET_VLAN_STRIP); - if (err) - goto out; - } - offloads->vlan_push_pop_refcount++; - - if (push) { - if (vport->vlan_refcount) - goto skip_set_push; - - err = __mlx5_eswitch_set_vport_vlan(esw, vport->vport, esw_attr->vlan_vid[0], - 0, SET_VLAN_INSERT | SET_VLAN_STRIP); - if (err) - goto out; - vport->vlan = esw_attr->vlan_vid[0]; -skip_set_push: - vport->vlan_refcount++; - } -out: - if (!err) - attr->flags |= MLX5_ATTR_FLAG_VLAN_HANDLED; -unlock: - mutex_unlock(&esw->state_lock); - return err; -} - -int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw, - struct mlx5_flow_attr *attr) -{ - struct offloads_fdb *offloads = &esw->fdb_table.offloads; - struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; - struct mlx5_eswitch_rep *vport = NULL; - bool push, pop, fwd; - int err = 0; - - /* nop if we're on the vlan push/pop non emulation mode */ - if (mlx5_eswitch_vlan_actions_supported(esw->dev, 1)) - return 0; - - if (!(attr->flags & MLX5_ATTR_FLAG_VLAN_HANDLED)) - return 0; - - push = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH); - pop = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP); - fwd = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST); - - mutex_lock(&esw->state_lock); - - vport = esw_vlan_action_get_vport(esw_attr, push, pop); - - if (!push && !pop && fwd) { - /* tracks VF --> wire rules without vlan push action */ - if (esw_attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) - vport->vlan_refcount--; - - goto out; - } - - if (push) { - vport->vlan_refcount--; - if (vport->vlan_refcount) - goto skip_unset_push; - - vport->vlan = 0; - err = __mlx5_eswitch_set_vport_vlan(esw, vport->vport, - 0, 0, SET_VLAN_STRIP); - if (err) - goto out; - } - -skip_unset_push: - offloads->vlan_push_pop_refcount--; - if (offloads->vlan_push_pop_refcount) - goto out; - - /* no more vlan rules, stop global vlan pop policy */ - err = esw_set_global_vlan_pop(esw, 0); - -out: - mutex_unlock(&esw->state_lock); - return err; -} - struct mlx5_flow_handle * mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw, struct mlx5_eswitch *from_esw, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c index 9459e56ee90a..718cf09c28ce 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/events.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c @@ -424,6 +424,7 @@ int mlx5_blocking_notifier_register(struct mlx5_core_dev *dev, struct notifier_b return blocking_notifier_chain_register(&events->sw_nh, nb); } +EXPORT_SYMBOL(mlx5_blocking_notifier_register); int mlx5_blocking_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb) { @@ -431,6 +432,7 @@ int mlx5_blocking_notifier_unregister(struct mlx5_core_dev *dev, struct notifier return blocking_notifier_chain_unregister(&events->sw_nh, nb); } +EXPORT_SYMBOL(mlx5_blocking_notifier_unregister); int mlx5_blocking_notifier_call_chain(struct mlx5_core_dev *dev, unsigned int event, void *data) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 32d4c967469c..374c17445e54 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -272,8 +272,6 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns, unsigned int size; int err; - if (ft_attr->max_fte != POOL_NEXT_SIZE) - size = roundup_pow_of_two(ft_attr->max_fte); size = mlx5_ft_pool_get_avail_sz(dev, ft->type, ft_attr->max_fte); if (!size) return -ENOSPC; @@ -412,11 +410,6 @@ static int mlx5_cmd_create_flow_group(struct mlx5_flow_root_namespace *ns, MLX5_CMD_OP_CREATE_FLOW_GROUP); MLX5_SET(create_flow_group_in, in, table_type, ft->type); MLX5_SET(create_flow_group_in, in, table_id, ft->id); - if (ft->vport) { - MLX5_SET(create_flow_group_in, in, vport_number, ft->vport); - MLX5_SET(create_flow_group_in, in, other_vport, 1); - } - MLX5_SET(create_flow_group_in, in, vport_number, ft->vport); MLX5_SET(create_flow_group_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index dd43a940499b..fad479df12e4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1776,7 +1776,6 @@ static int build_match_list(struct match_list *match_head, { struct rhlist_head *tmp, *list; struct mlx5_flow_group *g; - int err = 0; rcu_read_lock(); INIT_LIST_HEAD(&match_head->list); @@ -1802,7 +1801,7 @@ static int build_match_list(struct match_list *match_head, list_add_tail(&curr_match->list, &match_head->list); } rcu_read_unlock(); - return err; + return 0; } static u64 matched_fgs_get_version(struct list_head *match_head) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index f34e758a2f1f..7bb7be01225a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -267,6 +267,12 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) return err; } + if (MLX5_CAP_GEN(dev, crypto)) { + err = mlx5_core_get_caps(dev, MLX5_CAP_CRYPTO); + if (err) + return err; + } + if (MLX5_CAP_GEN(dev, shampo)) { err = mlx5_core_get_caps(dev, MLX5_CAP_DEV_SHAMPO); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 1da4da564e6d..63290da84010 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -371,6 +371,7 @@ static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev) mlx5_core_err(dev, "PCI link not ready (0x%04x) after %llu ms\n", reg16, mlx5_tout_ms(dev, PCI_TOGGLE)); err = -ETIMEDOUT; + goto restore; } do { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 879555ba847d..1e8bee906c31 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -62,7 +62,7 @@ enum { }; enum { - MLX5_DROP_NEW_HEALTH_WORK, + MLX5_DROP_HEALTH_WORK, }; enum { @@ -675,7 +675,7 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work) devlink = priv_to_devlink(dev); mutex_lock(&dev->intf_state_mutex); - if (test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) { + if (test_bit(MLX5_DROP_HEALTH_WORK, &health->flags)) { mlx5_core_err(dev, "health works are not permitted at this stage\n"); mutex_unlock(&dev->intf_state_mutex); return; @@ -771,14 +771,8 @@ static unsigned long get_next_poll_jiffies(struct mlx5_core_dev *dev) void mlx5_trigger_health_work(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; - unsigned long flags; - spin_lock_irqsave(&health->wq_lock, flags); - if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) - queue_work(health->wq, &health->fatal_report_work); - else - mlx5_core_err(dev, "new health works are not permitted at this stage\n"); - spin_unlock_irqrestore(&health->wq_lock, flags); + queue_work(health->wq, &health->fatal_report_work); } #define MLX5_MSEC_PER_HOUR (MSEC_PER_SEC * 60 * 60) @@ -858,7 +852,7 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev) timer_setup(&health->timer, poll_health, 0); health->fatal_error = MLX5_SENSOR_NO_ERR; - clear_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); + clear_bit(MLX5_DROP_HEALTH_WORK, &health->flags); health->health = &dev->iseg->health; health->health_counter = &dev->iseg->health_counter; @@ -869,13 +863,9 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev) void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health) { struct mlx5_core_health *health = &dev->priv.health; - unsigned long flags; - if (disable_health) { - spin_lock_irqsave(&health->wq_lock, flags); - set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); - spin_unlock_irqrestore(&health->wq_lock, flags); - } + if (disable_health) + set_bit(MLX5_DROP_HEALTH_WORK, &health->flags); del_timer_sync(&health->timer); } @@ -891,11 +881,8 @@ void mlx5_start_health_fw_log_up(struct mlx5_core_dev *dev) void mlx5_drain_health_wq(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; - unsigned long flags; - spin_lock_irqsave(&health->wq_lock, flags); - set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); - spin_unlock_irqrestore(&health->wq_lock, flags); + set_bit(MLX5_DROP_HEALTH_WORK, &health->flags); cancel_delayed_work_sync(&health->update_fw_log_ts_work); cancel_work_sync(&health->report_work); cancel_work_sync(&health->fatal_report_work); @@ -928,7 +915,6 @@ int mlx5_health_init(struct mlx5_core_dev *dev) kfree(name); if (!health->wq) goto out_err; - spin_lock_init(&health->wq_lock); INIT_WORK(&health->fatal_report_work, mlx5_fw_fatal_reporter_err_work); INIT_WORK(&health->report_work, mlx5_fw_reporter_err_work); INIT_DELAYED_WORK(&health->update_fw_log_ts_work, mlx5_health_log_ts_update); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index eff92dc0927c..779d92b762d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -172,6 +172,7 @@ enum mlx5_ptys_rate { MLX5_PTYS_RATE_EDR = 1 << 5, MLX5_PTYS_RATE_HDR = 1 << 6, MLX5_PTYS_RATE_NDR = 1 << 7, + MLX5_PTYS_RATE_XDR = 1 << 8, }; static inline int mlx5_ptys_rate_enum_to_int(enum mlx5_ptys_rate rate) @@ -185,20 +186,21 @@ static inline int mlx5_ptys_rate_enum_to_int(enum mlx5_ptys_rate rate) case MLX5_PTYS_RATE_EDR: return 25000; case MLX5_PTYS_RATE_HDR: return 50000; case MLX5_PTYS_RATE_NDR: return 100000; + case MLX5_PTYS_RATE_XDR: return 200000; default: return -1; } } -static int mlx5i_get_speed_settings(u16 ib_link_width_oper, u16 ib_proto_oper) +static u32 mlx5i_get_speed_settings(u16 ib_link_width_oper, u16 ib_proto_oper) { int rate, width; rate = mlx5_ptys_rate_enum_to_int(ib_proto_oper); if (rate < 0) - return -EINVAL; + return SPEED_UNKNOWN; width = mlx5_ptys_width_enum_to_int(ib_link_width_oper); if (width < 0) - return -EINVAL; + return SPEED_UNKNOWN; return rate * width; } @@ -221,16 +223,13 @@ static int mlx5i_get_link_ksettings(struct net_device *netdev, ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); speed = mlx5i_get_speed_settings(ib_link_width_oper, ib_proto_oper); - if (speed < 0) - return -EINVAL; + link_ksettings->base.speed = speed; + link_ksettings->base.duplex = speed == SPEED_UNKNOWN ? DUPLEX_UNKNOWN : DUPLEX_FULL; - link_ksettings->base.duplex = DUPLEX_FULL; link_ksettings->base.port = PORT_OTHER; link_ksettings->base.autoneg = AUTONEG_DISABLE; - link_ksettings->base.speed = speed; - return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c index b8feaf0f5c4c..f4b777d4e108 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c @@ -22,7 +22,7 @@ static int type_show(struct seq_file *file, void *priv) struct mlx5_lag *ldev; char *mode = NULL; - ldev = dev->priv.lag; + ldev = mlx5_lag_dev(dev); mutex_lock(&ldev->lock); if (__mlx5_lag_is_active(ldev)) mode = get_str_mode_type(ldev); @@ -41,7 +41,7 @@ static int port_sel_mode_show(struct seq_file *file, void *priv) int ret = 0; char *mode; - ldev = dev->priv.lag; + ldev = mlx5_lag_dev(dev); mutex_lock(&ldev->lock); if (__mlx5_lag_is_active(ldev)) mode = mlx5_get_str_port_sel_mode(ldev->mode, ldev->mode_flags); @@ -61,7 +61,7 @@ static int state_show(struct seq_file *file, void *priv) struct mlx5_lag *ldev; bool active; - ldev = dev->priv.lag; + ldev = mlx5_lag_dev(dev); mutex_lock(&ldev->lock); active = __mlx5_lag_is_active(ldev); mutex_unlock(&ldev->lock); @@ -77,7 +77,7 @@ static int flags_show(struct seq_file *file, void *priv) bool shared_fdb; bool lag_active; - ldev = dev->priv.lag; + ldev = mlx5_lag_dev(dev); mutex_lock(&ldev->lock); lag_active = __mlx5_lag_is_active(ldev); if (!lag_active) @@ -108,7 +108,7 @@ static int mapping_show(struct seq_file *file, void *priv) int num_ports; int i; - ldev = dev->priv.lag; + ldev = mlx5_lag_dev(dev); mutex_lock(&ldev->lock); lag_active = __mlx5_lag_is_active(ldev); if (lag_active) { @@ -142,7 +142,7 @@ static int members_show(struct seq_file *file, void *priv) struct mlx5_lag *ldev; int i; - ldev = dev->priv.lag; + ldev = mlx5_lag_dev(dev); mutex_lock(&ldev->lock); for (i = 0; i < ldev->ports; i++) { if (!ldev->pf[i].dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index ad32b80e8501..dbf218cac535 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -1187,7 +1187,7 @@ static int __mlx5_lag_dev_add_mdev(struct mlx5_core_dev *dev) tmp_dev = mlx5_get_next_phys_dev_lag(dev); if (tmp_dev) - ldev = tmp_dev->priv.lag; + ldev = mlx5_lag_dev(tmp_dev); if (!ldev) { ldev = mlx5_lag_dev_alloc(dev); @@ -1386,8 +1386,7 @@ bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev) spin_lock_irqsave(&lag_lock, flags); ldev = mlx5_lag_dev(dev); - res = ldev && __mlx5_lag_is_sriov(ldev) && - test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags); + res = ldev && test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags); spin_unlock_irqrestore(&lag_lock, flags); return res; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h index f30ac2de639f..66013bef9939 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h @@ -50,19 +50,6 @@ struct lag_tracker { enum netdev_lag_hash hash_type; }; -enum mpesw_op { - MLX5_MPESW_OP_ENABLE, - MLX5_MPESW_OP_DISABLE, -}; - -struct mlx5_mpesw_work_st { - struct work_struct work; - struct mlx5_lag *lag; - enum mpesw_op op; - struct completion comp; - int result; -}; - /* LAG data of a ConnectX card. * It serves both its phys functions. */ @@ -124,8 +111,6 @@ int mlx5_activate_lag(struct mlx5_lag *ldev, int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev, struct net_device *ndev); bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev); -void mlx5_lag_del_mpesw_rule(struct mlx5_core_dev *dev); -int mlx5_lag_add_mpesw_rule(struct mlx5_core_dev *dev); char *mlx5_get_str_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags); void mlx5_infer_tx_enabled(struct lag_tracker *tracker, u8 num_ports, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c index d9fcb9ed726f..d85a8dfc153d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c @@ -28,13 +28,9 @@ static bool mlx5_lag_multipath_check_prereq(struct mlx5_lag *ldev) bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev) { - struct mlx5_lag *ldev; - bool res; - - ldev = mlx5_lag_dev(dev); - res = ldev && __mlx5_lag_is_multipath(ldev); + struct mlx5_lag *ldev = mlx5_lag_dev(dev); - return res; + return ldev && __mlx5_lag_is_multipath(ldev); } /** diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c index c17e8f1ec914..3799f89ed1a6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c @@ -58,7 +58,7 @@ static void mlx5_mpesw_work(struct work_struct *work) static int mlx5_lag_mpesw_queue_work(struct mlx5_core_dev *dev, enum mpesw_op op) { - struct mlx5_lag *ldev = dev->priv.lag; + struct mlx5_lag *ldev = mlx5_lag_dev(dev); struct mlx5_mpesw_work_st *work; int err = 0; @@ -96,25 +96,27 @@ int mlx5_lag_add_mpesw_rule(struct mlx5_core_dev *dev) return mlx5_lag_mpesw_queue_work(dev, MLX5_MPESW_OP_ENABLE); } -int mlx5_lag_do_mirred(struct mlx5_core_dev *mdev, struct net_device *out_dev) +int mlx5_lag_mpesw_do_mirred(struct mlx5_core_dev *mdev, + struct net_device *out_dev, + struct netlink_ext_ack *extack) { - struct mlx5_lag *ldev = mdev->priv.lag; + struct mlx5_lag *ldev = mlx5_lag_dev(mdev); if (!netif_is_bond_master(out_dev) || !ldev) return 0; - if (ldev->mode == MLX5_LAG_MODE_MPESW) - return -EOPNOTSUPP; + if (ldev->mode != MLX5_LAG_MODE_MPESW) + return 0; - return 0; + NL_SET_ERR_MSG_MOD(extack, "can't forward to bond in mpesw mode"); + return -EOPNOTSUPP; } bool mlx5_lag_mpesw_is_activated(struct mlx5_core_dev *dev) { - bool ret; + struct mlx5_lag *ldev = mlx5_lag_dev(dev); - ret = dev->priv.lag && dev->priv.lag->mode == MLX5_LAG_MODE_MPESW; - return ret; + return ldev && ldev->mode == MLX5_LAG_MODE_MPESW; } void mlx5_lag_mpesw_init(struct mlx5_lag *ldev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h index 88e8daffcf92..818f19b5a984 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h @@ -12,8 +12,25 @@ struct lag_mpesw { atomic_t mpesw_rule_count; }; -int mlx5_lag_do_mirred(struct mlx5_core_dev *mdev, struct net_device *out_dev); +enum mpesw_op { + MLX5_MPESW_OP_ENABLE, + MLX5_MPESW_OP_DISABLE, +}; + +struct mlx5_mpesw_work_st { + struct work_struct work; + struct mlx5_lag *lag; + enum mpesw_op op; + struct completion comp; + int result; +}; + +int mlx5_lag_mpesw_do_mirred(struct mlx5_core_dev *mdev, + struct net_device *out_dev, + struct netlink_ext_ack *extack); bool mlx5_lag_mpesw_is_activated(struct mlx5_core_dev *dev); +void mlx5_lag_del_mpesw_rule(struct mlx5_core_dev *dev); +int mlx5_lag_add_mpesw_rule(struct mlx5_core_dev *dev); #if IS_ENABLED(CONFIG_MLX5_ESWITCH) void mlx5_lag_mpesw_init(struct mlx5_lag *ldev); void mlx5_lag_mpesw_cleanup(struct mlx5_lag *ldev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 75510a12ab02..4c9a40211059 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -362,7 +362,7 @@ static int mlx5_ptp_adjphase(struct ptp_clock_info *ptp, s32 delta) return mlx5_ptp_adjtime(ptp, delta); } -static int mlx5_ptp_adjfreq_real_time(struct mlx5_core_dev *mdev, s32 freq) +static int mlx5_ptp_freq_adj_real_time(struct mlx5_core_dev *mdev, long scaled_ppm) { u32 in[MLX5_ST_SZ_DW(mtutc_reg)] = {}; @@ -370,7 +370,15 @@ static int mlx5_ptp_adjfreq_real_time(struct mlx5_core_dev *mdev, s32 freq) return 0; MLX5_SET(mtutc_reg, in, operation, MLX5_MTUTC_OPERATION_ADJUST_FREQ_UTC); - MLX5_SET(mtutc_reg, in, freq_adjustment, freq); + + if (MLX5_CAP_MCAM_FEATURE(mdev, mtutc_freq_adj_units)) { + MLX5_SET(mtutc_reg, in, freq_adj_units, + MLX5_MTUTC_FREQ_ADJ_UNITS_SCALED_PPM); + MLX5_SET(mtutc_reg, in, freq_adjustment, scaled_ppm); + } else { + MLX5_SET(mtutc_reg, in, freq_adj_units, MLX5_MTUTC_FREQ_ADJ_UNITS_PPB); + MLX5_SET(mtutc_reg, in, freq_adjustment, scaled_ppm_to_ppb(scaled_ppm)); + } return mlx5_set_mtutc(mdev, in, sizeof(in)); } @@ -385,7 +393,8 @@ static int mlx5_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) int err; mdev = container_of(clock, struct mlx5_core_dev, clock); - err = mlx5_ptp_adjfreq_real_time(mdev, scaled_ppm_to_ppb(scaled_ppm)); + + err = mlx5_ptp_freq_adj_real_time(mdev, scaled_ppm); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.c index e995f8378df7..3a94b8f8031e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.c @@ -2,53 +2,253 @@ // Copyright (c) 2019 Mellanox Technologies. #include "mlx5_core.h" -#include "lib/mlx5.h" +#include "lib/crypto.h" -int mlx5_create_encryption_key(struct mlx5_core_dev *mdev, - void *key, u32 sz_bytes, - u32 key_type, u32 *p_key_id) -{ - u32 in[MLX5_ST_SZ_DW(create_encryption_key_in)] = {}; - u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)]; - u32 sz_bits = sz_bytes * BITS_PER_BYTE; - u8 general_obj_key_size; - u64 general_obj_types; - void *obj, *key_p; - int err; +#define MLX5_CRYPTO_DEK_POOLS_NUM (MLX5_ACCEL_OBJ_TYPE_KEY_NUM - 1) +#define type2idx(type) ((type) - 1) - obj = MLX5_ADDR_OF(create_encryption_key_in, in, encryption_key_object); - key_p = MLX5_ADDR_OF(encryption_key_obj, obj, key); +#define MLX5_CRYPTO_DEK_POOL_SYNC_THRESH 128 - general_obj_types = MLX5_CAP_GEN_64(mdev, general_obj_types); - if (!(general_obj_types & - MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY)) - return -EINVAL; +/* calculate the num of DEKs, which are freed by any user + * (for example, TLS) after last revalidation in a pool or a bulk. + */ +#define MLX5_CRYPTO_DEK_CALC_FREED(a) \ + ({ typeof(a) _a = (a); \ + _a->num_deks - _a->avail_deks - _a->in_use_deks; }) + +#define MLX5_CRYPTO_DEK_POOL_CALC_FREED(pool) MLX5_CRYPTO_DEK_CALC_FREED(pool) +#define MLX5_CRYPTO_DEK_BULK_CALC_FREED(bulk) MLX5_CRYPTO_DEK_CALC_FREED(bulk) + +#define MLX5_CRYPTO_DEK_BULK_IDLE(bulk) \ + ({ typeof(bulk) _bulk = (bulk); \ + _bulk->avail_deks == _bulk->num_deks; }) + +enum { + MLX5_CRYPTO_DEK_ALL_TYPE = BIT(0), +}; + +struct mlx5_crypto_dek_pool { + struct mlx5_core_dev *mdev; + u32 key_purpose; + int num_deks; /* the total number of keys in this pool */ + int avail_deks; /* the number of available keys in this pool */ + int in_use_deks; /* the number of being used keys in this pool */ + struct mutex lock; /* protect the following lists, and the bulks */ + struct list_head partial_list; /* some of keys are available */ + struct list_head full_list; /* no available keys */ + struct list_head avail_list; /* all keys are available to use */ + + /* No in-used keys, and all need to be synced. + * These bulks will be put to avail list after sync. + */ + struct list_head sync_list; + + bool syncing; + struct list_head wait_for_free; + struct work_struct sync_work; + + spinlock_t destroy_lock; /* protect destroy_list */ + struct list_head destroy_list; + struct work_struct destroy_work; +}; + +struct mlx5_crypto_dek_bulk { + struct mlx5_core_dev *mdev; + int base_obj_id; + int avail_start; /* the bit to start search */ + int num_deks; /* the total number of keys in a bulk */ + int avail_deks; /* the number of keys available, with need_sync bit 0 */ + int in_use_deks; /* the number of keys being used, with in_use bit 1 */ + struct list_head entry; + + /* 0: not being used by any user, 1: otherwise */ + unsigned long *in_use; + + /* The bits are set when they are used, and reset after crypto_sync + * is executed. So, the value 0 means the key is newly created, or not + * used after sync, and 1 means it is in use, or freed but not synced + */ + unsigned long *need_sync; +}; + +struct mlx5_crypto_dek_priv { + struct mlx5_core_dev *mdev; + int log_dek_obj_range; +}; + +struct mlx5_crypto_dek { + struct mlx5_crypto_dek_bulk *bulk; + struct list_head entry; + u32 obj_id; +}; + +u32 mlx5_crypto_dek_get_id(struct mlx5_crypto_dek *dek) +{ + return dek->obj_id; +} + +static int mlx5_crypto_dek_get_key_sz(struct mlx5_core_dev *mdev, + u32 sz_bytes, u8 *key_sz_p) +{ + u32 sz_bits = sz_bytes * BITS_PER_BYTE; switch (sz_bits) { case 128: - general_obj_key_size = - MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_128; - key_p += sz_bytes; + *key_sz_p = MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_128; break; case 256: - general_obj_key_size = - MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_256; + *key_sz_p = MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_256; break; default: + mlx5_core_err(mdev, "Crypto offload error, invalid key size (%u bits)\n", + sz_bits); return -EINVAL; } - memcpy(key_p, key, sz_bytes); + return 0; +} + +static int mlx5_crypto_dek_fill_key(struct mlx5_core_dev *mdev, u8 *key_obj, + const void *key, u32 sz_bytes) +{ + void *dst; + u8 key_sz; + int err; + + err = mlx5_crypto_dek_get_key_sz(mdev, sz_bytes, &key_sz); + if (err) + return err; + + MLX5_SET(encryption_key_obj, key_obj, key_size, key_sz); + + if (sz_bytes == 16) + /* For key size of 128b the MSBs are reserved. */ + dst = MLX5_ADDR_OF(encryption_key_obj, key_obj, key[1]); + else + dst = MLX5_ADDR_OF(encryption_key_obj, key_obj, key); + + memcpy(dst, key, sz_bytes); + + return 0; +} + +static int mlx5_crypto_cmd_sync_crypto(struct mlx5_core_dev *mdev, + int crypto_type) +{ + u32 in[MLX5_ST_SZ_DW(sync_crypto_in)] = {}; + int err; + + mlx5_core_dbg(mdev, + "Execute SYNC_CRYPTO command with crypto_type(0x%x)\n", + crypto_type); + + MLX5_SET(sync_crypto_in, in, opcode, MLX5_CMD_OP_SYNC_CRYPTO); + MLX5_SET(sync_crypto_in, in, crypto_type, crypto_type); + + err = mlx5_cmd_exec_in(mdev, sync_crypto, in); + if (err) + mlx5_core_err(mdev, + "Failed to exec sync crypto, type=%d, err=%d\n", + crypto_type, err); + + return err; +} + +static int mlx5_crypto_create_dek_bulk(struct mlx5_core_dev *mdev, + u32 key_purpose, int log_obj_range, + u32 *obj_id) +{ + u32 in[MLX5_ST_SZ_DW(create_encryption_key_in)] = {}; + u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)]; + void *obj, *param; + int err; - MLX5_SET(encryption_key_obj, obj, key_size, general_obj_key_size); - MLX5_SET(encryption_key_obj, obj, key_type, key_type); MLX5_SET(general_obj_in_cmd_hdr, in, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT); MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY); + param = MLX5_ADDR_OF(general_obj_in_cmd_hdr, in, op_param); + MLX5_SET(general_obj_create_param, param, log_obj_range, log_obj_range); + + obj = MLX5_ADDR_OF(create_encryption_key_in, in, encryption_key_object); + MLX5_SET(encryption_key_obj, obj, key_purpose, key_purpose); MLX5_SET(encryption_key_obj, obj, pd, mdev->mlx5e_res.hw_objs.pdn); err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); + if (err) + return err; + + *obj_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id); + mlx5_core_dbg(mdev, "DEK objects created, bulk=%d, obj_id=%d\n", + 1 << log_obj_range, *obj_id); + + return 0; +} + +static int mlx5_crypto_modify_dek_key(struct mlx5_core_dev *mdev, + const void *key, u32 sz_bytes, u32 key_purpose, + u32 obj_id, u32 obj_offset) +{ + u32 in[MLX5_ST_SZ_DW(modify_encryption_key_in)] = {}; + u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)]; + void *obj, *param; + int err; + + MLX5_SET(general_obj_in_cmd_hdr, in, opcode, + MLX5_CMD_OP_MODIFY_GENERAL_OBJECT); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, + MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, obj_id); + + param = MLX5_ADDR_OF(general_obj_in_cmd_hdr, in, op_param); + MLX5_SET(general_obj_query_param, param, obj_offset, obj_offset); + + obj = MLX5_ADDR_OF(modify_encryption_key_in, in, encryption_key_object); + MLX5_SET64(encryption_key_obj, obj, modify_field_select, 1); + MLX5_SET(encryption_key_obj, obj, key_purpose, key_purpose); + MLX5_SET(encryption_key_obj, obj, pd, mdev->mlx5e_res.hw_objs.pdn); + + err = mlx5_crypto_dek_fill_key(mdev, obj, key, sz_bytes); + if (err) + return err; + + err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); + + /* avoid leaking key on the stack */ + memzero_explicit(in, sizeof(in)); + + return err; +} + +static int mlx5_crypto_create_dek_key(struct mlx5_core_dev *mdev, + const void *key, u32 sz_bytes, + u32 key_purpose, u32 *p_key_id) +{ + u32 in[MLX5_ST_SZ_DW(create_encryption_key_in)] = {}; + u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)]; + u64 general_obj_types; + void *obj; + int err; + + general_obj_types = MLX5_CAP_GEN_64(mdev, general_obj_types); + if (!(general_obj_types & + MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY)) + return -EINVAL; + + MLX5_SET(general_obj_in_cmd_hdr, in, opcode, + MLX5_CMD_OP_CREATE_GENERAL_OBJECT); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, + MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY); + + obj = MLX5_ADDR_OF(create_encryption_key_in, in, encryption_key_object); + MLX5_SET(encryption_key_obj, obj, key_purpose, key_purpose); + MLX5_SET(encryption_key_obj, obj, pd, mdev->mlx5e_res.hw_objs.pdn); + + err = mlx5_crypto_dek_fill_key(mdev, obj, key, sz_bytes); + if (err) + return err; + + err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); if (!err) *p_key_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id); @@ -58,7 +258,7 @@ int mlx5_create_encryption_key(struct mlx5_core_dev *mdev, return err; } -void mlx5_destroy_encryption_key(struct mlx5_core_dev *mdev, u32 key_id) +static void mlx5_crypto_destroy_dek_key(struct mlx5_core_dev *mdev, u32 key_id) { u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {}; u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)]; @@ -71,3 +271,504 @@ void mlx5_destroy_encryption_key(struct mlx5_core_dev *mdev, u32 key_id) mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); } + +int mlx5_create_encryption_key(struct mlx5_core_dev *mdev, + const void *key, u32 sz_bytes, + u32 key_type, u32 *p_key_id) +{ + return mlx5_crypto_create_dek_key(mdev, key, sz_bytes, key_type, p_key_id); +} + +void mlx5_destroy_encryption_key(struct mlx5_core_dev *mdev, u32 key_id) +{ + mlx5_crypto_destroy_dek_key(mdev, key_id); +} + +static struct mlx5_crypto_dek_bulk * +mlx5_crypto_dek_bulk_create(struct mlx5_crypto_dek_pool *pool) +{ + struct mlx5_crypto_dek_priv *dek_priv = pool->mdev->mlx5e_res.dek_priv; + struct mlx5_core_dev *mdev = pool->mdev; + struct mlx5_crypto_dek_bulk *bulk; + int num_deks, base_obj_id; + int err; + + bulk = kzalloc(sizeof(*bulk), GFP_KERNEL); + if (!bulk) + return ERR_PTR(-ENOMEM); + + num_deks = 1 << dek_priv->log_dek_obj_range; + bulk->need_sync = bitmap_zalloc(num_deks, GFP_KERNEL); + if (!bulk->need_sync) { + err = -ENOMEM; + goto err_out; + } + + bulk->in_use = bitmap_zalloc(num_deks, GFP_KERNEL); + if (!bulk->in_use) { + err = -ENOMEM; + goto err_out; + } + + err = mlx5_crypto_create_dek_bulk(mdev, pool->key_purpose, + dek_priv->log_dek_obj_range, + &base_obj_id); + if (err) + goto err_out; + + bulk->base_obj_id = base_obj_id; + bulk->num_deks = num_deks; + bulk->avail_deks = num_deks; + bulk->mdev = mdev; + + return bulk; + +err_out: + bitmap_free(bulk->in_use); + bitmap_free(bulk->need_sync); + kfree(bulk); + return ERR_PTR(err); +} + +static struct mlx5_crypto_dek_bulk * +mlx5_crypto_dek_pool_add_bulk(struct mlx5_crypto_dek_pool *pool) +{ + struct mlx5_crypto_dek_bulk *bulk; + + bulk = mlx5_crypto_dek_bulk_create(pool); + if (IS_ERR(bulk)) + return bulk; + + pool->avail_deks += bulk->num_deks; + pool->num_deks += bulk->num_deks; + list_add(&bulk->entry, &pool->partial_list); + + return bulk; +} + +static void mlx5_crypto_dek_bulk_free(struct mlx5_crypto_dek_bulk *bulk) +{ + mlx5_crypto_destroy_dek_key(bulk->mdev, bulk->base_obj_id); + bitmap_free(bulk->need_sync); + bitmap_free(bulk->in_use); + kfree(bulk); +} + +static void mlx5_crypto_dek_pool_remove_bulk(struct mlx5_crypto_dek_pool *pool, + struct mlx5_crypto_dek_bulk *bulk, + bool delay) +{ + pool->num_deks -= bulk->num_deks; + pool->avail_deks -= bulk->avail_deks; + pool->in_use_deks -= bulk->in_use_deks; + list_del(&bulk->entry); + if (!delay) + mlx5_crypto_dek_bulk_free(bulk); +} + +static struct mlx5_crypto_dek_bulk * +mlx5_crypto_dek_pool_pop(struct mlx5_crypto_dek_pool *pool, u32 *obj_offset) +{ + struct mlx5_crypto_dek_bulk *bulk; + int pos; + + mutex_lock(&pool->lock); + bulk = list_first_entry_or_null(&pool->partial_list, + struct mlx5_crypto_dek_bulk, entry); + + if (bulk) { + pos = find_next_zero_bit(bulk->need_sync, bulk->num_deks, + bulk->avail_start); + if (pos == bulk->num_deks) { + mlx5_core_err(pool->mdev, "Wrong DEK bulk avail_start.\n"); + pos = find_first_zero_bit(bulk->need_sync, bulk->num_deks); + } + WARN_ON(pos == bulk->num_deks); + } else { + bulk = list_first_entry_or_null(&pool->avail_list, + struct mlx5_crypto_dek_bulk, + entry); + if (bulk) { + list_move(&bulk->entry, &pool->partial_list); + } else { + bulk = mlx5_crypto_dek_pool_add_bulk(pool); + if (IS_ERR(bulk)) + goto out; + } + pos = 0; + } + + *obj_offset = pos; + bitmap_set(bulk->need_sync, pos, 1); + bitmap_set(bulk->in_use, pos, 1); + bulk->in_use_deks++; + bulk->avail_deks--; + if (!bulk->avail_deks) { + list_move(&bulk->entry, &pool->full_list); + bulk->avail_start = bulk->num_deks; + } else { + bulk->avail_start = pos + 1; + } + pool->avail_deks--; + pool->in_use_deks++; + +out: + mutex_unlock(&pool->lock); + return bulk; +} + +static bool mlx5_crypto_dek_need_sync(struct mlx5_crypto_dek_pool *pool) +{ + return !pool->syncing && + MLX5_CRYPTO_DEK_POOL_CALC_FREED(pool) > MLX5_CRYPTO_DEK_POOL_SYNC_THRESH; +} + +static int mlx5_crypto_dek_free_locked(struct mlx5_crypto_dek_pool *pool, + struct mlx5_crypto_dek *dek) +{ + struct mlx5_crypto_dek_bulk *bulk = dek->bulk; + int obj_offset; + bool old_val; + int err = 0; + + obj_offset = dek->obj_id - bulk->base_obj_id; + old_val = test_and_clear_bit(obj_offset, bulk->in_use); + WARN_ON_ONCE(!old_val); + if (!old_val) { + err = -ENOENT; + goto out_free; + } + pool->in_use_deks--; + bulk->in_use_deks--; + if (!bulk->avail_deks && !bulk->in_use_deks) + list_move(&bulk->entry, &pool->sync_list); + + if (mlx5_crypto_dek_need_sync(pool) && schedule_work(&pool->sync_work)) + pool->syncing = true; + +out_free: + kfree(dek); + return err; +} + +static int mlx5_crypto_dek_pool_push(struct mlx5_crypto_dek_pool *pool, + struct mlx5_crypto_dek *dek) +{ + int err = 0; + + mutex_lock(&pool->lock); + if (pool->syncing) + list_add(&dek->entry, &pool->wait_for_free); + else + err = mlx5_crypto_dek_free_locked(pool, dek); + mutex_unlock(&pool->lock); + + return err; +} + +/* Update the bits for a bulk while sync, and avail_next for search. + * As the combinations of (need_sync, in_use) of one DEK are + * - (0,0) means the key is ready for use, + * - (1,1) means the key is currently being used by a user, + * - (1,0) means the key is freed, and waiting for being synced, + * - (0,1) is invalid state. + * the number of revalidated DEKs can be calculated by + * hweight_long(need_sync XOR in_use), and the need_sync bits can be reset + * by simply copying from in_use bits. + */ +static void mlx5_crypto_dek_bulk_reset_synced(struct mlx5_crypto_dek_pool *pool, + struct mlx5_crypto_dek_bulk *bulk) +{ + unsigned long *need_sync = bulk->need_sync; + unsigned long *in_use = bulk->in_use; + int i, freed, reused, avail_next; + bool first = true; + + freed = MLX5_CRYPTO_DEK_BULK_CALC_FREED(bulk); + + for (i = 0; freed && i < BITS_TO_LONGS(bulk->num_deks); + i++, need_sync++, in_use++) { + reused = hweight_long((*need_sync) ^ (*in_use)); + if (!reused) + continue; + + bulk->avail_deks += reused; + pool->avail_deks += reused; + *need_sync = *in_use; + if (first) { + avail_next = i * BITS_PER_TYPE(long); + if (bulk->avail_start > avail_next) + bulk->avail_start = avail_next; + first = false; + } + + freed -= reused; + } +} + +/* Return true if the bulk is reused, false if destroyed with delay */ +static bool mlx5_crypto_dek_bulk_handle_avail(struct mlx5_crypto_dek_pool *pool, + struct mlx5_crypto_dek_bulk *bulk, + struct list_head *destroy_list) +{ + if (list_empty(&pool->avail_list)) { + list_move(&bulk->entry, &pool->avail_list); + return true; + } + + mlx5_crypto_dek_pool_remove_bulk(pool, bulk, true); + list_add(&bulk->entry, destroy_list); + return false; +} + +static void mlx5_crypto_dek_pool_splice_destroy_list(struct mlx5_crypto_dek_pool *pool, + struct list_head *list, + struct list_head *head) +{ + spin_lock(&pool->destroy_lock); + list_splice_init(list, head); + spin_unlock(&pool->destroy_lock); +} + +static void mlx5_crypto_dek_pool_free_wait_keys(struct mlx5_crypto_dek_pool *pool) +{ + struct mlx5_crypto_dek *dek, *next; + + list_for_each_entry_safe(dek, next, &pool->wait_for_free, entry) { + list_del(&dek->entry); + mlx5_crypto_dek_free_locked(pool, dek); + } +} + +/* For all the bulks in each list, reset the bits while sync. + * Move them to different lists according to the number of available DEKs. + * Destrory all the idle bulks, except one for quick service. + * And free DEKs in the waiting list at the end of this func. + */ +static void mlx5_crypto_dek_pool_reset_synced(struct mlx5_crypto_dek_pool *pool) +{ + struct mlx5_crypto_dek_bulk *bulk, *tmp; + LIST_HEAD(destroy_list); + + list_for_each_entry_safe(bulk, tmp, &pool->partial_list, entry) { + mlx5_crypto_dek_bulk_reset_synced(pool, bulk); + if (MLX5_CRYPTO_DEK_BULK_IDLE(bulk)) + mlx5_crypto_dek_bulk_handle_avail(pool, bulk, &destroy_list); + } + + list_for_each_entry_safe(bulk, tmp, &pool->full_list, entry) { + mlx5_crypto_dek_bulk_reset_synced(pool, bulk); + + if (!bulk->avail_deks) + continue; + + if (MLX5_CRYPTO_DEK_BULK_IDLE(bulk)) + mlx5_crypto_dek_bulk_handle_avail(pool, bulk, &destroy_list); + else + list_move(&bulk->entry, &pool->partial_list); + } + + list_for_each_entry_safe(bulk, tmp, &pool->sync_list, entry) { + bulk->avail_deks = bulk->num_deks; + pool->avail_deks += bulk->num_deks; + if (mlx5_crypto_dek_bulk_handle_avail(pool, bulk, &destroy_list)) { + memset(bulk->need_sync, 0, BITS_TO_BYTES(bulk->num_deks)); + bulk->avail_start = 0; + } + } + + mlx5_crypto_dek_pool_free_wait_keys(pool); + + if (!list_empty(&destroy_list)) { + mlx5_crypto_dek_pool_splice_destroy_list(pool, &destroy_list, + &pool->destroy_list); + schedule_work(&pool->destroy_work); + } +} + +static void mlx5_crypto_dek_sync_work_fn(struct work_struct *work) +{ + struct mlx5_crypto_dek_pool *pool = + container_of(work, struct mlx5_crypto_dek_pool, sync_work); + int err; + + err = mlx5_crypto_cmd_sync_crypto(pool->mdev, BIT(pool->key_purpose)); + mutex_lock(&pool->lock); + if (!err) + mlx5_crypto_dek_pool_reset_synced(pool); + pool->syncing = false; + mutex_unlock(&pool->lock); +} + +struct mlx5_crypto_dek *mlx5_crypto_dek_create(struct mlx5_crypto_dek_pool *dek_pool, + const void *key, u32 sz_bytes) +{ + struct mlx5_crypto_dek_priv *dek_priv = dek_pool->mdev->mlx5e_res.dek_priv; + struct mlx5_core_dev *mdev = dek_pool->mdev; + u32 key_purpose = dek_pool->key_purpose; + struct mlx5_crypto_dek_bulk *bulk; + struct mlx5_crypto_dek *dek; + int obj_offset; + int err; + + dek = kzalloc(sizeof(*dek), GFP_KERNEL); + if (!dek) + return ERR_PTR(-ENOMEM); + + if (!dek_priv) { + err = mlx5_crypto_create_dek_key(mdev, key, sz_bytes, + key_purpose, &dek->obj_id); + goto out; + } + + bulk = mlx5_crypto_dek_pool_pop(dek_pool, &obj_offset); + if (IS_ERR(bulk)) { + err = PTR_ERR(bulk); + goto out; + } + + dek->bulk = bulk; + dek->obj_id = bulk->base_obj_id + obj_offset; + err = mlx5_crypto_modify_dek_key(mdev, key, sz_bytes, key_purpose, + bulk->base_obj_id, obj_offset); + if (err) { + mlx5_crypto_dek_pool_push(dek_pool, dek); + return ERR_PTR(err); + } + +out: + if (err) { + kfree(dek); + return ERR_PTR(err); + } + + return dek; +} + +void mlx5_crypto_dek_destroy(struct mlx5_crypto_dek_pool *dek_pool, + struct mlx5_crypto_dek *dek) +{ + struct mlx5_crypto_dek_priv *dek_priv = dek_pool->mdev->mlx5e_res.dek_priv; + struct mlx5_core_dev *mdev = dek_pool->mdev; + + if (!dek_priv) { + mlx5_crypto_destroy_dek_key(mdev, dek->obj_id); + kfree(dek); + } else { + mlx5_crypto_dek_pool_push(dek_pool, dek); + } +} + +static void mlx5_crypto_dek_free_destroy_list(struct list_head *destroy_list) +{ + struct mlx5_crypto_dek_bulk *bulk, *tmp; + + list_for_each_entry_safe(bulk, tmp, destroy_list, entry) + mlx5_crypto_dek_bulk_free(bulk); +} + +static void mlx5_crypto_dek_destroy_work_fn(struct work_struct *work) +{ + struct mlx5_crypto_dek_pool *pool = + container_of(work, struct mlx5_crypto_dek_pool, destroy_work); + LIST_HEAD(destroy_list); + + mlx5_crypto_dek_pool_splice_destroy_list(pool, &pool->destroy_list, + &destroy_list); + mlx5_crypto_dek_free_destroy_list(&destroy_list); +} + +struct mlx5_crypto_dek_pool * +mlx5_crypto_dek_pool_create(struct mlx5_core_dev *mdev, int key_purpose) +{ + struct mlx5_crypto_dek_pool *pool; + + pool = kzalloc(sizeof(*pool), GFP_KERNEL); + if (!pool) + return ERR_PTR(-ENOMEM); + + pool->mdev = mdev; + pool->key_purpose = key_purpose; + + mutex_init(&pool->lock); + INIT_LIST_HEAD(&pool->avail_list); + INIT_LIST_HEAD(&pool->partial_list); + INIT_LIST_HEAD(&pool->full_list); + INIT_LIST_HEAD(&pool->sync_list); + INIT_LIST_HEAD(&pool->wait_for_free); + INIT_WORK(&pool->sync_work, mlx5_crypto_dek_sync_work_fn); + spin_lock_init(&pool->destroy_lock); + INIT_LIST_HEAD(&pool->destroy_list); + INIT_WORK(&pool->destroy_work, mlx5_crypto_dek_destroy_work_fn); + + return pool; +} + +void mlx5_crypto_dek_pool_destroy(struct mlx5_crypto_dek_pool *pool) +{ + struct mlx5_crypto_dek_bulk *bulk, *tmp; + + cancel_work_sync(&pool->sync_work); + cancel_work_sync(&pool->destroy_work); + + mlx5_crypto_dek_pool_free_wait_keys(pool); + + list_for_each_entry_safe(bulk, tmp, &pool->avail_list, entry) + mlx5_crypto_dek_pool_remove_bulk(pool, bulk, false); + + list_for_each_entry_safe(bulk, tmp, &pool->full_list, entry) + mlx5_crypto_dek_pool_remove_bulk(pool, bulk, false); + + list_for_each_entry_safe(bulk, tmp, &pool->sync_list, entry) + mlx5_crypto_dek_pool_remove_bulk(pool, bulk, false); + + list_for_each_entry_safe(bulk, tmp, &pool->partial_list, entry) + mlx5_crypto_dek_pool_remove_bulk(pool, bulk, false); + + mlx5_crypto_dek_free_destroy_list(&pool->destroy_list); + + mutex_destroy(&pool->lock); + + kfree(pool); +} + +void mlx5_crypto_dek_cleanup(struct mlx5_crypto_dek_priv *dek_priv) +{ + if (!dek_priv) + return; + + kfree(dek_priv); +} + +struct mlx5_crypto_dek_priv *mlx5_crypto_dek_init(struct mlx5_core_dev *mdev) +{ + struct mlx5_crypto_dek_priv *dek_priv; + int err; + + if (!MLX5_CAP_CRYPTO(mdev, log_dek_max_alloc)) + return NULL; + + dek_priv = kzalloc(sizeof(*dek_priv), GFP_KERNEL); + if (!dek_priv) + return ERR_PTR(-ENOMEM); + + dek_priv->mdev = mdev; + dek_priv->log_dek_obj_range = min_t(int, 12, + MLX5_CAP_CRYPTO(mdev, log_dek_max_alloc)); + + /* sync all types of objects */ + err = mlx5_crypto_cmd_sync_crypto(mdev, MLX5_CRYPTO_DEK_ALL_TYPE); + if (err) + goto err_sync_crypto; + + mlx5_core_dbg(mdev, "Crypto DEK enabled, %d deks per alloc (max %d), total %d\n", + 1 << dek_priv->log_dek_obj_range, + 1 << MLX5_CAP_CRYPTO(mdev, log_dek_max_alloc), + 1 << MLX5_CAP_CRYPTO(mdev, log_max_num_deks)); + + return dek_priv; + +err_sync_crypto: + kfree(dek_priv); + return ERR_PTR(err); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.h new file mode 100644 index 000000000000..c819c047bb9c --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef __MLX5_LIB_CRYPTO_H__ +#define __MLX5_LIB_CRYPTO_H__ + +enum { + MLX5_ACCEL_OBJ_TLS_KEY = MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_PURPOSE_TLS, + MLX5_ACCEL_OBJ_IPSEC_KEY = MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_PURPOSE_IPSEC, + MLX5_ACCEL_OBJ_MACSEC_KEY = MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_PURPOSE_MACSEC, + MLX5_ACCEL_OBJ_TYPE_KEY_NUM, +}; + +int mlx5_create_encryption_key(struct mlx5_core_dev *mdev, + const void *key, u32 sz_bytes, + u32 key_type, u32 *p_key_id); + +void mlx5_destroy_encryption_key(struct mlx5_core_dev *mdev, u32 key_id); + +struct mlx5_crypto_dek_pool; +struct mlx5_crypto_dek; + +struct mlx5_crypto_dek_pool *mlx5_crypto_dek_pool_create(struct mlx5_core_dev *mdev, + int key_purpose); +void mlx5_crypto_dek_pool_destroy(struct mlx5_crypto_dek_pool *pool); +struct mlx5_crypto_dek *mlx5_crypto_dek_create(struct mlx5_crypto_dek_pool *dek_pool, + const void *key, u32 sz_bytes); +void mlx5_crypto_dek_destroy(struct mlx5_crypto_dek_pool *dek_pool, + struct mlx5_crypto_dek *dek); +u32 mlx5_crypto_dek_get_id(struct mlx5_crypto_dek *dek); + +struct mlx5_crypto_dek_priv *mlx5_crypto_dek_init(struct mlx5_core_dev *mdev); +void mlx5_crypto_dek_cleanup(struct mlx5_crypto_dek_priv *dek_priv); +#endif /* __MLX5_LIB_CRYPTO_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h index 032adb21ad4b..ccf12f7db6f0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h @@ -79,28 +79,11 @@ struct mlx5_pme_stats { void mlx5_get_pme_stats(struct mlx5_core_dev *dev, struct mlx5_pme_stats *stats); int mlx5_notifier_call_chain(struct mlx5_events *events, unsigned int event, void *data); -/* Crypto */ -enum { - MLX5_ACCEL_OBJ_TLS_KEY = MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_TYPE_TLS, - MLX5_ACCEL_OBJ_IPSEC_KEY = MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_TYPE_IPSEC, - MLX5_ACCEL_OBJ_MACSEC_KEY = MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_TYPE_MACSEC, -}; - -int mlx5_create_encryption_key(struct mlx5_core_dev *mdev, - void *key, u32 sz_bytes, - u32 key_type, u32 *p_key_id); -void mlx5_destroy_encryption_key(struct mlx5_core_dev *mdev, u32 key_id); - static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev) { return devlink_net(priv_to_devlink(dev)); } -static inline void mlx5_uplink_netdev_set(struct mlx5_core_dev *mdev, struct net_device *netdev) -{ - mdev->mlx5e_res.uplink_netdev = netdev; -} - static inline struct net_device *mlx5_uplink_netdev_get(struct mlx5_core_dev *mdev) { return mdev->mlx5e_res.uplink_netdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 8823f20d2122..26e1057845fe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -336,6 +336,24 @@ static u16 to_fw_pkey_sz(struct mlx5_core_dev *dev, u32 size) } } +void mlx5_core_uplink_netdev_set(struct mlx5_core_dev *dev, struct net_device *netdev) +{ + mutex_lock(&dev->mlx5e_res.uplink_netdev_lock); + dev->mlx5e_res.uplink_netdev = netdev; + mlx5_blocking_notifier_call_chain(dev, MLX5_DRIVER_EVENT_UPLINK_NETDEV, + netdev); + mutex_unlock(&dev->mlx5e_res.uplink_netdev_lock); +} + +void mlx5_core_uplink_netdev_event_replay(struct mlx5_core_dev *dev) +{ + mutex_lock(&dev->mlx5e_res.uplink_netdev_lock); + mlx5_blocking_notifier_call_chain(dev, MLX5_DRIVER_EVENT_UPLINK_NETDEV, + dev->mlx5e_res.uplink_netdev); + mutex_unlock(&dev->mlx5e_res.uplink_netdev_lock); +} +EXPORT_SYMBOL(mlx5_core_uplink_netdev_event_replay); + static int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type, enum mlx5_cap_mode cap_mode) @@ -1555,6 +1573,7 @@ static const int types[] = { MLX5_CAP_DEV_SHAMPO, MLX5_CAP_MACSEC, MLX5_CAP_ADV_VIRTUALIZATION, + MLX5_CAP_CRYPTO, }; static void mlx5_hca_caps_free(struct mlx5_core_dev *dev) @@ -1608,6 +1627,7 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) lockdep_register_key(&dev->lock_key); mutex_init(&dev->intf_state_mutex); lockdep_set_class(&dev->intf_state_mutex, &dev->lock_key); + mutex_init(&dev->mlx5e_res.uplink_netdev_lock); mutex_init(&priv->bfregs.reg_head.lock); mutex_init(&priv->bfregs.wc_head.lock); @@ -1696,6 +1716,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev) mutex_destroy(&priv->alloc_mutex); mutex_destroy(&priv->bfregs.wc_head.lock); mutex_destroy(&priv->bfregs.reg_head.lock); + mutex_destroy(&dev->mlx5e_res.uplink_netdev_lock); mutex_destroy(&dev->intf_state_mutex); lockdep_unregister_key(&dev->lock_key); } @@ -2110,7 +2131,7 @@ static int __init mlx5_init(void) mlx5_core_verify_params(); mlx5_register_debugfs(); - err = pci_register_driver(&mlx5_core_driver); + err = mlx5e_init(); if (err) goto err_debug; @@ -2118,16 +2139,16 @@ static int __init mlx5_init(void) if (err) goto err_sf; - err = mlx5e_init(); + err = pci_register_driver(&mlx5_core_driver); if (err) - goto err_en; + goto err_pci; return 0; -err_en: +err_pci: mlx5_sf_driver_unregister(); err_sf: - pci_unregister_driver(&mlx5_core_driver); + mlx5e_cleanup(); err_debug: mlx5_unregister_debugfs(); return err; @@ -2135,9 +2156,9 @@ err_debug: static void __exit mlx5_cleanup(void) { - mlx5e_cleanup(); - mlx5_sf_driver_unregister(); pci_unregister_driver(&mlx5_core_driver); + mlx5_sf_driver_unregister(); + mlx5e_cleanup(); mlx5_unregister_debugfs(); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 60596357bfc7..64d4e7125e9b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -74,6 +74,14 @@ static u32 get_function(u16 func_id, bool ec_function) return (u32)func_id | (ec_function << 16); } +static u16 func_id_to_type(struct mlx5_core_dev *dev, u16 func_id, bool ec_function) +{ + if (!func_id) + return mlx5_core_is_ecpf(dev) && !ec_function ? MLX5_HOST_PF : MLX5_PF; + + return func_id <= mlx5_core_max_vfs(dev) ? MLX5_VF : MLX5_SF; +} + static struct rb_root *page_root_per_function(struct mlx5_core_dev *dev, u32 function) { struct rb_root *root; @@ -211,7 +219,8 @@ static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr, u32 function) n = find_first_bit(&fp->bitmask, 8 * sizeof(fp->bitmask)); if (n >= MLX5_NUM_4K_IN_PAGE) { - mlx5_core_warn(dev, "alloc 4k bug\n"); + mlx5_core_warn(dev, "alloc 4k bug: fw page = 0x%llx, n = %u, bitmask: %lu, max num of 4K pages: %d\n", + fp->addr, n, fp->bitmask, MLX5_NUM_4K_IN_PAGE); return -ENOENT; } clear_bit(n, &fp->bitmask); @@ -332,6 +341,7 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0}; int inlen = MLX5_ST_SZ_BYTES(manage_pages_in); int notify_fail = event; + u16 func_type; u64 addr; int err; u32 *in; @@ -383,11 +393,9 @@ retry: goto out_dropped; } + func_type = func_id_to_type(dev, func_id, ec_function); + dev->priv.page_counters[func_type] += npages; dev->priv.fw_pages += npages; - if (func_id) - dev->priv.vfs_pages += npages; - else if (mlx5_core_is_ecpf(dev) && !ec_function) - dev->priv.host_pf_pages += npages; mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x, err %d\n", npages, ec_function, func_id, err); @@ -414,6 +422,7 @@ static void release_all_pages(struct mlx5_core_dev *dev, u16 func_id, struct rb_root *root; struct rb_node *p; int npages = 0; + u16 func_type; root = xa_load(&dev->priv.page_root_xa, function); if (WARN_ON_ONCE(!root)) @@ -428,11 +437,9 @@ static void release_all_pages(struct mlx5_core_dev *dev, u16 func_id, free_fwp(dev, fwp, fwp->free_count); } + func_type = func_id_to_type(dev, func_id, ec_function); + dev->priv.page_counters[func_type] -= npages; dev->priv.fw_pages -= npages; - if (func_id) - dev->priv.vfs_pages -= npages; - else if (mlx5_core_is_ecpf(dev) && !ec_function) - dev->priv.host_pf_pages -= npages; mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x\n", npages, ec_function, func_id); @@ -498,6 +505,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, int outlen = MLX5_ST_SZ_BYTES(manage_pages_out); u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {}; int num_claimed; + u16 func_type; u32 *out; int err; int i; @@ -549,11 +557,9 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, if (nclaimed) *nclaimed = num_claimed; + func_type = func_id_to_type(dev, func_id, ec_function); + dev->priv.page_counters[func_type] -= num_claimed; dev->priv.fw_pages -= num_claimed; - if (func_id) - dev->priv.vfs_pages -= num_claimed; - else if (mlx5_core_is_ecpf(dev) && !ec_function) - dev->priv.host_pf_pages -= num_claimed; out_free: kvfree(out); @@ -706,12 +712,12 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev) WARN(dev->priv.fw_pages, "FW pages counter is %d after reclaiming all pages\n", dev->priv.fw_pages); - WARN(dev->priv.vfs_pages, + WARN(dev->priv.page_counters[MLX5_VF], "VFs FW pages counter is %d after reclaiming all pages\n", - dev->priv.vfs_pages); - WARN(dev->priv.host_pf_pages, + dev->priv.page_counters[MLX5_VF]); + WARN(dev->priv.page_counters[MLX5_HOST_PF], "External host PF FW pages counter is %d after reclaiming all pages\n", - dev->priv.host_pf_pages); + dev->priv.page_counters[MLX5_HOST_PF]); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index c0e6c487c63c..3008e9ce2bbf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -147,7 +147,7 @@ mlx5_device_disable_sriov(struct mlx5_core_dev *dev, int num_vfs, bool clear_vf) mlx5_eswitch_disable_sriov(dev->priv.eswitch, clear_vf); - if (mlx5_wait_for_pages(dev, &dev->priv.vfs_pages)) + if (mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_VF])) mlx5_core_warn(dev, "timeout reclaiming VFs pages\n"); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index b851141e03de..042ca0349124 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -1138,12 +1138,14 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, rule->flow_source)) return 0; + mlx5dr_domain_nic_lock(nic_dmn); + ret = mlx5dr_matcher_select_builders(matcher, nic_matcher, dr_rule_get_ipv(¶m->outer), dr_rule_get_ipv(¶m->inner)); if (ret) - return ret; + goto err_unlock; hw_ste_arr_is_opt = nic_matcher->num_of_builders <= DR_RULE_MAX_STES_OPTIMIZED; if (likely(hw_ste_arr_is_opt)) { @@ -1152,12 +1154,12 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, hw_ste_arr = kzalloc((nic_matcher->num_of_builders + DR_ACTION_MAX_STES) * DR_STE_SIZE, GFP_KERNEL); - if (!hw_ste_arr) - return -ENOMEM; + if (!hw_ste_arr) { + ret = -ENOMEM; + goto err_unlock; + } } - mlx5dr_domain_nic_lock(nic_dmn); - ret = mlx5dr_matcher_add_to_tbl_nic(dmn, nic_matcher); if (ret) goto free_hw_ste; @@ -1223,7 +1225,10 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, mlx5dr_domain_nic_unlock(nic_dmn); - goto out; + if (unlikely(!hw_ste_arr_is_opt)) + kfree(hw_ste_arr); + + return 0; free_rule: dr_rule_clean_rule_members(rule, nic_rule); @@ -1238,12 +1243,12 @@ remove_from_nic_tbl: mlx5dr_matcher_remove_from_tbl_nic(dmn, nic_matcher); free_hw_ste: - mlx5dr_domain_nic_unlock(nic_dmn); - -out: - if (unlikely(!hw_ste_arr_is_opt)) + if (!hw_ste_arr_is_opt) kfree(hw_ste_arr); +err_unlock: + mlx5dr_domain_nic_unlock(nic_dmn); + return ret; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index f8623e8388c8..22db0bb15c45 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -1750,29 +1750,12 @@ static const struct devlink_ops mlxsw_devlink_ops = { static int mlxsw_core_params_register(struct mlxsw_core *mlxsw_core) { - int err; - - err = mlxsw_core_fw_params_register(mlxsw_core); - if (err) - return err; - - if (mlxsw_core->driver->params_register) { - err = mlxsw_core->driver->params_register(mlxsw_core); - if (err) - goto err_params_register; - } - return 0; - -err_params_register: - mlxsw_core_fw_params_unregister(mlxsw_core); - return err; + return mlxsw_core_fw_params_register(mlxsw_core); } static void mlxsw_core_params_unregister(struct mlxsw_core *mlxsw_core) { mlxsw_core_fw_params_unregister(mlxsw_core); - if (mlxsw_core->driver->params_register) - mlxsw_core->driver->params_unregister(mlxsw_core); } struct mlxsw_core_health_event { @@ -2201,6 +2184,7 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, goto err_devlink_alloc; } devl_lock(devlink); + devl_register(devlink); } mlxsw_core = devlink_priv(devlink); @@ -2284,11 +2268,8 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, goto err_driver_init; } - if (!reload) { - devlink_set_features(devlink, DEVLINK_F_RELOAD); + if (!reload) devl_unlock(devlink); - devlink_register(devlink); - } return 0; err_driver_init: @@ -2320,6 +2301,7 @@ err_register_resources: err_bus_init: mlxsw_core_irq_event_handler_fini(mlxsw_core); if (!reload) { + devl_unregister(devlink); devl_unlock(devlink); devlink_free(devlink); } @@ -2358,10 +2340,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, { struct devlink *devlink = priv_to_devlink(mlxsw_core); - if (!reload) { - devlink_unregister(devlink); + if (!reload) devl_lock(devlink); - } if (devlink_is_reload_failed(devlink)) { if (!reload) @@ -2390,6 +2370,7 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, mlxsw_core->bus->fini(mlxsw_core->bus_priv); mlxsw_core_irq_event_handler_fini(mlxsw_core); if (!reload) { + devl_unregister(devlink); devl_unlock(devlink); devlink_free(devlink); } @@ -2399,6 +2380,7 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, reload_fail_deinit: mlxsw_core_params_unregister(mlxsw_core); devl_resources_unregister(devlink); + devl_unregister(devlink); devl_unlock(devlink); devlink_free(devlink); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index a77cb0be7108..e5474d3e34db 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -421,8 +421,6 @@ struct mlxsw_driver { const struct mlxsw_config_profile *profile, u64 *p_single_size, u64 *p_double_size, u64 *p_linear_size); - int (*params_register)(struct mlxsw_core *mlxsw_core); - void (*params_unregister)(struct mlxsw_core *mlxsw_core); /* Notify a driver that a timestamped packet was transmitted. Driver * is responsible for freeing the passed-in SKB. diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index b0bdb9640ebf..a8f94b7544ee 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3861,62 +3861,6 @@ static int mlxsw_sp_kvd_sizes_get(struct mlxsw_core *mlxsw_core, return 0; } -static int -mlxsw_sp_params_acl_region_rehash_intrvl_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) -{ - struct mlxsw_core *mlxsw_core = devlink_priv(devlink); - struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); - - ctx->val.vu32 = mlxsw_sp_acl_region_rehash_intrvl_get(mlxsw_sp); - return 0; -} - -static int -mlxsw_sp_params_acl_region_rehash_intrvl_set(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) -{ - struct mlxsw_core *mlxsw_core = devlink_priv(devlink); - struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); - - return mlxsw_sp_acl_region_rehash_intrvl_set(mlxsw_sp, ctx->val.vu32); -} - -static const struct devlink_param mlxsw_sp2_devlink_params[] = { - DEVLINK_PARAM_DRIVER(MLXSW_DEVLINK_PARAM_ID_ACL_REGION_REHASH_INTERVAL, - "acl_region_rehash_interval", - DEVLINK_PARAM_TYPE_U32, - BIT(DEVLINK_PARAM_CMODE_RUNTIME), - mlxsw_sp_params_acl_region_rehash_intrvl_get, - mlxsw_sp_params_acl_region_rehash_intrvl_set, - NULL), -}; - -static int mlxsw_sp2_params_register(struct mlxsw_core *mlxsw_core) -{ - struct devlink *devlink = priv_to_devlink(mlxsw_core); - union devlink_param_value value; - int err; - - err = devl_params_register(devlink, mlxsw_sp2_devlink_params, - ARRAY_SIZE(mlxsw_sp2_devlink_params)); - if (err) - return err; - - value.vu32 = 0; - devl_param_driverinit_value_set(devlink, - MLXSW_DEVLINK_PARAM_ID_ACL_REGION_REHASH_INTERVAL, - value); - return 0; -} - -static void mlxsw_sp2_params_unregister(struct mlxsw_core *mlxsw_core) -{ - devl_params_unregister(priv_to_devlink(mlxsw_core), - mlxsw_sp2_devlink_params, - ARRAY_SIZE(mlxsw_sp2_devlink_params)); -} - static void mlxsw_sp_ptp_transmitted(struct mlxsw_core *mlxsw_core, struct sk_buff *skb, u16 local_port) { @@ -3994,8 +3938,6 @@ static struct mlxsw_driver mlxsw_sp2_driver = { .trap_policer_counter_get = mlxsw_sp_trap_policer_counter_get, .txhdr_construct = mlxsw_sp_txhdr_construct, .resources_register = mlxsw_sp2_resources_register, - .params_register = mlxsw_sp2_params_register, - .params_unregister = mlxsw_sp2_params_unregister, .ptp_transmitted = mlxsw_sp_ptp_transmitted, .txhdr_len = MLXSW_TXHDR_LEN, .profile = &mlxsw_sp2_config_profile, @@ -4033,8 +3975,6 @@ static struct mlxsw_driver mlxsw_sp3_driver = { .trap_policer_counter_get = mlxsw_sp_trap_policer_counter_get, .txhdr_construct = mlxsw_sp_txhdr_construct, .resources_register = mlxsw_sp2_resources_register, - .params_register = mlxsw_sp2_params_register, - .params_unregister = mlxsw_sp2_params_unregister, .ptp_transmitted = mlxsw_sp_ptp_transmitted, .txhdr_len = MLXSW_TXHDR_LEN, .profile = &mlxsw_sp2_config_profile, @@ -4070,8 +4010,6 @@ static struct mlxsw_driver mlxsw_sp4_driver = { .trap_policer_counter_get = mlxsw_sp_trap_policer_counter_get, .txhdr_construct = mlxsw_sp_txhdr_construct, .resources_register = mlxsw_sp2_resources_register, - .params_register = mlxsw_sp2_params_register, - .params_unregister = mlxsw_sp2_params_unregister, .ptp_transmitted = mlxsw_sp_ptp_transmitted, .txhdr_len = MLXSW_TXHDR_LEN, .profile = &mlxsw_sp4_config_profile, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index bbc73324451d..4c22f8004514 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -973,6 +973,7 @@ enum mlxsw_sp_acl_profile { }; struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl); +struct mlxsw_sp_acl_tcam *mlxsw_sp_acl_to_tcam(struct mlxsw_sp_acl *acl); int mlxsw_sp_acl_ruleset_bind(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_flow_block *block, @@ -1096,8 +1097,6 @@ mlxsw_sp_acl_act_cookie_lookup(struct mlxsw_sp *mlxsw_sp, u32 cookie_index) int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp); void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp); -u32 mlxsw_sp_acl_region_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp); -int mlxsw_sp_acl_region_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp, u32 val); struct mlxsw_sp_acl_mangle_action; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 6c5af018546f..0423ac262d89 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -40,6 +40,11 @@ struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl) return acl->afk; } +struct mlxsw_sp_acl_tcam *mlxsw_sp_acl_to_tcam(struct mlxsw_sp_acl *acl) +{ + return &acl->tcam; +} + struct mlxsw_sp_acl_ruleset_ht_key { struct mlxsw_sp_flow_block *block; u32 chain_index; @@ -1099,22 +1104,6 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp) kfree(acl); } -u32 mlxsw_sp_acl_region_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp) -{ - struct mlxsw_sp_acl *acl = mlxsw_sp->acl; - - return mlxsw_sp_acl_tcam_vregion_rehash_intrvl_get(mlxsw_sp, - &acl->tcam); -} - -int mlxsw_sp_acl_region_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp, u32 val) -{ - struct mlxsw_sp_acl *acl = mlxsw_sp->acl; - - return mlxsw_sp_acl_tcam_vregion_rehash_intrvl_set(mlxsw_sp, - &acl->tcam, val); -} - struct mlxsw_sp_acl_rulei_ops mlxsw_sp1_acl_rulei_ops = { .act_mangle_field = mlxsw_sp1_acl_rulei_act_mangle_field, }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 3b9ba8fa247a..d50786b0a6ce 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -9,6 +9,7 @@ #include <linux/rhashtable.h> #include <linux/netdevice.h> #include <linux/mutex.h> +#include <net/devlink.h> #include <trace/events/mlxsw.h> #include "reg.h" @@ -29,67 +30,6 @@ size_t mlxsw_sp_acl_tcam_priv_size(struct mlxsw_sp *mlxsw_sp) #define MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_MIN 3000 /* ms */ #define MLXSW_SP_ACL_TCAM_VREGION_REHASH_CREDITS 100 /* number of entries */ -int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam *tcam) -{ - const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - u64 max_tcam_regions; - u64 max_regions; - u64 max_groups; - int err; - - mutex_init(&tcam->lock); - tcam->vregion_rehash_intrvl = - MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_DFLT; - INIT_LIST_HEAD(&tcam->vregion_list); - - max_tcam_regions = MLXSW_CORE_RES_GET(mlxsw_sp->core, - ACL_MAX_TCAM_REGIONS); - max_regions = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_REGIONS); - - /* Use 1:1 mapping between ACL region and TCAM region */ - if (max_tcam_regions < max_regions) - max_regions = max_tcam_regions; - - tcam->used_regions = bitmap_zalloc(max_regions, GFP_KERNEL); - if (!tcam->used_regions) - return -ENOMEM; - tcam->max_regions = max_regions; - - max_groups = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_GROUPS); - tcam->used_groups = bitmap_zalloc(max_groups, GFP_KERNEL); - if (!tcam->used_groups) { - err = -ENOMEM; - goto err_alloc_used_groups; - } - tcam->max_groups = max_groups; - tcam->max_group_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, - ACL_MAX_GROUP_SIZE); - - err = ops->init(mlxsw_sp, tcam->priv, tcam); - if (err) - goto err_tcam_init; - - return 0; - -err_tcam_init: - bitmap_free(tcam->used_groups); -err_alloc_used_groups: - bitmap_free(tcam->used_regions); - return err; -} - -void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam *tcam) -{ - const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - - mutex_destroy(&tcam->lock); - ops->fini(mlxsw_sp, tcam->priv); - bitmap_free(tcam->used_groups); - bitmap_free(tcam->used_regions); -} - int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_rule_info *rulei, u32 *priority, bool fillup_priority) @@ -893,41 +833,6 @@ mlxsw_sp_acl_tcam_vregion_destroy(struct mlxsw_sp *mlxsw_sp, kfree(vregion); } -u32 mlxsw_sp_acl_tcam_vregion_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam *tcam) -{ - const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - u32 vregion_rehash_intrvl; - - if (WARN_ON(!ops->region_rehash_hints_get)) - return 0; - vregion_rehash_intrvl = tcam->vregion_rehash_intrvl; - return vregion_rehash_intrvl; -} - -int mlxsw_sp_acl_tcam_vregion_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam *tcam, - u32 val) -{ - const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - struct mlxsw_sp_acl_tcam_vregion *vregion; - - if (val < MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_MIN && val) - return -EINVAL; - if (WARN_ON(!ops->region_rehash_hints_get)) - return -EOPNOTSUPP; - tcam->vregion_rehash_intrvl = val; - mutex_lock(&tcam->lock); - list_for_each_entry(vregion, &tcam->vregion_list, tlist) { - if (val) - mlxsw_core_schedule_dw(&vregion->rehash.dw, 0); - else - cancel_delayed_work_sync(&vregion->rehash.dw); - } - mutex_unlock(&tcam->lock); - return 0; -} - static struct mlxsw_sp_acl_tcam_vregion * mlxsw_sp_acl_tcam_vregion_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam_vgroup *vgroup, @@ -1542,6 +1447,153 @@ mlxsw_sp_acl_tcam_vregion_rehash(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_acl_tcam_vregion_rehash_end(mlxsw_sp, vregion, ctx); } +static int +mlxsw_sp_acl_tcam_region_rehash_intrvl_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + struct mlxsw_sp_acl_tcam *tcam; + struct mlxsw_sp *mlxsw_sp; + + mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); + tcam = mlxsw_sp_acl_to_tcam(mlxsw_sp->acl); + ctx->val.vu32 = tcam->vregion_rehash_intrvl; + + return 0; +} + +static int +mlxsw_sp_acl_tcam_region_rehash_intrvl_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + struct mlxsw_sp_acl_tcam_vregion *vregion; + struct mlxsw_sp_acl_tcam *tcam; + struct mlxsw_sp *mlxsw_sp; + u32 val = ctx->val.vu32; + + if (val < MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_MIN && val) + return -EINVAL; + + mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); + tcam = mlxsw_sp_acl_to_tcam(mlxsw_sp->acl); + tcam->vregion_rehash_intrvl = val; + mutex_lock(&tcam->lock); + list_for_each_entry(vregion, &tcam->vregion_list, tlist) { + if (val) + mlxsw_core_schedule_dw(&vregion->rehash.dw, 0); + else + cancel_delayed_work_sync(&vregion->rehash.dw); + } + mutex_unlock(&tcam->lock); + return 0; +} + +static const struct devlink_param mlxsw_sp_acl_tcam_rehash_params[] = { + DEVLINK_PARAM_DRIVER(MLXSW_DEVLINK_PARAM_ID_ACL_REGION_REHASH_INTERVAL, + "acl_region_rehash_interval", + DEVLINK_PARAM_TYPE_U32, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + mlxsw_sp_acl_tcam_region_rehash_intrvl_get, + mlxsw_sp_acl_tcam_region_rehash_intrvl_set, + NULL), +}; + +static int mlxsw_sp_acl_tcam_rehash_params_register(struct mlxsw_sp *mlxsw_sp) +{ + struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); + + if (!mlxsw_sp->acl_tcam_ops->region_rehash_hints_get) + return 0; + + return devl_params_register(devlink, mlxsw_sp_acl_tcam_rehash_params, + ARRAY_SIZE(mlxsw_sp_acl_tcam_rehash_params)); +} + +static void +mlxsw_sp_acl_tcam_rehash_params_unregister(struct mlxsw_sp *mlxsw_sp) +{ + struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); + + if (!mlxsw_sp->acl_tcam_ops->region_rehash_hints_get) + return; + + devl_params_unregister(devlink, mlxsw_sp_acl_tcam_rehash_params, + ARRAY_SIZE(mlxsw_sp_acl_tcam_rehash_params)); +} + +int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam *tcam) +{ + const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; + u64 max_tcam_regions; + u64 max_regions; + u64 max_groups; + int err; + + mutex_init(&tcam->lock); + tcam->vregion_rehash_intrvl = + MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_DFLT; + INIT_LIST_HEAD(&tcam->vregion_list); + + err = mlxsw_sp_acl_tcam_rehash_params_register(mlxsw_sp); + if (err) + goto err_rehash_params_register; + + max_tcam_regions = MLXSW_CORE_RES_GET(mlxsw_sp->core, + ACL_MAX_TCAM_REGIONS); + max_regions = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_REGIONS); + + /* Use 1:1 mapping between ACL region and TCAM region */ + if (max_tcam_regions < max_regions) + max_regions = max_tcam_regions; + + tcam->used_regions = bitmap_zalloc(max_regions, GFP_KERNEL); + if (!tcam->used_regions) { + err = -ENOMEM; + goto err_alloc_used_regions; + } + tcam->max_regions = max_regions; + + max_groups = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_GROUPS); + tcam->used_groups = bitmap_zalloc(max_groups, GFP_KERNEL); + if (!tcam->used_groups) { + err = -ENOMEM; + goto err_alloc_used_groups; + } + tcam->max_groups = max_groups; + tcam->max_group_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, + ACL_MAX_GROUP_SIZE); + + err = ops->init(mlxsw_sp, tcam->priv, tcam); + if (err) + goto err_tcam_init; + + return 0; + +err_tcam_init: + bitmap_free(tcam->used_groups); +err_alloc_used_groups: + bitmap_free(tcam->used_regions); +err_alloc_used_regions: + mlxsw_sp_acl_tcam_rehash_params_unregister(mlxsw_sp); +err_rehash_params_register: + mutex_destroy(&tcam->lock); + return err; +} + +void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam *tcam) +{ + const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; + + ops->fini(mlxsw_sp, tcam->priv); + bitmap_free(tcam->used_groups); + bitmap_free(tcam->used_regions); + mlxsw_sp_acl_tcam_rehash_params_unregister(mlxsw_sp); + mutex_destroy(&tcam->lock); +} + static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = { MLXSW_AFK_ELEMENT_SRC_SYS_PORT, MLXSW_AFK_ELEMENT_DMAC_32_47, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h index edbbc89e7a71..462bf448497d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h @@ -29,11 +29,6 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam *tcam); void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam *tcam); -u32 mlxsw_sp_acl_tcam_vregion_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam *tcam); -int mlxsw_sp_acl_tcam_vregion_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam *tcam, - u32 val); int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_rule_info *rulei, u32 *priority, bool fillup_priority); diff --git a/drivers/net/ethernet/microchip/lan966x/Makefile b/drivers/net/ethernet/microchip/lan966x/Makefile index 56afd694f3c7..7b0cda4ffa6b 100644 --- a/drivers/net/ethernet/microchip/lan966x/Makefile +++ b/drivers/net/ethernet/microchip/lan966x/Makefile @@ -15,5 +15,7 @@ lan966x-switch-objs := lan966x_main.o lan966x_phylink.o lan966x_port.o \ lan966x_xdp.o lan966x_vcap_impl.o lan966x_vcap_ag_api.o \ lan966x_tc_flower.o lan966x_goto.o +lan966x-switch-$(CONFIG_DEBUG_FS) += lan966x_vcap_debugfs.o + # Provide include files ccflags-y += -I$(srctree)/drivers/net/ethernet/microchip/vcap diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 580c91d24a52..47b37ab9d7d5 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -1035,6 +1035,8 @@ static int lan966x_probe(struct platform_device *pdev) platform_set_drvdata(pdev, lan966x); lan966x->dev = &pdev->dev; + lan966x->debugfs_root = debugfs_create_dir("lan966x", NULL); + if (!device_get_mac_address(&pdev->dev, mac_addr)) { ether_addr_copy(lan966x->base_mac, mac_addr); } else { @@ -1223,6 +1225,8 @@ static int lan966x_remove(struct platform_device *pdev) lan966x_fdb_deinit(lan966x); lan966x_ptp_deinit(lan966x); + debugfs_remove_recursive(lan966x->debugfs_root); + return 0; } diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h index 0106f9487cbe..49f5159afbf3 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h @@ -3,6 +3,7 @@ #ifndef __LAN966X_MAIN_H__ #define __LAN966X_MAIN_H__ +#include <linux/debugfs.h> #include <linux/etherdevice.h> #include <linux/if_vlan.h> #include <linux/jiffies.h> @@ -14,6 +15,9 @@ #include <net/pkt_sched.h> #include <net/switchdev.h> +#include <vcap_api.h> +#include <vcap_api_client.h> + #include "lan966x_regs.h" #include "lan966x_ifh.h" @@ -128,6 +132,13 @@ enum LAN966X_PORT_MASK_MODE { LAN966X_PMM_REDIRECT, }; +enum vcap_is2_port_sel_ipv6 { + VCAP_IS2_PS_IPV6_TCPUDP_OTHER, + VCAP_IS2_PS_IPV6_STD, + VCAP_IS2_PS_IPV6_IP4_TCPUDP_IP4_OTHER, + VCAP_IS2_PS_IPV6_MAC_ETYPE, +}; + struct lan966x_port; struct lan966x_db { @@ -315,6 +326,9 @@ struct lan966x { /* vcap */ struct vcap_control *vcap_ctrl; + + /* debugfs */ + struct dentry *debugfs_root; }; struct lan966x_port_config { @@ -601,9 +615,22 @@ static inline bool lan966x_xdp_port_present(struct lan966x_port *port) int lan966x_vcap_init(struct lan966x *lan966x); void lan966x_vcap_deinit(struct lan966x *lan966x); +#if defined(CONFIG_DEBUG_FS) +int lan966x_vcap_port_info(struct net_device *dev, + struct vcap_admin *admin, + struct vcap_output_print *out); +#else +static inline int lan966x_vcap_port_info(struct net_device *dev, + struct vcap_admin *admin, + struct vcap_output_print *out) +{ + return 0; +} +#endif int lan966x_tc_flower(struct lan966x_port *port, - struct flow_cls_offload *f); + struct flow_cls_offload *f, + bool ingress); int lan966x_goto_port_add(struct lan966x_port *port, int from_cid, int to_cid, diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_tc.c b/drivers/net/ethernet/microchip/lan966x/lan966x_tc.c index 01072121c999..cf0cc7562d04 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_tc.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_tc.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0+ #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include "lan966x_main.h" @@ -70,7 +71,7 @@ static int lan966x_tc_block_cb(enum tc_setup_type type, void *type_data, case TC_SETUP_CLSMATCHALL: return lan966x_tc_matchall(port, type_data, ingress); case TC_SETUP_CLSFLOWER: - return lan966x_tc_flower(port, type_data); + return lan966x_tc_flower(port, type_data, ingress); default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c b/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c index b66a8725a071..bd10a7189741 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c @@ -3,53 +3,135 @@ #include "lan966x_main.h" #include "vcap_api.h" #include "vcap_api_client.h" +#include "vcap_tc.h" -struct lan966x_tc_flower_parse_usage { - struct flow_cls_offload *f; - struct flow_rule *frule; - struct vcap_rule *vrule; - unsigned int used_keys; - u16 l3_proto; -}; +static bool lan966x_tc_is_known_etype(u16 etype) +{ + switch (etype) { + case ETH_P_ALL: + case ETH_P_ARP: + case ETH_P_IP: + case ETH_P_IPV6: + return true; + } + + return false; +} -static int lan966x_tc_flower_handler_ethaddr_usage(struct lan966x_tc_flower_parse_usage *st) +static int +lan966x_tc_flower_handler_control_usage(struct vcap_tc_flower_parse_usage *st) { - enum vcap_key_field smac_key = VCAP_KF_L2_SMAC; - enum vcap_key_field dmac_key = VCAP_KF_L2_DMAC; - struct flow_match_eth_addrs match; - struct vcap_u48_key smac, dmac; + struct flow_match_control match; int err = 0; - flow_rule_match_eth_addrs(st->frule, &match); - - if (!is_zero_ether_addr(match.mask->src)) { - vcap_netbytes_copy(smac.value, match.key->src, ETH_ALEN); - vcap_netbytes_copy(smac.mask, match.mask->src, ETH_ALEN); - err = vcap_rule_add_key_u48(st->vrule, smac_key, &smac); + flow_rule_match_control(st->frule, &match); + if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) { + if (match.key->flags & FLOW_DIS_IS_FRAGMENT) + err = vcap_rule_add_key_bit(st->vrule, + VCAP_KF_L3_FRAGMENT, + VCAP_BIT_1); + else + err = vcap_rule_add_key_bit(st->vrule, + VCAP_KF_L3_FRAGMENT, + VCAP_BIT_0); if (err) goto out; } - if (!is_zero_ether_addr(match.mask->dst)) { - vcap_netbytes_copy(dmac.value, match.key->dst, ETH_ALEN); - vcap_netbytes_copy(dmac.mask, match.mask->dst, ETH_ALEN); - err = vcap_rule_add_key_u48(st->vrule, dmac_key, &dmac); + if (match.mask->flags & FLOW_DIS_FIRST_FRAG) { + if (match.key->flags & FLOW_DIS_FIRST_FRAG) + err = vcap_rule_add_key_bit(st->vrule, + VCAP_KF_L3_FRAG_OFS_GT0, + VCAP_BIT_0); + else + err = vcap_rule_add_key_bit(st->vrule, + VCAP_KF_L3_FRAG_OFS_GT0, + VCAP_BIT_1); if (err) goto out; } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS); + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL); return err; out: - NL_SET_ERR_MSG_MOD(st->f->common.extack, "eth_addr parse error"); + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_frag parse error"); + return err; +} + +static int +lan966x_tc_flower_handler_basic_usage(struct vcap_tc_flower_parse_usage *st) +{ + struct flow_match_basic match; + int err = 0; + + flow_rule_match_basic(st->frule, &match); + if (match.mask->n_proto) { + st->l3_proto = be16_to_cpu(match.key->n_proto); + if (!lan966x_tc_is_known_etype(st->l3_proto)) { + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_ETYPE, + st->l3_proto, ~0); + if (err) + goto out; + } else if (st->l3_proto == ETH_P_IP) { + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_IP4_IS, + VCAP_BIT_1); + if (err) + goto out; + } + } + if (match.mask->ip_proto) { + st->l4_proto = match.key->ip_proto; + + if (st->l4_proto == IPPROTO_TCP) { + err = vcap_rule_add_key_bit(st->vrule, + VCAP_KF_TCP_IS, + VCAP_BIT_1); + if (err) + goto out; + } else if (st->l4_proto == IPPROTO_UDP) { + err = vcap_rule_add_key_bit(st->vrule, + VCAP_KF_TCP_IS, + VCAP_BIT_0); + if (err) + goto out; + } else { + err = vcap_rule_add_key_u32(st->vrule, + VCAP_KF_L3_IP_PROTO, + st->l4_proto, ~0); + if (err) + goto out; + } + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_BASIC); + return err; +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_proto parse error"); return err; } static int -(*lan966x_tc_flower_handlers_usage[])(struct lan966x_tc_flower_parse_usage *st) = { - [FLOW_DISSECTOR_KEY_ETH_ADDRS] = lan966x_tc_flower_handler_ethaddr_usage, +lan966x_tc_flower_handler_vlan_usage(struct vcap_tc_flower_parse_usage *st) +{ + return vcap_tc_flower_handler_vlan_usage(st, + VCAP_KF_8021Q_VID_CLS, + VCAP_KF_8021Q_PCP_CLS); +} + +static int +(*lan966x_tc_flower_handlers_usage[])(struct vcap_tc_flower_parse_usage *st) = { + [FLOW_DISSECTOR_KEY_ETH_ADDRS] = vcap_tc_flower_handler_ethaddr_usage, + [FLOW_DISSECTOR_KEY_IPV4_ADDRS] = vcap_tc_flower_handler_ipv4_usage, + [FLOW_DISSECTOR_KEY_IPV6_ADDRS] = vcap_tc_flower_handler_ipv6_usage, + [FLOW_DISSECTOR_KEY_CONTROL] = lan966x_tc_flower_handler_control_usage, + [FLOW_DISSECTOR_KEY_PORTS] = vcap_tc_flower_handler_portnum_usage, + [FLOW_DISSECTOR_KEY_BASIC] = lan966x_tc_flower_handler_basic_usage, + [FLOW_DISSECTOR_KEY_VLAN] = lan966x_tc_flower_handler_vlan_usage, + [FLOW_DISSECTOR_KEY_TCP] = vcap_tc_flower_handler_tcp_usage, + [FLOW_DISSECTOR_KEY_ARP] = vcap_tc_flower_handler_arp_usage, + [FLOW_DISSECTOR_KEY_IP] = vcap_tc_flower_handler_ip_usage, }; static int lan966x_tc_flower_use_dissectors(struct flow_cls_offload *f, @@ -57,8 +139,8 @@ static int lan966x_tc_flower_use_dissectors(struct flow_cls_offload *f, struct vcap_rule *vrule, u16 *l3_proto) { - struct lan966x_tc_flower_parse_usage state = { - .f = f, + struct vcap_tc_flower_parse_usage state = { + .fco = f, .vrule = vrule, .l3_proto = ETH_P_ALL, }; @@ -83,7 +165,8 @@ static int lan966x_tc_flower_use_dissectors(struct flow_cls_offload *f, static int lan966x_tc_flower_action_check(struct vcap_control *vctrl, struct net_device *dev, - struct flow_cls_offload *fco) + struct flow_cls_offload *fco, + bool ingress) { struct flow_rule *rule = flow_cls_offload_flow_rule(fco); struct flow_action_entry *actent, *last_actent = NULL; @@ -120,7 +203,8 @@ static int lan966x_tc_flower_action_check(struct vcap_control *vctrl, "Invalid goto chain"); return -EINVAL; } - } else if (!vcap_is_last_chain(vctrl, fco->common.chain_index)) { + } else if (!vcap_is_last_chain(vctrl, fco->common.chain_index, + ingress)) { NL_SET_ERR_MSG_MOD(fco->common.extack, "Last action must be 'goto'"); return -EINVAL; @@ -139,7 +223,8 @@ static int lan966x_tc_flower_action_check(struct vcap_control *vctrl, static int lan966x_tc_flower_add(struct lan966x_port *port, struct flow_cls_offload *f, - struct vcap_admin *admin) + struct vcap_admin *admin, + bool ingress) { struct flow_action_entry *act; u16 l3_proto = ETH_P_ALL; @@ -148,7 +233,7 @@ static int lan966x_tc_flower_add(struct lan966x_port *port, int err, idx; err = lan966x_tc_flower_action_check(port->lan966x->vcap_ctrl, - port->dev, f); + port->dev, f, ingress); if (err) return err; @@ -231,8 +316,27 @@ static int lan966x_tc_flower_del(struct lan966x_port *port, return err; } +static int lan966x_tc_flower_stats(struct lan966x_port *port, + struct flow_cls_offload *f, + struct vcap_admin *admin) +{ + struct vcap_counter count = {}; + int err; + + err = vcap_get_rule_count_by_cookie(port->lan966x->vcap_ctrl, + &count, f->cookie); + if (err) + return err; + + flow_stats_update(&f->stats, 0x0, count.value, 0, 0, + FLOW_ACTION_HW_STATS_IMMEDIATE); + + return err; +} + int lan966x_tc_flower(struct lan966x_port *port, - struct flow_cls_offload *f) + struct flow_cls_offload *f, + bool ingress) { struct vcap_admin *admin; @@ -245,9 +349,11 @@ int lan966x_tc_flower(struct lan966x_port *port, switch (f->command) { case FLOW_CLS_REPLACE: - return lan966x_tc_flower_add(port, f, admin); + return lan966x_tc_flower_add(port, f, admin, ingress); case FLOW_CLS_DESTROY: return lan966x_tc_flower_del(port, f, admin); + case FLOW_CLS_STATS: + return lan966x_tc_flower_stats(port, f, admin); default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_debugfs.c b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_debugfs.c new file mode 100644 index 000000000000..7a0db58f5513 --- /dev/null +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_debugfs.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include "lan966x_main.h" +#include "lan966x_vcap_ag_api.h" +#include "vcap_api.h" +#include "vcap_api_client.h" + +static void lan966x_vcap_port_keys(struct lan966x_port *port, + struct vcap_admin *admin, + struct vcap_output_print *out) +{ + struct lan966x *lan966x = port->lan966x; + u32 val; + + out->prf(out->dst, " port[%d] (%s): ", port->chip_port, + netdev_name(port->dev)); + + val = lan_rd(lan966x, ANA_VCAP_S2_CFG(port->chip_port)); + out->prf(out->dst, "\n state: "); + if (ANA_VCAP_S2_CFG_ENA_GET(val)) + out->prf(out->dst, "on"); + else + out->prf(out->dst, "off"); + + for (int l = 0; l < admin->lookups; ++l) { + out->prf(out->dst, "\n Lookup %d: ", l); + + out->prf(out->dst, "\n snap: "); + if (ANA_VCAP_S2_CFG_SNAP_DIS_GET(val) & (BIT(0) << l)) + out->prf(out->dst, "mac_llc"); + else + out->prf(out->dst, "mac_snap"); + + out->prf(out->dst, "\n oam: "); + if (ANA_VCAP_S2_CFG_OAM_DIS_GET(val) & (BIT(0) << l)) + out->prf(out->dst, "mac_etype"); + else + out->prf(out->dst, "mac_oam"); + + out->prf(out->dst, "\n arp: "); + if (ANA_VCAP_S2_CFG_ARP_DIS_GET(val) & (BIT(0) << l)) + out->prf(out->dst, "mac_etype"); + else + out->prf(out->dst, "mac_arp"); + + out->prf(out->dst, "\n ipv4_other: "); + if (ANA_VCAP_S2_CFG_IP_OTHER_DIS_GET(val) & (BIT(0) << l)) + out->prf(out->dst, "mac_etype"); + else + out->prf(out->dst, "ip4_other"); + + out->prf(out->dst, "\n ipv4_tcp_udp: "); + if (ANA_VCAP_S2_CFG_IP_TCPUDP_DIS_GET(val) & (BIT(0) << l)) + out->prf(out->dst, "mac_etype"); + else + out->prf(out->dst, "ipv4_tcp_udp"); + + out->prf(out->dst, "\n ipv6: "); + switch (ANA_VCAP_S2_CFG_IP6_CFG_GET(val) & (0x3 << l)) { + case VCAP_IS2_PS_IPV6_TCPUDP_OTHER: + out->prf(out->dst, "ipv6_tcp_udp ipv6_tcp_udp"); + break; + case VCAP_IS2_PS_IPV6_STD: + out->prf(out->dst, "ipv6_std"); + break; + case VCAP_IS2_PS_IPV6_IP4_TCPUDP_IP4_OTHER: + out->prf(out->dst, "ipv4_tcp_udp ipv4_tcp_udp"); + break; + case VCAP_IS2_PS_IPV6_MAC_ETYPE: + out->prf(out->dst, "mac_etype"); + break; + } + } + + out->prf(out->dst, "\n"); +} + +int lan966x_vcap_port_info(struct net_device *dev, + struct vcap_admin *admin, + struct vcap_output_print *out) +{ + struct lan966x_port *port = netdev_priv(dev); + struct lan966x *lan966x = port->lan966x; + const struct vcap_info *vcap; + struct vcap_control *vctrl; + + vctrl = lan966x->vcap_ctrl; + vcap = &vctrl->vcaps[admin->vtype]; + + out->prf(out->dst, "%s:\n", vcap->name); + lan966x_vcap_port_keys(port, admin, out); + + return 0; +} diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c index 76a9fb113f50..68f9d69fd37b 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c @@ -4,18 +4,12 @@ #include "lan966x_vcap_ag_api.h" #include "vcap_api.h" #include "vcap_api_client.h" +#include "vcap_api_debugfs.h" #define STREAMSIZE (64 * 4) #define LAN966X_IS2_LOOKUPS 2 -enum vcap_is2_port_sel_ipv6 { - VCAP_IS2_PS_IPV6_TCPUDP_OTHER, - VCAP_IS2_PS_IPV6_STD, - VCAP_IS2_PS_IPV6_IP4_TCPUDP_IP4_OTHER, - VCAP_IS2_PS_IPV6_MAC_ETYPE, -}; - static struct lan966x_vcap_inst { enum vcap_type vtype; /* type of vcap */ int tgt_inst; /* hardware instance number */ @@ -23,6 +17,7 @@ static struct lan966x_vcap_inst { int first_cid; /* first chain id in this vcap */ int last_cid; /* last chain id in this vcap */ int count; /* number of available addresses */ + bool ingress; /* is vcap in the ingress path */ } lan966x_vcap_inst_cfg[] = { { .vtype = VCAP_TYPE_IS2, /* IS2-0 */ @@ -31,6 +26,7 @@ static struct lan966x_vcap_inst { .first_cid = LAN966X_VCAP_CID_IS2_L0, .last_cid = LAN966X_VCAP_CID_IS2_MAX, .count = 256, + .ingress = true, }, }; @@ -383,13 +379,6 @@ static void lan966x_vcap_move(struct net_device *dev, lan966x_vcap_wait_update(lan966x, admin->tgt_inst); } -static int lan966x_vcap_port_info(struct net_device *dev, - struct vcap_admin *admin, - struct vcap_output_print *out) -{ - return 0; -} - static struct vcap_operations lan966x_vcap_ops = { .validate_keyset = lan966x_vcap_validate_keyset, .add_default_fields = lan966x_vcap_add_default_fields, @@ -431,6 +420,7 @@ lan966x_vcap_admin_alloc(struct lan966x *lan966x, struct vcap_control *ctrl, admin->vtype = cfg->vtype; admin->vinst = 0; + admin->ingress = cfg->ingress; admin->w32be = true; admin->tgt_inst = cfg->tgt_inst; @@ -483,6 +473,7 @@ int lan966x_vcap_init(struct lan966x *lan966x) struct lan966x_vcap_inst *cfg; struct vcap_control *ctrl; struct vcap_admin *admin; + struct dentry *dir; ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL); if (!ctrl) @@ -506,11 +497,17 @@ int lan966x_vcap_init(struct lan966x *lan966x) list_add_tail(&admin->list, &ctrl->list); } - for (int p = 0; p < lan966x->num_phys_ports; ++p) - if (lan966x->ports[p]) + dir = vcap_debugfs(lan966x->dev, lan966x->debugfs_root, ctrl); + for (int p = 0; p < lan966x->num_phys_ports; ++p) { + if (lan966x->ports[p]) { + vcap_port_debugfs(lan966x->dev, dir, ctrl, + lan966x->ports[p]->dev); + lan_rmw(ANA_VCAP_S2_CFG_ENA_SET(true), ANA_VCAP_S2_CFG_ENA, lan966x, ANA_VCAP_S2_CFG(lan966x->ports[p]->chip_port)); + } + } lan966x->vcap_ctrl = ctrl; diff --git a/drivers/net/ethernet/microchip/sparx5/Makefile b/drivers/net/ethernet/microchip/sparx5/Makefile index d0ed7090aa54..1cb1cc3f1a85 100644 --- a/drivers/net/ethernet/microchip/sparx5/Makefile +++ b/drivers/net/ethernet/microchip/sparx5/Makefile @@ -9,7 +9,8 @@ sparx5-switch-y := sparx5_main.o sparx5_packet.o \ sparx5_netdev.o sparx5_phylink.o sparx5_port.o sparx5_mactable.o sparx5_vlan.o \ sparx5_switchdev.o sparx5_calendar.o sparx5_ethtool.o sparx5_fdma.o \ sparx5_ptp.o sparx5_pgid.o sparx5_tc.o sparx5_qos.o \ - sparx5_vcap_impl.o sparx5_vcap_ag_api.o sparx5_tc_flower.o sparx5_tc_matchall.o + sparx5_vcap_impl.o sparx5_vcap_ag_api.o sparx5_tc_flower.o \ + sparx5_tc_matchall.o sparx5_pool.o sparx5_sdlb.o sparx5_police.o sparx5_psfp.o sparx5-switch-$(CONFIG_SPARX5_DCB) += sparx5_dcb.o sparx5-switch-$(CONFIG_DEBUG_FS) += sparx5_vcap_debugfs.o diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c index 3c5d4fe99373..c213a4414e65 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -198,12 +198,14 @@ static const struct sparx5_main_io_resource sparx5_main_iomap[] = { { TARGET_QSYS, 0x110a0000, 2 }, /* 0x6110a0000 */ { TARGET_QFWD, 0x110b0000, 2 }, /* 0x6110b0000 */ { TARGET_XQS, 0x110c0000, 2 }, /* 0x6110c0000 */ + { TARGET_VCAP_ES2, 0x110d0000, 2 }, /* 0x6110d0000 */ { TARGET_CLKGEN, 0x11100000, 2 }, /* 0x611100000 */ { TARGET_ANA_AC_POL, 0x11200000, 2 }, /* 0x611200000 */ { TARGET_QRES, 0x11280000, 2 }, /* 0x611280000 */ { TARGET_EACL, 0x112c0000, 2 }, /* 0x6112c0000 */ { TARGET_ANA_CL, 0x11400000, 2 }, /* 0x611400000 */ { TARGET_ANA_L3, 0x11480000, 2 }, /* 0x611480000 */ + { TARGET_ANA_AC_SDLB, 0x11500000, 2 }, /* 0x611500000 */ { TARGET_HSCH, 0x11580000, 2 }, /* 0x611580000 */ { TARGET_REW, 0x11600000, 2 }, /* 0x611600000 */ { TARGET_ANA_L2, 0x11800000, 2 }, /* 0x611800000 */ @@ -500,8 +502,8 @@ static int sparx5_init_coreclock(struct sparx5 *sparx5) clk_period = sparx5_clk_period(freq); - spx5_rmw(HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS_SET(clk_period / 100), - HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS, + spx5_rmw(HSCH_SYS_CLK_PER_100PS_SET(clk_period / 100), + HSCH_SYS_CLK_PER_100PS, sparx5, HSCH_SYS_CLK_PER); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h index 4a574cdcb584..72e7928912eb 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h @@ -396,6 +396,7 @@ int sparx5_ptp_txtstamp_request(struct sparx5_port *port, void sparx5_ptp_txtstamp_release(struct sparx5_port *port, struct sk_buff *skb); irqreturn_t sparx5_ptp_irq_handler(int irq, void *args); +int sparx5_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts); /* sparx5_vcap_impl.c */ int sparx5_vcap_init(struct sparx5 *sparx5); @@ -413,6 +414,129 @@ int sparx5_pgid_alloc_glag(struct sparx5 *spx5, u16 *idx); int sparx5_pgid_alloc_mcast(struct sparx5 *spx5, u16 *idx); int sparx5_pgid_free(struct sparx5 *spx5, u16 idx); +/* sparx5_pool.c */ +struct sparx5_pool_entry { + u16 ref_cnt; + u32 idx; /* tc index */ +}; + +u32 sparx5_pool_idx_to_id(u32 idx); +int sparx5_pool_put(struct sparx5_pool_entry *pool, int size, u32 id); +int sparx5_pool_get(struct sparx5_pool_entry *pool, int size, u32 *id); +int sparx5_pool_get_with_idx(struct sparx5_pool_entry *pool, int size, u32 idx, + u32 *id); + +/* sparx5_sdlb.c */ +#define SPX5_SDLB_PUP_TOKEN_DISABLE 0x1FFF +#define SPX5_SDLB_PUP_TOKEN_MAX (SPX5_SDLB_PUP_TOKEN_DISABLE - 1) +#define SPX5_SDLB_GROUP_RATE_MAX 25000000000ULL +#define SPX5_SDLB_2CYCLES_TYPE2_THRES_OFFSET 13 +#define SPX5_SDLB_CNT 4096 +#define SPX5_SDLB_GROUP_CNT 10 +#define SPX5_CLK_PER_100PS_DEFAULT 16 + +struct sparx5_sdlb_group { + u64 max_rate; + u32 min_burst; + u32 frame_size; + u32 pup_interval; + u32 nsets; +}; + +extern struct sparx5_sdlb_group sdlb_groups[SPX5_SDLB_GROUP_CNT]; +int sparx5_sdlb_pup_token_get(struct sparx5 *sparx5, u32 pup_interval, + u64 rate); + +int sparx5_sdlb_clk_hz_get(struct sparx5 *sparx5); +int sparx5_sdlb_group_get_by_rate(struct sparx5 *sparx5, u32 rate, u32 burst); +int sparx5_sdlb_group_get_by_index(struct sparx5 *sparx5, u32 idx, u32 *group); + +int sparx5_sdlb_group_add(struct sparx5 *sparx5, u32 group, u32 idx); +int sparx5_sdlb_group_del(struct sparx5 *sparx5, u32 group, u32 idx); + +void sparx5_sdlb_group_init(struct sparx5 *sparx5, u64 max_rate, u32 min_burst, + u32 frame_size, u32 idx); + +/* sparx5_police.c */ +enum { + /* More policer types will be added later */ + SPX5_POL_SERVICE +}; + +struct sparx5_policer { + u32 type; + u32 idx; + u64 rate; + u32 burst; + u32 group; + u8 event_mask; +}; + +int sparx5_policer_conf_set(struct sparx5 *sparx5, struct sparx5_policer *pol); + +/* sparx5_psfp.c */ +#define SPX5_PSFP_GCE_CNT 4 +#define SPX5_PSFP_SG_CNT 1024 +#define SPX5_PSFP_SG_MIN_CYCLE_TIME_NS (1 * NSEC_PER_USEC) +#define SPX5_PSFP_SG_MAX_CYCLE_TIME_NS ((1 * NSEC_PER_SEC) - 1) +#define SPX5_PSFP_SG_MAX_IPV (SPX5_PRIOS - 1) +#define SPX5_PSFP_SG_OPEN (SPX5_PSFP_SG_CNT - 1) +#define SPX5_PSFP_SG_CYCLE_TIME_DEFAULT 1000000 +#define SPX5_PSFP_SF_MAX_SDU 16383 + +struct sparx5_psfp_fm { + struct sparx5_policer pol; +}; + +struct sparx5_psfp_gce { + bool gate_state; /* StreamGateState */ + u32 interval; /* TimeInterval */ + u32 ipv; /* InternalPriorityValue */ + u32 maxoctets; /* IntervalOctetMax */ +}; + +struct sparx5_psfp_sg { + bool gate_state; /* PSFPAdminGateStates */ + bool gate_enabled; /* PSFPGateEnabled */ + u32 ipv; /* PSFPAdminIPV */ + struct timespec64 basetime; /* PSFPAdminBaseTime */ + u32 cycletime; /* PSFPAdminCycleTime */ + u32 cycletimeext; /* PSFPAdminCycleTimeExtension */ + u32 num_entries; /* PSFPAdminControlListLength */ + struct sparx5_psfp_gce gce[SPX5_PSFP_GCE_CNT]; +}; + +struct sparx5_psfp_sf { + bool sblock_osize_ena; + bool sblock_osize; + u32 max_sdu; + u32 sgid; /* Gate id */ + u32 fmid; /* Flow meter id */ +}; + +int sparx5_psfp_fm_add(struct sparx5 *sparx5, u32 uidx, + struct sparx5_psfp_fm *fm, u32 *id); +int sparx5_psfp_fm_del(struct sparx5 *sparx5, u32 id); + +int sparx5_psfp_sg_add(struct sparx5 *sparx5, u32 uidx, + struct sparx5_psfp_sg *sg, u32 *id); +int sparx5_psfp_sg_del(struct sparx5 *sparx5, u32 id); + +int sparx5_psfp_sf_add(struct sparx5 *sparx5, const struct sparx5_psfp_sf *sf, + u32 *id); +int sparx5_psfp_sf_del(struct sparx5 *sparx5, u32 id); + +u32 sparx5_psfp_isdx_get_sf(struct sparx5 *sparx5, u32 isdx); +u32 sparx5_psfp_isdx_get_fm(struct sparx5 *sparx5, u32 isdx); +u32 sparx5_psfp_sf_get_sg(struct sparx5 *sparx5, u32 sfid); +void sparx5_isdx_conf_set(struct sparx5 *sparx5, u32 isdx, u32 sfid, u32 fmid); + +void sparx5_psfp_init(struct sparx5 *sparx5); + +/* sparx5_qos.c */ +void sparx5_new_base_time(struct sparx5 *sparx5, const u32 cycle_time, + const ktime_t org_base_time, ktime_t *new_base_time); + /* Clock period in picoseconds */ static inline u32 sparx5_clk_period(enum sparx5_core_clockfreq cclock) { diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h index e3bf0460333d..bd73742939d3 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h @@ -4,8 +4,8 @@ * Copyright (c) 2021 Microchip Technology Inc. */ -/* This file is autogenerated by cml-utils 2022-12-06 15:28:38 +0100. - * Commit ID: 3db2ac730f134c160496f2b9f10915e347d871cb +/* This file is autogenerated by cml-utils 2023-01-17 17:04:43 +0100. + * Commit ID: cc027a9bd71002aebf074df5ad8584fe1545e05e */ #ifndef _SPARX5_MAIN_REGS_H_ @@ -19,6 +19,7 @@ enum sparx5_target { TARGET_ANA_AC = 1, TARGET_ANA_ACL = 2, TARGET_ANA_AC_POL = 4, + TARGET_ANA_AC_SDLB = 5, TARGET_ANA_CL = 6, TARGET_ANA_L2 = 7, TARGET_ANA_L3 = 8, @@ -46,6 +47,7 @@ enum sparx5_target { TARGET_QS = 177, TARGET_QSYS = 178, TARGET_REW = 179, + TARGET_VCAP_ES2 = 324, TARGET_VCAP_SUPER = 326, TARGET_VOP = 327, TARGET_XQS = 331, @@ -129,6 +131,254 @@ enum sparx5_target { #define ANA_AC_PGID_MISC_CFG_PGID_CPU_COPY_ENA_GET(x)\ FIELD_GET(ANA_AC_PGID_MISC_CFG_PGID_CPU_COPY_ENA, x) +/* ANA_AC:TSN_SF:TSN_SF */ +#define ANA_AC_TSN_SF \ + __REG(TARGET_ANA_AC, 0, 1, 839136, 0, 1, 4, 0, 0, 1, 4) + +#define ANA_AC_TSN_SF_TSN_STREAM_BLOCK_OVERSIZE_STICKY BIT(9) +#define ANA_AC_TSN_SF_TSN_STREAM_BLOCK_OVERSIZE_STICKY_SET(x)\ + FIELD_PREP(ANA_AC_TSN_SF_TSN_STREAM_BLOCK_OVERSIZE_STICKY, x) +#define ANA_AC_TSN_SF_TSN_STREAM_BLOCK_OVERSIZE_STICKY_GET(x)\ + FIELD_GET(ANA_AC_TSN_SF_TSN_STREAM_BLOCK_OVERSIZE_STICKY, x) + +#define ANA_AC_TSN_SF_PORT_NUM GENMASK(8, 0) +#define ANA_AC_TSN_SF_PORT_NUM_SET(x)\ + FIELD_PREP(ANA_AC_TSN_SF_PORT_NUM, x) +#define ANA_AC_TSN_SF_PORT_NUM_GET(x)\ + FIELD_GET(ANA_AC_TSN_SF_PORT_NUM, x) + +/* ANA_AC:TSN_SF_CFG:TSN_SF_CFG */ +#define ANA_AC_TSN_SF_CFG(g) \ + __REG(TARGET_ANA_AC, 0, 1, 839680, g, 1024, 4, 0, 0, 1, 4) + +#define ANA_AC_TSN_SF_CFG_TSN_SGID GENMASK(25, 16) +#define ANA_AC_TSN_SF_CFG_TSN_SGID_SET(x)\ + FIELD_PREP(ANA_AC_TSN_SF_CFG_TSN_SGID, x) +#define ANA_AC_TSN_SF_CFG_TSN_SGID_GET(x)\ + FIELD_GET(ANA_AC_TSN_SF_CFG_TSN_SGID, x) + +#define ANA_AC_TSN_SF_CFG_TSN_MAX_SDU GENMASK(15, 2) +#define ANA_AC_TSN_SF_CFG_TSN_MAX_SDU_SET(x)\ + FIELD_PREP(ANA_AC_TSN_SF_CFG_TSN_MAX_SDU, x) +#define ANA_AC_TSN_SF_CFG_TSN_MAX_SDU_GET(x)\ + FIELD_GET(ANA_AC_TSN_SF_CFG_TSN_MAX_SDU, x) + +#define ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_ENA BIT(1) +#define ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_ENA_SET(x) \ + FIELD_PREP(ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_ENA, x) +#define ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_ENA_GET(x) \ + FIELD_GET(ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_ENA, x) + +#define ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_STATE BIT(0) +#define ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_STATE_SET(x) \ + FIELD_PREP(ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_STATE, x) +#define ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_STATE_GET(x) \ + FIELD_GET(ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_STATE, x) + +/* ANA_AC:TSN_SF_STATUS:TSN_SF_STATUS */ +#define ANA_AC_TSN_SF_STATUS \ + __REG(TARGET_ANA_AC, 0, 1, 839072, 0, 1, 16, 0, 0, 1, 4) + +#define ANA_AC_TSN_SF_STATUS_FRM_LEN GENMASK(25, 12) +#define ANA_AC_TSN_SF_STATUS_FRM_LEN_SET(x)\ + FIELD_PREP(ANA_AC_TSN_SF_STATUS_FRM_LEN, x) +#define ANA_AC_TSN_SF_STATUS_FRM_LEN_GET(x)\ + FIELD_GET(ANA_AC_TSN_SF_STATUS_FRM_LEN, x) + +#define ANA_AC_TSN_SF_STATUS_DLB_DROP BIT(11) +#define ANA_AC_TSN_SF_STATUS_DLB_DROP_SET(x)\ + FIELD_PREP(ANA_AC_TSN_SF_STATUS_DLB_DROP, x) +#define ANA_AC_TSN_SF_STATUS_DLB_DROP_GET(x)\ + FIELD_GET(ANA_AC_TSN_SF_STATUS_DLB_DROP, x) + +#define ANA_AC_TSN_SF_STATUS_TSN_SFID GENMASK(10, 1) +#define ANA_AC_TSN_SF_STATUS_TSN_SFID_SET(x)\ + FIELD_PREP(ANA_AC_TSN_SF_STATUS_TSN_SFID, x) +#define ANA_AC_TSN_SF_STATUS_TSN_SFID_GET(x)\ + FIELD_GET(ANA_AC_TSN_SF_STATUS_TSN_SFID, x) + +#define ANA_AC_TSN_SF_STATUS_TSTAMP_VLD BIT(0) +#define ANA_AC_TSN_SF_STATUS_TSTAMP_VLD_SET(x)\ + FIELD_PREP(ANA_AC_TSN_SF_STATUS_TSTAMP_VLD, x) +#define ANA_AC_TSN_SF_STATUS_TSTAMP_VLD_GET(x)\ + FIELD_GET(ANA_AC_TSN_SF_STATUS_TSTAMP_VLD, x) + +/* ANA_AC:SG_ACCESS:SG_ACCESS_CTRL */ +#define ANA_AC_SG_ACCESS_CTRL \ + __REG(TARGET_ANA_AC, 0, 1, 839140, 0, 1, 12, 0, 0, 1, 4) + +#define ANA_AC_SG_ACCESS_CTRL_SGID GENMASK(9, 0) +#define ANA_AC_SG_ACCESS_CTRL_SGID_SET(x)\ + FIELD_PREP(ANA_AC_SG_ACCESS_CTRL_SGID, x) +#define ANA_AC_SG_ACCESS_CTRL_SGID_GET(x)\ + FIELD_GET(ANA_AC_SG_ACCESS_CTRL_SGID, x) + +#define ANA_AC_SG_ACCESS_CTRL_CONFIG_CHANGE BIT(28) +#define ANA_AC_SG_ACCESS_CTRL_CONFIG_CHANGE_SET(x)\ + FIELD_PREP(ANA_AC_SG_ACCESS_CTRL_CONFIG_CHANGE, x) +#define ANA_AC_SG_ACCESS_CTRL_CONFIG_CHANGE_GET(x)\ + FIELD_GET(ANA_AC_SG_ACCESS_CTRL_CONFIG_CHANGE, x) + +/* ANA_AC:SG_ACCESS:SG_CYCLETIME_UPDATE_PERIOD */ +#define ANA_AC_SG_CYCLETIME_UPDATE_PERIOD \ + __REG(TARGET_ANA_AC, 0, 1, 839140, 0, 1, 12, 8, 0, 1, 4) + +#define ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_CLKS GENMASK(15, 0) +#define ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_CLKS_SET(x)\ + FIELD_PREP(ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_CLKS, x) +#define ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_CLKS_GET(x)\ + FIELD_GET(ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_CLKS, x) + +#define ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_UPDATE_ENA BIT(31) +#define ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_UPDATE_ENA_SET(x)\ + FIELD_PREP(ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_UPDATE_ENA, x) +#define ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_UPDATE_ENA_GET(x)\ + FIELD_GET(ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_UPDATE_ENA, x) + +/* ANA_AC:SG_CONFIG:SG_CONFIG_REG_1 */ +#define ANA_AC_SG_CONFIG_REG_1 \ + __REG(TARGET_ANA_AC, 0, 1, 851584, 0, 1, 128, 48, 0, 1, 4) + +/* ANA_AC:SG_CONFIG:SG_CONFIG_REG_2 */ +#define ANA_AC_SG_CONFIG_REG_2 \ + __REG(TARGET_ANA_AC, 0, 1, 851584, 0, 1, 128, 52, 0, 1, 4) + +/* ANA_AC:SG_CONFIG:SG_CONFIG_REG_3 */ +#define ANA_AC_SG_CONFIG_REG_3 \ + __REG(TARGET_ANA_AC, 0, 1, 851584, 0, 1, 128, 56, 0, 1, 4) + +#define ANA_AC_SG_CONFIG_REG_3_BASE_TIME_SEC_MSB GENMASK(15, 0) +#define ANA_AC_SG_CONFIG_REG_3_BASE_TIME_SEC_MSB_SET(x)\ + FIELD_PREP(ANA_AC_SG_CONFIG_REG_3_BASE_TIME_SEC_MSB, x) +#define ANA_AC_SG_CONFIG_REG_3_BASE_TIME_SEC_MSB_GET(x)\ + FIELD_GET(ANA_AC_SG_CONFIG_REG_3_BASE_TIME_SEC_MSB, x) + +#define ANA_AC_SG_CONFIG_REG_3_LIST_LENGTH GENMASK(18, 16) +#define ANA_AC_SG_CONFIG_REG_3_LIST_LENGTH_SET(x)\ + FIELD_PREP(ANA_AC_SG_CONFIG_REG_3_LIST_LENGTH, x) +#define ANA_AC_SG_CONFIG_REG_3_LIST_LENGTH_GET(x)\ + FIELD_GET(ANA_AC_SG_CONFIG_REG_3_LIST_LENGTH, x) + +#define ANA_AC_SG_CONFIG_REG_3_GATE_ENABLE BIT(20) +#define ANA_AC_SG_CONFIG_REG_3_GATE_ENABLE_SET(x)\ + FIELD_PREP(ANA_AC_SG_CONFIG_REG_3_GATE_ENABLE, x) +#define ANA_AC_SG_CONFIG_REG_3_GATE_ENABLE_GET(x)\ + FIELD_GET(ANA_AC_SG_CONFIG_REG_3_GATE_ENABLE, x) + +#define ANA_AC_SG_CONFIG_REG_3_INIT_IPS GENMASK(24, 21) +#define ANA_AC_SG_CONFIG_REG_3_INIT_IPS_SET(x)\ + FIELD_PREP(ANA_AC_SG_CONFIG_REG_3_INIT_IPS, x) +#define ANA_AC_SG_CONFIG_REG_3_INIT_IPS_GET(x)\ + FIELD_GET(ANA_AC_SG_CONFIG_REG_3_INIT_IPS, x) + +#define ANA_AC_SG_CONFIG_REG_3_INIT_GATE_STATE BIT(25) +#define ANA_AC_SG_CONFIG_REG_3_INIT_GATE_STATE_SET(x)\ + FIELD_PREP(ANA_AC_SG_CONFIG_REG_3_INIT_GATE_STATE, x) +#define ANA_AC_SG_CONFIG_REG_3_INIT_GATE_STATE_GET(x)\ + FIELD_GET(ANA_AC_SG_CONFIG_REG_3_INIT_GATE_STATE, x) + +#define ANA_AC_SG_CONFIG_REG_3_INVALID_RX_ENA BIT(26) +#define ANA_AC_SG_CONFIG_REG_3_INVALID_RX_ENA_SET(x)\ + FIELD_PREP(ANA_AC_SG_CONFIG_REG_3_INVALID_RX_ENA, x) +#define ANA_AC_SG_CONFIG_REG_3_INVALID_RX_ENA_GET(x)\ + FIELD_GET(ANA_AC_SG_CONFIG_REG_3_INVALID_RX_ENA, x) + +#define ANA_AC_SG_CONFIG_REG_3_INVALID_RX BIT(27) +#define ANA_AC_SG_CONFIG_REG_3_INVALID_RX_SET(x)\ + FIELD_PREP(ANA_AC_SG_CONFIG_REG_3_INVALID_RX, x) +#define ANA_AC_SG_CONFIG_REG_3_INVALID_RX_GET(x)\ + FIELD_GET(ANA_AC_SG_CONFIG_REG_3_INVALID_RX, x) + +#define ANA_AC_SG_CONFIG_REG_3_OCTETS_EXCEEDED_ENA BIT(28) +#define ANA_AC_SG_CONFIG_REG_3_OCTETS_EXCEEDED_ENA_SET(x)\ + FIELD_PREP(ANA_AC_SG_CONFIG_REG_3_OCTETS_EXCEEDED_ENA, x) +#define ANA_AC_SG_CONFIG_REG_3_OCTETS_EXCEEDED_ENA_GET(x)\ + FIELD_GET(ANA_AC_SG_CONFIG_REG_3_OCTETS_EXCEEDED_ENA, x) + +#define ANA_AC_SG_CONFIG_REG_3_OCTETS_EXCEEDED BIT(29) +#define ANA_AC_SG_CONFIG_REG_3_OCTETS_EXCEEDED_SET(x)\ + FIELD_PREP(ANA_AC_SG_CONFIG_REG_3_OCTETS_EXCEEDED, x) +#define ANA_AC_SG_CONFIG_REG_3_OCTETS_EXCEEDED_GET(x)\ + FIELD_GET(ANA_AC_SG_CONFIG_REG_3_OCTETS_EXCEEDED, x) + +/* ANA_AC:SG_CONFIG:SG_CONFIG_REG_4 */ +#define ANA_AC_SG_CONFIG_REG_4 \ + __REG(TARGET_ANA_AC, 0, 1, 851584, 0, 1, 128, 60, 0, 1, 4) + +/* ANA_AC:SG_CONFIG:SG_CONFIG_REG_5 */ +#define ANA_AC_SG_CONFIG_REG_5 \ + __REG(TARGET_ANA_AC, 0, 1, 851584, 0, 1, 128, 64, 0, 1, 4) + +/* ANA_AC:SG_CONFIG:SG_GCL_GS_CONFIG */ +#define ANA_AC_SG_GCL_GS_CONFIG(r) \ + __REG(TARGET_ANA_AC, 0, 1, 851584, 0, 1, 128, 0, r, 4, 4) + +#define ANA_AC_SG_GCL_GS_CONFIG_IPS GENMASK(3, 0) +#define ANA_AC_SG_GCL_GS_CONFIG_IPS_SET(x)\ + FIELD_PREP(ANA_AC_SG_GCL_GS_CONFIG_IPS, x) +#define ANA_AC_SG_GCL_GS_CONFIG_IPS_GET(x)\ + FIELD_GET(ANA_AC_SG_GCL_GS_CONFIG_IPS, x) + +#define ANA_AC_SG_GCL_GS_CONFIG_GATE_STATE BIT(4) +#define ANA_AC_SG_GCL_GS_CONFIG_GATE_STATE_SET(x)\ + FIELD_PREP(ANA_AC_SG_GCL_GS_CONFIG_GATE_STATE, x) +#define ANA_AC_SG_GCL_GS_CONFIG_GATE_STATE_GET(x)\ + FIELD_GET(ANA_AC_SG_GCL_GS_CONFIG_GATE_STATE, x) + +/* ANA_AC:SG_CONFIG:SG_GCL_TI_CONFIG */ +#define ANA_AC_SG_GCL_TI_CONFIG(r) \ + __REG(TARGET_ANA_AC, 0, 1, 851584, 0, 1, 128, 16, r, 4, 4) + +/* ANA_AC:SG_CONFIG:SG_GCL_OCT_CONFIG */ +#define ANA_AC_SG_GCL_OCT_CONFIG(r) \ + __REG(TARGET_ANA_AC, 0, 1, 851584, 0, 1, 128, 32, r, 4, 4) + +/* ANA_AC:SG_STATUS:SG_STATUS_REG_1 */ +#define ANA_AC_SG_STATUS_REG_1 \ + __REG(TARGET_ANA_AC, 0, 1, 839088, 0, 1, 16, 0, 0, 1, 4) + +/* ANA_AC:SG_STATUS:SG_STATUS_REG_2 */ +#define ANA_AC_SG_STATUS_REG_2 \ + __REG(TARGET_ANA_AC, 0, 1, 839088, 0, 1, 16, 4, 0, 1, 4) + +/* ANA_AC:SG_STATUS:SG_STATUS_REG_3 */ +#define ANA_AC_SG_STATUS_REG_3 \ + __REG(TARGET_ANA_AC, 0, 1, 839088, 0, 1, 16, 8, 0, 1, 4) + +#define ANA_AC_SG_STATUS_REG_3_CFG_CHG_TIME_SEC_MSB GENMASK(15, 0) +#define ANA_AC_SG_STATUS_REG_3_CFG_CHG_TIME_SEC_MSB_SET(x)\ + FIELD_PREP(ANA_AC_SG_STATUS_REG_3_CFG_CHG_TIME_SEC_MSB, x) +#define ANA_AC_SG_STATUS_REG_3_CFG_CHG_TIME_SEC_MSB_GET(x)\ + FIELD_GET(ANA_AC_SG_STATUS_REG_3_CFG_CHG_TIME_SEC_MSB, x) + +#define ANA_AC_SG_STATUS_REG_3_GATE_STATE BIT(16) +#define ANA_AC_SG_STATUS_REG_3_GATE_STATE_SET(x)\ + FIELD_PREP(ANA_AC_SG_STATUS_REG_3_GATE_STATE, x) +#define ANA_AC_SG_STATUS_REG_3_GATE_STATE_GET(x)\ + FIELD_GET(ANA_AC_SG_STATUS_REG_3_GATE_STATE, x) + +#define ANA_AC_SG_STATUS_REG_3_IPS GENMASK(23, 20) +#define ANA_AC_SG_STATUS_REG_3_IPS_SET(x)\ + FIELD_PREP(ANA_AC_SG_STATUS_REG_3_IPS, x) +#define ANA_AC_SG_STATUS_REG_3_IPS_GET(x)\ + FIELD_GET(ANA_AC_SG_STATUS_REG_3_IPS, x) + +#define ANA_AC_SG_STATUS_REG_3_CONFIG_PENDING BIT(24) +#define ANA_AC_SG_STATUS_REG_3_CONFIG_PENDING_SET(x)\ + FIELD_PREP(ANA_AC_SG_STATUS_REG_3_CONFIG_PENDING, x) +#define ANA_AC_SG_STATUS_REG_3_CONFIG_PENDING_GET(x)\ + FIELD_GET(ANA_AC_SG_STATUS_REG_3_CONFIG_PENDING, x) + +#define ANA_AC_SG_STATUS_REG_3_GCL_OCTET_INDEX GENMASK(27, 25) +#define ANA_AC_SG_STATUS_REG_3_GCL_OCTET_INDEX_SET(x)\ + FIELD_PREP(ANA_AC_SG_STATUS_REG_3_GCL_OCTET_INDEX, x) +#define ANA_AC_SG_STATUS_REG_3_GCL_OCTET_INDEX_GET(x)\ + FIELD_GET(ANA_AC_SG_STATUS_REG_3_GCL_OCTET_INDEX, x) + +/* ANA_AC:SG_STATUS:SG_STATUS_REG_4 */ +#define ANA_AC_SG_STATUS_REG_4 \ + __REG(TARGET_ANA_AC, 0, 1, 839088, 0, 1, 16, 12, 0, 1, 4) + /* ANA_AC:STAT_GLOBAL_CFG_PORT:STAT_GLOBAL_EVENT_MASK */ #define ANA_AC_PORT_SGE_CFG(r) __REG(TARGET_ANA_AC, 0, 1, 851552, 0, 1, 20, 0, r, 4, 4) @@ -567,6 +817,232 @@ enum sparx5_target { #define ANA_AC_POL_SLB_DLB_CTRL_DLB_ADD_ENA_GET(x)\ FIELD_GET(ANA_AC_POL_SLB_DLB_CTRL_DLB_ADD_ENA, x) +/* ANA_AC_SDLB:LBGRP_TBL:XLB_START */ +#define ANA_AC_SDLB_XLB_START(g) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 295468, g, 10, 24, 0, 0, 1, 4) + +#define ANA_AC_SDLB_XLB_START_LBSET_START GENMASK(12, 0) +#define ANA_AC_SDLB_XLB_START_LBSET_START_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_XLB_START_LBSET_START, x) +#define ANA_AC_SDLB_XLB_START_LBSET_START_GET(x)\ + FIELD_GET(ANA_AC_SDLB_XLB_START_LBSET_START, x) + +/* ANA_AC_SDLB:LBGRP_TBL:PUP_INTERVAL */ +#define ANA_AC_SDLB_PUP_INTERVAL(g) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 295468, g, 10, 24, 4, 0, 1, 4) + +#define ANA_AC_SDLB_PUP_INTERVAL_PUP_INTERVAL GENMASK(19, 0) +#define ANA_AC_SDLB_PUP_INTERVAL_PUP_INTERVAL_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_PUP_INTERVAL_PUP_INTERVAL, x) +#define ANA_AC_SDLB_PUP_INTERVAL_PUP_INTERVAL_GET(x)\ + FIELD_GET(ANA_AC_SDLB_PUP_INTERVAL_PUP_INTERVAL, x) + +/* ANA_AC_SDLB:LBGRP_TBL:PUP_CTRL */ +#define ANA_AC_SDLB_PUP_CTRL(g) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 295468, g, 10, 24, 8, 0, 1, 4) + +#define ANA_AC_SDLB_PUP_CTRL_PUP_LB_DT GENMASK(18, 0) +#define ANA_AC_SDLB_PUP_CTRL_PUP_LB_DT_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_PUP_CTRL_PUP_LB_DT, x) +#define ANA_AC_SDLB_PUP_CTRL_PUP_LB_DT_GET(x)\ + FIELD_GET(ANA_AC_SDLB_PUP_CTRL_PUP_LB_DT, x) + +#define ANA_AC_SDLB_PUP_CTRL_PUP_ENA BIT(24) +#define ANA_AC_SDLB_PUP_CTRL_PUP_ENA_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_PUP_CTRL_PUP_ENA, x) +#define ANA_AC_SDLB_PUP_CTRL_PUP_ENA_GET(x)\ + FIELD_GET(ANA_AC_SDLB_PUP_CTRL_PUP_ENA, x) + +/* ANA_AC_SDLB:LBGRP_TBL:LBGRP_MISC */ +#define ANA_AC_SDLB_LBGRP_MISC(g)\ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 295468, g, 10, 24, 12, 0, 1, 4) + +#define ANA_AC_SDLB_LBGRP_MISC_THRES_SHIFT GENMASK(12, 8) +#define ANA_AC_SDLB_LBGRP_MISC_THRES_SHIFT_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_LBGRP_MISC_THRES_SHIFT, x) +#define ANA_AC_SDLB_LBGRP_MISC_THRES_SHIFT_GET(x)\ + FIELD_GET(ANA_AC_SDLB_LBGRP_MISC_THRES_SHIFT, x) + +/* ANA_AC_SDLB:LBGRP_TBL:FRM_RATE_TOKENS */ +#define ANA_AC_SDLB_FRM_RATE_TOKENS(g) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 295468, g, 10, 24, 16, 0, 1, 4) + +#define ANA_AC_SDLB_FRM_RATE_TOKENS_FRM_RATE_TOKENS GENMASK(12, 0) +#define ANA_AC_SDLB_FRM_RATE_TOKENS_FRM_RATE_TOKENS_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_FRM_RATE_TOKENS_FRM_RATE_TOKENS, x) +#define ANA_AC_SDLB_FRM_RATE_TOKENS_FRM_RATE_TOKENS_GET(x)\ + FIELD_GET(ANA_AC_SDLB_FRM_RATE_TOKENS_FRM_RATE_TOKENS, x) + +/* ANA_AC_SDLB:LBGRP_TBL:LBGRP_STATE_TBL */ +#define ANA_AC_SDLB_LBGRP_STATE_TBL(g) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 295468, g, 10, 24, 20, 0, 1, 4) + +#define ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_ONGOING BIT(0) +#define ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_ONGOING_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_ONGOING, x) +#define ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_ONGOING_GET(x)\ + FIELD_GET(ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_ONGOING, x) + +#define ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_WAIT_ACK BIT(1) +#define ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_WAIT_ACK_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_WAIT_ACK, x) +#define ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_WAIT_ACK_GET(x)\ + FIELD_GET(ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_WAIT_ACK, x) + +#define ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_LBSET_NEXT GENMASK(28, 16) +#define ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_LBSET_NEXT_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_LBSET_NEXT, x) +#define ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_LBSET_NEXT_GET(x)\ + FIELD_GET(ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_LBSET_NEXT, x) + +/* ANA_AC_SDLB:LBSET_TBL:PUP_TOKENS */ +#define ANA_AC_SDLB_PUP_TOKENS(g, r) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 0, g, 4616, 64, 0, r, 2, 4) + +#define ANA_AC_SDLB_PUP_TOKENS_PUP_TOKENS GENMASK(12, 0) +#define ANA_AC_SDLB_PUP_TOKENS_PUP_TOKENS_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_PUP_TOKENS_PUP_TOKENS, x) +#define ANA_AC_SDLB_PUP_TOKENS_PUP_TOKENS_GET(x)\ + FIELD_GET(ANA_AC_SDLB_PUP_TOKENS_PUP_TOKENS, x) + +/* ANA_AC_SDLB:LBSET_TBL:THRES */ +#define ANA_AC_SDLB_THRES(g, r) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 0, g, 4616, 64, 8, r, 2, 4) + +#define ANA_AC_SDLB_THRES_THRES GENMASK(9, 0) +#define ANA_AC_SDLB_THRES_THRES_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_THRES_THRES, x) +#define ANA_AC_SDLB_THRES_THRES_GET(x)\ + FIELD_GET(ANA_AC_SDLB_THRES_THRES, x) + +#define ANA_AC_SDLB_THRES_THRES_HYS GENMASK(25, 16) +#define ANA_AC_SDLB_THRES_THRES_HYS_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_THRES_THRES_HYS, x) +#define ANA_AC_SDLB_THRES_THRES_HYS_GET(x)\ + FIELD_GET(ANA_AC_SDLB_THRES_THRES_HYS, x) + +/* ANA_AC_SDLB:LBSET_TBL:XLB_NEXT */ +#define ANA_AC_SDLB_XLB_NEXT(g) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 0, g, 4616, 64, 16, 0, 1, 4) + +#define ANA_AC_SDLB_XLB_NEXT_LBSET_NEXT GENMASK(12, 0) +#define ANA_AC_SDLB_XLB_NEXT_LBSET_NEXT_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_XLB_NEXT_LBSET_NEXT, x) +#define ANA_AC_SDLB_XLB_NEXT_LBSET_NEXT_GET(x)\ + FIELD_GET(ANA_AC_SDLB_XLB_NEXT_LBSET_NEXT, x) + +#define ANA_AC_SDLB_XLB_NEXT_LBGRP GENMASK(27, 24) +#define ANA_AC_SDLB_XLB_NEXT_LBGRP_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_XLB_NEXT_LBGRP, x) +#define ANA_AC_SDLB_XLB_NEXT_LBGRP_GET(x)\ + FIELD_GET(ANA_AC_SDLB_XLB_NEXT_LBGRP, x) + +/* ANA_AC_SDLB:LBSET_TBL:INH_CTRL */ +#define ANA_AC_SDLB_INH_CTRL(g, r) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 0, g, 4616, 64, 20, r, 2, 4) + +#define ANA_AC_SDLB_INH_CTRL_PUP_TOKENS_MAX GENMASK(12, 0) +#define ANA_AC_SDLB_INH_CTRL_PUP_TOKENS_MAX_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_INH_CTRL_PUP_TOKENS_MAX, x) +#define ANA_AC_SDLB_INH_CTRL_PUP_TOKENS_MAX_GET(x)\ + FIELD_GET(ANA_AC_SDLB_INH_CTRL_PUP_TOKENS_MAX, x) + +#define ANA_AC_SDLB_INH_CTRL_INH_MODE GENMASK(21, 20) +#define ANA_AC_SDLB_INH_CTRL_INH_MODE_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_INH_CTRL_INH_MODE, x) +#define ANA_AC_SDLB_INH_CTRL_INH_MODE_GET(x)\ + FIELD_GET(ANA_AC_SDLB_INH_CTRL_INH_MODE, x) + +#define ANA_AC_SDLB_INH_CTRL_INH_LB BIT(24) +#define ANA_AC_SDLB_INH_CTRL_INH_LB_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_INH_CTRL_INH_LB, x) +#define ANA_AC_SDLB_INH_CTRL_INH_LB_GET(x)\ + FIELD_GET(ANA_AC_SDLB_INH_CTRL_INH_LB, x) + +/* ANA_AC_SDLB:LBSET_TBL:INH_LBSET_ADDR */ +#define ANA_AC_SDLB_INH_LBSET_ADDR(g) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 0, g, 4616, 64, 28, 0, 1, 4) + +#define ANA_AC_SDLB_INH_LBSET_ADDR_INH_LBSET_ADDR GENMASK(12, 0) +#define ANA_AC_SDLB_INH_LBSET_ADDR_INH_LBSET_ADDR_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_INH_LBSET_ADDR_INH_LBSET_ADDR, x) +#define ANA_AC_SDLB_INH_LBSET_ADDR_INH_LBSET_ADDR_GET(x)\ + FIELD_GET(ANA_AC_SDLB_INH_LBSET_ADDR_INH_LBSET_ADDR, x) + +/* ANA_AC_SDLB:LBSET_TBL:DLB_MISC */ +#define ANA_AC_SDLB_DLB_MISC(g) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 0, g, 4616, 64, 32, 0, 1, 4) + +#define ANA_AC_SDLB_DLB_MISC_DLB_FRM_RATE_ENA BIT(0) +#define ANA_AC_SDLB_DLB_MISC_DLB_FRM_RATE_ENA_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_MISC_DLB_FRM_RATE_ENA, x) +#define ANA_AC_SDLB_DLB_MISC_DLB_FRM_RATE_ENA_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_MISC_DLB_FRM_RATE_ENA, x) + +#define ANA_AC_SDLB_DLB_MISC_MARK_ALL_FRMS_RED_ENA BIT(6) +#define ANA_AC_SDLB_DLB_MISC_MARK_ALL_FRMS_RED_ENA_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_MISC_MARK_ALL_FRMS_RED_ENA, x) +#define ANA_AC_SDLB_DLB_MISC_MARK_ALL_FRMS_RED_ENA_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_MISC_MARK_ALL_FRMS_RED_ENA, x) + +#define ANA_AC_SDLB_DLB_MISC_DLB_FRM_ADJ GENMASK(14, 8) +#define ANA_AC_SDLB_DLB_MISC_DLB_FRM_ADJ_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_MISC_DLB_FRM_ADJ, x) +#define ANA_AC_SDLB_DLB_MISC_DLB_FRM_ADJ_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_MISC_DLB_FRM_ADJ, x) + +/* ANA_AC_SDLB:LBSET_TBL:DLB_CFG */ +#define ANA_AC_SDLB_DLB_CFG(g) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 0, g, 4616, 64, 36, 0, 1, 4) + +#define ANA_AC_SDLB_DLB_CFG_DROP_ON_YELLOW_ENA BIT(11) +#define ANA_AC_SDLB_DLB_CFG_DROP_ON_YELLOW_ENA_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_CFG_DROP_ON_YELLOW_ENA, x) +#define ANA_AC_SDLB_DLB_CFG_DROP_ON_YELLOW_ENA_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_CFG_DROP_ON_YELLOW_ENA, x) + +#define ANA_AC_SDLB_DLB_CFG_DP_BYPASS_LVL GENMASK(10, 9) +#define ANA_AC_SDLB_DLB_CFG_DP_BYPASS_LVL_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_CFG_DP_BYPASS_LVL, x) +#define ANA_AC_SDLB_DLB_CFG_DP_BYPASS_LVL_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_CFG_DP_BYPASS_LVL, x) + +#define ANA_AC_SDLB_DLB_CFG_HIER_DLB_DIS BIT(8) +#define ANA_AC_SDLB_DLB_CFG_HIER_DLB_DIS_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_CFG_HIER_DLB_DIS, x) +#define ANA_AC_SDLB_DLB_CFG_HIER_DLB_DIS_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_CFG_HIER_DLB_DIS, x) + +#define ANA_AC_SDLB_DLB_CFG_ENCAP_DATA_DIS BIT(7) +#define ANA_AC_SDLB_DLB_CFG_ENCAP_DATA_DIS_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_CFG_ENCAP_DATA_DIS, x) +#define ANA_AC_SDLB_DLB_CFG_ENCAP_DATA_DIS_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_CFG_ENCAP_DATA_DIS, x) + +#define ANA_AC_SDLB_DLB_CFG_COLOR_AWARE_LVL GENMASK(6, 5) +#define ANA_AC_SDLB_DLB_CFG_COLOR_AWARE_LVL_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_CFG_COLOR_AWARE_LVL, x) +#define ANA_AC_SDLB_DLB_CFG_COLOR_AWARE_LVL_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_CFG_COLOR_AWARE_LVL, x) + +#define ANA_AC_SDLB_DLB_CFG_CIR_INC_DP_VAL GENMASK(4, 3) +#define ANA_AC_SDLB_DLB_CFG_CIR_INC_DP_VAL_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_CFG_CIR_INC_DP_VAL, x) +#define ANA_AC_SDLB_DLB_CFG_CIR_INC_DP_VAL_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_CFG_CIR_INC_DP_VAL, x) + +#define ANA_AC_SDLB_DLB_CFG_DLB_MODE BIT(2) +#define ANA_AC_SDLB_DLB_CFG_DLB_MODE_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_CFG_DLB_MODE, x) +#define ANA_AC_SDLB_DLB_CFG_DLB_MODE_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_CFG_DLB_MODE, x) + +#define ANA_AC_SDLB_DLB_CFG_TRAFFIC_TYPE_MASK GENMASK(1, 0) +#define ANA_AC_SDLB_DLB_CFG_TRAFFIC_TYPE_MASK_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_CFG_TRAFFIC_TYPE_MASK, x) +#define ANA_AC_SDLB_DLB_CFG_TRAFFIC_TYPE_MASK_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_CFG_TRAFFIC_TYPE_MASK, x) + /* ANA_CL:PORT:FILTER_CTRL */ #define ANA_CL_FILTER_CTRL(g) __REG(TARGET_ANA_CL, 0, 1, 131072, g, 70, 512, 4, 0, 1, 4) @@ -955,6 +1431,82 @@ enum sparx5_target { #define ANA_CL_QOS_MAP_CFG_DSCP_REWR_VAL_GET(x)\ FIELD_GET(ANA_CL_QOS_MAP_CFG_DSCP_REWR_VAL, x) +/* ANA_L2:COMMON:FWD_CFG */ +#define ANA_L2_FWD_CFG \ + __REG(TARGET_ANA_L2, 0, 1, 566024, 0, 1, 700, 0, 0, 1, 4) + +#define ANA_L2_FWD_CFG_MAC_TBL_SPLIT_SEL GENMASK(21, 20) +#define ANA_L2_FWD_CFG_MAC_TBL_SPLIT_SEL_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_MAC_TBL_SPLIT_SEL, x) +#define ANA_L2_FWD_CFG_MAC_TBL_SPLIT_SEL_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_MAC_TBL_SPLIT_SEL, x) + +#define ANA_L2_FWD_CFG_PORT_DEFAULT_BDLB_ENA BIT(18) +#define ANA_L2_FWD_CFG_PORT_DEFAULT_BDLB_ENA_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_PORT_DEFAULT_BDLB_ENA, x) +#define ANA_L2_FWD_CFG_PORT_DEFAULT_BDLB_ENA_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_PORT_DEFAULT_BDLB_ENA, x) + +#define ANA_L2_FWD_CFG_QUEUE_DEFAULT_SDLB_ENA BIT(17) +#define ANA_L2_FWD_CFG_QUEUE_DEFAULT_SDLB_ENA_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_QUEUE_DEFAULT_SDLB_ENA, x) +#define ANA_L2_FWD_CFG_QUEUE_DEFAULT_SDLB_ENA_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_QUEUE_DEFAULT_SDLB_ENA, x) + +#define ANA_L2_FWD_CFG_ISDX_LOOKUP_ENA BIT(16) +#define ANA_L2_FWD_CFG_ISDX_LOOKUP_ENA_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_ISDX_LOOKUP_ENA, x) +#define ANA_L2_FWD_CFG_ISDX_LOOKUP_ENA_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_ISDX_LOOKUP_ENA, x) + +#define ANA_L2_FWD_CFG_CPU_DMAC_QU GENMASK(10, 8) +#define ANA_L2_FWD_CFG_CPU_DMAC_QU_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_CPU_DMAC_QU, x) +#define ANA_L2_FWD_CFG_CPU_DMAC_QU_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_CPU_DMAC_QU, x) + +#define ANA_L2_FWD_CFG_LOOPBACK_ENA BIT(7) +#define ANA_L2_FWD_CFG_LOOPBACK_ENA_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_LOOPBACK_ENA, x) +#define ANA_L2_FWD_CFG_LOOPBACK_ENA_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_LOOPBACK_ENA, x) + +#define ANA_L2_FWD_CFG_CPU_DMAC_COPY_ENA BIT(6) +#define ANA_L2_FWD_CFG_CPU_DMAC_COPY_ENA_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_CPU_DMAC_COPY_ENA, x) +#define ANA_L2_FWD_CFG_CPU_DMAC_COPY_ENA_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_CPU_DMAC_COPY_ENA, x) + +#define ANA_L2_FWD_CFG_FILTER_MODE_SEL BIT(4) +#define ANA_L2_FWD_CFG_FILTER_MODE_SEL_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_FILTER_MODE_SEL, x) +#define ANA_L2_FWD_CFG_FILTER_MODE_SEL_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_FILTER_MODE_SEL, x) + +#define ANA_L2_FWD_CFG_FLOOD_MIRROR_ENA BIT(3) +#define ANA_L2_FWD_CFG_FLOOD_MIRROR_ENA_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_FLOOD_MIRROR_ENA, x) +#define ANA_L2_FWD_CFG_FLOOD_MIRROR_ENA_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_FLOOD_MIRROR_ENA, x) + +#define ANA_L2_FWD_CFG_FLOOD_IGNORE_VLAN_ENA BIT(2) +#define ANA_L2_FWD_CFG_FLOOD_IGNORE_VLAN_ENA_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_FLOOD_IGNORE_VLAN_ENA, x) +#define ANA_L2_FWD_CFG_FLOOD_IGNORE_VLAN_ENA_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_FLOOD_IGNORE_VLAN_ENA, x) + +#define ANA_L2_FWD_CFG_FLOOD_CPU_COPY_ENA BIT(1) +#define ANA_L2_FWD_CFG_FLOOD_CPU_COPY_ENA_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_FLOOD_CPU_COPY_ENA, x) +#define ANA_L2_FWD_CFG_FLOOD_CPU_COPY_ENA_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_FLOOD_CPU_COPY_ENA, x) + +#define ANA_L2_FWD_CFG_FWD_ENA BIT(0) +#define ANA_L2_FWD_CFG_FWD_ENA_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_FWD_ENA, x) +#define ANA_L2_FWD_CFG_FWD_ENA_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_FWD_ENA, x) + /* ANA_L2:COMMON:AUTO_LRN_CFG */ #define ANA_L2_AUTO_LRN_CFG __REG(TARGET_ANA_L2, 0, 1, 566024, 0, 1, 700, 24, 0, 1, 4) @@ -979,6 +1531,26 @@ enum sparx5_target { #define ANA_L2_OWN_UPSID_OWN_UPSID_GET(x)\ FIELD_GET(ANA_L2_OWN_UPSID_OWN_UPSID, x) +/* ANA_L2:ISDX:DLB_CFG */ +#define ANA_L2_DLB_CFG(g) \ + __REG(TARGET_ANA_L2, 0, 1, 0, g, 4096, 128, 56, 0, 1, 4) + +#define ANA_L2_DLB_CFG_DLB_IDX GENMASK(12, 0) +#define ANA_L2_DLB_CFG_DLB_IDX_SET(x)\ + FIELD_PREP(ANA_L2_DLB_CFG_DLB_IDX, x) +#define ANA_L2_DLB_CFG_DLB_IDX_GET(x)\ + FIELD_GET(ANA_L2_DLB_CFG_DLB_IDX, x) + +/* ANA_L2:ISDX:TSN_CFG */ +#define ANA_L2_TSN_CFG(g) \ + __REG(TARGET_ANA_L2, 0, 1, 0, g, 4096, 128, 100, 0, 1, 4) + +#define ANA_L2_TSN_CFG_TSN_SFID GENMASK(9, 0) +#define ANA_L2_TSN_CFG_TSN_SFID_SET(x)\ + FIELD_PREP(ANA_L2_TSN_CFG_TSN_SFID, x) +#define ANA_L2_TSN_CFG_TSN_SFID_GET(x)\ + FIELD_GET(ANA_L2_TSN_CFG_TSN_SFID, x) + /* ANA_L3:COMMON:VLAN_CTRL */ #define ANA_L3_VLAN_CTRL __REG(TARGET_ANA_L3, 0, 1, 493632, 0, 1, 184, 4, 0, 1, 4) @@ -3120,6 +3692,36 @@ enum sparx5_target { #define DSM_TAXI_CAL_CFG_CAL_PGM_ENA_GET(x)\ FIELD_GET(DSM_TAXI_CAL_CFG_CAL_PGM_ENA, x) +/* EACL:ES2_KEY_SELECT_PROFILE:VCAP_ES2_KEY_SEL */ +#define EACL_VCAP_ES2_KEY_SEL(g, r) __REG(TARGET_EACL, 0, 1, 149504, g, 138, 8, 0, r, 2, 4) + +#define EACL_VCAP_ES2_KEY_SEL_IP6_KEY_SEL GENMASK(7, 5) +#define EACL_VCAP_ES2_KEY_SEL_IP6_KEY_SEL_SET(x)\ + FIELD_PREP(EACL_VCAP_ES2_KEY_SEL_IP6_KEY_SEL, x) +#define EACL_VCAP_ES2_KEY_SEL_IP6_KEY_SEL_GET(x)\ + FIELD_GET(EACL_VCAP_ES2_KEY_SEL_IP6_KEY_SEL, x) + +#define EACL_VCAP_ES2_KEY_SEL_IP4_KEY_SEL GENMASK(4, 2) +#define EACL_VCAP_ES2_KEY_SEL_IP4_KEY_SEL_SET(x)\ + FIELD_PREP(EACL_VCAP_ES2_KEY_SEL_IP4_KEY_SEL, x) +#define EACL_VCAP_ES2_KEY_SEL_IP4_KEY_SEL_GET(x)\ + FIELD_GET(EACL_VCAP_ES2_KEY_SEL_IP4_KEY_SEL, x) + +#define EACL_VCAP_ES2_KEY_SEL_ARP_KEY_SEL BIT(1) +#define EACL_VCAP_ES2_KEY_SEL_ARP_KEY_SEL_SET(x)\ + FIELD_PREP(EACL_VCAP_ES2_KEY_SEL_ARP_KEY_SEL, x) +#define EACL_VCAP_ES2_KEY_SEL_ARP_KEY_SEL_GET(x)\ + FIELD_GET(EACL_VCAP_ES2_KEY_SEL_ARP_KEY_SEL, x) + +#define EACL_VCAP_ES2_KEY_SEL_KEY_ENA BIT(0) +#define EACL_VCAP_ES2_KEY_SEL_KEY_ENA_SET(x)\ + FIELD_PREP(EACL_VCAP_ES2_KEY_SEL_KEY_ENA, x) +#define EACL_VCAP_ES2_KEY_SEL_KEY_ENA_GET(x)\ + FIELD_GET(EACL_VCAP_ES2_KEY_SEL_KEY_ENA, x) + +/* EACL:CNT_TBL:ES2_CNT */ +#define EACL_ES2_CNT(g) __REG(TARGET_EACL, 0, 1, 122880, g, 2048, 4, 0, 0, 1, 4) + /* EACL:POL_CFG:POL_EACL_CFG */ #define EACL_POL_EACL_CFG __REG(TARGET_EACL, 0, 1, 150608, 0, 1, 780, 768, 0, 1, 4) @@ -3159,6 +3761,57 @@ enum sparx5_target { #define EACL_POL_EACL_CFG_EACL_FORCE_INIT_GET(x)\ FIELD_GET(EACL_POL_EACL_CFG_EACL_FORCE_INIT, x) +/* EACL:ES2_STICKY:SEC_LOOKUP_STICKY */ +#define EACL_SEC_LOOKUP_STICKY(r) __REG(TARGET_EACL, 0, 1, 118696, 0, 1, 8, 0, r, 2, 4) + +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP_7TUPLE_STICKY BIT(7) +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP_7TUPLE_STICKY_SET(x)\ + FIELD_PREP(EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP_7TUPLE_STICKY, x) +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP_7TUPLE_STICKY_GET(x)\ + FIELD_GET(EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP_7TUPLE_STICKY, x) + +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_VID_STICKY BIT(6) +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_VID_STICKY_SET(x)\ + FIELD_PREP(EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_VID_STICKY, x) +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_VID_STICKY_GET(x)\ + FIELD_GET(EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_VID_STICKY, x) + +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_STD_STICKY BIT(5) +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_STD_STICKY_SET(x)\ + FIELD_PREP(EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_STD_STICKY, x) +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_STD_STICKY_GET(x)\ + FIELD_GET(EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_STD_STICKY, x) + +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_TCPUDP_STICKY BIT(4) +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_TCPUDP_STICKY_SET(x)\ + FIELD_PREP(EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_TCPUDP_STICKY, x) +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_TCPUDP_STICKY_GET(x)\ + FIELD_GET(EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_TCPUDP_STICKY, x) + +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_VID_STICKY BIT(3) +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_VID_STICKY_SET(x)\ + FIELD_PREP(EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_VID_STICKY, x) +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_VID_STICKY_GET(x)\ + FIELD_GET(EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_VID_STICKY, x) + +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_OTHER_STICKY BIT(2) +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_OTHER_STICKY_SET(x)\ + FIELD_PREP(EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_OTHER_STICKY, x) +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_OTHER_STICKY_GET(x)\ + FIELD_GET(EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_OTHER_STICKY, x) + +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_ARP_STICKY BIT(1) +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_ARP_STICKY_SET(x)\ + FIELD_PREP(EACL_SEC_LOOKUP_STICKY_SEC_TYPE_ARP_STICKY, x) +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_ARP_STICKY_GET(x)\ + FIELD_GET(EACL_SEC_LOOKUP_STICKY_SEC_TYPE_ARP_STICKY, x) + +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_ETYPE_STICKY BIT(0) +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_ETYPE_STICKY_SET(x)\ + FIELD_PREP(EACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_ETYPE_STICKY, x) +#define EACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_ETYPE_STICKY_GET(x)\ + FIELD_GET(EACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_ETYPE_STICKY, x) + /* EACL:RAM_CTRL:RAM_INIT */ #define EACL_RAM_INIT __REG(TARGET_EACL, 0, 1, 118736, 0, 1, 4, 0, 0, 1, 4) @@ -3654,11 +4307,11 @@ enum sparx5_target { /* HSCH:HSCH_MISC:SYS_CLK_PER */ #define HSCH_SYS_CLK_PER __REG(TARGET_HSCH, 0, 1, 163104, 0, 1, 648, 640, 0, 1, 4) -#define HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS GENMASK(7, 0) -#define HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS_SET(x)\ - FIELD_PREP(HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS, x) -#define HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS_GET(x)\ - FIELD_GET(HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS, x) +#define HSCH_SYS_CLK_PER_100PS GENMASK(7, 0) +#define HSCH_SYS_CLK_PER_100PS_SET(x)\ + FIELD_PREP(HSCH_SYS_CLK_PER_100PS, x) +#define HSCH_SYS_CLK_PER_100PS_GET(x)\ + FIELD_GET(HSCH_SYS_CLK_PER_100PS, x) /* HSCH:HSCH_LEAK_LISTS:HSCH_TIMER_CFG */ #define HSCH_HSCH_TIMER_CFG(g, r) __REG(TARGET_HSCH, 0, 1, 161664, g, 4, 32, 0, r, 4, 4) @@ -5612,6 +6265,147 @@ enum sparx5_target { #define REW_RAM_INIT_RAM_CFG_HOOK_GET(x)\ FIELD_GET(REW_RAM_INIT_RAM_CFG_HOOK, x) +/* VCAP_ES2:VCAP_CORE_CFG:VCAP_UPDATE_CTRL */ +#define VCAP_ES2_CTRL __REG(TARGET_VCAP_ES2, 0, 1, 0, 0, 1, 8, 0, 0, 1, 4) + +#define VCAP_ES2_CTRL_UPDATE_CMD GENMASK(24, 22) +#define VCAP_ES2_CTRL_UPDATE_CMD_SET(x)\ + FIELD_PREP(VCAP_ES2_CTRL_UPDATE_CMD, x) +#define VCAP_ES2_CTRL_UPDATE_CMD_GET(x)\ + FIELD_GET(VCAP_ES2_CTRL_UPDATE_CMD, x) + +#define VCAP_ES2_CTRL_UPDATE_ENTRY_DIS BIT(21) +#define VCAP_ES2_CTRL_UPDATE_ENTRY_DIS_SET(x)\ + FIELD_PREP(VCAP_ES2_CTRL_UPDATE_ENTRY_DIS, x) +#define VCAP_ES2_CTRL_UPDATE_ENTRY_DIS_GET(x)\ + FIELD_GET(VCAP_ES2_CTRL_UPDATE_ENTRY_DIS, x) + +#define VCAP_ES2_CTRL_UPDATE_ACTION_DIS BIT(20) +#define VCAP_ES2_CTRL_UPDATE_ACTION_DIS_SET(x)\ + FIELD_PREP(VCAP_ES2_CTRL_UPDATE_ACTION_DIS, x) +#define VCAP_ES2_CTRL_UPDATE_ACTION_DIS_GET(x)\ + FIELD_GET(VCAP_ES2_CTRL_UPDATE_ACTION_DIS, x) + +#define VCAP_ES2_CTRL_UPDATE_CNT_DIS BIT(19) +#define VCAP_ES2_CTRL_UPDATE_CNT_DIS_SET(x)\ + FIELD_PREP(VCAP_ES2_CTRL_UPDATE_CNT_DIS, x) +#define VCAP_ES2_CTRL_UPDATE_CNT_DIS_GET(x)\ + FIELD_GET(VCAP_ES2_CTRL_UPDATE_CNT_DIS, x) + +#define VCAP_ES2_CTRL_UPDATE_ADDR GENMASK(18, 3) +#define VCAP_ES2_CTRL_UPDATE_ADDR_SET(x)\ + FIELD_PREP(VCAP_ES2_CTRL_UPDATE_ADDR, x) +#define VCAP_ES2_CTRL_UPDATE_ADDR_GET(x)\ + FIELD_GET(VCAP_ES2_CTRL_UPDATE_ADDR, x) + +#define VCAP_ES2_CTRL_UPDATE_SHOT BIT(2) +#define VCAP_ES2_CTRL_UPDATE_SHOT_SET(x)\ + FIELD_PREP(VCAP_ES2_CTRL_UPDATE_SHOT, x) +#define VCAP_ES2_CTRL_UPDATE_SHOT_GET(x)\ + FIELD_GET(VCAP_ES2_CTRL_UPDATE_SHOT, x) + +#define VCAP_ES2_CTRL_CLEAR_CACHE BIT(1) +#define VCAP_ES2_CTRL_CLEAR_CACHE_SET(x)\ + FIELD_PREP(VCAP_ES2_CTRL_CLEAR_CACHE, x) +#define VCAP_ES2_CTRL_CLEAR_CACHE_GET(x)\ + FIELD_GET(VCAP_ES2_CTRL_CLEAR_CACHE, x) + +#define VCAP_ES2_CTRL_MV_TRAFFIC_IGN BIT(0) +#define VCAP_ES2_CTRL_MV_TRAFFIC_IGN_SET(x)\ + FIELD_PREP(VCAP_ES2_CTRL_MV_TRAFFIC_IGN, x) +#define VCAP_ES2_CTRL_MV_TRAFFIC_IGN_GET(x)\ + FIELD_GET(VCAP_ES2_CTRL_MV_TRAFFIC_IGN, x) + +/* VCAP_ES2:VCAP_CORE_CFG:VCAP_MV_CFG */ +#define VCAP_ES2_CFG __REG(TARGET_VCAP_ES2, 0, 1, 0, 0, 1, 8, 4, 0, 1, 4) + +#define VCAP_ES2_CFG_MV_NUM_POS GENMASK(31, 16) +#define VCAP_ES2_CFG_MV_NUM_POS_SET(x)\ + FIELD_PREP(VCAP_ES2_CFG_MV_NUM_POS, x) +#define VCAP_ES2_CFG_MV_NUM_POS_GET(x)\ + FIELD_GET(VCAP_ES2_CFG_MV_NUM_POS, x) + +#define VCAP_ES2_CFG_MV_SIZE GENMASK(15, 0) +#define VCAP_ES2_CFG_MV_SIZE_SET(x)\ + FIELD_PREP(VCAP_ES2_CFG_MV_SIZE, x) +#define VCAP_ES2_CFG_MV_SIZE_GET(x)\ + FIELD_GET(VCAP_ES2_CFG_MV_SIZE, x) + +/* VCAP_ES2:VCAP_CORE_CACHE:VCAP_ENTRY_DAT */ +#define VCAP_ES2_VCAP_ENTRY_DAT(r) __REG(TARGET_VCAP_ES2, 0, 1, 8, 0, 1, 904, 0, r, 64, 4) + +/* VCAP_ES2:VCAP_CORE_CACHE:VCAP_MASK_DAT */ +#define VCAP_ES2_VCAP_MASK_DAT(r) __REG(TARGET_VCAP_ES2, 0, 1, 8, 0, 1, 904, 256, r, 64, 4) + +/* VCAP_ES2:VCAP_CORE_CACHE:VCAP_ACTION_DAT */ +#define VCAP_ES2_VCAP_ACTION_DAT(r) __REG(TARGET_VCAP_ES2, 0, 1, 8, 0, 1, 904, 512, r, 64, 4) + +/* VCAP_ES2:VCAP_CORE_CACHE:VCAP_CNT_DAT */ +#define VCAP_ES2_VCAP_CNT_DAT(r) __REG(TARGET_VCAP_ES2, 0, 1, 8, 0, 1, 904, 768, r, 32, 4) + +/* VCAP_ES2:VCAP_CORE_CACHE:VCAP_CNT_FW_DAT */ +#define VCAP_ES2_VCAP_CNT_FW_DAT __REG(TARGET_VCAP_ES2, 0, 1, 8, 0, 1, 904, 896, 0, 1, 4) + +/* VCAP_ES2:VCAP_CORE_CACHE:VCAP_TG_DAT */ +#define VCAP_ES2_VCAP_TG_DAT __REG(TARGET_VCAP_ES2, 0, 1, 8, 0, 1, 904, 900, 0, 1, 4) + +/* VCAP_ES2:VCAP_CORE_MAP:VCAP_CORE_IDX */ +#define VCAP_ES2_IDX __REG(TARGET_VCAP_ES2, 0, 1, 912, 0, 1, 8, 0, 0, 1, 4) + +#define VCAP_ES2_IDX_CORE_IDX GENMASK(3, 0) +#define VCAP_ES2_IDX_CORE_IDX_SET(x)\ + FIELD_PREP(VCAP_ES2_IDX_CORE_IDX, x) +#define VCAP_ES2_IDX_CORE_IDX_GET(x)\ + FIELD_GET(VCAP_ES2_IDX_CORE_IDX, x) + +/* VCAP_ES2:VCAP_CORE_MAP:VCAP_CORE_MAP */ +#define VCAP_ES2_MAP __REG(TARGET_VCAP_ES2, 0, 1, 912, 0, 1, 8, 4, 0, 1, 4) + +#define VCAP_ES2_MAP_CORE_MAP GENMASK(2, 0) +#define VCAP_ES2_MAP_CORE_MAP_SET(x)\ + FIELD_PREP(VCAP_ES2_MAP_CORE_MAP, x) +#define VCAP_ES2_MAP_CORE_MAP_GET(x)\ + FIELD_GET(VCAP_ES2_MAP_CORE_MAP, x) + +/* VCAP_ES2:VCAP_CORE_STICKY:VCAP_STICKY */ +#define VCAP_ES2_VCAP_STICKY __REG(TARGET_VCAP_ES2, 0, 1, 920, 0, 1, 4, 0, 0, 1, 4) + +#define VCAP_ES2_VCAP_STICKY_VCAP_ROW_DELETED_STICKY BIT(0) +#define VCAP_ES2_VCAP_STICKY_VCAP_ROW_DELETED_STICKY_SET(x)\ + FIELD_PREP(VCAP_ES2_VCAP_STICKY_VCAP_ROW_DELETED_STICKY, x) +#define VCAP_ES2_VCAP_STICKY_VCAP_ROW_DELETED_STICKY_GET(x)\ + FIELD_GET(VCAP_ES2_VCAP_STICKY_VCAP_ROW_DELETED_STICKY, x) + +/* VCAP_ES2:VCAP_CONST:VCAP_VER */ +#define VCAP_ES2_VCAP_VER __REG(TARGET_VCAP_ES2, 0, 1, 924, 0, 1, 40, 0, 0, 1, 4) + +/* VCAP_ES2:VCAP_CONST:ENTRY_WIDTH */ +#define VCAP_ES2_ENTRY_WIDTH __REG(TARGET_VCAP_ES2, 0, 1, 924, 0, 1, 40, 4, 0, 1, 4) + +/* VCAP_ES2:VCAP_CONST:ENTRY_CNT */ +#define VCAP_ES2_ENTRY_CNT __REG(TARGET_VCAP_ES2, 0, 1, 924, 0, 1, 40, 8, 0, 1, 4) + +/* VCAP_ES2:VCAP_CONST:ENTRY_SWCNT */ +#define VCAP_ES2_ENTRY_SWCNT __REG(TARGET_VCAP_ES2, 0, 1, 924, 0, 1, 40, 12, 0, 1, 4) + +/* VCAP_ES2:VCAP_CONST:ENTRY_TG_WIDTH */ +#define VCAP_ES2_ENTRY_TG_WIDTH __REG(TARGET_VCAP_ES2, 0, 1, 924, 0, 1, 40, 16, 0, 1, 4) + +/* VCAP_ES2:VCAP_CONST:ACTION_DEF_CNT */ +#define VCAP_ES2_ACTION_DEF_CNT __REG(TARGET_VCAP_ES2, 0, 1, 924, 0, 1, 40, 20, 0, 1, 4) + +/* VCAP_ES2:VCAP_CONST:ACTION_WIDTH */ +#define VCAP_ES2_ACTION_WIDTH __REG(TARGET_VCAP_ES2, 0, 1, 924, 0, 1, 40, 24, 0, 1, 4) + +/* VCAP_ES2:VCAP_CONST:CNT_WIDTH */ +#define VCAP_ES2_CNT_WIDTH __REG(TARGET_VCAP_ES2, 0, 1, 924, 0, 1, 40, 28, 0, 1, 4) + +/* VCAP_ES2:VCAP_CONST:CORE_CNT */ +#define VCAP_ES2_CORE_CNT __REG(TARGET_VCAP_ES2, 0, 1, 924, 0, 1, 40, 32, 0, 1, 4) + +/* VCAP_ES2:VCAP_CONST:IF_CNT */ +#define VCAP_ES2_IF_CNT __REG(TARGET_VCAP_ES2, 0, 1, 924, 0, 1, 40, 36, 0, 1, 4) + /* VCAP_SUPER:VCAP_CORE_CFG:VCAP_UPDATE_CTRL */ #define VCAP_SUPER_CTRL __REG(TARGET_VCAP_SUPER, 0, 1, 0, 0, 1, 8, 0, 0, 1, 4) diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_police.c b/drivers/net/ethernet/microchip/sparx5/sparx5_police.c new file mode 100644 index 000000000000..8ada5cee1342 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_police.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2023 Microchip Technology Inc. and its subsidiaries. + */ + +#include "sparx5_main_regs.h" +#include "sparx5_main.h" + +static int sparx5_policer_service_conf_set(struct sparx5 *sparx5, + struct sparx5_policer *pol) +{ + u32 idx, pup_tokens, max_pup_tokens, burst, thres; + struct sparx5_sdlb_group *g; + u64 rate; + + g = &sdlb_groups[pol->group]; + idx = pol->idx; + + rate = pol->rate * 1000; + burst = pol->burst; + + pup_tokens = sparx5_sdlb_pup_token_get(sparx5, g->pup_interval, rate); + max_pup_tokens = + sparx5_sdlb_pup_token_get(sparx5, g->pup_interval, g->max_rate); + + thres = DIV_ROUND_UP(burst, g->min_burst); + + spx5_wr(ANA_AC_SDLB_PUP_TOKENS_PUP_TOKENS_SET(pup_tokens), sparx5, + ANA_AC_SDLB_PUP_TOKENS(idx, 0)); + + spx5_rmw(ANA_AC_SDLB_INH_CTRL_PUP_TOKENS_MAX_SET(max_pup_tokens), + ANA_AC_SDLB_INH_CTRL_PUP_TOKENS_MAX, sparx5, + ANA_AC_SDLB_INH_CTRL(idx, 0)); + + spx5_rmw(ANA_AC_SDLB_THRES_THRES_SET(thres), ANA_AC_SDLB_THRES_THRES, + sparx5, ANA_AC_SDLB_THRES(idx, 0)); + + return 0; +} + +int sparx5_policer_conf_set(struct sparx5 *sparx5, struct sparx5_policer *pol) +{ + /* More policer types will be added later */ + switch (pol->type) { + case SPX5_POL_SERVICE: + return sparx5_policer_service_conf_set(sparx5, pol); + default: + break; + } + + return 0; +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_pool.c b/drivers/net/ethernet/microchip/sparx5/sparx5_pool.c new file mode 100644 index 000000000000..b4b280c6138b --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_pool.c @@ -0,0 +1,81 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2023 Microchip Technology Inc. and its subsidiaries. + */ + +#include "sparx5_main_regs.h" +#include "sparx5_main.h" + +static u32 sparx5_pool_id_to_idx(u32 id) +{ + return --id; +} + +u32 sparx5_pool_idx_to_id(u32 idx) +{ + return ++idx; +} + +/* Release resource from pool. + * Return reference count on success, otherwise return error. + */ +int sparx5_pool_put(struct sparx5_pool_entry *pool, int size, u32 id) +{ + struct sparx5_pool_entry *e_itr; + + e_itr = (pool + sparx5_pool_id_to_idx(id)); + if (e_itr->ref_cnt == 0) + return -EINVAL; + + return --e_itr->ref_cnt; +} + +/* Get resource from pool. + * Return reference count on success, otherwise return error. + */ +int sparx5_pool_get(struct sparx5_pool_entry *pool, int size, u32 *id) +{ + struct sparx5_pool_entry *e_itr; + int i; + + for (i = 0, e_itr = pool; i < size; i++, e_itr++) { + if (e_itr->ref_cnt == 0) { + *id = sparx5_pool_idx_to_id(i); + return ++e_itr->ref_cnt; + } + } + + return -ENOSPC; +} + +/* Get resource from pool that matches index. + * Return reference count on success, otherwise return error. + */ +int sparx5_pool_get_with_idx(struct sparx5_pool_entry *pool, int size, u32 idx, + u32 *id) +{ + struct sparx5_pool_entry *e_itr; + int i, ret = -ENOSPC; + + for (i = 0, e_itr = pool; i < size; i++, e_itr++) { + /* Pool index of first free entry */ + if (e_itr->ref_cnt == 0 && ret == -ENOSPC) + ret = i; + /* Tc index already in use ? */ + if (e_itr->idx == idx && e_itr->ref_cnt > 0) { + ret = i; + break; + } + } + + /* Did we find a free entry? */ + if (ret >= 0) { + *id = sparx5_pool_idx_to_id(ret); + e_itr = (pool + ret); + e_itr->idx = idx; + return ++e_itr->ref_cnt; + } + + return ret; +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_psfp.c b/drivers/net/ethernet/microchip/sparx5/sparx5_psfp.c new file mode 100644 index 000000000000..8dee1ab1fa75 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_psfp.c @@ -0,0 +1,332 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2023 Microchip Technology Inc. and its subsidiaries. + */ + +#include "sparx5_main_regs.h" +#include "sparx5_main.h" + +#define SPX5_PSFP_SF_CNT 1024 +#define SPX5_PSFP_SG_CONFIG_CHANGE_SLEEP 1000 +#define SPX5_PSFP_SG_CONFIG_CHANGE_TIMEO 100000 + +/* Pool of available service policers */ +static struct sparx5_pool_entry sparx5_psfp_fm_pool[SPX5_SDLB_CNT]; + +/* Pool of available stream gates */ +static struct sparx5_pool_entry sparx5_psfp_sg_pool[SPX5_PSFP_SG_CNT]; + +/* Pool of available stream filters */ +static struct sparx5_pool_entry sparx5_psfp_sf_pool[SPX5_PSFP_SF_CNT]; + +static int sparx5_psfp_sf_get(u32 *id) +{ + return sparx5_pool_get(sparx5_psfp_sf_pool, SPX5_PSFP_SF_CNT, id); +} + +static int sparx5_psfp_sf_put(u32 id) +{ + return sparx5_pool_put(sparx5_psfp_sf_pool, SPX5_PSFP_SF_CNT, id); +} + +static int sparx5_psfp_sg_get(u32 idx, u32 *id) +{ + return sparx5_pool_get_with_idx(sparx5_psfp_sg_pool, SPX5_PSFP_SG_CNT, + idx, id); +} + +static int sparx5_psfp_sg_put(u32 id) +{ + return sparx5_pool_put(sparx5_psfp_sg_pool, SPX5_PSFP_SG_CNT, id); +} + +static int sparx5_psfp_fm_get(u32 idx, u32 *id) +{ + return sparx5_pool_get_with_idx(sparx5_psfp_fm_pool, SPX5_SDLB_CNT, idx, + id); +} + +static int sparx5_psfp_fm_put(u32 id) +{ + return sparx5_pool_put(sparx5_psfp_fm_pool, SPX5_SDLB_CNT, id); +} + +u32 sparx5_psfp_isdx_get_sf(struct sparx5 *sparx5, u32 isdx) +{ + return ANA_L2_TSN_CFG_TSN_SFID_GET(spx5_rd(sparx5, + ANA_L2_TSN_CFG(isdx))); +} + +u32 sparx5_psfp_isdx_get_fm(struct sparx5 *sparx5, u32 isdx) +{ + return ANA_L2_DLB_CFG_DLB_IDX_GET(spx5_rd(sparx5, + ANA_L2_DLB_CFG(isdx))); +} + +u32 sparx5_psfp_sf_get_sg(struct sparx5 *sparx5, u32 sfid) +{ + return ANA_AC_TSN_SF_CFG_TSN_SGID_GET(spx5_rd(sparx5, + ANA_AC_TSN_SF_CFG(sfid))); +} + +void sparx5_isdx_conf_set(struct sparx5 *sparx5, u32 isdx, u32 sfid, u32 fmid) +{ + spx5_rmw(ANA_L2_TSN_CFG_TSN_SFID_SET(sfid), ANA_L2_TSN_CFG_TSN_SFID, + sparx5, ANA_L2_TSN_CFG(isdx)); + + spx5_rmw(ANA_L2_DLB_CFG_DLB_IDX_SET(fmid), ANA_L2_DLB_CFG_DLB_IDX, + sparx5, ANA_L2_DLB_CFG(isdx)); +} + +/* Internal priority value to internal priority selector */ +static u32 sparx5_psfp_ipv_to_ips(s32 ipv) +{ + return ipv > 0 ? (ipv | BIT(3)) : 0; +} + +static int sparx5_psfp_sgid_get_status(struct sparx5 *sparx5) +{ + return spx5_rd(sparx5, ANA_AC_SG_ACCESS_CTRL); +} + +static int sparx5_psfp_sgid_wait_for_completion(struct sparx5 *sparx5) +{ + u32 val; + + return readx_poll_timeout(sparx5_psfp_sgid_get_status, sparx5, val, + !ANA_AC_SG_ACCESS_CTRL_CONFIG_CHANGE_GET(val), + SPX5_PSFP_SG_CONFIG_CHANGE_SLEEP, + SPX5_PSFP_SG_CONFIG_CHANGE_TIMEO); +} + +static void sparx5_psfp_sg_config_change(struct sparx5 *sparx5, u32 id) +{ + spx5_wr(ANA_AC_SG_ACCESS_CTRL_SGID_SET(id), sparx5, + ANA_AC_SG_ACCESS_CTRL); + + spx5_wr(ANA_AC_SG_ACCESS_CTRL_CONFIG_CHANGE_SET(1) | + ANA_AC_SG_ACCESS_CTRL_SGID_SET(id), + sparx5, ANA_AC_SG_ACCESS_CTRL); + + if (sparx5_psfp_sgid_wait_for_completion(sparx5) < 0) + pr_debug("%s:%d timed out waiting for sgid completion", + __func__, __LINE__); +} + +static void sparx5_psfp_sf_set(struct sparx5 *sparx5, u32 id, + const struct sparx5_psfp_sf *sf) +{ + /* Configure stream gate*/ + spx5_rmw(ANA_AC_TSN_SF_CFG_TSN_SGID_SET(sf->sgid) | + ANA_AC_TSN_SF_CFG_TSN_MAX_SDU_SET(sf->max_sdu) | + ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_STATE_SET(sf->sblock_osize) | + ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_ENA_SET(sf->sblock_osize_ena), + ANA_AC_TSN_SF_CFG_TSN_SGID | ANA_AC_TSN_SF_CFG_TSN_MAX_SDU | + ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_STATE | + ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_ENA, + sparx5, ANA_AC_TSN_SF_CFG(id)); +} + +static int sparx5_psfp_sg_set(struct sparx5 *sparx5, u32 id, + const struct sparx5_psfp_sg *sg) +{ + u32 ips, base_lsb, base_msb, accum_time_interval = 0; + const struct sparx5_psfp_gce *gce; + int i; + + ips = sparx5_psfp_ipv_to_ips(sg->ipv); + base_lsb = sg->basetime.tv_sec & 0xffffffff; + base_msb = sg->basetime.tv_sec >> 32; + + /* Set stream gate id */ + spx5_wr(ANA_AC_SG_ACCESS_CTRL_SGID_SET(id), sparx5, + ANA_AC_SG_ACCESS_CTRL); + + /* Write AdminPSFP values */ + spx5_wr(sg->basetime.tv_nsec, sparx5, ANA_AC_SG_CONFIG_REG_1); + spx5_wr(base_lsb, sparx5, ANA_AC_SG_CONFIG_REG_2); + + spx5_rmw(ANA_AC_SG_CONFIG_REG_3_BASE_TIME_SEC_MSB_SET(base_msb) | + ANA_AC_SG_CONFIG_REG_3_INIT_IPS_SET(ips) | + ANA_AC_SG_CONFIG_REG_3_LIST_LENGTH_SET(sg->num_entries) | + ANA_AC_SG_CONFIG_REG_3_INIT_GATE_STATE_SET(sg->gate_state) | + ANA_AC_SG_CONFIG_REG_3_GATE_ENABLE_SET(1), + ANA_AC_SG_CONFIG_REG_3_BASE_TIME_SEC_MSB | + ANA_AC_SG_CONFIG_REG_3_INIT_IPS | + ANA_AC_SG_CONFIG_REG_3_LIST_LENGTH | + ANA_AC_SG_CONFIG_REG_3_INIT_GATE_STATE | + ANA_AC_SG_CONFIG_REG_3_GATE_ENABLE, + sparx5, ANA_AC_SG_CONFIG_REG_3); + + spx5_wr(sg->cycletime, sparx5, ANA_AC_SG_CONFIG_REG_4); + spx5_wr(sg->cycletimeext, sparx5, ANA_AC_SG_CONFIG_REG_5); + + /* For each scheduling entry */ + for (i = 0; i < sg->num_entries; i++) { + gce = &sg->gce[i]; + ips = sparx5_psfp_ipv_to_ips(gce->ipv); + /* hardware needs TimeInterval to be cumulative */ + accum_time_interval += gce->interval; + /* Set gate state */ + spx5_wr(ANA_AC_SG_GCL_GS_CONFIG_IPS_SET(ips) | + ANA_AC_SG_GCL_GS_CONFIG_GATE_STATE_SET(gce->gate_state), + sparx5, ANA_AC_SG_GCL_GS_CONFIG(i)); + + /* Set time interval */ + spx5_wr(accum_time_interval, sparx5, + ANA_AC_SG_GCL_TI_CONFIG(i)); + + /* Set maximum octets */ + spx5_wr(gce->maxoctets, sparx5, ANA_AC_SG_GCL_OCT_CONFIG(i)); + } + + return 0; +} + +static int sparx5_sdlb_conf_set(struct sparx5 *sparx5, + struct sparx5_psfp_fm *fm) +{ + int (*sparx5_sdlb_group_action)(struct sparx5 *sparx5, u32 group, + u32 idx); + + if (!fm->pol.rate && !fm->pol.burst) + sparx5_sdlb_group_action = &sparx5_sdlb_group_del; + else + sparx5_sdlb_group_action = &sparx5_sdlb_group_add; + + sparx5_policer_conf_set(sparx5, &fm->pol); + + return sparx5_sdlb_group_action(sparx5, fm->pol.group, fm->pol.idx); +} + +int sparx5_psfp_sf_add(struct sparx5 *sparx5, const struct sparx5_psfp_sf *sf, + u32 *id) +{ + int ret; + + ret = sparx5_psfp_sf_get(id); + if (ret < 0) + return ret; + + sparx5_psfp_sf_set(sparx5, *id, sf); + + return 0; +} + +int sparx5_psfp_sf_del(struct sparx5 *sparx5, u32 id) +{ + const struct sparx5_psfp_sf sf = { 0 }; + + sparx5_psfp_sf_set(sparx5, id, &sf); + + return sparx5_psfp_sf_put(id); +} + +int sparx5_psfp_sg_add(struct sparx5 *sparx5, u32 uidx, + struct sparx5_psfp_sg *sg, u32 *id) +{ + ktime_t basetime; + int ret; + + ret = sparx5_psfp_sg_get(uidx, id); + if (ret < 0) + return ret; + /* Was already in use, no need to reconfigure */ + if (ret > 1) + return 0; + + /* Calculate basetime for this stream gate */ + sparx5_new_base_time(sparx5, sg->cycletime, 0, &basetime); + sg->basetime = ktime_to_timespec64(basetime); + + sparx5_psfp_sg_set(sparx5, *id, sg); + + /* Signal hardware to copy AdminPSFP values into OperPSFP values */ + sparx5_psfp_sg_config_change(sparx5, *id); + + return 0; +} + +int sparx5_psfp_sg_del(struct sparx5 *sparx5, u32 id) +{ + const struct sparx5_psfp_sg sg = { 0 }; + int ret; + + ret = sparx5_psfp_sg_put(id); + if (ret < 0) + return ret; + /* Stream gate still in use ? */ + if (ret > 0) + return 0; + + return sparx5_psfp_sg_set(sparx5, id, &sg); +} + +int sparx5_psfp_fm_add(struct sparx5 *sparx5, u32 uidx, + struct sparx5_psfp_fm *fm, u32 *id) +{ + struct sparx5_policer *pol = &fm->pol; + int ret; + + /* Get flow meter */ + ret = sparx5_psfp_fm_get(uidx, &fm->pol.idx); + if (ret < 0) + return ret; + /* Was already in use, no need to reconfigure */ + if (ret > 1) + return 0; + + ret = sparx5_sdlb_group_get_by_rate(sparx5, pol->rate, pol->burst); + if (ret < 0) + return ret; + + fm->pol.group = ret; + + ret = sparx5_sdlb_conf_set(sparx5, fm); + if (ret < 0) + return ret; + + *id = fm->pol.idx; + + return 0; +} + +int sparx5_psfp_fm_del(struct sparx5 *sparx5, u32 id) +{ + struct sparx5_psfp_fm fm = { .pol.idx = id, + .pol.type = SPX5_POL_SERVICE }; + int ret; + + /* Find the group that this lb belongs to */ + ret = sparx5_sdlb_group_get_by_index(sparx5, id, &fm.pol.group); + if (ret < 0) + return ret; + + ret = sparx5_psfp_fm_put(id); + if (ret < 0) + return ret; + /* Do not reset flow-meter if still in use. */ + if (ret > 0) + return 0; + + return sparx5_sdlb_conf_set(sparx5, &fm); +} + +void sparx5_psfp_init(struct sparx5 *sparx5) +{ + const struct sparx5_sdlb_group *group; + int i; + + for (i = 0; i < SPX5_SDLB_GROUP_CNT; i++) { + group = &sdlb_groups[i]; + sparx5_sdlb_group_init(sparx5, group->max_rate, + group->min_burst, group->frame_size, i); + } + + spx5_wr(ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_UPDATE_ENA_SET(1), + sparx5, ANA_AC_SG_CYCLETIME_UPDATE_PERIOD); + + spx5_rmw(ANA_L2_FWD_CFG_ISDX_LOOKUP_ENA_SET(1), + ANA_L2_FWD_CFG_ISDX_LOOKUP_ENA, sparx5, ANA_L2_FWD_CFG); +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c b/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c index 0ed1ea7727c5..0edb98cef7e4 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c @@ -476,8 +476,7 @@ static int sparx5_ptp_settime64(struct ptp_clock_info *ptp, return 0; } -static int sparx5_ptp_gettime64(struct ptp_clock_info *ptp, - struct timespec64 *ts) +int sparx5_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts) { struct sparx5_phc *phc = container_of(ptp, struct sparx5_phc, info); struct sparx5 *sparx5 = phc->sparx5; @@ -633,7 +632,7 @@ int sparx5_ptp_init(struct sparx5 *sparx5) /* Enable master counters */ spx5_wr(PTP_PTP_DOM_CFG_PTP_ENA_SET(0x7), sparx5, PTP_PTP_DOM_CFG); - for (i = 0; i < sparx5->port_count; i++) { + for (i = 0; i < SPX5_PORTS; i++) { port = sparx5->ports[i]; if (!port) continue; @@ -649,7 +648,7 @@ void sparx5_ptp_deinit(struct sparx5 *sparx5) struct sparx5_port *port; int i; - for (i = 0; i < sparx5->port_count; i++) { + for (i = 0; i < SPX5_PORTS; i++) { port = sparx5->ports[i]; if (!port) continue; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_qos.c b/drivers/net/ethernet/microchip/sparx5/sparx5_qos.c index 379e540e5e6a..5f34febaee6b 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_qos.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_qos.c @@ -9,6 +9,63 @@ #include "sparx5_main.h" #include "sparx5_qos.h" +/* Calculate new base_time based on cycle_time. + * + * The hardware requires a base_time that is always in the future. + * We define threshold_time as current_time + (2 * cycle_time). + * If base_time is below threshold_time this function recalculates it to be in + * the interval: + * threshold_time <= base_time < (threshold_time + cycle_time) + * + * A very simple algorithm could be like this: + * new_base_time = org_base_time + N * cycle_time + * using the lowest N so (new_base_time >= threshold_time + */ +void sparx5_new_base_time(struct sparx5 *sparx5, const u32 cycle_time, + const ktime_t org_base_time, ktime_t *new_base_time) +{ + ktime_t current_time, threshold_time, new_time; + struct timespec64 ts; + u64 nr_of_cycles_p2; + u64 nr_of_cycles; + u64 diff_time; + + new_time = org_base_time; + + sparx5_ptp_gettime64(&sparx5->phc[SPARX5_PHC_PORT].info, &ts); + current_time = timespec64_to_ktime(ts); + threshold_time = current_time + (2 * cycle_time); + diff_time = threshold_time - new_time; + nr_of_cycles = div_u64(diff_time, cycle_time); + nr_of_cycles_p2 = 1; /* Use 2^0 as start value */ + + if (new_time >= threshold_time) { + *new_base_time = new_time; + return; + } + + /* Calculate the smallest power of 2 (nr_of_cycles_p2) + * that is larger than nr_of_cycles. + */ + while (nr_of_cycles_p2 < nr_of_cycles) + nr_of_cycles_p2 <<= 1; /* Next (higher) power of 2 */ + + /* Add as big chunks (power of 2 * cycle_time) + * as possible for each power of 2 + */ + while (nr_of_cycles_p2) { + if (new_time < threshold_time) { + new_time += cycle_time * nr_of_cycles_p2; + while (new_time < threshold_time) + new_time += cycle_time * nr_of_cycles_p2; + new_time -= cycle_time * nr_of_cycles_p2; + } + nr_of_cycles_p2 >>= 1; /* Next (lower) power of 2 */ + } + new_time += cycle_time; + *new_base_time = new_time; +} + /* Max rates for leak groups */ static const u32 spx5_hsch_max_group_rate[SPX5_HSCH_LEAK_GRP_CNT] = { 1048568, /* 1.049 Gbps */ @@ -393,6 +450,8 @@ int sparx5_qos_init(struct sparx5 *sparx5) if (ret < 0) return ret; + sparx5_psfp_init(sparx5); + return 0; } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_sdlb.c b/drivers/net/ethernet/microchip/sparx5/sparx5_sdlb.c new file mode 100644 index 000000000000..f5267218caeb --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_sdlb.c @@ -0,0 +1,335 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2023 Microchip Technology Inc. and its subsidiaries. + */ + +#include "sparx5_main_regs.h" +#include "sparx5_main.h" + +struct sparx5_sdlb_group sdlb_groups[SPX5_SDLB_GROUP_CNT] = { + { SPX5_SDLB_GROUP_RATE_MAX, 8192 / 1, 64 }, /* 25 G */ + { 15000000000ULL, 8192 / 1, 64 }, /* 15 G */ + { 10000000000ULL, 8192 / 1, 64 }, /* 10 G */ + { 5000000000ULL, 8192 / 1, 64 }, /* 5 G */ + { 2500000000ULL, 8192 / 1, 64 }, /* 2.5 G */ + { 1000000000ULL, 8192 / 2, 64 }, /* 1 G */ + { 500000000ULL, 8192 / 2, 64 }, /* 500 M */ + { 100000000ULL, 8192 / 4, 64 }, /* 100 M */ + { 50000000ULL, 8192 / 4, 64 }, /* 50 M */ + { 5000000ULL, 8192 / 8, 64 } /* 5 M */ +}; + +int sparx5_sdlb_clk_hz_get(struct sparx5 *sparx5) +{ + u32 clk_per_100ps; + u64 clk_hz; + + clk_per_100ps = HSCH_SYS_CLK_PER_100PS_GET(spx5_rd(sparx5, + HSCH_SYS_CLK_PER)); + if (!clk_per_100ps) + clk_per_100ps = SPX5_CLK_PER_100PS_DEFAULT; + + clk_hz = (10 * 1000 * 1000) / clk_per_100ps; + return clk_hz *= 1000; +} + +static int sparx5_sdlb_pup_interval_get(struct sparx5 *sparx5, u32 max_token, + u64 max_rate) +{ + u64 clk_hz; + + clk_hz = sparx5_sdlb_clk_hz_get(sparx5); + + return div64_u64((8 * clk_hz * max_token), max_rate); +} + +int sparx5_sdlb_pup_token_get(struct sparx5 *sparx5, u32 pup_interval, u64 rate) +{ + u64 clk_hz; + + if (!rate) + return SPX5_SDLB_PUP_TOKEN_DISABLE; + + clk_hz = sparx5_sdlb_clk_hz_get(sparx5); + + return DIV64_U64_ROUND_UP((rate * pup_interval), (clk_hz * 8)); +} + +static void sparx5_sdlb_group_disable(struct sparx5 *sparx5, u32 group) +{ + spx5_rmw(ANA_AC_SDLB_PUP_CTRL_PUP_ENA_SET(0), + ANA_AC_SDLB_PUP_CTRL_PUP_ENA, sparx5, + ANA_AC_SDLB_PUP_CTRL(group)); +} + +static void sparx5_sdlb_group_enable(struct sparx5 *sparx5, u32 group) +{ + spx5_rmw(ANA_AC_SDLB_PUP_CTRL_PUP_ENA_SET(1), + ANA_AC_SDLB_PUP_CTRL_PUP_ENA, sparx5, + ANA_AC_SDLB_PUP_CTRL(group)); +} + +static u32 sparx5_sdlb_group_get_first(struct sparx5 *sparx5, u32 group) +{ + u32 val; + + val = spx5_rd(sparx5, ANA_AC_SDLB_XLB_START(group)); + + return ANA_AC_SDLB_XLB_START_LBSET_START_GET(val); +} + +static u32 sparx5_sdlb_group_get_next(struct sparx5 *sparx5, u32 group, + u32 lb) +{ + u32 val; + + val = spx5_rd(sparx5, ANA_AC_SDLB_XLB_NEXT(lb)); + + return ANA_AC_SDLB_XLB_NEXT_LBSET_NEXT_GET(val); +} + +static bool sparx5_sdlb_group_is_first(struct sparx5 *sparx5, u32 group, + u32 lb) +{ + return lb == sparx5_sdlb_group_get_first(sparx5, group); +} + +static bool sparx5_sdlb_group_is_last(struct sparx5 *sparx5, u32 group, + u32 lb) +{ + return lb == sparx5_sdlb_group_get_next(sparx5, group, lb); +} + +static bool sparx5_sdlb_group_is_empty(struct sparx5 *sparx5, u32 group) +{ + u32 val; + + val = spx5_rd(sparx5, ANA_AC_SDLB_PUP_CTRL(group)); + + return ANA_AC_SDLB_PUP_CTRL_PUP_ENA_GET(val) == 0; +} + +static u32 sparx5_sdlb_group_get_last(struct sparx5 *sparx5, u32 group) +{ + u32 itr, next; + + itr = sparx5_sdlb_group_get_first(sparx5, group); + + for (;;) { + next = sparx5_sdlb_group_get_next(sparx5, group, itr); + if (itr == next) + return itr; + + itr = next; + } +} + +static bool sparx5_sdlb_group_is_singular(struct sparx5 *sparx5, u32 group) +{ + if (sparx5_sdlb_group_is_empty(sparx5, group)) + return false; + + return sparx5_sdlb_group_get_first(sparx5, group) == + sparx5_sdlb_group_get_last(sparx5, group); +} + +static int sparx5_sdlb_group_get_adjacent(struct sparx5 *sparx5, u32 group, + u32 idx, u32 *prev, u32 *next, + u32 *first) +{ + u32 itr; + + *first = sparx5_sdlb_group_get_first(sparx5, group); + *prev = *first; + *next = *first; + itr = *first; + + for (;;) { + *next = sparx5_sdlb_group_get_next(sparx5, group, itr); + + if (itr == idx) + return 0; /* Found it */ + + if (itr == *next) + return -EINVAL; /* Was not found */ + + *prev = itr; + itr = *next; + } +} + +static int sparx5_sdlb_group_get_count(struct sparx5 *sparx5, u32 group) +{ + u32 itr, next; + int count = 0; + + itr = sparx5_sdlb_group_get_first(sparx5, group); + + for (;;) { + next = sparx5_sdlb_group_get_next(sparx5, group, itr); + if (itr == next) + return count; + + itr = next; + count++; + } +} + +int sparx5_sdlb_group_get_by_rate(struct sparx5 *sparx5, u32 rate, u32 burst) +{ + const struct sparx5_sdlb_group *group; + u64 rate_bps; + int i, count; + + rate_bps = rate * 1000; + + for (i = SPX5_SDLB_GROUP_CNT - 1; i >= 0; i--) { + group = &sdlb_groups[i]; + + count = sparx5_sdlb_group_get_count(sparx5, i); + + /* Check that this group is not full. + * According to LB group configuration rules: the number of XLBs + * in a group must not exceed PUP_INTERVAL/4 - 1. + */ + if (count > ((group->pup_interval / 4) - 1)) + continue; + + if (rate_bps < group->max_rate) + return i; + } + + return -ENOSPC; +} + +int sparx5_sdlb_group_get_by_index(struct sparx5 *sparx5, u32 idx, u32 *group) +{ + u32 itr, next; + int i; + + for (i = 0; i < SPX5_SDLB_GROUP_CNT; i++) { + if (sparx5_sdlb_group_is_empty(sparx5, i)) + continue; + + itr = sparx5_sdlb_group_get_first(sparx5, i); + + for (;;) { + next = sparx5_sdlb_group_get_next(sparx5, i, itr); + + if (itr == idx) { + *group = i; + return 0; /* Found it */ + } + if (itr == next) + break; /* Was not found */ + + itr = next; + } + } + + return -EINVAL; +} + +static int sparx5_sdlb_group_link(struct sparx5 *sparx5, u32 group, u32 idx, + u32 first, u32 next, bool empty) +{ + /* Stop leaking */ + sparx5_sdlb_group_disable(sparx5, group); + + if (empty) + return 0; + + /* Link insertion lb to next lb */ + spx5_wr(ANA_AC_SDLB_XLB_NEXT_LBSET_NEXT_SET(next) | + ANA_AC_SDLB_XLB_NEXT_LBGRP_SET(group), + sparx5, ANA_AC_SDLB_XLB_NEXT(idx)); + + /* Set the first lb */ + spx5_wr(ANA_AC_SDLB_XLB_START_LBSET_START_SET(first), sparx5, + ANA_AC_SDLB_XLB_START(group)); + + /* Start leaking */ + sparx5_sdlb_group_enable(sparx5, group); + + return 0; +}; + +int sparx5_sdlb_group_add(struct sparx5 *sparx5, u32 group, u32 idx) +{ + u32 first, next; + + /* We always add to head of the list */ + first = idx; + + if (sparx5_sdlb_group_is_empty(sparx5, group)) + next = idx; + else + next = sparx5_sdlb_group_get_first(sparx5, group); + + return sparx5_sdlb_group_link(sparx5, group, idx, first, next, false); +} + +int sparx5_sdlb_group_del(struct sparx5 *sparx5, u32 group, u32 idx) +{ + u32 first, next, prev; + bool empty = false; + + if (sparx5_sdlb_group_get_adjacent(sparx5, group, idx, &prev, &next, + &first) < 0) { + pr_err("%s:%d Could not find idx: %d in group: %d", __func__, + __LINE__, idx, group); + return -EINVAL; + } + + if (sparx5_sdlb_group_is_singular(sparx5, group)) { + empty = true; + } else if (sparx5_sdlb_group_is_last(sparx5, group, idx)) { + /* idx is removed, prev is now last */ + idx = prev; + next = prev; + } else if (sparx5_sdlb_group_is_first(sparx5, group, idx)) { + /* idx is removed and points to itself, first is next */ + first = next; + next = idx; + } else { + /* Next is not touched */ + idx = prev; + } + + return sparx5_sdlb_group_link(sparx5, group, idx, first, next, empty); +} + +void sparx5_sdlb_group_init(struct sparx5 *sparx5, u64 max_rate, u32 min_burst, + u32 frame_size, u32 idx) +{ + u32 thres_shift, mask = 0x01, power = 0; + struct sparx5_sdlb_group *group; + u64 max_token; + + group = &sdlb_groups[idx]; + + /* Number of positions to right-shift LB's threshold value. */ + while ((min_burst & mask) == 0) { + power++; + mask <<= 1; + } + thres_shift = SPX5_SDLB_2CYCLES_TYPE2_THRES_OFFSET - power; + + max_token = (min_burst > SPX5_SDLB_PUP_TOKEN_MAX) ? + SPX5_SDLB_PUP_TOKEN_MAX : + min_burst; + group->pup_interval = + sparx5_sdlb_pup_interval_get(sparx5, max_token, max_rate); + + group->frame_size = frame_size; + + spx5_wr(ANA_AC_SDLB_PUP_INTERVAL_PUP_INTERVAL_SET(group->pup_interval), + sparx5, ANA_AC_SDLB_PUP_INTERVAL(idx)); + + spx5_wr(ANA_AC_SDLB_FRM_RATE_TOKENS_FRM_RATE_TOKENS_SET(frame_size), + sparx5, ANA_AC_SDLB_FRM_RATE_TOKENS(idx)); + + spx5_wr(ANA_AC_SDLB_LBGRP_MISC_THRES_SHIFT_SET(thres_shift), sparx5, + ANA_AC_SDLB_LBGRP_MISC(idx)); +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c index 205246b5af82..e80f3166db7d 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c @@ -5,6 +5,7 @@ */ #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include "sparx5_tc.h" #include "sparx5_main.h" diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c index 59d6ed6f4191..d73668dcc6b6 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c @@ -4,11 +4,13 @@ * Copyright (c) 2022 Microchip Technology Inc. and its subsidiaries. */ +#include <net/tc_act/tc_gate.h> #include <net/tcp.h> #include "sparx5_tc.h" #include "vcap_api.h" #include "vcap_api_client.h" +#include "vcap_tc.h" #include "sparx5_main.h" #include "sparx5_vcap_impl.h" @@ -26,223 +28,8 @@ struct sparx5_multiple_rules { struct sparx5_wildcard_rule rule[SPX5_MAX_RULE_SIZE]; }; -struct sparx5_tc_flower_parse_usage { - struct flow_cls_offload *fco; - struct flow_rule *frule; - struct vcap_rule *vrule; - struct vcap_admin *admin; - u16 l3_proto; - u8 l4_proto; - unsigned int used_keys; -}; - -enum sparx5_is2_arp_opcode { - SPX5_IS2_ARP_REQUEST, - SPX5_IS2_ARP_REPLY, - SPX5_IS2_RARP_REQUEST, - SPX5_IS2_RARP_REPLY, -}; - -enum tc_arp_opcode { - TC_ARP_OP_RESERVED, - TC_ARP_OP_REQUEST, - TC_ARP_OP_REPLY, -}; - -static int sparx5_tc_flower_handler_ethaddr_usage(struct sparx5_tc_flower_parse_usage *st) -{ - enum vcap_key_field smac_key = VCAP_KF_L2_SMAC; - enum vcap_key_field dmac_key = VCAP_KF_L2_DMAC; - struct flow_match_eth_addrs match; - struct vcap_u48_key smac, dmac; - int err = 0; - - flow_rule_match_eth_addrs(st->frule, &match); - - if (!is_zero_ether_addr(match.mask->src)) { - vcap_netbytes_copy(smac.value, match.key->src, ETH_ALEN); - vcap_netbytes_copy(smac.mask, match.mask->src, ETH_ALEN); - err = vcap_rule_add_key_u48(st->vrule, smac_key, &smac); - if (err) - goto out; - } - - if (!is_zero_ether_addr(match.mask->dst)) { - vcap_netbytes_copy(dmac.value, match.key->dst, ETH_ALEN); - vcap_netbytes_copy(dmac.mask, match.mask->dst, ETH_ALEN); - err = vcap_rule_add_key_u48(st->vrule, dmac_key, &dmac); - if (err) - goto out; - } - - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS); - - return err; - -out: - NL_SET_ERR_MSG_MOD(st->fco->common.extack, "eth_addr parse error"); - return err; -} - static int -sparx5_tc_flower_handler_ipv4_usage(struct sparx5_tc_flower_parse_usage *st) -{ - int err = 0; - - if (st->l3_proto == ETH_P_IP) { - struct flow_match_ipv4_addrs mt; - - flow_rule_match_ipv4_addrs(st->frule, &mt); - if (mt.mask->src) { - err = vcap_rule_add_key_u32(st->vrule, - VCAP_KF_L3_IP4_SIP, - be32_to_cpu(mt.key->src), - be32_to_cpu(mt.mask->src)); - if (err) - goto out; - } - if (mt.mask->dst) { - err = vcap_rule_add_key_u32(st->vrule, - VCAP_KF_L3_IP4_DIP, - be32_to_cpu(mt.key->dst), - be32_to_cpu(mt.mask->dst)); - if (err) - goto out; - } - } - - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS); - - return err; - -out: - NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ipv4_addr parse error"); - return err; -} - -static int -sparx5_tc_flower_handler_ipv6_usage(struct sparx5_tc_flower_parse_usage *st) -{ - int err = 0; - - if (st->l3_proto == ETH_P_IPV6) { - struct flow_match_ipv6_addrs mt; - struct vcap_u128_key sip; - struct vcap_u128_key dip; - - flow_rule_match_ipv6_addrs(st->frule, &mt); - /* Check if address masks are non-zero */ - if (!ipv6_addr_any(&mt.mask->src)) { - vcap_netbytes_copy(sip.value, mt.key->src.s6_addr, 16); - vcap_netbytes_copy(sip.mask, mt.mask->src.s6_addr, 16); - err = vcap_rule_add_key_u128(st->vrule, - VCAP_KF_L3_IP6_SIP, &sip); - if (err) - goto out; - } - if (!ipv6_addr_any(&mt.mask->dst)) { - vcap_netbytes_copy(dip.value, mt.key->dst.s6_addr, 16); - vcap_netbytes_copy(dip.mask, mt.mask->dst.s6_addr, 16); - err = vcap_rule_add_key_u128(st->vrule, - VCAP_KF_L3_IP6_DIP, &dip); - if (err) - goto out; - } - } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS); - return err; -out: - NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ipv6_addr parse error"); - return err; -} - -static int -sparx5_tc_flower_handler_control_usage(struct sparx5_tc_flower_parse_usage *st) -{ - struct flow_match_control mt; - u32 value, mask; - int err = 0; - - flow_rule_match_control(st->frule, &mt); - - if (mt.mask->flags) { - if (mt.mask->flags & FLOW_DIS_FIRST_FRAG) { - if (mt.key->flags & FLOW_DIS_FIRST_FRAG) { - value = 1; /* initial fragment */ - mask = 0x3; - } else { - if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) { - value = 3; /* follow up fragment */ - mask = 0x3; - } else { - value = 0; /* no fragment */ - mask = 0x3; - } - } - } else { - if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) { - value = 3; /* follow up fragment */ - mask = 0x3; - } else { - value = 0; /* no fragment */ - mask = 0x3; - } - } - - err = vcap_rule_add_key_u32(st->vrule, - VCAP_KF_L3_FRAGMENT_TYPE, - value, mask); - if (err) - goto out; - } - - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL); - - return err; - -out: - NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_frag parse error"); - return err; -} - -static int -sparx5_tc_flower_handler_portnum_usage(struct sparx5_tc_flower_parse_usage *st) -{ - struct flow_match_ports mt; - u16 value, mask; - int err = 0; - - flow_rule_match_ports(st->frule, &mt); - - if (mt.mask->src) { - value = be16_to_cpu(mt.key->src); - mask = be16_to_cpu(mt.mask->src); - err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L4_SPORT, value, - mask); - if (err) - goto out; - } - - if (mt.mask->dst) { - value = be16_to_cpu(mt.key->dst); - mask = be16_to_cpu(mt.mask->dst); - err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L4_DPORT, value, - mask); - if (err) - goto out; - } - - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_PORTS); - - return err; - -out: - NL_SET_ERR_MSG_MOD(st->fco->common.extack, "port parse error"); - return err; -} - -static int -sparx5_tc_flower_handler_basic_usage(struct sparx5_tc_flower_parse_usage *st) +sparx5_tc_flower_handler_basic_usage(struct vcap_tc_flower_parse_usage *st) { struct flow_match_basic mt; int err = 0; @@ -266,6 +53,13 @@ sparx5_tc_flower_handler_basic_usage(struct sparx5_tc_flower_parse_usage *st) VCAP_BIT_0); if (err) goto out; + if (st->admin->vtype == VCAP_TYPE_IS0) { + err = vcap_rule_add_key_bit(st->vrule, + VCAP_KF_IP_SNAP_IS, + VCAP_BIT_1); + if (err) + goto out; + } } } @@ -309,265 +103,92 @@ out: } static int -sparx5_tc_flower_handler_cvlan_usage(struct sparx5_tc_flower_parse_usage *st) -{ - enum vcap_key_field vid_key = VCAP_KF_8021Q_VID0; - enum vcap_key_field pcp_key = VCAP_KF_8021Q_PCP0; - struct flow_match_vlan mt; - u16 tpid; - int err; - - if (st->admin->vtype != VCAP_TYPE_IS0) - return -EINVAL; - - flow_rule_match_cvlan(st->frule, &mt); - - tpid = be16_to_cpu(mt.key->vlan_tpid); - - if (tpid == ETH_P_8021Q) { - vid_key = VCAP_KF_8021Q_VID1; - pcp_key = VCAP_KF_8021Q_PCP1; - } - - if (mt.mask->vlan_id) { - err = vcap_rule_add_key_u32(st->vrule, vid_key, - mt.key->vlan_id, - mt.mask->vlan_id); - if (err) - goto out; - } - - if (mt.mask->vlan_priority) { - err = vcap_rule_add_key_u32(st->vrule, pcp_key, - mt.key->vlan_priority, - mt.mask->vlan_priority); - if (err) - goto out; - } - - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_CVLAN); - - return 0; -out: - NL_SET_ERR_MSG_MOD(st->fco->common.extack, "cvlan parse error"); - return err; -} - -static int -sparx5_tc_flower_handler_vlan_usage(struct sparx5_tc_flower_parse_usage *st) -{ - enum vcap_key_field vid_key = VCAP_KF_8021Q_VID_CLS; - enum vcap_key_field pcp_key = VCAP_KF_8021Q_PCP_CLS; - struct flow_match_vlan mt; - int err; - - flow_rule_match_vlan(st->frule, &mt); - - if (st->admin->vtype == VCAP_TYPE_IS0) { - vid_key = VCAP_KF_8021Q_VID0; - pcp_key = VCAP_KF_8021Q_PCP0; - } - - if (mt.mask->vlan_id) { - err = vcap_rule_add_key_u32(st->vrule, vid_key, - mt.key->vlan_id, - mt.mask->vlan_id); - if (err) - goto out; - } - - if (mt.mask->vlan_priority) { - err = vcap_rule_add_key_u32(st->vrule, pcp_key, - mt.key->vlan_priority, - mt.mask->vlan_priority); - if (err) - goto out; - } - - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_VLAN); - - return 0; -out: - NL_SET_ERR_MSG_MOD(st->fco->common.extack, "vlan parse error"); - return err; -} - -static int -sparx5_tc_flower_handler_tcp_usage(struct sparx5_tc_flower_parse_usage *st) +sparx5_tc_flower_handler_control_usage(struct vcap_tc_flower_parse_usage *st) { - struct flow_match_tcp mt; - u16 tcp_flags_mask; - u16 tcp_flags_key; - enum vcap_bit val; + struct flow_match_control mt; + u32 value, mask; int err = 0; - flow_rule_match_tcp(st->frule, &mt); - tcp_flags_key = be16_to_cpu(mt.key->flags); - tcp_flags_mask = be16_to_cpu(mt.mask->flags); - - if (tcp_flags_mask & TCPHDR_FIN) { - val = VCAP_BIT_0; - if (tcp_flags_key & TCPHDR_FIN) - val = VCAP_BIT_1; - err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_FIN, val); - if (err) - goto out; - } - - if (tcp_flags_mask & TCPHDR_SYN) { - val = VCAP_BIT_0; - if (tcp_flags_key & TCPHDR_SYN) - val = VCAP_BIT_1; - err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_SYN, val); - if (err) - goto out; - } - - if (tcp_flags_mask & TCPHDR_RST) { - val = VCAP_BIT_0; - if (tcp_flags_key & TCPHDR_RST) - val = VCAP_BIT_1; - err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_RST, val); - if (err) - goto out; - } - - if (tcp_flags_mask & TCPHDR_PSH) { - val = VCAP_BIT_0; - if (tcp_flags_key & TCPHDR_PSH) - val = VCAP_BIT_1; - err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_PSH, val); - if (err) - goto out; - } + flow_rule_match_control(st->frule, &mt); - if (tcp_flags_mask & TCPHDR_ACK) { - val = VCAP_BIT_0; - if (tcp_flags_key & TCPHDR_ACK) - val = VCAP_BIT_1; - err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_ACK, val); - if (err) - goto out; - } + if (mt.mask->flags) { + if (mt.mask->flags & FLOW_DIS_FIRST_FRAG) { + if (mt.key->flags & FLOW_DIS_FIRST_FRAG) { + value = 1; /* initial fragment */ + mask = 0x3; + } else { + if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) { + value = 3; /* follow up fragment */ + mask = 0x3; + } else { + value = 0; /* no fragment */ + mask = 0x3; + } + } + } else { + if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) { + value = 3; /* follow up fragment */ + mask = 0x3; + } else { + value = 0; /* no fragment */ + mask = 0x3; + } + } - if (tcp_flags_mask & TCPHDR_URG) { - val = VCAP_BIT_0; - if (tcp_flags_key & TCPHDR_URG) - val = VCAP_BIT_1; - err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_URG, val); + err = vcap_rule_add_key_u32(st->vrule, + VCAP_KF_L3_FRAGMENT_TYPE, + value, mask); if (err) goto out; } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_TCP); + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL); return err; out: - NL_SET_ERR_MSG_MOD(st->fco->common.extack, "tcp_flags parse error"); + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_frag parse error"); return err; } static int -sparx5_tc_flower_handler_arp_usage(struct sparx5_tc_flower_parse_usage *st) +sparx5_tc_flower_handler_cvlan_usage(struct vcap_tc_flower_parse_usage *st) { - struct flow_match_arp mt; - u16 value, mask; - u32 ipval, ipmsk; - int err; - - flow_rule_match_arp(st->frule, &mt); - - if (mt.mask->op) { - mask = 0x3; - if (st->l3_proto == ETH_P_ARP) { - value = mt.key->op == TC_ARP_OP_REQUEST ? - SPX5_IS2_ARP_REQUEST : - SPX5_IS2_ARP_REPLY; - } else { /* RARP */ - value = mt.key->op == TC_ARP_OP_REQUEST ? - SPX5_IS2_RARP_REQUEST : - SPX5_IS2_RARP_REPLY; - } - err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_ARP_OPCODE, - value, mask); - if (err) - goto out; - } - - /* The IS2 ARP keyset does not support ARP hardware addresses */ - if (!is_zero_ether_addr(mt.mask->sha) || - !is_zero_ether_addr(mt.mask->tha)) { - err = -EINVAL; - goto out; - } - - if (mt.mask->sip) { - ipval = be32_to_cpu((__force __be32)mt.key->sip); - ipmsk = be32_to_cpu((__force __be32)mt.mask->sip); - - err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L3_IP4_SIP, - ipval, ipmsk); - if (err) - goto out; - } - - if (mt.mask->tip) { - ipval = be32_to_cpu((__force __be32)mt.key->tip); - ipmsk = be32_to_cpu((__force __be32)mt.mask->tip); - - err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L3_IP4_DIP, - ipval, ipmsk); - if (err) - goto out; + if (st->admin->vtype != VCAP_TYPE_IS0) { + NL_SET_ERR_MSG_MOD(st->fco->common.extack, + "cvlan not supported in this VCAP"); + return -EINVAL; } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_ARP); - - return 0; - -out: - NL_SET_ERR_MSG_MOD(st->fco->common.extack, "arp parse error"); - return err; + return vcap_tc_flower_handler_cvlan_usage(st); } static int -sparx5_tc_flower_handler_ip_usage(struct sparx5_tc_flower_parse_usage *st) +sparx5_tc_flower_handler_vlan_usage(struct vcap_tc_flower_parse_usage *st) { - struct flow_match_ip mt; - int err = 0; - - flow_rule_match_ip(st->frule, &mt); + enum vcap_key_field vid_key = VCAP_KF_8021Q_VID_CLS; + enum vcap_key_field pcp_key = VCAP_KF_8021Q_PCP_CLS; - if (mt.mask->tos) { - err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L3_TOS, - mt.key->tos, - mt.mask->tos); - if (err) - goto out; + if (st->admin->vtype == VCAP_TYPE_IS0) { + vid_key = VCAP_KF_8021Q_VID0; + pcp_key = VCAP_KF_8021Q_PCP0; } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IP); - - return err; - -out: - NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_tos parse error"); - return err; + return vcap_tc_flower_handler_vlan_usage(st, vid_key, pcp_key); } -static int (*sparx5_tc_flower_usage_handlers[])(struct sparx5_tc_flower_parse_usage *st) = { - [FLOW_DISSECTOR_KEY_ETH_ADDRS] = sparx5_tc_flower_handler_ethaddr_usage, - [FLOW_DISSECTOR_KEY_IPV4_ADDRS] = sparx5_tc_flower_handler_ipv4_usage, - [FLOW_DISSECTOR_KEY_IPV6_ADDRS] = sparx5_tc_flower_handler_ipv6_usage, +static int (*sparx5_tc_flower_usage_handlers[])(struct vcap_tc_flower_parse_usage *st) = { + [FLOW_DISSECTOR_KEY_ETH_ADDRS] = vcap_tc_flower_handler_ethaddr_usage, + [FLOW_DISSECTOR_KEY_IPV4_ADDRS] = vcap_tc_flower_handler_ipv4_usage, + [FLOW_DISSECTOR_KEY_IPV6_ADDRS] = vcap_tc_flower_handler_ipv6_usage, [FLOW_DISSECTOR_KEY_CONTROL] = sparx5_tc_flower_handler_control_usage, - [FLOW_DISSECTOR_KEY_PORTS] = sparx5_tc_flower_handler_portnum_usage, + [FLOW_DISSECTOR_KEY_PORTS] = vcap_tc_flower_handler_portnum_usage, [FLOW_DISSECTOR_KEY_BASIC] = sparx5_tc_flower_handler_basic_usage, [FLOW_DISSECTOR_KEY_CVLAN] = sparx5_tc_flower_handler_cvlan_usage, [FLOW_DISSECTOR_KEY_VLAN] = sparx5_tc_flower_handler_vlan_usage, - [FLOW_DISSECTOR_KEY_TCP] = sparx5_tc_flower_handler_tcp_usage, - [FLOW_DISSECTOR_KEY_ARP] = sparx5_tc_flower_handler_arp_usage, - [FLOW_DISSECTOR_KEY_IP] = sparx5_tc_flower_handler_ip_usage, + [FLOW_DISSECTOR_KEY_TCP] = vcap_tc_flower_handler_tcp_usage, + [FLOW_DISSECTOR_KEY_ARP] = vcap_tc_flower_handler_arp_usage, + [FLOW_DISSECTOR_KEY_IP] = vcap_tc_flower_handler_ip_usage, }; static int sparx5_tc_use_dissectors(struct flow_cls_offload *fco, @@ -575,7 +196,7 @@ static int sparx5_tc_use_dissectors(struct flow_cls_offload *fco, struct vcap_rule *vrule, u16 *l3_proto) { - struct sparx5_tc_flower_parse_usage state = { + struct vcap_tc_flower_parse_usage state = { .fco = fco, .vrule = vrule, .l3_proto = ETH_P_ALL, @@ -607,7 +228,8 @@ static int sparx5_tc_use_dissectors(struct flow_cls_offload *fco, static int sparx5_tc_flower_action_check(struct vcap_control *vctrl, struct net_device *ndev, - struct flow_cls_offload *fco) + struct flow_cls_offload *fco, + bool ingress) { struct flow_rule *rule = flow_cls_offload_flow_rule(fco); struct flow_action_entry *actent, *last_actent = NULL; @@ -644,7 +266,8 @@ static int sparx5_tc_flower_action_check(struct vcap_control *vctrl, "Invalid goto chain"); return -EINVAL; } - } else if (!vcap_is_last_chain(vctrl, fco->common.chain_index)) { + } else if (!vcap_is_last_chain(vctrl, fco->common.chain_index, + ingress)) { NL_SET_ERR_MSG_MOD(fco->common.extack, "Last action must be 'goto'"); return -EINVAL; @@ -667,7 +290,7 @@ static int sparx5_tc_add_rule_counter(struct vcap_admin *admin, { int err; - if (admin->vtype == VCAP_TYPE_IS2) { + if (admin->vtype == VCAP_TYPE_IS2 || admin->vtype == VCAP_TYPE_ES2) { err = vcap_rule_mod_action_u32(vrule, VCAP_AF_CNT_ID, vrule->id); if (err) @@ -870,6 +493,9 @@ static int sparx5_tc_set_actionset(struct vcap_admin *admin, case VCAP_TYPE_IS2: aset = VCAP_AFS_BASE_TYPE; break; + case VCAP_TYPE_ES2: + aset = VCAP_AFS_BASE_TYPE; + break; default: return -EINVAL; } @@ -906,6 +532,10 @@ static int sparx5_tc_add_rule_link_target(struct vcap_admin *admin, return vcap_rule_add_key_u32(vrule, VCAP_KF_LOOKUP_PAG, link_val, /* target */ ~0); + case VCAP_TYPE_ES2: + /* Add ISDX key for chaining rules from IS0 */ + return vcap_rule_add_key_u32(vrule, VCAP_KF_ISDX_CLS, link_val, + ~0); default: break; } @@ -948,6 +578,18 @@ static int sparx5_tc_add_rule_link(struct vcap_control *vctrl, 0xff); if (err) goto out; + } else if (admin->vtype == VCAP_TYPE_IS0 && + to_admin->vtype == VCAP_TYPE_ES2) { + /* Between IS0 and ES2 the ISDX value is used */ + err = vcap_rule_add_action_u32(vrule, VCAP_AF_ISDX_VAL, + diff); + if (err) + goto out; + err = vcap_rule_add_action_bit(vrule, + VCAP_AF_ISDX_ADD_REPLACE_SEL, + VCAP_BIT_1); + if (err) + goto out; } else { pr_err("%s:%d: unsupported chain destination: %d\n", __func__, __LINE__, to_cid); @@ -957,22 +599,160 @@ out: return err; } +static int sparx5_tc_flower_parse_act_gate(struct sparx5_psfp_sg *sg, + struct flow_action_entry *act, + struct netlink_ext_ack *extack) +{ + int i; + + if (act->gate.prio < -1 || act->gate.prio > SPX5_PSFP_SG_MAX_IPV) { + NL_SET_ERR_MSG_MOD(extack, "Invalid gate priority"); + return -EINVAL; + } + + if (act->gate.cycletime < SPX5_PSFP_SG_MIN_CYCLE_TIME_NS || + act->gate.cycletime > SPX5_PSFP_SG_MAX_CYCLE_TIME_NS) { + NL_SET_ERR_MSG_MOD(extack, "Invalid gate cycletime"); + return -EINVAL; + } + + if (act->gate.cycletimeext > SPX5_PSFP_SG_MAX_CYCLE_TIME_NS) { + NL_SET_ERR_MSG_MOD(extack, "Invalid gate cycletimeext"); + return -EINVAL; + } + + if (act->gate.num_entries >= SPX5_PSFP_GCE_CNT) { + NL_SET_ERR_MSG_MOD(extack, "Invalid number of gate entries"); + return -EINVAL; + } + + sg->gate_state = true; + sg->ipv = act->gate.prio; + sg->num_entries = act->gate.num_entries; + sg->cycletime = act->gate.cycletime; + sg->cycletimeext = act->gate.cycletimeext; + + for (i = 0; i < sg->num_entries; i++) { + sg->gce[i].gate_state = !!act->gate.entries[i].gate_state; + sg->gce[i].interval = act->gate.entries[i].interval; + sg->gce[i].ipv = act->gate.entries[i].ipv; + sg->gce[i].maxoctets = act->gate.entries[i].maxoctets; + } + + return 0; +} + +static int sparx5_tc_flower_parse_act_police(struct sparx5_policer *pol, + struct flow_action_entry *act, + struct netlink_ext_ack *extack) +{ + pol->type = SPX5_POL_SERVICE; + pol->rate = div_u64(act->police.rate_bytes_ps, 1000) * 8; + pol->burst = act->police.burst; + pol->idx = act->hw_index; + + /* rate is now in kbit */ + if (pol->rate > DIV_ROUND_UP(SPX5_SDLB_GROUP_RATE_MAX, 1000)) { + NL_SET_ERR_MSG_MOD(extack, "Maximum rate exceeded"); + return -EINVAL; + } + + if (act->police.exceed.act_id != FLOW_ACTION_DROP) { + NL_SET_ERR_MSG_MOD(extack, "Offload not supported when exceed action is not drop"); + return -EOPNOTSUPP; + } + + if (act->police.notexceed.act_id != FLOW_ACTION_PIPE && + act->police.notexceed.act_id != FLOW_ACTION_ACCEPT) { + NL_SET_ERR_MSG_MOD(extack, "Offload not supported when conform action is not pipe or ok"); + return -EOPNOTSUPP; + } + + return 0; +} + +static int sparx5_tc_flower_psfp_setup(struct sparx5 *sparx5, + struct vcap_rule *vrule, int sg_idx, + int pol_idx, struct sparx5_psfp_sg *sg, + struct sparx5_psfp_fm *fm, + struct sparx5_psfp_sf *sf) +{ + u32 psfp_sfid = 0, psfp_fmid = 0, psfp_sgid = 0; + int ret; + + /* Must always have a stream gate - max sdu (filter option) is evaluated + * after frames have passed the gate, so in case of only a policer, we + * allocate a stream gate that is always open. + */ + if (sg_idx < 0) { + sg_idx = sparx5_pool_idx_to_id(SPX5_PSFP_SG_OPEN); + sg->ipv = 0; /* Disabled */ + sg->cycletime = SPX5_PSFP_SG_CYCLE_TIME_DEFAULT; + sg->num_entries = 1; + sg->gate_state = 1; /* Open */ + sg->gate_enabled = 1; + sg->gce[0].gate_state = 1; + sg->gce[0].interval = SPX5_PSFP_SG_CYCLE_TIME_DEFAULT; + sg->gce[0].ipv = 0; + sg->gce[0].maxoctets = 0; /* Disabled */ + } + + ret = sparx5_psfp_sg_add(sparx5, sg_idx, sg, &psfp_sgid); + if (ret < 0) + return ret; + + if (pol_idx >= 0) { + /* Add new flow-meter */ + ret = sparx5_psfp_fm_add(sparx5, pol_idx, fm, &psfp_fmid); + if (ret < 0) + return ret; + } + + /* Map stream filter to stream gate */ + sf->sgid = psfp_sgid; + + /* Add new stream-filter and map it to a steam gate */ + ret = sparx5_psfp_sf_add(sparx5, sf, &psfp_sfid); + if (ret < 0) + return ret; + + /* Streams are classified by ISDX - map ISDX 1:1 to sfid for now. */ + sparx5_isdx_conf_set(sparx5, psfp_sfid, psfp_sfid, psfp_fmid); + + ret = vcap_rule_add_action_bit(vrule, VCAP_AF_ISDX_ADD_REPLACE_SEL, + VCAP_BIT_1); + if (ret) + return ret; + + ret = vcap_rule_add_action_u32(vrule, VCAP_AF_ISDX_VAL, psfp_sfid); + if (ret) + return ret; + + return 0; +} + static int sparx5_tc_flower_replace(struct net_device *ndev, struct flow_cls_offload *fco, - struct vcap_admin *admin) + struct vcap_admin *admin, + bool ingress) { + struct sparx5_psfp_sf sf = { .max_sdu = SPX5_PSFP_SF_MAX_SDU }; + struct netlink_ext_ack *extack = fco->common.extack; + int err, idx, tc_sg_idx = -1, tc_pol_idx = -1; struct sparx5_port *port = netdev_priv(ndev); struct sparx5_multiple_rules multi = {}; + struct sparx5 *sparx5 = port->sparx5; + struct sparx5_psfp_sg sg = { 0 }; + struct sparx5_psfp_fm fm = { 0 }; struct flow_action_entry *act; struct vcap_control *vctrl; struct flow_rule *frule; struct vcap_rule *vrule; u16 l3_proto; - int err, idx; vctrl = port->sparx5->vcap_ctrl; - err = sparx5_tc_flower_action_check(vctrl, ndev, fco); + err = sparx5_tc_flower_action_check(vctrl, ndev, fco, ingress); if (err) return err; @@ -1000,8 +780,29 @@ static int sparx5_tc_flower_replace(struct net_device *ndev, frule = flow_cls_offload_flow_rule(fco); flow_action_for_each(idx, act, &frule->action) { switch (act->id) { + case FLOW_ACTION_GATE: { + err = sparx5_tc_flower_parse_act_gate(&sg, act, extack); + if (err < 0) + goto out; + + tc_sg_idx = act->hw_index; + + break; + } + case FLOW_ACTION_POLICE: { + err = sparx5_tc_flower_parse_act_police(&fm.pol, act, + extack); + if (err < 0) + goto out; + + tc_pol_idx = fm.pol.idx; + sf.max_sdu = act->police.mtu; + + break; + } case FLOW_ACTION_TRAP: - if (admin->vtype != VCAP_TYPE_IS2) { + if (admin->vtype != VCAP_TYPE_IS2 && + admin->vtype != VCAP_TYPE_ES2) { NL_SET_ERR_MSG_MOD(fco->common.extack, "Trap action not supported in this VCAP"); err = -EOPNOTSUPP; @@ -1016,8 +817,11 @@ static int sparx5_tc_flower_replace(struct net_device *ndev, VCAP_AF_CPU_QUEUE_NUM, 0); if (err) goto out; - err = vcap_rule_add_action_u32(vrule, VCAP_AF_MASK_MODE, - SPX5_PMM_REPLACE_ALL); + if (admin->vtype != VCAP_TYPE_IS2) + break; + err = vcap_rule_add_action_u32(vrule, + VCAP_AF_MASK_MODE, + SPX5_PMM_REPLACE_ALL); if (err) goto out; break; @@ -1042,6 +846,14 @@ static int sparx5_tc_flower_replace(struct net_device *ndev, } } + /* Setup PSFP */ + if (tc_sg_idx >= 0 || tc_pol_idx >= 0) { + err = sparx5_tc_flower_psfp_setup(sparx5, vrule, tc_sg_idx, + tc_pol_idx, &sg, &fm, &sf); + if (err) + goto out; + } + err = sparx5_tc_select_protocol_keyset(ndev, vrule, admin, l3_proto, &multi); if (err) { @@ -1070,19 +882,86 @@ out: return err; } +static void sparx5_tc_free_psfp_resources(struct sparx5 *sparx5, + struct vcap_rule *vrule) +{ + struct vcap_client_actionfield *afield; + u32 isdx, sfid, sgid, fmid; + + /* Check if VCAP_AF_ISDX_VAL action is set for this rule - and if + * it is used for stream and/or flow-meter classification. + */ + afield = vcap_find_actionfield(vrule, VCAP_AF_ISDX_VAL); + if (!afield) + return; + + isdx = afield->data.u32.value; + sfid = sparx5_psfp_isdx_get_sf(sparx5, isdx); + + if (!sfid) + return; + + fmid = sparx5_psfp_isdx_get_fm(sparx5, isdx); + sgid = sparx5_psfp_sf_get_sg(sparx5, sfid); + + if (fmid && sparx5_psfp_fm_del(sparx5, fmid) < 0) + pr_err("%s:%d Could not delete invalid fmid: %d", __func__, + __LINE__, fmid); + + if (sgid && sparx5_psfp_sg_del(sparx5, sgid) < 0) + pr_err("%s:%d Could not delete invalid sgid: %d", __func__, + __LINE__, sgid); + + if (sparx5_psfp_sf_del(sparx5, sfid) < 0) + pr_err("%s:%d Could not delete invalid sfid: %d", __func__, + __LINE__, sfid); + + sparx5_isdx_conf_set(sparx5, isdx, 0, 0); +} + +static int sparx5_tc_free_rule_resources(struct net_device *ndev, + struct vcap_control *vctrl, + int rule_id) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + struct vcap_rule *vrule; + int ret = 0; + + vrule = vcap_get_rule(vctrl, rule_id); + if (!vrule || IS_ERR(vrule)) + return -EINVAL; + + sparx5_tc_free_psfp_resources(sparx5, vrule); + + vcap_free_rule(vrule); + return ret; +} + static int sparx5_tc_flower_destroy(struct net_device *ndev, struct flow_cls_offload *fco, struct vcap_admin *admin) { struct sparx5_port *port = netdev_priv(ndev); + int err = -ENOENT, count = 0, rule_id; struct vcap_control *vctrl; - int err = -ENOENT, rule_id; vctrl = port->sparx5->vcap_ctrl; while (true) { rule_id = vcap_lookup_rule_by_cookie(vctrl, fco->cookie); if (rule_id <= 0) break; + if (count == 0) { + /* Resources are attached to the first rule of + * a set of rules. Only works if the rules are + * in the correct order. + */ + err = sparx5_tc_free_rule_resources(ndev, vctrl, + rule_id); + if (err) + pr_err("%s:%d: could not free resources %d\n", + __func__, __LINE__, rule_id); + } err = vcap_del_rule(vctrl, ndev, rule_id); if (err) { pr_err("%s:%d: could not delete rule %d\n", @@ -1130,7 +1009,7 @@ int sparx5_tc_flower(struct net_device *ndev, struct flow_cls_offload *fco, switch (fco->command) { case FLOW_CLS_REPLACE: - return sparx5_tc_flower_replace(ndev, fco, admin); + return sparx5_tc_flower_replace(ndev, fco, admin, ingress); case FLOW_CLS_DESTROY: return sparx5_tc_flower_destroy(ndev, fco, admin); case FLOW_CLS_STATS: diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_ag_api.c b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_ag_api.c index 41e50743f3ac..561001ee0516 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_ag_api.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_ag_api.c @@ -1,10 +1,10 @@ // SPDX-License-Identifier: BSD-3-Clause -/* Copyright (C) 2022 Microchip Technology Inc. and its subsidiaries. +/* Copyright (C) 2023 Microchip Technology Inc. and its subsidiaries. * Microchip VCAP API */ -/* This file is autogenerated by cml-utils 2022-12-06 12:43:54 +0100. - * Commit ID: 3db2ac730f134c160496f2b9f10915e347d871cb +/* This file is autogenerated by cml-utils 2023-01-17 16:55:38 +0100. + * Commit ID: cc027a9bd71002aebf074df5ad8584fe1545e05e */ #include <linux/types.h> @@ -1333,6 +1333,909 @@ static const struct vcap_field is2_ip_7tuple_keyfield[] = { }, }; +static const struct vcap_field es2_mac_etype_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 3, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 3, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 14, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 15, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 12, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 28, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 29, + .width = 13, + }, + [VCAP_KF_IF_EGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 42, + .width = 3, + }, + [VCAP_KF_IF_EGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 45, + .width = 32, + }, + [VCAP_KF_IF_IGR_PORT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 77, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 78, + .width = 9, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 87, + .width = 3, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 90, + .width = 1, + }, + [VCAP_KF_COSID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 91, + .width = 3, + }, + [VCAP_KF_L3_DPL_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 94, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 95, + .width = 1, + }, + [VCAP_KF_L2_DMAC] = { + .type = VCAP_FIELD_U48, + .offset = 99, + .width = 48, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 147, + .width = 48, + }, + [VCAP_KF_ETYPE_LEN_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 195, + .width = 1, + }, + [VCAP_KF_ETYPE] = { + .type = VCAP_FIELD_U32, + .offset = 196, + .width = 16, + }, + [VCAP_KF_L2_PAYLOAD_ETYPE] = { + .type = VCAP_FIELD_U64, + .offset = 212, + .width = 64, + }, + [VCAP_KF_OAM_CCM_CNTS_EQ0] = { + .type = VCAP_FIELD_BIT, + .offset = 276, + .width = 1, + }, + [VCAP_KF_OAM_Y1731_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 277, + .width = 1, + }, +}; + +static const struct vcap_field es2_arp_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 3, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 3, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 14, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 15, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 12, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 28, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 29, + .width = 13, + }, + [VCAP_KF_IF_EGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 42, + .width = 3, + }, + [VCAP_KF_IF_EGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 45, + .width = 32, + }, + [VCAP_KF_IF_IGR_PORT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 77, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 78, + .width = 9, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 87, + .width = 3, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 90, + .width = 1, + }, + [VCAP_KF_COSID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 91, + .width = 3, + }, + [VCAP_KF_L3_DPL_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 94, + .width = 1, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 98, + .width = 48, + }, + [VCAP_KF_ARP_ADDR_SPACE_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 146, + .width = 1, + }, + [VCAP_KF_ARP_PROTO_SPACE_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 147, + .width = 1, + }, + [VCAP_KF_ARP_LEN_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 148, + .width = 1, + }, + [VCAP_KF_ARP_TGT_MATCH_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 149, + .width = 1, + }, + [VCAP_KF_ARP_SENDER_MATCH_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 150, + .width = 1, + }, + [VCAP_KF_ARP_OPCODE_UNKNOWN_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 151, + .width = 1, + }, + [VCAP_KF_ARP_OPCODE] = { + .type = VCAP_FIELD_U32, + .offset = 152, + .width = 2, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 154, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 186, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 218, + .width = 1, + }, +}; + +static const struct vcap_field es2_ip4_tcp_udp_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 3, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 3, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 14, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 15, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 12, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 28, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 29, + .width = 13, + }, + [VCAP_KF_IF_EGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 42, + .width = 3, + }, + [VCAP_KF_IF_EGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 45, + .width = 32, + }, + [VCAP_KF_IF_IGR_PORT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 77, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 78, + .width = 9, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 87, + .width = 3, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 90, + .width = 1, + }, + [VCAP_KF_COSID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 91, + .width = 3, + }, + [VCAP_KF_L3_DPL_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 94, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 95, + .width = 1, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 99, + .width = 1, + }, + [VCAP_KF_L3_FRAGMENT_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 100, + .width = 2, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 102, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 103, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 104, + .width = 8, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 112, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 144, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 176, + .width = 1, + }, + [VCAP_KF_TCP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 177, + .width = 1, + }, + [VCAP_KF_L4_DPORT] = { + .type = VCAP_FIELD_U32, + .offset = 178, + .width = 16, + }, + [VCAP_KF_L4_SPORT] = { + .type = VCAP_FIELD_U32, + .offset = 194, + .width = 16, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 210, + .width = 16, + }, + [VCAP_KF_L4_SPORT_EQ_DPORT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 226, + .width = 1, + }, + [VCAP_KF_L4_SEQUENCE_EQ0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 227, + .width = 1, + }, + [VCAP_KF_L4_FIN] = { + .type = VCAP_FIELD_BIT, + .offset = 228, + .width = 1, + }, + [VCAP_KF_L4_SYN] = { + .type = VCAP_FIELD_BIT, + .offset = 229, + .width = 1, + }, + [VCAP_KF_L4_RST] = { + .type = VCAP_FIELD_BIT, + .offset = 230, + .width = 1, + }, + [VCAP_KF_L4_PSH] = { + .type = VCAP_FIELD_BIT, + .offset = 231, + .width = 1, + }, + [VCAP_KF_L4_ACK] = { + .type = VCAP_FIELD_BIT, + .offset = 232, + .width = 1, + }, + [VCAP_KF_L4_URG] = { + .type = VCAP_FIELD_BIT, + .offset = 233, + .width = 1, + }, + [VCAP_KF_L4_PAYLOAD] = { + .type = VCAP_FIELD_U64, + .offset = 234, + .width = 64, + }, +}; + +static const struct vcap_field es2_ip4_other_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 3, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 3, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 14, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 15, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 12, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 28, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 29, + .width = 13, + }, + [VCAP_KF_IF_EGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 42, + .width = 3, + }, + [VCAP_KF_IF_EGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 45, + .width = 32, + }, + [VCAP_KF_IF_IGR_PORT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 77, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 78, + .width = 9, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 87, + .width = 3, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 90, + .width = 1, + }, + [VCAP_KF_COSID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 91, + .width = 3, + }, + [VCAP_KF_L3_DPL_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 94, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 95, + .width = 1, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 99, + .width = 1, + }, + [VCAP_KF_L3_FRAGMENT_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 100, + .width = 2, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 102, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 103, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 104, + .width = 8, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 112, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 144, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 176, + .width = 1, + }, + [VCAP_KF_L3_IP_PROTO] = { + .type = VCAP_FIELD_U32, + .offset = 177, + .width = 8, + }, + [VCAP_KF_L3_PAYLOAD] = { + .type = VCAP_FIELD_U112, + .offset = 185, + .width = 96, + }, +}; + +static const struct vcap_field es2_ip_7tuple_keyfield[] = { + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 10, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 11, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 12, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 13, + .width = 12, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 25, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 26, + .width = 13, + }, + [VCAP_KF_IF_EGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 39, + .width = 3, + }, + [VCAP_KF_IF_EGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 42, + .width = 32, + }, + [VCAP_KF_IF_IGR_PORT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 74, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 75, + .width = 9, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 84, + .width = 3, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 87, + .width = 1, + }, + [VCAP_KF_COSID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 88, + .width = 3, + }, + [VCAP_KF_L3_DPL_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 91, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 92, + .width = 1, + }, + [VCAP_KF_L2_DMAC] = { + .type = VCAP_FIELD_U48, + .offset = 96, + .width = 48, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 144, + .width = 48, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 192, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 193, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 194, + .width = 8, + }, + [VCAP_KF_L3_IP6_DIP] = { + .type = VCAP_FIELD_U128, + .offset = 202, + .width = 128, + }, + [VCAP_KF_L3_IP6_SIP] = { + .type = VCAP_FIELD_U128, + .offset = 330, + .width = 128, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 458, + .width = 1, + }, + [VCAP_KF_TCP_UDP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 459, + .width = 1, + }, + [VCAP_KF_TCP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 460, + .width = 1, + }, + [VCAP_KF_L4_DPORT] = { + .type = VCAP_FIELD_U32, + .offset = 461, + .width = 16, + }, + [VCAP_KF_L4_SPORT] = { + .type = VCAP_FIELD_U32, + .offset = 477, + .width = 16, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 493, + .width = 16, + }, + [VCAP_KF_L4_SPORT_EQ_DPORT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 509, + .width = 1, + }, + [VCAP_KF_L4_SEQUENCE_EQ0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 510, + .width = 1, + }, + [VCAP_KF_L4_FIN] = { + .type = VCAP_FIELD_BIT, + .offset = 511, + .width = 1, + }, + [VCAP_KF_L4_SYN] = { + .type = VCAP_FIELD_BIT, + .offset = 512, + .width = 1, + }, + [VCAP_KF_L4_RST] = { + .type = VCAP_FIELD_BIT, + .offset = 513, + .width = 1, + }, + [VCAP_KF_L4_PSH] = { + .type = VCAP_FIELD_BIT, + .offset = 514, + .width = 1, + }, + [VCAP_KF_L4_ACK] = { + .type = VCAP_FIELD_BIT, + .offset = 515, + .width = 1, + }, + [VCAP_KF_L4_URG] = { + .type = VCAP_FIELD_BIT, + .offset = 516, + .width = 1, + }, + [VCAP_KF_L4_PAYLOAD] = { + .type = VCAP_FIELD_U64, + .offset = 517, + .width = 64, + }, +}; + +static const struct vcap_field es2_ip6_std_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 3, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 3, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 14, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 15, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 12, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 28, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 29, + .width = 13, + }, + [VCAP_KF_IF_EGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 42, + .width = 3, + }, + [VCAP_KF_IF_EGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 45, + .width = 32, + }, + [VCAP_KF_IF_IGR_PORT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 77, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 78, + .width = 9, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 87, + .width = 3, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 90, + .width = 1, + }, + [VCAP_KF_COSID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 91, + .width = 3, + }, + [VCAP_KF_L3_DPL_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 94, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 95, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 99, + .width = 1, + }, + [VCAP_KF_L3_IP6_SIP] = { + .type = VCAP_FIELD_U128, + .offset = 100, + .width = 128, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 228, + .width = 1, + }, + [VCAP_KF_L3_IP_PROTO] = { + .type = VCAP_FIELD_U32, + .offset = 229, + .width = 8, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 237, + .width = 16, + }, + [VCAP_KF_L3_PAYLOAD] = { + .type = VCAP_FIELD_U48, + .offset = 253, + .width = 40, + }, +}; + /* keyfield_set */ static const struct vcap_set is0_keyfield_set[] = { [VCAP_KFS_NORMAL_7TUPLE] = { @@ -1380,6 +2283,39 @@ static const struct vcap_set is2_keyfield_set[] = { }, }; +static const struct vcap_set es2_keyfield_set[] = { + [VCAP_KFS_MAC_ETYPE] = { + .type_id = 0, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_ARP] = { + .type_id = 1, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP4_TCP_UDP] = { + .type_id = 2, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP4_OTHER] = { + .type_id = 3, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP_7TUPLE] = { + .type_id = -1, + .sw_per_item = 12, + .sw_cnt = 1, + }, + [VCAP_KFS_IP6_STD] = { + .type_id = 4, + .sw_per_item = 6, + .sw_cnt = 2, + }, +}; + /* keyfield_set map */ static const struct vcap_field *is0_keyfield_set_map[] = { [VCAP_KFS_NORMAL_7TUPLE] = is0_normal_7tuple_keyfield, @@ -1395,6 +2331,15 @@ static const struct vcap_field *is2_keyfield_set_map[] = { [VCAP_KFS_IP_7TUPLE] = is2_ip_7tuple_keyfield, }; +static const struct vcap_field *es2_keyfield_set_map[] = { + [VCAP_KFS_MAC_ETYPE] = es2_mac_etype_keyfield, + [VCAP_KFS_ARP] = es2_arp_keyfield, + [VCAP_KFS_IP4_TCP_UDP] = es2_ip4_tcp_udp_keyfield, + [VCAP_KFS_IP4_OTHER] = es2_ip4_other_keyfield, + [VCAP_KFS_IP_7TUPLE] = es2_ip_7tuple_keyfield, + [VCAP_KFS_IP6_STD] = es2_ip6_std_keyfield, +}; + /* keyfield_set map sizes */ static int is0_keyfield_set_map_size[] = { [VCAP_KFS_NORMAL_7TUPLE] = ARRAY_SIZE(is0_normal_7tuple_keyfield), @@ -1410,6 +2355,15 @@ static int is2_keyfield_set_map_size[] = { [VCAP_KFS_IP_7TUPLE] = ARRAY_SIZE(is2_ip_7tuple_keyfield), }; +static int es2_keyfield_set_map_size[] = { + [VCAP_KFS_MAC_ETYPE] = ARRAY_SIZE(es2_mac_etype_keyfield), + [VCAP_KFS_ARP] = ARRAY_SIZE(es2_arp_keyfield), + [VCAP_KFS_IP4_TCP_UDP] = ARRAY_SIZE(es2_ip4_tcp_udp_keyfield), + [VCAP_KFS_IP4_OTHER] = ARRAY_SIZE(es2_ip4_other_keyfield), + [VCAP_KFS_IP_7TUPLE] = ARRAY_SIZE(es2_ip_7tuple_keyfield), + [VCAP_KFS_IP6_STD] = ARRAY_SIZE(es2_ip6_std_keyfield), +}; + /* actionfields */ static const struct vcap_field is0_classification_actionfield[] = { [VCAP_AF_TYPE] = { @@ -1798,6 +2752,79 @@ static const struct vcap_field is2_base_type_actionfield[] = { }, }; +static const struct vcap_field es2_base_type_actionfield[] = { + [VCAP_AF_HIT_ME_ONCE] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_AF_INTR_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 1, + .width = 1, + }, + [VCAP_AF_FWD_MODE] = { + .type = VCAP_FIELD_U32, + .offset = 2, + .width = 2, + }, + [VCAP_AF_COPY_QUEUE_NUM] = { + .type = VCAP_FIELD_U32, + .offset = 4, + .width = 16, + }, + [VCAP_AF_COPY_PORT_NUM] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 7, + }, + [VCAP_AF_MIRROR_PROBE_ID] = { + .type = VCAP_FIELD_U32, + .offset = 27, + .width = 2, + }, + [VCAP_AF_CPU_COPY_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 29, + .width = 1, + }, + [VCAP_AF_CPU_QUEUE_NUM] = { + .type = VCAP_FIELD_U32, + .offset = 30, + .width = 3, + }, + [VCAP_AF_POLICE_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 33, + .width = 1, + }, + [VCAP_AF_POLICE_REMARK] = { + .type = VCAP_FIELD_BIT, + .offset = 34, + .width = 1, + }, + [VCAP_AF_POLICE_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 35, + .width = 6, + }, + [VCAP_AF_ES2_REW_CMD] = { + .type = VCAP_FIELD_U32, + .offset = 41, + .width = 3, + }, + [VCAP_AF_CNT_ID] = { + .type = VCAP_FIELD_U32, + .offset = 44, + .width = 11, + }, + [VCAP_AF_IGNORE_PIPELINE_CTRL] = { + .type = VCAP_FIELD_BIT, + .offset = 55, + .width = 1, + }, +}; + /* actionfield_set */ static const struct vcap_set is0_actionfield_set[] = { [VCAP_AFS_CLASSIFICATION] = { @@ -1825,6 +2852,14 @@ static const struct vcap_set is2_actionfield_set[] = { }, }; +static const struct vcap_set es2_actionfield_set[] = { + [VCAP_AFS_BASE_TYPE] = { + .type_id = -1, + .sw_per_item = 3, + .sw_cnt = 4, + }, +}; + /* actionfield_set map */ static const struct vcap_field *is0_actionfield_set_map[] = { [VCAP_AFS_CLASSIFICATION] = is0_classification_actionfield, @@ -1836,6 +2871,10 @@ static const struct vcap_field *is2_actionfield_set_map[] = { [VCAP_AFS_BASE_TYPE] = is2_base_type_actionfield, }; +static const struct vcap_field *es2_actionfield_set_map[] = { + [VCAP_AFS_BASE_TYPE] = es2_base_type_actionfield, +}; + /* actionfield_set map size */ static int is0_actionfield_set_map_size[] = { [VCAP_AFS_CLASSIFICATION] = ARRAY_SIZE(is0_classification_actionfield), @@ -1847,6 +2886,10 @@ static int is2_actionfield_set_map_size[] = { [VCAP_AFS_BASE_TYPE] = ARRAY_SIZE(is2_base_type_actionfield), }; +static int es2_actionfield_set_map_size[] = { + [VCAP_AFS_BASE_TYPE] = ARRAY_SIZE(es2_base_type_actionfield), +}; + /* Type Groups */ static const struct vcap_typegroup is0_x12_keyfield_set_typegroups[] = { { @@ -2004,6 +3047,52 @@ static const struct vcap_typegroup is2_x1_keyfield_set_typegroups[] = { {} }; +static const struct vcap_typegroup es2_x12_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 3, + .value = 4, + }, + { + .offset = 156, + .width = 1, + .value = 0, + }, + { + .offset = 312, + .width = 2, + .value = 0, + }, + { + .offset = 468, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup es2_x6_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 2, + .value = 2, + }, + { + .offset = 156, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup es2_x3_keyfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup es2_x1_keyfield_set_typegroups[] = { + {} +}; + static const struct vcap_typegroup *is0_keyfield_set_typegroups[] = { [12] = is0_x12_keyfield_set_typegroups, [6] = is0_x6_keyfield_set_typegroups, @@ -2021,6 +3110,14 @@ static const struct vcap_typegroup *is2_keyfield_set_typegroups[] = { [13] = NULL, }; +static const struct vcap_typegroup *es2_keyfield_set_typegroups[] = { + [12] = es2_x12_keyfield_set_typegroups, + [6] = es2_x6_keyfield_set_typegroups, + [3] = es2_x3_keyfield_set_typegroups, + [1] = es2_x1_keyfield_set_typegroups, + [13] = NULL, +}; + static const struct vcap_typegroup is0_x3_actionfield_set_typegroups[] = { { .offset = 0, @@ -2086,6 +3183,29 @@ static const struct vcap_typegroup is2_x1_actionfield_set_typegroups[] = { {} }; +static const struct vcap_typegroup es2_x3_actionfield_set_typegroups[] = { + { + .offset = 0, + .width = 2, + .value = 2, + }, + { + .offset = 21, + .width = 1, + .value = 0, + }, + { + .offset = 42, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup es2_x1_actionfield_set_typegroups[] = { + {} +}; + static const struct vcap_typegroup *is0_actionfield_set_typegroups[] = { [3] = is0_x3_actionfield_set_typegroups, [2] = is0_x2_actionfield_set_typegroups, @@ -2099,6 +3219,12 @@ static const struct vcap_typegroup *is2_actionfield_set_typegroups[] = { [13] = NULL, }; +static const struct vcap_typegroup *es2_actionfield_set_typegroups[] = { + [3] = es2_x3_actionfield_set_typegroups, + [1] = es2_x1_actionfield_set_typegroups, + [13] = NULL, +}; + /* Keyfieldset names */ static const char * const vcap_keyfield_set_names[] = { [VCAP_KFS_NO_VALUE] = "(None)", @@ -2156,14 +3282,18 @@ static const char * const vcap_keyfield_names[] = { [VCAP_KF_ARP_PROTO_SPACE_OK_IS] = "ARP_PROTO_SPACE_OK_IS", [VCAP_KF_ARP_SENDER_MATCH_IS] = "ARP_SENDER_MATCH_IS", [VCAP_KF_ARP_TGT_MATCH_IS] = "ARP_TGT_MATCH_IS", + [VCAP_KF_COSID_CLS] = "COSID_CLS", [VCAP_KF_ETYPE] = "ETYPE", [VCAP_KF_ETYPE_LEN_IS] = "ETYPE_LEN_IS", [VCAP_KF_HOST_MATCH] = "HOST_MATCH", + [VCAP_KF_IF_EGR_PORT_MASK] = "IF_EGR_PORT_MASK", + [VCAP_KF_IF_EGR_PORT_MASK_RNG] = "IF_EGR_PORT_MASK_RNG", [VCAP_KF_IF_IGR_PORT] = "IF_IGR_PORT", [VCAP_KF_IF_IGR_PORT_MASK] = "IF_IGR_PORT_MASK", [VCAP_KF_IF_IGR_PORT_MASK_L3] = "IF_IGR_PORT_MASK_L3", [VCAP_KF_IF_IGR_PORT_MASK_RNG] = "IF_IGR_PORT_MASK_RNG", [VCAP_KF_IF_IGR_PORT_MASK_SEL] = "IF_IGR_PORT_MASK_SEL", + [VCAP_KF_IF_IGR_PORT_SEL] = "IF_IGR_PORT_SEL", [VCAP_KF_IP4_IS] = "IP4_IS", [VCAP_KF_IP_MC_IS] = "IP_MC_IS", [VCAP_KF_IP_PAYLOAD_5TUPLE] = "IP_PAYLOAD_5TUPLE", @@ -2183,6 +3313,7 @@ static const char * const vcap_keyfield_names[] = { [VCAP_KF_L2_SMAC] = "L2_SMAC", [VCAP_KF_L2_SNAP] = "L2_SNAP", [VCAP_KF_L3_DIP_EQ_SIP_IS] = "L3_DIP_EQ_SIP_IS", + [VCAP_KF_L3_DPL_CLS] = "L3_DPL_CLS", [VCAP_KF_L3_DSCP] = "L3_DSCP", [VCAP_KF_L3_DST_IS] = "L3_DST_IS", [VCAP_KF_L3_FRAGMENT] = "L3_FRAGMENT", @@ -2236,6 +3367,8 @@ static const char * const vcap_actionfield_names[] = { [VCAP_AF_ACL_ID] = "ACL_ID", [VCAP_AF_CLS_VID_SEL] = "CLS_VID_SEL", [VCAP_AF_CNT_ID] = "CNT_ID", + [VCAP_AF_COPY_PORT_NUM] = "COPY_PORT_NUM", + [VCAP_AF_COPY_QUEUE_NUM] = "COPY_QUEUE_NUM", [VCAP_AF_CPU_COPY_ENA] = "CPU_COPY_ENA", [VCAP_AF_CPU_QUEUE_NUM] = "CPU_QUEUE_NUM", [VCAP_AF_DEI_ENA] = "DEI_ENA", @@ -2244,7 +3377,9 @@ static const char * const vcap_actionfield_names[] = { [VCAP_AF_DP_VAL] = "DP_VAL", [VCAP_AF_DSCP_ENA] = "DSCP_ENA", [VCAP_AF_DSCP_VAL] = "DSCP_VAL", + [VCAP_AF_ES2_REW_CMD] = "ES2_REW_CMD", [VCAP_AF_FWD_KILL_ENA] = "FWD_KILL_ENA", + [VCAP_AF_FWD_MODE] = "FWD_MODE", [VCAP_AF_HIT_ME_ONCE] = "HIT_ME_ONCE", [VCAP_AF_HOST_MATCH] = "HOST_MATCH", [VCAP_AF_IGNORE_PIPELINE_CTRL] = "IGNORE_PIPELINE_CTRL", @@ -2261,6 +3396,7 @@ static const char * const vcap_actionfield_names[] = { [VCAP_AF_MATCH_ID_MASK] = "MATCH_ID_MASK", [VCAP_AF_MIRROR_ENA] = "MIRROR_ENA", [VCAP_AF_MIRROR_PROBE] = "MIRROR_PROBE", + [VCAP_AF_MIRROR_PROBE_ID] = "MIRROR_PROBE_ID", [VCAP_AF_NXT_IDX] = "NXT_IDX", [VCAP_AF_NXT_IDX_CTRL] = "NXT_IDX_CTRL", [VCAP_AF_PAG_OVERRIDE_MASK] = "PAG_OVERRIDE_MASK", @@ -2271,6 +3407,7 @@ static const char * const vcap_actionfield_names[] = { [VCAP_AF_PIPELINE_PT] = "PIPELINE_PT", [VCAP_AF_POLICE_ENA] = "POLICE_ENA", [VCAP_AF_POLICE_IDX] = "POLICE_IDX", + [VCAP_AF_POLICE_REMARK] = "POLICE_REMARK", [VCAP_AF_POLICE_VCAP_ONLY] = "POLICE_VCAP_ONLY", [VCAP_AF_PORT_MASK] = "PORT_MASK", [VCAP_AF_QOS_ENA] = "QOS_ENA", @@ -2325,11 +3462,32 @@ const struct vcap_info sparx5_vcaps[] = { .keyfield_set_typegroups = is2_keyfield_set_typegroups, .actionfield_set_typegroups = is2_actionfield_set_typegroups, }, + [VCAP_TYPE_ES2] = { + .name = "es2", + .rows = 1024, + .sw_count = 12, + .sw_width = 52, + .sticky_width = 1, + .act_width = 21, + .default_cnt = 74, + .require_cnt_dis = 0, + .version = 1, + .keyfield_set = es2_keyfield_set, + .keyfield_set_size = ARRAY_SIZE(es2_keyfield_set), + .actionfield_set = es2_actionfield_set, + .actionfield_set_size = ARRAY_SIZE(es2_actionfield_set), + .keyfield_set_map = es2_keyfield_set_map, + .keyfield_set_map_size = es2_keyfield_set_map_size, + .actionfield_set_map = es2_actionfield_set_map, + .actionfield_set_map_size = es2_actionfield_set_map_size, + .keyfield_set_typegroups = es2_keyfield_set_typegroups, + .actionfield_set_typegroups = es2_actionfield_set_typegroups, + }, }; const struct vcap_statistics sparx5_vcap_stats = { .name = "sparx5", - .count = 2, + .count = 3, .keyfield_set_names = vcap_keyfield_set_names, .actionfield_set_names = vcap_actionfield_set_names, .keyfield_names = vcap_keyfield_names, diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_debugfs.c b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_debugfs.c index 58f86dfa54bb..f3b2e58af212 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_debugfs.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_debugfs.c @@ -284,6 +284,119 @@ static void sparx5_vcap_is2_port_stickies(struct sparx5 *sparx5, out->prf(out->dst, "\n"); } +static void sparx5_vcap_es2_port_keys(struct sparx5 *sparx5, + struct vcap_admin *admin, + struct sparx5_port *port, + struct vcap_output_print *out) +{ + int lookup; + u32 value; + + out->prf(out->dst, " port[%02d] (%s): ", port->portno, + netdev_name(port->ndev)); + for (lookup = 0; lookup < admin->lookups; ++lookup) { + out->prf(out->dst, "\n Lookup %d: ", lookup); + + /* Get lookup state */ + value = spx5_rd(sparx5, EACL_VCAP_ES2_KEY_SEL(port->portno, + lookup)); + out->prf(out->dst, "\n state: "); + if (EACL_VCAP_ES2_KEY_SEL_KEY_ENA_GET(value)) + out->prf(out->dst, "on"); + else + out->prf(out->dst, "off"); + + out->prf(out->dst, "\n arp: "); + switch (EACL_VCAP_ES2_KEY_SEL_ARP_KEY_SEL_GET(value)) { + case VCAP_ES2_PS_ARP_MAC_ETYPE: + out->prf(out->dst, "mac_etype"); + break; + case VCAP_ES2_PS_ARP_ARP: + out->prf(out->dst, "arp"); + break; + } + out->prf(out->dst, "\n ipv4: "); + switch (EACL_VCAP_ES2_KEY_SEL_IP4_KEY_SEL_GET(value)) { + case VCAP_ES2_PS_IPV4_MAC_ETYPE: + out->prf(out->dst, "mac_etype"); + break; + case VCAP_ES2_PS_IPV4_IP_7TUPLE: + out->prf(out->dst, "ip_7tuple"); + break; + case VCAP_ES2_PS_IPV4_IP4_TCP_UDP_VID: + out->prf(out->dst, "ip4_tcp_udp ip4_vid"); + break; + case VCAP_ES2_PS_IPV4_IP4_TCP_UDP_OTHER: + out->prf(out->dst, "ip4_tcp_udp ip4_other"); + break; + case VCAP_ES2_PS_IPV4_IP4_VID: + out->prf(out->dst, "ip4_vid"); + break; + case VCAP_ES2_PS_IPV4_IP4_OTHER: + out->prf(out->dst, "ip4_other"); + break; + } + out->prf(out->dst, "\n ipv6: "); + switch (EACL_VCAP_ES2_KEY_SEL_IP6_KEY_SEL_GET(value)) { + case VCAP_ES2_PS_IPV6_MAC_ETYPE: + out->prf(out->dst, "mac_etype"); + break; + case VCAP_ES2_PS_IPV6_IP_7TUPLE: + out->prf(out->dst, "ip_7tuple"); + break; + case VCAP_ES2_PS_IPV6_IP_7TUPLE_VID: + out->prf(out->dst, "ip_7tuple ip6_vid"); + break; + case VCAP_ES2_PS_IPV6_IP_7TUPLE_STD: + out->prf(out->dst, "ip_7tuple ip6_std"); + break; + case VCAP_ES2_PS_IPV6_IP6_VID: + out->prf(out->dst, "ip6_vid"); + break; + case VCAP_ES2_PS_IPV6_IP6_STD: + out->prf(out->dst, "ip6_std"); + break; + case VCAP_ES2_PS_IPV6_IP4_DOWNGRADE: + out->prf(out->dst, "ip4_downgrade"); + break; + } + } + out->prf(out->dst, "\n"); +} + +static void sparx5_vcap_es2_port_stickies(struct sparx5 *sparx5, + struct vcap_admin *admin, + struct vcap_output_print *out) +{ + int lookup; + u32 value; + + out->prf(out->dst, " Sticky bits: "); + for (lookup = 0; lookup < admin->lookups; ++lookup) { + value = spx5_rd(sparx5, EACL_SEC_LOOKUP_STICKY(lookup)); + out->prf(out->dst, "\n Lookup %d: ", lookup); + if (EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP_7TUPLE_STICKY_GET(value)) + out->prf(out->dst, " ip_7tuple"); + if (EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_VID_STICKY_GET(value)) + out->prf(out->dst, " ip6_vid"); + if (EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP6_STD_STICKY_GET(value)) + out->prf(out->dst, " ip6_std"); + if (EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_TCPUDP_STICKY_GET(value)) + out->prf(out->dst, " ip4_tcp_udp"); + if (EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_VID_STICKY_GET(value)) + out->prf(out->dst, " ip4_vid"); + if (EACL_SEC_LOOKUP_STICKY_SEC_TYPE_IP4_OTHER_STICKY_GET(value)) + out->prf(out->dst, " ip4_other"); + if (EACL_SEC_LOOKUP_STICKY_SEC_TYPE_ARP_STICKY_GET(value)) + out->prf(out->dst, " arp"); + if (EACL_SEC_LOOKUP_STICKY_SEC_TYPE_MAC_ETYPE_STICKY_GET(value)) + out->prf(out->dst, " mac_etype"); + /* Clear stickies */ + spx5_wr(value, sparx5, EACL_SEC_LOOKUP_STICKY(lookup)); + } + out->prf(out->dst, "\n"); +} + /* Provide port information via a callback interface */ int sparx5_port_info(struct net_device *ndev, struct vcap_admin *admin, @@ -305,6 +418,10 @@ int sparx5_port_info(struct net_device *ndev, sparx5_vcap_is2_port_keys(sparx5, admin, port, out); sparx5_vcap_is2_port_stickies(sparx5, admin, out); break; + case VCAP_TYPE_ES2: + sparx5_vcap_es2_port_keys(sparx5, admin, port, out); + sparx5_vcap_es2_port_stickies(sparx5, admin, out); + break; default: out->prf(out->dst, " no info\n"); break; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c index 92073bfddc99..cadc4926d550 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c @@ -37,6 +37,13 @@ ANA_CL_ADV_CL_CFG_MPLS_MC_CLM_KEY_SEL_SET(_mpls_mc) | \ ANA_CL_ADV_CL_CFG_MLBS_CLM_KEY_SEL_SET(_mlbs)) +#define SPARX5_ES2_LOOKUPS 2 +#define VCAP_ES2_KEYSEL(_ena, _arp, _ipv4, _ipv6) \ + (EACL_VCAP_ES2_KEY_SEL_KEY_ENA_SET(_ena) | \ + EACL_VCAP_ES2_KEY_SEL_ARP_KEY_SEL_SET(_arp) | \ + EACL_VCAP_ES2_KEY_SEL_IP4_KEY_SEL_SET(_ipv4) | \ + EACL_VCAP_ES2_KEY_SEL_IP6_KEY_SEL_SET(_ipv6)) + static struct sparx5_vcap_inst { enum vcap_type vtype; /* type of vcap */ int vinst; /* instance number within the same type */ @@ -48,6 +55,7 @@ static struct sparx5_vcap_inst { int map_id; /* id in the super vcap block mapping (if applicable) */ int blockno; /* starting block in super vcap (if applicable) */ int blocks; /* number of blocks in super vcap (if applicable) */ + bool ingress; /* is vcap in the ingress path */ } sparx5_vcap_inst_cfg[] = { { .vtype = VCAP_TYPE_IS0, /* CLM-0 */ @@ -59,6 +67,7 @@ static struct sparx5_vcap_inst { .last_cid = SPARX5_VCAP_CID_IS0_L2 - 1, .blockno = 8, /* Maps block 8-9 */ .blocks = 2, + .ingress = true, }, { .vtype = VCAP_TYPE_IS0, /* CLM-1 */ @@ -70,6 +79,7 @@ static struct sparx5_vcap_inst { .last_cid = SPARX5_VCAP_CID_IS0_L4 - 1, .blockno = 6, /* Maps block 6-7 */ .blocks = 2, + .ingress = true, }, { .vtype = VCAP_TYPE_IS0, /* CLM-2 */ @@ -81,6 +91,7 @@ static struct sparx5_vcap_inst { .last_cid = SPARX5_VCAP_CID_IS0_MAX, .blockno = 4, /* Maps block 4-5 */ .blocks = 2, + .ingress = true, }, { .vtype = VCAP_TYPE_IS2, /* IS2-0 */ @@ -92,6 +103,7 @@ static struct sparx5_vcap_inst { .last_cid = SPARX5_VCAP_CID_IS2_L2 - 1, .blockno = 0, /* Maps block 0-1 */ .blocks = 2, + .ingress = true, }, { .vtype = VCAP_TYPE_IS2, /* IS2-1 */ @@ -103,6 +115,16 @@ static struct sparx5_vcap_inst { .last_cid = SPARX5_VCAP_CID_IS2_MAX, .blockno = 2, /* Maps block 2-3 */ .blocks = 2, + .ingress = true, + }, + { + .vtype = VCAP_TYPE_ES2, + .lookups = SPARX5_ES2_LOOKUPS, + .lookups_per_instance = SPARX5_ES2_LOOKUPS, + .first_cid = SPARX5_VCAP_CID_ES2_L0, + .last_cid = SPARX5_VCAP_CID_ES2_MAX, + .count = 12288, /* Addresses according to datasheet */ + .ingress = false, }, }; @@ -121,6 +143,14 @@ static u16 sparx5_vcap_is2_known_etypes[] = { ETH_P_IPV6, }; +/* These protocols have dedicated keysets in ES2 and a TC dissector */ +static u16 sparx5_vcap_es2_known_etypes[] = { + ETH_P_ALL, + ETH_P_ARP, + ETH_P_IP, + ETH_P_IPV6, +}; + static void sparx5_vcap_type_err(struct sparx5 *sparx5, struct vcap_admin *admin, const char *fname) @@ -139,25 +169,57 @@ static void sparx5_vcap_wait_super_update(struct sparx5 *sparx5) false, sparx5, VCAP_SUPER_CTRL); } -/* Initializing a VCAP address range: IS0 and IS2 for now */ +/* Await the ES2 VCAP completion of the current operation */ +static void sparx5_vcap_wait_es2_update(struct sparx5 *sparx5) +{ + u32 value; + + read_poll_timeout(spx5_rd, value, + !VCAP_ES2_CTRL_UPDATE_SHOT_GET(value), 500, 10000, + false, sparx5, VCAP_ES2_CTRL); +} + +/* Initializing a VCAP address range */ static void _sparx5_vcap_range_init(struct sparx5 *sparx5, struct vcap_admin *admin, u32 addr, u32 count) { u32 size = count - 1; - spx5_wr(VCAP_SUPER_CFG_MV_NUM_POS_SET(0) | - VCAP_SUPER_CFG_MV_SIZE_SET(size), - sparx5, VCAP_SUPER_CFG); - spx5_wr(VCAP_SUPER_CTRL_UPDATE_CMD_SET(VCAP_CMD_INITIALIZE) | - VCAP_SUPER_CTRL_UPDATE_ENTRY_DIS_SET(0) | - VCAP_SUPER_CTRL_UPDATE_ACTION_DIS_SET(0) | - VCAP_SUPER_CTRL_UPDATE_CNT_DIS_SET(0) | - VCAP_SUPER_CTRL_UPDATE_ADDR_SET(addr) | - VCAP_SUPER_CTRL_CLEAR_CACHE_SET(true) | - VCAP_SUPER_CTRL_UPDATE_SHOT_SET(true), - sparx5, VCAP_SUPER_CTRL); - sparx5_vcap_wait_super_update(sparx5); + switch (admin->vtype) { + case VCAP_TYPE_IS0: + case VCAP_TYPE_IS2: + spx5_wr(VCAP_SUPER_CFG_MV_NUM_POS_SET(0) | + VCAP_SUPER_CFG_MV_SIZE_SET(size), + sparx5, VCAP_SUPER_CFG); + spx5_wr(VCAP_SUPER_CTRL_UPDATE_CMD_SET(VCAP_CMD_INITIALIZE) | + VCAP_SUPER_CTRL_UPDATE_ENTRY_DIS_SET(0) | + VCAP_SUPER_CTRL_UPDATE_ACTION_DIS_SET(0) | + VCAP_SUPER_CTRL_UPDATE_CNT_DIS_SET(0) | + VCAP_SUPER_CTRL_UPDATE_ADDR_SET(addr) | + VCAP_SUPER_CTRL_CLEAR_CACHE_SET(true) | + VCAP_SUPER_CTRL_UPDATE_SHOT_SET(true), + sparx5, VCAP_SUPER_CTRL); + sparx5_vcap_wait_super_update(sparx5); + break; + case VCAP_TYPE_ES2: + spx5_wr(VCAP_ES2_CFG_MV_NUM_POS_SET(0) | + VCAP_ES2_CFG_MV_SIZE_SET(size), + sparx5, VCAP_ES2_CFG); + spx5_wr(VCAP_ES2_CTRL_UPDATE_CMD_SET(VCAP_CMD_INITIALIZE) | + VCAP_ES2_CTRL_UPDATE_ENTRY_DIS_SET(0) | + VCAP_ES2_CTRL_UPDATE_ACTION_DIS_SET(0) | + VCAP_ES2_CTRL_UPDATE_CNT_DIS_SET(0) | + VCAP_ES2_CTRL_UPDATE_ADDR_SET(addr) | + VCAP_ES2_CTRL_CLEAR_CACHE_SET(true) | + VCAP_ES2_CTRL_UPDATE_SHOT_SET(true), + sparx5, VCAP_ES2_CTRL); + sparx5_vcap_wait_es2_update(sparx5); + break; + default: + sparx5_vcap_type_err(sparx5, admin, __func__); + break; + } } /* Initializing VCAP rule data area */ @@ -198,9 +260,15 @@ static bool sparx5_vcap_is2_is_first_chain(struct vcap_rule *rule) rule->vcap_chain_id < SPARX5_VCAP_CID_IS2_L3)); } +static bool sparx5_vcap_es2_is_first_chain(struct vcap_rule *rule) +{ + return (rule->vcap_chain_id >= SPARX5_VCAP_CID_ES2_L0 && + rule->vcap_chain_id < SPARX5_VCAP_CID_ES2_L1); +} + /* Set the narrow range ingress port mask on a rule */ -static void sparx5_vcap_add_range_port_mask(struct vcap_rule *rule, - struct net_device *ndev) +static void sparx5_vcap_add_ingress_range_port_mask(struct vcap_rule *rule, + struct net_device *ndev) { struct sparx5_port *port = netdev_priv(ndev); u32 port_mask; @@ -230,6 +298,27 @@ static void sparx5_vcap_add_wide_port_mask(struct vcap_rule *rule, vcap_rule_add_key_u72(rule, VCAP_KF_IF_IGR_PORT_MASK, &port_mask); } +static void sparx5_vcap_add_egress_range_port_mask(struct vcap_rule *rule, + struct net_device *ndev) +{ + struct sparx5_port *port = netdev_priv(ndev); + u32 port_mask; + u32 range; + + /* Mask range selects: + * 0-2: Physical/Logical egress port number 0-31, 32–63, 64. + * 3-5: Virtual Interface Number 0-31, 32-63, 64. + * 6: CPU queue Number 0-7. + * + * Use physical/logical port ranges (0-2) + */ + range = port->portno / BITS_PER_TYPE(u32); + /* Port bit set to match-any */ + port_mask = ~BIT(port->portno % BITS_PER_TYPE(u32)); + vcap_rule_add_key_u32(rule, VCAP_KF_IF_EGR_PORT_MASK_RNG, range, 0xf); + vcap_rule_add_key_u32(rule, VCAP_KF_IF_EGR_PORT_MASK, 0, port_mask); +} + /* Convert IS0 chain id to vcap lookup id */ static int sparx5_vcap_is0_cid_to_lookup(int cid) { @@ -264,6 +353,17 @@ static int sparx5_vcap_is2_cid_to_lookup(int cid) return lookup; } +/* Convert ES2 chain id to vcap lookup id */ +static int sparx5_vcap_es2_cid_to_lookup(int cid) +{ + int lookup = 0; + + if (cid >= SPARX5_VCAP_CID_ES2_L1) + lookup = 1; + + return lookup; +} + /* Add ethernet type IS0 keyset to a list */ static void sparx5_vcap_is0_get_port_etype_keysets(struct vcap_keyset_list *keysetlist, @@ -435,6 +535,97 @@ static int sparx5_vcap_is2_get_port_keysets(struct net_device *ndev, return 0; } +/* Return the keysets for the vcap port IP4 traffic class configuration */ +static void +sparx5_vcap_es2_get_port_ipv4_keysets(struct vcap_keyset_list *keysetlist, + u32 value) +{ + switch (EACL_VCAP_ES2_KEY_SEL_IP4_KEY_SEL_GET(value)) { + case VCAP_ES2_PS_IPV4_MAC_ETYPE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + break; + case VCAP_ES2_PS_IPV4_IP_7TUPLE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP_7TUPLE); + break; + case VCAP_ES2_PS_IPV4_IP4_TCP_UDP_VID: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_TCP_UDP); + break; + case VCAP_ES2_PS_IPV4_IP4_TCP_UDP_OTHER: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_TCP_UDP); + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_OTHER); + break; + case VCAP_ES2_PS_IPV4_IP4_VID: + /* Not used */ + break; + case VCAP_ES2_PS_IPV4_IP4_OTHER: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_OTHER); + break; + } +} + +/* Return the list of keysets for the vcap port configuration */ +static int sparx5_vcap_es2_get_port_keysets(struct net_device *ndev, + int lookup, + struct vcap_keyset_list *keysetlist, + u16 l3_proto) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + int portno = port->portno; + u32 value; + + value = spx5_rd(sparx5, EACL_VCAP_ES2_KEY_SEL(portno, lookup)); + + /* Collect all keysets for the port in a list */ + if (l3_proto == ETH_P_ALL || l3_proto == ETH_P_ARP) { + switch (EACL_VCAP_ES2_KEY_SEL_ARP_KEY_SEL_GET(value)) { + case VCAP_ES2_PS_ARP_MAC_ETYPE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + break; + case VCAP_ES2_PS_ARP_ARP: + vcap_keyset_list_add(keysetlist, VCAP_KFS_ARP); + break; + } + } + + if (l3_proto == ETH_P_ALL || l3_proto == ETH_P_IP) + sparx5_vcap_es2_get_port_ipv4_keysets(keysetlist, value); + + if (l3_proto == ETH_P_ALL || l3_proto == ETH_P_IPV6) { + switch (EACL_VCAP_ES2_KEY_SEL_IP6_KEY_SEL_GET(value)) { + case VCAP_ES2_PS_IPV6_MAC_ETYPE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + break; + case VCAP_ES2_PS_IPV6_IP_7TUPLE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP_7TUPLE); + break; + case VCAP_ES2_PS_IPV6_IP_7TUPLE_VID: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP_7TUPLE); + break; + case VCAP_ES2_PS_IPV6_IP_7TUPLE_STD: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP_7TUPLE); + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP6_STD); + break; + case VCAP_ES2_PS_IPV6_IP6_VID: + /* Not used */ + break; + case VCAP_ES2_PS_IPV6_IP6_STD: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP6_STD); + break; + case VCAP_ES2_PS_IPV6_IP4_DOWNGRADE: + sparx5_vcap_es2_get_port_ipv4_keysets(keysetlist, + value); + break; + } + } + + if (l3_proto != ETH_P_ARP && l3_proto != ETH_P_IP && + l3_proto != ETH_P_IPV6) { + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + } + return 0; +} + /* Get the port keyset for the vcap lookup */ int sparx5_vcap_get_port_keyset(struct net_device *ndev, struct vcap_admin *admin, @@ -456,6 +647,11 @@ int sparx5_vcap_get_port_keyset(struct net_device *ndev, err = sparx5_vcap_is2_get_port_keysets(ndev, lookup, kslist, l3_proto); break; + case VCAP_TYPE_ES2: + lookup = sparx5_vcap_es2_cid_to_lookup(cid); + err = sparx5_vcap_es2_get_port_keysets(ndev, lookup, kslist, + l3_proto); + break; default: port = netdev_priv(ndev); sparx5_vcap_type_err(port->sparx5, admin, __func__); @@ -479,6 +675,10 @@ bool sparx5_vcap_is_known_etype(struct vcap_admin *admin, u16 etype) known_etypes = sparx5_vcap_is2_known_etypes; size = ARRAY_SIZE(sparx5_vcap_is2_known_etypes); break; + case VCAP_TYPE_ES2: + known_etypes = sparx5_vcap_es2_known_etypes; + size = ARRAY_SIZE(sparx5_vcap_es2_known_etypes); + break; default: return false; } @@ -519,6 +719,11 @@ sparx5_vcap_validate_keyset(struct net_device *ndev, sparx5_vcap_is2_get_port_keysets(ndev, lookup, &keysetlist, l3_proto); break; + case VCAP_TYPE_ES2: + lookup = sparx5_vcap_es2_cid_to_lookup(rule->vcap_chain_id); + sparx5_vcap_es2_get_port_keysets(ndev, lookup, &keysetlist, + l3_proto); + break; default: port = netdev_priv(ndev); sparx5_vcap_type_err(port->sparx5, admin, __func__); @@ -538,43 +743,82 @@ sparx5_vcap_validate_keyset(struct net_device *ndev, return -ENOENT; } -/* API callback used for adding default fields to a rule */ -static void sparx5_vcap_add_default_fields(struct net_device *ndev, - struct vcap_admin *admin, - struct vcap_rule *rule) +static void sparx5_vcap_ingress_add_default_fields(struct net_device *ndev, + struct vcap_admin *admin, + struct vcap_rule *rule) { const struct vcap_field *field; - struct sparx5_port *port; - bool is_first = true; + bool is_first; + /* Add ingress port mask matching the net device */ field = vcap_lookup_keyfield(rule, VCAP_KF_IF_IGR_PORT_MASK); if (field && field->width == SPX5_PORTS) sparx5_vcap_add_wide_port_mask(rule, ndev); else if (field && field->width == BITS_PER_TYPE(u32)) - sparx5_vcap_add_range_port_mask(rule, ndev); + sparx5_vcap_add_ingress_range_port_mask(rule, ndev); else pr_err("%s:%d: %s: could not add an ingress port mask for: %s\n", __func__, __LINE__, netdev_name(ndev), sparx5_vcap_keyset_name(ndev, rule->keyset)); + if (admin->vtype == VCAP_TYPE_IS0) + is_first = sparx5_vcap_is0_is_first_chain(rule); + else + is_first = sparx5_vcap_is2_is_first_chain(rule); + + /* Add key that selects the first/second lookup */ + if (is_first) + vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, + VCAP_BIT_1); + else + vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, + VCAP_BIT_0); +} + +static void sparx5_vcap_es2_add_default_fields(struct net_device *ndev, + struct vcap_admin *admin, + struct vcap_rule *rule) +{ + const struct vcap_field *field; + bool is_first; + + /* Add egress port mask matching the net device */ + field = vcap_lookup_keyfield(rule, VCAP_KF_IF_EGR_PORT_MASK); + if (field) + sparx5_vcap_add_egress_range_port_mask(rule, ndev); + + /* Add key that selects the first/second lookup */ + is_first = sparx5_vcap_es2_is_first_chain(rule); + + if (is_first) + vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, + VCAP_BIT_1); + else + vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, + VCAP_BIT_0); +} + +/* API callback used for adding default fields to a rule */ +static void sparx5_vcap_add_default_fields(struct net_device *ndev, + struct vcap_admin *admin, + struct vcap_rule *rule) +{ + struct sparx5_port *port; + /* add the lookup bit */ switch (admin->vtype) { case VCAP_TYPE_IS0: - is_first = sparx5_vcap_is0_is_first_chain(rule); - break; case VCAP_TYPE_IS2: - is_first = sparx5_vcap_is2_is_first_chain(rule); + sparx5_vcap_ingress_add_default_fields(ndev, admin, rule); + break; + case VCAP_TYPE_ES2: + sparx5_vcap_es2_add_default_fields(ndev, admin, rule); break; default: port = netdev_priv(ndev); sparx5_vcap_type_err(port->sparx5, admin, __func__); break; } - - if (is_first) - vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, VCAP_BIT_1); - else - vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, VCAP_BIT_0); } /* API callback used for erasing the vcap cache area (not the register area) */ @@ -586,21 +830,60 @@ static void sparx5_vcap_cache_erase(struct vcap_admin *admin) memset(&admin->cache.counter, 0, sizeof(admin->cache.counter)); } -/* API callback used for writing to the VCAP cache */ -static void sparx5_vcap_cache_write(struct net_device *ndev, - struct vcap_admin *admin, - enum vcap_selection sel, - u32 start, - u32 count) +static void sparx5_vcap_is0_cache_write(struct sparx5 *sparx5, + struct vcap_admin *admin, + enum vcap_selection sel, + u32 start, + u32 count) +{ + u32 *keystr, *mskstr, *actstr; + int idx; + + keystr = &admin->cache.keystream[start]; + mskstr = &admin->cache.maskstream[start]; + actstr = &admin->cache.actionstream[start]; + + switch (sel) { + case VCAP_SEL_ENTRY: + for (idx = 0; idx < count; ++idx) { + /* Avoid 'match-off' by setting value & mask */ + spx5_wr(keystr[idx] & mskstr[idx], sparx5, + VCAP_SUPER_VCAP_ENTRY_DAT(idx)); + spx5_wr(~mskstr[idx], sparx5, + VCAP_SUPER_VCAP_MASK_DAT(idx)); + } + break; + case VCAP_SEL_ACTION: + for (idx = 0; idx < count; ++idx) + spx5_wr(actstr[idx], sparx5, + VCAP_SUPER_VCAP_ACTION_DAT(idx)); + break; + case VCAP_SEL_ALL: + pr_err("%s:%d: cannot write all streams at once\n", + __func__, __LINE__); + break; + default: + break; + } + + if (sel & VCAP_SEL_COUNTER) + spx5_wr(admin->cache.counter, sparx5, + VCAP_SUPER_VCAP_CNT_DAT(0)); +} + +static void sparx5_vcap_is2_cache_write(struct sparx5 *sparx5, + struct vcap_admin *admin, + enum vcap_selection sel, + u32 start, + u32 count) { - struct sparx5_port *port = netdev_priv(ndev); - struct sparx5 *sparx5 = port->sparx5; u32 *keystr, *mskstr, *actstr; int idx; keystr = &admin->cache.keystream[start]; mskstr = &admin->cache.maskstream[start]; actstr = &admin->cache.actionstream[start]; + switch (sel) { case VCAP_SEL_ENTRY: for (idx = 0; idx < count; ++idx) { @@ -624,44 +907,99 @@ static void sparx5_vcap_cache_write(struct net_device *ndev, break; } if (sel & VCAP_SEL_COUNTER) { - switch (admin->vtype) { - case VCAP_TYPE_IS0: + start = start & 0xfff; /* counter limit */ + if (admin->vinst == 0) spx5_wr(admin->cache.counter, sparx5, - VCAP_SUPER_VCAP_CNT_DAT(0)); - break; - case VCAP_TYPE_IS2: - start = start & 0xfff; /* counter limit */ - if (admin->vinst == 0) - spx5_wr(admin->cache.counter, sparx5, - ANA_ACL_CNT_A(start)); - else - spx5_wr(admin->cache.counter, sparx5, - ANA_ACL_CNT_B(start)); - spx5_wr(admin->cache.sticky, sparx5, - VCAP_SUPER_VCAP_CNT_DAT(0)); - break; - default: - sparx5_vcap_type_err(sparx5, admin, __func__); - break; + ANA_ACL_CNT_A(start)); + else + spx5_wr(admin->cache.counter, sparx5, + ANA_ACL_CNT_B(start)); + spx5_wr(admin->cache.sticky, sparx5, + VCAP_SUPER_VCAP_CNT_DAT(0)); + } +} + +static void sparx5_vcap_es2_cache_write(struct sparx5 *sparx5, + struct vcap_admin *admin, + enum vcap_selection sel, + u32 start, + u32 count) +{ + u32 *keystr, *mskstr, *actstr; + int idx; + + keystr = &admin->cache.keystream[start]; + mskstr = &admin->cache.maskstream[start]; + actstr = &admin->cache.actionstream[start]; + + switch (sel) { + case VCAP_SEL_ENTRY: + for (idx = 0; idx < count; ++idx) { + /* Avoid 'match-off' by setting value & mask */ + spx5_wr(keystr[idx] & mskstr[idx], sparx5, + VCAP_ES2_VCAP_ENTRY_DAT(idx)); + spx5_wr(~mskstr[idx], sparx5, + VCAP_ES2_VCAP_MASK_DAT(idx)); } + break; + case VCAP_SEL_ACTION: + for (idx = 0; idx < count; ++idx) + spx5_wr(actstr[idx], sparx5, + VCAP_ES2_VCAP_ACTION_DAT(idx)); + break; + case VCAP_SEL_ALL: + pr_err("%s:%d: cannot write all streams at once\n", + __func__, __LINE__); + break; + default: + break; + } + if (sel & VCAP_SEL_COUNTER) { + start = start & 0x7ff; /* counter limit */ + spx5_wr(admin->cache.counter, sparx5, EACL_ES2_CNT(start)); + spx5_wr(admin->cache.sticky, sparx5, VCAP_ES2_VCAP_CNT_DAT(0)); } } -/* API callback used for reading from the VCAP into the VCAP cache */ -static void sparx5_vcap_cache_read(struct net_device *ndev, - struct vcap_admin *admin, - enum vcap_selection sel, - u32 start, - u32 count) +/* API callback used for writing to the VCAP cache */ +static void sparx5_vcap_cache_write(struct net_device *ndev, + struct vcap_admin *admin, + enum vcap_selection sel, + u32 start, + u32 count) { struct sparx5_port *port = netdev_priv(ndev); struct sparx5 *sparx5 = port->sparx5; + + switch (admin->vtype) { + case VCAP_TYPE_IS0: + sparx5_vcap_is0_cache_write(sparx5, admin, sel, start, count); + break; + case VCAP_TYPE_IS2: + sparx5_vcap_is2_cache_write(sparx5, admin, sel, start, count); + break; + case VCAP_TYPE_ES2: + sparx5_vcap_es2_cache_write(sparx5, admin, sel, start, count); + break; + default: + sparx5_vcap_type_err(sparx5, admin, __func__); + break; + } +} + +static void sparx5_vcap_is0_cache_read(struct sparx5 *sparx5, + struct vcap_admin *admin, + enum vcap_selection sel, + u32 start, + u32 count) +{ u32 *keystr, *mskstr, *actstr; int idx; keystr = &admin->cache.keystream[start]; mskstr = &admin->cache.maskstream[start]; actstr = &admin->cache.actionstream[start]; + if (sel & VCAP_SEL_ENTRY) { for (idx = 0; idx < count; ++idx) { keystr[idx] = spx5_rd(sparx5, @@ -670,35 +1008,120 @@ static void sparx5_vcap_cache_read(struct net_device *ndev, VCAP_SUPER_VCAP_MASK_DAT(idx)); } } - if (sel & VCAP_SEL_ACTION) { + + if (sel & VCAP_SEL_ACTION) for (idx = 0; idx < count; ++idx) actstr[idx] = spx5_rd(sparx5, VCAP_SUPER_VCAP_ACTION_DAT(idx)); + + if (sel & VCAP_SEL_COUNTER) { + admin->cache.counter = + spx5_rd(sparx5, VCAP_SUPER_VCAP_CNT_DAT(0)); + admin->cache.sticky = + spx5_rd(sparx5, VCAP_SUPER_VCAP_CNT_DAT(0)); + } +} + +static void sparx5_vcap_is2_cache_read(struct sparx5 *sparx5, + struct vcap_admin *admin, + enum vcap_selection sel, + u32 start, + u32 count) +{ + u32 *keystr, *mskstr, *actstr; + int idx; + + keystr = &admin->cache.keystream[start]; + mskstr = &admin->cache.maskstream[start]; + actstr = &admin->cache.actionstream[start]; + + if (sel & VCAP_SEL_ENTRY) { + for (idx = 0; idx < count; ++idx) { + keystr[idx] = spx5_rd(sparx5, + VCAP_SUPER_VCAP_ENTRY_DAT(idx)); + mskstr[idx] = ~spx5_rd(sparx5, + VCAP_SUPER_VCAP_MASK_DAT(idx)); + } } + + if (sel & VCAP_SEL_ACTION) + for (idx = 0; idx < count; ++idx) + actstr[idx] = spx5_rd(sparx5, + VCAP_SUPER_VCAP_ACTION_DAT(idx)); + if (sel & VCAP_SEL_COUNTER) { - switch (admin->vtype) { - case VCAP_TYPE_IS0: + start = start & 0xfff; /* counter limit */ + if (admin->vinst == 0) admin->cache.counter = - spx5_rd(sparx5, VCAP_SUPER_VCAP_CNT_DAT(0)); - admin->cache.sticky = - spx5_rd(sparx5, VCAP_SUPER_VCAP_CNT_DAT(0)); - break; - case VCAP_TYPE_IS2: - start = start & 0xfff; /* counter limit */ - if (admin->vinst == 0) - admin->cache.counter = - spx5_rd(sparx5, ANA_ACL_CNT_A(start)); - else - admin->cache.counter = - spx5_rd(sparx5, ANA_ACL_CNT_B(start)); - admin->cache.sticky = - spx5_rd(sparx5, VCAP_SUPER_VCAP_CNT_DAT(0)); - break; - default: - sparx5_vcap_type_err(sparx5, admin, __func__); - break; + spx5_rd(sparx5, ANA_ACL_CNT_A(start)); + else + admin->cache.counter = + spx5_rd(sparx5, ANA_ACL_CNT_B(start)); + admin->cache.sticky = + spx5_rd(sparx5, VCAP_SUPER_VCAP_CNT_DAT(0)); + } +} + +static void sparx5_vcap_es2_cache_read(struct sparx5 *sparx5, + struct vcap_admin *admin, + enum vcap_selection sel, + u32 start, + u32 count) +{ + u32 *keystr, *mskstr, *actstr; + int idx; + + keystr = &admin->cache.keystream[start]; + mskstr = &admin->cache.maskstream[start]; + actstr = &admin->cache.actionstream[start]; + + if (sel & VCAP_SEL_ENTRY) { + for (idx = 0; idx < count; ++idx) { + keystr[idx] = + spx5_rd(sparx5, VCAP_ES2_VCAP_ENTRY_DAT(idx)); + mskstr[idx] = + ~spx5_rd(sparx5, VCAP_ES2_VCAP_MASK_DAT(idx)); } } + + if (sel & VCAP_SEL_ACTION) + for (idx = 0; idx < count; ++idx) + actstr[idx] = + spx5_rd(sparx5, VCAP_ES2_VCAP_ACTION_DAT(idx)); + + if (sel & VCAP_SEL_COUNTER) { + start = start & 0x7ff; /* counter limit */ + admin->cache.counter = + spx5_rd(sparx5, EACL_ES2_CNT(start)); + admin->cache.sticky = + spx5_rd(sparx5, VCAP_ES2_VCAP_CNT_DAT(0)); + } +} + +/* API callback used for reading from the VCAP into the VCAP cache */ +static void sparx5_vcap_cache_read(struct net_device *ndev, + struct vcap_admin *admin, + enum vcap_selection sel, + u32 start, + u32 count) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + + switch (admin->vtype) { + case VCAP_TYPE_IS0: + sparx5_vcap_is0_cache_read(sparx5, admin, sel, start, count); + break; + case VCAP_TYPE_IS2: + sparx5_vcap_is2_cache_read(sparx5, admin, sel, start, count); + break; + case VCAP_TYPE_ES2: + sparx5_vcap_es2_cache_read(sparx5, admin, sel, start, count); + break; + default: + sparx5_vcap_type_err(sparx5, admin, __func__); + break; + } } /* API callback used for initializing a VCAP address range */ @@ -712,16 +1135,12 @@ static void sparx5_vcap_range_init(struct net_device *ndev, _sparx5_vcap_range_init(sparx5, admin, addr, count); } -/* API callback used for updating the VCAP cache, IS0 and IS2 for now */ -static void sparx5_vcap_update(struct net_device *ndev, - struct vcap_admin *admin, enum vcap_command cmd, - enum vcap_selection sel, u32 addr) +static void sparx5_vcap_super_update(struct sparx5 *sparx5, + enum vcap_command cmd, + enum vcap_selection sel, u32 addr) { - struct sparx5_port *port = netdev_priv(ndev); - struct sparx5 *sparx5 = port->sparx5; - bool clear; + bool clear = (cmd == VCAP_CMD_INITIALIZE); - clear = (cmd == VCAP_CMD_INITIALIZE); spx5_wr(VCAP_SUPER_CFG_MV_NUM_POS_SET(0) | VCAP_SUPER_CFG_MV_SIZE_SET(0), sparx5, VCAP_SUPER_CFG); spx5_wr(VCAP_SUPER_CTRL_UPDATE_CMD_SET(cmd) | @@ -735,6 +1154,87 @@ static void sparx5_vcap_update(struct net_device *ndev, sparx5_vcap_wait_super_update(sparx5); } +static void sparx5_vcap_es2_update(struct sparx5 *sparx5, + enum vcap_command cmd, + enum vcap_selection sel, u32 addr) +{ + bool clear = (cmd == VCAP_CMD_INITIALIZE); + + spx5_wr(VCAP_ES2_CFG_MV_NUM_POS_SET(0) | + VCAP_ES2_CFG_MV_SIZE_SET(0), sparx5, VCAP_ES2_CFG); + spx5_wr(VCAP_ES2_CTRL_UPDATE_CMD_SET(cmd) | + VCAP_ES2_CTRL_UPDATE_ENTRY_DIS_SET((VCAP_SEL_ENTRY & sel) == 0) | + VCAP_ES2_CTRL_UPDATE_ACTION_DIS_SET((VCAP_SEL_ACTION & sel) == 0) | + VCAP_ES2_CTRL_UPDATE_CNT_DIS_SET((VCAP_SEL_COUNTER & sel) == 0) | + VCAP_ES2_CTRL_UPDATE_ADDR_SET(addr) | + VCAP_ES2_CTRL_CLEAR_CACHE_SET(clear) | + VCAP_ES2_CTRL_UPDATE_SHOT_SET(true), + sparx5, VCAP_ES2_CTRL); + sparx5_vcap_wait_es2_update(sparx5); +} + +/* API callback used for updating the VCAP cache */ +static void sparx5_vcap_update(struct net_device *ndev, + struct vcap_admin *admin, enum vcap_command cmd, + enum vcap_selection sel, u32 addr) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + + switch (admin->vtype) { + case VCAP_TYPE_IS0: + case VCAP_TYPE_IS2: + sparx5_vcap_super_update(sparx5, cmd, sel, addr); + break; + case VCAP_TYPE_ES2: + sparx5_vcap_es2_update(sparx5, cmd, sel, addr); + break; + default: + sparx5_vcap_type_err(sparx5, admin, __func__); + break; + } +} + +static void sparx5_vcap_super_move(struct sparx5 *sparx5, + u32 addr, + enum vcap_command cmd, + u16 mv_num_pos, + u16 mv_size) +{ + spx5_wr(VCAP_SUPER_CFG_MV_NUM_POS_SET(mv_num_pos) | + VCAP_SUPER_CFG_MV_SIZE_SET(mv_size), + sparx5, VCAP_SUPER_CFG); + spx5_wr(VCAP_SUPER_CTRL_UPDATE_CMD_SET(cmd) | + VCAP_SUPER_CTRL_UPDATE_ENTRY_DIS_SET(0) | + VCAP_SUPER_CTRL_UPDATE_ACTION_DIS_SET(0) | + VCAP_SUPER_CTRL_UPDATE_CNT_DIS_SET(0) | + VCAP_SUPER_CTRL_UPDATE_ADDR_SET(addr) | + VCAP_SUPER_CTRL_CLEAR_CACHE_SET(false) | + VCAP_SUPER_CTRL_UPDATE_SHOT_SET(true), + sparx5, VCAP_SUPER_CTRL); + sparx5_vcap_wait_super_update(sparx5); +} + +static void sparx5_vcap_es2_move(struct sparx5 *sparx5, + u32 addr, + enum vcap_command cmd, + u16 mv_num_pos, + u16 mv_size) +{ + spx5_wr(VCAP_ES2_CFG_MV_NUM_POS_SET(mv_num_pos) | + VCAP_ES2_CFG_MV_SIZE_SET(mv_size), + sparx5, VCAP_ES2_CFG); + spx5_wr(VCAP_ES2_CTRL_UPDATE_CMD_SET(cmd) | + VCAP_ES2_CTRL_UPDATE_ENTRY_DIS_SET(0) | + VCAP_ES2_CTRL_UPDATE_ACTION_DIS_SET(0) | + VCAP_ES2_CTRL_UPDATE_CNT_DIS_SET(0) | + VCAP_ES2_CTRL_UPDATE_ADDR_SET(addr) | + VCAP_ES2_CTRL_CLEAR_CACHE_SET(false) | + VCAP_ES2_CTRL_UPDATE_SHOT_SET(true), + sparx5, VCAP_ES2_CTRL); + sparx5_vcap_wait_es2_update(sparx5); +} + /* API callback used for moving a block of rules in the VCAP */ static void sparx5_vcap_move(struct net_device *ndev, struct vcap_admin *admin, u32 addr, int offset, int count) @@ -753,18 +1253,19 @@ static void sparx5_vcap_move(struct net_device *ndev, struct vcap_admin *admin, mv_num_pos = -offset - 1; cmd = VCAP_CMD_MOVE_UP; } - spx5_wr(VCAP_SUPER_CFG_MV_NUM_POS_SET(mv_num_pos) | - VCAP_SUPER_CFG_MV_SIZE_SET(mv_size), - sparx5, VCAP_SUPER_CFG); - spx5_wr(VCAP_SUPER_CTRL_UPDATE_CMD_SET(cmd) | - VCAP_SUPER_CTRL_UPDATE_ENTRY_DIS_SET(0) | - VCAP_SUPER_CTRL_UPDATE_ACTION_DIS_SET(0) | - VCAP_SUPER_CTRL_UPDATE_CNT_DIS_SET(0) | - VCAP_SUPER_CTRL_UPDATE_ADDR_SET(addr) | - VCAP_SUPER_CTRL_CLEAR_CACHE_SET(false) | - VCAP_SUPER_CTRL_UPDATE_SHOT_SET(true), - sparx5, VCAP_SUPER_CTRL); - sparx5_vcap_wait_super_update(sparx5); + + switch (admin->vtype) { + case VCAP_TYPE_IS0: + case VCAP_TYPE_IS2: + sparx5_vcap_super_move(sparx5, addr, cmd, mv_num_pos, mv_size); + break; + case VCAP_TYPE_ES2: + sparx5_vcap_es2_move(sparx5, addr, cmd, mv_num_pos, mv_size); + break; + default: + sparx5_vcap_type_err(sparx5, admin, __func__); + break; + } } static struct vcap_operations sparx5_vcap_ops = { @@ -832,6 +1333,22 @@ static void sparx5_vcap_is2_port_key_selection(struct sparx5 *sparx5, ANA_ACL_VCAP_S2_CFG(portno)); } +/* Enable ES2 lookups per port and set the keyset generation */ +static void sparx5_vcap_es2_port_key_selection(struct sparx5 *sparx5, + struct vcap_admin *admin) +{ + int portno, lookup; + u32 keysel; + + keysel = VCAP_ES2_KEYSEL(true, VCAP_ES2_PS_ARP_MAC_ETYPE, + VCAP_ES2_PS_IPV4_IP4_TCP_UDP_OTHER, + VCAP_ES2_PS_IPV6_IP_7TUPLE); + for (lookup = 0; lookup < admin->lookups; ++lookup) + for (portno = 0; portno < SPX5_PORTS; ++portno) + spx5_wr(keysel, sparx5, + EACL_VCAP_ES2_KEY_SEL(portno, lookup)); +} + /* Enable lookups per port and set the keyset generation */ static void sparx5_vcap_port_key_selection(struct sparx5 *sparx5, struct vcap_admin *admin) @@ -843,6 +1360,9 @@ static void sparx5_vcap_port_key_selection(struct sparx5 *sparx5, case VCAP_TYPE_IS2: sparx5_vcap_is2_port_key_selection(sparx5, admin); break; + case VCAP_TYPE_ES2: + sparx5_vcap_es2_port_key_selection(sparx5, admin); + break; default: sparx5_vcap_type_err(sparx5, admin, __func__); break; @@ -871,6 +1391,14 @@ static void sparx5_vcap_port_key_deselection(struct sparx5 *sparx5, sparx5, ANA_ACL_VCAP_S2_CFG(portno)); break; + case VCAP_TYPE_ES2: + for (lookup = 0; lookup < admin->lookups; ++lookup) + for (portno = 0; portno < SPX5_PORTS; ++portno) + spx5_rmw(EACL_VCAP_ES2_KEY_SEL_KEY_ENA_SET(0), + EACL_VCAP_ES2_KEY_SEL_KEY_ENA, + sparx5, + EACL_VCAP_ES2_KEY_SEL(portno, lookup)); + break; default: sparx5_vcap_type_err(sparx5, admin, __func__); break; @@ -904,6 +1432,7 @@ sparx5_vcap_admin_alloc(struct sparx5 *sparx5, struct vcap_control *ctrl, mutex_init(&admin->lock); admin->vtype = cfg->vtype; admin->vinst = cfg->vinst; + admin->ingress = cfg->ingress; admin->lookups = cfg->lookups; admin->lookups_per_instance = cfg->lookups_per_instance; admin->first_cid = cfg->first_cid; @@ -927,22 +1456,43 @@ static void sparx5_vcap_block_alloc(struct sparx5 *sparx5, struct vcap_admin *admin, const struct sparx5_vcap_inst *cfg) { - int idx; + int idx, cores; - /* Super VCAP block mapping and address configuration. Block 0 - * is assigned addresses 0 through 3071, block 1 is assigned - * addresses 3072 though 6143, and so on. - */ - for (idx = cfg->blockno; idx < cfg->blockno + cfg->blocks; ++idx) { - spx5_wr(VCAP_SUPER_IDX_CORE_IDX_SET(idx), sparx5, - VCAP_SUPER_IDX); - spx5_wr(VCAP_SUPER_MAP_CORE_MAP_SET(cfg->map_id), sparx5, - VCAP_SUPER_MAP); - } - admin->first_valid_addr = cfg->blockno * SUPER_VCAP_BLK_SIZE; - admin->last_used_addr = admin->first_valid_addr + - cfg->blocks * SUPER_VCAP_BLK_SIZE; - admin->last_valid_addr = admin->last_used_addr - 1; + switch (admin->vtype) { + case VCAP_TYPE_IS0: + case VCAP_TYPE_IS2: + /* Super VCAP block mapping and address configuration. Block 0 + * is assigned addresses 0 through 3071, block 1 is assigned + * addresses 3072 though 6143, and so on. + */ + for (idx = cfg->blockno; idx < cfg->blockno + cfg->blocks; + ++idx) { + spx5_wr(VCAP_SUPER_IDX_CORE_IDX_SET(idx), sparx5, + VCAP_SUPER_IDX); + spx5_wr(VCAP_SUPER_MAP_CORE_MAP_SET(cfg->map_id), + sparx5, VCAP_SUPER_MAP); + } + admin->first_valid_addr = cfg->blockno * SUPER_VCAP_BLK_SIZE; + admin->last_used_addr = admin->first_valid_addr + + cfg->blocks * SUPER_VCAP_BLK_SIZE; + admin->last_valid_addr = admin->last_used_addr - 1; + break; + case VCAP_TYPE_ES2: + admin->first_valid_addr = 0; + admin->last_used_addr = cfg->count; + admin->last_valid_addr = cfg->count - 1; + cores = spx5_rd(sparx5, VCAP_ES2_CORE_CNT); + for (idx = 0; idx < cores; ++idx) { + spx5_wr(VCAP_ES2_IDX_CORE_IDX_SET(idx), sparx5, + VCAP_ES2_IDX); + spx5_wr(VCAP_ES2_MAP_CORE_MAP_SET(1), sparx5, + VCAP_ES2_MAP); + } + break; + default: + sparx5_vcap_type_err(sparx5, admin, __func__); + break; + } } /* Allocate a vcap control and vcap instances and configure the system */ diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.h b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.h index aabdf4355103..46a08d5aff3d 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.h @@ -32,6 +32,11 @@ #define SPARX5_VCAP_CID_IS2_MAX \ (VCAP_CID_INGRESS_STAGE2_L3 + VCAP_CID_LOOKUP_SIZE - 1) /* IS2 Max */ +#define SPARX5_VCAP_CID_ES2_L0 VCAP_CID_EGRESS_STAGE2_L0 /* ES2 lookup 0 */ +#define SPARX5_VCAP_CID_ES2_L1 VCAP_CID_EGRESS_STAGE2_L1 /* ES2 lookup 1 */ +#define SPARX5_VCAP_CID_ES2_MAX \ + (VCAP_CID_EGRESS_STAGE2_L1 + VCAP_CID_LOOKUP_SIZE - 1) /* ES2 Max */ + /* IS0 port keyset selection control */ /* IS0 ethernet, IPv4, IPv6 traffic type keyset generation */ @@ -129,6 +134,35 @@ enum vcap_is2_port_sel_arp { VCAP_IS2_PS_ARP_ARP, }; +/* ES2 port keyset selection control */ + +/* ES2 IPv4 traffic type keyset generation */ +enum vcap_es2_port_sel_ipv4 { + VCAP_ES2_PS_IPV4_MAC_ETYPE, + VCAP_ES2_PS_IPV4_IP_7TUPLE, + VCAP_ES2_PS_IPV4_IP4_TCP_UDP_VID, + VCAP_ES2_PS_IPV4_IP4_TCP_UDP_OTHER, + VCAP_ES2_PS_IPV4_IP4_VID, + VCAP_ES2_PS_IPV4_IP4_OTHER, +}; + +/* ES2 IPv6 traffic type keyset generation */ +enum vcap_es2_port_sel_ipv6 { + VCAP_ES2_PS_IPV6_MAC_ETYPE, + VCAP_ES2_PS_IPV6_IP_7TUPLE, + VCAP_ES2_PS_IPV6_IP_7TUPLE_VID, + VCAP_ES2_PS_IPV6_IP_7TUPLE_STD, + VCAP_ES2_PS_IPV6_IP6_VID, + VCAP_ES2_PS_IPV6_IP6_STD, + VCAP_ES2_PS_IPV6_IP4_DOWNGRADE, +}; + +/* ES2 ARP traffic type keyset generation */ +enum vcap_es2_port_sel_arp { + VCAP_ES2_PS_ARP_MAC_ETYPE, + VCAP_ES2_PS_ARP_ARP, +}; + /* Get the port keyset for the vcap lookup */ int sparx5_vcap_get_port_keyset(struct net_device *ndev, struct vcap_admin *admin, diff --git a/drivers/net/ethernet/microchip/vcap/Makefile b/drivers/net/ethernet/microchip/vcap/Makefile index 0adb8f5a8735..c86f20e6491f 100644 --- a/drivers/net/ethernet/microchip/vcap/Makefile +++ b/drivers/net/ethernet/microchip/vcap/Makefile @@ -7,4 +7,4 @@ obj-$(CONFIG_VCAP) += vcap.o obj-$(CONFIG_VCAP_KUNIT_TEST) += vcap_model_kunit.o vcap-$(CONFIG_DEBUG_FS) += vcap_api_debugfs.o -vcap-y += vcap_api.o +vcap-y += vcap_api.o vcap_tc.o diff --git a/drivers/net/ethernet/microchip/vcap/vcap_ag_api.h b/drivers/net/ethernet/microchip/vcap/vcap_ag_api.h index 962383f20f1b..9c6766c4b75d 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_ag_api.h +++ b/drivers/net/ethernet/microchip/vcap/vcap_ag_api.h @@ -1,10 +1,10 @@ /* SPDX-License-Identifier: BSD-3-Clause */ -/* Copyright (C) 2022 Microchip Technology Inc. and its subsidiaries. +/* Copyright (C) 2023 Microchip Technology Inc. and its subsidiaries. * Microchip VCAP API */ -/* This file is autogenerated by cml-utils 2022-12-06 09:49:28 +0100. - * Commit ID: cd9451f1b9d8cafa58f845de66a6e373658019ef +/* This file is autogenerated by cml-utils 2023-01-17 16:52:16 +0100. + * Commit ID: 229ec79be5df142c1f335a01d0e63232d4feb2ba */ #ifndef __VCAP_AG_API__ @@ -276,7 +276,8 @@ enum vcap_keyfield_set { * Select the mode of the Generic Index * VCAP_KF_LOOKUP_PAG: W8, sparx5: is2, lan966x: is2 * Classified Policy Association Group: chains rules from IS1/CLM to IS2 - * VCAP_KF_MIRROR_ENA: *** No docstring *** + * VCAP_KF_MIRROR_PROBE: W2, sparx5: es2 + * Identifies frame copies generated as a result of mirroring * VCAP_KF_OAM_CCM_CNTS_EQ0: W1, sparx5: is2/es2, lan966x: is2 * Dual-ended loss measurement counters in CCM frames are all zero * VCAP_KF_OAM_DETECTED: W1, lan966x: is2 @@ -407,7 +408,7 @@ enum vcap_key_field { VCAP_KF_LOOKUP_GEN_IDX, VCAP_KF_LOOKUP_GEN_IDX_SEL, VCAP_KF_LOOKUP_PAG, - VCAP_KF_MIRROR_ENA, + VCAP_KF_MIRROR_PROBE, VCAP_KF_OAM_CCM_CNTS_EQ0, VCAP_KF_OAM_DETECTED, VCAP_KF_OAM_FLAGS, diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.c b/drivers/net/ethernet/microchip/vcap/vcap_api.c index 83223c4770f2..6307d59f23da 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api.c @@ -1601,15 +1601,17 @@ struct vcap_admin *vcap_find_admin(struct vcap_control *vctrl, int cid) } EXPORT_SYMBOL_GPL(vcap_find_admin); -/* Is this the last admin instance ordered by chain id */ +/* Is this the last admin instance ordered by chain id and direction */ static bool vcap_admin_is_last(struct vcap_control *vctrl, - struct vcap_admin *admin) + struct vcap_admin *admin, + bool ingress) { struct vcap_admin *iter, *last = NULL; int max_cid = 0; list_for_each_entry(iter, &vctrl->list, list) { - if (iter->first_cid > max_cid) { + if (iter->first_cid > max_cid && + iter->ingress == ingress) { last = iter; max_cid = iter->first_cid; } @@ -2753,7 +2755,7 @@ int vcap_rule_get_key_u32(struct vcap_rule *rule, enum vcap_key_field key, EXPORT_SYMBOL_GPL(vcap_rule_get_key_u32); /* Find a client action field in a rule */ -static struct vcap_client_actionfield * +struct vcap_client_actionfield * vcap_find_actionfield(struct vcap_rule *rule, enum vcap_action_field act) { struct vcap_rule_internal *ri = (struct vcap_rule_internal *)rule; @@ -2764,6 +2766,7 @@ vcap_find_actionfield(struct vcap_rule *rule, enum vcap_action_field act) return caf; return NULL; } +EXPORT_SYMBOL_GPL(vcap_find_actionfield); /* Check if the actionfield is already in the rule */ static bool vcap_actionfield_unique(struct vcap_rule *rule, @@ -3177,7 +3180,7 @@ int vcap_enable_lookups(struct vcap_control *vctrl, struct net_device *ndev, EXPORT_SYMBOL_GPL(vcap_enable_lookups); /* Is this chain id the last lookup of all VCAPs */ -bool vcap_is_last_chain(struct vcap_control *vctrl, int cid) +bool vcap_is_last_chain(struct vcap_control *vctrl, int cid, bool ingress) { struct vcap_admin *admin; int lookup; @@ -3189,7 +3192,7 @@ bool vcap_is_last_chain(struct vcap_control *vctrl, int cid) if (!admin) return false; - if (!vcap_admin_is_last(vctrl, admin)) + if (!vcap_admin_is_last(vctrl, admin, ingress)) return false; /* This must be the last lookup in this VCAP type */ @@ -3264,6 +3267,28 @@ static int vcap_rule_get_key(struct vcap_rule *rule, return 0; } +/* Find a keyset having the same size as the provided rule, where the keyset + * does not have a type id. + */ +static int vcap_rule_get_untyped_keyset(struct vcap_rule_internal *ri, + struct vcap_keyset_list *matches) +{ + struct vcap_control *vctrl = ri->vctrl; + enum vcap_type vt = ri->admin->vtype; + const struct vcap_set *keyfield_set; + int idx; + + keyfield_set = vctrl->vcaps[vt].keyfield_set; + for (idx = 0; idx < vctrl->vcaps[vt].keyfield_set_size; ++idx) { + if (keyfield_set[idx].sw_per_item == ri->keyset_sw && + keyfield_set[idx].type_id == (u8)-1) { + vcap_keyset_list_add(matches, idx); + return 0; + } + } + return -EINVAL; +} + /* Get the keysets that matches the rule key type/mask */ int vcap_rule_get_keysets(struct vcap_rule_internal *ri, struct vcap_keyset_list *matches) @@ -3277,7 +3302,7 @@ int vcap_rule_get_keysets(struct vcap_rule_internal *ri, err = vcap_rule_get_key(&ri->data, VCAP_KF_TYPE, &kf); if (err) - return err; + return vcap_rule_get_untyped_keyset(ri, matches); if (kf.ctrl.type == VCAP_FIELD_BIT) { value = kf.data.u1.value; diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.h b/drivers/net/ethernet/microchip/vcap/vcap_api.h index 40491116b0a9..62db270f65af 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api.h +++ b/drivers/net/ethernet/microchip/vcap/vcap_api.h @@ -176,6 +176,7 @@ struct vcap_admin { int first_valid_addr; /* bottom of address range to be used */ int last_used_addr; /* address of lowest added rule */ bool w32be; /* vcap uses "32bit-word big-endian" encoding */ + bool ingress; /* chain traffic direction */ struct vcap_cache_data cache; /* encoded rule data */ }; diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_client.h b/drivers/net/ethernet/microchip/vcap/vcap_api_client.h index 69ea230ba8a1..417af9754bcc 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_client.h +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_client.h @@ -222,7 +222,7 @@ int vcap_chain_offset(struct vcap_control *vctrl, int from_cid, int to_cid); /* Is the next chain id in the following lookup, possible in another VCAP */ bool vcap_is_next_lookup(struct vcap_control *vctrl, int cur_cid, int next_cid); /* Is this chain id the last lookup of all VCAPs */ -bool vcap_is_last_chain(struct vcap_control *vctrl, int cid); +bool vcap_is_last_chain(struct vcap_control *vctrl, int cid, bool ingress); /* Provide all rules via a callback interface */ int vcap_rule_iter(struct vcap_control *vctrl, int (*callback)(void *, struct vcap_rule *), void *arg); @@ -268,4 +268,7 @@ int vcap_rule_mod_action_u32(struct vcap_rule *rule, /* Get a 32 bit key field value and mask from the rule */ int vcap_rule_get_key_u32(struct vcap_rule *rule, enum vcap_key_field key, u32 *value, u32 *mask); + +struct vcap_client_actionfield * +vcap_find_actionfield(struct vcap_rule *rule, enum vcap_action_field act); #endif /* __VCAP_API_CLIENT__ */ diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.c b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.c index d49b1cf7712f..c2c3397c5898 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.c @@ -44,11 +44,14 @@ static void vcap_debugfs_show_rule_keyfield(struct vcap_control *vctrl, out->prf(out->dst, "%pI4h/%pI4h", &data->u32.value, &data->u32.mask); } else if (key == VCAP_KF_ETYPE || - key == VCAP_KF_IF_IGR_PORT_MASK) { + key == VCAP_KF_IF_IGR_PORT_MASK || + key == VCAP_KF_IF_EGR_PORT_MASK) { hex = true; } else { u32 fmsk = (1 << keyfield[key].width) - 1; + if (keyfield[key].width == 32) + fmsk = ~0; out->prf(out->dst, "%u/%u", data->u32.value & fmsk, data->u32.mask & fmsk); } @@ -277,6 +280,7 @@ static void vcap_show_admin_info(struct vcap_control *vctrl, out->prf(out->dst, "version: %d\n", vcap->version); out->prf(out->dst, "vtype: %d\n", admin->vtype); out->prf(out->dst, "vinst: %d\n", admin->vinst); + out->prf(out->dst, "ingress: %d\n", admin->ingress); out->prf(out->dst, "first_cid: %d\n", admin->first_cid); out->prf(out->dst, "last_cid: %d\n", admin->last_cid); out->prf(out->dst, "lookups: %d\n", admin->lookups); diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c index cbf7e0f110b8..b9c1c9d5eee8 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c @@ -389,6 +389,7 @@ static const char * const test_admin_info_expect[] = { "version: 1\n", "vtype: 2\n", "vinst: 0\n", + "ingress: 1\n", "first_cid: 10000\n", "last_cid: 19999\n", "lookups: 4\n", @@ -407,6 +408,7 @@ static void vcap_api_show_admin_test(struct kunit *test) .last_valid_addr = 3071, .first_valid_addr = 0, .last_used_addr = 794, + .ingress = true, }; struct vcap_output_print out = { .prf = (void *)test_prf, @@ -435,6 +437,7 @@ static const char * const test_admin_expect[] = { "version: 1\n", "vtype: 2\n", "vinst: 0\n", + "ingress: 1\n", "first_cid: 8000000\n", "last_cid: 8199999\n", "lookups: 4\n", @@ -496,6 +499,7 @@ static void vcap_api_show_admin_rule_test(struct kunit *test) .last_valid_addr = 3071, .first_valid_addr = 0, .last_used_addr = 794, + .ingress = true, .cache = { .keystream = keydata, .maskstream = mskdata, diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c index a31cd08e3752..b2753aac8ad2 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c @@ -2145,6 +2145,71 @@ static void vcap_api_filter_keylist_test(struct kunit *test) KUNIT_EXPECT_EQ(test, 26, idx); } +static void vcap_api_rule_chain_path_test(struct kunit *test) +{ + struct vcap_admin admin1 = { + .vtype = VCAP_TYPE_IS0, + .vinst = 0, + .first_cid = 1000000, + .last_cid = 1199999, + .lookups = 6, + .lookups_per_instance = 2, + }; + struct vcap_enabled_port eport3 = { + .ndev = &test_netdev, + .cookie = 0x100, + .src_cid = 0, + .dst_cid = 1000000, + }; + struct vcap_enabled_port eport2 = { + .ndev = &test_netdev, + .cookie = 0x200, + .src_cid = 1000000, + .dst_cid = 1100000, + }; + struct vcap_enabled_port eport1 = { + .ndev = &test_netdev, + .cookie = 0x300, + .src_cid = 1100000, + .dst_cid = 8000000, + }; + bool ret; + int chain; + + vcap_test_api_init(&admin1); + list_add_tail(&eport1.list, &admin1.enabled); + list_add_tail(&eport2.list, &admin1.enabled); + list_add_tail(&eport3.list, &admin1.enabled); + + ret = vcap_path_exist(&test_vctrl, &test_netdev, 1000000); + KUNIT_EXPECT_EQ(test, true, ret); + + ret = vcap_path_exist(&test_vctrl, &test_netdev, 1100000); + KUNIT_EXPECT_EQ(test, true, ret); + + ret = vcap_path_exist(&test_vctrl, &test_netdev, 1200000); + KUNIT_EXPECT_EQ(test, false, ret); + + chain = vcap_get_next_chain(&test_vctrl, &test_netdev, 0); + KUNIT_EXPECT_EQ(test, 1000000, chain); + + chain = vcap_get_next_chain(&test_vctrl, &test_netdev, 1000000); + KUNIT_EXPECT_EQ(test, 1100000, chain); + + chain = vcap_get_next_chain(&test_vctrl, &test_netdev, 1100000); + KUNIT_EXPECT_EQ(test, 8000000, chain); +} + +static struct kunit_case vcap_api_rule_enable_test_cases[] = { + KUNIT_CASE(vcap_api_rule_chain_path_test), + {} +}; + +static struct kunit_suite vcap_api_rule_enable_test_suite = { + .name = "VCAP_API_Rule_Enable_Testsuite", + .test_cases = vcap_api_rule_enable_test_cases, +}; + static struct kunit_suite vcap_api_rule_remove_test_suite = { .name = "VCAP_API_Rule_Remove_Testsuite", .test_cases = vcap_api_rule_remove_test_cases, @@ -2235,6 +2300,7 @@ static struct kunit_suite vcap_api_encoding_test_suite = { .test_cases = vcap_api_encoding_test_cases, }; +kunit_test_suite(vcap_api_rule_enable_test_suite); kunit_test_suite(vcap_api_rule_remove_test_suite); kunit_test_suite(vcap_api_rule_insert_test_suite); kunit_test_suite(vcap_api_rule_counter_test_suite); diff --git a/drivers/net/ethernet/microchip/vcap/vcap_model_kunit.c b/drivers/net/ethernet/microchip/vcap/vcap_model_kunit.c index 85a8d8566aa2..6d5d73d00562 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_model_kunit.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_model_kunit.c @@ -1709,7 +1709,7 @@ static const struct vcap_field es2_mac_etype_keyfield[] = { .offset = 96, .width = 1, }, - [VCAP_KF_MIRROR_ENA] = { + [VCAP_KF_MIRROR_PROBE] = { .type = VCAP_FIELD_U32, .offset = 97, .width = 2, @@ -1847,7 +1847,7 @@ static const struct vcap_field es2_arp_keyfield[] = { .offset = 95, .width = 1, }, - [VCAP_KF_MIRROR_ENA] = { + [VCAP_KF_MIRROR_PROBE] = { .type = VCAP_FIELD_U32, .offset = 96, .width = 2, @@ -2010,7 +2010,7 @@ static const struct vcap_field es2_ip4_tcp_udp_keyfield[] = { .offset = 96, .width = 1, }, - [VCAP_KF_MIRROR_ENA] = { + [VCAP_KF_MIRROR_PROBE] = { .type = VCAP_FIELD_U32, .offset = 97, .width = 2, @@ -2223,7 +2223,7 @@ static const struct vcap_field es2_ip4_other_keyfield[] = { .offset = 96, .width = 1, }, - [VCAP_KF_MIRROR_ENA] = { + [VCAP_KF_MIRROR_PROBE] = { .type = VCAP_FIELD_U32, .offset = 97, .width = 2, @@ -2376,7 +2376,7 @@ static const struct vcap_field es2_ip_7tuple_keyfield[] = { .offset = 93, .width = 1, }, - [VCAP_KF_MIRROR_ENA] = { + [VCAP_KF_MIRROR_PROBE] = { .type = VCAP_FIELD_U32, .offset = 94, .width = 2, @@ -2569,7 +2569,7 @@ static const struct vcap_field es2_ip4_vid_keyfield[] = { .offset = 48, .width = 1, }, - [VCAP_KF_MIRROR_ENA] = { + [VCAP_KF_MIRROR_PROBE] = { .type = VCAP_FIELD_U32, .offset = 49, .width = 2, @@ -3847,7 +3847,7 @@ static const char * const vcap_keyfield_names[] = { [VCAP_KF_LOOKUP_GEN_IDX] = "LOOKUP_GEN_IDX", [VCAP_KF_LOOKUP_GEN_IDX_SEL] = "LOOKUP_GEN_IDX_SEL", [VCAP_KF_LOOKUP_PAG] = "LOOKUP_PAG", - [VCAP_KF_MIRROR_ENA] = "MIRROR_ENA", + [VCAP_KF_MIRROR_PROBE] = "MIRROR_PROBE", [VCAP_KF_OAM_CCM_CNTS_EQ0] = "OAM_CCM_CNTS_EQ0", [VCAP_KF_OAM_DETECTED] = "OAM_DETECTED", [VCAP_KF_OAM_FLAGS] = "OAM_FLAGS", diff --git a/drivers/net/ethernet/microchip/vcap/vcap_tc.c b/drivers/net/ethernet/microchip/vcap/vcap_tc.c new file mode 100644 index 000000000000..09a994a7cec2 --- /dev/null +++ b/drivers/net/ethernet/microchip/vcap/vcap_tc.c @@ -0,0 +1,409 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip VCAP TC + * + * Copyright (c) 2023 Microchip Technology Inc. and its subsidiaries. + */ + +#include <net/flow_offload.h> +#include <net/ipv6.h> +#include <net/tcp.h> + +#include "vcap_api_client.h" +#include "vcap_tc.h" + +enum vcap_is2_arp_opcode { + VCAP_IS2_ARP_REQUEST, + VCAP_IS2_ARP_REPLY, + VCAP_IS2_RARP_REQUEST, + VCAP_IS2_RARP_REPLY, +}; + +enum vcap_arp_opcode { + VCAP_ARP_OP_RESERVED, + VCAP_ARP_OP_REQUEST, + VCAP_ARP_OP_REPLY, +}; + +int vcap_tc_flower_handler_ethaddr_usage(struct vcap_tc_flower_parse_usage *st) +{ + enum vcap_key_field smac_key = VCAP_KF_L2_SMAC; + enum vcap_key_field dmac_key = VCAP_KF_L2_DMAC; + struct flow_match_eth_addrs match; + struct vcap_u48_key smac, dmac; + int err = 0; + + flow_rule_match_eth_addrs(st->frule, &match); + + if (!is_zero_ether_addr(match.mask->src)) { + vcap_netbytes_copy(smac.value, match.key->src, ETH_ALEN); + vcap_netbytes_copy(smac.mask, match.mask->src, ETH_ALEN); + err = vcap_rule_add_key_u48(st->vrule, smac_key, &smac); + if (err) + goto out; + } + + if (!is_zero_ether_addr(match.mask->dst)) { + vcap_netbytes_copy(dmac.value, match.key->dst, ETH_ALEN); + vcap_netbytes_copy(dmac.mask, match.mask->dst, ETH_ALEN); + err = vcap_rule_add_key_u48(st->vrule, dmac_key, &dmac); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "eth_addr parse error"); + return err; +} +EXPORT_SYMBOL_GPL(vcap_tc_flower_handler_ethaddr_usage); + +int vcap_tc_flower_handler_ipv4_usage(struct vcap_tc_flower_parse_usage *st) +{ + int err = 0; + + if (st->l3_proto == ETH_P_IP) { + struct flow_match_ipv4_addrs mt; + + flow_rule_match_ipv4_addrs(st->frule, &mt); + if (mt.mask->src) { + err = vcap_rule_add_key_u32(st->vrule, + VCAP_KF_L3_IP4_SIP, + be32_to_cpu(mt.key->src), + be32_to_cpu(mt.mask->src)); + if (err) + goto out; + } + if (mt.mask->dst) { + err = vcap_rule_add_key_u32(st->vrule, + VCAP_KF_L3_IP4_DIP, + be32_to_cpu(mt.key->dst), + be32_to_cpu(mt.mask->dst)); + if (err) + goto out; + } + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ipv4_addr parse error"); + return err; +} +EXPORT_SYMBOL_GPL(vcap_tc_flower_handler_ipv4_usage); + +int vcap_tc_flower_handler_ipv6_usage(struct vcap_tc_flower_parse_usage *st) +{ + int err = 0; + + if (st->l3_proto == ETH_P_IPV6) { + struct flow_match_ipv6_addrs mt; + struct vcap_u128_key sip; + struct vcap_u128_key dip; + + flow_rule_match_ipv6_addrs(st->frule, &mt); + /* Check if address masks are non-zero */ + if (!ipv6_addr_any(&mt.mask->src)) { + vcap_netbytes_copy(sip.value, mt.key->src.s6_addr, 16); + vcap_netbytes_copy(sip.mask, mt.mask->src.s6_addr, 16); + err = vcap_rule_add_key_u128(st->vrule, + VCAP_KF_L3_IP6_SIP, &sip); + if (err) + goto out; + } + if (!ipv6_addr_any(&mt.mask->dst)) { + vcap_netbytes_copy(dip.value, mt.key->dst.s6_addr, 16); + vcap_netbytes_copy(dip.mask, mt.mask->dst.s6_addr, 16); + err = vcap_rule_add_key_u128(st->vrule, + VCAP_KF_L3_IP6_DIP, &dip); + if (err) + goto out; + } + } + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS); + return err; +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ipv6_addr parse error"); + return err; +} +EXPORT_SYMBOL_GPL(vcap_tc_flower_handler_ipv6_usage); + +int vcap_tc_flower_handler_portnum_usage(struct vcap_tc_flower_parse_usage *st) +{ + struct flow_match_ports mt; + u16 value, mask; + int err = 0; + + flow_rule_match_ports(st->frule, &mt); + + if (mt.mask->src) { + value = be16_to_cpu(mt.key->src); + mask = be16_to_cpu(mt.mask->src); + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L4_SPORT, value, + mask); + if (err) + goto out; + } + + if (mt.mask->dst) { + value = be16_to_cpu(mt.key->dst); + mask = be16_to_cpu(mt.mask->dst); + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L4_DPORT, value, + mask); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_PORTS); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "port parse error"); + return err; +} +EXPORT_SYMBOL_GPL(vcap_tc_flower_handler_portnum_usage); + +int vcap_tc_flower_handler_cvlan_usage(struct vcap_tc_flower_parse_usage *st) +{ + enum vcap_key_field vid_key = VCAP_KF_8021Q_VID0; + enum vcap_key_field pcp_key = VCAP_KF_8021Q_PCP0; + struct flow_match_vlan mt; + u16 tpid; + int err; + + flow_rule_match_cvlan(st->frule, &mt); + + tpid = be16_to_cpu(mt.key->vlan_tpid); + + if (tpid == ETH_P_8021Q) { + vid_key = VCAP_KF_8021Q_VID1; + pcp_key = VCAP_KF_8021Q_PCP1; + } + + if (mt.mask->vlan_id) { + err = vcap_rule_add_key_u32(st->vrule, vid_key, + mt.key->vlan_id, + mt.mask->vlan_id); + if (err) + goto out; + } + + if (mt.mask->vlan_priority) { + err = vcap_rule_add_key_u32(st->vrule, pcp_key, + mt.key->vlan_priority, + mt.mask->vlan_priority); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_CVLAN); + + return 0; +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "cvlan parse error"); + return err; +} +EXPORT_SYMBOL_GPL(vcap_tc_flower_handler_cvlan_usage); + +int vcap_tc_flower_handler_vlan_usage(struct vcap_tc_flower_parse_usage *st, + enum vcap_key_field vid_key, + enum vcap_key_field pcp_key) +{ + struct flow_match_vlan mt; + int err; + + flow_rule_match_vlan(st->frule, &mt); + + if (mt.mask->vlan_id) { + err = vcap_rule_add_key_u32(st->vrule, vid_key, + mt.key->vlan_id, + mt.mask->vlan_id); + if (err) + goto out; + } + + if (mt.mask->vlan_priority) { + err = vcap_rule_add_key_u32(st->vrule, pcp_key, + mt.key->vlan_priority, + mt.mask->vlan_priority); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_VLAN); + + return 0; +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "vlan parse error"); + return err; +} +EXPORT_SYMBOL_GPL(vcap_tc_flower_handler_vlan_usage); + +int vcap_tc_flower_handler_tcp_usage(struct vcap_tc_flower_parse_usage *st) +{ + struct flow_match_tcp mt; + u16 tcp_flags_mask; + u16 tcp_flags_key; + enum vcap_bit val; + int err = 0; + + flow_rule_match_tcp(st->frule, &mt); + tcp_flags_key = be16_to_cpu(mt.key->flags); + tcp_flags_mask = be16_to_cpu(mt.mask->flags); + + if (tcp_flags_mask & TCPHDR_FIN) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_FIN) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_FIN, val); + if (err) + goto out; + } + + if (tcp_flags_mask & TCPHDR_SYN) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_SYN) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_SYN, val); + if (err) + goto out; + } + + if (tcp_flags_mask & TCPHDR_RST) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_RST) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_RST, val); + if (err) + goto out; + } + + if (tcp_flags_mask & TCPHDR_PSH) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_PSH) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_PSH, val); + if (err) + goto out; + } + + if (tcp_flags_mask & TCPHDR_ACK) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_ACK) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_ACK, val); + if (err) + goto out; + } + + if (tcp_flags_mask & TCPHDR_URG) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_URG) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_URG, val); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_TCP); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "tcp_flags parse error"); + return err; +} +EXPORT_SYMBOL_GPL(vcap_tc_flower_handler_tcp_usage); + +int vcap_tc_flower_handler_arp_usage(struct vcap_tc_flower_parse_usage *st) +{ + struct flow_match_arp mt; + u16 value, mask; + u32 ipval, ipmsk; + int err; + + flow_rule_match_arp(st->frule, &mt); + + if (mt.mask->op) { + mask = 0x3; + if (st->l3_proto == ETH_P_ARP) { + value = mt.key->op == VCAP_ARP_OP_REQUEST ? + VCAP_IS2_ARP_REQUEST : + VCAP_IS2_ARP_REPLY; + } else { /* RARP */ + value = mt.key->op == VCAP_ARP_OP_REQUEST ? + VCAP_IS2_RARP_REQUEST : + VCAP_IS2_RARP_REPLY; + } + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_ARP_OPCODE, + value, mask); + if (err) + goto out; + } + + /* The IS2 ARP keyset does not support ARP hardware addresses */ + if (!is_zero_ether_addr(mt.mask->sha) || + !is_zero_ether_addr(mt.mask->tha)) { + err = -EINVAL; + goto out; + } + + if (mt.mask->sip) { + ipval = be32_to_cpu((__force __be32)mt.key->sip); + ipmsk = be32_to_cpu((__force __be32)mt.mask->sip); + + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L3_IP4_SIP, + ipval, ipmsk); + if (err) + goto out; + } + + if (mt.mask->tip) { + ipval = be32_to_cpu((__force __be32)mt.key->tip); + ipmsk = be32_to_cpu((__force __be32)mt.mask->tip); + + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L3_IP4_DIP, + ipval, ipmsk); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_ARP); + + return 0; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "arp parse error"); + return err; +} +EXPORT_SYMBOL_GPL(vcap_tc_flower_handler_arp_usage); + +int vcap_tc_flower_handler_ip_usage(struct vcap_tc_flower_parse_usage *st) +{ + struct flow_match_ip mt; + int err = 0; + + flow_rule_match_ip(st->frule, &mt); + + if (mt.mask->tos) { + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L3_TOS, + mt.key->tos, + mt.mask->tos); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IP); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_tos parse error"); + return err; +} +EXPORT_SYMBOL_GPL(vcap_tc_flower_handler_ip_usage); diff --git a/drivers/net/ethernet/microchip/vcap/vcap_tc.h b/drivers/net/ethernet/microchip/vcap/vcap_tc.h new file mode 100644 index 000000000000..5c55ccbee175 --- /dev/null +++ b/drivers/net/ethernet/microchip/vcap/vcap_tc.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ +/* Copyright (C) 2023 Microchip Technology Inc. and its subsidiaries. + * Microchip VCAP TC + */ + +#ifndef __VCAP_TC__ +#define __VCAP_TC__ + +struct vcap_tc_flower_parse_usage { + struct flow_cls_offload *fco; + struct flow_rule *frule; + struct vcap_rule *vrule; + struct vcap_admin *admin; + u16 l3_proto; + u8 l4_proto; + unsigned int used_keys; +}; + +int vcap_tc_flower_handler_ethaddr_usage(struct vcap_tc_flower_parse_usage *st); +int vcap_tc_flower_handler_ipv4_usage(struct vcap_tc_flower_parse_usage *st); +int vcap_tc_flower_handler_ipv6_usage(struct vcap_tc_flower_parse_usage *st); +int vcap_tc_flower_handler_portnum_usage(struct vcap_tc_flower_parse_usage *st); +int vcap_tc_flower_handler_cvlan_usage(struct vcap_tc_flower_parse_usage *st); +int vcap_tc_flower_handler_vlan_usage(struct vcap_tc_flower_parse_usage *st, + enum vcap_key_field vid_key, + enum vcap_key_field pcp_key); +int vcap_tc_flower_handler_tcp_usage(struct vcap_tc_flower_parse_usage *st); +int vcap_tc_flower_handler_arp_usage(struct vcap_tc_flower_parse_usage *st); +int vcap_tc_flower_handler_ip_usage(struct vcap_tc_flower_parse_usage *st); + +#endif /* __VCAP_TC__ */ diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index b144f2237748..f9b8f372ec8a 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -1217,9 +1217,7 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) unsigned int max_queues_per_port = num_online_cpus(); struct gdma_context *gc = pci_get_drvdata(pdev); struct gdma_irq_context *gic; - unsigned int max_irqs; - u16 *cpus; - cpumask_var_t req_mask; + unsigned int max_irqs, cpu; int nvec, irq; int err, i = 0, j; @@ -1240,21 +1238,7 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) goto free_irq_vector; } - if (!zalloc_cpumask_var(&req_mask, GFP_KERNEL)) { - err = -ENOMEM; - goto free_irq; - } - - cpus = kcalloc(nvec, sizeof(*cpus), GFP_KERNEL); - if (!cpus) { - err = -ENOMEM; - goto free_mask; - } - for (i = 0; i < nvec; i++) - cpus[i] = cpumask_local_spread(i, gc->numa_node); - for (i = 0; i < nvec; i++) { - cpumask_set_cpu(cpus[i], req_mask); gic = &gc->irq_contexts[i]; gic->handler = NULL; gic->arg = NULL; @@ -1269,17 +1253,16 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) irq = pci_irq_vector(pdev, i); if (irq < 0) { err = irq; - goto free_mask; + goto free_irq; } err = request_irq(irq, mana_gd_intr, 0, gic->name, gic); if (err) - goto free_mask; - irq_set_affinity_and_hint(irq, req_mask); - cpumask_clear(req_mask); + goto free_irq; + + cpu = cpumask_local_spread(i, gc->numa_node); + irq_set_affinity_and_hint(irq, cpumask_of(cpu)); } - free_cpumask_var(req_mask); - kfree(cpus); err = mana_gd_alloc_res_map(nvec, &gc->msix_resource); if (err) @@ -1290,13 +1273,12 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) return 0; -free_mask: - free_cpumask_var(req_mask); - kfree(cpus); free_irq: for (j = i - 1; j >= 0; j--) { irq = pci_irq_vector(pdev, j); gic = &gc->irq_contexts[j]; + + irq_update_affinity_hint(irq, NULL); free_irq(irq, gic); } @@ -1324,6 +1306,9 @@ static void mana_gd_remove_irqs(struct pci_dev *pdev) continue; gic = &gc->irq_contexts[i]; + + /* Need to clear the hint before free_irq */ + irq_update_affinity_hint(irq, NULL); free_irq(irq, gic); } diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index c060b03f7e27..08acb7b89086 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -6,12 +6,16 @@ */ #include <linux/dsa/ocelot.h> #include <linux/if_bridge.h> +#include <linux/iopoll.h> #include <soc/mscc/ocelot_vcap.h> #include "ocelot.h" #include "ocelot_vcap.h" -#define TABLE_UPDATE_SLEEP_US 10 -#define TABLE_UPDATE_TIMEOUT_US 100000 +#define TABLE_UPDATE_SLEEP_US 10 +#define TABLE_UPDATE_TIMEOUT_US 100000 +#define MEM_INIT_SLEEP_US 1000 +#define MEM_INIT_TIMEOUT_US 100000 + #define OCELOT_RSV_VLAN_RANGE_START 4000 struct ocelot_mact_entry { @@ -2713,6 +2717,46 @@ static void ocelot_detect_features(struct ocelot *ocelot) ocelot->num_frame_refs = QSYS_MMGT_EQ_CTRL_FP_FREE_CNT(eq_ctrl); } +static int ocelot_mem_init_status(struct ocelot *ocelot) +{ + unsigned int val; + int err; + + err = regmap_field_read(ocelot->regfields[SYS_RESET_CFG_MEM_INIT], + &val); + + return err ?: val; +} + +int ocelot_reset(struct ocelot *ocelot) +{ + int err; + u32 val; + + err = regmap_field_write(ocelot->regfields[SYS_RESET_CFG_MEM_INIT], 1); + if (err) + return err; + + err = regmap_field_write(ocelot->regfields[SYS_RESET_CFG_MEM_ENA], 1); + if (err) + return err; + + /* MEM_INIT is a self-clearing bit. Wait for it to be cleared (should be + * 100us) before enabling the switch core. + */ + err = readx_poll_timeout(ocelot_mem_init_status, ocelot, val, !val, + MEM_INIT_SLEEP_US, MEM_INIT_TIMEOUT_US); + if (err) + return err; + + err = regmap_field_write(ocelot->regfields[SYS_RESET_CFG_MEM_ENA], 1); + if (err) + return err; + + return regmap_field_write(ocelot->regfields[SYS_RESET_CFG_CORE_ENA], 1); +} +EXPORT_SYMBOL(ocelot_reset); + int ocelot_init(struct ocelot *ocelot) { int i, ret; diff --git a/drivers/net/ethernet/mscc/ocelot_devlink.c b/drivers/net/ethernet/mscc/ocelot_devlink.c index b8737efd2a85..d9ea75a14f2f 100644 --- a/drivers/net/ethernet/mscc/ocelot_devlink.c +++ b/drivers/net/ethernet/mscc/ocelot_devlink.c @@ -487,6 +487,37 @@ static void ocelot_watermark_init(struct ocelot *ocelot) ocelot_setup_sharing_watermarks(ocelot); } +/* Watermark encode + * Bit 8: Unit; 0:1, 1:16 + * Bit 7-0: Value to be multiplied with unit + */ +u16 ocelot_wm_enc(u16 value) +{ + WARN_ON(value >= 16 * BIT(8)); + + if (value >= BIT(8)) + return BIT(8) | (value / 16); + + return value; +} +EXPORT_SYMBOL(ocelot_wm_enc); + +u16 ocelot_wm_dec(u16 wm) +{ + if (wm & BIT(8)) + return (wm & GENMASK(7, 0)) * 16; + + return wm; +} +EXPORT_SYMBOL(ocelot_wm_dec); + +void ocelot_wm_stat(u32 val, u32 *inuse, u32 *maxuse) +{ + *inuse = (val & GENMASK(23, 12)) >> 12; + *maxuse = val & GENMASK(11, 0); +} +EXPORT_SYMBOL(ocelot_wm_stat); + /* Pool size and type are fixed up at runtime. Keeping this structure to * look up the cell size multipliers. */ diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c index 7c0897e779dc..ee052404eb55 100644 --- a/drivers/net/ethernet/mscc/ocelot_flower.c +++ b/drivers/net/ethernet/mscc/ocelot_flower.c @@ -605,6 +605,18 @@ ocelot_flower_parse_key(struct ocelot *ocelot, int port, bool ingress, flow_rule_match_control(rule, &match); } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; + + flow_rule_match_vlan(rule, &match); + filter->key_type = OCELOT_VCAP_KEY_ANY; + filter->vlan.vid.value = match.key->vlan_id; + filter->vlan.vid.mask = match.mask->vlan_id; + filter->vlan.pcp.value[0] = match.key->vlan_priority; + filter->vlan.pcp.mask[0] = match.mask->vlan_priority; + match_protocol = false; + } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct flow_match_eth_addrs match; @@ -737,18 +749,6 @@ ocelot_flower_parse_key(struct ocelot *ocelot, int port, bool ingress, match_protocol = false; } - if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_match_vlan match; - - flow_rule_match_vlan(rule, &match); - filter->key_type = OCELOT_VCAP_KEY_ANY; - filter->vlan.vid.value = match.key->vlan_id; - filter->vlan.vid.mask = match.mask->vlan_id; - filter->vlan.pcp.value[0] = match.key->vlan_priority; - filter->vlan.pcp.mask[0] = match.mask->vlan_priority; - match_protocol = false; - } - finished_key_parsing: if (match_protocol && proto != ETH_P_ALL) { if (filter->block_id == VCAP_ES0) { diff --git a/drivers/net/ethernet/mscc/ocelot_ptp.c b/drivers/net/ethernet/mscc/ocelot_ptp.c index 1a82f10c8853..2180ae94c744 100644 --- a/drivers/net/ethernet/mscc/ocelot_ptp.c +++ b/drivers/net/ethernet/mscc/ocelot_ptp.c @@ -335,8 +335,8 @@ static void ocelot_populate_ipv6_ptp_event_trap_key(struct ocelot_vcap_filter *trap) { trap->key_type = OCELOT_VCAP_KEY_IPV6; - trap->key.ipv4.proto.value[0] = IPPROTO_UDP; - trap->key.ipv4.proto.mask[0] = 0xff; + trap->key.ipv6.proto.value[0] = IPPROTO_UDP; + trap->key.ipv6.proto.mask[0] = 0xff; trap->key.ipv6.dport.value = PTP_EV_PORT; trap->key.ipv6.dport.mask = 0xffff; } @@ -355,8 +355,8 @@ static void ocelot_populate_ipv6_ptp_general_trap_key(struct ocelot_vcap_filter *trap) { trap->key_type = OCELOT_VCAP_KEY_IPV6; - trap->key.ipv4.proto.value[0] = IPPROTO_UDP; - trap->key.ipv4.proto.mask[0] = 0xff; + trap->key.ipv6.proto.value[0] = IPPROTO_UDP; + trap->key.ipv6.proto.mask[0] = 0xff; trap->key.ipv6.dport.value = PTP_GEN_PORT; trap->key.ipv6.dport.mask = 0xffff; } diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c index b097fd4a4061..7388c3b0535c 100644 --- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c +++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c @@ -6,7 +6,6 @@ */ #include <linux/dsa/ocelot.h> #include <linux/interrupt.h> -#include <linux/iopoll.h> #include <linux/module.h> #include <linux/of_net.h> #include <linux/netdevice.h> @@ -17,6 +16,7 @@ #include <linux/skbuff.h> #include <net/switchdev.h> +#include <soc/mscc/ocelot.h> #include <soc/mscc/ocelot_vcap.h> #include <soc/mscc/ocelot_hsio.h> #include <soc/mscc/vsc7514_regs.h> @@ -26,80 +26,6 @@ #define VSC7514_VCAP_POLICER_BASE 128 #define VSC7514_VCAP_POLICER_MAX 191 -#define MEM_INIT_SLEEP_US 1000 -#define MEM_INIT_TIMEOUT_US 100000 - -static const u32 *ocelot_regmap[TARGET_MAX] = { - [ANA] = vsc7514_ana_regmap, - [QS] = vsc7514_qs_regmap, - [QSYS] = vsc7514_qsys_regmap, - [REW] = vsc7514_rew_regmap, - [SYS] = vsc7514_sys_regmap, - [S0] = vsc7514_vcap_regmap, - [S1] = vsc7514_vcap_regmap, - [S2] = vsc7514_vcap_regmap, - [PTP] = vsc7514_ptp_regmap, - [DEV_GMII] = vsc7514_dev_gmii_regmap, -}; - -static const struct reg_field ocelot_regfields[REGFIELD_MAX] = { - [ANA_ADVLEARN_VLAN_CHK] = REG_FIELD(ANA_ADVLEARN, 11, 11), - [ANA_ADVLEARN_LEARN_MIRROR] = REG_FIELD(ANA_ADVLEARN, 0, 10), - [ANA_ANEVENTS_MSTI_DROP] = REG_FIELD(ANA_ANEVENTS, 27, 27), - [ANA_ANEVENTS_ACLKILL] = REG_FIELD(ANA_ANEVENTS, 26, 26), - [ANA_ANEVENTS_ACLUSED] = REG_FIELD(ANA_ANEVENTS, 25, 25), - [ANA_ANEVENTS_AUTOAGE] = REG_FIELD(ANA_ANEVENTS, 24, 24), - [ANA_ANEVENTS_VS2TTL1] = REG_FIELD(ANA_ANEVENTS, 23, 23), - [ANA_ANEVENTS_STORM_DROP] = REG_FIELD(ANA_ANEVENTS, 22, 22), - [ANA_ANEVENTS_LEARN_DROP] = REG_FIELD(ANA_ANEVENTS, 21, 21), - [ANA_ANEVENTS_AGED_ENTRY] = REG_FIELD(ANA_ANEVENTS, 20, 20), - [ANA_ANEVENTS_CPU_LEARN_FAILED] = REG_FIELD(ANA_ANEVENTS, 19, 19), - [ANA_ANEVENTS_AUTO_LEARN_FAILED] = REG_FIELD(ANA_ANEVENTS, 18, 18), - [ANA_ANEVENTS_LEARN_REMOVE] = REG_FIELD(ANA_ANEVENTS, 17, 17), - [ANA_ANEVENTS_AUTO_LEARNED] = REG_FIELD(ANA_ANEVENTS, 16, 16), - [ANA_ANEVENTS_AUTO_MOVED] = REG_FIELD(ANA_ANEVENTS, 15, 15), - [ANA_ANEVENTS_DROPPED] = REG_FIELD(ANA_ANEVENTS, 14, 14), - [ANA_ANEVENTS_CLASSIFIED_DROP] = REG_FIELD(ANA_ANEVENTS, 13, 13), - [ANA_ANEVENTS_CLASSIFIED_COPY] = REG_FIELD(ANA_ANEVENTS, 12, 12), - [ANA_ANEVENTS_VLAN_DISCARD] = REG_FIELD(ANA_ANEVENTS, 11, 11), - [ANA_ANEVENTS_FWD_DISCARD] = REG_FIELD(ANA_ANEVENTS, 10, 10), - [ANA_ANEVENTS_MULTICAST_FLOOD] = REG_FIELD(ANA_ANEVENTS, 9, 9), - [ANA_ANEVENTS_UNICAST_FLOOD] = REG_FIELD(ANA_ANEVENTS, 8, 8), - [ANA_ANEVENTS_DEST_KNOWN] = REG_FIELD(ANA_ANEVENTS, 7, 7), - [ANA_ANEVENTS_BUCKET3_MATCH] = REG_FIELD(ANA_ANEVENTS, 6, 6), - [ANA_ANEVENTS_BUCKET2_MATCH] = REG_FIELD(ANA_ANEVENTS, 5, 5), - [ANA_ANEVENTS_BUCKET1_MATCH] = REG_FIELD(ANA_ANEVENTS, 4, 4), - [ANA_ANEVENTS_BUCKET0_MATCH] = REG_FIELD(ANA_ANEVENTS, 3, 3), - [ANA_ANEVENTS_CPU_OPERATION] = REG_FIELD(ANA_ANEVENTS, 2, 2), - [ANA_ANEVENTS_DMAC_LOOKUP] = REG_FIELD(ANA_ANEVENTS, 1, 1), - [ANA_ANEVENTS_SMAC_LOOKUP] = REG_FIELD(ANA_ANEVENTS, 0, 0), - [ANA_TABLES_MACACCESS_B_DOM] = REG_FIELD(ANA_TABLES_MACACCESS, 18, 18), - [ANA_TABLES_MACTINDX_BUCKET] = REG_FIELD(ANA_TABLES_MACTINDX, 10, 11), - [ANA_TABLES_MACTINDX_M_INDEX] = REG_FIELD(ANA_TABLES_MACTINDX, 0, 9), - [QSYS_TIMED_FRAME_ENTRY_TFRM_VLD] = REG_FIELD(QSYS_TIMED_FRAME_ENTRY, 20, 20), - [QSYS_TIMED_FRAME_ENTRY_TFRM_FP] = REG_FIELD(QSYS_TIMED_FRAME_ENTRY, 8, 19), - [QSYS_TIMED_FRAME_ENTRY_TFRM_PORTNO] = REG_FIELD(QSYS_TIMED_FRAME_ENTRY, 4, 7), - [QSYS_TIMED_FRAME_ENTRY_TFRM_TM_SEL] = REG_FIELD(QSYS_TIMED_FRAME_ENTRY, 1, 3), - [QSYS_TIMED_FRAME_ENTRY_TFRM_TM_T] = REG_FIELD(QSYS_TIMED_FRAME_ENTRY, 0, 0), - [SYS_RESET_CFG_CORE_ENA] = REG_FIELD(SYS_RESET_CFG, 2, 2), - [SYS_RESET_CFG_MEM_ENA] = REG_FIELD(SYS_RESET_CFG, 1, 1), - [SYS_RESET_CFG_MEM_INIT] = REG_FIELD(SYS_RESET_CFG, 0, 0), - /* Replicated per number of ports (12), register size 4 per port */ - [QSYS_SWITCH_PORT_MODE_PORT_ENA] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 14, 14, 12, 4), - [QSYS_SWITCH_PORT_MODE_SCH_NEXT_CFG] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 11, 13, 12, 4), - [QSYS_SWITCH_PORT_MODE_YEL_RSRVD] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 10, 10, 12, 4), - [QSYS_SWITCH_PORT_MODE_INGRESS_DROP_MODE] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 9, 9, 12, 4), - [QSYS_SWITCH_PORT_MODE_TX_PFC_ENA] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 1, 8, 12, 4), - [QSYS_SWITCH_PORT_MODE_TX_PFC_MODE] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 0, 0, 12, 4), - [SYS_PORT_MODE_DATA_WO_TS] = REG_FIELD_ID(SYS_PORT_MODE, 5, 6, 12, 4), - [SYS_PORT_MODE_INCL_INJ_HDR] = REG_FIELD_ID(SYS_PORT_MODE, 3, 4, 12, 4), - [SYS_PORT_MODE_INCL_XTR_HDR] = REG_FIELD_ID(SYS_PORT_MODE, 1, 2, 12, 4), - [SYS_PORT_MODE_INCL_HDR_ERR] = REG_FIELD_ID(SYS_PORT_MODE, 0, 0, 12, 4), - [SYS_PAUSE_CFG_PAUSE_START] = REG_FIELD_ID(SYS_PAUSE_CFG, 10, 18, 12, 4), - [SYS_PAUSE_CFG_PAUSE_STOP] = REG_FIELD_ID(SYS_PAUSE_CFG, 1, 9, 12, 4), - [SYS_PAUSE_CFG_PAUSE_ENA] = REG_FIELD_ID(SYS_PAUSE_CFG, 0, 1, 12, 4), -}; - static void ocelot_pll5_init(struct ocelot *ocelot) { /* Configure PLL5. This will need a proper CCF driver @@ -133,11 +59,11 @@ static int ocelot_chip_init(struct ocelot *ocelot, const struct ocelot_ops *ops) { int ret; - ocelot->map = ocelot_regmap; + ocelot->map = vsc7514_regmap; ocelot->num_mact_rows = 1024; ocelot->ops = ops; - ret = ocelot_regfields_init(ocelot, ocelot_regfields); + ret = ocelot_regfields_init(ocelot, vsc7514_regfields); if (ret) return ret; @@ -190,73 +116,6 @@ static const struct of_device_id mscc_ocelot_match[] = { }; MODULE_DEVICE_TABLE(of, mscc_ocelot_match); -static int ocelot_mem_init_status(struct ocelot *ocelot) -{ - unsigned int val; - int err; - - err = regmap_field_read(ocelot->regfields[SYS_RESET_CFG_MEM_INIT], - &val); - - return err ?: val; -} - -static int ocelot_reset(struct ocelot *ocelot) -{ - int err; - u32 val; - - err = regmap_field_write(ocelot->regfields[SYS_RESET_CFG_MEM_INIT], 1); - if (err) - return err; - - err = regmap_field_write(ocelot->regfields[SYS_RESET_CFG_MEM_ENA], 1); - if (err) - return err; - - /* MEM_INIT is a self-clearing bit. Wait for it to be cleared (should be - * 100us) before enabling the switch core. - */ - err = readx_poll_timeout(ocelot_mem_init_status, ocelot, val, !val, - MEM_INIT_SLEEP_US, MEM_INIT_TIMEOUT_US); - if (err) - return err; - - err = regmap_field_write(ocelot->regfields[SYS_RESET_CFG_MEM_ENA], 1); - if (err) - return err; - - return regmap_field_write(ocelot->regfields[SYS_RESET_CFG_CORE_ENA], 1); -} - -/* Watermark encode - * Bit 8: Unit; 0:1, 1:16 - * Bit 7-0: Value to be multiplied with unit - */ -static u16 ocelot_wm_enc(u16 value) -{ - WARN_ON(value >= 16 * BIT(8)); - - if (value >= BIT(8)) - return BIT(8) | (value / 16); - - return value; -} - -static u16 ocelot_wm_dec(u16 wm) -{ - if (wm & BIT(8)) - return (wm & GENMASK(7, 0)) * 16; - - return wm; -} - -static void ocelot_wm_stat(u32 val, u32 *inuse, u32 *maxuse) -{ - *inuse = (val & GENMASK(23, 12)) >> 12; - *maxuse = val & GENMASK(11, 0); -} - static const struct ocelot_ops ocelot_ops = { .reset = ocelot_reset, .wm_enc = ocelot_wm_enc, @@ -266,49 +125,6 @@ static const struct ocelot_ops ocelot_ops = { .netdev_to_port = ocelot_netdev_to_port, }; -static struct vcap_props vsc7514_vcap_props[] = { - [VCAP_ES0] = { - .action_type_width = 0, - .action_table = { - [ES0_ACTION_TYPE_NORMAL] = { - .width = 73, /* HIT_STICKY not included */ - .count = 1, - }, - }, - .target = S0, - .keys = vsc7514_vcap_es0_keys, - .actions = vsc7514_vcap_es0_actions, - }, - [VCAP_IS1] = { - .action_type_width = 0, - .action_table = { - [IS1_ACTION_TYPE_NORMAL] = { - .width = 78, /* HIT_STICKY not included */ - .count = 4, - }, - }, - .target = S1, - .keys = vsc7514_vcap_is1_keys, - .actions = vsc7514_vcap_is1_actions, - }, - [VCAP_IS2] = { - .action_type_width = 1, - .action_table = { - [IS2_ACTION_TYPE_NORMAL] = { - .width = 49, - .count = 2 - }, - [IS2_ACTION_TYPE_SMAC_SIP] = { - .width = 6, - .count = 4 - }, - }, - .target = S2, - .keys = vsc7514_vcap_is2_keys, - .actions = vsc7514_vcap_is2_actions, - }, -}; - static struct ptp_clock_info ocelot_ptp_clock_info = { .owner = THIS_MODULE, .name = "ocelot ptp", diff --git a/drivers/net/ethernet/mscc/vsc7514_regs.c b/drivers/net/ethernet/mscc/vsc7514_regs.c index 9d2d3e13cacf..ef6fd3f6be30 100644 --- a/drivers/net/ethernet/mscc/vsc7514_regs.c +++ b/drivers/net/ethernet/mscc/vsc7514_regs.c @@ -9,7 +9,66 @@ #include <soc/mscc/vsc7514_regs.h> #include "ocelot.h" -const u32 vsc7514_ana_regmap[] = { +const struct reg_field vsc7514_regfields[REGFIELD_MAX] = { + [ANA_ADVLEARN_VLAN_CHK] = REG_FIELD(ANA_ADVLEARN, 11, 11), + [ANA_ADVLEARN_LEARN_MIRROR] = REG_FIELD(ANA_ADVLEARN, 0, 10), + [ANA_ANEVENTS_MSTI_DROP] = REG_FIELD(ANA_ANEVENTS, 27, 27), + [ANA_ANEVENTS_ACLKILL] = REG_FIELD(ANA_ANEVENTS, 26, 26), + [ANA_ANEVENTS_ACLUSED] = REG_FIELD(ANA_ANEVENTS, 25, 25), + [ANA_ANEVENTS_AUTOAGE] = REG_FIELD(ANA_ANEVENTS, 24, 24), + [ANA_ANEVENTS_VS2TTL1] = REG_FIELD(ANA_ANEVENTS, 23, 23), + [ANA_ANEVENTS_STORM_DROP] = REG_FIELD(ANA_ANEVENTS, 22, 22), + [ANA_ANEVENTS_LEARN_DROP] = REG_FIELD(ANA_ANEVENTS, 21, 21), + [ANA_ANEVENTS_AGED_ENTRY] = REG_FIELD(ANA_ANEVENTS, 20, 20), + [ANA_ANEVENTS_CPU_LEARN_FAILED] = REG_FIELD(ANA_ANEVENTS, 19, 19), + [ANA_ANEVENTS_AUTO_LEARN_FAILED] = REG_FIELD(ANA_ANEVENTS, 18, 18), + [ANA_ANEVENTS_LEARN_REMOVE] = REG_FIELD(ANA_ANEVENTS, 17, 17), + [ANA_ANEVENTS_AUTO_LEARNED] = REG_FIELD(ANA_ANEVENTS, 16, 16), + [ANA_ANEVENTS_AUTO_MOVED] = REG_FIELD(ANA_ANEVENTS, 15, 15), + [ANA_ANEVENTS_DROPPED] = REG_FIELD(ANA_ANEVENTS, 14, 14), + [ANA_ANEVENTS_CLASSIFIED_DROP] = REG_FIELD(ANA_ANEVENTS, 13, 13), + [ANA_ANEVENTS_CLASSIFIED_COPY] = REG_FIELD(ANA_ANEVENTS, 12, 12), + [ANA_ANEVENTS_VLAN_DISCARD] = REG_FIELD(ANA_ANEVENTS, 11, 11), + [ANA_ANEVENTS_FWD_DISCARD] = REG_FIELD(ANA_ANEVENTS, 10, 10), + [ANA_ANEVENTS_MULTICAST_FLOOD] = REG_FIELD(ANA_ANEVENTS, 9, 9), + [ANA_ANEVENTS_UNICAST_FLOOD] = REG_FIELD(ANA_ANEVENTS, 8, 8), + [ANA_ANEVENTS_DEST_KNOWN] = REG_FIELD(ANA_ANEVENTS, 7, 7), + [ANA_ANEVENTS_BUCKET3_MATCH] = REG_FIELD(ANA_ANEVENTS, 6, 6), + [ANA_ANEVENTS_BUCKET2_MATCH] = REG_FIELD(ANA_ANEVENTS, 5, 5), + [ANA_ANEVENTS_BUCKET1_MATCH] = REG_FIELD(ANA_ANEVENTS, 4, 4), + [ANA_ANEVENTS_BUCKET0_MATCH] = REG_FIELD(ANA_ANEVENTS, 3, 3), + [ANA_ANEVENTS_CPU_OPERATION] = REG_FIELD(ANA_ANEVENTS, 2, 2), + [ANA_ANEVENTS_DMAC_LOOKUP] = REG_FIELD(ANA_ANEVENTS, 1, 1), + [ANA_ANEVENTS_SMAC_LOOKUP] = REG_FIELD(ANA_ANEVENTS, 0, 0), + [ANA_TABLES_MACACCESS_B_DOM] = REG_FIELD(ANA_TABLES_MACACCESS, 18, 18), + [ANA_TABLES_MACTINDX_BUCKET] = REG_FIELD(ANA_TABLES_MACTINDX, 10, 11), + [ANA_TABLES_MACTINDX_M_INDEX] = REG_FIELD(ANA_TABLES_MACTINDX, 0, 9), + [QSYS_TIMED_FRAME_ENTRY_TFRM_VLD] = REG_FIELD(QSYS_TIMED_FRAME_ENTRY, 20, 20), + [QSYS_TIMED_FRAME_ENTRY_TFRM_FP] = REG_FIELD(QSYS_TIMED_FRAME_ENTRY, 8, 19), + [QSYS_TIMED_FRAME_ENTRY_TFRM_PORTNO] = REG_FIELD(QSYS_TIMED_FRAME_ENTRY, 4, 7), + [QSYS_TIMED_FRAME_ENTRY_TFRM_TM_SEL] = REG_FIELD(QSYS_TIMED_FRAME_ENTRY, 1, 3), + [QSYS_TIMED_FRAME_ENTRY_TFRM_TM_T] = REG_FIELD(QSYS_TIMED_FRAME_ENTRY, 0, 0), + [SYS_RESET_CFG_CORE_ENA] = REG_FIELD(SYS_RESET_CFG, 2, 2), + [SYS_RESET_CFG_MEM_ENA] = REG_FIELD(SYS_RESET_CFG, 1, 1), + [SYS_RESET_CFG_MEM_INIT] = REG_FIELD(SYS_RESET_CFG, 0, 0), + /* Replicated per number of ports (12), register size 4 per port */ + [QSYS_SWITCH_PORT_MODE_PORT_ENA] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 14, 14, 12, 4), + [QSYS_SWITCH_PORT_MODE_SCH_NEXT_CFG] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 11, 13, 12, 4), + [QSYS_SWITCH_PORT_MODE_YEL_RSRVD] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 10, 10, 12, 4), + [QSYS_SWITCH_PORT_MODE_INGRESS_DROP_MODE] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 9, 9, 12, 4), + [QSYS_SWITCH_PORT_MODE_TX_PFC_ENA] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 1, 8, 12, 4), + [QSYS_SWITCH_PORT_MODE_TX_PFC_MODE] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 0, 0, 12, 4), + [SYS_PORT_MODE_DATA_WO_TS] = REG_FIELD_ID(SYS_PORT_MODE, 5, 6, 12, 4), + [SYS_PORT_MODE_INCL_INJ_HDR] = REG_FIELD_ID(SYS_PORT_MODE, 3, 4, 12, 4), + [SYS_PORT_MODE_INCL_XTR_HDR] = REG_FIELD_ID(SYS_PORT_MODE, 1, 2, 12, 4), + [SYS_PORT_MODE_INCL_HDR_ERR] = REG_FIELD_ID(SYS_PORT_MODE, 0, 0, 12, 4), + [SYS_PAUSE_CFG_PAUSE_START] = REG_FIELD_ID(SYS_PAUSE_CFG, 10, 18, 12, 4), + [SYS_PAUSE_CFG_PAUSE_STOP] = REG_FIELD_ID(SYS_PAUSE_CFG, 1, 9, 12, 4), + [SYS_PAUSE_CFG_PAUSE_ENA] = REG_FIELD_ID(SYS_PAUSE_CFG, 0, 1, 12, 4), +}; +EXPORT_SYMBOL(vsc7514_regfields); + +static const u32 vsc7514_ana_regmap[] = { REG(ANA_ADVLEARN, 0x009000), REG(ANA_VLANMASK, 0x009004), REG(ANA_PORT_B_DOMAIN, 0x009008), @@ -89,9 +148,8 @@ const u32 vsc7514_ana_regmap[] = { REG(ANA_POL_HYST, 0x008bec), REG(ANA_POL_MISC_CFG, 0x008bf0), }; -EXPORT_SYMBOL(vsc7514_ana_regmap); -const u32 vsc7514_qs_regmap[] = { +static const u32 vsc7514_qs_regmap[] = { REG(QS_XTR_GRP_CFG, 0x000000), REG(QS_XTR_RD, 0x000008), REG(QS_XTR_FRM_PRUNING, 0x000010), @@ -105,9 +163,8 @@ const u32 vsc7514_qs_regmap[] = { REG(QS_INJ_ERR, 0x000040), REG(QS_INH_DBG, 0x000048), }; -EXPORT_SYMBOL(vsc7514_qs_regmap); -const u32 vsc7514_qsys_regmap[] = { +static const u32 vsc7514_qsys_regmap[] = { REG(QSYS_PORT_MODE, 0x011200), REG(QSYS_SWITCH_PORT_MODE, 0x011234), REG(QSYS_STAT_CNT_CFG, 0x011264), @@ -150,9 +207,8 @@ const u32 vsc7514_qsys_regmap[] = { REG(QSYS_SE_STATE, 0x00004c), REG(QSYS_HSCH_MISC_CFG, 0x011388), }; -EXPORT_SYMBOL(vsc7514_qsys_regmap); -const u32 vsc7514_rew_regmap[] = { +static const u32 vsc7514_rew_regmap[] = { REG(REW_PORT_VLAN_CFG, 0x000000), REG(REW_TAG_CFG, 0x000004), REG(REW_PORT_CFG, 0x000008), @@ -165,9 +221,8 @@ const u32 vsc7514_rew_regmap[] = { REG(REW_STAT_CFG, 0x000890), REG(REW_PPT, 0x000680), }; -EXPORT_SYMBOL(vsc7514_rew_regmap); -const u32 vsc7514_sys_regmap[] = { +static const u32 vsc7514_sys_regmap[] = { REG(SYS_COUNT_RX_OCTETS, 0x000000), REG(SYS_COUNT_RX_UNICAST, 0x000004), REG(SYS_COUNT_RX_MULTICAST, 0x000008), @@ -288,9 +343,8 @@ const u32 vsc7514_sys_regmap[] = { REG(SYS_PTP_NXT, 0x0006c0), REG(SYS_PTP_CFG, 0x0006c4), }; -EXPORT_SYMBOL(vsc7514_sys_regmap); -const u32 vsc7514_vcap_regmap[] = { +static const u32 vsc7514_vcap_regmap[] = { /* VCAP_CORE_CFG */ REG(VCAP_CORE_UPDATE_CTRL, 0x000000), REG(VCAP_CORE_MV_CFG, 0x000004), @@ -312,9 +366,8 @@ const u32 vsc7514_vcap_regmap[] = { REG(VCAP_CONST_CORE_CNT, 0x0003b8), REG(VCAP_CONST_IF_CNT, 0x0003bc), }; -EXPORT_SYMBOL(vsc7514_vcap_regmap); -const u32 vsc7514_ptp_regmap[] = { +static const u32 vsc7514_ptp_regmap[] = { REG(PTP_PIN_CFG, 0x000000), REG(PTP_PIN_TOD_SEC_MSB, 0x000004), REG(PTP_PIN_TOD_SEC_LSB, 0x000008), @@ -325,9 +378,8 @@ const u32 vsc7514_ptp_regmap[] = { REG(PTP_CLK_CFG_ADJ_CFG, 0x0000a4), REG(PTP_CLK_CFG_ADJ_FREQ, 0x0000a8), }; -EXPORT_SYMBOL(vsc7514_ptp_regmap); -const u32 vsc7514_dev_gmii_regmap[] = { +static const u32 vsc7514_dev_gmii_regmap[] = { REG(DEV_CLOCK_CFG, 0x0), REG(DEV_PORT_MISC, 0x4), REG(DEV_EVENTS, 0x8), @@ -368,9 +420,22 @@ const u32 vsc7514_dev_gmii_regmap[] = { REG(DEV_PCS_FX100_CFG, 0x94), REG(DEV_PCS_FX100_STATUS, 0x98), }; -EXPORT_SYMBOL(vsc7514_dev_gmii_regmap); -const struct vcap_field vsc7514_vcap_es0_keys[] = { +const u32 *vsc7514_regmap[TARGET_MAX] = { + [ANA] = vsc7514_ana_regmap, + [QS] = vsc7514_qs_regmap, + [QSYS] = vsc7514_qsys_regmap, + [REW] = vsc7514_rew_regmap, + [SYS] = vsc7514_sys_regmap, + [S0] = vsc7514_vcap_regmap, + [S1] = vsc7514_vcap_regmap, + [S2] = vsc7514_vcap_regmap, + [PTP] = vsc7514_ptp_regmap, + [DEV_GMII] = vsc7514_dev_gmii_regmap, +}; +EXPORT_SYMBOL(vsc7514_regmap); + +static const struct vcap_field vsc7514_vcap_es0_keys[] = { [VCAP_ES0_EGR_PORT] = { 0, 4 }, [VCAP_ES0_IGR_PORT] = { 4, 4 }, [VCAP_ES0_RSV] = { 8, 2 }, @@ -380,9 +445,8 @@ const struct vcap_field vsc7514_vcap_es0_keys[] = { [VCAP_ES0_DP] = { 24, 1 }, [VCAP_ES0_PCP] = { 25, 3 }, }; -EXPORT_SYMBOL(vsc7514_vcap_es0_keys); -const struct vcap_field vsc7514_vcap_es0_actions[] = { +static const struct vcap_field vsc7514_vcap_es0_actions[] = { [VCAP_ES0_ACT_PUSH_OUTER_TAG] = { 0, 2 }, [VCAP_ES0_ACT_PUSH_INNER_TAG] = { 2, 1 }, [VCAP_ES0_ACT_TAG_A_TPID_SEL] = { 3, 2 }, @@ -402,9 +466,8 @@ const struct vcap_field vsc7514_vcap_es0_actions[] = { [VCAP_ES0_ACT_RSV] = { 49, 24 }, [VCAP_ES0_ACT_HIT_STICKY] = { 73, 1 }, }; -EXPORT_SYMBOL(vsc7514_vcap_es0_actions); -const struct vcap_field vsc7514_vcap_is1_keys[] = { +static const struct vcap_field vsc7514_vcap_is1_keys[] = { [VCAP_IS1_HK_TYPE] = { 0, 1 }, [VCAP_IS1_HK_LOOKUP] = { 1, 2 }, [VCAP_IS1_HK_IGR_PORT_MASK] = { 3, 12 }, @@ -454,9 +517,8 @@ const struct vcap_field vsc7514_vcap_is1_keys[] = { [VCAP_IS1_HK_IP4_L4_RNG] = { 148, 8 }, [VCAP_IS1_HK_IP4_IP_PAYLOAD_S1_5TUPLE] = { 156, 32 }, }; -EXPORT_SYMBOL(vsc7514_vcap_is1_keys); -const struct vcap_field vsc7514_vcap_is1_actions[] = { +static const struct vcap_field vsc7514_vcap_is1_actions[] = { [VCAP_IS1_ACT_DSCP_ENA] = { 0, 1 }, [VCAP_IS1_ACT_DSCP_VAL] = { 1, 6 }, [VCAP_IS1_ACT_QOS_ENA] = { 7, 1 }, @@ -479,9 +541,8 @@ const struct vcap_field vsc7514_vcap_is1_actions[] = { [VCAP_IS1_ACT_CUSTOM_ACE_TYPE_ENA] = { 74, 4 }, [VCAP_IS1_ACT_HIT_STICKY] = { 78, 1 }, }; -EXPORT_SYMBOL(vsc7514_vcap_is1_actions); -const struct vcap_field vsc7514_vcap_is2_keys[] = { +static const struct vcap_field vsc7514_vcap_is2_keys[] = { /* Common: 46 bits */ [VCAP_IS2_TYPE] = { 0, 4 }, [VCAP_IS2_HK_FIRST] = { 4, 1 }, @@ -560,9 +621,8 @@ const struct vcap_field vsc7514_vcap_is2_keys[] = { [VCAP_IS2_HK_OAM_CCM_CNTS_EQ0] = { 186, 1 }, [VCAP_IS2_HK_OAM_IS_Y1731] = { 187, 1 }, }; -EXPORT_SYMBOL(vsc7514_vcap_is2_keys); -const struct vcap_field vsc7514_vcap_is2_actions[] = { +static const struct vcap_field vsc7514_vcap_is2_actions[] = { [VCAP_IS2_ACT_HIT_ME_ONCE] = { 0, 1 }, [VCAP_IS2_ACT_CPU_COPY_ENA] = { 1, 1 }, [VCAP_IS2_ACT_CPU_QU_NUM] = { 2, 3 }, @@ -579,4 +639,47 @@ const struct vcap_field vsc7514_vcap_is2_actions[] = { [VCAP_IS2_ACT_ACL_ID] = { 43, 6 }, [VCAP_IS2_ACT_HIT_CNT] = { 49, 32 }, }; -EXPORT_SYMBOL(vsc7514_vcap_is2_actions); + +struct vcap_props vsc7514_vcap_props[] = { + [VCAP_ES0] = { + .action_type_width = 0, + .action_table = { + [ES0_ACTION_TYPE_NORMAL] = { + .width = 73, /* HIT_STICKY not included */ + .count = 1, + }, + }, + .target = S0, + .keys = vsc7514_vcap_es0_keys, + .actions = vsc7514_vcap_es0_actions, + }, + [VCAP_IS1] = { + .action_type_width = 0, + .action_table = { + [IS1_ACTION_TYPE_NORMAL] = { + .width = 78, /* HIT_STICKY not included */ + .count = 4, + }, + }, + .target = S1, + .keys = vsc7514_vcap_is1_keys, + .actions = vsc7514_vcap_is1_actions, + }, + [VCAP_IS2] = { + .action_type_width = 1, + .action_table = { + [IS2_ACTION_TYPE_NORMAL] = { + .width = 49, + .count = 2 + }, + [IS2_ACTION_TYPE_SMAC_SIP] = { + .width = 6, + .count = 4 + }, + }, + .target = S2, + .keys = vsc7514_vcap_is2_keys, + .actions = vsc7514_vcap_is2_actions, + }, +}; +EXPORT_SYMBOL(vsc7514_vcap_props); diff --git a/drivers/net/ethernet/netronome/nfp/Makefile b/drivers/net/ethernet/netronome/nfp/Makefile index c90d35f5ebca..808599b8066e 100644 --- a/drivers/net/ethernet/netronome/nfp/Makefile +++ b/drivers/net/ethernet/netronome/nfp/Makefile @@ -80,7 +80,7 @@ nfp-objs += \ abm/main.o endif -nfp-$(CONFIG_NFP_NET_IPSEC) += crypto/ipsec.o nfd3/ipsec.o +nfp-$(CONFIG_NFP_NET_IPSEC) += crypto/ipsec.o nfd3/ipsec.o nfdk/ipsec.o nfp-$(CONFIG_NFP_DEBUG) += nfp_net_debugfs.o diff --git a/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c b/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c index b44263177981..b8bc89fc2540 100644 --- a/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c +++ b/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c @@ -10,6 +10,7 @@ #include <linux/ktime.h> #include <net/xfrm.h> +#include "../nfpcore/nfp_dev.h" #include "../nfp_net_ctrl.h" #include "../nfp_net.h" #include "crypto.h" @@ -330,6 +331,10 @@ static int nfp_net_xfrm_add_state(struct xfrm_state *x, trunc_len = -1; break; case SADB_AALG_MD5HMAC: + if (nn->pdev->device == PCI_DEVICE_ID_NFP3800) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported authentication algorithm"); + return -EINVAL; + } set_md5hmac(cfg, &trunc_len); break; case SADB_AALG_SHA1HMAC: @@ -373,6 +378,10 @@ static int nfp_net_xfrm_add_state(struct xfrm_state *x, cfg->ctrl_word.cipher = NFP_IPSEC_CIPHER_NULL; break; case SADB_EALG_3DESCBC: + if (nn->pdev->device == PCI_DEVICE_ID_NFP3800) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported encryption algorithm for offload"); + return -EINVAL; + } cfg->ctrl_word.cimode = NFP_IPSEC_CIMODE_CBC; cfg->ctrl_word.cipher = NFP_IPSEC_CIPHER_3DES; break; diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c index f693119541d5..d23830b5bcb8 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c +++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c @@ -1964,6 +1964,27 @@ int nfp_fl_ct_stats(struct flow_cls_offload *flow, return 0; } +static bool +nfp_fl_ct_offload_nft_supported(struct flow_cls_offload *flow) +{ + struct flow_rule *flow_rule = flow->rule; + struct flow_action *flow_action = + &flow_rule->action; + struct flow_action_entry *act; + int i; + + flow_action_for_each(i, act, flow_action) { + if (act->id == FLOW_ACTION_CT_METADATA) { + enum ip_conntrack_info ctinfo = + act->ct_metadata.cookie & NFCT_INFOMASK; + + return ctinfo != IP_CT_NEW; + } + } + + return false; +} + static int nfp_fl_ct_offload_nft_flow(struct nfp_fl_ct_zone_entry *zt, struct flow_cls_offload *flow) { @@ -1976,6 +1997,9 @@ nfp_fl_ct_offload_nft_flow(struct nfp_fl_ct_zone_entry *zt, struct flow_cls_offl extack = flow->common.extack; switch (flow->command) { case FLOW_CLS_REPLACE: + if (!nfp_fl_ct_offload_nft_supported(flow)) + return -EOPNOTSUPP; + /* Netfilter can request offload multiple times for the same * flow - protect against adding duplicates. */ diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index a8678d5612ee..060a77f2265d 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -460,6 +460,7 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, sizeof(struct nfp_tun_neigh_v4); unsigned long cookie = (unsigned long)neigh; struct nfp_flower_priv *priv = app->priv; + struct nfp_tun_neigh_lag lag_info; struct nfp_neigh_entry *nn_entry; u32 port_id; u8 mtype; @@ -468,6 +469,11 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, if (!port_id) return; + if ((port_id & NFP_FL_LAG_OUT) == NFP_FL_LAG_OUT) { + memset(&lag_info, 0, sizeof(struct nfp_tun_neigh_lag)); + nfp_flower_lag_get_info_from_netdev(app, netdev, &lag_info); + } + spin_lock_bh(&priv->predt_lock); nn_entry = rhashtable_lookup_fast(&priv->neigh_table, &cookie, neigh_table_params); @@ -515,7 +521,7 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, neigh_ha_snapshot(common->dst_addr, neigh, netdev); if ((port_id & NFP_FL_LAG_OUT) == NFP_FL_LAG_OUT) - nfp_flower_lag_get_info_from_netdev(app, netdev, lag); + memcpy(lag, &lag_info, sizeof(struct nfp_tun_neigh_lag)); common->port_id = cpu_to_be32(port_id); if (rhashtable_insert_fast(&priv->neigh_table, diff --git a/drivers/net/ethernet/netronome/nfp/nfd3/dp.c b/drivers/net/ethernet/netronome/nfp/nfd3/dp.c index 861082c5dbff..59fb0583cc08 100644 --- a/drivers/net/ethernet/netronome/nfp/nfd3/dp.c +++ b/drivers/net/ethernet/netronome/nfp/nfd3/dp.c @@ -192,10 +192,10 @@ static int nfp_nfd3_prep_tx_meta(struct nfp_net_dp *dp, struct sk_buff *skb, return 0; md_bytes = sizeof(meta_id) + - !!md_dst * NFP_NET_META_PORTID_SIZE + - !!tls_handle * NFP_NET_META_CONN_HANDLE_SIZE + - vlan_insert * NFP_NET_META_VLAN_SIZE + - *ipsec * NFP_NET_META_IPSEC_FIELD_SIZE; /* IPsec has 12 bytes of metadata */ + (!!md_dst ? NFP_NET_META_PORTID_SIZE : 0) + + (!!tls_handle ? NFP_NET_META_CONN_HANDLE_SIZE : 0) + + (vlan_insert ? NFP_NET_META_VLAN_SIZE : 0) + + (*ipsec ? NFP_NET_META_IPSEC_FIELD_SIZE : 0); if (unlikely(skb_cow_head(skb, md_bytes))) return -ENOMEM; @@ -226,9 +226,6 @@ static int nfp_nfd3_prep_tx_meta(struct nfp_net_dp *dp, struct sk_buff *skb, meta_id |= NFP_NET_META_VLAN; } if (*ipsec) { - /* IPsec has three consecutive 4-bit IPsec metadata types, - * so in total IPsec has three 4 bytes of metadata. - */ data -= NFP_NET_META_IPSEC_SIZE; put_unaligned_be32(offload_info.seq_hi, data); data -= NFP_NET_META_IPSEC_SIZE; diff --git a/drivers/net/ethernet/netronome/nfp/nfdk/dp.c b/drivers/net/ethernet/netronome/nfp/nfdk/dp.c index ccacb6ab6c39..d60c0e991a91 100644 --- a/drivers/net/ethernet/netronome/nfp/nfdk/dp.c +++ b/drivers/net/ethernet/netronome/nfp/nfdk/dp.c @@ -6,6 +6,7 @@ #include <linux/overflow.h> #include <linux/sizes.h> #include <linux/bitfield.h> +#include <net/xfrm.h> #include "../nfp_app.h" #include "../nfp_net.h" @@ -172,25 +173,32 @@ close_block: static int nfp_nfdk_prep_tx_meta(struct nfp_net_dp *dp, struct nfp_app *app, - struct sk_buff *skb) + struct sk_buff *skb, bool *ipsec) { struct metadata_dst *md_dst = skb_metadata_dst(skb); + struct nfp_ipsec_offload offload_info; unsigned char *data; bool vlan_insert; u32 meta_id = 0; int md_bytes; +#ifdef CONFIG_NFP_NET_IPSEC + if (xfrm_offload(skb)) + *ipsec = nfp_net_ipsec_tx_prep(dp, skb, &offload_info); +#endif + if (unlikely(md_dst && md_dst->type != METADATA_HW_PORT_MUX)) md_dst = NULL; vlan_insert = skb_vlan_tag_present(skb) && (dp->ctrl & NFP_NET_CFG_CTRL_TXVLAN_V2); - if (!(md_dst || vlan_insert)) + if (!(md_dst || vlan_insert || *ipsec)) return 0; md_bytes = sizeof(meta_id) + - !!md_dst * NFP_NET_META_PORTID_SIZE + - vlan_insert * NFP_NET_META_VLAN_SIZE; + (!!md_dst ? NFP_NET_META_PORTID_SIZE : 0) + + (vlan_insert ? NFP_NET_META_VLAN_SIZE : 0) + + (*ipsec ? NFP_NET_META_IPSEC_FIELD_SIZE : 0); if (unlikely(skb_cow_head(skb, md_bytes))) return -ENOMEM; @@ -212,6 +220,17 @@ nfp_nfdk_prep_tx_meta(struct nfp_net_dp *dp, struct nfp_app *app, meta_id |= NFP_NET_META_VLAN; } + if (*ipsec) { + data -= NFP_NET_META_IPSEC_SIZE; + put_unaligned_be32(offload_info.seq_hi, data); + data -= NFP_NET_META_IPSEC_SIZE; + put_unaligned_be32(offload_info.seq_low, data); + data -= NFP_NET_META_IPSEC_SIZE; + put_unaligned_be32(offload_info.handle - 1, data); + meta_id <<= NFP_NET_META_IPSEC_FIELD_SIZE; + meta_id |= NFP_NET_META_IPSEC << 8 | NFP_NET_META_IPSEC << 4 | NFP_NET_META_IPSEC; + } + meta_id = FIELD_PREP(NFDK_META_LEN, md_bytes) | FIELD_PREP(NFDK_META_FIELDS, meta_id); @@ -243,6 +262,7 @@ netdev_tx_t nfp_nfdk_tx(struct sk_buff *skb, struct net_device *netdev) struct nfp_net_dp *dp; int nr_frags, wr_idx; dma_addr_t dma_addr; + bool ipsec = false; u64 metadata; dp = &nn->dp; @@ -263,7 +283,7 @@ netdev_tx_t nfp_nfdk_tx(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_BUSY; } - metadata = nfp_nfdk_prep_tx_meta(dp, nn->app, skb); + metadata = nfp_nfdk_prep_tx_meta(dp, nn->app, skb, &ipsec); if (unlikely((int)metadata < 0)) goto err_flush; @@ -361,6 +381,9 @@ netdev_tx_t nfp_nfdk_tx(struct sk_buff *skb, struct net_device *netdev) (txd - 1)->dma_len_type = cpu_to_le16(dlen_type | NFDK_DESC_TX_EOP); + if (ipsec) + metadata = nfp_nfdk_ipsec_tx(metadata, skb); + if (!skb_is_gso(skb)) { real_len = skb->len; /* Metadata desc */ @@ -760,6 +783,15 @@ nfp_nfdk_parse_meta(struct net_device *netdev, struct nfp_meta_parsed *meta, return false; data += sizeof(struct nfp_net_tls_resync_req); break; +#ifdef CONFIG_NFP_NET_IPSEC + case NFP_NET_META_IPSEC: + /* Note: IPsec packet could have zero saidx, so need add 1 + * to indicate packet is IPsec packet within driver. + */ + meta->ipsec_saidx = get_unaligned_be32(data) + 1; + data += 4; + break; +#endif default: return true; } @@ -1186,6 +1218,13 @@ static int nfp_nfdk_rx(struct nfp_net_rx_ring *rx_ring, int budget) continue; } +#ifdef CONFIG_NFP_NET_IPSEC + if (meta.ipsec_saidx != 0 && unlikely(nfp_net_ipsec_rx(&meta, skb))) { + nfp_nfdk_rx_drop(dp, r_vec, rx_ring, NULL, skb); + continue; + } +#endif + if (meta_len_xdp) skb_metadata_set(skb, meta_len_xdp); diff --git a/drivers/net/ethernet/netronome/nfp/nfdk/ipsec.c b/drivers/net/ethernet/netronome/nfp/nfdk/ipsec.c new file mode 100644 index 000000000000..58d8f59eb885 --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/nfdk/ipsec.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2023 Corigine, Inc */ + +#include <net/xfrm.h> + +#include "../nfp_net.h" +#include "nfdk.h" + +u64 nfp_nfdk_ipsec_tx(u64 flags, struct sk_buff *skb) +{ + struct xfrm_state *x = xfrm_input_state(skb); + + if (x->xso.dev && (x->xso.dev->features & NETIF_F_HW_ESP_TX_CSUM)) + flags |= NFDK_DESC_TX_L3_CSUM | NFDK_DESC_TX_L4_CSUM; + + return flags; +} diff --git a/drivers/net/ethernet/netronome/nfp/nfdk/nfdk.h b/drivers/net/ethernet/netronome/nfp/nfdk/nfdk.h index 0ea51d9f2325..fe55980348e9 100644 --- a/drivers/net/ethernet/netronome/nfp/nfdk/nfdk.h +++ b/drivers/net/ethernet/netronome/nfp/nfdk/nfdk.h @@ -125,4 +125,12 @@ nfp_nfdk_ctrl_tx_one(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, void nfp_nfdk_ctrl_poll(struct tasklet_struct *t); void nfp_nfdk_rx_ring_fill_freelist(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring); +#ifndef CONFIG_NFP_NET_IPSEC +static inline u64 nfp_nfdk_ipsec_tx(u64 flags, struct sk_buff *skb) +{ + return flags; +} +#else +u64 nfp_nfdk_ipsec_tx(u64 flags, struct sk_buff *skb); +#endif #endif diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index e9d228d7a95d..918319f965b3 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -293,35 +293,131 @@ nfp_net_set_fec_link_mode(struct nfp_eth_table_port *eth_port, } } -static const u16 nfp_eth_media_table[] = { - [NFP_MEDIA_1000BASE_CX] = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, - [NFP_MEDIA_1000BASE_KX] = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, - [NFP_MEDIA_10GBASE_KX4] = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, - [NFP_MEDIA_10GBASE_KR] = ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, - [NFP_MEDIA_10GBASE_CX4] = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, - [NFP_MEDIA_10GBASE_CR] = ETHTOOL_LINK_MODE_10000baseCR_Full_BIT, - [NFP_MEDIA_10GBASE_SR] = ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, - [NFP_MEDIA_10GBASE_ER] = ETHTOOL_LINK_MODE_10000baseER_Full_BIT, - [NFP_MEDIA_25GBASE_KR] = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, - [NFP_MEDIA_25GBASE_KR_S] = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, - [NFP_MEDIA_25GBASE_CR] = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, - [NFP_MEDIA_25GBASE_CR_S] = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, - [NFP_MEDIA_25GBASE_SR] = ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, - [NFP_MEDIA_40GBASE_CR4] = ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, - [NFP_MEDIA_40GBASE_KR4] = ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, - [NFP_MEDIA_40GBASE_SR4] = ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT, - [NFP_MEDIA_40GBASE_LR4] = ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT, - [NFP_MEDIA_50GBASE_KR] = ETHTOOL_LINK_MODE_50000baseKR_Full_BIT, - [NFP_MEDIA_50GBASE_SR] = ETHTOOL_LINK_MODE_50000baseSR_Full_BIT, - [NFP_MEDIA_50GBASE_CR] = ETHTOOL_LINK_MODE_50000baseCR_Full_BIT, - [NFP_MEDIA_50GBASE_LR] = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, - [NFP_MEDIA_50GBASE_ER] = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, - [NFP_MEDIA_50GBASE_FR] = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, - [NFP_MEDIA_100GBASE_KR4] = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, - [NFP_MEDIA_100GBASE_SR4] = ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT, - [NFP_MEDIA_100GBASE_CR4] = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, - [NFP_MEDIA_100GBASE_KP4] = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, - [NFP_MEDIA_100GBASE_CR10] = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, +static const struct nfp_eth_media_link_mode { + u16 ethtool_link_mode; + u16 speed; +} nfp_eth_media_table[NFP_MEDIA_LINK_MODES_NUMBER] = { + [NFP_MEDIA_1000BASE_CX] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, + .speed = NFP_SPEED_1G, + }, + [NFP_MEDIA_1000BASE_KX] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, + .speed = NFP_SPEED_1G, + }, + [NFP_MEDIA_10GBASE_KX4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_10GBASE_KR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_10GBASE_CX4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_10GBASE_CR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseCR_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_10GBASE_SR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_10GBASE_ER] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseER_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_25GBASE_KR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, + .speed = NFP_SPEED_25G, + }, + [NFP_MEDIA_25GBASE_KR_S] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, + .speed = NFP_SPEED_25G, + }, + [NFP_MEDIA_25GBASE_CR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, + .speed = NFP_SPEED_25G, + }, + [NFP_MEDIA_25GBASE_CR_S] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, + .speed = NFP_SPEED_25G, + }, + [NFP_MEDIA_25GBASE_SR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, + .speed = NFP_SPEED_25G, + }, + [NFP_MEDIA_40GBASE_CR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, + .speed = NFP_SPEED_40G, + }, + [NFP_MEDIA_40GBASE_KR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, + .speed = NFP_SPEED_40G, + }, + [NFP_MEDIA_40GBASE_SR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT, + .speed = NFP_SPEED_40G, + }, + [NFP_MEDIA_40GBASE_LR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT, + .speed = NFP_SPEED_40G, + }, + [NFP_MEDIA_50GBASE_KR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseKR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_50GBASE_SR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseSR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_50GBASE_CR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseCR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_50GBASE_LR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_50GBASE_ER] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_50GBASE_FR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_100GBASE_KR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, + .speed = NFP_SPEED_100G, + }, + [NFP_MEDIA_100GBASE_SR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT, + .speed = NFP_SPEED_100G, + }, + [NFP_MEDIA_100GBASE_CR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, + .speed = NFP_SPEED_100G, + }, + [NFP_MEDIA_100GBASE_KP4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, + .speed = NFP_SPEED_100G, + }, + [NFP_MEDIA_100GBASE_CR10] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, + .speed = NFP_SPEED_100G, + }, +}; + +static const unsigned int nfp_eth_speed_map[NFP_SUP_SPEED_NUMBER] = { + [NFP_SPEED_1G] = SPEED_1000, + [NFP_SPEED_10G] = SPEED_10000, + [NFP_SPEED_25G] = SPEED_25000, + [NFP_SPEED_40G] = SPEED_40000, + [NFP_SPEED_50G] = SPEED_50000, + [NFP_SPEED_100G] = SPEED_100000, }; static void nfp_add_media_link_mode(struct nfp_port *port, @@ -334,8 +430,12 @@ static void nfp_add_media_link_mode(struct nfp_port *port, }; struct nfp_cpp *cpp = port->app->cpp; - if (nfp_eth_read_media(cpp, ðm)) + if (nfp_eth_read_media(cpp, ðm)) { + bitmap_fill(port->speed_bitmap, NFP_SUP_SPEED_NUMBER); return; + } + + bitmap_zero(port->speed_bitmap, NFP_SUP_SPEED_NUMBER); for (u32 i = 0; i < 2; i++) { supported_modes[i] = le64_to_cpu(ethm.supported_modes[i]); @@ -344,20 +444,26 @@ static void nfp_add_media_link_mode(struct nfp_port *port, for (u32 i = 0; i < NFP_MEDIA_LINK_MODES_NUMBER; i++) { if (i < 64) { - if (supported_modes[0] & BIT_ULL(i)) - __set_bit(nfp_eth_media_table[i], + if (supported_modes[0] & BIT_ULL(i)) { + __set_bit(nfp_eth_media_table[i].ethtool_link_mode, cmd->link_modes.supported); + __set_bit(nfp_eth_media_table[i].speed, + port->speed_bitmap); + } if (advertised_modes[0] & BIT_ULL(i)) - __set_bit(nfp_eth_media_table[i], + __set_bit(nfp_eth_media_table[i].ethtool_link_mode, cmd->link_modes.advertising); } else { - if (supported_modes[1] & BIT_ULL(i - 64)) - __set_bit(nfp_eth_media_table[i], + if (supported_modes[1] & BIT_ULL(i - 64)) { + __set_bit(nfp_eth_media_table[i].ethtool_link_mode, cmd->link_modes.supported); + __set_bit(nfp_eth_media_table[i].speed, + port->speed_bitmap); + } if (advertised_modes[1] & BIT_ULL(i - 64)) - __set_bit(nfp_eth_media_table[i], + __set_bit(nfp_eth_media_table[i].ethtool_link_mode, cmd->link_modes.advertising); } } @@ -468,6 +574,22 @@ nfp_net_set_link_ksettings(struct net_device *netdev, if (cmd->base.speed != SPEED_UNKNOWN) { u32 speed = cmd->base.speed / eth_port->lanes; + bool is_supported = false; + + for (u32 i = 0; i < NFP_SUP_SPEED_NUMBER; i++) { + if (cmd->base.speed == nfp_eth_speed_map[i] && + test_bit(i, port->speed_bitmap)) { + is_supported = true; + break; + } + } + + if (!is_supported) { + netdev_err(netdev, "Speed %u is not supported.\n", + cmd->base.speed); + err = -EINVAL; + goto err_bad_set; + } if (req_aneg) { netdev_err(netdev, "Speed changing is not allowed when working on autoneg mode.\n"); @@ -1908,12 +2030,12 @@ nfp_net_get_eeprom(struct net_device *netdev, struct nfp_app *app = nfp_app_from_netdev(netdev); u8 buf[NFP_EEPROM_LEN] = {}; - if (eeprom->len == 0) - return -EINVAL; - if (nfp_net_get_port_mac_by_hwinfo(netdev, buf)) return -EOPNOTSUPP; + if (eeprom->len == 0) + return -EINVAL; + eeprom->magic = app->pdev->vendor | (app->pdev->device << 16); memcpy(bytes, buf + eeprom->offset, eeprom->len); @@ -1927,15 +2049,15 @@ nfp_net_set_eeprom(struct net_device *netdev, struct nfp_app *app = nfp_app_from_netdev(netdev); u8 buf[NFP_EEPROM_LEN] = {}; + if (nfp_net_get_port_mac_by_hwinfo(netdev, buf)) + return -EOPNOTSUPP; + if (eeprom->len == 0) return -EINVAL; if (eeprom->magic != (app->pdev->vendor | app->pdev->device << 16)) return -EINVAL; - if (nfp_net_get_port_mac_by_hwinfo(netdev, buf)) - return -EOPNOTSUPP; - memcpy(buf + eeprom->offset, bytes, eeprom->len); if (nfp_net_set_port_mac_by_hwinfo(netdev, buf)) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.h b/drivers/net/ethernet/netronome/nfp/nfp_port.h index f8cd157ca1d7..9c04f9f0e2c9 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_port.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_port.h @@ -38,6 +38,16 @@ enum nfp_port_flags { NFP_PORT_CHANGED = 0, }; +enum { + NFP_SPEED_1G, + NFP_SPEED_10G, + NFP_SPEED_25G, + NFP_SPEED_40G, + NFP_SPEED_50G, + NFP_SPEED_100G, + NFP_SUP_SPEED_NUMBER +}; + /** * struct nfp_port - structure representing NFP port * @netdev: backpointer to associated netdev @@ -52,6 +62,7 @@ enum nfp_port_flags { * @eth_forced: for %NFP_PORT_PHYS_PORT port is forced UP or DOWN, don't change * @eth_port: for %NFP_PORT_PHYS_PORT translated ETH Table port entry * @eth_stats: for %NFP_PORT_PHYS_PORT MAC stats if available + * @speed_bitmap: for %NFP_PORT_PHYS_PORT supported speed bitmap * @pf_id: for %NFP_PORT_PF_PORT, %NFP_PORT_VF_PORT ID of the PCI PF (0-3) * @vf_id: for %NFP_PORT_VF_PORT ID of the PCI VF within @pf_id * @pf_split: for %NFP_PORT_PF_PORT %true if PCI PF has more than one vNIC @@ -78,6 +89,7 @@ struct nfp_port { bool eth_forced; struct nfp_eth_table_port *eth_port; u8 __iomem *eth_stats; + DECLARE_BITMAP(speed_bitmap, NFP_SUP_SPEED_NUMBER); }; /* NFP_PORT_PF_PORT, NFP_PORT_VF_PORT */ struct { diff --git a/drivers/net/ethernet/netronome/nfp/nic/main.c b/drivers/net/ethernet/netronome/nfp/nic/main.c index f78c2447d45b..9dd5afe37f6e 100644 --- a/drivers/net/ethernet/netronome/nfp/nic/main.c +++ b/drivers/net/ethernet/netronome/nfp/nic/main.c @@ -32,9 +32,12 @@ static void nfp_nic_sriov_disable(struct nfp_app *app) static int nfp_nic_vnic_init(struct nfp_app *app, struct nfp_net *nn) { - nfp_nic_dcb_init(nn); + return nfp_nic_dcb_init(nn); +} - return 0; +static void nfp_nic_vnic_clean(struct nfp_app *app, struct nfp_net *nn) +{ + nfp_nic_dcb_clean(nn); } static int nfp_nic_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, @@ -72,4 +75,5 @@ const struct nfp_app_type app_nic = { .sriov_disable = nfp_nic_sriov_disable, .vnic_init = nfp_nic_vnic_init, + .vnic_clean = nfp_nic_vnic_clean, }; diff --git a/drivers/net/ethernet/netronome/nfp/nic/main.h b/drivers/net/ethernet/netronome/nfp/nic/main.h index 7ba04451b8ba..094374df42b8 100644 --- a/drivers/net/ethernet/netronome/nfp/nic/main.h +++ b/drivers/net/ethernet/netronome/nfp/nic/main.h @@ -33,7 +33,7 @@ struct nfp_dcb { int nfp_nic_dcb_init(struct nfp_net *nn); void nfp_nic_dcb_clean(struct nfp_net *nn); #else -static inline int nfp_nic_dcb_init(struct nfp_net *nn) {return 0; } +static inline int nfp_nic_dcb_init(struct nfp_net *nn) { return 0; } static inline void nfp_nic_dcb_clean(struct nfp_net *nn) {} #endif diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index 626b9113e7c4..d911f4fd9af6 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -708,9 +708,16 @@ void ionic_q_post(struct ionic_queue *q, bool ring_doorbell, ionic_desc_cb cb, q->lif->index, q->name, q->hw_type, q->hw_index, q->head_idx, ring_doorbell); - if (ring_doorbell) + if (ring_doorbell) { ionic_dbell_ring(lif->kern_dbpage, q->hw_type, q->dbval | q->head_idx); + + q->dbell_jiffies = jiffies; + + if (q_to_qcq(q)->napi_qcq) + mod_timer(&q_to_qcq(q)->napi_qcq->napi_deadline, + jiffies + IONIC_NAPI_DEADLINE); + } } static bool ionic_q_is_posted(struct ionic_queue *q, unsigned int pos) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h index 2a1d7b9c07e7..bce3ca38669b 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h @@ -25,6 +25,12 @@ #define IONIC_DEV_INFO_REG_COUNT 32 #define IONIC_DEV_CMD_REG_COUNT 32 +#define IONIC_NAPI_DEADLINE (HZ / 200) /* 5ms */ +#define IONIC_ADMIN_DOORBELL_DEADLINE (HZ / 2) /* 500ms */ +#define IONIC_TX_DOORBELL_DEADLINE (HZ / 100) /* 10ms */ +#define IONIC_RX_MIN_DOORBELL_DEADLINE (HZ / 100) /* 10ms */ +#define IONIC_RX_MAX_DOORBELL_DEADLINE (HZ * 5) /* 5s */ + struct ionic_dev_bar { void __iomem *vaddr; phys_addr_t bus_addr; @@ -216,6 +222,8 @@ struct ionic_queue { struct ionic_lif *lif; struct ionic_desc_info *info; u64 dbval; + unsigned long dbell_deadline; + unsigned long dbell_jiffies; u16 head_idx; u16 tail_idx; unsigned int index; @@ -361,4 +369,8 @@ void ionic_q_service(struct ionic_queue *q, struct ionic_cq_info *cq_info, int ionic_heartbeat_check(struct ionic *ionic); bool ionic_is_fw_running(struct ionic_dev *idev); +bool ionic_adminq_poke_doorbell(struct ionic_queue *q); +bool ionic_txq_poke_doorbell(struct ionic_queue *q); +bool ionic_rxq_poke_doorbell(struct ionic_queue *q); + #endif /* _IONIC_DEV_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 4dd16c487f2b..63a78a9ac241 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -16,6 +16,7 @@ #include "ionic.h" #include "ionic_bus.h" +#include "ionic_dev.h" #include "ionic_lif.h" #include "ionic_txrx.h" #include "ionic_ethtool.h" @@ -200,6 +201,13 @@ void ionic_link_status_check_request(struct ionic_lif *lif, bool can_sleep) } } +static void ionic_napi_deadline(struct timer_list *timer) +{ + struct ionic_qcq *qcq = container_of(timer, struct ionic_qcq, napi_deadline); + + napi_schedule(&qcq->napi); +} + static irqreturn_t ionic_isr(int irq, void *data) { struct napi_struct *napi = data; @@ -269,6 +277,7 @@ static int ionic_qcq_enable(struct ionic_qcq *qcq) .oper = IONIC_Q_ENABLE, }, }; + int ret; idev = &lif->ionic->idev; dev = lif->ionic->dev; @@ -276,16 +285,24 @@ static int ionic_qcq_enable(struct ionic_qcq *qcq) dev_dbg(dev, "q_enable.index %d q_enable.qtype %d\n", ctx.cmd.q_control.index, ctx.cmd.q_control.type); + if (qcq->flags & IONIC_QCQ_F_INTR) + ionic_intr_clean(idev->intr_ctrl, qcq->intr.index); + + ret = ionic_adminq_post_wait(lif, &ctx); + if (ret) + return ret; + + if (qcq->napi.poll) + napi_enable(&qcq->napi); + if (qcq->flags & IONIC_QCQ_F_INTR) { irq_set_affinity_hint(qcq->intr.vector, &qcq->intr.affinity_mask); - napi_enable(&qcq->napi); - ionic_intr_clean(idev->intr_ctrl, qcq->intr.index); ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, IONIC_INTR_MASK_CLEAR); } - return ionic_adminq_post_wait(lif, &ctx); + return 0; } static int ionic_qcq_disable(struct ionic_lif *lif, struct ionic_qcq *qcq, int fw_err) @@ -316,6 +333,7 @@ static int ionic_qcq_disable(struct ionic_lif *lif, struct ionic_qcq *qcq, int f synchronize_irq(qcq->intr.vector); irq_set_affinity_hint(qcq->intr.vector, NULL); napi_disable(&qcq->napi); + del_timer_sync(&qcq->napi_deadline); } /* If there was a previous fw communcation error, don't bother with @@ -451,6 +469,7 @@ static void ionic_link_qcq_interrupts(struct ionic_qcq *src_qcq, n_qcq->intr.vector = src_qcq->intr.vector; n_qcq->intr.index = src_qcq->intr.index; + n_qcq->napi_qcq = src_qcq->napi_qcq; } static int ionic_alloc_qcq_interrupt(struct ionic_lif *lif, struct ionic_qcq *qcq) @@ -564,13 +583,15 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, } if (flags & IONIC_QCQ_F_NOTIFYQ) { - int q_size, cq_size; + int q_size; - /* q & cq need to be contiguous in case of notifyq */ + /* q & cq need to be contiguous in NotifyQ, so alloc it all in q + * and don't alloc qc. We leave new->qc_size and new->qc_base + * as 0 to be sure we don't try to free it later. + */ q_size = ALIGN(num_descs * desc_size, PAGE_SIZE); - cq_size = ALIGN(num_descs * cq_desc_size, PAGE_SIZE); - - new->q_size = PAGE_SIZE + q_size + cq_size; + new->q_size = PAGE_SIZE + q_size + + ALIGN(num_descs * cq_desc_size, PAGE_SIZE); new->q_base = dma_alloc_coherent(dev, new->q_size, &new->q_base_pa, GFP_KERNEL); if (!new->q_base) { @@ -773,8 +794,14 @@ static int ionic_lif_txq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) dev_dbg(dev, "txq->hw_type %d\n", q->hw_type); dev_dbg(dev, "txq->hw_index %d\n", q->hw_index); - if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) + q->dbell_deadline = IONIC_TX_DOORBELL_DEADLINE; + q->dbell_jiffies = jiffies; + + if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) { netif_napi_add(lif->netdev, &qcq->napi, ionic_tx_napi); + qcq->napi_qcq = qcq; + timer_setup(&qcq->napi_deadline, ionic_napi_deadline, 0); + } qcq->flags |= IONIC_QCQ_F_INITED; @@ -828,11 +855,17 @@ static int ionic_lif_rxq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) dev_dbg(dev, "rxq->hw_type %d\n", q->hw_type); dev_dbg(dev, "rxq->hw_index %d\n", q->hw_index); + q->dbell_deadline = IONIC_RX_MIN_DOORBELL_DEADLINE; + q->dbell_jiffies = jiffies; + if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) netif_napi_add(lif->netdev, &qcq->napi, ionic_rx_napi); else netif_napi_add(lif->netdev, &qcq->napi, ionic_txrx_napi); + qcq->napi_qcq = qcq; + timer_setup(&qcq->napi_deadline, ionic_napi_deadline, 0); + qcq->flags |= IONIC_QCQ_F_INITED; return 0; @@ -1150,6 +1183,7 @@ static int ionic_adminq_napi(struct napi_struct *napi, int budget) struct ionic_dev *idev = &lif->ionic->idev; unsigned long irqflags; unsigned int flags = 0; + bool resched = false; int rx_work = 0; int tx_work = 0; int n_work = 0; @@ -1187,6 +1221,16 @@ static int ionic_adminq_napi(struct napi_struct *napi, int budget) ionic_intr_credits(idev->intr_ctrl, intr->index, credits, flags); } + if (!a_work && ionic_adminq_poke_doorbell(&lif->adminqcq->q)) + resched = true; + if (lif->hwstamp_rxq && !rx_work && ionic_rxq_poke_doorbell(&lif->hwstamp_rxq->q)) + resched = true; + if (lif->hwstamp_txq && !tx_work && ionic_txq_poke_doorbell(&lif->hwstamp_txq->q)) + resched = true; + if (resched) + mod_timer(&lif->adminqcq->napi_deadline, + jiffies + IONIC_NAPI_DEADLINE); + return work_done; } @@ -3245,8 +3289,14 @@ static int ionic_lif_adminq_init(struct ionic_lif *lif) dev_dbg(dev, "adminq->hw_type %d\n", q->hw_type); dev_dbg(dev, "adminq->hw_index %d\n", q->hw_index); + q->dbell_deadline = IONIC_ADMIN_DOORBELL_DEADLINE; + q->dbell_jiffies = jiffies; + netif_napi_add(lif->netdev, &qcq->napi, ionic_adminq_napi); + qcq->napi_qcq = qcq; + timer_setup(&qcq->napi_deadline, ionic_napi_deadline, 0); + napi_enable(&qcq->napi); if (qcq->flags & IONIC_QCQ_F_INTR) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index a53984bf3544..734519895614 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -74,8 +74,10 @@ struct ionic_qcq { struct ionic_queue q; struct ionic_cq cq; struct ionic_intr_info intr; + struct timer_list napi_deadline; struct napi_struct napi; unsigned int flags; + struct ionic_qcq *napi_qcq; struct dentry *dentry; }; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index a13530ec4dd8..08c42b039d92 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -289,6 +289,35 @@ static void ionic_adminq_cb(struct ionic_queue *q, complete_all(&ctx->work); } +bool ionic_adminq_poke_doorbell(struct ionic_queue *q) +{ + struct ionic_lif *lif = q->lif; + unsigned long now, then, dif; + unsigned long irqflags; + + spin_lock_irqsave(&lif->adminq_lock, irqflags); + + if (q->tail_idx == q->head_idx) { + spin_unlock_irqrestore(&lif->adminq_lock, irqflags); + return false; + } + + now = READ_ONCE(jiffies); + then = q->dbell_jiffies; + dif = now - then; + + if (dif > q->dbell_deadline) { + ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, + q->dbval | q->head_idx); + + q->dbell_jiffies = now; + } + + spin_unlock_irqrestore(&lif->adminq_lock, irqflags); + + return true; +} + int ionic_adminq_post(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) { struct ionic_desc_info *desc_info; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 0c3977416cd1..f761780f0162 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -22,6 +22,67 @@ static inline void ionic_rxq_post(struct ionic_queue *q, bool ring_dbell, ionic_q_post(q, ring_dbell, cb_func, cb_arg); } +bool ionic_txq_poke_doorbell(struct ionic_queue *q) +{ + unsigned long now, then, dif; + struct netdev_queue *netdev_txq; + struct net_device *netdev; + + netdev = q->lif->netdev; + netdev_txq = netdev_get_tx_queue(netdev, q->index); + + HARD_TX_LOCK(netdev, netdev_txq, smp_processor_id()); + + if (q->tail_idx == q->head_idx) { + HARD_TX_UNLOCK(netdev, netdev_txq); + return false; + } + + now = READ_ONCE(jiffies); + then = q->dbell_jiffies; + dif = now - then; + + if (dif > q->dbell_deadline) { + ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, + q->dbval | q->head_idx); + + q->dbell_jiffies = now; + } + + HARD_TX_UNLOCK(netdev, netdev_txq); + + return true; +} + +bool ionic_rxq_poke_doorbell(struct ionic_queue *q) +{ + unsigned long now, then, dif; + + /* no lock, called from rx napi or txrx napi, nothing else can fill */ + + if (q->tail_idx == q->head_idx) + return false; + + now = READ_ONCE(jiffies); + then = q->dbell_jiffies; + dif = now - then; + + if (dif > q->dbell_deadline) { + ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, + q->dbval | q->head_idx); + + q->dbell_jiffies = now; + + dif = 2 * q->dbell_deadline; + if (dif > IONIC_RX_MAX_DOORBELL_DEADLINE) + dif = IONIC_RX_MAX_DOORBELL_DEADLINE; + + q->dbell_deadline = dif; + } + + return true; +} + static inline struct netdev_queue *q_to_ndq(struct ionic_queue *q) { return netdev_get_tx_queue(q->lif->netdev, q->index); @@ -424,6 +485,12 @@ void ionic_rx_fill(struct ionic_queue *q) ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, q->dbval | q->head_idx); + + q->dbell_deadline = IONIC_RX_MIN_DOORBELL_DEADLINE; + q->dbell_jiffies = jiffies; + + mod_timer(&q_to_qcq(q)->napi_qcq->napi_deadline, + jiffies + IONIC_NAPI_DEADLINE); } void ionic_rx_empty(struct ionic_queue *q) @@ -511,6 +578,9 @@ int ionic_tx_napi(struct napi_struct *napi, int budget) work_done, flags); } + if (!work_done && ionic_txq_poke_doorbell(&qcq->q)) + mod_timer(&qcq->napi_deadline, jiffies + IONIC_NAPI_DEADLINE); + return work_done; } @@ -544,23 +614,29 @@ int ionic_rx_napi(struct napi_struct *napi, int budget) work_done, flags); } + if (!work_done && ionic_rxq_poke_doorbell(&qcq->q)) + mod_timer(&qcq->napi_deadline, jiffies + IONIC_NAPI_DEADLINE); + return work_done; } int ionic_txrx_napi(struct napi_struct *napi, int budget) { - struct ionic_qcq *qcq = napi_to_qcq(napi); + struct ionic_qcq *rxqcq = napi_to_qcq(napi); struct ionic_cq *rxcq = napi_to_cq(napi); unsigned int qi = rxcq->bound_q->index; + struct ionic_qcq *txqcq; struct ionic_dev *idev; struct ionic_lif *lif; struct ionic_cq *txcq; + bool resched = false; u32 rx_work_done = 0; u32 tx_work_done = 0; u32 flags = 0; lif = rxcq->bound_q->lif; idev = &lif->ionic->idev; + txqcq = lif->txqcqs[qi]; txcq = &lif->txqcqs[qi]->cq; tx_work_done = ionic_cq_service(txcq, IONIC_TX_BUDGET_DEFAULT, @@ -572,7 +648,7 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) ionic_rx_fill(rxcq->bound_q); if (rx_work_done < budget && napi_complete_done(napi, rx_work_done)) { - ionic_dim_update(qcq, 0); + ionic_dim_update(rxqcq, 0); flags |= IONIC_INTR_CRED_UNMASK; rxcq->bound_intr->rearm_count++; } @@ -583,6 +659,13 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) tx_work_done + rx_work_done, flags); } + if (!rx_work_done && ionic_rxq_poke_doorbell(&rxqcq->q)) + resched = true; + if (!tx_work_done && ionic_txq_poke_doorbell(&txqcq->q)) + resched = true; + if (resched) + mod_timer(&rxqcq->napi_deadline, jiffies + IONIC_NAPI_DEADLINE); + return rx_work_done; } diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index 14fc0af304ce..50b61a0a7f53 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -16,7 +16,6 @@ #include <linux/of_irq.h> #include <linux/of_mdio.h> #include <linux/of_net.h> -#include <linux/phylink.h> #include <linux/phy/phy.h> #include <linux/pm_runtime.h> #include <linux/rtnetlink.h> @@ -1071,33 +1070,25 @@ out: return port; } -/* Call of_node_put(mdio) after done */ -static struct device_node *rswitch_get_mdio_node(struct rswitch_device *rdev) -{ - struct device_node *port, *mdio; - - port = rswitch_get_port_node(rdev); - if (!port) - return NULL; - - mdio = of_get_child_by_name(port, "mdio"); - of_node_put(port); - - return mdio; -} - static int rswitch_etha_get_params(struct rswitch_device *rdev) { - struct device_node *port; + u32 max_speed; int err; - port = rswitch_get_port_node(rdev); - if (!port) + if (!rdev->np_port) return 0; /* ignored */ - err = of_get_phy_mode(port, &rdev->etha->phy_interface); - of_node_put(port); + err = of_get_phy_mode(rdev->np_port, &rdev->etha->phy_interface); + if (err) + return err; + err = of_property_read_u32(rdev->np_port, "max-speed", &max_speed); + if (!err) { + rdev->etha->speed = max_speed; + return 0; + } + + /* if no "max-speed" property, let's use default speed */ switch (rdev->etha->phy_interface) { case PHY_INTERFACE_MODE_MII: rdev->etha->speed = SPEED_100; @@ -1109,11 +1100,10 @@ static int rswitch_etha_get_params(struct rswitch_device *rdev) rdev->etha->speed = SPEED_2500; break; default: - err = -EINVAL; - break; + return -EINVAL; } - return err; + return 0; } static int rswitch_mii_register(struct rswitch_device *rdev) @@ -1133,7 +1123,7 @@ static int rswitch_mii_register(struct rswitch_device *rdev) mii_bus->write_c45 = rswitch_etha_mii_write_c45; mii_bus->parent = &rdev->priv->pdev->dev; - mdio_np = rswitch_get_mdio_node(rdev); + mdio_np = of_get_child_by_name(rdev->np_port, "mdio"); err = of_mdiobus_register(mii_bus, mdio_np); if (err < 0) { mdiobus_free(mii_bus); @@ -1157,114 +1147,107 @@ static void rswitch_mii_unregister(struct rswitch_device *rdev) } } -static void rswitch_mac_config(struct phylink_config *config, - unsigned int mode, - const struct phylink_link_state *state) +static void rswitch_adjust_link(struct net_device *ndev) { -} + struct rswitch_device *rdev = netdev_priv(ndev); + struct phy_device *phydev = ndev->phydev; -static void rswitch_mac_link_down(struct phylink_config *config, - unsigned int mode, - phy_interface_t interface) -{ + /* Current hardware has a restriction not to change speed at runtime */ + if (phydev->link != rdev->etha->link) { + phy_print_status(phydev); + if (phydev->link) + phy_power_on(rdev->serdes); + else + phy_power_off(rdev->serdes); + + rdev->etha->link = phydev->link; + } } -static void rswitch_mac_link_up(struct phylink_config *config, - struct phy_device *phydev, unsigned int mode, - phy_interface_t interface, int speed, - int duplex, bool tx_pause, bool rx_pause) +static void rswitch_phy_remove_link_mode(struct rswitch_device *rdev, + struct phy_device *phydev) { - /* Current hardware cannot change speed at runtime */ -} + /* Current hardware has a restriction not to change speed at runtime */ + switch (rdev->etha->speed) { + case SPEED_2500: + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Full_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Full_BIT); + break; + case SPEED_1000: + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_2500baseX_Full_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Full_BIT); + break; + case SPEED_100: + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_2500baseX_Full_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Full_BIT); + break; + default: + break; + } -static const struct phylink_mac_ops rswitch_phylink_ops = { - .mac_config = rswitch_mac_config, - .mac_link_down = rswitch_mac_link_down, - .mac_link_up = rswitch_mac_link_up, -}; + phy_set_max_speed(phydev, rdev->etha->speed); +} -static int rswitch_phylink_init(struct rswitch_device *rdev) +static int rswitch_phy_device_init(struct rswitch_device *rdev) { - struct device_node *port; - struct phylink *phylink; - int err; + struct phy_device *phydev; + struct device_node *phy; + int err = -ENOENT; - port = rswitch_get_port_node(rdev); - if (!port) + if (!rdev->np_port) return -ENODEV; - rdev->phylink_config.dev = &rdev->ndev->dev; - rdev->phylink_config.type = PHYLINK_NETDEV; - __set_bit(PHY_INTERFACE_MODE_SGMII, rdev->phylink_config.supported_interfaces); - __set_bit(PHY_INTERFACE_MODE_USXGMII, rdev->phylink_config.supported_interfaces); - rdev->phylink_config.mac_capabilities = MAC_100FD | MAC_1000FD | MAC_2500FD; + phy = of_parse_phandle(rdev->np_port, "phy-handle", 0); + if (!phy) + return -ENODEV; - phylink = phylink_create(&rdev->phylink_config, &port->fwnode, - rdev->etha->phy_interface, &rswitch_phylink_ops); - if (IS_ERR(phylink)) { - err = PTR_ERR(phylink); + /* Set phydev->host_interfaces before calling of_phy_connect() to + * configure the PHY with the information of host_interfaces. + */ + phydev = of_phy_find_device(phy); + if (!phydev) goto out; - } + __set_bit(rdev->etha->phy_interface, phydev->host_interfaces); - rdev->phylink = phylink; - err = phylink_of_phy_connect(rdev->phylink, port, rdev->etha->phy_interface); + phydev = of_phy_connect(rdev->ndev, phy, rswitch_adjust_link, 0, + rdev->etha->phy_interface); + if (!phydev) + goto out; + + phy_set_max_speed(phydev, SPEED_2500); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Half_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Full_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); + rswitch_phy_remove_link_mode(rdev, phydev); + + phy_attached_info(phydev); + + err = 0; out: - of_node_put(port); + of_node_put(phy); return err; } -static void rswitch_phylink_deinit(struct rswitch_device *rdev) +static void rswitch_phy_device_deinit(struct rswitch_device *rdev) { - rtnl_lock(); - phylink_disconnect_phy(rdev->phylink); - rtnl_unlock(); - phylink_destroy(rdev->phylink); + if (rdev->ndev->phydev) { + phy_disconnect(rdev->ndev->phydev); + rdev->ndev->phydev = NULL; + } } static int rswitch_serdes_set_params(struct rswitch_device *rdev) { - struct device_node *port = rswitch_get_port_node(rdev); - struct phy *serdes; int err; - serdes = devm_of_phy_get(&rdev->priv->pdev->dev, port, NULL); - of_node_put(port); - if (IS_ERR(serdes)) - return PTR_ERR(serdes); - - err = phy_set_mode_ext(serdes, PHY_MODE_ETHERNET, + err = phy_set_mode_ext(rdev->serdes, PHY_MODE_ETHERNET, rdev->etha->phy_interface); if (err < 0) return err; - return phy_set_speed(serdes, rdev->etha->speed); -} - -static int rswitch_serdes_init(struct rswitch_device *rdev) -{ - struct device_node *port = rswitch_get_port_node(rdev); - struct phy *serdes; - - serdes = devm_of_phy_get(&rdev->priv->pdev->dev, port, NULL); - of_node_put(port); - if (IS_ERR(serdes)) - return PTR_ERR(serdes); - - return phy_init(serdes); -} - -static int rswitch_serdes_deinit(struct rswitch_device *rdev) -{ - struct device_node *port = rswitch_get_port_node(rdev); - struct phy *serdes; - - serdes = devm_of_phy_get(&rdev->priv->pdev->dev, port, NULL); - of_node_put(port); - if (IS_ERR(serdes)) - return PTR_ERR(serdes); - - return phy_exit(serdes); + return phy_set_speed(rdev->serdes, rdev->etha->speed); } static int rswitch_ether_port_init_one(struct rswitch_device *rdev) @@ -1282,9 +1265,15 @@ static int rswitch_ether_port_init_one(struct rswitch_device *rdev) if (err < 0) return err; - err = rswitch_phylink_init(rdev); + err = rswitch_phy_device_init(rdev); if (err < 0) - goto err_phylink_init; + goto err_phy_device_init; + + rdev->serdes = devm_of_phy_get(&rdev->priv->pdev->dev, rdev->np_port, NULL); + if (IS_ERR(rdev->serdes)) { + err = PTR_ERR(rdev->serdes); + goto err_serdes_phy_get; + } err = rswitch_serdes_set_params(rdev); if (err < 0) @@ -1293,9 +1282,10 @@ static int rswitch_ether_port_init_one(struct rswitch_device *rdev) return 0; err_serdes_set_params: - rswitch_phylink_deinit(rdev); +err_serdes_phy_get: + rswitch_phy_device_deinit(rdev); -err_phylink_init: +err_phy_device_init: rswitch_mii_unregister(rdev); return err; @@ -1303,7 +1293,7 @@ err_phylink_init: static void rswitch_ether_port_deinit_one(struct rswitch_device *rdev) { - rswitch_phylink_deinit(rdev); + rswitch_phy_device_deinit(rdev); rswitch_mii_unregister(rdev); } @@ -1318,7 +1308,7 @@ static int rswitch_ether_port_init_all(struct rswitch_private *priv) } rswitch_for_each_enabled_port(priv, i) { - err = rswitch_serdes_init(priv->rdev[i]); + err = phy_init(priv->rdev[i]->serdes); if (err) goto err_serdes; } @@ -1327,7 +1317,7 @@ static int rswitch_ether_port_init_all(struct rswitch_private *priv) err_serdes: rswitch_for_each_enabled_port_continue_reverse(priv, i) - rswitch_serdes_deinit(priv->rdev[i]); + phy_exit(priv->rdev[i]->serdes); i = RSWITCH_NUM_PORTS; err_init_one: @@ -1342,7 +1332,7 @@ static void rswitch_ether_port_deinit_all(struct rswitch_private *priv) int i; for (i = 0; i < RSWITCH_NUM_PORTS; i++) { - rswitch_serdes_deinit(priv->rdev[i]); + phy_exit(priv->rdev[i]->serdes); rswitch_ether_port_deinit_one(priv->rdev[i]); } } @@ -1351,7 +1341,7 @@ static int rswitch_open(struct net_device *ndev) { struct rswitch_device *rdev = netdev_priv(ndev); - phylink_start(rdev->phylink); + phy_start(ndev->phydev); napi_enable(&rdev->napi); netif_start_queue(ndev); @@ -1371,7 +1361,7 @@ static int rswitch_stop(struct net_device *ndev) rswitch_enadis_data_irq(rdev->priv, rdev->tx_queue->index, false); rswitch_enadis_data_irq(rdev->priv, rdev->rx_queue->index, false); - phylink_stop(rdev->phylink); + phy_stop(ndev->phydev); napi_disable(&rdev->napi); return 0; @@ -1499,8 +1489,6 @@ static int rswitch_hwstamp_set(struct net_device *ndev, struct ifreq *req) static int rswitch_eth_ioctl(struct net_device *ndev, struct ifreq *req, int cmd) { - struct rswitch_device *rdev = netdev_priv(ndev); - if (!netif_running(ndev)) return -EINVAL; @@ -1510,7 +1498,7 @@ static int rswitch_eth_ioctl(struct net_device *ndev, struct ifreq *req, int cmd case SIOCSHWTSTAMP: return rswitch_hwstamp_set(ndev, req); default: - return phylink_mii_ioctl(rdev->phylink, req, cmd); + return phy_mii_ioctl(ndev->phydev, req, cmd); } } @@ -1565,7 +1553,6 @@ static int rswitch_device_alloc(struct rswitch_private *priv, int index) { struct platform_device *pdev = priv->pdev; struct rswitch_device *rdev; - struct device_node *port; struct net_device *ndev; int err; @@ -1594,10 +1581,10 @@ static int rswitch_device_alloc(struct rswitch_private *priv, int index) netif_napi_add(ndev, &rdev->napi, rswitch_poll); - port = rswitch_get_port_node(rdev); - rdev->disabled = !port; - err = of_get_ethdev_address(port, ndev); - of_node_put(port); + rdev->np_port = rswitch_get_port_node(rdev); + rdev->disabled = !rdev->np_port; + err = of_get_ethdev_address(rdev->np_port, ndev); + of_node_put(rdev->np_port); if (err) { if (is_valid_ether_addr(rdev->etha->mac_addr)) eth_hw_addr_set(ndev, rdev->etha->mac_addr); @@ -1798,7 +1785,7 @@ static void rswitch_deinit(struct rswitch_private *priv) for (i = 0; i < RSWITCH_NUM_PORTS; i++) { struct rswitch_device *rdev = priv->rdev[i]; - rswitch_serdes_deinit(rdev); + phy_exit(priv->rdev[i]->serdes); rswitch_ether_port_deinit_one(rdev); unregister_netdev(rdev->ndev); rswitch_device_free(priv, i); diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h index 49efb0f31c77..59830ab91a69 100644 --- a/drivers/net/ethernet/renesas/rswitch.h +++ b/drivers/net/ethernet/renesas/rswitch.h @@ -943,8 +943,6 @@ struct rswitch_device { struct rswitch_private *priv; struct net_device *ndev; struct napi_struct napi; - struct phylink *phylink; - struct phylink_config phylink_config; void __iomem *addr; struct rswitch_gwca_queue *tx_queue; struct rswitch_gwca_queue *rx_queue; @@ -953,6 +951,8 @@ struct rswitch_device { int port; struct rswitch_etha *etha; + struct device_node *np_port; + struct phy *serdes; }; struct rswitch_mfwd_mac_table_entry { diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 9569c3356b4a..02c2adeb0a12 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1003,8 +1003,11 @@ static int efx_pci_probe_post_io(struct efx_nic *efx) /* Determine netdevice features */ net_dev->features |= (efx->type->offload_features | NETIF_F_SG | NETIF_F_TSO | NETIF_F_RXCSUM | NETIF_F_RXALL); - if (efx->type->offload_features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) + if (efx->type->offload_features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) { net_dev->features |= NETIF_F_TSO6; + if (efx_has_cap(efx, TX_TSO_V2_ENCAP)) + net_dev->hw_enc_features |= NETIF_F_TSO6; + } /* Check whether device supports TSO */ if (!efx->type->tso_versions || !efx->type->tso_versions(efx)) net_dev->features &= ~NETIF_F_ALL_TSO; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index 835caa15d55f..732774645c1a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -560,6 +560,8 @@ static int qcom_ethqos_probe(struct platform_device *pdev) plat_dat->has_gmac4 = 1; plat_dat->pmt = 1; plat_dat->tso_en = of_property_read_bool(np, "snps,tso"); + if (of_device_is_compatible(np, "qcom,qcs404-ethqos")) + plat_dat->rx_clk_runs_in_lpi = 1; ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (ret) diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 592b4067f9b8..16a7421715cb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -567,6 +567,7 @@ struct tc_cbs_qopt_offload; struct flow_cls_offload; struct tc_taprio_qopt_offload; struct tc_etf_qopt_offload; +struct tc_query_caps_base; struct stmmac_tc_ops { int (*init)(struct stmmac_priv *priv); @@ -580,6 +581,8 @@ struct stmmac_tc_ops { struct tc_taprio_qopt_offload *qopt); int (*setup_etf)(struct stmmac_priv *priv, struct tc_etf_qopt_offload *qopt); + int (*query_caps)(struct stmmac_priv *priv, + struct tc_query_caps_base *base); }; #define stmmac_tc_init(__priv, __args...) \ @@ -594,6 +597,8 @@ struct stmmac_tc_ops { stmmac_do_callback(__priv, tc, setup_taprio, __args) #define stmmac_tc_setup_etf(__priv, __args...) \ stmmac_do_callback(__priv, tc, setup_etf, __args) +#define stmmac_tc_query_caps(__priv, __args...) \ + stmmac_do_callback(__priv, tc, query_caps, __args) struct stmmac_counters; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 734d84263fd2..868f59ec8439 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1080,7 +1080,8 @@ static void stmmac_mac_link_up(struct phylink_config *config, stmmac_mac_set(priv, priv->ioaddr, true); if (phy && priv->dma_cap.eee) { - priv->eee_active = phy_init_eee(phy, 1) >= 0; + priv->eee_active = + phy_init_eee(phy, !priv->plat->rx_clk_runs_in_lpi) >= 0; priv->eee_enabled = stmmac_eee_init(priv); priv->tx_lpi_enabled = priv->eee_enabled; stmmac_set_eee_pls(priv, priv->hw, true); @@ -5991,6 +5992,8 @@ static int stmmac_setup_tc(struct net_device *ndev, enum tc_setup_type type, struct stmmac_priv *priv = netdev_priv(ndev); switch (type) { + case TC_QUERY_CAPS: + return stmmac_tc_query_caps(priv, priv, type_data); case TC_SETUP_BLOCK: return flow_block_cb_setup_simple(type_data, &stmmac_block_cb_list, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 2cfb18cef1d4..9d55226479b4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -1107,6 +1107,25 @@ static int tc_setup_etf(struct stmmac_priv *priv, return 0; } +static int tc_query_caps(struct stmmac_priv *priv, + struct tc_query_caps_base *base) +{ + switch (base->type) { + case TC_SETUP_QDISC_TAPRIO: { + struct tc_taprio_caps *caps = base->caps; + + if (!priv->dma_cap.estsel) + return -EOPNOTSUPP; + + caps->gate_mask_per_txq = true; + + return 0; + } + default: + return -EOPNOTSUPP; + } +} + const struct stmmac_tc_ops dwmac510_tc_ops = { .init = tc_init, .setup_cls_u32 = tc_setup_cls_u32, @@ -1114,4 +1133,5 @@ const struct stmmac_tc_ops dwmac510_tc_ops = { .setup_cls = tc_setup_cls, .setup_taprio = tc_setup_taprio, .setup_etf = tc_setup_etf, + .query_caps = tc_query_caps, }; diff --git a/drivers/net/ethernet/ti/am65-cpsw-qos.c b/drivers/net/ethernet/ti/am65-cpsw-qos.c index e162771893af..8dc2c3085dcf 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-qos.c +++ b/drivers/net/ethernet/ti/am65-cpsw-qos.c @@ -585,6 +585,26 @@ static int am65_cpsw_setup_taprio(struct net_device *ndev, void *type_data) return am65_cpsw_set_taprio(ndev, type_data); } +static int am65_cpsw_tc_query_caps(struct net_device *ndev, void *type_data) +{ + struct tc_query_caps_base *base = type_data; + + switch (base->type) { + case TC_SETUP_QDISC_TAPRIO: { + struct tc_taprio_caps *caps = base->caps; + + if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_TAS)) + return -EOPNOTSUPP; + + caps->gate_mask_per_txq = true; + + return 0; + } + default: + return -EOPNOTSUPP; + } +} + static int am65_cpsw_qos_clsflower_add_policer(struct am65_cpsw_port *port, struct netlink_ext_ack *extack, struct flow_cls_offload *cls, @@ -765,6 +785,8 @@ int am65_cpsw_qos_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type, void *type_data) { switch (type) { + case TC_QUERY_CAPS: + return am65_cpsw_tc_query_caps(ndev, type_data); case TC_SETUP_QDISC_TAPRIO: return am65_cpsw_setup_taprio(ndev, type_data); case TC_SETUP_BLOCK: diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c index 758295c898ac..e966dd47e2db 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.c +++ b/drivers/net/ethernet/ti/cpsw_priv.c @@ -20,6 +20,7 @@ #include <linux/skbuff.h> #include <net/page_pool.h> #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include "cpsw.h" #include "cpts.h" diff --git a/drivers/net/ethernet/wangxun/Kconfig b/drivers/net/ethernet/wangxun/Kconfig index 0922beac3ec0..c9d88673d306 100644 --- a/drivers/net/ethernet/wangxun/Kconfig +++ b/drivers/net/ethernet/wangxun/Kconfig @@ -18,6 +18,7 @@ if NET_VENDOR_WANGXUN config LIBWX tristate + select PAGE_POOL help Common library for Wangxun(R) Ethernet drivers. diff --git a/drivers/net/ethernet/wangxun/libwx/Makefile b/drivers/net/ethernet/wangxun/libwx/Makefile index 1ed5e23af944..850d1615cd18 100644 --- a/drivers/net/ethernet/wangxun/libwx/Makefile +++ b/drivers/net/ethernet/wangxun/libwx/Makefile @@ -4,4 +4,4 @@ obj-$(CONFIG_LIBWX) += libwx.o -libwx-objs := wx_hw.o +libwx-objs := wx_hw.o wx_lib.o diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index 3d7ba0c0df38..7db57f934a91 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -8,13 +8,14 @@ #include <linux/pci.h> #include "wx_type.h" +#include "wx_lib.h" #include "wx_hw.h" static void wx_intr_disable(struct wx *wx, u64 qmask) { u32 mask; - mask = (qmask & 0xFFFFFFFF); + mask = (qmask & U32_MAX); if (mask) wr32(wx, WX_PX_IMS(0), mask); @@ -25,6 +26,45 @@ static void wx_intr_disable(struct wx *wx, u64 qmask) } } +void wx_intr_enable(struct wx *wx, u64 qmask) +{ + u32 mask; + + mask = (qmask & U32_MAX); + if (mask) + wr32(wx, WX_PX_IMC(0), mask); + if (wx->mac.type == wx_mac_sp) { + mask = (qmask >> 32); + if (mask) + wr32(wx, WX_PX_IMC(1), mask); + } +} +EXPORT_SYMBOL(wx_intr_enable); + +/** + * wx_irq_disable - Mask off interrupt generation on the NIC + * @wx: board private structure + **/ +void wx_irq_disable(struct wx *wx) +{ + struct pci_dev *pdev = wx->pdev; + + wr32(wx, WX_PX_MISC_IEN, 0); + wx_intr_disable(wx, WX_INTR_ALL); + + if (pdev->msix_enabled) { + int vector; + + for (vector = 0; vector < wx->num_q_vectors; vector++) + synchronize_irq(wx->msix_entries[vector].vector); + + synchronize_irq(wx->msix_entries[vector].vector); + } else { + synchronize_irq(pdev->irq); + } +} +EXPORT_SYMBOL(wx_irq_disable); + /* cmd_addr is used for some special command: * 1. to be sector address, when implemented erase sector command * 2. to be flash address when implemented read, write flash address @@ -765,6 +805,37 @@ void wx_flush_sw_mac_table(struct wx *wx) } EXPORT_SYMBOL(wx_flush_sw_mac_table); +static int wx_add_mac_filter(struct wx *wx, u8 *addr, u16 pool) +{ + u32 i; + + if (is_zero_ether_addr(addr)) + return -EINVAL; + + for (i = 0; i < wx->mac.num_rar_entries; i++) { + if (wx->mac_table[i].state & WX_MAC_STATE_IN_USE) { + if (ether_addr_equal(addr, wx->mac_table[i].addr)) { + if (wx->mac_table[i].pools != (1ULL << pool)) { + memcpy(wx->mac_table[i].addr, addr, ETH_ALEN); + wx->mac_table[i].pools |= (1ULL << pool); + wx_sync_mac_table(wx); + return i; + } + } + } + + if (wx->mac_table[i].state & WX_MAC_STATE_IN_USE) + continue; + wx->mac_table[i].state |= (WX_MAC_STATE_MODIFIED | + WX_MAC_STATE_IN_USE); + memcpy(wx->mac_table[i].addr, addr, ETH_ALEN); + wx->mac_table[i].pools |= (1ULL << pool); + wx_sync_mac_table(wx); + return i; + } + return -ENOMEM; +} + static int wx_del_mac_filter(struct wx *wx, u8 *addr, u16 pool) { u32 i; @@ -789,6 +860,184 @@ static int wx_del_mac_filter(struct wx *wx, u8 *addr, u16 pool) return -ENOMEM; } +static int wx_available_rars(struct wx *wx) +{ + u32 i, count = 0; + + for (i = 0; i < wx->mac.num_rar_entries; i++) { + if (wx->mac_table[i].state == 0) + count++; + } + + return count; +} + +/** + * wx_write_uc_addr_list - write unicast addresses to RAR table + * @netdev: network interface device structure + * @pool: index for mac table + * + * Writes unicast address list to the RAR table. + * Returns: -ENOMEM on failure/insufficient address space + * 0 on no addresses written + * X on writing X addresses to the RAR table + **/ +static int wx_write_uc_addr_list(struct net_device *netdev, int pool) +{ + struct wx *wx = netdev_priv(netdev); + int count = 0; + + /* return ENOMEM indicating insufficient memory for addresses */ + if (netdev_uc_count(netdev) > wx_available_rars(wx)) + return -ENOMEM; + + if (!netdev_uc_empty(netdev)) { + struct netdev_hw_addr *ha; + + netdev_for_each_uc_addr(ha, netdev) { + wx_del_mac_filter(wx, ha->addr, pool); + wx_add_mac_filter(wx, ha->addr, pool); + count++; + } + } + return count; +} + +/** + * wx_mta_vector - Determines bit-vector in multicast table to set + * @wx: pointer to private structure + * @mc_addr: the multicast address + * + * Extracts the 12 bits, from a multicast address, to determine which + * bit-vector to set in the multicast table. The hardware uses 12 bits, from + * incoming rx multicast addresses, to determine the bit-vector to check in + * the MTA. Which of the 4 combination, of 12-bits, the hardware uses is set + * by the MO field of the MCSTCTRL. The MO field is set during initialization + * to mc_filter_type. + **/ +static u32 wx_mta_vector(struct wx *wx, u8 *mc_addr) +{ + u32 vector = 0; + + switch (wx->mac.mc_filter_type) { + case 0: /* use bits [47:36] of the address */ + vector = ((mc_addr[4] >> 4) | (((u16)mc_addr[5]) << 4)); + break; + case 1: /* use bits [46:35] of the address */ + vector = ((mc_addr[4] >> 3) | (((u16)mc_addr[5]) << 5)); + break; + case 2: /* use bits [45:34] of the address */ + vector = ((mc_addr[4] >> 2) | (((u16)mc_addr[5]) << 6)); + break; + case 3: /* use bits [43:32] of the address */ + vector = ((mc_addr[4]) | (((u16)mc_addr[5]) << 8)); + break; + default: /* Invalid mc_filter_type */ + wx_err(wx, "MC filter type param set incorrectly\n"); + break; + } + + /* vector can only be 12-bits or boundary will be exceeded */ + vector &= 0xFFF; + return vector; +} + +/** + * wx_set_mta - Set bit-vector in multicast table + * @wx: pointer to private structure + * @mc_addr: Multicast address + * + * Sets the bit-vector in the multicast table. + **/ +static void wx_set_mta(struct wx *wx, u8 *mc_addr) +{ + u32 vector, vector_bit, vector_reg; + + wx->addr_ctrl.mta_in_use++; + + vector = wx_mta_vector(wx, mc_addr); + wx_dbg(wx, " bit-vector = 0x%03X\n", vector); + + /* The MTA is a register array of 128 32-bit registers. It is treated + * like an array of 4096 bits. We want to set bit + * BitArray[vector_value]. So we figure out what register the bit is + * in, read it, OR in the new bit, then write back the new value. The + * register is determined by the upper 7 bits of the vector value and + * the bit within that register are determined by the lower 5 bits of + * the value. + */ + vector_reg = (vector >> 5) & 0x7F; + vector_bit = vector & 0x1F; + wx->mac.mta_shadow[vector_reg] |= (1 << vector_bit); +} + +/** + * wx_update_mc_addr_list - Updates MAC list of multicast addresses + * @wx: pointer to private structure + * @netdev: pointer to net device structure + * + * The given list replaces any existing list. Clears the MC addrs from receive + * address registers and the multicast table. Uses unused receive address + * registers for the first multicast addresses, and hashes the rest into the + * multicast table. + **/ +static void wx_update_mc_addr_list(struct wx *wx, struct net_device *netdev) +{ + struct netdev_hw_addr *ha; + u32 i, psrctl; + + /* Set the new number of MC addresses that we are being requested to + * use. + */ + wx->addr_ctrl.num_mc_addrs = netdev_mc_count(netdev); + wx->addr_ctrl.mta_in_use = 0; + + /* Clear mta_shadow */ + wx_dbg(wx, " Clearing MTA\n"); + memset(&wx->mac.mta_shadow, 0, sizeof(wx->mac.mta_shadow)); + + /* Update mta_shadow */ + netdev_for_each_mc_addr(ha, netdev) { + wx_dbg(wx, " Adding the multicast addresses:\n"); + wx_set_mta(wx, ha->addr); + } + + /* Enable mta */ + for (i = 0; i < wx->mac.mcft_size; i++) + wr32a(wx, WX_PSR_MC_TBL(0), i, + wx->mac.mta_shadow[i]); + + if (wx->addr_ctrl.mta_in_use > 0) { + psrctl = rd32(wx, WX_PSR_CTL); + psrctl &= ~(WX_PSR_CTL_MO | WX_PSR_CTL_MFE); + psrctl |= WX_PSR_CTL_MFE | + (wx->mac.mc_filter_type << WX_PSR_CTL_MO_SHIFT); + wr32(wx, WX_PSR_CTL, psrctl); + } + + wx_dbg(wx, "Update mc addr list Complete\n"); +} + +/** + * wx_write_mc_addr_list - write multicast addresses to MTA + * @netdev: network interface device structure + * + * Writes multicast address list to the MTA hash table. + * Returns: 0 on no addresses written + * X on writing X addresses to MTA + **/ +static int wx_write_mc_addr_list(struct net_device *netdev) +{ + struct wx *wx = netdev_priv(netdev); + + if (!netif_running(netdev)) + return 0; + + wx_update_mc_addr_list(wx, netdev); + + return netdev_mc_count(netdev); +} + /** * wx_set_mac - Change the Ethernet Address of the NIC * @netdev: network interface device structure @@ -844,6 +1093,430 @@ void wx_disable_rx(struct wx *wx) } EXPORT_SYMBOL(wx_disable_rx); +static void wx_enable_rx(struct wx *wx) +{ + u32 psrctl; + + /* enable mac receiver */ + wr32m(wx, WX_MAC_RX_CFG, + WX_MAC_RX_CFG_RE, WX_MAC_RX_CFG_RE); + + wr32m(wx, WX_RDB_PB_CTL, + WX_RDB_PB_CTL_RXEN, WX_RDB_PB_CTL_RXEN); + + if (wx->mac.set_lben) { + psrctl = rd32(wx, WX_PSR_CTL); + psrctl |= WX_PSR_CTL_SW_EN; + wr32(wx, WX_PSR_CTL, psrctl); + wx->mac.set_lben = false; + } +} + +/** + * wx_set_rxpba - Initialize Rx packet buffer + * @wx: pointer to private structure + **/ +static void wx_set_rxpba(struct wx *wx) +{ + u32 rxpktsize, txpktsize, txpbthresh; + + rxpktsize = wx->mac.rx_pb_size << WX_RDB_PB_SZ_SHIFT; + wr32(wx, WX_RDB_PB_SZ(0), rxpktsize); + + /* Only support an equally distributed Tx packet buffer strategy. */ + txpktsize = wx->mac.tx_pb_size; + txpbthresh = (txpktsize / 1024) - WX_TXPKT_SIZE_MAX; + wr32(wx, WX_TDB_PB_SZ(0), txpktsize); + wr32(wx, WX_TDM_PB_THRE(0), txpbthresh); +} + +static void wx_configure_port(struct wx *wx) +{ + u32 value, i; + + value = WX_CFG_PORT_CTL_D_VLAN | WX_CFG_PORT_CTL_QINQ; + wr32m(wx, WX_CFG_PORT_CTL, + WX_CFG_PORT_CTL_D_VLAN | + WX_CFG_PORT_CTL_QINQ, + value); + + wr32(wx, WX_CFG_TAG_TPID(0), + ETH_P_8021Q | ETH_P_8021AD << 16); + wx->tpid[0] = ETH_P_8021Q; + wx->tpid[1] = ETH_P_8021AD; + for (i = 1; i < 4; i++) + wr32(wx, WX_CFG_TAG_TPID(i), + ETH_P_8021Q | ETH_P_8021Q << 16); + for (i = 2; i < 8; i++) + wx->tpid[i] = ETH_P_8021Q; +} + +/** + * wx_disable_sec_rx_path - Stops the receive data path + * @wx: pointer to private structure + * + * Stops the receive data path and waits for the HW to internally empty + * the Rx security block + **/ +static int wx_disable_sec_rx_path(struct wx *wx) +{ + u32 secrx; + + wr32m(wx, WX_RSC_CTL, + WX_RSC_CTL_RX_DIS, WX_RSC_CTL_RX_DIS); + + return read_poll_timeout(rd32, secrx, secrx & WX_RSC_ST_RSEC_RDY, + 1000, 40000, false, wx, WX_RSC_ST); +} + +/** + * wx_enable_sec_rx_path - Enables the receive data path + * @wx: pointer to private structure + * + * Enables the receive data path. + **/ +static void wx_enable_sec_rx_path(struct wx *wx) +{ + wr32m(wx, WX_RSC_CTL, WX_RSC_CTL_RX_DIS, 0); + WX_WRITE_FLUSH(wx); +} + +void wx_set_rx_mode(struct net_device *netdev) +{ + struct wx *wx = netdev_priv(netdev); + u32 fctrl, vmolr, vlnctrl; + int count; + + /* Check for Promiscuous and All Multicast modes */ + fctrl = rd32(wx, WX_PSR_CTL); + fctrl &= ~(WX_PSR_CTL_UPE | WX_PSR_CTL_MPE); + vmolr = rd32(wx, WX_PSR_VM_L2CTL(0)); + vmolr &= ~(WX_PSR_VM_L2CTL_UPE | + WX_PSR_VM_L2CTL_MPE | + WX_PSR_VM_L2CTL_ROPE | + WX_PSR_VM_L2CTL_ROMPE); + vlnctrl = rd32(wx, WX_PSR_VLAN_CTL); + vlnctrl &= ~(WX_PSR_VLAN_CTL_VFE | WX_PSR_VLAN_CTL_CFIEN); + + /* set all bits that we expect to always be set */ + fctrl |= WX_PSR_CTL_BAM | WX_PSR_CTL_MFE; + vmolr |= WX_PSR_VM_L2CTL_BAM | + WX_PSR_VM_L2CTL_AUPE | + WX_PSR_VM_L2CTL_VACC; + vlnctrl |= WX_PSR_VLAN_CTL_VFE; + + wx->addr_ctrl.user_set_promisc = false; + if (netdev->flags & IFF_PROMISC) { + wx->addr_ctrl.user_set_promisc = true; + fctrl |= WX_PSR_CTL_UPE | WX_PSR_CTL_MPE; + /* pf don't want packets routing to vf, so clear UPE */ + vmolr |= WX_PSR_VM_L2CTL_MPE; + vlnctrl &= ~WX_PSR_VLAN_CTL_VFE; + } + + if (netdev->flags & IFF_ALLMULTI) { + fctrl |= WX_PSR_CTL_MPE; + vmolr |= WX_PSR_VM_L2CTL_MPE; + } + + if (netdev->features & NETIF_F_RXALL) { + vmolr |= (WX_PSR_VM_L2CTL_UPE | WX_PSR_VM_L2CTL_MPE); + vlnctrl &= ~WX_PSR_VLAN_CTL_VFE; + /* receive bad packets */ + wr32m(wx, WX_RSC_CTL, + WX_RSC_CTL_SAVE_MAC_ERR, + WX_RSC_CTL_SAVE_MAC_ERR); + } else { + vmolr |= WX_PSR_VM_L2CTL_ROPE | WX_PSR_VM_L2CTL_ROMPE; + } + + /* Write addresses to available RAR registers, if there is not + * sufficient space to store all the addresses then enable + * unicast promiscuous mode + */ + count = wx_write_uc_addr_list(netdev, 0); + if (count < 0) { + vmolr &= ~WX_PSR_VM_L2CTL_ROPE; + vmolr |= WX_PSR_VM_L2CTL_UPE; + } + + /* Write addresses to the MTA, if the attempt fails + * then we should just turn on promiscuous mode so + * that we can at least receive multicast traffic + */ + count = wx_write_mc_addr_list(netdev); + if (count < 0) { + vmolr &= ~WX_PSR_VM_L2CTL_ROMPE; + vmolr |= WX_PSR_VM_L2CTL_MPE; + } + + wr32(wx, WX_PSR_VLAN_CTL, vlnctrl); + wr32(wx, WX_PSR_CTL, fctrl); + wr32(wx, WX_PSR_VM_L2CTL(0), vmolr); +} +EXPORT_SYMBOL(wx_set_rx_mode); + +static void wx_set_rx_buffer_len(struct wx *wx) +{ + struct net_device *netdev = wx->netdev; + u32 mhadd, max_frame; + + max_frame = netdev->mtu + ETH_HLEN + ETH_FCS_LEN; + /* adjust max frame to be at least the size of a standard frame */ + if (max_frame < (ETH_FRAME_LEN + ETH_FCS_LEN)) + max_frame = (ETH_FRAME_LEN + ETH_FCS_LEN); + + mhadd = rd32(wx, WX_PSR_MAX_SZ); + if (max_frame != mhadd) + wr32(wx, WX_PSR_MAX_SZ, max_frame); +} + +/* Disable the specified rx queue */ +void wx_disable_rx_queue(struct wx *wx, struct wx_ring *ring) +{ + u8 reg_idx = ring->reg_idx; + u32 rxdctl; + int ret; + + /* write value back with RRCFG.EN bit cleared */ + wr32m(wx, WX_PX_RR_CFG(reg_idx), + WX_PX_RR_CFG_RR_EN, 0); + + /* the hardware may take up to 100us to really disable the rx queue */ + ret = read_poll_timeout(rd32, rxdctl, !(rxdctl & WX_PX_RR_CFG_RR_EN), + 10, 100, true, wx, WX_PX_RR_CFG(reg_idx)); + + if (ret == -ETIMEDOUT) { + /* Just for information */ + wx_err(wx, + "RRCFG.EN on Rx queue %d not cleared within the polling period\n", + reg_idx); + } +} +EXPORT_SYMBOL(wx_disable_rx_queue); + +static void wx_enable_rx_queue(struct wx *wx, struct wx_ring *ring) +{ + u8 reg_idx = ring->reg_idx; + u32 rxdctl; + int ret; + + ret = read_poll_timeout(rd32, rxdctl, rxdctl & WX_PX_RR_CFG_RR_EN, + 1000, 10000, true, wx, WX_PX_RR_CFG(reg_idx)); + + if (ret == -ETIMEDOUT) { + /* Just for information */ + wx_err(wx, + "RRCFG.EN on Rx queue %d not set within the polling period\n", + reg_idx); + } +} + +static void wx_configure_srrctl(struct wx *wx, + struct wx_ring *rx_ring) +{ + u16 reg_idx = rx_ring->reg_idx; + u32 srrctl; + + srrctl = rd32(wx, WX_PX_RR_CFG(reg_idx)); + srrctl &= ~(WX_PX_RR_CFG_RR_HDR_SZ | + WX_PX_RR_CFG_RR_BUF_SZ | + WX_PX_RR_CFG_SPLIT_MODE); + /* configure header buffer length, needed for RSC */ + srrctl |= WX_RXBUFFER_256 << WX_PX_RR_CFG_BHDRSIZE_SHIFT; + + /* configure the packet buffer length */ + srrctl |= WX_RX_BUFSZ >> WX_PX_RR_CFG_BSIZEPKT_SHIFT; + + wr32(wx, WX_PX_RR_CFG(reg_idx), srrctl); +} + +static void wx_configure_tx_ring(struct wx *wx, + struct wx_ring *ring) +{ + u32 txdctl = WX_PX_TR_CFG_ENABLE; + u8 reg_idx = ring->reg_idx; + u64 tdba = ring->dma; + int ret; + + /* disable queue to avoid issues while updating state */ + wr32(wx, WX_PX_TR_CFG(reg_idx), WX_PX_TR_CFG_SWFLSH); + WX_WRITE_FLUSH(wx); + + wr32(wx, WX_PX_TR_BAL(reg_idx), tdba & DMA_BIT_MASK(32)); + wr32(wx, WX_PX_TR_BAH(reg_idx), upper_32_bits(tdba)); + + /* reset head and tail pointers */ + wr32(wx, WX_PX_TR_RP(reg_idx), 0); + wr32(wx, WX_PX_TR_WP(reg_idx), 0); + ring->tail = wx->hw_addr + WX_PX_TR_WP(reg_idx); + + if (ring->count < WX_MAX_TXD) + txdctl |= ring->count / 128 << WX_PX_TR_CFG_TR_SIZE_SHIFT; + txdctl |= 0x20 << WX_PX_TR_CFG_WTHRESH_SHIFT; + + /* reinitialize tx_buffer_info */ + memset(ring->tx_buffer_info, 0, + sizeof(struct wx_tx_buffer) * ring->count); + + /* enable queue */ + wr32(wx, WX_PX_TR_CFG(reg_idx), txdctl); + + /* poll to verify queue is enabled */ + ret = read_poll_timeout(rd32, txdctl, txdctl & WX_PX_TR_CFG_ENABLE, + 1000, 10000, true, wx, WX_PX_TR_CFG(reg_idx)); + if (ret == -ETIMEDOUT) + wx_err(wx, "Could not enable Tx Queue %d\n", reg_idx); +} + +static void wx_configure_rx_ring(struct wx *wx, + struct wx_ring *ring) +{ + u16 reg_idx = ring->reg_idx; + union wx_rx_desc *rx_desc; + u64 rdba = ring->dma; + u32 rxdctl; + + /* disable queue to avoid issues while updating state */ + rxdctl = rd32(wx, WX_PX_RR_CFG(reg_idx)); + wx_disable_rx_queue(wx, ring); + + wr32(wx, WX_PX_RR_BAL(reg_idx), rdba & DMA_BIT_MASK(32)); + wr32(wx, WX_PX_RR_BAH(reg_idx), upper_32_bits(rdba)); + + if (ring->count == WX_MAX_RXD) + rxdctl |= 0 << WX_PX_RR_CFG_RR_SIZE_SHIFT; + else + rxdctl |= (ring->count / 128) << WX_PX_RR_CFG_RR_SIZE_SHIFT; + + rxdctl |= 0x1 << WX_PX_RR_CFG_RR_THER_SHIFT; + wr32(wx, WX_PX_RR_CFG(reg_idx), rxdctl); + + /* reset head and tail pointers */ + wr32(wx, WX_PX_RR_RP(reg_idx), 0); + wr32(wx, WX_PX_RR_WP(reg_idx), 0); + ring->tail = wx->hw_addr + WX_PX_RR_WP(reg_idx); + + wx_configure_srrctl(wx, ring); + + /* initialize rx_buffer_info */ + memset(ring->rx_buffer_info, 0, + sizeof(struct wx_rx_buffer) * ring->count); + + /* initialize Rx descriptor 0 */ + rx_desc = WX_RX_DESC(ring, 0); + rx_desc->wb.upper.length = 0; + + /* enable receive descriptor ring */ + wr32m(wx, WX_PX_RR_CFG(reg_idx), + WX_PX_RR_CFG_RR_EN, WX_PX_RR_CFG_RR_EN); + + wx_enable_rx_queue(wx, ring); + wx_alloc_rx_buffers(ring, wx_desc_unused(ring)); +} + +/** + * wx_configure_tx - Configure Transmit Unit after Reset + * @wx: pointer to private structure + * + * Configure the Tx unit of the MAC after a reset. + **/ +static void wx_configure_tx(struct wx *wx) +{ + u32 i; + + /* TDM_CTL.TE must be before Tx queues are enabled */ + wr32m(wx, WX_TDM_CTL, + WX_TDM_CTL_TE, WX_TDM_CTL_TE); + + /* Setup the HW Tx Head and Tail descriptor pointers */ + for (i = 0; i < wx->num_tx_queues; i++) + wx_configure_tx_ring(wx, wx->tx_ring[i]); + + wr32m(wx, WX_TSC_BUF_AE, WX_TSC_BUF_AE_THR, 0x10); + + if (wx->mac.type == wx_mac_em) + wr32m(wx, WX_TSC_CTL, WX_TSC_CTL_TX_DIS | WX_TSC_CTL_TSEC_DIS, 0x1); + + /* enable mac transmitter */ + wr32m(wx, WX_MAC_TX_CFG, + WX_MAC_TX_CFG_TE, WX_MAC_TX_CFG_TE); +} + +/** + * wx_configure_rx - Configure Receive Unit after Reset + * @wx: pointer to private structure + * + * Configure the Rx unit of the MAC after a reset. + **/ +static void wx_configure_rx(struct wx *wx) +{ + u32 psrtype, i; + int ret; + + wx_disable_rx(wx); + + psrtype = WX_RDB_PL_CFG_L4HDR | + WX_RDB_PL_CFG_L3HDR | + WX_RDB_PL_CFG_L2HDR | + WX_RDB_PL_CFG_TUN_TUNHDR | + WX_RDB_PL_CFG_TUN_TUNHDR; + wr32(wx, WX_RDB_PL_CFG(0), psrtype); + + /* enable hw crc stripping */ + wr32m(wx, WX_RSC_CTL, WX_RSC_CTL_CRC_STRIP, WX_RSC_CTL_CRC_STRIP); + + if (wx->mac.type == wx_mac_sp) { + u32 psrctl; + + /* RSC Setup */ + psrctl = rd32(wx, WX_PSR_CTL); + psrctl |= WX_PSR_CTL_RSC_ACK; /* Disable RSC for ACK packets */ + psrctl |= WX_PSR_CTL_RSC_DIS; + wr32(wx, WX_PSR_CTL, psrctl); + } + + /* set_rx_buffer_len must be called before ring initialization */ + wx_set_rx_buffer_len(wx); + + /* Setup the HW Rx Head and Tail Descriptor Pointers and + * the Base and Length of the Rx Descriptor Ring + */ + for (i = 0; i < wx->num_rx_queues; i++) + wx_configure_rx_ring(wx, wx->rx_ring[i]); + + /* Enable all receives, disable security engine prior to block traffic */ + ret = wx_disable_sec_rx_path(wx); + if (ret < 0) + wx_err(wx, "The register status is abnormal, please check device."); + + wx_enable_rx(wx); + wx_enable_sec_rx_path(wx); +} + +static void wx_configure_isb(struct wx *wx) +{ + /* set ISB Address */ + wr32(wx, WX_PX_ISB_ADDR_L, wx->isb_dma & DMA_BIT_MASK(32)); + if (IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT)) + wr32(wx, WX_PX_ISB_ADDR_H, upper_32_bits(wx->isb_dma)); +} + +void wx_configure(struct wx *wx) +{ + wx_set_rxpba(wx); + wx_configure_port(wx); + + wx_set_rx_mode(wx->netdev); + + wx_enable_sec_rx_path(wx); + + wx_configure_tx(wx); + wx_configure_rx(wx); + wx_configure_isb(wx); +} +EXPORT_SYMBOL(wx_configure); + /** * wx_disable_pcie_master - Disable PCI-express master access * @wx: pointer to hardware structure diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.h b/drivers/net/ethernet/wangxun/libwx/wx_hw.h index 803983546f3a..44dfd6ea442a 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.h @@ -4,6 +4,8 @@ #ifndef _WX_HW_H_ #define _WX_HW_H_ +void wx_intr_enable(struct wx *wx, u64 qmask); +void wx_irq_disable(struct wx *wx); int wx_check_flash_load(struct wx *wx, u32 check_bit); void wx_control_hw(struct wx *wx, bool drv); int wx_mng_present(struct wx *wx); @@ -20,6 +22,9 @@ void wx_mac_set_default_filter(struct wx *wx, u8 *addr); void wx_flush_sw_mac_table(struct wx *wx); int wx_set_mac(struct net_device *netdev, void *p); void wx_disable_rx(struct wx *wx); +void wx_set_rx_mode(struct net_device *netdev); +void wx_disable_rx_queue(struct wx *wx, struct wx_ring *ring); +void wx_configure(struct wx *wx); int wx_disable_pcie_master(struct wx *wx); int wx_stop_adapter(struct wx *wx); void wx_reset_misc(struct wx *wx); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c new file mode 100644 index 000000000000..2ee286b2b177 --- /dev/null +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -0,0 +1,2004 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 - 2022 Beijing WangXun Technology Co., Ltd. */ + +#include <linux/etherdevice.h> +#include <net/page_pool.h> +#include <linux/iopoll.h> +#include <linux/pci.h> + +#include "wx_type.h" +#include "wx_lib.h" +#include "wx_hw.h" + +/* wx_test_staterr - tests bits in Rx descriptor status and error fields */ +static __le32 wx_test_staterr(union wx_rx_desc *rx_desc, + const u32 stat_err_bits) +{ + return rx_desc->wb.upper.status_error & cpu_to_le32(stat_err_bits); +} + +static bool wx_can_reuse_rx_page(struct wx_rx_buffer *rx_buffer, + int rx_buffer_pgcnt) +{ + unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; + struct page *page = rx_buffer->page; + + /* avoid re-using remote and pfmemalloc pages */ + if (!dev_page_is_reusable(page)) + return false; + +#if (PAGE_SIZE < 8192) + /* if we are only owner of page we can reuse it */ + if (unlikely((rx_buffer_pgcnt - pagecnt_bias) > 1)) + return false; +#endif + + /* If we have drained the page fragment pool we need to update + * the pagecnt_bias and page count so that we fully restock the + * number of references the driver holds. + */ + if (unlikely(pagecnt_bias == 1)) { + page_ref_add(page, USHRT_MAX - 1); + rx_buffer->pagecnt_bias = USHRT_MAX; + } + + return true; +} + +/** + * wx_reuse_rx_page - page flip buffer and store it back on the ring + * @rx_ring: rx descriptor ring to store buffers on + * @old_buff: donor buffer to have page reused + * + * Synchronizes page for reuse by the adapter + **/ +static void wx_reuse_rx_page(struct wx_ring *rx_ring, + struct wx_rx_buffer *old_buff) +{ + u16 nta = rx_ring->next_to_alloc; + struct wx_rx_buffer *new_buff; + + new_buff = &rx_ring->rx_buffer_info[nta]; + + /* update, and store next to alloc */ + nta++; + rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; + + /* transfer page from old buffer to new buffer */ + new_buff->page = old_buff->page; + new_buff->page_dma = old_buff->page_dma; + new_buff->page_offset = old_buff->page_offset; + new_buff->pagecnt_bias = old_buff->pagecnt_bias; +} + +static void wx_dma_sync_frag(struct wx_ring *rx_ring, + struct wx_rx_buffer *rx_buffer) +{ + struct sk_buff *skb = rx_buffer->skb; + skb_frag_t *frag = &skb_shinfo(skb)->frags[0]; + + dma_sync_single_range_for_cpu(rx_ring->dev, + WX_CB(skb)->dma, + skb_frag_off(frag), + skb_frag_size(frag), + DMA_FROM_DEVICE); + + /* If the page was released, just unmap it. */ + if (unlikely(WX_CB(skb)->page_released)) + page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, false); +} + +static struct wx_rx_buffer *wx_get_rx_buffer(struct wx_ring *rx_ring, + union wx_rx_desc *rx_desc, + struct sk_buff **skb, + int *rx_buffer_pgcnt) +{ + struct wx_rx_buffer *rx_buffer; + unsigned int size; + + rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + size = le16_to_cpu(rx_desc->wb.upper.length); + +#if (PAGE_SIZE < 8192) + *rx_buffer_pgcnt = page_count(rx_buffer->page); +#else + *rx_buffer_pgcnt = 0; +#endif + + prefetchw(rx_buffer->page); + *skb = rx_buffer->skb; + + /* Delay unmapping of the first packet. It carries the header + * information, HW may still access the header after the writeback. + * Only unmap it when EOP is reached + */ + if (!wx_test_staterr(rx_desc, WX_RXD_STAT_EOP)) { + if (!*skb) + goto skip_sync; + } else { + if (*skb) + wx_dma_sync_frag(rx_ring, rx_buffer); + } + + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + size, + DMA_FROM_DEVICE); +skip_sync: + rx_buffer->pagecnt_bias--; + + return rx_buffer; +} + +static void wx_put_rx_buffer(struct wx_ring *rx_ring, + struct wx_rx_buffer *rx_buffer, + struct sk_buff *skb, + int rx_buffer_pgcnt) +{ + if (wx_can_reuse_rx_page(rx_buffer, rx_buffer_pgcnt)) { + /* hand second half of page back to the ring */ + wx_reuse_rx_page(rx_ring, rx_buffer); + } else { + if (!IS_ERR(skb) && WX_CB(skb)->dma == rx_buffer->dma) + /* the page has been released from the ring */ + WX_CB(skb)->page_released = true; + else + page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, false); + + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); + } + + /* clear contents of rx_buffer */ + rx_buffer->page = NULL; + rx_buffer->skb = NULL; +} + +static struct sk_buff *wx_build_skb(struct wx_ring *rx_ring, + struct wx_rx_buffer *rx_buffer, + union wx_rx_desc *rx_desc) +{ + unsigned int size = le16_to_cpu(rx_desc->wb.upper.length); +#if (PAGE_SIZE < 8192) + unsigned int truesize = WX_RX_BUFSZ; +#else + unsigned int truesize = ALIGN(size, L1_CACHE_BYTES); +#endif + struct sk_buff *skb = rx_buffer->skb; + + if (!skb) { + void *page_addr = page_address(rx_buffer->page) + + rx_buffer->page_offset; + + /* prefetch first cache line of first page */ + prefetch(page_addr); +#if L1_CACHE_BYTES < 128 + prefetch(page_addr + L1_CACHE_BYTES); +#endif + + /* allocate a skb to store the frags */ + skb = napi_alloc_skb(&rx_ring->q_vector->napi, WX_RXBUFFER_256); + if (unlikely(!skb)) + return NULL; + + /* we will be copying header into skb->data in + * pskb_may_pull so it is in our interest to prefetch + * it now to avoid a possible cache miss + */ + prefetchw(skb->data); + + if (size <= WX_RXBUFFER_256) { + memcpy(__skb_put(skb, size), page_addr, + ALIGN(size, sizeof(long))); + rx_buffer->pagecnt_bias++; + + return skb; + } + + if (!wx_test_staterr(rx_desc, WX_RXD_STAT_EOP)) + WX_CB(skb)->dma = rx_buffer->dma; + + skb_add_rx_frag(skb, 0, rx_buffer->page, + rx_buffer->page_offset, + size, truesize); + goto out; + + } else { + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, + rx_buffer->page_offset, size, truesize); + } + +out: +#if (PAGE_SIZE < 8192) + /* flip page offset to other buffer */ + rx_buffer->page_offset ^= truesize; +#else + /* move offset up to the next cache line */ + rx_buffer->page_offset += truesize; +#endif + + return skb; +} + +static bool wx_alloc_mapped_page(struct wx_ring *rx_ring, + struct wx_rx_buffer *bi) +{ + struct page *page = bi->page; + dma_addr_t dma; + + /* since we are recycling buffers we should seldom need to alloc */ + if (likely(page)) + return true; + + page = page_pool_dev_alloc_pages(rx_ring->page_pool); + WARN_ON(!page); + dma = page_pool_get_dma_addr(page); + + bi->page_dma = dma; + bi->page = page; + bi->page_offset = 0; + page_ref_add(page, USHRT_MAX - 1); + bi->pagecnt_bias = USHRT_MAX; + + return true; +} + +/** + * wx_alloc_rx_buffers - Replace used receive buffers + * @rx_ring: ring to place buffers on + * @cleaned_count: number of buffers to replace + **/ +void wx_alloc_rx_buffers(struct wx_ring *rx_ring, u16 cleaned_count) +{ + u16 i = rx_ring->next_to_use; + union wx_rx_desc *rx_desc; + struct wx_rx_buffer *bi; + + /* nothing to do */ + if (!cleaned_count) + return; + + rx_desc = WX_RX_DESC(rx_ring, i); + bi = &rx_ring->rx_buffer_info[i]; + i -= rx_ring->count; + + do { + if (!wx_alloc_mapped_page(rx_ring, bi)) + break; + + /* sync the buffer for use by the device */ + dma_sync_single_range_for_device(rx_ring->dev, bi->dma, + bi->page_offset, + WX_RX_BUFSZ, + DMA_FROM_DEVICE); + + rx_desc->read.pkt_addr = + cpu_to_le64(bi->page_dma + bi->page_offset); + + rx_desc++; + bi++; + i++; + if (unlikely(!i)) { + rx_desc = WX_RX_DESC(rx_ring, 0); + bi = rx_ring->rx_buffer_info; + i -= rx_ring->count; + } + + /* clear the status bits for the next_to_use descriptor */ + rx_desc->wb.upper.status_error = 0; + + cleaned_count--; + } while (cleaned_count); + + i += rx_ring->count; + + if (rx_ring->next_to_use != i) { + rx_ring->next_to_use = i; + /* update next to alloc since we have filled the ring */ + rx_ring->next_to_alloc = i; + + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, + * such as IA-64). + */ + wmb(); + writel(i, rx_ring->tail); + } +} + +u16 wx_desc_unused(struct wx_ring *ring) +{ + u16 ntc = ring->next_to_clean; + u16 ntu = ring->next_to_use; + + return ((ntc > ntu) ? 0 : ring->count) + ntc - ntu - 1; +} + +/** + * wx_is_non_eop - process handling of non-EOP buffers + * @rx_ring: Rx ring being processed + * @rx_desc: Rx descriptor for current buffer + * @skb: Current socket buffer containing buffer in progress + * + * This function updates next to clean. If the buffer is an EOP buffer + * this function exits returning false, otherwise it will place the + * sk_buff in the next buffer to be chained and return true indicating + * that this is in fact a non-EOP buffer. + **/ +static bool wx_is_non_eop(struct wx_ring *rx_ring, + union wx_rx_desc *rx_desc, + struct sk_buff *skb) +{ + u32 ntc = rx_ring->next_to_clean + 1; + + /* fetch, update, and store next to clean */ + ntc = (ntc < rx_ring->count) ? ntc : 0; + rx_ring->next_to_clean = ntc; + + prefetch(WX_RX_DESC(rx_ring, ntc)); + + /* if we are the last buffer then there is nothing else to do */ + if (likely(wx_test_staterr(rx_desc, WX_RXD_STAT_EOP))) + return false; + + rx_ring->rx_buffer_info[ntc].skb = skb; + + return true; +} + +static void wx_pull_tail(struct sk_buff *skb) +{ + skb_frag_t *frag = &skb_shinfo(skb)->frags[0]; + unsigned int pull_len; + unsigned char *va; + + /* it is valid to use page_address instead of kmap since we are + * working with pages allocated out of the lomem pool per + * alloc_page(GFP_ATOMIC) + */ + va = skb_frag_address(frag); + + /* we need the header to contain the greater of either ETH_HLEN or + * 60 bytes if the skb->len is less than 60 for skb_pad. + */ + pull_len = eth_get_headlen(skb->dev, va, WX_RXBUFFER_256); + + /* align pull length to size of long to optimize memcpy performance */ + skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long))); + + /* update all of the pointers */ + skb_frag_size_sub(frag, pull_len); + skb_frag_off_add(frag, pull_len); + skb->data_len -= pull_len; + skb->tail += pull_len; +} + +/** + * wx_cleanup_headers - Correct corrupted or empty headers + * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_desc: pointer to the EOP Rx descriptor + * @skb: pointer to current skb being fixed + * + * Check for corrupted packet headers caused by senders on the local L2 + * embedded NIC switch not setting up their Tx Descriptors right. These + * should be very rare. + * + * Also address the case where we are pulling data in on pages only + * and as such no data is present in the skb header. + * + * In addition if skb is not at least 60 bytes we need to pad it so that + * it is large enough to qualify as a valid Ethernet frame. + * + * Returns true if an error was encountered and skb was freed. + **/ +static bool wx_cleanup_headers(struct wx_ring *rx_ring, + union wx_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct net_device *netdev = rx_ring->netdev; + + /* verify that the packet does not have any known errors */ + if (!netdev || + unlikely(wx_test_staterr(rx_desc, WX_RXD_ERR_RXE) && + !(netdev->features & NETIF_F_RXALL))) { + dev_kfree_skb_any(skb); + return true; + } + + /* place header in linear portion of buffer */ + if (!skb_headlen(skb)) + wx_pull_tail(skb); + + /* if eth_skb_pad returns an error the skb was freed */ + if (eth_skb_pad(skb)) + return true; + + return false; +} + +/** + * wx_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf + * @q_vector: structure containing interrupt and ring information + * @rx_ring: rx descriptor ring to transact packets on + * @budget: Total limit on number of packets to process + * + * This function provides a "bounce buffer" approach to Rx interrupt + * processing. The advantage to this is that on systems that have + * expensive overhead for IOMMU access this provides a means of avoiding + * it by maintaining the mapping of the page to the system. + * + * Returns amount of work completed. + **/ +static int wx_clean_rx_irq(struct wx_q_vector *q_vector, + struct wx_ring *rx_ring, + int budget) +{ + unsigned int total_rx_bytes = 0, total_rx_packets = 0; + u16 cleaned_count = wx_desc_unused(rx_ring); + + do { + struct wx_rx_buffer *rx_buffer; + union wx_rx_desc *rx_desc; + struct sk_buff *skb; + int rx_buffer_pgcnt; + + /* return some buffers to hardware, one at a time is too slow */ + if (cleaned_count >= WX_RX_BUFFER_WRITE) { + wx_alloc_rx_buffers(rx_ring, cleaned_count); + cleaned_count = 0; + } + + rx_desc = WX_RX_DESC(rx_ring, rx_ring->next_to_clean); + if (!wx_test_staterr(rx_desc, WX_RXD_STAT_DD)) + break; + + /* This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we know the + * descriptor has been written back + */ + dma_rmb(); + + rx_buffer = wx_get_rx_buffer(rx_ring, rx_desc, &skb, &rx_buffer_pgcnt); + + /* retrieve a buffer from the ring */ + skb = wx_build_skb(rx_ring, rx_buffer, rx_desc); + + /* exit if we failed to retrieve a buffer */ + if (!skb) { + rx_buffer->pagecnt_bias++; + break; + } + + wx_put_rx_buffer(rx_ring, rx_buffer, skb, rx_buffer_pgcnt); + cleaned_count++; + + /* place incomplete frames back on ring for completion */ + if (wx_is_non_eop(rx_ring, rx_desc, skb)) + continue; + + /* verify the packet layout is correct */ + if (wx_cleanup_headers(rx_ring, rx_desc, skb)) + continue; + + /* probably a little skewed due to removing CRC */ + total_rx_bytes += skb->len; + + skb_record_rx_queue(skb, rx_ring->queue_index); + skb->protocol = eth_type_trans(skb, rx_ring->netdev); + napi_gro_receive(&q_vector->napi, skb); + + /* update budget accounting */ + total_rx_packets++; + } while (likely(total_rx_packets < budget)); + + u64_stats_update_begin(&rx_ring->syncp); + rx_ring->stats.packets += total_rx_packets; + rx_ring->stats.bytes += total_rx_bytes; + u64_stats_update_end(&rx_ring->syncp); + q_vector->rx.total_packets += total_rx_packets; + q_vector->rx.total_bytes += total_rx_bytes; + + return total_rx_packets; +} + +static struct netdev_queue *wx_txring_txq(const struct wx_ring *ring) +{ + return netdev_get_tx_queue(ring->netdev, ring->queue_index); +} + +/** + * wx_clean_tx_irq - Reclaim resources after transmit completes + * @q_vector: structure containing interrupt and ring information + * @tx_ring: tx ring to clean + * @napi_budget: Used to determine if we are in netpoll + **/ +static bool wx_clean_tx_irq(struct wx_q_vector *q_vector, + struct wx_ring *tx_ring, int napi_budget) +{ + unsigned int budget = q_vector->wx->tx_work_limit; + unsigned int total_bytes = 0, total_packets = 0; + unsigned int i = tx_ring->next_to_clean; + struct wx_tx_buffer *tx_buffer; + union wx_tx_desc *tx_desc; + + if (!netif_carrier_ok(tx_ring->netdev)) + return true; + + tx_buffer = &tx_ring->tx_buffer_info[i]; + tx_desc = WX_TX_DESC(tx_ring, i); + i -= tx_ring->count; + + do { + union wx_tx_desc *eop_desc = tx_buffer->next_to_watch; + + /* if next_to_watch is not set then there is no work pending */ + if (!eop_desc) + break; + + /* prevent any other reads prior to eop_desc */ + smp_rmb(); + + /* if DD is not set pending work has not been completed */ + if (!(eop_desc->wb.status & cpu_to_le32(WX_TXD_STAT_DD))) + break; + + /* clear next_to_watch to prevent false hangs */ + tx_buffer->next_to_watch = NULL; + + /* update the statistics for this packet */ + total_bytes += tx_buffer->bytecount; + total_packets += tx_buffer->gso_segs; + + /* free the skb */ + napi_consume_skb(tx_buffer->skb, napi_budget); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + + /* clear tx_buffer data */ + dma_unmap_len_set(tx_buffer, len, 0); + + /* unmap remaining buffers */ + while (tx_desc != eop_desc) { + tx_buffer++; + tx_desc++; + i++; + if (unlikely(!i)) { + i -= tx_ring->count; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = WX_TX_DESC(tx_ring, 0); + } + + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buffer, len)) { + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + } + } + + /* move us one more past the eop_desc for start of next pkt */ + tx_buffer++; + tx_desc++; + i++; + if (unlikely(!i)) { + i -= tx_ring->count; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = WX_TX_DESC(tx_ring, 0); + } + + /* issue prefetch for next Tx descriptor */ + prefetch(tx_desc); + + /* update budget accounting */ + budget--; + } while (likely(budget)); + + i += tx_ring->count; + tx_ring->next_to_clean = i; + u64_stats_update_begin(&tx_ring->syncp); + tx_ring->stats.bytes += total_bytes; + tx_ring->stats.packets += total_packets; + u64_stats_update_end(&tx_ring->syncp); + q_vector->tx.total_bytes += total_bytes; + q_vector->tx.total_packets += total_packets; + + netdev_tx_completed_queue(wx_txring_txq(tx_ring), + total_packets, total_bytes); + +#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2) + if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) && + (wx_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD))) { + /* Make sure that anybody stopping the queue after this + * sees the new next_to_clean. + */ + smp_mb(); + + if (__netif_subqueue_stopped(tx_ring->netdev, + tx_ring->queue_index) && + netif_running(tx_ring->netdev)) + netif_wake_subqueue(tx_ring->netdev, + tx_ring->queue_index); + } + + return !!budget; +} + +/** + * wx_poll - NAPI polling RX/TX cleanup routine + * @napi: napi struct with our devices info in it + * @budget: amount of work driver is allowed to do this pass, in packets + * + * This function will clean all queues associated with a q_vector. + **/ +static int wx_poll(struct napi_struct *napi, int budget) +{ + struct wx_q_vector *q_vector = container_of(napi, struct wx_q_vector, napi); + int per_ring_budget, work_done = 0; + struct wx *wx = q_vector->wx; + bool clean_complete = true; + struct wx_ring *ring; + + wx_for_each_ring(ring, q_vector->tx) { + if (!wx_clean_tx_irq(q_vector, ring, budget)) + clean_complete = false; + } + + /* Exit if we are called by netpoll */ + if (budget <= 0) + return budget; + + /* attempt to distribute budget to each queue fairly, but don't allow + * the budget to go below 1 because we'll exit polling + */ + if (q_vector->rx.count > 1) + per_ring_budget = max(budget / q_vector->rx.count, 1); + else + per_ring_budget = budget; + + wx_for_each_ring(ring, q_vector->rx) { + int cleaned = wx_clean_rx_irq(q_vector, ring, per_ring_budget); + + work_done += cleaned; + if (cleaned >= per_ring_budget) + clean_complete = false; + } + + /* If all work not completed, return budget and keep polling */ + if (!clean_complete) + return budget; + + /* all work done, exit the polling mode */ + if (likely(napi_complete_done(napi, work_done))) { + if (netif_running(wx->netdev)) + wx_intr_enable(wx, WX_INTR_Q(q_vector->v_idx)); + } + + return min(work_done, budget - 1); +} + +static int wx_maybe_stop_tx(struct wx_ring *tx_ring, u16 size) +{ + if (likely(wx_desc_unused(tx_ring) >= size)) + return 0; + + netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); + + /* For the next check */ + smp_mb(); + + /* We need to check again in a case another CPU has just + * made room available. + */ + if (likely(wx_desc_unused(tx_ring) < size)) + return -EBUSY; + + /* A reprieve! - use start_queue because it doesn't call schedule */ + netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index); + + return 0; +} + +static void wx_tx_map(struct wx_ring *tx_ring, + struct wx_tx_buffer *first) +{ + struct sk_buff *skb = first->skb; + struct wx_tx_buffer *tx_buffer; + u16 i = tx_ring->next_to_use; + unsigned int data_len, size; + union wx_tx_desc *tx_desc; + skb_frag_t *frag; + dma_addr_t dma; + u32 cmd_type; + + cmd_type = WX_TXD_DTYP_DATA | WX_TXD_IFCS; + tx_desc = WX_TX_DESC(tx_ring, i); + + tx_desc->read.olinfo_status = cpu_to_le32(skb->len << WX_TXD_PAYLEN_SHIFT); + + size = skb_headlen(skb); + data_len = skb->data_len; + dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE); + + tx_buffer = first; + + for (frag = &skb_shinfo(skb)->frags[0];; frag++) { + if (dma_mapping_error(tx_ring->dev, dma)) + goto dma_error; + + /* record length, and DMA address */ + dma_unmap_len_set(tx_buffer, len, size); + dma_unmap_addr_set(tx_buffer, dma, dma); + + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + while (unlikely(size > WX_MAX_DATA_PER_TXD)) { + tx_desc->read.cmd_type_len = + cpu_to_le32(cmd_type ^ WX_MAX_DATA_PER_TXD); + + i++; + tx_desc++; + if (i == tx_ring->count) { + tx_desc = WX_TX_DESC(tx_ring, 0); + i = 0; + } + tx_desc->read.olinfo_status = 0; + + dma += WX_MAX_DATA_PER_TXD; + size -= WX_MAX_DATA_PER_TXD; + + tx_desc->read.buffer_addr = cpu_to_le64(dma); + } + + if (likely(!data_len)) + break; + + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type ^ size); + + i++; + tx_desc++; + if (i == tx_ring->count) { + tx_desc = WX_TX_DESC(tx_ring, 0); + i = 0; + } + tx_desc->read.olinfo_status = 0; + + size = skb_frag_size(frag); + + data_len -= size; + + dma = skb_frag_dma_map(tx_ring->dev, frag, 0, size, + DMA_TO_DEVICE); + + tx_buffer = &tx_ring->tx_buffer_info[i]; + } + + /* write last descriptor with RS and EOP bits */ + cmd_type |= size | WX_TXD_EOP | WX_TXD_RS; + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + + netdev_tx_sent_queue(wx_txring_txq(tx_ring), first->bytecount); + + skb_tx_timestamp(skb); + + /* Force memory writes to complete before letting h/w know there + * are new descriptors to fetch. (Only applicable for weak-ordered + * memory model archs, such as IA-64). + * + * We also need this memory barrier to make certain all of the + * status bits have been updated before next_to_watch is written. + */ + wmb(); + + /* set next_to_watch value indicating a packet is present */ + first->next_to_watch = tx_desc; + + i++; + if (i == tx_ring->count) + i = 0; + + tx_ring->next_to_use = i; + + wx_maybe_stop_tx(tx_ring, DESC_NEEDED); + + if (netif_xmit_stopped(wx_txring_txq(tx_ring)) || !netdev_xmit_more()) + writel(i, tx_ring->tail); + + return; +dma_error: + dev_err(tx_ring->dev, "TX DMA map failed\n"); + + /* clear dma mappings for failed tx_buffer_info map */ + for (;;) { + tx_buffer = &tx_ring->tx_buffer_info[i]; + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + if (tx_buffer == first) + break; + if (i == 0) + i += tx_ring->count; + i--; + } + + dev_kfree_skb_any(first->skb); + first->skb = NULL; + + tx_ring->next_to_use = i; +} + +static netdev_tx_t wx_xmit_frame_ring(struct sk_buff *skb, + struct wx_ring *tx_ring) +{ + u16 count = TXD_USE_COUNT(skb_headlen(skb)); + struct wx_tx_buffer *first; + unsigned short f; + + /* need: 1 descriptor per page * PAGE_SIZE/WX_MAX_DATA_PER_TXD, + * + 1 desc for skb_headlen/WX_MAX_DATA_PER_TXD, + * + 2 desc gap to keep tail from touching head, + * + 1 desc for context descriptor, + * otherwise try next time + */ + for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) + count += TXD_USE_COUNT(skb_frag_size(&skb_shinfo(skb)-> + frags[f])); + + if (wx_maybe_stop_tx(tx_ring, count + 3)) + return NETDEV_TX_BUSY; + + /* record the location of the first descriptor for this packet */ + first = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + first->skb = skb; + first->bytecount = skb->len; + first->gso_segs = 1; + + wx_tx_map(tx_ring, first); + + return NETDEV_TX_OK; +} + +netdev_tx_t wx_xmit_frame(struct sk_buff *skb, + struct net_device *netdev) +{ + unsigned int r_idx = skb->queue_mapping; + struct wx *wx = netdev_priv(netdev); + struct wx_ring *tx_ring; + + if (!netif_carrier_ok(netdev)) { + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + + /* The minimum packet size for olinfo paylen is 17 so pad the skb + * in order to meet this minimum size requirement. + */ + if (skb_put_padto(skb, 17)) + return NETDEV_TX_OK; + + if (r_idx >= wx->num_tx_queues) + r_idx = r_idx % wx->num_tx_queues; + tx_ring = wx->tx_ring[r_idx]; + + return wx_xmit_frame_ring(skb, tx_ring); +} +EXPORT_SYMBOL(wx_xmit_frame); + +void wx_napi_enable_all(struct wx *wx) +{ + struct wx_q_vector *q_vector; + int q_idx; + + for (q_idx = 0; q_idx < wx->num_q_vectors; q_idx++) { + q_vector = wx->q_vector[q_idx]; + napi_enable(&q_vector->napi); + } +} +EXPORT_SYMBOL(wx_napi_enable_all); + +void wx_napi_disable_all(struct wx *wx) +{ + struct wx_q_vector *q_vector; + int q_idx; + + for (q_idx = 0; q_idx < wx->num_q_vectors; q_idx++) { + q_vector = wx->q_vector[q_idx]; + napi_disable(&q_vector->napi); + } +} +EXPORT_SYMBOL(wx_napi_disable_all); + +/** + * wx_set_rss_queues: Allocate queues for RSS + * @wx: board private structure to initialize + * + * This is our "base" multiqueue mode. RSS (Receive Side Scaling) will try + * to allocate one Rx queue per CPU, and if available, one Tx queue per CPU. + * + **/ +static void wx_set_rss_queues(struct wx *wx) +{ + wx->num_rx_queues = wx->mac.max_rx_queues; + wx->num_tx_queues = wx->mac.max_tx_queues; +} + +static void wx_set_num_queues(struct wx *wx) +{ + /* Start with base case */ + wx->num_rx_queues = 1; + wx->num_tx_queues = 1; + wx->queues_per_pool = 1; + + wx_set_rss_queues(wx); +} + +/** + * wx_acquire_msix_vectors - acquire MSI-X vectors + * @wx: board private structure + * + * Attempts to acquire a suitable range of MSI-X vector interrupts. Will + * return a negative error code if unable to acquire MSI-X vectors for any + * reason. + */ +static int wx_acquire_msix_vectors(struct wx *wx) +{ + struct irq_affinity affd = {0, }; + int nvecs, i; + + nvecs = min_t(int, num_online_cpus(), wx->mac.max_msix_vectors); + + wx->msix_entries = kcalloc(nvecs, + sizeof(struct msix_entry), + GFP_KERNEL); + if (!wx->msix_entries) + return -ENOMEM; + + nvecs = pci_alloc_irq_vectors_affinity(wx->pdev, nvecs, + nvecs, + PCI_IRQ_MSIX | PCI_IRQ_AFFINITY, + &affd); + if (nvecs < 0) { + wx_err(wx, "Failed to allocate MSI-X interrupts. Err: %d\n", nvecs); + kfree(wx->msix_entries); + wx->msix_entries = NULL; + return nvecs; + } + + for (i = 0; i < nvecs; i++) { + wx->msix_entries[i].entry = i; + wx->msix_entries[i].vector = pci_irq_vector(wx->pdev, i); + } + + /* one for msix_other */ + nvecs -= 1; + wx->num_q_vectors = nvecs; + wx->num_rx_queues = nvecs; + wx->num_tx_queues = nvecs; + + return 0; +} + +/** + * wx_set_interrupt_capability - set MSI-X or MSI if supported + * @wx: board private structure to initialize + * + * Attempt to configure the interrupts using the best available + * capabilities of the hardware and the kernel. + **/ +static int wx_set_interrupt_capability(struct wx *wx) +{ + struct pci_dev *pdev = wx->pdev; + int nvecs, ret; + + /* We will try to get MSI-X interrupts first */ + ret = wx_acquire_msix_vectors(wx); + if (ret == 0 || (ret == -ENOMEM)) + return ret; + + wx->num_rx_queues = 1; + wx->num_tx_queues = 1; + wx->num_q_vectors = 1; + + /* minmum one for queue, one for misc*/ + nvecs = 1; + nvecs = pci_alloc_irq_vectors(pdev, nvecs, + nvecs, PCI_IRQ_MSI | PCI_IRQ_LEGACY); + if (nvecs == 1) { + if (pdev->msi_enabled) + wx_err(wx, "Fallback to MSI.\n"); + else + wx_err(wx, "Fallback to LEGACY.\n"); + } else { + wx_err(wx, "Failed to allocate MSI/LEGACY interrupts. Error: %d\n", nvecs); + return nvecs; + } + + pdev->irq = pci_irq_vector(pdev, 0); + + return 0; +} + +/** + * wx_cache_ring_rss - Descriptor ring to register mapping for RSS + * @wx: board private structure to initialize + * + * Cache the descriptor ring offsets for RSS, ATR, FCoE, and SR-IOV. + * + **/ +static void wx_cache_ring_rss(struct wx *wx) +{ + u16 i; + + for (i = 0; i < wx->num_rx_queues; i++) + wx->rx_ring[i]->reg_idx = i; + + for (i = 0; i < wx->num_tx_queues; i++) + wx->tx_ring[i]->reg_idx = i; +} + +static void wx_add_ring(struct wx_ring *ring, struct wx_ring_container *head) +{ + ring->next = head->ring; + head->ring = ring; + head->count++; +} + +/** + * wx_alloc_q_vector - Allocate memory for a single interrupt vector + * @wx: board private structure to initialize + * @v_count: q_vectors allocated on wx, used for ring interleaving + * @v_idx: index of vector in wx struct + * @txr_count: total number of Tx rings to allocate + * @txr_idx: index of first Tx ring to allocate + * @rxr_count: total number of Rx rings to allocate + * @rxr_idx: index of first Rx ring to allocate + * + * We allocate one q_vector. If allocation fails we return -ENOMEM. + **/ +static int wx_alloc_q_vector(struct wx *wx, + unsigned int v_count, unsigned int v_idx, + unsigned int txr_count, unsigned int txr_idx, + unsigned int rxr_count, unsigned int rxr_idx) +{ + struct wx_q_vector *q_vector; + int ring_count, default_itr; + struct wx_ring *ring; + + /* note this will allocate space for the ring structure as well! */ + ring_count = txr_count + rxr_count; + + q_vector = kzalloc(struct_size(q_vector, ring, ring_count), + GFP_KERNEL); + if (!q_vector) + return -ENOMEM; + + /* initialize NAPI */ + netif_napi_add(wx->netdev, &q_vector->napi, + wx_poll); + + /* tie q_vector and wx together */ + wx->q_vector[v_idx] = q_vector; + q_vector->wx = wx; + q_vector->v_idx = v_idx; + if (cpu_online(v_idx)) + q_vector->numa_node = cpu_to_node(v_idx); + + /* initialize pointer to rings */ + ring = q_vector->ring; + + if (wx->mac.type == wx_mac_sp) + default_itr = WX_12K_ITR; + else + default_itr = WX_7K_ITR; + /* initialize ITR */ + if (txr_count && !rxr_count) + /* tx only vector */ + q_vector->itr = wx->tx_itr_setting ? + default_itr : wx->tx_itr_setting; + else + /* rx or rx/tx vector */ + q_vector->itr = wx->rx_itr_setting ? + default_itr : wx->rx_itr_setting; + + while (txr_count) { + /* assign generic ring traits */ + ring->dev = &wx->pdev->dev; + ring->netdev = wx->netdev; + + /* configure backlink on ring */ + ring->q_vector = q_vector; + + /* update q_vector Tx values */ + wx_add_ring(ring, &q_vector->tx); + + /* apply Tx specific ring traits */ + ring->count = wx->tx_ring_count; + + ring->queue_index = txr_idx; + + /* assign ring to wx */ + wx->tx_ring[txr_idx] = ring; + + /* update count and index */ + txr_count--; + txr_idx += v_count; + + /* push pointer to next ring */ + ring++; + } + + while (rxr_count) { + /* assign generic ring traits */ + ring->dev = &wx->pdev->dev; + ring->netdev = wx->netdev; + + /* configure backlink on ring */ + ring->q_vector = q_vector; + + /* update q_vector Rx values */ + wx_add_ring(ring, &q_vector->rx); + + /* apply Rx specific ring traits */ + ring->count = wx->rx_ring_count; + ring->queue_index = rxr_idx; + + /* assign ring to wx */ + wx->rx_ring[rxr_idx] = ring; + + /* update count and index */ + rxr_count--; + rxr_idx += v_count; + + /* push pointer to next ring */ + ring++; + } + + return 0; +} + +/** + * wx_free_q_vector - Free memory allocated for specific interrupt vector + * @wx: board private structure to initialize + * @v_idx: Index of vector to be freed + * + * This function frees the memory allocated to the q_vector. In addition if + * NAPI is enabled it will delete any references to the NAPI struct prior + * to freeing the q_vector. + **/ +static void wx_free_q_vector(struct wx *wx, int v_idx) +{ + struct wx_q_vector *q_vector = wx->q_vector[v_idx]; + struct wx_ring *ring; + + wx_for_each_ring(ring, q_vector->tx) + wx->tx_ring[ring->queue_index] = NULL; + + wx_for_each_ring(ring, q_vector->rx) + wx->rx_ring[ring->queue_index] = NULL; + + wx->q_vector[v_idx] = NULL; + netif_napi_del(&q_vector->napi); + kfree_rcu(q_vector, rcu); +} + +/** + * wx_alloc_q_vectors - Allocate memory for interrupt vectors + * @wx: board private structure to initialize + * + * We allocate one q_vector per queue interrupt. If allocation fails we + * return -ENOMEM. + **/ +static int wx_alloc_q_vectors(struct wx *wx) +{ + unsigned int rxr_idx = 0, txr_idx = 0, v_idx = 0; + unsigned int rxr_remaining = wx->num_rx_queues; + unsigned int txr_remaining = wx->num_tx_queues; + unsigned int q_vectors = wx->num_q_vectors; + int rqpv, tqpv; + int err; + + for (; v_idx < q_vectors; v_idx++) { + rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - v_idx); + tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - v_idx); + err = wx_alloc_q_vector(wx, q_vectors, v_idx, + tqpv, txr_idx, + rqpv, rxr_idx); + + if (err) + goto err_out; + + /* update counts and index */ + rxr_remaining -= rqpv; + txr_remaining -= tqpv; + rxr_idx++; + txr_idx++; + } + + return 0; + +err_out: + wx->num_tx_queues = 0; + wx->num_rx_queues = 0; + wx->num_q_vectors = 0; + + while (v_idx--) + wx_free_q_vector(wx, v_idx); + + return -ENOMEM; +} + +/** + * wx_free_q_vectors - Free memory allocated for interrupt vectors + * @wx: board private structure to initialize + * + * This function frees the memory allocated to the q_vectors. In addition if + * NAPI is enabled it will delete any references to the NAPI struct prior + * to freeing the q_vector. + **/ +static void wx_free_q_vectors(struct wx *wx) +{ + int v_idx = wx->num_q_vectors; + + wx->num_tx_queues = 0; + wx->num_rx_queues = 0; + wx->num_q_vectors = 0; + + while (v_idx--) + wx_free_q_vector(wx, v_idx); +} + +void wx_reset_interrupt_capability(struct wx *wx) +{ + struct pci_dev *pdev = wx->pdev; + + if (!pdev->msi_enabled && !pdev->msix_enabled) + return; + + pci_free_irq_vectors(wx->pdev); + if (pdev->msix_enabled) { + kfree(wx->msix_entries); + wx->msix_entries = NULL; + } +} +EXPORT_SYMBOL(wx_reset_interrupt_capability); + +/** + * wx_clear_interrupt_scheme - Clear the current interrupt scheme settings + * @wx: board private structure to clear interrupt scheme on + * + * We go through and clear interrupt specific resources and reset the structure + * to pre-load conditions + **/ +void wx_clear_interrupt_scheme(struct wx *wx) +{ + wx_free_q_vectors(wx); + wx_reset_interrupt_capability(wx); +} +EXPORT_SYMBOL(wx_clear_interrupt_scheme); + +int wx_init_interrupt_scheme(struct wx *wx) +{ + int ret; + + /* Number of supported queues */ + wx_set_num_queues(wx); + + /* Set interrupt mode */ + ret = wx_set_interrupt_capability(wx); + if (ret) { + wx_err(wx, "Allocate irq vectors for failed.\n"); + return ret; + } + + /* Allocate memory for queues */ + ret = wx_alloc_q_vectors(wx); + if (ret) { + wx_err(wx, "Unable to allocate memory for queue vectors.\n"); + wx_reset_interrupt_capability(wx); + return ret; + } + + wx_cache_ring_rss(wx); + + return 0; +} +EXPORT_SYMBOL(wx_init_interrupt_scheme); + +irqreturn_t wx_msix_clean_rings(int __always_unused irq, void *data) +{ + struct wx_q_vector *q_vector = data; + + /* EIAM disabled interrupts (on this vector) for us */ + if (q_vector->rx.ring || q_vector->tx.ring) + napi_schedule_irqoff(&q_vector->napi); + + return IRQ_HANDLED; +} +EXPORT_SYMBOL(wx_msix_clean_rings); + +void wx_free_irq(struct wx *wx) +{ + struct pci_dev *pdev = wx->pdev; + int vector; + + if (!(pdev->msix_enabled)) { + free_irq(pdev->irq, wx); + return; + } + + for (vector = 0; vector < wx->num_q_vectors; vector++) { + struct wx_q_vector *q_vector = wx->q_vector[vector]; + struct msix_entry *entry = &wx->msix_entries[vector]; + + /* free only the irqs that were actually requested */ + if (!q_vector->rx.ring && !q_vector->tx.ring) + continue; + + free_irq(entry->vector, q_vector); + } + + free_irq(wx->msix_entries[vector].vector, wx); +} +EXPORT_SYMBOL(wx_free_irq); + +/** + * wx_setup_isb_resources - allocate interrupt status resources + * @wx: board private structure + * + * Return 0 on success, negative on failure + **/ +int wx_setup_isb_resources(struct wx *wx) +{ + struct pci_dev *pdev = wx->pdev; + + wx->isb_mem = dma_alloc_coherent(&pdev->dev, + sizeof(u32) * 4, + &wx->isb_dma, + GFP_KERNEL); + if (!wx->isb_mem) { + wx_err(wx, "Alloc isb_mem failed\n"); + return -ENOMEM; + } + + return 0; +} +EXPORT_SYMBOL(wx_setup_isb_resources); + +/** + * wx_free_isb_resources - allocate all queues Rx resources + * @wx: board private structure + * + * Return 0 on success, negative on failure + **/ +void wx_free_isb_resources(struct wx *wx) +{ + struct pci_dev *pdev = wx->pdev; + + dma_free_coherent(&pdev->dev, sizeof(u32) * 4, + wx->isb_mem, wx->isb_dma); + wx->isb_mem = NULL; +} +EXPORT_SYMBOL(wx_free_isb_resources); + +u32 wx_misc_isb(struct wx *wx, enum wx_isb_idx idx) +{ + u32 cur_tag = 0; + + cur_tag = wx->isb_mem[WX_ISB_HEADER]; + wx->isb_tag[idx] = cur_tag; + + return (__force u32)cpu_to_le32(wx->isb_mem[idx]); +} +EXPORT_SYMBOL(wx_misc_isb); + +/** + * wx_set_ivar - set the IVAR registers, mapping interrupt causes to vectors + * @wx: pointer to wx struct + * @direction: 0 for Rx, 1 for Tx, -1 for other causes + * @queue: queue to map the corresponding interrupt to + * @msix_vector: the vector to map to the corresponding queue + * + **/ +static void wx_set_ivar(struct wx *wx, s8 direction, + u16 queue, u16 msix_vector) +{ + u32 ivar, index; + + if (direction == -1) { + /* other causes */ + msix_vector |= WX_PX_IVAR_ALLOC_VAL; + index = 0; + ivar = rd32(wx, WX_PX_MISC_IVAR); + ivar &= ~(0xFF << index); + ivar |= (msix_vector << index); + wr32(wx, WX_PX_MISC_IVAR, ivar); + } else { + /* tx or rx causes */ + msix_vector |= WX_PX_IVAR_ALLOC_VAL; + index = ((16 * (queue & 1)) + (8 * direction)); + ivar = rd32(wx, WX_PX_IVAR(queue >> 1)); + ivar &= ~(0xFF << index); + ivar |= (msix_vector << index); + wr32(wx, WX_PX_IVAR(queue >> 1), ivar); + } +} + +/** + * wx_write_eitr - write EITR register in hardware specific way + * @q_vector: structure containing interrupt and ring information + * + * This function is made to be called by ethtool and by the driver + * when it needs to update EITR registers at runtime. Hardware + * specific quirks/differences are taken care of here. + */ +static void wx_write_eitr(struct wx_q_vector *q_vector) +{ + struct wx *wx = q_vector->wx; + int v_idx = q_vector->v_idx; + u32 itr_reg; + + if (wx->mac.type == wx_mac_sp) + itr_reg = q_vector->itr & WX_SP_MAX_EITR; + else + itr_reg = q_vector->itr & WX_EM_MAX_EITR; + + itr_reg |= WX_PX_ITR_CNT_WDIS; + + wr32(wx, WX_PX_ITR(v_idx), itr_reg); +} + +/** + * wx_configure_vectors - Configure vectors for hardware + * @wx: board private structure + * + * wx_configure_vectors sets up the hardware to properly generate MSI-X/MSI/LEGACY + * interrupts. + **/ +void wx_configure_vectors(struct wx *wx) +{ + struct pci_dev *pdev = wx->pdev; + u32 eitrsel = 0; + u16 v_idx; + + if (pdev->msix_enabled) { + /* Populate MSIX to EITR Select */ + wr32(wx, WX_PX_ITRSEL, eitrsel); + /* use EIAM to auto-mask when MSI-X interrupt is asserted + * this saves a register write for every interrupt + */ + wr32(wx, WX_PX_GPIE, WX_PX_GPIE_MODEL); + } else { + /* legacy interrupts, use EIAM to auto-mask when reading EICR, + * specifically only auto mask tx and rx interrupts. + */ + wr32(wx, WX_PX_GPIE, 0); + } + + /* Populate the IVAR table and set the ITR values to the + * corresponding register. + */ + for (v_idx = 0; v_idx < wx->num_q_vectors; v_idx++) { + struct wx_q_vector *q_vector = wx->q_vector[v_idx]; + struct wx_ring *ring; + + wx_for_each_ring(ring, q_vector->rx) + wx_set_ivar(wx, 0, ring->reg_idx, v_idx); + + wx_for_each_ring(ring, q_vector->tx) + wx_set_ivar(wx, 1, ring->reg_idx, v_idx); + + wx_write_eitr(q_vector); + } + + wx_set_ivar(wx, -1, 0, v_idx); + if (pdev->msix_enabled) + wr32(wx, WX_PX_ITR(v_idx), 1950); +} +EXPORT_SYMBOL(wx_configure_vectors); + +/** + * wx_clean_rx_ring - Free Rx Buffers per Queue + * @rx_ring: ring to free buffers from + **/ +static void wx_clean_rx_ring(struct wx_ring *rx_ring) +{ + struct wx_rx_buffer *rx_buffer; + u16 i = rx_ring->next_to_clean; + + rx_buffer = &rx_ring->rx_buffer_info[i]; + + /* Free all the Rx ring sk_buffs */ + while (i != rx_ring->next_to_alloc) { + if (rx_buffer->skb) { + struct sk_buff *skb = rx_buffer->skb; + + if (WX_CB(skb)->page_released) + page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, false); + + dev_kfree_skb(skb); + } + + /* Invalidate cache lines that may have been written to by + * device so that we avoid corrupting memory. + */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + WX_RX_BUFSZ, + DMA_FROM_DEVICE); + + /* free resources associated with mapping */ + page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, false); + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); + + i++; + rx_buffer++; + if (i == rx_ring->count) { + i = 0; + rx_buffer = rx_ring->rx_buffer_info; + } + } + + rx_ring->next_to_alloc = 0; + rx_ring->next_to_clean = 0; + rx_ring->next_to_use = 0; +} + +/** + * wx_clean_all_rx_rings - Free Rx Buffers for all queues + * @wx: board private structure + **/ +void wx_clean_all_rx_rings(struct wx *wx) +{ + int i; + + for (i = 0; i < wx->num_rx_queues; i++) + wx_clean_rx_ring(wx->rx_ring[i]); +} +EXPORT_SYMBOL(wx_clean_all_rx_rings); + +/** + * wx_free_rx_resources - Free Rx Resources + * @rx_ring: ring to clean the resources from + * + * Free all receive software resources + **/ +static void wx_free_rx_resources(struct wx_ring *rx_ring) +{ + wx_clean_rx_ring(rx_ring); + kvfree(rx_ring->rx_buffer_info); + rx_ring->rx_buffer_info = NULL; + + /* if not set, then don't free */ + if (!rx_ring->desc) + return; + + dma_free_coherent(rx_ring->dev, rx_ring->size, + rx_ring->desc, rx_ring->dma); + + rx_ring->desc = NULL; + + if (rx_ring->page_pool) { + page_pool_destroy(rx_ring->page_pool); + rx_ring->page_pool = NULL; + } +} + +/** + * wx_free_all_rx_resources - Free Rx Resources for All Queues + * @wx: pointer to hardware structure + * + * Free all receive software resources + **/ +static void wx_free_all_rx_resources(struct wx *wx) +{ + int i; + + for (i = 0; i < wx->num_rx_queues; i++) + wx_free_rx_resources(wx->rx_ring[i]); +} + +/** + * wx_clean_tx_ring - Free Tx Buffers + * @tx_ring: ring to be cleaned + **/ +static void wx_clean_tx_ring(struct wx_ring *tx_ring) +{ + struct wx_tx_buffer *tx_buffer; + u16 i = tx_ring->next_to_clean; + + tx_buffer = &tx_ring->tx_buffer_info[i]; + + while (i != tx_ring->next_to_use) { + union wx_tx_desc *eop_desc, *tx_desc; + + /* Free all the Tx ring sk_buffs */ + dev_kfree_skb_any(tx_buffer->skb); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + + /* check for eop_desc to determine the end of the packet */ + eop_desc = tx_buffer->next_to_watch; + tx_desc = WX_TX_DESC(tx_ring, i); + + /* unmap remaining buffers */ + while (tx_desc != eop_desc) { + tx_buffer++; + tx_desc++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = WX_TX_DESC(tx_ring, 0); + } + + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + } + + /* move us one more past the eop_desc for start of next pkt */ + tx_buffer++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + } + } + + netdev_tx_reset_queue(wx_txring_txq(tx_ring)); + + /* reset next_to_use and next_to_clean */ + tx_ring->next_to_use = 0; + tx_ring->next_to_clean = 0; +} + +/** + * wx_clean_all_tx_rings - Free Tx Buffers for all queues + * @wx: board private structure + **/ +void wx_clean_all_tx_rings(struct wx *wx) +{ + int i; + + for (i = 0; i < wx->num_tx_queues; i++) + wx_clean_tx_ring(wx->tx_ring[i]); +} +EXPORT_SYMBOL(wx_clean_all_tx_rings); + +/** + * wx_free_tx_resources - Free Tx Resources per Queue + * @tx_ring: Tx descriptor ring for a specific queue + * + * Free all transmit software resources + **/ +static void wx_free_tx_resources(struct wx_ring *tx_ring) +{ + wx_clean_tx_ring(tx_ring); + kvfree(tx_ring->tx_buffer_info); + tx_ring->tx_buffer_info = NULL; + + /* if not set, then don't free */ + if (!tx_ring->desc) + return; + + dma_free_coherent(tx_ring->dev, tx_ring->size, + tx_ring->desc, tx_ring->dma); + tx_ring->desc = NULL; +} + +/** + * wx_free_all_tx_resources - Free Tx Resources for All Queues + * @wx: pointer to hardware structure + * + * Free all transmit software resources + **/ +static void wx_free_all_tx_resources(struct wx *wx) +{ + int i; + + for (i = 0; i < wx->num_tx_queues; i++) + wx_free_tx_resources(wx->tx_ring[i]); +} + +void wx_free_resources(struct wx *wx) +{ + wx_free_isb_resources(wx); + wx_free_all_rx_resources(wx); + wx_free_all_tx_resources(wx); +} +EXPORT_SYMBOL(wx_free_resources); + +static int wx_alloc_page_pool(struct wx_ring *rx_ring) +{ + int ret = 0; + + struct page_pool_params pp_params = { + .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, + .order = 0, + .pool_size = rx_ring->size, + .nid = dev_to_node(rx_ring->dev), + .dev = rx_ring->dev, + .dma_dir = DMA_FROM_DEVICE, + .offset = 0, + .max_len = PAGE_SIZE, + }; + + rx_ring->page_pool = page_pool_create(&pp_params); + if (IS_ERR(rx_ring->page_pool)) { + rx_ring->page_pool = NULL; + ret = PTR_ERR(rx_ring->page_pool); + } + + return ret; +} + +/** + * wx_setup_rx_resources - allocate Rx resources (Descriptors) + * @rx_ring: rx descriptor ring (for a specific queue) to setup + * + * Returns 0 on success, negative on failure + **/ +static int wx_setup_rx_resources(struct wx_ring *rx_ring) +{ + struct device *dev = rx_ring->dev; + int orig_node = dev_to_node(dev); + int numa_node = NUMA_NO_NODE; + int size, ret; + + size = sizeof(struct wx_rx_buffer) * rx_ring->count; + + if (rx_ring->q_vector) + numa_node = rx_ring->q_vector->numa_node; + + rx_ring->rx_buffer_info = kvmalloc_node(size, GFP_KERNEL, numa_node); + if (!rx_ring->rx_buffer_info) + rx_ring->rx_buffer_info = kvmalloc(size, GFP_KERNEL); + if (!rx_ring->rx_buffer_info) + goto err; + + /* Round up to nearest 4K */ + rx_ring->size = rx_ring->count * sizeof(union wx_rx_desc); + rx_ring->size = ALIGN(rx_ring->size, 4096); + + set_dev_node(dev, numa_node); + rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size, + &rx_ring->dma, GFP_KERNEL); + if (!rx_ring->desc) { + set_dev_node(dev, orig_node); + rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size, + &rx_ring->dma, GFP_KERNEL); + } + + if (!rx_ring->desc) + goto err; + + rx_ring->next_to_clean = 0; + rx_ring->next_to_use = 0; + + ret = wx_alloc_page_pool(rx_ring); + if (ret < 0) { + dev_err(rx_ring->dev, "Page pool creation failed: %d\n", ret); + goto err; + } + + return 0; +err: + kvfree(rx_ring->rx_buffer_info); + rx_ring->rx_buffer_info = NULL; + dev_err(dev, "Unable to allocate memory for the Rx descriptor ring\n"); + return -ENOMEM; +} + +/** + * wx_setup_all_rx_resources - allocate all queues Rx resources + * @wx: pointer to hardware structure + * + * If this function returns with an error, then it's possible one or + * more of the rings is populated (while the rest are not). It is the + * callers duty to clean those orphaned rings. + * + * Return 0 on success, negative on failure + **/ +static int wx_setup_all_rx_resources(struct wx *wx) +{ + int i, err = 0; + + for (i = 0; i < wx->num_rx_queues; i++) { + err = wx_setup_rx_resources(wx->rx_ring[i]); + if (!err) + continue; + + wx_err(wx, "Allocation for Rx Queue %u failed\n", i); + goto err_setup_rx; + } + + return 0; +err_setup_rx: + /* rewind the index freeing the rings as we go */ + while (i--) + wx_free_rx_resources(wx->rx_ring[i]); + return err; +} + +/** + * wx_setup_tx_resources - allocate Tx resources (Descriptors) + * @tx_ring: tx descriptor ring (for a specific queue) to setup + * + * Return 0 on success, negative on failure + **/ +static int wx_setup_tx_resources(struct wx_ring *tx_ring) +{ + struct device *dev = tx_ring->dev; + int orig_node = dev_to_node(dev); + int numa_node = NUMA_NO_NODE; + int size; + + size = sizeof(struct wx_tx_buffer) * tx_ring->count; + + if (tx_ring->q_vector) + numa_node = tx_ring->q_vector->numa_node; + + tx_ring->tx_buffer_info = kvmalloc_node(size, GFP_KERNEL, numa_node); + if (!tx_ring->tx_buffer_info) + tx_ring->tx_buffer_info = kvmalloc(size, GFP_KERNEL); + if (!tx_ring->tx_buffer_info) + goto err; + + /* round up to nearest 4K */ + tx_ring->size = tx_ring->count * sizeof(union wx_tx_desc); + tx_ring->size = ALIGN(tx_ring->size, 4096); + + set_dev_node(dev, numa_node); + tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size, + &tx_ring->dma, GFP_KERNEL); + if (!tx_ring->desc) { + set_dev_node(dev, orig_node); + tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size, + &tx_ring->dma, GFP_KERNEL); + } + + if (!tx_ring->desc) + goto err; + + tx_ring->next_to_use = 0; + tx_ring->next_to_clean = 0; + + return 0; + +err: + kvfree(tx_ring->tx_buffer_info); + tx_ring->tx_buffer_info = NULL; + dev_err(dev, "Unable to allocate memory for the Tx descriptor ring\n"); + return -ENOMEM; +} + +/** + * wx_setup_all_tx_resources - allocate all queues Tx resources + * @wx: pointer to private structure + * + * If this function returns with an error, then it's possible one or + * more of the rings is populated (while the rest are not). It is the + * callers duty to clean those orphaned rings. + * + * Return 0 on success, negative on failure + **/ +static int wx_setup_all_tx_resources(struct wx *wx) +{ + int i, err = 0; + + for (i = 0; i < wx->num_tx_queues; i++) { + err = wx_setup_tx_resources(wx->tx_ring[i]); + if (!err) + continue; + + wx_err(wx, "Allocation for Tx Queue %u failed\n", i); + goto err_setup_tx; + } + + return 0; +err_setup_tx: + /* rewind the index freeing the rings as we go */ + while (i--) + wx_free_tx_resources(wx->tx_ring[i]); + return err; +} + +int wx_setup_resources(struct wx *wx) +{ + int err; + + /* allocate transmit descriptors */ + err = wx_setup_all_tx_resources(wx); + if (err) + return err; + + /* allocate receive descriptors */ + err = wx_setup_all_rx_resources(wx); + if (err) + goto err_free_tx; + + err = wx_setup_isb_resources(wx); + if (err) + goto err_free_rx; + + return 0; + +err_free_rx: + wx_free_all_rx_resources(wx); +err_free_tx: + wx_free_all_tx_resources(wx); + + return err; +} +EXPORT_SYMBOL(wx_setup_resources); + +/** + * wx_get_stats64 - Get System Network Statistics + * @netdev: network interface device structure + * @stats: storage space for 64bit statistics + */ +void wx_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) +{ + struct wx *wx = netdev_priv(netdev); + int i; + + rcu_read_lock(); + for (i = 0; i < wx->num_rx_queues; i++) { + struct wx_ring *ring = READ_ONCE(wx->rx_ring[i]); + u64 bytes, packets; + unsigned int start; + + if (ring) { + do { + start = u64_stats_fetch_begin(&ring->syncp); + packets = ring->stats.packets; + bytes = ring->stats.bytes; + } while (u64_stats_fetch_retry(&ring->syncp, start)); + stats->rx_packets += packets; + stats->rx_bytes += bytes; + } + } + + for (i = 0; i < wx->num_tx_queues; i++) { + struct wx_ring *ring = READ_ONCE(wx->tx_ring[i]); + u64 bytes, packets; + unsigned int start; + + if (ring) { + do { + start = u64_stats_fetch_begin(&ring->syncp); + packets = ring->stats.packets; + bytes = ring->stats.bytes; + } while (u64_stats_fetch_retry(&ring->syncp, + start)); + stats->tx_packets += packets; + stats->tx_bytes += bytes; + } + } + + rcu_read_unlock(); +} +EXPORT_SYMBOL(wx_get_stats64); + +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.h b/drivers/net/ethernet/wangxun/libwx/wx_lib.h new file mode 100644 index 000000000000..50ee41f1fa10 --- /dev/null +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * WangXun Gigabit PCI Express Linux driver + * Copyright (c) 2019 - 2022 Beijing WangXun Technology Co., Ltd. + */ + +#ifndef _WX_LIB_H_ +#define _WX_LIB_H_ + +void wx_alloc_rx_buffers(struct wx_ring *rx_ring, u16 cleaned_count); +u16 wx_desc_unused(struct wx_ring *ring); +netdev_tx_t wx_xmit_frame(struct sk_buff *skb, + struct net_device *netdev); +void wx_napi_enable_all(struct wx *wx); +void wx_napi_disable_all(struct wx *wx); +void wx_reset_interrupt_capability(struct wx *wx); +void wx_clear_interrupt_scheme(struct wx *wx); +int wx_init_interrupt_scheme(struct wx *wx); +irqreturn_t wx_msix_clean_rings(int __always_unused irq, void *data); +void wx_free_irq(struct wx *wx); +int wx_setup_isb_resources(struct wx *wx); +void wx_free_isb_resources(struct wx *wx); +u32 wx_misc_isb(struct wx *wx, enum wx_isb_idx idx); +void wx_configure_vectors(struct wx *wx); +void wx_clean_all_rx_rings(struct wx *wx); +void wx_clean_all_tx_rings(struct wx *wx); +void wx_free_resources(struct wx *wx); +int wx_setup_resources(struct wx *wx); +void wx_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats); + +#endif /* _NGBE_LIB_H_ */ diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h index c86a37914d43..eede93d4120d 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_type.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h @@ -5,6 +5,7 @@ #define _WX_TYPE_H_ #include <linux/bitfield.h> +#include <linux/netdevice.h> /* Vendor ID */ #ifndef PCI_VENDOR_ID_WANGXUN @@ -65,21 +66,50 @@ /* port cfg Registers */ #define WX_CFG_PORT_CTL 0x14400 #define WX_CFG_PORT_CTL_DRV_LOAD BIT(3) +#define WX_CFG_PORT_CTL_QINQ BIT(2) +#define WX_CFG_PORT_CTL_D_VLAN BIT(0) /* double vlan*/ +#define WX_CFG_TAG_TPID(_i) (0x14430 + ((_i) * 4)) + +/* GPIO Registers */ +#define WX_GPIO_DR 0x14800 +#define WX_GPIO_DR_0 BIT(0) /* SDP0 Data Value */ +#define WX_GPIO_DR_1 BIT(1) /* SDP1 Data Value */ +#define WX_GPIO_DDR 0x14804 +#define WX_GPIO_DDR_0 BIT(0) /* SDP0 IO direction */ +#define WX_GPIO_DDR_1 BIT(1) /* SDP1 IO direction */ +#define WX_GPIO_CTL 0x14808 +#define WX_GPIO_INTEN 0x14830 +#define WX_GPIO_INTEN_0 BIT(0) +#define WX_GPIO_INTEN_1 BIT(1) +#define WX_GPIO_INTMASK 0x14834 +#define WX_GPIO_INTTYPE_LEVEL 0x14838 +#define WX_GPIO_POLARITY 0x1483C +#define WX_GPIO_EOI 0x1484C /*********************** Transmit DMA registers **************************/ /* transmit global control */ #define WX_TDM_CTL 0x18000 /* TDM CTL BIT */ #define WX_TDM_CTL_TE BIT(0) /* Transmit Enable */ +#define WX_TDM_PB_THRE(_i) (0x18020 + ((_i) * 4)) /***************************** RDB registers *********************************/ /* receive packet buffer */ #define WX_RDB_PB_CTL 0x19000 #define WX_RDB_PB_CTL_RXEN BIT(31) /* Enable Receiver */ #define WX_RDB_PB_CTL_DISABLED BIT(0) +#define WX_RDB_PB_SZ(_i) (0x19020 + ((_i) * 4)) +#define WX_RDB_PB_SZ_SHIFT 10 /* statistic */ #define WX_RDB_PFCMACDAL 0x19210 #define WX_RDB_PFCMACDAH 0x19214 +/* ring assignment */ +#define WX_RDB_PL_CFG(_i) (0x19300 + ((_i) * 4)) +#define WX_RDB_PL_CFG_L4HDR BIT(1) +#define WX_RDB_PL_CFG_L3HDR BIT(2) +#define WX_RDB_PL_CFG_L2HDR BIT(3) +#define WX_RDB_PL_CFG_TUN_TUNHDR BIT(4) +#define WX_RDB_PL_CFG_TUN_OUTL2HDR BIT(5) /******************************* PSR Registers *******************************/ /* psr control */ @@ -97,10 +127,24 @@ #define WX_PSR_CTL_MO_SHIFT 5 #define WX_PSR_CTL_MO (0x3 << WX_PSR_CTL_MO_SHIFT) #define WX_PSR_CTL_TPE BIT(4) +#define WX_PSR_MAX_SZ 0x15020 +#define WX_PSR_VLAN_CTL 0x15088 +#define WX_PSR_VLAN_CTL_CFIEN BIT(29) /* bit 29 */ +#define WX_PSR_VLAN_CTL_VFE BIT(30) /* bit 30 */ /* mcasst/ucast overflow tbl */ #define WX_PSR_MC_TBL(_i) (0x15200 + ((_i) * 4)) #define WX_PSR_UC_TBL(_i) (0x15400 + ((_i) * 4)) +/* VM L2 contorl */ +#define WX_PSR_VM_L2CTL(_i) (0x15600 + ((_i) * 4)) +#define WX_PSR_VM_L2CTL_UPE BIT(4) /* unicast promiscuous */ +#define WX_PSR_VM_L2CTL_VACC BIT(6) /* accept nomatched vlan */ +#define WX_PSR_VM_L2CTL_AUPE BIT(8) /* accept untagged packets */ +#define WX_PSR_VM_L2CTL_ROMPE BIT(9) /* accept packets in MTA tbl */ +#define WX_PSR_VM_L2CTL_ROPE BIT(10) /* accept packets in UC tbl */ +#define WX_PSR_VM_L2CTL_BAM BIT(11) /* accept broadcast packets */ +#define WX_PSR_VM_L2CTL_MPE BIT(12) /* multicast promiscuous */ + /* Management */ #define WX_PSR_MNG_FLEX_SEL 0x1582C #define WX_PSR_MNG_FLEX_DW_L(_i) (0x15A00 + ((_i) * 16)) @@ -122,6 +166,27 @@ #define WX_PSR_MAC_SWC_IDX 0x16210 #define WX_CLEAR_VMDQ_ALL 0xFFFFFFFFU +/********************************* RSEC **************************************/ +/* general rsec */ +#define WX_RSC_CTL 0x17000 +#define WX_RSC_CTL_SAVE_MAC_ERR BIT(6) +#define WX_RSC_CTL_CRC_STRIP BIT(2) +#define WX_RSC_CTL_RX_DIS BIT(1) +#define WX_RSC_ST 0x17004 +#define WX_RSC_ST_RSEC_RDY BIT(0) + +/****************************** TDB ******************************************/ +#define WX_TDB_PB_SZ(_i) (0x1CC00 + ((_i) * 4)) +#define WX_TXPKT_SIZE_MAX 0xA /* Max Tx Packet size */ + +/****************************** TSEC *****************************************/ +/* Security Control Registers */ +#define WX_TSC_CTL 0x1D000 +#define WX_TSC_CTL_TX_DIS BIT(1) +#define WX_TSC_CTL_TSEC_DIS BIT(0) +#define WX_TSC_BUF_AE 0x1D00C +#define WX_TSC_BUF_AE_THR GENMASK(9, 0) + /************************************** MNG ********************************/ #define WX_MNG_SWFW_SYNC 0x1E008 #define WX_MNG_SWFW_SYNC_SW_MB BIT(2) @@ -135,6 +200,7 @@ #define WX_MAC_TX_CFG 0x11000 #define WX_MAC_TX_CFG_TE BIT(0) #define WX_MAC_TX_CFG_SPEED_MASK GENMASK(30, 29) +#define WX_MAC_TX_CFG_SPEED_10G FIELD_PREP(WX_MAC_TX_CFG_SPEED_MASK, 0) #define WX_MAC_TX_CFG_SPEED_1G FIELD_PREP(WX_MAC_TX_CFG_SPEED_MASK, 3) #define WX_MAC_RX_CFG 0x11004 #define WX_MAC_RX_CFG_RE BIT(0) @@ -151,10 +217,34 @@ /* Interrupt Registers */ #define WX_BME_CTL 0x12020 #define WX_PX_MISC_IC 0x100 +#define WX_PX_MISC_ICS 0x104 +#define WX_PX_MISC_IEN 0x108 +#define WX_PX_INTA 0x110 +#define WX_PX_GPIE 0x118 +#define WX_PX_GPIE_MODEL BIT(0) +#define WX_PX_IC 0x120 #define WX_PX_IMS(_i) (0x140 + (_i) * 4) +#define WX_PX_IMC(_i) (0x150 + (_i) * 4) +#define WX_PX_ISB_ADDR_L 0x160 +#define WX_PX_ISB_ADDR_H 0x164 #define WX_PX_TRANSACTION_PENDING 0x168 +#define WX_PX_ITRSEL 0x180 +#define WX_PX_ITR(_i) (0x200 + (_i) * 4) +#define WX_PX_ITR_CNT_WDIS BIT(31) +#define WX_PX_MISC_IVAR 0x4FC +#define WX_PX_IVAR(_i) (0x500 + (_i) * 4) + +#define WX_PX_IVAR_ALLOC_VAL 0x80 /* Interrupt Allocation valid */ +#define WX_7K_ITR 595 +#define WX_12K_ITR 336 +#define WX_SP_MAX_EITR 0x00000FF8U +#define WX_EM_MAX_EITR 0x00007FFCU /* transmit DMA Registers */ +#define WX_PX_TR_BAL(_i) (0x03000 + ((_i) * 0x40)) +#define WX_PX_TR_BAH(_i) (0x03004 + ((_i) * 0x40)) +#define WX_PX_TR_WP(_i) (0x03008 + ((_i) * 0x40)) +#define WX_PX_TR_RP(_i) (0x0300C + ((_i) * 0x40)) #define WX_PX_TR_CFG(_i) (0x03010 + ((_i) * 0x40)) /* Transmit Config masks */ #define WX_PX_TR_CFG_ENABLE BIT(0) /* Ena specific Tx Queue */ @@ -164,8 +254,22 @@ #define WX_PX_TR_CFG_THRE_SHIFT 8 /* Receive DMA Registers */ +#define WX_PX_RR_BAL(_i) (0x01000 + ((_i) * 0x40)) +#define WX_PX_RR_BAH(_i) (0x01004 + ((_i) * 0x40)) +#define WX_PX_RR_WP(_i) (0x01008 + ((_i) * 0x40)) +#define WX_PX_RR_RP(_i) (0x0100C + ((_i) * 0x40)) #define WX_PX_RR_CFG(_i) (0x01010 + ((_i) * 0x40)) /* PX_RR_CFG bit definitions */ +#define WX_PX_RR_CFG_SPLIT_MODE BIT(26) +#define WX_PX_RR_CFG_RR_THER_SHIFT 16 +#define WX_PX_RR_CFG_RR_HDR_SZ GENMASK(15, 12) +#define WX_PX_RR_CFG_RR_BUF_SZ GENMASK(11, 8) +#define WX_PX_RR_CFG_BHDRSIZE_SHIFT 6 /* 64byte resolution (>> 6) + * + at bit 8 offset (<< 12) + * = (<< 6) + */ +#define WX_PX_RR_CFG_BSIZEPKT_SHIFT 2 /* so many KBs */ +#define WX_PX_RR_CFG_RR_SIZE_SHIFT 1 #define WX_PX_RR_CFG_RR_EN BIT(0) /* Number of 80 microseconds we wait for PCI Express master disable */ @@ -193,8 +297,46 @@ #define WX_MAC_STATE_MODIFIED 0x2 #define WX_MAC_STATE_IN_USE 0x4 +#define WX_MAX_RXD 8192 +#define WX_MAX_TXD 8192 + +/* Supported Rx Buffer Sizes */ +#define WX_RXBUFFER_256 256 /* Used for skb receive header */ +#define WX_RXBUFFER_2K 2048 +#define WX_MAX_RXBUFFER 16384 /* largest size for single descriptor */ + +#if MAX_SKB_FRAGS < 8 +#define WX_RX_BUFSZ ALIGN(WX_MAX_RXBUFFER / MAX_SKB_FRAGS, 1024) +#else +#define WX_RX_BUFSZ WX_RXBUFFER_2K +#endif + +#define WX_RX_BUFFER_WRITE 16 /* Must be power of 2 */ + +#define WX_MAX_DATA_PER_TXD BIT(14) +/* Tx Descriptors needed, worst case */ +#define TXD_USE_COUNT(S) DIV_ROUND_UP((S), WX_MAX_DATA_PER_TXD) +#define DESC_NEEDED (MAX_SKB_FRAGS + 4) + +/* Ether Types */ +#define WX_ETH_P_CNM 0x22E7 + #define WX_CFG_PORT_ST 0x14404 +/******************* Receive Descriptor bit definitions **********************/ +#define WX_RXD_STAT_DD BIT(0) /* Done */ +#define WX_RXD_STAT_EOP BIT(1) /* End of Packet */ + +#define WX_RXD_ERR_RXE BIT(29) /* Any MAC Error */ + +/*********************** Transmit Descriptor Config Masks ****************/ +#define WX_TXD_STAT_DD BIT(0) /* Descriptor Done */ +#define WX_TXD_DTYP_DATA 0 /* Adv Data Descriptor */ +#define WX_TXD_PAYLEN_SHIFT 13 /* Desc PAYLEN shift */ +#define WX_TXD_EOP BIT(24) /* End of Packet */ +#define WX_TXD_IFCS BIT(25) /* Insert FCS */ +#define WX_TXD_RS BIT(27) /* Report Status */ + /* Host Interface Command Structures */ struct wx_hic_hdr { u8 cmd; @@ -270,9 +412,12 @@ struct wx_mac_info { bool set_lben; u8 addr[ETH_ALEN]; u8 perm_addr[ETH_ALEN]; + u32 mta_shadow[128]; s32 mc_filter_type; u32 mcft_size; u32 num_rar_entries; + u32 rx_pb_size; + u32 tx_pb_size; u32 max_tx_queues; u32 max_rx_queues; @@ -312,6 +457,161 @@ enum wx_reset_type { WX_GLOBAL_RESET }; +struct wx_cb { + dma_addr_t dma; + u16 append_cnt; /* number of skb's appended */ + bool page_released; + bool dma_released; +}; + +#define WX_CB(skb) ((struct wx_cb *)(skb)->cb) + +/* Transmit Descriptor */ +union wx_tx_desc { + struct { + __le64 buffer_addr; /* Address of descriptor's data buf */ + __le32 cmd_type_len; + __le32 olinfo_status; + } read; + struct { + __le64 rsvd; /* Reserved */ + __le32 nxtseq_seed; + __le32 status; + } wb; +}; + +/* Receive Descriptor */ +union wx_rx_desc { + struct { + __le64 pkt_addr; /* Packet buffer address */ + __le64 hdr_addr; /* Header buffer address */ + } read; + struct { + struct { + union { + __le32 data; + struct { + __le16 pkt_info; /* RSS, Pkt type */ + __le16 hdr_info; /* Splithdr, hdrlen */ + } hs_rss; + } lo_dword; + union { + __le32 rss; /* RSS Hash */ + struct { + __le16 ip_id; /* IP id */ + __le16 csum; /* Packet Checksum */ + } csum_ip; + } hi_dword; + } lower; + struct { + __le32 status_error; /* ext status/error */ + __le16 length; /* Packet length */ + __le16 vlan; /* VLAN tag */ + } upper; + } wb; /* writeback */ +}; + +#define WX_RX_DESC(R, i) \ + (&(((union wx_rx_desc *)((R)->desc))[i])) +#define WX_TX_DESC(R, i) \ + (&(((union wx_tx_desc *)((R)->desc))[i])) + +/* wrapper around a pointer to a socket buffer, + * so a DMA handle can be stored along with the buffer + */ +struct wx_tx_buffer { + union wx_tx_desc *next_to_watch; + struct sk_buff *skb; + unsigned int bytecount; + unsigned short gso_segs; + DEFINE_DMA_UNMAP_ADDR(dma); + DEFINE_DMA_UNMAP_LEN(len); +}; + +struct wx_rx_buffer { + struct sk_buff *skb; + dma_addr_t dma; + dma_addr_t page_dma; + struct page *page; + unsigned int page_offset; + u16 pagecnt_bias; +}; + +struct wx_queue_stats { + u64 packets; + u64 bytes; +}; + +/* iterator for handling rings in ring container */ +#define wx_for_each_ring(posm, headm) \ + for (posm = (headm).ring; posm; posm = posm->next) + +struct wx_ring_container { + struct wx_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 */ + u8 count; /* total number of rings in vector */ + u8 itr; /* current ITR setting for ring */ +}; + +struct wx_ring { + struct wx_ring *next; /* pointer to next ring in q_vector */ + struct wx_q_vector *q_vector; /* backpointer to host q_vector */ + struct net_device *netdev; /* netdev ring belongs to */ + struct device *dev; /* device for DMA mapping */ + struct page_pool *page_pool; + void *desc; /* descriptor ring memory */ + union { + struct wx_tx_buffer *tx_buffer_info; + struct wx_rx_buffer *rx_buffer_info; + }; + u8 __iomem *tail; + dma_addr_t dma; /* phys. address of descriptor ring */ + unsigned int size; /* length in bytes */ + + u16 count; /* amount of descriptors */ + + u8 queue_index; /* needed for multiqueue queue management */ + u8 reg_idx; /* holds the special value that gets + * the hardware register offset + * associated with this ring, which is + * different for DCB and RSS modes + */ + u16 next_to_use; + u16 next_to_clean; + u16 next_to_alloc; + + struct wx_queue_stats stats; + struct u64_stats_sync syncp; +} ____cacheline_internodealigned_in_smp; + +struct wx_q_vector { + struct wx *wx; + int cpu; /* CPU for DCA */ + int numa_node; + u16 v_idx; /* index of q_vector within array, also used for + * finding the bit in EICR and friends that + * represents the vector for this ring + */ + u16 itr; /* Interrupt throttle rate written to EITR */ + struct wx_ring_container rx, tx; + struct napi_struct napi; + struct rcu_head rcu; /* to avoid race with update stats on free */ + + char name[IFNAMSIZ + 17]; + + /* for dynamic allocation of rings associated with this q_vector */ + struct wx_ring ring[0] ____cacheline_internodealigned_in_smp; +}; + +enum wx_isb_idx { + WX_ISB_HEADER, + WX_ISB_MISC, + WX_ISB_VEC0, + WX_ISB_VEC1, + WX_ISB_MAX +}; + struct wx { u8 __iomem *hw_addr; struct pci_dev *pdev; @@ -331,6 +631,7 @@ struct wx { u16 oem_svid; u16 msg_enable; bool adapter_stopped; + u16 tpid[8]; char eeprom_id[32]; enum wx_reset_type reset_type; @@ -360,6 +661,18 @@ struct wx { u32 tx_ring_count; u32 rx_ring_count; + struct wx_ring *tx_ring[64] ____cacheline_aligned_in_smp; + struct wx_ring *rx_ring[64]; + struct wx_q_vector *q_vector[64]; + + unsigned int queues_per_pool; + struct msix_entry *msix_entries; + + /* misc interrupt status block */ + dma_addr_t isb_dma; + u32 *isb_mem; + u32 isb_tag[WX_ISB_MAX]; + #define WX_MAX_RETA_ENTRIES 128 u8 rss_indir_tbl[WX_MAX_RETA_ENTRIES]; @@ -371,6 +684,7 @@ struct wx { }; #define WX_INTR_ALL (~0ULL) +#define WX_INTR_Q(i) BIT(i) /* register operations */ #define wr32(a, reg, value) writel((value), ((a)->hw_addr + (reg))) diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c index ed52f80b5475..f94d415daf3c 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c @@ -13,6 +13,7 @@ #include "../libwx/wx_type.h" #include "../libwx/wx_hw.h" +#include "../libwx/wx_lib.h" #include "ngbe_type.h" #include "ngbe_mdio.h" #include "ngbe_hw.h" @@ -112,6 +113,9 @@ static int ngbe_sw_init(struct wx *wx) wx->mac.num_rar_entries = NGBE_RAR_ENTRIES; wx->mac.max_rx_queues = NGBE_MAX_RX_QUEUES; wx->mac.max_tx_queues = NGBE_MAX_TX_QUEUES; + wx->mac.mcft_size = NGBE_MC_TBL_SIZE; + wx->mac.rx_pb_size = NGBE_RX_PB_SIZE; + wx->mac.tx_pb_size = NGBE_TDB_PB_SZ; /* PCI config space info */ err = wx_sw_init(wx); @@ -148,27 +152,211 @@ static int ngbe_sw_init(struct wx *wx) return 0; } +/** + * ngbe_irq_enable - Enable default interrupt generation settings + * @wx: board private structure + * @queues: enable all queues interrupts + **/ +static void ngbe_irq_enable(struct wx *wx, bool queues) +{ + u32 mask; + + /* enable misc interrupt */ + mask = NGBE_PX_MISC_IEN_MASK; + + wr32(wx, WX_GPIO_DDR, WX_GPIO_DDR_0); + wr32(wx, WX_GPIO_INTEN, WX_GPIO_INTEN_0 | WX_GPIO_INTEN_1); + wr32(wx, WX_GPIO_INTTYPE_LEVEL, 0x0); + wr32(wx, WX_GPIO_POLARITY, wx->gpio_ctrl ? 0 : 0x3); + + wr32(wx, WX_PX_MISC_IEN, mask); + + /* mask interrupt */ + if (queues) + wx_intr_enable(wx, NGBE_INTR_ALL); + else + wx_intr_enable(wx, NGBE_INTR_MISC(wx)); +} + +/** + * ngbe_intr - msi/legacy mode Interrupt Handler + * @irq: interrupt number + * @data: pointer to a network interface device structure + **/ +static irqreturn_t ngbe_intr(int __always_unused irq, void *data) +{ + struct wx_q_vector *q_vector; + struct wx *wx = data; + struct pci_dev *pdev; + u32 eicr; + + q_vector = wx->q_vector[0]; + pdev = wx->pdev; + + eicr = wx_misc_isb(wx, WX_ISB_VEC0); + if (!eicr) { + /* shared interrupt alert! + * the interrupt that we masked before the EICR read. + */ + if (netif_running(wx->netdev)) + ngbe_irq_enable(wx, true); + return IRQ_NONE; /* Not our interrupt */ + } + wx->isb_mem[WX_ISB_VEC0] = 0; + if (!(pdev->msi_enabled)) + wr32(wx, WX_PX_INTA, 1); + + wx->isb_mem[WX_ISB_MISC] = 0; + /* would disable interrupts here but it is auto disabled */ + napi_schedule_irqoff(&q_vector->napi); + + if (netif_running(wx->netdev)) + ngbe_irq_enable(wx, false); + + return IRQ_HANDLED; +} + +static irqreturn_t ngbe_msix_other(int __always_unused irq, void *data) +{ + struct wx *wx = data; + + /* re-enable the original interrupt state, no lsc, no queues */ + if (netif_running(wx->netdev)) + ngbe_irq_enable(wx, false); + + return IRQ_HANDLED; +} + +/** + * ngbe_request_msix_irqs - Initialize MSI-X interrupts + * @wx: board private structure + * + * ngbe_request_msix_irqs allocates MSI-X vectors and requests + * interrupts from the kernel. + **/ +static int ngbe_request_msix_irqs(struct wx *wx) +{ + struct net_device *netdev = wx->netdev; + int vector, err; + + for (vector = 0; vector < wx->num_q_vectors; vector++) { + struct wx_q_vector *q_vector = wx->q_vector[vector]; + struct msix_entry *entry = &wx->msix_entries[vector]; + + if (q_vector->tx.ring && q_vector->rx.ring) + snprintf(q_vector->name, sizeof(q_vector->name) - 1, + "%s-TxRx-%d", netdev->name, entry->entry); + else + /* skip this unused q_vector */ + continue; + + err = request_irq(entry->vector, wx_msix_clean_rings, 0, + q_vector->name, q_vector); + if (err) { + wx_err(wx, "request_irq failed for MSIX interrupt %s Error: %d\n", + q_vector->name, err); + goto free_queue_irqs; + } + } + + err = request_irq(wx->msix_entries[vector].vector, + ngbe_msix_other, 0, netdev->name, wx); + + if (err) { + wx_err(wx, "request_irq for msix_other failed: %d\n", err); + goto free_queue_irqs; + } + + return 0; + +free_queue_irqs: + while (vector) { + vector--; + free_irq(wx->msix_entries[vector].vector, + wx->q_vector[vector]); + } + wx_reset_interrupt_capability(wx); + return err; +} + +/** + * ngbe_request_irq - initialize interrupts + * @wx: board private structure + * + * Attempts to configure interrupts using the best available + * capabilities of the hardware and kernel. + **/ +static int ngbe_request_irq(struct wx *wx) +{ + struct net_device *netdev = wx->netdev; + struct pci_dev *pdev = wx->pdev; + int err; + + if (pdev->msix_enabled) + err = ngbe_request_msix_irqs(wx); + else if (pdev->msi_enabled) + err = request_irq(pdev->irq, ngbe_intr, 0, + netdev->name, wx); + else + err = request_irq(pdev->irq, ngbe_intr, IRQF_SHARED, + netdev->name, wx); + + if (err) + wx_err(wx, "request_irq failed, Error %d\n", err); + + return err; +} + static void ngbe_disable_device(struct wx *wx) { struct net_device *netdev = wx->netdev; + u32 i; + /* disable all enabled rx queues */ + for (i = 0; i < wx->num_rx_queues; i++) + /* this call also flushes the previous write */ + wx_disable_rx_queue(wx, wx->rx_ring[i]); /* disable receives */ wx_disable_rx(wx); + wx_napi_disable_all(wx); + netif_tx_stop_all_queues(netdev); netif_tx_disable(netdev); if (wx->gpio_ctrl) ngbe_sfp_modules_txrx_powerctl(wx, false); + wx_irq_disable(wx); + /* disable transmits in the hardware now that interrupts are off */ + for (i = 0; i < wx->num_tx_queues; i++) { + u8 reg_idx = wx->tx_ring[i]->reg_idx; + + wr32(wx, WX_PX_TR_CFG(reg_idx), WX_PX_TR_CFG_SWFLSH); + } } static void ngbe_down(struct wx *wx) { phy_stop(wx->phydev); ngbe_disable_device(wx); + wx_clean_all_tx_rings(wx); + wx_clean_all_rx_rings(wx); } static void ngbe_up(struct wx *wx) { + wx_configure_vectors(wx); + + /* make sure to complete pre-operations */ + smp_mb__before_atomic(); + wx_napi_enable_all(wx); + /* enable transmits */ + netif_tx_start_all_queues(wx->netdev); + + /* clear any pending interrupts, may auto mask */ + rd32(wx, WX_PX_IC); + rd32(wx, WX_PX_MISC_IC); + ngbe_irq_enable(wx, true); if (wx->gpio_ctrl) ngbe_sfp_modules_txrx_powerctl(wx, true); + phy_start(wx->phydev); } @@ -187,12 +375,39 @@ static int ngbe_open(struct net_device *netdev) int err; wx_control_hw(wx, true); - err = ngbe_phy_connect(wx); + + err = wx_setup_resources(wx); if (err) return err; + + wx_configure(wx); + + err = ngbe_request_irq(wx); + if (err) + goto err_free_resources; + + err = ngbe_phy_connect(wx); + if (err) + goto err_free_irq; + + err = netif_set_real_num_tx_queues(netdev, wx->num_tx_queues); + if (err) + goto err_dis_phy; + + err = netif_set_real_num_rx_queues(netdev, wx->num_rx_queues); + if (err) + goto err_dis_phy; + ngbe_up(wx); return 0; +err_dis_phy: + phy_disconnect(wx->phydev); +err_free_irq: + wx_free_irq(wx); +err_free_resources: + wx_free_resources(wx); + return err; } /** @@ -211,18 +426,14 @@ static int ngbe_close(struct net_device *netdev) struct wx *wx = netdev_priv(netdev); ngbe_down(wx); + wx_free_irq(wx); + wx_free_resources(wx); phy_disconnect(wx->phydev); wx_control_hw(wx, false); return 0; } -static netdev_tx_t ngbe_xmit_frame(struct sk_buff *skb, - struct net_device *netdev) -{ - return NETDEV_TX_OK; -} - static void ngbe_dev_shutdown(struct pci_dev *pdev, bool *enable_wake) { struct wx *wx = pci_get_drvdata(pdev); @@ -258,9 +469,11 @@ static void ngbe_shutdown(struct pci_dev *pdev) static const struct net_device_ops ngbe_netdev_ops = { .ndo_open = ngbe_open, .ndo_stop = ngbe_close, - .ndo_start_xmit = ngbe_xmit_frame, + .ndo_start_xmit = wx_xmit_frame, + .ndo_set_rx_mode = wx_set_rx_mode, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = wx_set_mac, + .ndo_get_stats64 = wx_get_stats64, }; /** @@ -336,6 +549,17 @@ static int ngbe_probe(struct pci_dev *pdev, netdev->netdev_ops = &ngbe_netdev_ops; netdev->features |= NETIF_F_HIGHDMA; + netdev->features = NETIF_F_SG; + + /* copy netdev features into list of user selectable features */ + netdev->hw_features |= netdev->features | + NETIF_F_RXALL; + + netdev->priv_flags |= IFF_UNICAST_FLT; + netdev->priv_flags |= IFF_SUPP_NOFCS; + + netdev->min_mtu = ETH_MIN_MTU; + netdev->max_mtu = NGBE_MAX_JUMBO_FRAME_SIZE - (ETH_HLEN + ETH_FCS_LEN); wx->bd_number = func_nums; /* setup the private structure */ @@ -411,10 +635,14 @@ static int ngbe_probe(struct pci_dev *pdev, eth_hw_addr_set(netdev, wx->mac.perm_addr); wx_mac_set_default_filter(wx, wx->mac.perm_addr); + err = wx_init_interrupt_scheme(wx); + if (err) + goto err_free_mac_table; + /* phy Interface Configuration */ err = ngbe_mdio_init(wx); if (err) - goto err_free_mac_table; + goto err_clear_interrupt_scheme; err = register_netdev(netdev); if (err) @@ -431,6 +659,8 @@ static int ngbe_probe(struct pci_dev *pdev, err_register: wx_control_hw(wx, false); +err_clear_interrupt_scheme: + wx_clear_interrupt_scheme(wx); err_free_mac_table: kfree(wx->mac_table); err_pci_release_regions: @@ -462,6 +692,7 @@ static void ngbe_remove(struct pci_dev *pdev) pci_select_bars(pdev, IORESOURCE_MEM)); kfree(wx->mac_table); + wx_clear_interrupt_scheme(wx); pci_disable_pcie_error_reporting(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h index fd71260f73de..a2351349785e 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h @@ -90,6 +90,20 @@ enum NGBE_MSCA_CMD_value { #define NGBE_GPIO_DDR_0 BIT(0) /* SDP0 IO direction */ #define NGBE_GPIO_DDR_1 BIT(1) /* SDP1 IO direction */ +/* Extended Interrupt Enable Set */ +#define NGBE_PX_MISC_IEN_DEV_RST BIT(10) +#define NGBE_PX_MISC_IEN_ETH_LK BIT(18) +#define NGBE_PX_MISC_IEN_INT_ERR BIT(20) +#define NGBE_PX_MISC_IEN_GPIO BIT(26) +#define NGBE_PX_MISC_IEN_MASK ( \ + NGBE_PX_MISC_IEN_DEV_RST | \ + NGBE_PX_MISC_IEN_ETH_LK | \ + NGBE_PX_MISC_IEN_INT_ERR | \ + NGBE_PX_MISC_IEN_GPIO) + +#define NGBE_INTR_ALL 0x1FF +#define NGBE_INTR_MISC(A) BIT((A)->num_q_vectors) + #define NGBE_PHY_CONFIG(reg_offset) (0x14000 + ((reg_offset) * 4)) #define NGBE_CFG_LAN_SPEED 0x14440 #define NGBE_CFG_PORT_ST 0x14404 @@ -120,6 +134,10 @@ enum NGBE_MSCA_CMD_value { #define NGBE_ETH_LENGTH_OF_ADDRESS 6 #define NGBE_MAX_MSIX_VECTORS 0x09 #define NGBE_RAR_ENTRIES 32 +#define NGBE_RX_PB_SIZE 42 +#define NGBE_MC_TBL_SIZE 128 +#define NGBE_TDB_PB_SZ (20 * 1024) /* 160KB Packet Buffer */ +#define NGBE_MAX_JUMBO_FRAME_SIZE 9432 /* max payload 9414 */ /* TX/RX descriptor defines */ #define NGBE_DEFAULT_TXD 512 /* default ring size */ diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c index aa4d09df3b01..094df377726b 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c @@ -11,6 +11,7 @@ #include <net/ip.h> #include "../libwx/wx_type.h" +#include "../libwx/wx_lib.h" #include "../libwx/wx_hw.h" #include "txgbe_type.h" #include "txgbe_hw.h" @@ -72,9 +73,177 @@ static int txgbe_enumerate_functions(struct wx *wx) return physfns; } +/** + * txgbe_irq_enable - Enable default interrupt generation settings + * @wx: pointer to private structure + * @queues: enable irqs for queues + **/ +static void txgbe_irq_enable(struct wx *wx, bool queues) +{ + /* unmask interrupt */ + wx_intr_enable(wx, TXGBE_INTR_MISC(wx)); + if (queues) + wx_intr_enable(wx, TXGBE_INTR_QALL(wx)); +} + +/** + * txgbe_intr - msi/legacy mode Interrupt Handler + * @irq: interrupt number + * @data: pointer to a network interface device structure + **/ +static irqreturn_t txgbe_intr(int __always_unused irq, void *data) +{ + struct wx_q_vector *q_vector; + struct wx *wx = data; + struct pci_dev *pdev; + u32 eicr; + + q_vector = wx->q_vector[0]; + pdev = wx->pdev; + + eicr = wx_misc_isb(wx, WX_ISB_VEC0); + if (!eicr) { + /* shared interrupt alert! + * the interrupt that we masked before the ICR read. + */ + if (netif_running(wx->netdev)) + txgbe_irq_enable(wx, true); + return IRQ_NONE; /* Not our interrupt */ + } + wx->isb_mem[WX_ISB_VEC0] = 0; + if (!(pdev->msi_enabled)) + wr32(wx, WX_PX_INTA, 1); + + wx->isb_mem[WX_ISB_MISC] = 0; + /* would disable interrupts here but it is auto disabled */ + napi_schedule_irqoff(&q_vector->napi); + + /* re-enable link(maybe) and non-queue interrupts, no flush. + * txgbe_poll will re-enable the queue interrupts + */ + if (netif_running(wx->netdev)) + txgbe_irq_enable(wx, false); + + return IRQ_HANDLED; +} + +static irqreturn_t txgbe_msix_other(int __always_unused irq, void *data) +{ + struct wx *wx = data; + + /* re-enable the original interrupt state */ + if (netif_running(wx->netdev)) + txgbe_irq_enable(wx, false); + + return IRQ_HANDLED; +} + +/** + * txgbe_request_msix_irqs - Initialize MSI-X interrupts + * @wx: board private structure + * + * Allocate MSI-X vectors and request interrupts from the kernel. + **/ +static int txgbe_request_msix_irqs(struct wx *wx) +{ + struct net_device *netdev = wx->netdev; + int vector, err; + + for (vector = 0; vector < wx->num_q_vectors; vector++) { + struct wx_q_vector *q_vector = wx->q_vector[vector]; + struct msix_entry *entry = &wx->msix_entries[vector]; + + if (q_vector->tx.ring && q_vector->rx.ring) + snprintf(q_vector->name, sizeof(q_vector->name) - 1, + "%s-TxRx-%d", netdev->name, entry->entry); + else + /* skip this unused q_vector */ + continue; + + err = request_irq(entry->vector, wx_msix_clean_rings, 0, + q_vector->name, q_vector); + if (err) { + wx_err(wx, "request_irq failed for MSIX interrupt %s Error: %d\n", + q_vector->name, err); + goto free_queue_irqs; + } + } + + err = request_irq(wx->msix_entries[vector].vector, + txgbe_msix_other, 0, netdev->name, wx); + if (err) { + wx_err(wx, "request_irq for msix_other failed: %d\n", err); + goto free_queue_irqs; + } + + return 0; + +free_queue_irqs: + while (vector) { + vector--; + free_irq(wx->msix_entries[vector].vector, + wx->q_vector[vector]); + } + wx_reset_interrupt_capability(wx); + return err; +} + +/** + * txgbe_request_irq - initialize interrupts + * @wx: board private structure + * + * Attempt to configure interrupts using the best available + * capabilities of the hardware and kernel. + **/ +static int txgbe_request_irq(struct wx *wx) +{ + struct net_device *netdev = wx->netdev; + struct pci_dev *pdev = wx->pdev; + int err; + + if (pdev->msix_enabled) + err = txgbe_request_msix_irqs(wx); + else if (pdev->msi_enabled) + err = request_irq(wx->pdev->irq, &txgbe_intr, 0, + netdev->name, wx); + else + err = request_irq(wx->pdev->irq, &txgbe_intr, IRQF_SHARED, + netdev->name, wx); + + if (err) + wx_err(wx, "request_irq failed, Error %d\n", err); + + return err; +} + static void txgbe_up_complete(struct wx *wx) { + u32 reg; + wx_control_hw(wx, true); + wx_configure_vectors(wx); + + /* make sure to complete pre-operations */ + smp_mb__before_atomic(); + wx_napi_enable_all(wx); + + /* clear any pending interrupts, may auto mask */ + rd32(wx, WX_PX_IC); + rd32(wx, WX_PX_MISC_IC); + txgbe_irq_enable(wx, true); + + /* Configure MAC Rx and Tx when link is up */ + reg = rd32(wx, WX_MAC_RX_CFG); + wr32(wx, WX_MAC_RX_CFG, reg); + wr32(wx, WX_MAC_PKT_FLT, WX_MAC_PKT_FLT_PR); + reg = rd32(wx, WX_MAC_WDG_TIMEOUT); + wr32(wx, WX_MAC_WDG_TIMEOUT, reg); + reg = rd32(wx, WX_MAC_TX_CFG); + wr32(wx, WX_MAC_TX_CFG, (reg & ~WX_MAC_TX_CFG_SPEED_MASK) | WX_MAC_TX_CFG_SPEED_10G); + + /* enable transmits */ + netif_tx_start_all_queues(wx->netdev); + netif_carrier_on(wx->netdev); } static void txgbe_reset(struct wx *wx) @@ -96,14 +265,24 @@ static void txgbe_reset(struct wx *wx) static void txgbe_disable_device(struct wx *wx) { struct net_device *netdev = wx->netdev; + u32 i; wx_disable_pcie_master(wx); /* disable receives */ wx_disable_rx(wx); + /* disable all enabled rx queues */ + for (i = 0; i < wx->num_rx_queues; i++) + /* this call also flushes the previous write */ + wx_disable_rx_queue(wx, wx->rx_ring[i]); + + netif_tx_stop_all_queues(netdev); netif_carrier_off(netdev); netif_tx_disable(netdev); + wx_irq_disable(wx); + wx_napi_disable_all(wx); + if (wx->bus.func < 2) wr32m(wx, TXGBE_MIS_PRB_CTL, TXGBE_MIS_PRB_CTL_LAN_UP(wx->bus.func), 0); else @@ -116,6 +295,13 @@ static void txgbe_disable_device(struct wx *wx) wr32m(wx, WX_MAC_TX_CFG, WX_MAC_TX_CFG_TE, 0); } + /* disable transmits in the hardware now that interrupts are off */ + for (i = 0; i < wx->num_tx_queues; i++) { + u8 reg_idx = wx->tx_ring[i]->reg_idx; + + wr32(wx, WX_PX_TR_CFG(reg_idx), WX_PX_TR_CFG_SWFLSH); + } + /* Disable the Tx DMA engine */ wr32m(wx, WX_TDM_CTL, WX_TDM_CTL_TE, 0); } @@ -124,6 +310,9 @@ static void txgbe_down(struct wx *wx) { txgbe_disable_device(wx); txgbe_reset(wx); + + wx_clean_all_tx_rings(wx); + wx_clean_all_rx_rings(wx); } /** @@ -132,12 +321,15 @@ static void txgbe_down(struct wx *wx) **/ static int txgbe_sw_init(struct wx *wx) { + u16 msix_count = 0; int err; wx->mac.num_rar_entries = TXGBE_SP_RAR_ENTRIES; wx->mac.max_tx_queues = TXGBE_SP_MAX_TX_QUEUES; wx->mac.max_rx_queues = TXGBE_SP_MAX_RX_QUEUES; wx->mac.mcft_size = TXGBE_SP_MC_TBL_SIZE; + wx->mac.rx_pb_size = TXGBE_SP_RX_PB_SIZE; + wx->mac.tx_pb_size = TXGBE_SP_TDB_PB_SZ; /* PCI config space info */ err = wx_sw_init(wx); @@ -156,6 +348,25 @@ static int txgbe_sw_init(struct wx *wx) break; } + /* Set common capability flags and settings */ + wx->max_q_vectors = TXGBE_MAX_MSIX_VECTORS; + err = wx_get_pcie_msix_counts(wx, &msix_count, TXGBE_MAX_MSIX_VECTORS); + if (err) + wx_err(wx, "Do not support MSI-X\n"); + wx->mac.max_msix_vectors = msix_count; + + /* enable itr by default in dynamic mode */ + wx->rx_itr_setting = 1; + wx->tx_itr_setting = 1; + + /* set default ring sizes */ + wx->tx_ring_count = TXGBE_DEFAULT_TXD; + wx->rx_ring_count = TXGBE_DEFAULT_RXD; + + /* set default work limits */ + wx->tx_work_limit = TXGBE_DEFAULT_TX_WORK; + wx->rx_work_limit = TXGBE_DEFAULT_RX_WORK; + return 0; } @@ -171,10 +382,39 @@ static int txgbe_sw_init(struct wx *wx) static int txgbe_open(struct net_device *netdev) { struct wx *wx = netdev_priv(netdev); + int err; + + err = wx_setup_resources(wx); + if (err) + goto err_reset; + + wx_configure(wx); + + err = txgbe_request_irq(wx); + if (err) + goto err_free_isb; + + /* Notify the stack of the actual queue counts. */ + err = netif_set_real_num_tx_queues(netdev, wx->num_tx_queues); + if (err) + goto err_free_irq; + + err = netif_set_real_num_rx_queues(netdev, wx->num_rx_queues); + if (err) + goto err_free_irq; txgbe_up_complete(wx); return 0; + +err_free_irq: + wx_free_irq(wx); +err_free_isb: + wx_free_isb_resources(wx); +err_reset: + txgbe_reset(wx); + + return err; } /** @@ -187,6 +427,7 @@ static int txgbe_open(struct net_device *netdev) static void txgbe_close_suspend(struct wx *wx) { txgbe_disable_device(wx); + wx_free_resources(wx); } /** @@ -205,6 +446,8 @@ static int txgbe_close(struct net_device *netdev) struct wx *wx = netdev_priv(netdev); txgbe_down(wx); + wx_free_irq(wx); + wx_free_resources(wx); wx_control_hw(wx, false); return 0; @@ -240,18 +483,14 @@ static void txgbe_shutdown(struct pci_dev *pdev) } } -static netdev_tx_t txgbe_xmit_frame(struct sk_buff *skb, - struct net_device *netdev) -{ - return NETDEV_TX_OK; -} - static const struct net_device_ops txgbe_netdev_ops = { .ndo_open = txgbe_open, .ndo_stop = txgbe_close, - .ndo_start_xmit = txgbe_xmit_frame, + .ndo_start_xmit = wx_xmit_frame, + .ndo_set_rx_mode = wx_set_rx_mode, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = wx_set_mac, + .ndo_get_stats64 = wx_get_stats64, }; /** @@ -354,6 +593,16 @@ static int txgbe_probe(struct pci_dev *pdev, } netdev->features |= NETIF_F_HIGHDMA; + netdev->features = NETIF_F_SG; + + /* copy netdev features into list of user selectable features */ + netdev->hw_features |= netdev->features | NETIF_F_RXALL; + + netdev->priv_flags |= IFF_UNICAST_FLT; + netdev->priv_flags |= IFF_SUPP_NOFCS; + + netdev->min_mtu = ETH_MIN_MTU; + netdev->max_mtu = TXGBE_MAX_JUMBO_FRAME_SIZE - (ETH_HLEN + ETH_FCS_LEN); /* make sure the EEPROM is good */ err = txgbe_validate_eeprom_checksum(wx, NULL); @@ -367,6 +616,10 @@ static int txgbe_probe(struct pci_dev *pdev, eth_hw_addr_set(netdev, wx->mac.perm_addr); wx_mac_set_default_filter(wx, wx->mac.perm_addr); + err = wx_init_interrupt_scheme(wx); + if (err) + goto err_free_mac_table; + /* Save off EEPROM version number and Option Rom version which * together make a unique identify for the eeprom */ @@ -411,6 +664,8 @@ static int txgbe_probe(struct pci_dev *pdev, pci_set_drvdata(pdev, wx); + netif_tx_stop_all_queues(netdev); + /* calculate the expected PCIe bandwidth required for optimal * performance. Note that some older parts will never have enough * bandwidth due to being older generation PCIe parts. We clamp these @@ -435,6 +690,7 @@ static int txgbe_probe(struct pci_dev *pdev, return 0; err_release_hw: + wx_clear_interrupt_scheme(wx); wx_control_hw(wx, false); err_free_mac_table: kfree(wx->mac_table); @@ -468,6 +724,7 @@ static void txgbe_remove(struct pci_dev *pdev) pci_select_bars(pdev, IORESOURCE_MEM)); kfree(wx->mac_table); + wx_clear_interrupt_scheme(wx); pci_disable_pcie_error_reporting(pdev); diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h index cbd705a9f4bd..563ea51deca6 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h @@ -67,6 +67,7 @@ #define TXGBE_PBANUM1_PTR 0x06 #define TXGBE_PBANUM_PTR_GUARD 0xFAFA +#define TXGBE_MAX_MSIX_VECTORS 64 #define TXGBE_MAX_FDIR_INDICES 63 #define TXGBE_MAX_RX_QUEUES (TXGBE_MAX_FDIR_INDICES + 1) @@ -76,6 +77,26 @@ #define TXGBE_SP_MAX_RX_QUEUES 128 #define TXGBE_SP_RAR_ENTRIES 128 #define TXGBE_SP_MC_TBL_SIZE 128 +#define TXGBE_SP_RX_PB_SIZE 512 +#define TXGBE_SP_TDB_PB_SZ (160 * 1024) /* 160KB Packet Buffer */ +#define TXGBE_MAX_JUMBO_FRAME_SIZE 9432 /* max payload 9414 */ + +/* TX/RX descriptor defines */ +#define TXGBE_DEFAULT_TXD 512 +#define TXGBE_DEFAULT_TX_WORK 256 + +#if (PAGE_SIZE < 8192) +#define TXGBE_DEFAULT_RXD 512 +#define TXGBE_DEFAULT_RX_WORK 256 +#else +#define TXGBE_DEFAULT_RXD 256 +#define TXGBE_DEFAULT_RX_WORK 128 +#endif + +#define TXGBE_INTR_MISC(A) BIT((A)->num_q_vectors) +#define TXGBE_INTR_QALL(A) (TXGBE_INTR_MISC(A) - 1) + +#define TXGBE_MAX_EITR GENMASK(11, 3) extern char txgbe_driver_name[]; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 9352dad58996..79f4e13620a4 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -987,9 +987,6 @@ static void netvsc_copy_to_send_buf(struct netvsc_device *net_device, void netvsc_dma_unmap(struct hv_device *hv_dev, struct hv_netvsc_packet *packet) { - u32 page_count = packet->cp_partial ? - packet->page_buf_cnt - packet->rmsg_pgcnt : - packet->page_buf_cnt; int i; if (!hv_is_isolation_supported()) @@ -998,7 +995,7 @@ void netvsc_dma_unmap(struct hv_device *hv_dev, if (!packet->dma_range) return; - for (i = 0; i < page_count; i++) + for (i = 0; i < packet->page_buf_cnt; i++) dma_unmap_single(&hv_dev->device, packet->dma_range[i].dma, packet->dma_range[i].mapping_size, DMA_TO_DEVICE); @@ -1028,9 +1025,7 @@ static int netvsc_dma_map(struct hv_device *hv_dev, struct hv_netvsc_packet *packet, struct hv_page_buffer *pb) { - u32 page_count = packet->cp_partial ? - packet->page_buf_cnt - packet->rmsg_pgcnt : - packet->page_buf_cnt; + u32 page_count = packet->page_buf_cnt; dma_addr_t dma; int i; @@ -1039,7 +1034,7 @@ static int netvsc_dma_map(struct hv_device *hv_dev, packet->dma_range = kcalloc(page_count, sizeof(*packet->dma_range), - GFP_KERNEL); + GFP_ATOMIC); if (!packet->dma_range) return -ENOMEM; diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c index bea2da1c4c51..2cb1710f6ac3 100644 --- a/drivers/net/ipa/gsi.c +++ b/drivers/net/ipa/gsi.c @@ -182,6 +182,41 @@ static bool gsi_channel_initialized(struct gsi_channel *channel) return !!channel->gsi; } +/* Encode the channel protocol for the CH_C_CNTXT_0 register */ +static u32 ch_c_cntxt_0_type_encode(enum ipa_version version, + enum gsi_channel_type type) +{ + u32 val; + + val = u32_encode_bits(type, CHTYPE_PROTOCOL_FMASK); + if (version < IPA_VERSION_4_5) + return val; + + type >>= hweight32(CHTYPE_PROTOCOL_FMASK); + + return val | u32_encode_bits(type, CHTYPE_PROTOCOL_MSB_FMASK); +} + +/* Encode a channel ring buffer length for the CH_C_CNTXT_1 register */ +static u32 ch_c_cntxt_1_length_encode(enum ipa_version version, u32 length) +{ + if (version < IPA_VERSION_4_9) + return u32_encode_bits(length, GENMASK(15, 0)); + + return u32_encode_bits(length, GENMASK(19, 0)); +} + +/* Encode the length of the event channel ring buffer for the + * EV_CH_E_CNTXT_1 register. + */ +static u32 ev_ch_e_cntxt_1_length_encode(enum ipa_version version, u32 length) +{ + if (version < IPA_VERSION_4_9) + return u32_encode_bits(length, GENMASK(15, 0)); + + return u32_encode_bits(length, GENMASK(19, 0)); +} + /* Update the GSI IRQ type register with the cached value */ static void gsi_irq_type_update(struct gsi *gsi, u32 val) { @@ -191,12 +226,12 @@ static void gsi_irq_type_update(struct gsi *gsi, u32 val) static void gsi_irq_type_enable(struct gsi *gsi, enum gsi_irq_type_id type_id) { - gsi_irq_type_update(gsi, gsi->type_enabled_bitmap | BIT(type_id)); + gsi_irq_type_update(gsi, gsi->type_enabled_bitmap | type_id); } static void gsi_irq_type_disable(struct gsi *gsi, enum gsi_irq_type_id type_id) { - gsi_irq_type_update(gsi, gsi->type_enabled_bitmap & ~BIT(type_id)); + gsi_irq_type_update(gsi, gsi->type_enabled_bitmap & ~type_id); } /* Event ring commands are performed one at a time. Their completion @@ -292,19 +327,19 @@ static void gsi_irq_enable(struct gsi *gsi) /* Global interrupts include hardware error reports. Enable * that so we can at least report the error should it occur. */ - iowrite32(BIT(ERROR_INT), gsi->virt + GSI_CNTXT_GLOB_IRQ_EN_OFFSET); - gsi_irq_type_update(gsi, gsi->type_enabled_bitmap | BIT(GSI_GLOB_EE)); + iowrite32(ERROR_INT, gsi->virt + GSI_CNTXT_GLOB_IRQ_EN_OFFSET); + gsi_irq_type_update(gsi, gsi->type_enabled_bitmap | GSI_GLOB_EE); /* General GSI interrupts are reported to all EEs; if they occur * they are unrecoverable (without reset). A breakpoint interrupt * also exists, but we don't support that. We want to be notified * of errors so we can report them, even if they can't be handled. */ - val = BIT(BUS_ERROR); - val |= BIT(CMD_FIFO_OVRFLOW); - val |= BIT(MCS_STACK_OVRFLOW); + val = BUS_ERROR; + val |= CMD_FIFO_OVRFLOW; + val |= MCS_STACK_OVRFLOW; iowrite32(val, gsi->virt + GSI_CNTXT_GSI_IRQ_EN_OFFSET); - gsi_irq_type_update(gsi, gsi->type_enabled_bitmap | BIT(GSI_GENERAL)); + gsi_irq_type_update(gsi, gsi->type_enabled_bitmap | GSI_GENERAL); } /* Disable all GSI interrupt types */ @@ -676,7 +711,7 @@ static void gsi_evt_ring_program(struct gsi *gsi, u32 evt_ring_id) iowrite32(val, gsi->virt + GSI_EV_CH_E_CNTXT_0_OFFSET(evt_ring_id)); size = ring->count * GSI_RING_ELEMENT_SIZE; - val = ev_r_length_encoded(gsi->version, size); + val = ev_ch_e_cntxt_1_length_encode(gsi->version, size); iowrite32(val, gsi->virt + GSI_EV_CH_E_CNTXT_1_OFFSET(evt_ring_id)); /* The context 2 and 3 registers store the low-order and @@ -765,14 +800,14 @@ static void gsi_channel_program(struct gsi_channel *channel, bool doorbell) u32 val; /* We program all channels as GPI type/protocol */ - val = chtype_protocol_encoded(gsi->version, GSI_CHANNEL_TYPE_GPI); + val = ch_c_cntxt_0_type_encode(gsi->version, GSI_CHANNEL_TYPE_GPI); if (channel->toward_ipa) val |= CHTYPE_DIR_FMASK; val |= u32_encode_bits(channel->evt_ring_id, ERINDEX_FMASK); val |= u32_encode_bits(GSI_RING_ELEMENT_SIZE, ELEMENT_SIZE_FMASK); iowrite32(val, gsi->virt + GSI_CH_C_CNTXT_0_OFFSET(channel_id)); - val = r_length_encoded(gsi->version, size); + val = ch_c_cntxt_1_length_encode(gsi->version, size); iowrite32(val, gsi->virt + GSI_CH_C_CNTXT_1_OFFSET(channel_id)); /* The context 2 and 3 registers store the low-order and @@ -1195,15 +1230,15 @@ static void gsi_isr_glob_ee(struct gsi *gsi) val = ioread32(gsi->virt + GSI_CNTXT_GLOB_IRQ_STTS_OFFSET); - if (val & BIT(ERROR_INT)) + if (val & ERROR_INT) gsi_isr_glob_err(gsi); iowrite32(val, gsi->virt + GSI_CNTXT_GLOB_IRQ_CLR_OFFSET); - val &= ~BIT(ERROR_INT); + val &= ~ERROR_INT; - if (val & BIT(GP_INT1)) { - val ^= BIT(GP_INT1); + if (val & GP_INT1) { + val ^= GP_INT1; gsi_isr_gp_int1(gsi); } @@ -1264,19 +1299,19 @@ static irqreturn_t gsi_isr(int irq, void *dev_id) intr_mask ^= gsi_intr; switch (gsi_intr) { - case BIT(GSI_CH_CTRL): + case GSI_CH_CTRL: gsi_isr_chan_ctrl(gsi); break; - case BIT(GSI_EV_CTRL): + case GSI_EV_CTRL: gsi_isr_evt_ctrl(gsi); break; - case BIT(GSI_GLOB_EE): + case GSI_GLOB_EE: gsi_isr_glob_ee(gsi); break; - case BIT(GSI_IEOB): + case GSI_IEOB: gsi_isr_ieob(gsi); break; - case BIT(GSI_GENERAL): + case GSI_GENERAL: gsi_isr_general(gsi); break; default: @@ -1654,7 +1689,7 @@ static int gsi_generic_command(struct gsi *gsi, u32 channel_id, * channel), and only from this function. So we enable the GP_INT1 * IRQ type here, and disable it again after the command completes. */ - val = BIT(ERROR_INT) | BIT(GP_INT1); + val = ERROR_INT | GP_INT1; iowrite32(val, gsi->virt + GSI_CNTXT_GLOB_IRQ_EN_OFFSET); /* First zero the result code field */ @@ -1666,12 +1701,13 @@ static int gsi_generic_command(struct gsi *gsi, u32 channel_id, val = u32_encode_bits(opcode, GENERIC_OPCODE_FMASK); val |= u32_encode_bits(channel_id, GENERIC_CHID_FMASK); val |= u32_encode_bits(GSI_EE_MODEM, GENERIC_EE_FMASK); - val |= u32_encode_bits(params, GENERIC_PARAMS_FMASK); + if (gsi->version >= IPA_VERSION_4_11) + val |= u32_encode_bits(params, GENERIC_PARAMS_FMASK); timeout = !gsi_command(gsi, GSI_GENERIC_CMD_OFFSET, val); /* Disable the GP_INT1 IRQ type again */ - iowrite32(BIT(ERROR_INT), gsi->virt + GSI_CNTXT_GLOB_IRQ_EN_OFFSET); + iowrite32(ERROR_INT, gsi->virt + GSI_CNTXT_GLOB_IRQ_EN_OFFSET); if (!timeout) return gsi->result; diff --git a/drivers/net/ipa/gsi_reg.h b/drivers/net/ipa/gsi_reg.h index 3763359f208f..d171f65d4198 100644 --- a/drivers/net/ipa/gsi_reg.h +++ b/drivers/net/ipa/gsi_reg.h @@ -62,6 +62,18 @@ /* All other register offsets are relative to gsi->virt */ +#define GSI_CH_C_CNTXT_0_OFFSET(ch) \ + (0x0001c000 + 0x4000 * GSI_EE_AP + 0x80 * (ch)) +#define CHTYPE_PROTOCOL_FMASK GENMASK(2, 0) +#define CHTYPE_DIR_FMASK GENMASK(3, 3) +#define EE_FMASK GENMASK(7, 4) +#define CHID_FMASK GENMASK(12, 8) +/* The next field is present for IPA v4.5 and above */ +#define CHTYPE_PROTOCOL_MSB_FMASK GENMASK(13, 13) +#define ERINDEX_FMASK GENMASK(18, 14) +#define CHSTATE_FMASK GENMASK(23, 20) +#define ELEMENT_SIZE_FMASK GENMASK(31, 24) + /** enum gsi_channel_type - CHTYPE_PROTOCOL field values in CH_C_CNTXT_0 */ enum gsi_channel_type { GSI_CHANNEL_TYPE_MHI = 0x0, @@ -76,46 +88,9 @@ enum gsi_channel_type { GSI_CHANNEL_TYPE_11AD = 0x9, }; -#define GSI_CH_C_CNTXT_0_OFFSET(ch) \ - (0x0001c000 + 0x4000 * GSI_EE_AP + 0x80 * (ch)) -#define CHTYPE_PROTOCOL_FMASK GENMASK(2, 0) -#define CHTYPE_DIR_FMASK GENMASK(3, 3) -#define EE_FMASK GENMASK(7, 4) -#define CHID_FMASK GENMASK(12, 8) -/* The next field is present for IPA v4.5 and above */ -#define CHTYPE_PROTOCOL_MSB_FMASK GENMASK(13, 13) -#define ERINDEX_FMASK GENMASK(18, 14) -#define CHSTATE_FMASK GENMASK(23, 20) -#define ELEMENT_SIZE_FMASK GENMASK(31, 24) - -/* Encoded value for CH_C_CNTXT_0 register channel protocol fields */ -static inline u32 -chtype_protocol_encoded(enum ipa_version version, enum gsi_channel_type type) -{ - u32 val; - - val = u32_encode_bits(type, CHTYPE_PROTOCOL_FMASK); - if (version < IPA_VERSION_4_5) - return val; - - /* Encode upper bit(s) as well */ - type >>= hweight32(CHTYPE_PROTOCOL_FMASK); - val |= u32_encode_bits(type, CHTYPE_PROTOCOL_MSB_FMASK); - - return val; -} - #define GSI_CH_C_CNTXT_1_OFFSET(ch) \ (0x0001c004 + 0x4000 * GSI_EE_AP + 0x80 * (ch)) -/* Encoded value for CH_C_CNTXT_1 register R_LENGTH field */ -static inline u32 r_length_encoded(enum ipa_version version, u32 length) -{ - if (version < IPA_VERSION_4_9) - return u32_encode_bits(length, GENMASK(15, 0)); - return u32_encode_bits(length, GENMASK(19, 0)); -} - #define GSI_CH_C_CNTXT_2_OFFSET(ch) \ (0x0001c008 + 0x4000 * GSI_EE_AP + 0x80 * (ch)) @@ -167,13 +142,6 @@ enum gsi_prefetch_mode { #define GSI_EV_CH_E_CNTXT_1_OFFSET(ev) \ (0x0001d004 + 0x4000 * GSI_EE_AP + 0x80 * (ev)) -/* Encoded value for EV_CH_C_CNTXT_1 register EV_R_LENGTH field */ -static inline u32 ev_r_length_encoded(enum ipa_version version, u32 length) -{ - if (version < IPA_VERSION_4_9) - return u32_encode_bits(length, GENMASK(15, 0)); - return u32_encode_bits(length, GENMASK(19, 0)); -} #define GSI_EV_CH_E_CNTXT_2_OFFSET(ev) \ (0x0001d008 + 0x4000 * GSI_EE_AP + 0x80 * (ev)) @@ -299,15 +267,25 @@ enum gsi_iram_size { #define GSI_CNTXT_TYPE_IRQ_MSK_OFFSET \ (0x0001f088 + 0x4000 * GSI_EE_AP) -/* Values here are bit positions in the TYPE_IRQ and TYPE_IRQ_MSK registers */ +/** + * enum gsi_irq_type_id: GSI IRQ types + * @GSI_CH_CTRL: Channel allocation, deallocation, etc. + * @GSI_EV_CTRL: Event ring allocation, deallocation, etc. + * @GSI_GLOB_EE: Global/general event + * @GSI_IEOB: Transfer (TRE) completion + * @GSI_INTER_EE_CH_CTRL: Remote-issued stop/reset (unused) + * @GSI_INTER_EE_EV_CTRL: Remote-issued event reset (unused) + * @GSI_GENERAL: General hardware event (bus error, etc.) + */ enum gsi_irq_type_id { - GSI_CH_CTRL = 0x0, /* channel allocation, etc. */ - GSI_EV_CTRL = 0x1, /* event ring allocation, etc. */ - GSI_GLOB_EE = 0x2, /* global/general event */ - GSI_IEOB = 0x3, /* TRE completion */ - GSI_INTER_EE_CH_CTRL = 0x4, /* remote-issued stop/reset (unused) */ - GSI_INTER_EE_EV_CTRL = 0x5, /* remote-issued event reset (unused) */ - GSI_GENERAL = 0x6, /* general-purpose event */ + GSI_CH_CTRL = BIT(0), + GSI_EV_CTRL = BIT(1), + GSI_GLOB_EE = BIT(2), + GSI_IEOB = BIT(3), + GSI_INTER_EE_CH_CTRL = BIT(4), + GSI_INTER_EE_EV_CTRL = BIT(5), + GSI_GENERAL = BIT(6), + /* IRQ types 7-31 (and their bit values) are reserved */ }; #define GSI_CNTXT_SRC_CH_IRQ_OFFSET \ @@ -343,12 +321,14 @@ enum gsi_irq_type_id { (0x0001f108 + 0x4000 * GSI_EE_AP) #define GSI_CNTXT_GLOB_IRQ_CLR_OFFSET \ (0x0001f110 + 0x4000 * GSI_EE_AP) -/* Values here are bit positions in the GLOB_IRQ_* registers */ + +/** enum gsi_global_irq_id: Global GSI interrupt events */ enum gsi_global_irq_id { - ERROR_INT = 0x0, - GP_INT1 = 0x1, - GP_INT2 = 0x2, - GP_INT3 = 0x3, + ERROR_INT = BIT(0), + GP_INT1 = BIT(1), + GP_INT2 = BIT(2), + GP_INT3 = BIT(3), + /* Global IRQ types 4-31 (and their bit values) are reserved */ }; #define GSI_CNTXT_GSI_IRQ_STTS_OFFSET \ @@ -357,12 +337,14 @@ enum gsi_global_irq_id { (0x0001f120 + 0x4000 * GSI_EE_AP) #define GSI_CNTXT_GSI_IRQ_CLR_OFFSET \ (0x0001f128 + 0x4000 * GSI_EE_AP) -/* Values here are bit positions in the (general) GSI_IRQ_* registers */ -enum gsi_general_id { - BREAK_POINT = 0x0, - BUS_ERROR = 0x1, - CMD_FIFO_OVRFLOW = 0x2, - MCS_STACK_OVRFLOW = 0x3, + +/** enum gsi_general_irq_id: GSI general IRQ conditions */ +enum gsi_general_irq_id { + BREAK_POINT = BIT(0), + BUS_ERROR = BIT(1), + CMD_FIFO_OVRFLOW = BIT(2), + MCS_STACK_OVRFLOW = BIT(3), + /* General IRQ types 4-31 (and their bit values) are reserved */ }; #define GSI_CNTXT_INTSET_OFFSET \ @@ -372,7 +354,6 @@ enum gsi_general_id { #define GSI_ERROR_LOG_OFFSET \ (0x0001f200 + 0x4000 * GSI_EE_AP) -/* Fields below are present for IPA v3.5.1 and above */ #define ERR_ARG3_FMASK GENMASK(3, 0) #define ERR_ARG2_FMASK GENMASK(7, 4) #define ERR_ARG1_FMASK GENMASK(11, 8) diff --git a/drivers/net/ipa/ipa.h b/drivers/net/ipa/ipa.h index 5372db58b5bd..f3355e040a9e 100644 --- a/drivers/net/ipa/ipa.h +++ b/drivers/net/ipa/ipa.h @@ -45,7 +45,6 @@ struct ipa_interrupt; * @interrupt: IPA Interrupt information * @uc_powered: true if power is active by proxy for microcontroller * @uc_loaded: true after microcontroller has reported it's ready - * @reg_addr: DMA address used for IPA register access * @reg_virt: Virtual address used for IPA register access * @regs: IPA register definitions * @mem_addr: DMA address of IPA-local memory space @@ -97,9 +96,8 @@ struct ipa { bool uc_powered; bool uc_loaded; - dma_addr_t reg_addr; void __iomem *reg_virt; - const struct ipa_regs *regs; + const struct regs *regs; dma_addr_t mem_addr; void *mem_virt; diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c index bb3dfa9a2bc8..f1419fbd776c 100644 --- a/drivers/net/ipa/ipa_cmd.c +++ b/drivers/net/ipa/ipa_cmd.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2012-2018, The Linux Foundation. All rights reserved. - * Copyright (C) 2019-2022 Linaro Ltd. + * Copyright (C) 2019-2023 Linaro Ltd. */ #include <linux/types.h> @@ -94,11 +94,11 @@ struct ipa_cmd_register_write { /* IPA_CMD_IP_PACKET_INIT */ struct ipa_cmd_ip_packet_init { - u8 dest_endpoint; + u8 dest_endpoint; /* Full 8 bits used for IPA v5.0+ */ u8 reserved[7]; }; -/* Field masks for ipa_cmd_ip_packet_init dest_endpoint field */ +/* Field mask for ipa_cmd_ip_packet_init dest_endpoint field (unused v5.0+) */ #define IPA_PACKET_INIT_DEST_ENDPOINT_FMASK GENMASK(4, 0) /* IPA_CMD_DMA_SHARED_MEM */ @@ -157,9 +157,14 @@ static void ipa_cmd_validate_build(void) BUILD_BUG_ON(field_max(IP_FLTRT_FLAGS_HASH_ADDR_FMASK) != field_max(IP_FLTRT_FLAGS_NHASH_ADDR_FMASK)); - /* Valid endpoint numbers must fit in the IP packet init command */ - BUILD_BUG_ON(field_max(IPA_PACKET_INIT_DEST_ENDPOINT_FMASK) < - IPA_ENDPOINT_MAX - 1); + /* Prior to IPA v5.0, we supported no more than 32 endpoints, + * and this was reflected in some 5-bit fields that held + * endpoint numbers. Starting with IPA v5.0, the widths of + * these fields were extended to 8 bits, meaning up to 256 + * endpoints. If the driver claims to support more than + * that it's an error. + */ + BUILD_BUG_ON(IPA_ENDPOINT_MAX - 1 > U8_MAX); } /* Validate a memory region holding a table */ @@ -282,7 +287,7 @@ static bool ipa_cmd_register_write_offset_valid(struct ipa *ipa, /* Check whether offsets passed to register_write are valid */ static bool ipa_cmd_register_write_valid(struct ipa *ipa) { - const struct ipa_reg *reg; + const struct reg *reg; const char *name; u32 offset; @@ -290,8 +295,12 @@ static bool ipa_cmd_register_write_valid(struct ipa *ipa) * offset will fit in a register write IPA immediate command. */ if (ipa_table_hash_support(ipa)) { - reg = ipa_reg(ipa, FILT_ROUT_HASH_FLUSH); - offset = ipa_reg_offset(reg); + if (ipa->version < IPA_VERSION_5_0) + reg = ipa_reg(ipa, FILT_ROUT_HASH_FLUSH); + else + reg = ipa_reg(ipa, FILT_ROUT_CACHE_FLUSH); + + offset = reg_offset(reg); name = "filter/route hash flush"; if (!ipa_cmd_register_write_offset_valid(ipa, name, offset)) return false; @@ -305,7 +314,7 @@ static bool ipa_cmd_register_write_valid(struct ipa *ipa) * fits in the register write command field(s) that must hold it. */ reg = ipa_reg(ipa, ENDP_STATUS); - offset = ipa_reg_n_offset(reg, IPA_ENDPOINT_COUNT - 1); + offset = reg_n_offset(reg, IPA_ENDPOINT_COUNT - 1); name = "maximal endpoint status"; if (!ipa_cmd_register_write_offset_valid(ipa, name, offset)) return false; @@ -486,8 +495,13 @@ static void ipa_cmd_ip_packet_init_add(struct gsi_trans *trans, u8 endpoint_id) cmd_payload = ipa_cmd_payload_alloc(ipa, &payload_addr); payload = &cmd_payload->ip_packet_init; - payload->dest_endpoint = u8_encode_bits(endpoint_id, - IPA_PACKET_INIT_DEST_ENDPOINT_FMASK); + if (ipa->version < IPA_VERSION_5_0) { + payload->dest_endpoint = + u8_encode_bits(endpoint_id, + IPA_PACKET_INIT_DEST_ENDPOINT_FMASK); + } else { + payload->dest_endpoint = endpoint_id; + } gsi_trans_cmd_add(trans, payload, sizeof(*payload), payload_addr, opcode); diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index ce7f2d6e447e..2ee80ed140b7 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2012-2018, The Linux Foundation. All rights reserved. - * Copyright (C) 2019-2022 Linaro Ltd. + * Copyright (C) 2019-2023 Linaro Ltd. */ #include <linux/types.h> @@ -241,7 +241,7 @@ static bool ipa_endpoint_data_valid_one(struct ipa *ipa, u32 count, if (!data->toward_ipa) { const struct ipa_endpoint_rx *rx_config; - const struct ipa_reg *reg; + const struct reg *reg; u32 buffer_size; u32 aggr_size; u32 limit; @@ -304,7 +304,7 @@ static bool ipa_endpoint_data_valid_one(struct ipa *ipa, u32 count, rx_config->aggr_hard_limit); reg = ipa_reg(ipa, ENDP_INIT_AGGR); - limit = ipa_reg_field_max(reg, BYTE_LIMIT); + limit = reg_field_max(reg, BYTE_LIMIT); if (aggr_size > limit) { dev_err(dev, "aggregated size too large for RX endpoint %u (%u KB > %u KB)\n", data->endpoint_id, aggr_size, limit); @@ -447,7 +447,7 @@ static bool ipa_endpoint_init_ctrl(struct ipa_endpoint *endpoint, bool suspend_delay) { struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 field_id; u32 offset; bool state; @@ -460,11 +460,11 @@ ipa_endpoint_init_ctrl(struct ipa_endpoint *endpoint, bool suspend_delay) WARN_ON(ipa->version >= IPA_VERSION_4_0); reg = ipa_reg(ipa, ENDP_INIT_CTRL); - offset = ipa_reg_n_offset(reg, endpoint->endpoint_id); + offset = reg_n_offset(reg, endpoint->endpoint_id); val = ioread32(ipa->reg_virt + offset); field_id = endpoint->toward_ipa ? ENDP_DELAY : ENDP_SUSPEND; - mask = ipa_reg_bit(reg, field_id); + mask = reg_bit(reg, field_id); state = !!(val & mask); @@ -493,13 +493,13 @@ static bool ipa_endpoint_aggr_active(struct ipa_endpoint *endpoint) u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; u32 unit = endpoint_id / 32; - const struct ipa_reg *reg; + const struct reg *reg; u32 val; WARN_ON(!test_bit(endpoint_id, ipa->available)); reg = ipa_reg(ipa, STATE_AGGR_ACTIVE); - val = ioread32(ipa->reg_virt + ipa_reg_n_offset(reg, unit)); + val = ioread32(ipa->reg_virt + reg_n_offset(reg, unit)); return !!(val & BIT(endpoint_id % 32)); } @@ -510,12 +510,12 @@ static void ipa_endpoint_force_close(struct ipa_endpoint *endpoint) u32 mask = BIT(endpoint_id % 32); struct ipa *ipa = endpoint->ipa; u32 unit = endpoint_id / 32; - const struct ipa_reg *reg; + const struct reg *reg; WARN_ON(!test_bit(endpoint_id, ipa->available)); reg = ipa_reg(ipa, AGGR_FORCE_CLOSE); - iowrite32(mask, ipa->reg_virt + ipa_reg_n_offset(reg, unit)); + iowrite32(mask, ipa->reg_virt + reg_n_offset(reg, unit)); } /** @@ -613,7 +613,7 @@ int ipa_endpoint_modem_exception_reset_all(struct ipa *ipa) for_each_set_bit(endpoint_id, ipa->defined, ipa->endpoint_count) { struct ipa_endpoint *endpoint; - const struct ipa_reg *reg; + const struct reg *reg; u32 offset; /* We only reset modem TX endpoints */ @@ -622,7 +622,7 @@ int ipa_endpoint_modem_exception_reset_all(struct ipa *ipa) continue; reg = ipa_reg(ipa, ENDP_STATUS); - offset = ipa_reg_n_offset(reg, endpoint_id); + offset = reg_n_offset(reg, endpoint_id); /* Value written is 0, and all bits are updated. That * means status is disabled on the endpoint, and as a @@ -645,7 +645,7 @@ static void ipa_endpoint_init_cfg(struct ipa_endpoint *endpoint) u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; enum ipa_cs_offload_en enabled; - const struct ipa_reg *reg; + const struct reg *reg; u32 val = 0; reg = ipa_reg(ipa, ENDP_INIT_CFG); @@ -658,7 +658,7 @@ static void ipa_endpoint_init_cfg(struct ipa_endpoint *endpoint) /* Checksum header offset is in 4-byte units */ off = sizeof(struct rmnet_map_header) / sizeof(u32); - val |= ipa_reg_encode(reg, CS_METADATA_HDR_OFFSET, off); + val |= reg_encode(reg, CS_METADATA_HDR_OFFSET, off); enabled = version < IPA_VERSION_4_5 ? IPA_CS_OFFLOAD_UL @@ -671,26 +671,26 @@ static void ipa_endpoint_init_cfg(struct ipa_endpoint *endpoint) } else { enabled = IPA_CS_OFFLOAD_NONE; } - val |= ipa_reg_encode(reg, CS_OFFLOAD_EN, enabled); + val |= reg_encode(reg, CS_OFFLOAD_EN, enabled); /* CS_GEN_QMB_MASTER_SEL is 0 */ - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, endpoint_id)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, endpoint_id)); } static void ipa_endpoint_init_nat(struct ipa_endpoint *endpoint) { u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 val; if (!endpoint->toward_ipa) return; reg = ipa_reg(ipa, ENDP_INIT_NAT); - val = ipa_reg_encode(reg, NAT_EN, IPA_NAT_TYPE_BYPASS); + val = reg_encode(reg, NAT_EN, IPA_NAT_TYPE_BYPASS); - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, endpoint_id)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, endpoint_id)); } static u32 @@ -716,13 +716,13 @@ ipa_qmap_header_size(enum ipa_version version, struct ipa_endpoint *endpoint) /* Encoded value for ENDP_INIT_HDR register HDR_LEN* field(s) */ static u32 ipa_header_size_encode(enum ipa_version version, - const struct ipa_reg *reg, u32 header_size) + const struct reg *reg, u32 header_size) { - u32 field_max = ipa_reg_field_max(reg, HDR_LEN); + u32 field_max = reg_field_max(reg, HDR_LEN); u32 val; /* We know field_max can be used as a mask (2^n - 1) */ - val = ipa_reg_encode(reg, HDR_LEN, header_size & field_max); + val = reg_encode(reg, HDR_LEN, header_size & field_max); if (version < IPA_VERSION_4_5) { WARN_ON(header_size > field_max); return val; @@ -730,21 +730,21 @@ static u32 ipa_header_size_encode(enum ipa_version version, /* IPA v4.5 adds a few more most-significant bits */ header_size >>= hweight32(field_max); - WARN_ON(header_size > ipa_reg_field_max(reg, HDR_LEN_MSB)); - val |= ipa_reg_encode(reg, HDR_LEN_MSB, header_size); + WARN_ON(header_size > reg_field_max(reg, HDR_LEN_MSB)); + val |= reg_encode(reg, HDR_LEN_MSB, header_size); return val; } /* Encoded value for ENDP_INIT_HDR register OFST_METADATA* field(s) */ static u32 ipa_metadata_offset_encode(enum ipa_version version, - const struct ipa_reg *reg, u32 offset) + const struct reg *reg, u32 offset) { - u32 field_max = ipa_reg_field_max(reg, HDR_OFST_METADATA); + u32 field_max = reg_field_max(reg, HDR_OFST_METADATA); u32 val; /* We know field_max can be used as a mask (2^n - 1) */ - val = ipa_reg_encode(reg, HDR_OFST_METADATA, offset); + val = reg_encode(reg, HDR_OFST_METADATA, offset); if (version < IPA_VERSION_4_5) { WARN_ON(offset > field_max); return val; @@ -752,8 +752,8 @@ static u32 ipa_metadata_offset_encode(enum ipa_version version, /* IPA v4.5 adds a few more most-significant bits */ offset >>= hweight32(field_max); - WARN_ON(offset > ipa_reg_field_max(reg, HDR_OFST_METADATA_MSB)); - val |= ipa_reg_encode(reg, HDR_OFST_METADATA_MSB, offset); + WARN_ON(offset > reg_field_max(reg, HDR_OFST_METADATA_MSB)); + val |= reg_encode(reg, HDR_OFST_METADATA_MSB, offset); return val; } @@ -783,7 +783,7 @@ static void ipa_endpoint_init_hdr(struct ipa_endpoint *endpoint) { u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 val = 0; reg = ipa_reg(ipa, ENDP_INIT_HDR); @@ -806,13 +806,13 @@ static void ipa_endpoint_init_hdr(struct ipa_endpoint *endpoint) off = offsetof(struct rmnet_map_header, pkt_len); /* Upper bits are stored in HDR_EXT with IPA v4.5 */ if (version >= IPA_VERSION_4_5) - off &= ipa_reg_field_max(reg, HDR_OFST_PKT_SIZE); + off &= reg_field_max(reg, HDR_OFST_PKT_SIZE); - val |= ipa_reg_bit(reg, HDR_OFST_PKT_SIZE_VALID); - val |= ipa_reg_encode(reg, HDR_OFST_PKT_SIZE, off); + val |= reg_bit(reg, HDR_OFST_PKT_SIZE_VALID); + val |= reg_encode(reg, HDR_OFST_PKT_SIZE, off); } /* For QMAP TX, metadata offset is 0 (modem assumes this) */ - val |= ipa_reg_bit(reg, HDR_OFST_METADATA_VALID); + val |= reg_bit(reg, HDR_OFST_METADATA_VALID); /* HDR_ADDITIONAL_CONST_LEN is 0; (RX only) */ /* HDR_A5_MUX is 0 */ @@ -820,7 +820,7 @@ static void ipa_endpoint_init_hdr(struct ipa_endpoint *endpoint) /* HDR_METADATA_REG_VALID is 0 (TX only, version < v4.5) */ } - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, endpoint_id)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, endpoint_id)); } static void ipa_endpoint_init_hdr_ext(struct ipa_endpoint *endpoint) @@ -828,13 +828,13 @@ static void ipa_endpoint_init_hdr_ext(struct ipa_endpoint *endpoint) u32 pad_align = endpoint->config.rx.pad_align; u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 val = 0; reg = ipa_reg(ipa, ENDP_INIT_HDR_EXT); if (endpoint->config.qmap) { /* We have a header, so we must specify its endianness */ - val |= ipa_reg_bit(reg, HDR_ENDIANNESS); /* big endian */ + val |= reg_bit(reg, HDR_ENDIANNESS); /* big endian */ /* A QMAP header contains a 6 bit pad field at offset 0. * The RMNet driver assumes this field is meaningful in @@ -844,16 +844,16 @@ static void ipa_endpoint_init_hdr_ext(struct ipa_endpoint *endpoint) * (although 0) should be ignored. */ if (!endpoint->toward_ipa) { - val |= ipa_reg_bit(reg, HDR_TOTAL_LEN_OR_PAD_VALID); + val |= reg_bit(reg, HDR_TOTAL_LEN_OR_PAD_VALID); /* HDR_TOTAL_LEN_OR_PAD is 0 (pad, not total_len) */ - val |= ipa_reg_bit(reg, HDR_PAYLOAD_LEN_INC_PADDING); + val |= reg_bit(reg, HDR_PAYLOAD_LEN_INC_PADDING); /* HDR_TOTAL_LEN_OR_PAD_OFFSET is 0 */ } } /* HDR_PAYLOAD_LEN_INC_PADDING is 0 */ if (!endpoint->toward_ipa) - val |= ipa_reg_encode(reg, HDR_PAD_TO_ALIGNMENT, pad_align); + val |= reg_encode(reg, HDR_PAD_TO_ALIGNMENT, pad_align); /* IPA v4.5 adds some most-significant bits to a few fields, * two of which are defined in the HDR (not HDR_EXT) register. @@ -861,25 +861,25 @@ static void ipa_endpoint_init_hdr_ext(struct ipa_endpoint *endpoint) if (ipa->version >= IPA_VERSION_4_5) { /* HDR_TOTAL_LEN_OR_PAD_OFFSET is 0, so MSB is 0 */ if (endpoint->config.qmap && !endpoint->toward_ipa) { - u32 mask = ipa_reg_field_max(reg, HDR_OFST_PKT_SIZE); + u32 mask = reg_field_max(reg, HDR_OFST_PKT_SIZE); u32 off; /* Field offset within header */ off = offsetof(struct rmnet_map_header, pkt_len); /* Low bits are in the ENDP_INIT_HDR register */ off >>= hweight32(mask); - val |= ipa_reg_encode(reg, HDR_OFST_PKT_SIZE_MSB, off); + val |= reg_encode(reg, HDR_OFST_PKT_SIZE_MSB, off); /* HDR_ADDITIONAL_CONST_LEN is 0 so MSB is 0 */ } } - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, endpoint_id)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, endpoint_id)); } static void ipa_endpoint_init_hdr_metadata_mask(struct ipa_endpoint *endpoint) { u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 val = 0; u32 offset; @@ -887,7 +887,7 @@ static void ipa_endpoint_init_hdr_metadata_mask(struct ipa_endpoint *endpoint) return; /* Register not valid for TX endpoints */ reg = ipa_reg(ipa, ENDP_INIT_HDR_METADATA_MASK); - offset = ipa_reg_n_offset(reg, endpoint_id); + offset = reg_n_offset(reg, endpoint_id); /* Note that HDR_ENDIANNESS indicates big endian header fields */ if (endpoint->config.qmap) @@ -899,7 +899,7 @@ static void ipa_endpoint_init_hdr_metadata_mask(struct ipa_endpoint *endpoint) static void ipa_endpoint_init_mode(struct ipa_endpoint *endpoint) { struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 offset; u32 val; @@ -911,82 +911,90 @@ static void ipa_endpoint_init_mode(struct ipa_endpoint *endpoint) enum ipa_endpoint_name name = endpoint->config.dma_endpoint; u32 dma_endpoint_id = ipa->name_map[name]->endpoint_id; - val = ipa_reg_encode(reg, ENDP_MODE, IPA_DMA); - val |= ipa_reg_encode(reg, DEST_PIPE_INDEX, dma_endpoint_id); + val = reg_encode(reg, ENDP_MODE, IPA_DMA); + val |= reg_encode(reg, DEST_PIPE_INDEX, dma_endpoint_id); } else { - val = ipa_reg_encode(reg, ENDP_MODE, IPA_BASIC); + val = reg_encode(reg, ENDP_MODE, IPA_BASIC); } /* All other bits unspecified (and 0) */ - offset = ipa_reg_n_offset(reg, endpoint->endpoint_id); + offset = reg_n_offset(reg, endpoint->endpoint_id); iowrite32(val, ipa->reg_virt + offset); } -/* For IPA v4.5+, times are expressed using Qtime. The AP uses one of two - * pulse generators (0 and 1) to measure elapsed time. In ipa_qtime_config() - * they're configured to have granularity 100 usec and 1 msec, respectively. - * - * The return value is the positive or negative Qtime value to use to - * express the (microsecond) time provided. A positive return value - * means pulse generator 0 can be used; otherwise use pulse generator 1. +/* For IPA v4.5+, times are expressed using Qtime. A time is represented + * at one of several available granularities, which are configured in + * ipa_qtime_config(). Three (or, starting with IPA v5.0, four) pulse + * generators are set up with different "tick" periods. A Qtime value + * encodes a tick count along with an indication of a pulse generator + * (which has a fixed tick period). Two pulse generators are always + * available to the AP; a third is available starting with IPA v5.0. + * This function determines which pulse generator most accurately + * represents the time period provided, and returns the tick count to + * use to represent that time. */ -static int ipa_qtime_val(u32 microseconds, u32 max) -{ - u32 val; - - /* Use 100 microsecond granularity if possible */ - val = DIV_ROUND_CLOSEST(microseconds, 100); - if (val <= max) - return (int)val; - - /* Have to use pulse generator 1 (millisecond granularity) */ - val = DIV_ROUND_CLOSEST(microseconds, 1000); - WARN_ON(val > max); +static u32 +ipa_qtime_val(struct ipa *ipa, u32 microseconds, u32 max, u32 *select) +{ + u32 which = 0; + u32 ticks; + + /* Pulse generator 0 has 100 microsecond granularity */ + ticks = DIV_ROUND_CLOSEST(microseconds, 100); + if (ticks <= max) + goto out; + + /* Pulse generator 1 has millisecond granularity */ + which = 1; + ticks = DIV_ROUND_CLOSEST(microseconds, 1000); + if (ticks <= max) + goto out; + + if (ipa->version >= IPA_VERSION_5_0) { + /* Pulse generator 2 has 10 millisecond granularity */ + which = 2; + ticks = DIV_ROUND_CLOSEST(microseconds, 100); + } + WARN_ON(ticks > max); +out: + *select = which; - return (int)-val; + return ticks; } /* Encode the aggregation timer limit (microseconds) based on IPA version */ -static u32 aggr_time_limit_encode(struct ipa *ipa, const struct ipa_reg *reg, +static u32 aggr_time_limit_encode(struct ipa *ipa, const struct reg *reg, u32 microseconds) { + u32 ticks; u32 max; - u32 val; if (!microseconds) return 0; /* Nothing to compute if time limit is 0 */ - max = ipa_reg_field_max(reg, TIME_LIMIT); + max = reg_field_max(reg, TIME_LIMIT); if (ipa->version >= IPA_VERSION_4_5) { - u32 gran_sel; - int ret; - - /* Compute the Qtime limit value to use */ - ret = ipa_qtime_val(microseconds, max); - if (ret < 0) { - val = -ret; - gran_sel = ipa_reg_bit(reg, AGGR_GRAN_SEL); - } else { - val = ret; - gran_sel = 0; - } + u32 select; + + ticks = ipa_qtime_val(ipa, microseconds, max, &select); - return gran_sel | ipa_reg_encode(reg, TIME_LIMIT, val); + return reg_encode(reg, AGGR_GRAN_SEL, select) | + reg_encode(reg, TIME_LIMIT, ticks); } /* We program aggregation granularity in ipa_hardware_config() */ - val = DIV_ROUND_CLOSEST(microseconds, IPA_AGGR_GRANULARITY); - WARN(val > max, "aggr_time_limit too large (%u > %u usec)\n", + ticks = DIV_ROUND_CLOSEST(microseconds, IPA_AGGR_GRANULARITY); + WARN(ticks > max, "aggr_time_limit too large (%u > %u usec)\n", microseconds, max * IPA_AGGR_GRANULARITY); - return ipa_reg_encode(reg, TIME_LIMIT, val); + return reg_encode(reg, TIME_LIMIT, ticks); } static void ipa_endpoint_init_aggr(struct ipa_endpoint *endpoint) { u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 val = 0; reg = ipa_reg(ipa, ENDP_INIT_AGGR); @@ -997,13 +1005,13 @@ static void ipa_endpoint_init_aggr(struct ipa_endpoint *endpoint) u32 limit; rx_config = &endpoint->config.rx; - val |= ipa_reg_encode(reg, AGGR_EN, IPA_ENABLE_AGGR); - val |= ipa_reg_encode(reg, AGGR_TYPE, IPA_GENERIC); + val |= reg_encode(reg, AGGR_EN, IPA_ENABLE_AGGR); + val |= reg_encode(reg, AGGR_TYPE, IPA_GENERIC); buffer_size = rx_config->buffer_size; limit = ipa_aggr_size_kb(buffer_size - NET_SKB_PAD, rx_config->aggr_hard_limit); - val |= ipa_reg_encode(reg, BYTE_LIMIT, limit); + val |= reg_encode(reg, BYTE_LIMIT, limit); limit = rx_config->aggr_time_limit; val |= aggr_time_limit_encode(ipa, reg, limit); @@ -1011,20 +1019,20 @@ static void ipa_endpoint_init_aggr(struct ipa_endpoint *endpoint) /* AGGR_PKT_LIMIT is 0 (unlimited) */ if (rx_config->aggr_close_eof) - val |= ipa_reg_bit(reg, SW_EOF_ACTIVE); + val |= reg_bit(reg, SW_EOF_ACTIVE); } else { - val |= ipa_reg_encode(reg, AGGR_EN, IPA_ENABLE_DEAGGR); - val |= ipa_reg_encode(reg, AGGR_TYPE, IPA_QCMAP); + val |= reg_encode(reg, AGGR_EN, IPA_ENABLE_DEAGGR); + val |= reg_encode(reg, AGGR_TYPE, IPA_QCMAP); /* other fields ignored */ } /* AGGR_FORCE_CLOSE is 0 */ /* AGGR_GRAN_SEL is 0 for IPA v4.5 */ } else { - val |= ipa_reg_encode(reg, AGGR_EN, IPA_BYPASS_AGGR); + val |= reg_encode(reg, AGGR_EN, IPA_BYPASS_AGGR); /* other fields ignored */ } - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, endpoint_id)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, endpoint_id)); } /* The head-of-line blocking timer is defined as a tick count. For @@ -1035,7 +1043,7 @@ static void ipa_endpoint_init_aggr(struct ipa_endpoint *endpoint) * Return the encoded value representing the timeout period provided * that should be written to the ENDP_INIT_HOL_BLOCK_TIMER register. */ -static u32 hol_block_timer_encode(struct ipa *ipa, const struct ipa_reg *reg, +static u32 hol_block_timer_encode(struct ipa *ipa, const struct reg *reg, u32 microseconds) { u32 width; @@ -1049,21 +1057,14 @@ static u32 hol_block_timer_encode(struct ipa *ipa, const struct ipa_reg *reg, return 0; /* Nothing to compute if timer period is 0 */ if (ipa->version >= IPA_VERSION_4_5) { - u32 max = ipa_reg_field_max(reg, TIMER_LIMIT); - u32 gran_sel; - int ret; - - /* Compute the Qtime limit value to use */ - ret = ipa_qtime_val(microseconds, max); - if (ret < 0) { - val = -ret; - gran_sel = ipa_reg_bit(reg, TIMER_GRAN_SEL); - } else { - val = ret; - gran_sel = 0; - } + u32 max = reg_field_max(reg, TIMER_LIMIT); + u32 select; + u32 ticks; - return gran_sel | ipa_reg_encode(reg, TIMER_LIMIT, val); + ticks = ipa_qtime_val(ipa, microseconds, max, &select); + + return reg_encode(reg, TIMER_GRAN_SEL, 1) | + reg_encode(reg, TIMER_LIMIT, ticks); } /* Use 64 bit arithmetic to avoid overflow */ @@ -1071,11 +1072,11 @@ static u32 hol_block_timer_encode(struct ipa *ipa, const struct ipa_reg *reg, ticks = DIV_ROUND_CLOSEST(microseconds * rate, 128 * USEC_PER_SEC); /* We still need the result to fit into the field */ - WARN_ON(ticks > ipa_reg_field_max(reg, TIMER_BASE_VALUE)); + WARN_ON(ticks > reg_field_max(reg, TIMER_BASE_VALUE)); /* IPA v3.5.1 through v4.1 just record the tick count */ if (ipa->version < IPA_VERSION_4_2) - return ipa_reg_encode(reg, TIMER_BASE_VALUE, (u32)ticks); + return reg_encode(reg, TIMER_BASE_VALUE, (u32)ticks); /* For IPA v4.2, the tick count is represented by base and * scale fields within the 32-bit timer register, where: @@ -1086,7 +1087,7 @@ static u32 hol_block_timer_encode(struct ipa *ipa, const struct ipa_reg *reg, * such that high bit is included. */ high = fls(ticks); /* 1..32 (or warning above) */ - width = hweight32(ipa_reg_fmask(reg, TIMER_BASE_VALUE)); + width = hweight32(reg_fmask(reg, TIMER_BASE_VALUE)); scale = high > width ? high - width : 0; if (scale) { /* If we're scaling, round up to get a closer result */ @@ -1096,8 +1097,8 @@ static u32 hol_block_timer_encode(struct ipa *ipa, const struct ipa_reg *reg, scale++; } - val = ipa_reg_encode(reg, TIMER_SCALE, scale); - val |= ipa_reg_encode(reg, TIMER_BASE_VALUE, (u32)ticks >> scale); + val = reg_encode(reg, TIMER_SCALE, scale); + val |= reg_encode(reg, TIMER_BASE_VALUE, (u32)ticks >> scale); return val; } @@ -1108,14 +1109,14 @@ static void ipa_endpoint_init_hol_block_timer(struct ipa_endpoint *endpoint, { u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 val; /* This should only be changed when HOL_BLOCK_EN is disabled */ reg = ipa_reg(ipa, ENDP_INIT_HOL_BLOCK_TIMER); val = hol_block_timer_encode(ipa, reg, microseconds); - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, endpoint_id)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, endpoint_id)); } static void @@ -1123,13 +1124,13 @@ ipa_endpoint_init_hol_block_en(struct ipa_endpoint *endpoint, bool enable) { u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 offset; u32 val; reg = ipa_reg(ipa, ENDP_INIT_HOL_BLOCK_EN); - offset = ipa_reg_n_offset(reg, endpoint_id); - val = enable ? ipa_reg_bit(reg, HOL_BLOCK_EN) : 0; + offset = reg_n_offset(reg, endpoint_id); + val = enable ? reg_bit(reg, HOL_BLOCK_EN) : 0; iowrite32(val, ipa->reg_virt + offset); @@ -1170,7 +1171,7 @@ static void ipa_endpoint_init_deaggr(struct ipa_endpoint *endpoint) { u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 val = 0; if (!endpoint->toward_ipa) @@ -1182,7 +1183,7 @@ static void ipa_endpoint_init_deaggr(struct ipa_endpoint *endpoint) /* PACKET_OFFSET_LOCATION is ignored (not valid) */ /* MAX_PACKET_LEN is 0 (not enforced) */ - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, endpoint_id)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, endpoint_id)); } static void ipa_endpoint_init_rsrc_grp(struct ipa_endpoint *endpoint) @@ -1190,20 +1191,20 @@ static void ipa_endpoint_init_rsrc_grp(struct ipa_endpoint *endpoint) u32 resource_group = endpoint->config.resource_group; u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 val; reg = ipa_reg(ipa, ENDP_INIT_RSRC_GRP); - val = ipa_reg_encode(reg, ENDP_RSRC_GRP, resource_group); + val = reg_encode(reg, ENDP_RSRC_GRP, resource_group); - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, endpoint_id)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, endpoint_id)); } static void ipa_endpoint_init_seq(struct ipa_endpoint *endpoint) { u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 val; if (!endpoint->toward_ipa) @@ -1212,14 +1213,14 @@ static void ipa_endpoint_init_seq(struct ipa_endpoint *endpoint) reg = ipa_reg(ipa, ENDP_INIT_SEQ); /* Low-order byte configures primary packet processing */ - val = ipa_reg_encode(reg, SEQ_TYPE, endpoint->config.tx.seq_type); + val = reg_encode(reg, SEQ_TYPE, endpoint->config.tx.seq_type); /* Second byte (if supported) configures replicated packet processing */ if (ipa->version < IPA_VERSION_4_5) - val |= ipa_reg_encode(reg, SEQ_REP_TYPE, - endpoint->config.tx.seq_rep_type); + val |= reg_encode(reg, SEQ_REP_TYPE, + endpoint->config.tx.seq_rep_type); - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, endpoint_id)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, endpoint_id)); } /** @@ -1269,12 +1270,12 @@ static void ipa_endpoint_status(struct ipa_endpoint *endpoint) { u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 val = 0; reg = ipa_reg(ipa, ENDP_STATUS); if (endpoint->config.status_enable) { - val |= ipa_reg_bit(reg, STATUS_EN); + val |= reg_bit(reg, STATUS_EN); if (endpoint->toward_ipa) { enum ipa_endpoint_name name; u32 status_endpoint_id; @@ -1282,8 +1283,7 @@ static void ipa_endpoint_status(struct ipa_endpoint *endpoint) name = endpoint->config.tx.status_endpoint; status_endpoint_id = ipa->name_map[name]->endpoint_id; - val |= ipa_reg_encode(reg, STATUS_ENDP, - status_endpoint_id); + val |= reg_encode(reg, STATUS_ENDP, status_endpoint_id); } /* STATUS_LOCATION is 0, meaning IPA packet status * precedes the packet (not present for IPA v4.5+) @@ -1291,7 +1291,7 @@ static void ipa_endpoint_status(struct ipa_endpoint *endpoint) /* STATUS_PKT_SUPPRESS_FMASK is 0 (not present for v4.0+) */ } - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, endpoint_id)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, endpoint_id)); } static int ipa_endpoint_replenish_one(struct ipa_endpoint *endpoint, @@ -1635,18 +1635,18 @@ void ipa_endpoint_trans_release(struct ipa_endpoint *endpoint, void ipa_endpoint_default_route_set(struct ipa *ipa, u32 endpoint_id) { - const struct ipa_reg *reg; + const struct reg *reg; u32 val; reg = ipa_reg(ipa, ROUTE); /* ROUTE_DIS is 0 */ - val = ipa_reg_encode(reg, ROUTE_DEF_PIPE, endpoint_id); - val |= ipa_reg_bit(reg, ROUTE_DEF_HDR_TABLE); + val = reg_encode(reg, ROUTE_DEF_PIPE, endpoint_id); + val |= reg_bit(reg, ROUTE_DEF_HDR_TABLE); /* ROUTE_DEF_HDR_OFST is 0 */ - val |= ipa_reg_encode(reg, ROUTE_FRAG_DEF_PIPE, endpoint_id); - val |= ipa_reg_bit(reg, ROUTE_DEF_RETAIN_HDR); + val |= reg_encode(reg, ROUTE_FRAG_DEF_PIPE, endpoint_id); + val |= reg_bit(reg, ROUTE_DEF_RETAIN_HDR); - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); } void ipa_endpoint_default_route_clear(struct ipa *ipa) @@ -1984,8 +1984,9 @@ void ipa_endpoint_deconfig(struct ipa *ipa) int ipa_endpoint_config(struct ipa *ipa) { struct device *dev = &ipa->pdev->dev; - const struct ipa_reg *reg; + const struct reg *reg; u32 endpoint_id; + u32 hw_limit; u32 tx_count; u32 rx_count; u32 rx_base; @@ -2017,12 +2018,12 @@ int ipa_endpoint_config(struct ipa *ipa) * the highest one doesn't exceed the number supported by software. */ reg = ipa_reg(ipa, FLAVOR_0); - val = ioread32(ipa->reg_virt + ipa_reg_offset(reg)); + val = ioread32(ipa->reg_virt + reg_offset(reg)); /* Our RX is an IPA producer; our TX is an IPA consumer. */ - tx_count = ipa_reg_decode(reg, MAX_CONS_PIPES, val); - rx_count = ipa_reg_decode(reg, MAX_PROD_PIPES, val); - rx_base = ipa_reg_decode(reg, PROD_LOWEST, val); + tx_count = reg_decode(reg, MAX_CONS_PIPES, val); + rx_count = reg_decode(reg, MAX_PROD_PIPES, val); + rx_base = reg_decode(reg, PROD_LOWEST, val); limit = rx_base + rx_count; if (limit > IPA_ENDPOINT_MAX) { @@ -2031,6 +2032,14 @@ int ipa_endpoint_config(struct ipa *ipa) return -EINVAL; } + /* Until IPA v5.0, the max endpoint ID was 32 */ + hw_limit = ipa->version < IPA_VERSION_5_0 ? 32 : U8_MAX + 1; + if (limit > hw_limit) { + dev_err(dev, "unexpected endpoint count, %u > %u\n", + limit, hw_limit); + return -EINVAL; + } + /* Allocate and initialize the available endpoint bitmap */ ipa->available = bitmap_zalloc(limit, GFP_KERNEL); if (!ipa->available) diff --git a/drivers/net/ipa/ipa_endpoint.h b/drivers/net/ipa/ipa_endpoint.h index 4a5c3bc549df..3ad2e802040a 100644 --- a/drivers/net/ipa/ipa_endpoint.h +++ b/drivers/net/ipa/ipa_endpoint.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2012-2018, The Linux Foundation. All rights reserved. - * Copyright (C) 2019-2022 Linaro Ltd. + * Copyright (C) 2019-2023 Linaro Ltd. */ #ifndef _IPA_ENDPOINT_H_ #define _IPA_ENDPOINT_H_ @@ -38,7 +38,7 @@ enum ipa_endpoint_name { IPA_ENDPOINT_COUNT, /* Number of names (not an index) */ }; -#define IPA_ENDPOINT_MAX 32 /* Max supported by driver */ +#define IPA_ENDPOINT_MAX 36 /* Max supported by driver */ /** * struct ipa_endpoint_tx - Endpoint configuration for TX endpoints diff --git a/drivers/net/ipa/ipa_interrupt.c b/drivers/net/ipa/ipa_interrupt.c index c19cd27ac852..4bc05948f772 100644 --- a/drivers/net/ipa/ipa_interrupt.c +++ b/drivers/net/ipa/ipa_interrupt.c @@ -22,6 +22,7 @@ #include <linux/types.h> #include <linux/interrupt.h> #include <linux/pm_runtime.h> +#include <linux/pm_wakeirq.h> #include "ipa.h" #include "ipa_reg.h" @@ -46,12 +47,12 @@ struct ipa_interrupt { static void ipa_interrupt_process(struct ipa_interrupt *interrupt, u32 irq_id) { struct ipa *ipa = interrupt->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 mask = BIT(irq_id); u32 offset; reg = ipa_reg(ipa, IPA_IRQ_CLR); - offset = ipa_reg_offset(reg); + offset = reg_offset(reg); switch (irq_id) { case IPA_IRQ_UC_0: @@ -84,7 +85,7 @@ static irqreturn_t ipa_isr_thread(int irq, void *dev_id) struct ipa_interrupt *interrupt = dev_id; struct ipa *ipa = interrupt->ipa; u32 enabled = interrupt->enabled; - const struct ipa_reg *reg; + const struct reg *reg; struct device *dev; u32 pending; u32 offset; @@ -101,7 +102,7 @@ static irqreturn_t ipa_isr_thread(int irq, void *dev_id) * only the enabled ones. */ reg = ipa_reg(ipa, IPA_IRQ_STTS); - offset = ipa_reg_offset(reg); + offset = reg_offset(reg); pending = ioread32(ipa->reg_virt + offset); while ((mask = pending & enabled)) { do { @@ -119,8 +120,7 @@ static irqreturn_t ipa_isr_thread(int irq, void *dev_id) dev_dbg(dev, "clearing disabled IPA interrupts 0x%08x\n", pending); reg = ipa_reg(ipa, IPA_IRQ_CLR); - offset = ipa_reg_offset(reg); - iowrite32(pending, ipa->reg_virt + offset); + iowrite32(pending, ipa->reg_virt + reg_offset(reg)); } out_power_put: pm_runtime_mark_last_busy(dev); @@ -131,9 +131,9 @@ out_power_put: static void ipa_interrupt_enabled_update(struct ipa *ipa) { - const struct ipa_reg *reg = ipa_reg(ipa, IPA_IRQ_EN); + const struct reg *reg = ipa_reg(ipa, IPA_IRQ_EN); - iowrite32(ipa->interrupt->enabled, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(ipa->interrupt->enabled, ipa->reg_virt + reg_offset(reg)); } /* Enable an IPA interrupt type */ @@ -169,7 +169,7 @@ static void ipa_interrupt_suspend_control(struct ipa_interrupt *interrupt, struct ipa *ipa = interrupt->ipa; u32 mask = BIT(endpoint_id % 32); u32 unit = endpoint_id / 32; - const struct ipa_reg *reg; + const struct reg *reg; u32 offset; u32 val; @@ -180,7 +180,7 @@ static void ipa_interrupt_suspend_control(struct ipa_interrupt *interrupt, return; reg = ipa_reg(ipa, IRQ_SUSPEND_EN); - offset = ipa_reg_n_offset(reg, unit); + offset = reg_n_offset(reg, unit); val = ioread32(ipa->reg_virt + offset); if (enable) @@ -214,18 +214,18 @@ void ipa_interrupt_suspend_clear_all(struct ipa_interrupt *interrupt) unit_count = roundup(ipa->endpoint_count, 32); for (unit = 0; unit < unit_count; unit++) { - const struct ipa_reg *reg; + const struct reg *reg; u32 val; reg = ipa_reg(ipa, IRQ_SUSPEND_INFO); - val = ioread32(ipa->reg_virt + ipa_reg_n_offset(reg, unit)); + val = ioread32(ipa->reg_virt + reg_n_offset(reg, unit)); /* SUSPEND interrupt status isn't cleared on IPA version 3.0 */ if (ipa->version == IPA_VERSION_3_0) continue; reg = ipa_reg(ipa, IRQ_SUSPEND_CLR); - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, unit)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, unit)); } } @@ -240,7 +240,7 @@ struct ipa_interrupt *ipa_interrupt_config(struct ipa *ipa) { struct device *dev = &ipa->pdev->dev; struct ipa_interrupt *interrupt; - const struct ipa_reg *reg; + const struct reg *reg; unsigned int irq; int ret; @@ -260,7 +260,7 @@ struct ipa_interrupt *ipa_interrupt_config(struct ipa *ipa) /* Start with all IPA interrupts disabled */ reg = ipa_reg(ipa, IPA_IRQ_EN); - iowrite32(0, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(0, ipa->reg_virt + reg_offset(reg)); ret = request_threaded_irq(irq, NULL, ipa_isr_thread, IRQF_ONESHOT, "ipa", interrupt); @@ -269,9 +269,9 @@ struct ipa_interrupt *ipa_interrupt_config(struct ipa *ipa) goto err_kfree; } - ret = enable_irq_wake(irq); + ret = dev_pm_set_wake_irq(dev, irq); if (ret) { - dev_err(dev, "error %d enabling wakeup for \"ipa\" IRQ\n", ret); + dev_err(dev, "error %d registering \"ipa\" IRQ as wakeirq\n", ret); goto err_free_irq; } @@ -289,11 +289,8 @@ err_kfree: void ipa_interrupt_deconfig(struct ipa_interrupt *interrupt) { struct device *dev = &interrupt->ipa->pdev->dev; - int ret; - ret = disable_irq_wake(interrupt->irq); - if (ret) - dev_err(dev, "error %d disabling \"ipa\" IRQ wakeup\n", ret); + dev_pm_clear_wake_irq(dev); free_irq(interrupt->irq, interrupt); kfree(interrupt); } diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c index 4fb92f771974..6cb7bf96a626 100644 --- a/drivers/net/ipa/ipa_main.c +++ b/drivers/net/ipa/ipa_main.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2012-2018, The Linux Foundation. All rights reserved. - * Copyright (C) 2018-2022 Linaro Ltd. + * Copyright (C) 2018-2023 Linaro Ltd. */ #include <linux/types.h> @@ -203,7 +203,7 @@ static void ipa_teardown(struct ipa *ipa) static void ipa_hardware_config_bcr(struct ipa *ipa, const struct ipa_data *data) { - const struct ipa_reg *reg; + const struct reg *reg; u32 val; /* IPA v4.5+ has no backward compatibility register */ @@ -212,13 +212,13 @@ ipa_hardware_config_bcr(struct ipa *ipa, const struct ipa_data *data) reg = ipa_reg(ipa, IPA_BCR); val = data->backward_compat; - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); } static void ipa_hardware_config_tx(struct ipa *ipa) { enum ipa_version version = ipa->version; - const struct ipa_reg *reg; + const struct reg *reg; u32 offset; u32 val; @@ -227,11 +227,11 @@ static void ipa_hardware_config_tx(struct ipa *ipa) /* Disable PA mask to allow HOLB drop */ reg = ipa_reg(ipa, IPA_TX_CFG); - offset = ipa_reg_offset(reg); + offset = reg_offset(reg); val = ioread32(ipa->reg_virt + offset); - val &= ~ipa_reg_bit(reg, PA_MASK_EN); + val &= ~reg_bit(reg, PA_MASK_EN); iowrite32(val, ipa->reg_virt + offset); } @@ -239,7 +239,7 @@ static void ipa_hardware_config_tx(struct ipa *ipa) static void ipa_hardware_config_clkon(struct ipa *ipa) { enum ipa_version version = ipa->version; - const struct ipa_reg *reg; + const struct reg *reg; u32 val; if (version >= IPA_VERSION_4_5) @@ -252,20 +252,20 @@ static void ipa_hardware_config_clkon(struct ipa *ipa) reg = ipa_reg(ipa, CLKON_CFG); if (version == IPA_VERSION_3_1) { /* Disable MISC clock gating */ - val = ipa_reg_bit(reg, CLKON_MISC); + val = reg_bit(reg, CLKON_MISC); } else { /* IPA v4.0+ */ /* Enable open global clocks in the CLKON configuration */ - val = ipa_reg_bit(reg, CLKON_GLOBAL); - val |= ipa_reg_bit(reg, GLOBAL_2X_CLK); + val = reg_bit(reg, CLKON_GLOBAL); + val |= reg_bit(reg, GLOBAL_2X_CLK); } - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); } /* Configure bus access behavior for IPA components */ static void ipa_hardware_config_comp(struct ipa *ipa) { - const struct ipa_reg *reg; + const struct reg *reg; u32 offset; u32 val; @@ -274,21 +274,22 @@ static void ipa_hardware_config_comp(struct ipa *ipa) return; reg = ipa_reg(ipa, COMP_CFG); - offset = ipa_reg_offset(reg); + offset = reg_offset(reg); + val = ioread32(ipa->reg_virt + offset); if (ipa->version == IPA_VERSION_4_0) { - val &= ~ipa_reg_bit(reg, IPA_QMB_SELECT_CONS_EN); - val &= ~ipa_reg_bit(reg, IPA_QMB_SELECT_PROD_EN); - val &= ~ipa_reg_bit(reg, IPA_QMB_SELECT_GLOBAL_EN); + val &= ~reg_bit(reg, IPA_QMB_SELECT_CONS_EN); + val &= ~reg_bit(reg, IPA_QMB_SELECT_PROD_EN); + val &= ~reg_bit(reg, IPA_QMB_SELECT_GLOBAL_EN); } else if (ipa->version < IPA_VERSION_4_5) { - val |= ipa_reg_bit(reg, GSI_MULTI_AXI_MASTERS_DIS); + val |= reg_bit(reg, GSI_MULTI_AXI_MASTERS_DIS); } else { /* For IPA v4.5 FULL_FLUSH_WAIT_RS_CLOSURE_EN is 0 */ } - val |= ipa_reg_bit(reg, GSI_MULTI_INORDER_RD_DIS); - val |= ipa_reg_bit(reg, GSI_MULTI_INORDER_WR_DIS); + val |= reg_bit(reg, GSI_MULTI_INORDER_RD_DIS); + val |= reg_bit(reg, GSI_MULTI_INORDER_WR_DIS); iowrite32(val, ipa->reg_virt + offset); } @@ -299,7 +300,7 @@ ipa_hardware_config_qsb(struct ipa *ipa, const struct ipa_data *data) { const struct ipa_qsb_data *data0; const struct ipa_qsb_data *data1; - const struct ipa_reg *reg; + const struct reg *reg; u32 val; /* QMB 0 represents DDR; QMB 1 (if present) represents PCIe */ @@ -310,29 +311,27 @@ ipa_hardware_config_qsb(struct ipa *ipa, const struct ipa_data *data) /* Max outstanding write accesses for QSB masters */ reg = ipa_reg(ipa, QSB_MAX_WRITES); - val = ipa_reg_encode(reg, GEN_QMB_0_MAX_WRITES, data0->max_writes); + val = reg_encode(reg, GEN_QMB_0_MAX_WRITES, data0->max_writes); if (data->qsb_count > 1) - val |= ipa_reg_encode(reg, GEN_QMB_1_MAX_WRITES, - data1->max_writes); + val |= reg_encode(reg, GEN_QMB_1_MAX_WRITES, data1->max_writes); - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); /* Max outstanding read accesses for QSB masters */ reg = ipa_reg(ipa, QSB_MAX_READS); - val = ipa_reg_encode(reg, GEN_QMB_0_MAX_READS, data0->max_reads); + val = reg_encode(reg, GEN_QMB_0_MAX_READS, data0->max_reads); if (ipa->version >= IPA_VERSION_4_0) - val |= ipa_reg_encode(reg, GEN_QMB_0_MAX_READS_BEATS, - data0->max_reads_beats); + val |= reg_encode(reg, GEN_QMB_0_MAX_READS_BEATS, + data0->max_reads_beats); if (data->qsb_count > 1) { - val = ipa_reg_encode(reg, GEN_QMB_1_MAX_READS, - data1->max_reads); + val = reg_encode(reg, GEN_QMB_1_MAX_READS, data1->max_reads); if (ipa->version >= IPA_VERSION_4_0) - val |= ipa_reg_encode(reg, GEN_QMB_1_MAX_READS_BEATS, - data1->max_reads_beats); + val |= reg_encode(reg, GEN_QMB_1_MAX_READS_BEATS, + data1->max_reads_beats); } - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); } /* The internal inactivity timer clock is used for the aggregation timer */ @@ -368,41 +367,47 @@ static __always_inline u32 ipa_aggr_granularity_val(u32 usec) */ static void ipa_qtime_config(struct ipa *ipa) { - const struct ipa_reg *reg; + const struct reg *reg; u32 offset; u32 val; /* Timer clock divider must be disabled when we change the rate */ reg = ipa_reg(ipa, TIMERS_XO_CLK_DIV_CFG); - iowrite32(0, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(0, ipa->reg_virt + reg_offset(reg)); reg = ipa_reg(ipa, QTIME_TIMESTAMP_CFG); /* Set DPL time stamp resolution to use Qtime (instead of 1 msec) */ - val = ipa_reg_encode(reg, DPL_TIMESTAMP_LSB, DPL_TIMESTAMP_SHIFT); - val |= ipa_reg_bit(reg, DPL_TIMESTAMP_SEL); + val = reg_encode(reg, DPL_TIMESTAMP_LSB, DPL_TIMESTAMP_SHIFT); + val |= reg_bit(reg, DPL_TIMESTAMP_SEL); /* Configure tag and NAT Qtime timestamp resolution as well */ - val = ipa_reg_encode(reg, TAG_TIMESTAMP_LSB, TAG_TIMESTAMP_SHIFT); - val = ipa_reg_encode(reg, NAT_TIMESTAMP_LSB, NAT_TIMESTAMP_SHIFT); + val = reg_encode(reg, TAG_TIMESTAMP_LSB, TAG_TIMESTAMP_SHIFT); + val = reg_encode(reg, NAT_TIMESTAMP_LSB, NAT_TIMESTAMP_SHIFT); - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); /* Set granularity of pulse generators used for other timers */ reg = ipa_reg(ipa, TIMERS_PULSE_GRAN_CFG); - val = ipa_reg_encode(reg, PULSE_GRAN_0, IPA_GRAN_100_US); - val |= ipa_reg_encode(reg, PULSE_GRAN_1, IPA_GRAN_1_MS); - val |= ipa_reg_encode(reg, PULSE_GRAN_2, IPA_GRAN_1_MS); + val = reg_encode(reg, PULSE_GRAN_0, IPA_GRAN_100_US); + val |= reg_encode(reg, PULSE_GRAN_1, IPA_GRAN_1_MS); + if (ipa->version >= IPA_VERSION_5_0) { + val |= reg_encode(reg, PULSE_GRAN_2, IPA_GRAN_10_MS); + val |= reg_encode(reg, PULSE_GRAN_3, IPA_GRAN_10_MS); + } else { + val |= reg_encode(reg, PULSE_GRAN_2, IPA_GRAN_1_MS); + } - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); /* Actual divider is 1 more than value supplied here */ reg = ipa_reg(ipa, TIMERS_XO_CLK_DIV_CFG); - offset = ipa_reg_offset(reg); - val = ipa_reg_encode(reg, DIV_VALUE, IPA_XO_CLOCK_DIVIDER - 1); + offset = reg_offset(reg); + + val = reg_encode(reg, DIV_VALUE, IPA_XO_CLOCK_DIVIDER - 1); iowrite32(val, ipa->reg_virt + offset); /* Divider value is set; re-enable the common timer clock divider */ - val |= ipa_reg_bit(reg, DIV_ENABLE); + val |= reg_bit(reg, DIV_ENABLE); iowrite32(val, ipa->reg_virt + offset); } @@ -411,13 +416,13 @@ static void ipa_qtime_config(struct ipa *ipa) static void ipa_hardware_config_counter(struct ipa *ipa) { u32 granularity = ipa_aggr_granularity_val(IPA_AGGR_GRANULARITY); - const struct ipa_reg *reg; + const struct reg *reg; u32 val; reg = ipa_reg(ipa, COUNTER_CFG); /* If defined, EOT_COAL_GRANULARITY is 0 */ - val = ipa_reg_encode(reg, AGGR_GRANULARITY, granularity); - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + val = reg_encode(reg, AGGR_GRANULARITY, granularity); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); } static void ipa_hardware_config_timing(struct ipa *ipa) @@ -430,8 +435,13 @@ static void ipa_hardware_config_timing(struct ipa *ipa) static void ipa_hardware_config_hashing(struct ipa *ipa) { - const struct ipa_reg *reg; + const struct reg *reg; + /* Other than IPA v4.2, all versions enable "hashing". Starting + * with IPA v5.0, the filter and router tables are implemented + * differently, but the default configuration enables this feature + * (now referred to as "cacheing"), so there's nothing to do here. + */ if (ipa->version != IPA_VERSION_4_2) return; @@ -441,26 +451,26 @@ static void ipa_hardware_config_hashing(struct ipa *ipa) /* IPV6_ROUTER_HASH, IPV6_FILTER_HASH, IPV4_ROUTER_HASH, * IPV4_FILTER_HASH are all zero. */ - iowrite32(0, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(0, ipa->reg_virt + reg_offset(reg)); } static void ipa_idle_indication_cfg(struct ipa *ipa, u32 enter_idle_debounce_thresh, bool const_non_idle_enable) { - const struct ipa_reg *reg; + const struct reg *reg; u32 val; if (ipa->version < IPA_VERSION_3_5_1) return; reg = ipa_reg(ipa, IDLE_INDICATION_CFG); - val = ipa_reg_encode(reg, ENTER_IDLE_DEBOUNCE_THRESH, - enter_idle_debounce_thresh); + val = reg_encode(reg, ENTER_IDLE_DEBOUNCE_THRESH, + enter_idle_debounce_thresh); if (const_non_idle_enable) - val |= ipa_reg_bit(reg, CONST_NON_IDLE_ENABLE); + val |= reg_bit(reg, CONST_NON_IDLE_ENABLE); - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); } /** diff --git a/drivers/net/ipa/ipa_mem.c b/drivers/net/ipa/ipa_mem.c index 9ec5af323f73..85096d1efe5b 100644 --- a/drivers/net/ipa/ipa_mem.c +++ b/drivers/net/ipa/ipa_mem.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2012-2018, The Linux Foundation. All rights reserved. - * Copyright (C) 2019-2022 Linaro Ltd. + * Copyright (C) 2019-2023 Linaro Ltd. */ #include <linux/types.h> @@ -75,7 +75,7 @@ ipa_mem_zero_region_add(struct gsi_trans *trans, enum ipa_mem_id mem_id) int ipa_mem_setup(struct ipa *ipa) { dma_addr_t addr = ipa->zero_addr; - const struct ipa_reg *reg; + const struct reg *reg; const struct ipa_mem *mem; struct gsi_trans *trans; u32 offset; @@ -115,8 +115,8 @@ int ipa_mem_setup(struct ipa *ipa) offset = ipa->mem_offset + mem->offset; reg = ipa_reg(ipa, LOCAL_PKT_PROC_CNTXT); - val = ipa_reg_encode(reg, IPA_BASE_ADDR, offset); - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + val = reg_encode(reg, IPA_BASE_ADDR, offset); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); return 0; } @@ -163,6 +163,12 @@ static bool ipa_mem_id_valid(struct ipa *ipa, enum ipa_mem_id mem_id) return false; break; + case IPA_MEM_AP_V4_FILTER: + case IPA_MEM_AP_V6_FILTER: + if (version != IPA_VERSION_5_0) + return false; + break; + case IPA_MEM_NAT_TABLE: case IPA_MEM_STATS_FILTER_ROUTE: if (version < IPA_VERSION_4_5) @@ -312,8 +318,8 @@ static bool ipa_mem_size_valid(struct ipa *ipa) int ipa_mem_config(struct ipa *ipa) { struct device *dev = &ipa->pdev->dev; - const struct ipa_reg *reg; const struct ipa_mem *mem; + const struct reg *reg; dma_addr_t addr; u32 mem_size; void *virt; @@ -322,13 +328,13 @@ int ipa_mem_config(struct ipa *ipa) /* Check the advertised location and size of the shared memory area */ reg = ipa_reg(ipa, SHARED_MEM_SIZE); - val = ioread32(ipa->reg_virt + ipa_reg_offset(reg)); + val = ioread32(ipa->reg_virt + reg_offset(reg)); /* The fields in the register are in 8 byte units */ - ipa->mem_offset = 8 * ipa_reg_decode(reg, MEM_BADDR, val); + ipa->mem_offset = 8 * reg_decode(reg, MEM_BADDR, val); /* Make sure the end is within the region's mapped space */ - mem_size = 8 * ipa_reg_decode(reg, MEM_SIZE, val); + mem_size = 8 * reg_decode(reg, MEM_SIZE, val); /* If the sizes don't match, issue a warning */ if (ipa->mem_offset + mem_size < ipa->mem_size) { diff --git a/drivers/net/ipa/ipa_mem.h b/drivers/net/ipa/ipa_mem.h index 570bfdd99bff..868e9c20e8c4 100644 --- a/drivers/net/ipa/ipa_mem.h +++ b/drivers/net/ipa/ipa_mem.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2012-2018, The Linux Foundation. All rights reserved. - * Copyright (C) 2019-2021 Linaro Ltd. + * Copyright (C) 2019-2023 Linaro Ltd. */ #ifndef _IPA_MEM_H_ #define _IPA_MEM_H_ @@ -62,13 +62,15 @@ enum ipa_mem_id { IPA_MEM_PDN_CONFIG, /* 0/2 canaries (IPA v4.0+) */ IPA_MEM_STATS_QUOTA_MODEM, /* 2/4 canaries (IPA v4.0+) */ IPA_MEM_STATS_QUOTA_AP, /* 0 canaries, optional (IPA v4.0+) */ - IPA_MEM_STATS_TETHERING, /* 0 canaries (IPA v4.0+) */ + IPA_MEM_STATS_TETHERING, /* 0 canaries, optional (IPA v4.0+) */ IPA_MEM_STATS_DROP, /* 0 canaries, optional (IPA v4.0+) */ - /* The next 5 filter and route statistics regions are optional */ + /* The next 7 filter and route statistics regions are optional */ IPA_MEM_STATS_V4_FILTER, /* 0 canaries (IPA v4.0-v4.2) */ IPA_MEM_STATS_V6_FILTER, /* 0 canaries (IPA v4.0-v4.2) */ IPA_MEM_STATS_V4_ROUTE, /* 0 canaries (IPA v4.0-v4.2) */ IPA_MEM_STATS_V6_ROUTE, /* 0 canaries (IPA v4.0-v4.2) */ + IPA_MEM_AP_V4_FILTER, /* 2 canaries (IPA v5.0) */ + IPA_MEM_AP_V6_FILTER, /* 0 canaries (IPA v5.0) */ IPA_MEM_STATS_FILTER_ROUTE, /* 0 canaries (IPA v4.5+) */ IPA_MEM_NAT_TABLE, /* 4 canaries, optional (IPA v4.5+) */ IPA_MEM_END_MARKER, /* 1 canary (not a real region) */ diff --git a/drivers/net/ipa/ipa_reg.c b/drivers/net/ipa/ipa_reg.c index ddd529153e15..735fa6591609 100644 --- a/drivers/net/ipa/ipa_reg.c +++ b/drivers/net/ipa/ipa_reg.c @@ -9,73 +9,96 @@ #include "ipa.h" #include "ipa_reg.h" -/* Is this register valid and defined for the current IPA version? */ -static bool ipa_reg_valid(struct ipa *ipa, enum ipa_reg_id reg_id) +/* Is this register ID valid for the current IPA version? */ +static bool ipa_reg_id_valid(struct ipa *ipa, enum ipa_reg_id reg_id) { enum ipa_version version = ipa->version; - bool valid; - - /* Check for bogus (out of range) register IDs */ - if ((u32)reg_id >= ipa->regs->reg_count) - return false; switch (reg_id) { case IPA_BCR: case COUNTER_CFG: - valid = version < IPA_VERSION_4_5; - break; + return version < IPA_VERSION_4_5; case IPA_TX_CFG: case FLAVOR_0: case IDLE_INDICATION_CFG: - valid = version >= IPA_VERSION_3_5; - break; + return version >= IPA_VERSION_3_5; case QTIME_TIMESTAMP_CFG: case TIMERS_XO_CLK_DIV_CFG: case TIMERS_PULSE_GRAN_CFG: - valid = version >= IPA_VERSION_4_5; - break; + return version >= IPA_VERSION_4_5; case SRC_RSRC_GRP_45_RSRC_TYPE: case DST_RSRC_GRP_45_RSRC_TYPE: - valid = version <= IPA_VERSION_3_1 || - version == IPA_VERSION_4_5; - break; + return version <= IPA_VERSION_3_1 || + version == IPA_VERSION_4_5; case SRC_RSRC_GRP_67_RSRC_TYPE: case DST_RSRC_GRP_67_RSRC_TYPE: - valid = version <= IPA_VERSION_3_1; - break; + return version <= IPA_VERSION_3_1; case ENDP_FILTER_ROUTER_HSH_CFG: - valid = version != IPA_VERSION_4_2; - break; + return version != IPA_VERSION_4_2; case IRQ_SUSPEND_EN: case IRQ_SUSPEND_CLR: - valid = version >= IPA_VERSION_3_1; - break; + return version >= IPA_VERSION_3_1; + + case COMP_CFG: + case CLKON_CFG: + case ROUTE: + case SHARED_MEM_SIZE: + case QSB_MAX_WRITES: + case QSB_MAX_READS: + case FILT_ROUT_HASH_EN: + case FILT_ROUT_CACHE_CFG: + case FILT_ROUT_HASH_FLUSH: + case FILT_ROUT_CACHE_FLUSH: + case STATE_AGGR_ACTIVE: + case LOCAL_PKT_PROC_CNTXT: + case AGGR_FORCE_CLOSE: + case SRC_RSRC_GRP_01_RSRC_TYPE: + case SRC_RSRC_GRP_23_RSRC_TYPE: + case DST_RSRC_GRP_01_RSRC_TYPE: + case DST_RSRC_GRP_23_RSRC_TYPE: + case ENDP_INIT_CTRL: + case ENDP_INIT_CFG: + case ENDP_INIT_NAT: + case ENDP_INIT_HDR: + case ENDP_INIT_HDR_EXT: + case ENDP_INIT_HDR_METADATA_MASK: + case ENDP_INIT_MODE: + case ENDP_INIT_AGGR: + case ENDP_INIT_HOL_BLOCK_EN: + case ENDP_INIT_HOL_BLOCK_TIMER: + case ENDP_INIT_DEAGGR: + case ENDP_INIT_RSRC_GRP: + case ENDP_INIT_SEQ: + case ENDP_STATUS: + case ENDP_FILTER_CACHE_CFG: + case ENDP_ROUTER_CACHE_CFG: + case IPA_IRQ_STTS: + case IPA_IRQ_EN: + case IPA_IRQ_CLR: + case IPA_IRQ_UC: + case IRQ_SUSPEND_INFO: + return true; /* These should be defined for all versions */ default: - valid = true; /* Others should be defined for all versions */ - break; + return false; } - - /* To be valid, it must be defined */ - - return valid && ipa->regs->reg[reg_id]; } -const struct ipa_reg *ipa_reg(struct ipa *ipa, enum ipa_reg_id reg_id) +const struct reg *ipa_reg(struct ipa *ipa, enum ipa_reg_id reg_id) { - if (WARN_ON(!ipa_reg_valid(ipa, reg_id))) + if (WARN(!ipa_reg_id_valid(ipa, reg_id), "invalid reg %u\n", reg_id)) return NULL; - return ipa->regs->reg[reg_id]; + return reg(ipa->regs, reg_id); } -static const struct ipa_regs *ipa_regs(enum ipa_version version) +static const struct regs *ipa_regs(enum ipa_version version) { switch (version) { case IPA_VERSION_3_1: @@ -100,7 +123,7 @@ static const struct ipa_regs *ipa_regs(enum ipa_version version) int ipa_reg_init(struct ipa *ipa) { struct device *dev = &ipa->pdev->dev; - const struct ipa_regs *regs; + const struct regs *regs; struct resource *res; regs = ipa_regs(ipa->version); @@ -123,7 +146,6 @@ int ipa_reg_init(struct ipa *ipa) dev_err(dev, "unable to remap \"ipa-reg\" memory\n"); return -ENOMEM; } - ipa->reg_addr = res->start; ipa->regs = regs; return 0; diff --git a/drivers/net/ipa/ipa_reg.h b/drivers/net/ipa/ipa_reg.h index b1a3c2c7e167..28aa1351dd48 100644 --- a/drivers/net/ipa/ipa_reg.h +++ b/drivers/net/ipa/ipa_reg.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2012-2018, The Linux Foundation. All rights reserved. - * Copyright (C) 2018-2022 Linaro Ltd. + * Copyright (C) 2018-2023 Linaro Ltd. */ #ifndef _IPA_REG_H_ #define _IPA_REG_H_ @@ -10,6 +10,7 @@ #include <linux/bug.h> #include "ipa_version.h" +#include "reg.h" struct ipa; @@ -35,7 +36,7 @@ struct ipa; * by register ID. Each entry in the array specifies the base offset and * (for parameterized registers) a non-zero stride value. Not all versions * of IPA define all registers. The offset for a register is returned by - * ipa_reg_offset() when the register's ipa_reg structure is supplied; + * reg_offset() when the register's ipa_reg structure is supplied; * zero is returned for an undefined register (this should never happen). * * Some registers encode multiple fields within them. Each field in @@ -44,9 +45,9 @@ struct ipa; * an array of field masks, indexed by field ID. Two functions are * used to access register fields; both take an ipa_reg structure as * argument. To encode a value to be represented in a register field, - * the value and field ID are passed to ipa_reg_encode(). To extract + * the value and field ID are passed to reg_encode(). To extract * a value encoded in a register field, the field ID is passed to - * ipa_reg_decode(). In addition, for single-bit fields, ipa_reg_bit() + * reg_decode(). In addition, for single-bit fields, reg_bit() * can be used to either encode the bit value, or to generate a mask * used to extract the bit value. */ @@ -59,8 +60,10 @@ enum ipa_reg_id { SHARED_MEM_SIZE, QSB_MAX_WRITES, QSB_MAX_READS, - FILT_ROUT_HASH_EN, - FILT_ROUT_HASH_FLUSH, + FILT_ROUT_HASH_EN, /* Not IPA v5.0+ */ + FILT_ROUT_CACHE_CFG, /* IPA v5.0+ */ + FILT_ROUT_HASH_FLUSH, /* Not IPA v5.0+ */ + FILT_ROUT_CACHE_FLUSH, /* IPA v5.0+ */ STATE_AGGR_ACTIVE, IPA_BCR, /* Not IPA v4.5+ */ LOCAL_PKT_PROC_CNTXT, @@ -95,7 +98,9 @@ enum ipa_reg_id { ENDP_INIT_SEQ, /* TX only */ ENDP_STATUS, ENDP_FILTER_ROUTER_HSH_CFG, /* Not IPA v4.2 */ - /* The IRQ registers are only used for GSI_EE_AP */ + ENDP_FILTER_CACHE_CFG, /* IPA v5.0+ */ + ENDP_ROUTER_CACHE_CFG, /* IPA v5.0+ */ + /* The IRQ registers that follow are only used for GSI_EE_AP */ IPA_IRQ_STTS, IPA_IRQ_EN, IPA_IRQ_CLR, @@ -106,56 +111,6 @@ enum ipa_reg_id { IPA_REG_ID_COUNT, /* Last; not an ID */ }; -/** - * struct ipa_reg - An IPA register descriptor - * @offset: Register offset relative to base of the "ipa-reg" memory - * @stride: Distance between two instances, if parameterized - * @fcount: Number of entries in the @fmask array - * @fmask: Array of mask values defining position and width of fields - * @name: Upper-case name of the IPA register - */ -struct ipa_reg { - u32 offset; - u32 stride; - u32 fcount; - const u32 *fmask; /* BIT(nr) or GENMASK(h, l) */ - const char *name; -}; - -/* Helper macro for defining "simple" (non-parameterized) registers */ -#define IPA_REG(__NAME, __reg_id, __offset) \ - IPA_REG_STRIDE(__NAME, __reg_id, __offset, 0) - -/* Helper macro for defining parameterized registers, specifying stride */ -#define IPA_REG_STRIDE(__NAME, __reg_id, __offset, __stride) \ - static const struct ipa_reg ipa_reg_ ## __reg_id = { \ - .name = #__NAME, \ - .offset = __offset, \ - .stride = __stride, \ - } - -#define IPA_REG_FIELDS(__NAME, __name, __offset) \ - IPA_REG_STRIDE_FIELDS(__NAME, __name, __offset, 0) - -#define IPA_REG_STRIDE_FIELDS(__NAME, __name, __offset, __stride) \ - static const struct ipa_reg ipa_reg_ ## __name = { \ - .name = #__NAME, \ - .offset = __offset, \ - .stride = __stride, \ - .fcount = ARRAY_SIZE(ipa_reg_ ## __name ## _fmask), \ - .fmask = ipa_reg_ ## __name ## _fmask, \ - } - -/** - * struct ipa_regs - Description of registers supported by hardware - * @reg_count: Number of registers in the @reg[] array - * @reg: Array of register descriptors - */ -struct ipa_regs { - u32 reg_count; - const struct ipa_reg **reg; -}; - /* COMP_CFG register */ enum ipa_reg_comp_cfg_field_id { COMP_CFG_ENABLE, /* Not IPA v4.0+ */ @@ -251,14 +206,28 @@ enum ipa_reg_qsb_max_reads_field_id { GEN_QMB_1_MAX_READS_BEATS, /* IPA v4.0+ */ }; +/* FILT_ROUT_CACHE_CFG register */ +enum ipa_reg_filt_rout_cache_cfg_field_id { + ROUTER_CACHE_EN, + FILTER_CACHE_EN, + LOW_PRI_HASH_HIT_DISABLE, + LRU_EVICTION_THRESHOLD, +}; + /* FILT_ROUT_HASH_EN and FILT_ROUT_HASH_FLUSH registers */ -enum ipa_reg_rout_hash_field_id { +enum ipa_reg_filt_rout_hash_field_id { IPV6_ROUTER_HASH, IPV6_FILTER_HASH, IPV4_ROUTER_HASH, IPV4_FILTER_HASH, }; +/* FILT_ROUT_CACHE_FLUSH register */ +enum ipa_reg_filt_rout_cache_field_id { + ROUTER_CACHE, + FILTER_CACHE, +}; + /* BCR register */ enum ipa_bcr_compat { BCR_CMDQ_L_LACK_ONE_ENTRY = 0x0, /* Not IPA v4.2+ */ @@ -298,6 +267,7 @@ enum ipa_reg_ipa_tx_cfg_field_id { DUAL_TX_ENABLE, /* v4.5+ */ SSPND_PA_NO_START_STATE, /* v4,2+, not v4.5 */ SSPND_PA_NO_BQ_STATE, /* v4.2 only */ + HOLB_STICKY_DROP_EN, /* v5.0+ */ }; /* FLAVOR_0 register */ @@ -333,6 +303,7 @@ enum ipa_reg_timers_pulse_gran_cfg_field_id { PULSE_GRAN_0, PULSE_GRAN_1, PULSE_GRAN_2, + PULSE_GRAN_3, }; /* Values for IPA_GRAN_x fields of TIMERS_PULSE_GRAN_CFG */ @@ -415,6 +386,8 @@ enum ipa_reg_endp_init_hdr_ext_field_id { HDR_TOTAL_LEN_OR_PAD_OFFSET_MSB, /* v4.5+ */ HDR_OFST_PKT_SIZE_MSB, /* v4.5+ */ HDR_ADDITIONAL_CONST_LEN_MSB, /* v4.5+ */ + HDR_BYTES_TO_REMOVE_VALID, /* v5.0+ */ + HDR_BYTES_TO_REMOVE, /* v5.0+ */ }; /* ENDP_INIT_MODE register */ @@ -573,6 +546,17 @@ enum ipa_reg_endp_filter_router_hsh_cfg_field_id { ROUTER_HASH_MSK_ALL, /* Bitwise OR of the above 6 fields */ }; +/* ENDP_FILTER_CACHE_CFG and ENDP_ROUTER_CACHE_CFG registers */ +enum ipa_reg_endp_cache_cfg_field_id { + CACHE_MSK_SRC_ID, + CACHE_MSK_SRC_IP, + CACHE_MSK_DST_IP, + CACHE_MSK_SRC_PORT, + CACHE_MSK_DST_PORT, + CACHE_MSK_PROTOCOL, + CACHE_MSK_METADATA, +}; + /* IPA_IRQ_STTS, IPA_IRQ_EN, and IPA_IRQ_CLR registers */ /** * enum ipa_irq_id - Bit positions representing type of IPA IRQ @@ -654,79 +638,15 @@ enum ipa_reg_ipa_irq_uc_field_id { UC_INTR, }; -extern const struct ipa_regs ipa_regs_v3_1; -extern const struct ipa_regs ipa_regs_v3_5_1; -extern const struct ipa_regs ipa_regs_v4_2; -extern const struct ipa_regs ipa_regs_v4_5; -extern const struct ipa_regs ipa_regs_v4_7; -extern const struct ipa_regs ipa_regs_v4_9; -extern const struct ipa_regs ipa_regs_v4_11; - -/* Return the field mask for a field in a register */ -static inline u32 ipa_reg_fmask(const struct ipa_reg *reg, u32 field_id) -{ - if (!reg || WARN_ON(field_id >= reg->fcount)) - return 0; - - return reg->fmask[field_id]; -} - -/* Return the mask for a single-bit field in a register */ -static inline u32 ipa_reg_bit(const struct ipa_reg *reg, u32 field_id) -{ - u32 fmask = ipa_reg_fmask(reg, field_id); - - WARN_ON(!is_power_of_2(fmask)); - - return fmask; -} - -/* Encode a value into the given field of a register */ -static inline u32 -ipa_reg_encode(const struct ipa_reg *reg, u32 field_id, u32 val) -{ - u32 fmask = ipa_reg_fmask(reg, field_id); - - if (!fmask) - return 0; - - val <<= __ffs(fmask); - if (WARN_ON(val & ~fmask)) - return 0; - - return val; -} - -/* Given a register value, decode (extract) the value in the given field */ -static inline u32 -ipa_reg_decode(const struct ipa_reg *reg, u32 field_id, u32 val) -{ - u32 fmask = ipa_reg_fmask(reg, field_id); - - return fmask ? (val & fmask) >> __ffs(fmask) : 0; -} - -/* Return the maximum value representable by the given field; always 2^n - 1 */ -static inline u32 ipa_reg_field_max(const struct ipa_reg *reg, u32 field_id) -{ - u32 fmask = ipa_reg_fmask(reg, field_id); - - return fmask ? fmask >> __ffs(fmask) : 0; -} - -const struct ipa_reg *ipa_reg(struct ipa *ipa, enum ipa_reg_id reg_id); - -/* Returns 0 for NULL reg; warning will have already been issued */ -static inline u32 ipa_reg_offset(const struct ipa_reg *reg) -{ - return reg ? reg->offset : 0; -} +extern const struct regs ipa_regs_v3_1; +extern const struct regs ipa_regs_v3_5_1; +extern const struct regs ipa_regs_v4_2; +extern const struct regs ipa_regs_v4_5; +extern const struct regs ipa_regs_v4_7; +extern const struct regs ipa_regs_v4_9; +extern const struct regs ipa_regs_v4_11; -/* Returns 0 for NULL reg; warning will have already been issued */ -static inline u32 ipa_reg_n_offset(const struct ipa_reg *reg, u32 n) -{ - return reg ? reg->offset + n * reg->stride : 0; -} +const struct reg *ipa_reg(struct ipa *ipa, enum ipa_reg_id reg_id); int ipa_reg_init(struct ipa *ipa); void ipa_reg_exit(struct ipa *ipa); diff --git a/drivers/net/ipa/ipa_resource.c b/drivers/net/ipa/ipa_resource.c index a257f0e5e361..82c88a744d10 100644 --- a/drivers/net/ipa/ipa_resource.c +++ b/drivers/net/ipa/ipa_resource.c @@ -70,20 +70,20 @@ static bool ipa_resource_limits_valid(struct ipa *ipa, static void ipa_resource_config_common(struct ipa *ipa, u32 resource_type, - const struct ipa_reg *reg, + const struct reg *reg, const struct ipa_resource_limits *xlimits, const struct ipa_resource_limits *ylimits) { u32 val; - val = ipa_reg_encode(reg, X_MIN_LIM, xlimits->min); - val |= ipa_reg_encode(reg, X_MAX_LIM, xlimits->max); + val = reg_encode(reg, X_MIN_LIM, xlimits->min); + val |= reg_encode(reg, X_MAX_LIM, xlimits->max); if (ylimits) { - val |= ipa_reg_encode(reg, Y_MIN_LIM, ylimits->min); - val |= ipa_reg_encode(reg, Y_MAX_LIM, ylimits->max); + val |= reg_encode(reg, Y_MIN_LIM, ylimits->min); + val |= reg_encode(reg, Y_MAX_LIM, ylimits->max); } - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, resource_type)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, resource_type)); } static void ipa_resource_config_src(struct ipa *ipa, u32 resource_type, @@ -92,7 +92,7 @@ static void ipa_resource_config_src(struct ipa *ipa, u32 resource_type, u32 group_count = data->rsrc_group_src_count; const struct ipa_resource_limits *ylimits; const struct ipa_resource *resource; - const struct ipa_reg *reg; + const struct reg *reg; resource = &data->resource_src[resource_type]; @@ -129,7 +129,7 @@ static void ipa_resource_config_dst(struct ipa *ipa, u32 resource_type, u32 group_count = data->rsrc_group_dst_count; const struct ipa_resource_limits *ylimits; const struct ipa_resource *resource; - const struct ipa_reg *reg; + const struct reg *reg; resource = &data->resource_dst[resource_type]; diff --git a/drivers/net/ipa/ipa_table.c b/drivers/net/ipa/ipa_table.c index b81e27b61354..f0529c31d0b6 100644 --- a/drivers/net/ipa/ipa_table.c +++ b/drivers/net/ipa/ipa_table.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2012-2018, The Linux Foundation. All rights reserved. - * Copyright (C) 2018-2022 Linaro Ltd. + * Copyright (C) 2018-2023 Linaro Ltd. */ #include <linux/types.h> @@ -345,9 +345,8 @@ void ipa_table_reset(struct ipa *ipa, bool modem) int ipa_table_hash_flush(struct ipa *ipa) { - const struct ipa_reg *reg; struct gsi_trans *trans; - u32 offset; + const struct reg *reg; u32 val; if (!ipa_table_hash_support(ipa)) @@ -359,15 +358,22 @@ int ipa_table_hash_flush(struct ipa *ipa) return -EBUSY; } - reg = ipa_reg(ipa, FILT_ROUT_HASH_FLUSH); - offset = ipa_reg_offset(reg); + if (ipa->version < IPA_VERSION_5_0) { + reg = ipa_reg(ipa, FILT_ROUT_HASH_FLUSH); - val = ipa_reg_bit(reg, IPV6_ROUTER_HASH); - val |= ipa_reg_bit(reg, IPV6_FILTER_HASH); - val |= ipa_reg_bit(reg, IPV4_ROUTER_HASH); - val |= ipa_reg_bit(reg, IPV4_FILTER_HASH); + val = reg_bit(reg, IPV6_ROUTER_HASH); + val |= reg_bit(reg, IPV6_FILTER_HASH); + val |= reg_bit(reg, IPV4_ROUTER_HASH); + val |= reg_bit(reg, IPV4_FILTER_HASH); + } else { + reg = ipa_reg(ipa, FILT_ROUT_CACHE_FLUSH); - ipa_cmd_register_write_add(trans, offset, val, val, false); + /* IPA v5.0+ uses a unified cache (both IPv4 and IPv6) */ + val = reg_bit(reg, ROUTER_CACHE); + val |= reg_bit(reg, FILTER_CACHE); + } + + ipa_cmd_register_write_add(trans, reg_offset(reg), val, val, false); gsi_trans_commit_wait(trans); @@ -486,17 +492,26 @@ static void ipa_filter_tuple_zero(struct ipa_endpoint *endpoint) { u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 offset; u32 val; - reg = ipa_reg(ipa, ENDP_FILTER_ROUTER_HSH_CFG); + if (ipa->version < IPA_VERSION_5_0) { + reg = ipa_reg(ipa, ENDP_FILTER_ROUTER_HSH_CFG); + + offset = reg_n_offset(reg, endpoint_id); + val = ioread32(endpoint->ipa->reg_virt + offset); - offset = ipa_reg_n_offset(reg, endpoint_id); - val = ioread32(endpoint->ipa->reg_virt + offset); + /* Zero all filter-related fields, preserving the rest */ + val &= ~reg_fmask(reg, FILTER_HASH_MSK_ALL); + } else { + /* IPA v5.0 separates filter and router cache configuration */ + reg = ipa_reg(ipa, ENDP_FILTER_CACHE_CFG); + offset = reg_n_offset(reg, endpoint_id); - /* Zero all filter-related fields, preserving the rest */ - val &= ~ipa_reg_fmask(reg, FILTER_HASH_MSK_ALL); + /* Zero all filter-related fields */ + val = 0; + } iowrite32(val, endpoint->ipa->reg_virt + offset); } @@ -536,17 +551,26 @@ static bool ipa_route_id_modem(struct ipa *ipa, u32 route_id) */ static void ipa_route_tuple_zero(struct ipa *ipa, u32 route_id) { - const struct ipa_reg *reg; + const struct reg *reg; u32 offset; u32 val; - reg = ipa_reg(ipa, ENDP_FILTER_ROUTER_HSH_CFG); - offset = ipa_reg_n_offset(reg, route_id); + if (ipa->version < IPA_VERSION_5_0) { + reg = ipa_reg(ipa, ENDP_FILTER_ROUTER_HSH_CFG); + offset = reg_n_offset(reg, route_id); - val = ioread32(ipa->reg_virt + offset); + val = ioread32(ipa->reg_virt + offset); - /* Zero all route-related fields, preserving the rest */ - val &= ~ipa_reg_fmask(reg, ROUTER_HASH_MSK_ALL); + /* Zero all route-related fields, preserving the rest */ + val &= ~reg_fmask(reg, ROUTER_HASH_MSK_ALL); + } else { + /* IPA v5.0 separates filter and router cache configuration */ + reg = ipa_reg(ipa, ENDP_ROUTER_CACHE_CFG); + offset = reg_n_offset(reg, route_id); + + /* Zero all route-related fields */ + val = 0; + } iowrite32(val, ipa->reg_virt + offset); } diff --git a/drivers/net/ipa/ipa_uc.c b/drivers/net/ipa/ipa_uc.c index cb8a76a75f21..7eaa0b4ebed9 100644 --- a/drivers/net/ipa/ipa_uc.c +++ b/drivers/net/ipa/ipa_uc.c @@ -231,7 +231,7 @@ void ipa_uc_power(struct ipa *ipa) static void send_uc_command(struct ipa *ipa, u32 command, u32 command_param) { struct ipa_uc_mem_area *shared = ipa_uc_shared(ipa); - const struct ipa_reg *reg; + const struct reg *reg; u32 val; /* Fill in the command data */ @@ -243,9 +243,9 @@ static void send_uc_command(struct ipa *ipa, u32 command, u32 command_param) /* Use an interrupt to tell the microcontroller the command is ready */ reg = ipa_reg(ipa, IPA_IRQ_UC); - val = ipa_reg_bit(reg, UC_INTR); + val = reg_bit(reg, UC_INTR); - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); } /* Tell the microcontroller the AP is shutting down */ diff --git a/drivers/net/ipa/ipa_version.h b/drivers/net/ipa/ipa_version.h index d15821467743..06e75b8ece7e 100644 --- a/drivers/net/ipa/ipa_version.h +++ b/drivers/net/ipa/ipa_version.h @@ -9,7 +9,7 @@ /** * enum ipa_version * @IPA_VERSION_3_0: IPA version 3.0/GSI version 1.0 - * @IPA_VERSION_3_1: IPA version 3.1/GSI version 1.1 + * @IPA_VERSION_3_1: IPA version 3.1/GSI version 1.0 * @IPA_VERSION_3_5: IPA version 3.5/GSI version 1.2 * @IPA_VERSION_3_5_1: IPA version 3.5.1/GSI version 1.3 * @IPA_VERSION_4_0: IPA version 4.0/GSI version 2.0 @@ -20,6 +20,8 @@ * @IPA_VERSION_4_9: IPA version 4.9/GSI version 2.9 * @IPA_VERSION_4_11: IPA version 4.11/GSI version 2.11 (2.1.1) * @IPA_VERSION_5_0: IPA version 5.0/GSI version 3.0 + * @IPA_VERSION_5_1: IPA version 5.1/GSI version 3.0 + * @IPA_VERSION_5_5: IPA version 5.5/GSI version 5.5 * @IPA_VERSION_COUNT: Number of defined IPA versions * * Defines the version of IPA (and GSI) hardware present on the platform. @@ -38,6 +40,8 @@ enum ipa_version { IPA_VERSION_4_9, IPA_VERSION_4_11, IPA_VERSION_5_0, + IPA_VERSION_5_1, + IPA_VERSION_5_5, IPA_VERSION_COUNT, /* Last; not a version */ }; diff --git a/drivers/net/ipa/reg.h b/drivers/net/ipa/reg.h new file mode 100644 index 000000000000..57b457f39b6e --- /dev/null +++ b/drivers/net/ipa/reg.h @@ -0,0 +1,133 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* *Copyright (C) 2022-2023 Linaro Ltd. */ + +#ifndef _REG_H_ +#define _REG_H_ + +#include <linux/types.h> +#include <linux/bits.h> + +/** + * struct reg - A register descriptor + * @offset: Register offset relative to base of register memory + * @stride: Distance between two instances, if parameterized + * @fcount: Number of entries in the @fmask array + * @fmask: Array of mask values defining position and width of fields + * @name: Upper-case name of the register + */ +struct reg { + u32 offset; + u32 stride; + u32 fcount; + const u32 *fmask; /* BIT(nr) or GENMASK(h, l) */ + const char *name; +}; + +/* Helper macro for defining "simple" (non-parameterized) registers */ +#define REG(__NAME, __reg_id, __offset) \ + REG_STRIDE(__NAME, __reg_id, __offset, 0) + +/* Helper macro for defining parameterized registers, specifying stride */ +#define REG_STRIDE(__NAME, __reg_id, __offset, __stride) \ + static const struct reg reg_ ## __reg_id = { \ + .name = #__NAME, \ + .offset = __offset, \ + .stride = __stride, \ + } + +#define REG_FIELDS(__NAME, __name, __offset) \ + REG_STRIDE_FIELDS(__NAME, __name, __offset, 0) + +#define REG_STRIDE_FIELDS(__NAME, __name, __offset, __stride) \ + static const struct reg reg_ ## __name = { \ + .name = #__NAME, \ + .offset = __offset, \ + .stride = __stride, \ + .fcount = ARRAY_SIZE(reg_ ## __name ## _fmask), \ + .fmask = reg_ ## __name ## _fmask, \ + } + +/** + * struct regs - Description of registers supported by hardware + * @reg_count: Number of registers in the @reg[] array + * @reg: Array of register descriptors + */ +struct regs { + u32 reg_count; + const struct reg **reg; +}; + +static inline const struct reg *reg(const struct regs *regs, u32 reg_id) +{ + if (WARN(reg_id >= regs->reg_count, + "reg out of range (%u > %u)\n", reg_id, regs->reg_count - 1)) + return NULL; + + return regs->reg[reg_id]; +} + +/* Return the field mask for a field in a register, or 0 on error */ +static inline u32 reg_fmask(const struct reg *reg, u32 field_id) +{ + if (!reg || WARN_ON(field_id >= reg->fcount)) + return 0; + + return reg->fmask[field_id]; +} + +/* Return the mask for a single-bit field in a register, or 0 on error */ +static inline u32 reg_bit(const struct reg *reg, u32 field_id) +{ + u32 fmask = reg_fmask(reg, field_id); + + if (WARN_ON(!is_power_of_2(fmask))) + return 0; + + return fmask; +} + +/* Return the maximum value representable by the given field; always 2^n - 1 */ +static inline u32 reg_field_max(const struct reg *reg, u32 field_id) +{ + u32 fmask = reg_fmask(reg, field_id); + + return fmask ? fmask >> __ffs(fmask) : 0; +} + +/* Encode a value into the given field of a register */ +static inline u32 reg_encode(const struct reg *reg, u32 field_id, u32 val) +{ + u32 fmask = reg_fmask(reg, field_id); + + if (!fmask) + return 0; + + val <<= __ffs(fmask); + if (WARN_ON(val & ~fmask)) + return 0; + + return val; +} + +/* Given a register value, decode (extract) the value in the given field */ +static inline u32 reg_decode(const struct reg *reg, u32 field_id, u32 val) +{ + u32 fmask = reg_fmask(reg, field_id); + + return fmask ? (val & fmask) >> __ffs(fmask) : 0; +} + +/* Returns 0 for NULL reg; warning should have already been issued */ +static inline u32 reg_offset(const struct reg *reg) +{ + return reg ? reg->offset : 0; +} + +/* Returns 0 for NULL reg; warning should have already been issued */ +static inline u32 reg_n_offset(const struct reg *reg, u32 n) +{ + return reg ? reg->offset + n * reg->stride : 0; +} + +#endif /* _REG_H_ */ diff --git a/drivers/net/ipa/reg/ipa_reg-v3.1.c b/drivers/net/ipa/reg/ipa_reg-v3.1.c index 677ece3bce9e..648dbfe1fce3 100644 --- a/drivers/net/ipa/reg/ipa_reg-v3.1.c +++ b/drivers/net/ipa/reg/ipa_reg-v3.1.c @@ -7,7 +7,7 @@ #include "../ipa.h" #include "../ipa_reg.h" -static const u32 ipa_reg_comp_cfg_fmask[] = { +static const u32 reg_comp_cfg_fmask[] = { [COMP_CFG_ENABLE] = BIT(0), [GSI_SNOC_BYPASS_DIS] = BIT(1), [GEN_QMB_0_SNOC_BYPASS_DIS] = BIT(2), @@ -16,9 +16,9 @@ static const u32 ipa_reg_comp_cfg_fmask[] = { /* Bits 5-31 reserved */ }; -IPA_REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); +REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); -static const u32 ipa_reg_clkon_cfg_fmask[] = { +static const u32 reg_clkon_cfg_fmask[] = { [CLKON_RX] = BIT(0), [CLKON_PROC] = BIT(1), [TX_WRAPPER] = BIT(2), @@ -39,9 +39,9 @@ static const u32 ipa_reg_clkon_cfg_fmask[] = { /* Bits 17-31 reserved */ }; -IPA_REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); +REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); -static const u32 ipa_reg_route_fmask[] = { +static const u32 reg_route_fmask[] = { [ROUTE_DIS] = BIT(0), [ROUTE_DEF_PIPE] = GENMASK(5, 1), [ROUTE_DEF_HDR_TABLE] = BIT(6), @@ -52,31 +52,31 @@ static const u32 ipa_reg_route_fmask[] = { /* Bits 25-31 reserved */ }; -IPA_REG_FIELDS(ROUTE, route, 0x00000048); +REG_FIELDS(ROUTE, route, 0x00000048); -static const u32 ipa_reg_shared_mem_size_fmask[] = { +static const u32 reg_shared_mem_size_fmask[] = { [MEM_SIZE] = GENMASK(15, 0), [MEM_BADDR] = GENMASK(31, 16), }; -IPA_REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); +REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); -static const u32 ipa_reg_qsb_max_writes_fmask[] = { +static const u32 reg_qsb_max_writes_fmask[] = { [GEN_QMB_0_MAX_WRITES] = GENMASK(3, 0), [GEN_QMB_1_MAX_WRITES] = GENMASK(7, 4), /* Bits 8-31 reserved */ }; -IPA_REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); +REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); -static const u32 ipa_reg_qsb_max_reads_fmask[] = { +static const u32 reg_qsb_max_reads_fmask[] = { [GEN_QMB_0_MAX_READS] = GENMASK(3, 0), [GEN_QMB_1_MAX_READS] = GENMASK(7, 4), }; -IPA_REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); +REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); -static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { +static const u32 reg_filt_rout_hash_en_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -87,9 +87,9 @@ static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x000008c); +REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x000008c); -static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { +static const u32 reg_filt_rout_hash_flush_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -100,121 +100,121 @@ static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x0000090); +REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x0000090); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x0000010c, 0x0004); +REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x0000010c, 0x0004); -IPA_REG(IPA_BCR, ipa_bcr, 0x000001d0); +REG(IPA_BCR, ipa_bcr, 0x000001d0); -static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { +static const u32 reg_local_pkt_proc_cntxt_fmask[] = { [IPA_BASE_ADDR] = GENMASK(16, 0), /* Bits 17-31 reserved */ }; /* Offset must be a multiple of 8 */ -IPA_REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); +REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); +REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); -static const u32 ipa_reg_counter_cfg_fmask[] = { +static const u32 reg_counter_cfg_fmask[] = { [EOT_COAL_GRANULARITY] = GENMASK(3, 0), [AGGR_GRANULARITY] = GENMASK(8, 4), /* Bits 5-31 reserved */ }; -IPA_REG_FIELDS(COUNTER_CFG, counter_cfg, 0x000001f0); +REG_FIELDS(COUNTER_CFG, counter_cfg, 0x000001f0); -static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(7, 0), [X_MAX_LIM] = GENMASK(15, 8), [Y_MIN_LIM] = GENMASK(23, 16), [Y_MAX_LIM] = GENMASK(31, 24), }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, - 0x00000400, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, + 0x00000400, 0x0020); -static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(7, 0), [X_MAX_LIM] = GENMASK(15, 8), [Y_MIN_LIM] = GENMASK(23, 16), [Y_MAX_LIM] = GENMASK(31, 24), }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, - 0x00000404, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, + 0x00000404, 0x0020); -static const u32 ipa_reg_src_rsrc_grp_45_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_45_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(7, 0), [X_MAX_LIM] = GENMASK(15, 8), [Y_MIN_LIM] = GENMASK(23, 16), [Y_MAX_LIM] = GENMASK(31, 24), }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_45_RSRC_TYPE, src_rsrc_grp_45_rsrc_type, - 0x00000408, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_45_RSRC_TYPE, src_rsrc_grp_45_rsrc_type, + 0x00000408, 0x0020); -static const u32 ipa_reg_src_rsrc_grp_67_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_67_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(7, 0), [X_MAX_LIM] = GENMASK(15, 8), [Y_MIN_LIM] = GENMASK(23, 16), [Y_MAX_LIM] = GENMASK(31, 24), }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_67_RSRC_TYPE, src_rsrc_grp_67_rsrc_type, - 0x0000040c, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_67_RSRC_TYPE, src_rsrc_grp_67_rsrc_type, + 0x0000040c, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(7, 0), [X_MAX_LIM] = GENMASK(15, 8), [Y_MIN_LIM] = GENMASK(23, 16), [Y_MAX_LIM] = GENMASK(31, 24), }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, - 0x00000500, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, + 0x00000500, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(7, 0), [X_MAX_LIM] = GENMASK(15, 8), [Y_MIN_LIM] = GENMASK(23, 16), [Y_MAX_LIM] = GENMASK(31, 24), }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, - 0x00000504, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, + 0x00000504, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_45_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_45_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(7, 0), [X_MAX_LIM] = GENMASK(15, 8), [Y_MIN_LIM] = GENMASK(23, 16), [Y_MAX_LIM] = GENMASK(31, 24), }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_45_RSRC_TYPE, dst_rsrc_grp_45_rsrc_type, - 0x00000508, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_45_RSRC_TYPE, dst_rsrc_grp_45_rsrc_type, + 0x00000508, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_67_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_67_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(7, 0), [X_MAX_LIM] = GENMASK(15, 8), [Y_MIN_LIM] = GENMASK(23, 16), [Y_MAX_LIM] = GENMASK(31, 24), }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_67_RSRC_TYPE, dst_rsrc_grp_67_rsrc_type, - 0x0000050c, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_67_RSRC_TYPE, dst_rsrc_grp_67_rsrc_type, + 0x0000050c, 0x0020); -static const u32 ipa_reg_endp_init_ctrl_fmask[] = { +static const u32 reg_endp_init_ctrl_fmask[] = { [ENDP_SUSPEND] = BIT(0), [ENDP_DELAY] = BIT(1), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_CTRL, endp_init_ctrl, 0x00000800, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_CTRL, endp_init_ctrl, 0x00000800, 0x0070); -static const u32 ipa_reg_endp_init_cfg_fmask[] = { +static const u32 reg_endp_init_cfg_fmask[] = { [FRAG_OFFLOAD_EN] = BIT(0), [CS_OFFLOAD_EN] = GENMASK(2, 1), [CS_METADATA_HDR_OFFSET] = GENMASK(6, 3), @@ -223,16 +223,16 @@ static const u32 ipa_reg_endp_init_cfg_fmask[] = { /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); -static const u32 ipa_reg_endp_init_nat_fmask[] = { +static const u32 reg_endp_init_nat_fmask[] = { [NAT_EN] = GENMASK(1, 0), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); -static const u32 ipa_reg_endp_init_hdr_fmask[] = { +static const u32 reg_endp_init_hdr_fmask[] = { [HDR_LEN] = GENMASK(5, 0), [HDR_OFST_METADATA_VALID] = BIT(6), [HDR_OFST_METADATA] = GENMASK(12, 7), @@ -245,9 +245,9 @@ static const u32 ipa_reg_endp_init_hdr_fmask[] = { /* Bits 29-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); -static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { +static const u32 reg_endp_init_hdr_ext_fmask[] = { [HDR_ENDIANNESS] = BIT(0), [HDR_TOTAL_LEN_OR_PAD_VALID] = BIT(1), [HDR_TOTAL_LEN_OR_PAD] = BIT(2), @@ -257,12 +257,12 @@ static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { /* Bits 14-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); -IPA_REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, - 0x00000818, 0x0070); +REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, + 0x00000818, 0x0070); -static const u32 ipa_reg_endp_init_mode_fmask[] = { +static const u32 reg_endp_init_mode_fmask[] = { [ENDP_MODE] = GENMASK(2, 0), /* Bit 3 reserved */ [DEST_PIPE_INDEX] = GENMASK(8, 4), @@ -274,9 +274,9 @@ static const u32 ipa_reg_endp_init_mode_fmask[] = { /* Bit 31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); -static const u32 ipa_reg_endp_init_aggr_fmask[] = { +static const u32 reg_endp_init_aggr_fmask[] = { [AGGR_EN] = GENMASK(1, 0), [AGGR_TYPE] = GENMASK(4, 2), [BYTE_LIMIT] = GENMASK(9, 5), @@ -289,25 +289,25 @@ static const u32 ipa_reg_endp_init_aggr_fmask[] = { /* Bits 25-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_en_fmask[] = { +static const u32 reg_endp_init_hol_block_en_fmask[] = { [HOL_BLOCK_EN] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, - 0x0000082c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, + 0x0000082c, 0x0070); /* Entire register is a tick count */ -static const u32 ipa_reg_endp_init_hol_block_timer_fmask[] = { +static const u32 reg_endp_init_hol_block_timer_fmask[] = { [TIMER_BASE_VALUE] = GENMASK(31, 0), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, - 0x00000830, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, + 0x00000830, 0x0070); -static const u32 ipa_reg_endp_init_deaggr_fmask[] = { +static const u32 reg_endp_init_deaggr_fmask[] = { [DEAGGR_HDR_LEN] = GENMASK(5, 0), [SYSPIPE_ERR_DETECTION] = BIT(6), [PACKET_OFFSET_VALID] = BIT(7), @@ -317,25 +317,24 @@ static const u32 ipa_reg_endp_init_deaggr_fmask[] = { [MAX_PACKET_LEN] = GENMASK(31, 16), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); -static const u32 ipa_reg_endp_init_rsrc_grp_fmask[] = { +static const u32 reg_endp_init_rsrc_grp_fmask[] = { [ENDP_RSRC_GRP] = GENMASK(2, 0), /* Bits 3-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, - 0x00000838, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, 0x00000838, 0x0070); -static const u32 ipa_reg_endp_init_seq_fmask[] = { +static const u32 reg_endp_init_seq_fmask[] = { [SEQ_TYPE] = GENMASK(7, 0), [SEQ_REP_TYPE] = GENMASK(15, 8), /* Bits 16-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); -static const u32 ipa_reg_endp_status_fmask[] = { +static const u32 reg_endp_status_fmask[] = { [STATUS_EN] = BIT(0), [STATUS_ENDP] = GENMASK(5, 1), /* Bits 6-7 reserved */ @@ -343,9 +342,9 @@ static const u32 ipa_reg_endp_status_fmask[] = { /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); +REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); -static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { +static const u32 reg_endp_filter_router_hsh_cfg_fmask[] = { [FILTER_HASH_MSK_SRC_ID] = BIT(0), [FILTER_HASH_MSK_SRC_IP] = BIT(1), [FILTER_HASH_MSK_DST_IP] = BIT(2), @@ -366,84 +365,84 @@ static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { /* Bits 23-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, - 0x0000085c, 0x0070); +REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, + 0x0000085c, 0x0070); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00003008 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00003008 + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_EN, ipa_irq_en, 0x0000300c + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_EN, ipa_irq_en, 0x0000300c + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00003010 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00003010 + 0x1000 * GSI_EE_AP); -static const u32 ipa_reg_ipa_irq_uc_fmask[] = { +static const u32 reg_ipa_irq_uc_fmask[] = { [UC_INTR] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); +REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, - 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, + 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, - 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, + 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, - 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); - -static const struct ipa_reg *ipa_reg_array[] = { - [COMP_CFG] = &ipa_reg_comp_cfg, - [CLKON_CFG] = &ipa_reg_clkon_cfg, - [ROUTE] = &ipa_reg_route, - [SHARED_MEM_SIZE] = &ipa_reg_shared_mem_size, - [QSB_MAX_WRITES] = &ipa_reg_qsb_max_writes, - [QSB_MAX_READS] = &ipa_reg_qsb_max_reads, - [FILT_ROUT_HASH_EN] = &ipa_reg_filt_rout_hash_en, - [FILT_ROUT_HASH_FLUSH] = &ipa_reg_filt_rout_hash_flush, - [STATE_AGGR_ACTIVE] = &ipa_reg_state_aggr_active, - [IPA_BCR] = &ipa_reg_ipa_bcr, - [LOCAL_PKT_PROC_CNTXT] = &ipa_reg_local_pkt_proc_cntxt, - [AGGR_FORCE_CLOSE] = &ipa_reg_aggr_force_close, - [COUNTER_CFG] = &ipa_reg_counter_cfg, - [SRC_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_01_rsrc_type, - [SRC_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_23_rsrc_type, - [SRC_RSRC_GRP_45_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_45_rsrc_type, - [SRC_RSRC_GRP_67_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_67_rsrc_type, - [DST_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_01_rsrc_type, - [DST_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_23_rsrc_type, - [DST_RSRC_GRP_45_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_45_rsrc_type, - [DST_RSRC_GRP_67_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_67_rsrc_type, - [ENDP_INIT_CTRL] = &ipa_reg_endp_init_ctrl, - [ENDP_INIT_CFG] = &ipa_reg_endp_init_cfg, - [ENDP_INIT_NAT] = &ipa_reg_endp_init_nat, - [ENDP_INIT_HDR] = &ipa_reg_endp_init_hdr, - [ENDP_INIT_HDR_EXT] = &ipa_reg_endp_init_hdr_ext, - [ENDP_INIT_HDR_METADATA_MASK] = &ipa_reg_endp_init_hdr_metadata_mask, - [ENDP_INIT_MODE] = &ipa_reg_endp_init_mode, - [ENDP_INIT_AGGR] = &ipa_reg_endp_init_aggr, - [ENDP_INIT_HOL_BLOCK_EN] = &ipa_reg_endp_init_hol_block_en, - [ENDP_INIT_HOL_BLOCK_TIMER] = &ipa_reg_endp_init_hol_block_timer, - [ENDP_INIT_DEAGGR] = &ipa_reg_endp_init_deaggr, - [ENDP_INIT_RSRC_GRP] = &ipa_reg_endp_init_rsrc_grp, - [ENDP_INIT_SEQ] = &ipa_reg_endp_init_seq, - [ENDP_STATUS] = &ipa_reg_endp_status, - [ENDP_FILTER_ROUTER_HSH_CFG] = &ipa_reg_endp_filter_router_hsh_cfg, - [IPA_IRQ_STTS] = &ipa_reg_ipa_irq_stts, - [IPA_IRQ_EN] = &ipa_reg_ipa_irq_en, - [IPA_IRQ_CLR] = &ipa_reg_ipa_irq_clr, - [IPA_IRQ_UC] = &ipa_reg_ipa_irq_uc, - [IRQ_SUSPEND_INFO] = &ipa_reg_irq_suspend_info, - [IRQ_SUSPEND_EN] = &ipa_reg_irq_suspend_en, - [IRQ_SUSPEND_CLR] = &ipa_reg_irq_suspend_clr, -}; - -const struct ipa_regs ipa_regs_v3_1 = { - .reg_count = ARRAY_SIZE(ipa_reg_array), - .reg = ipa_reg_array, +REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, + 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); + +static const struct reg *reg_array[] = { + [COMP_CFG] = ®_comp_cfg, + [CLKON_CFG] = ®_clkon_cfg, + [ROUTE] = ®_route, + [SHARED_MEM_SIZE] = ®_shared_mem_size, + [QSB_MAX_WRITES] = ®_qsb_max_writes, + [QSB_MAX_READS] = ®_qsb_max_reads, + [FILT_ROUT_HASH_EN] = ®_filt_rout_hash_en, + [FILT_ROUT_HASH_FLUSH] = ®_filt_rout_hash_flush, + [STATE_AGGR_ACTIVE] = ®_state_aggr_active, + [IPA_BCR] = ®_ipa_bcr, + [LOCAL_PKT_PROC_CNTXT] = ®_local_pkt_proc_cntxt, + [AGGR_FORCE_CLOSE] = ®_aggr_force_close, + [COUNTER_CFG] = ®_counter_cfg, + [SRC_RSRC_GRP_01_RSRC_TYPE] = ®_src_rsrc_grp_01_rsrc_type, + [SRC_RSRC_GRP_23_RSRC_TYPE] = ®_src_rsrc_grp_23_rsrc_type, + [SRC_RSRC_GRP_45_RSRC_TYPE] = ®_src_rsrc_grp_45_rsrc_type, + [SRC_RSRC_GRP_67_RSRC_TYPE] = ®_src_rsrc_grp_67_rsrc_type, + [DST_RSRC_GRP_01_RSRC_TYPE] = ®_dst_rsrc_grp_01_rsrc_type, + [DST_RSRC_GRP_23_RSRC_TYPE] = ®_dst_rsrc_grp_23_rsrc_type, + [DST_RSRC_GRP_45_RSRC_TYPE] = ®_dst_rsrc_grp_45_rsrc_type, + [DST_RSRC_GRP_67_RSRC_TYPE] = ®_dst_rsrc_grp_67_rsrc_type, + [ENDP_INIT_CTRL] = ®_endp_init_ctrl, + [ENDP_INIT_CFG] = ®_endp_init_cfg, + [ENDP_INIT_NAT] = ®_endp_init_nat, + [ENDP_INIT_HDR] = ®_endp_init_hdr, + [ENDP_INIT_HDR_EXT] = ®_endp_init_hdr_ext, + [ENDP_INIT_HDR_METADATA_MASK] = ®_endp_init_hdr_metadata_mask, + [ENDP_INIT_MODE] = ®_endp_init_mode, + [ENDP_INIT_AGGR] = ®_endp_init_aggr, + [ENDP_INIT_HOL_BLOCK_EN] = ®_endp_init_hol_block_en, + [ENDP_INIT_HOL_BLOCK_TIMER] = ®_endp_init_hol_block_timer, + [ENDP_INIT_DEAGGR] = ®_endp_init_deaggr, + [ENDP_INIT_RSRC_GRP] = ®_endp_init_rsrc_grp, + [ENDP_INIT_SEQ] = ®_endp_init_seq, + [ENDP_STATUS] = ®_endp_status, + [ENDP_FILTER_ROUTER_HSH_CFG] = ®_endp_filter_router_hsh_cfg, + [IPA_IRQ_STTS] = ®_ipa_irq_stts, + [IPA_IRQ_EN] = ®_ipa_irq_en, + [IPA_IRQ_CLR] = ®_ipa_irq_clr, + [IPA_IRQ_UC] = ®_ipa_irq_uc, + [IRQ_SUSPEND_INFO] = ®_irq_suspend_info, + [IRQ_SUSPEND_EN] = ®_irq_suspend_en, + [IRQ_SUSPEND_CLR] = ®_irq_suspend_clr, +}; + +const struct regs ipa_regs_v3_1 = { + .reg_count = ARRAY_SIZE(reg_array), + .reg = reg_array, }; diff --git a/drivers/net/ipa/reg/ipa_reg-v3.5.1.c b/drivers/net/ipa/reg/ipa_reg-v3.5.1.c index b9c6a50de243..78b1bf60cd02 100644 --- a/drivers/net/ipa/reg/ipa_reg-v3.5.1.c +++ b/drivers/net/ipa/reg/ipa_reg-v3.5.1.c @@ -7,7 +7,7 @@ #include "../ipa.h" #include "../ipa_reg.h" -static const u32 ipa_reg_comp_cfg_fmask[] = { +static const u32 reg_comp_cfg_fmask[] = { [COMP_CFG_ENABLE] = BIT(0), [GSI_SNOC_BYPASS_DIS] = BIT(1), [GEN_QMB_0_SNOC_BYPASS_DIS] = BIT(2), @@ -16,9 +16,9 @@ static const u32 ipa_reg_comp_cfg_fmask[] = { /* Bits 5-31 reserved */ }; -IPA_REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); +REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); -static const u32 ipa_reg_clkon_cfg_fmask[] = { +static const u32 reg_clkon_cfg_fmask[] = { [CLKON_RX] = BIT(0), [CLKON_PROC] = BIT(1), [TX_WRAPPER] = BIT(2), @@ -44,9 +44,9 @@ static const u32 ipa_reg_clkon_cfg_fmask[] = { /* Bits 22-31 reserved */ }; -IPA_REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); +REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); -static const u32 ipa_reg_route_fmask[] = { +static const u32 reg_route_fmask[] = { [ROUTE_DIS] = BIT(0), [ROUTE_DEF_PIPE] = GENMASK(5, 1), [ROUTE_DEF_HDR_TABLE] = BIT(6), @@ -57,31 +57,31 @@ static const u32 ipa_reg_route_fmask[] = { /* Bits 25-31 reserved */ }; -IPA_REG_FIELDS(ROUTE, route, 0x00000048); +REG_FIELDS(ROUTE, route, 0x00000048); -static const u32 ipa_reg_shared_mem_size_fmask[] = { +static const u32 reg_shared_mem_size_fmask[] = { [MEM_SIZE] = GENMASK(15, 0), [MEM_BADDR] = GENMASK(31, 16), }; -IPA_REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); +REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); -static const u32 ipa_reg_qsb_max_writes_fmask[] = { +static const u32 reg_qsb_max_writes_fmask[] = { [GEN_QMB_0_MAX_WRITES] = GENMASK(3, 0), [GEN_QMB_1_MAX_WRITES] = GENMASK(7, 4), /* Bits 8-31 reserved */ }; -IPA_REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); +REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); -static const u32 ipa_reg_qsb_max_reads_fmask[] = { +static const u32 reg_qsb_max_reads_fmask[] = { [GEN_QMB_0_MAX_READS] = GENMASK(3, 0), [GEN_QMB_1_MAX_READS] = GENMASK(7, 4), }; -IPA_REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); +REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); -static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { +static const u32 reg_filt_rout_hash_en_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -92,9 +92,9 @@ static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x000008c); +REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x000008c); -static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { +static const u32 reg_filt_rout_hash_flush_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -105,42 +105,42 @@ static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x0000090); +REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x0000090); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x0000010c, 0x0004); +REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x0000010c, 0x0004); -IPA_REG(IPA_BCR, ipa_bcr, 0x000001d0); +REG(IPA_BCR, ipa_bcr, 0x000001d0); -static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { +static const u32 reg_local_pkt_proc_cntxt_fmask[] = { [IPA_BASE_ADDR] = GENMASK(16, 0), /* Bits 17-31 reserved */ }; /* Offset must be a multiple of 8 */ -IPA_REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); +REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); +REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); -static const u32 ipa_reg_counter_cfg_fmask[] = { +static const u32 reg_counter_cfg_fmask[] = { /* Bits 0-3 reserved */ [AGGR_GRANULARITY] = GENMASK(8, 4), /* Bits 5-31 reserved */ }; -IPA_REG_FIELDS(COUNTER_CFG, counter_cfg, 0x000001f0); +REG_FIELDS(COUNTER_CFG, counter_cfg, 0x000001f0); -static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { +static const u32 reg_ipa_tx_cfg_fmask[] = { [TX0_PREFETCH_DISABLE] = BIT(0), [TX1_PREFETCH_DISABLE] = BIT(1), [PREFETCH_ALMOST_EMPTY_SIZE] = GENMASK(4, 2), /* Bits 5-31 reserved */ }; -IPA_REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); +REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); -static const u32 ipa_reg_flavor_0_fmask[] = { +static const u32 reg_flavor_0_fmask[] = { [MAX_PIPES] = GENMASK(3, 0), /* Bits 4-7 reserved */ [MAX_CONS_PIPES] = GENMASK(12, 8), @@ -151,17 +151,17 @@ static const u32 ipa_reg_flavor_0_fmask[] = { /* Bits 28-31 reserved */ }; -IPA_REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); +REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); -static const u32 ipa_reg_idle_indication_cfg_fmask[] = { +static const u32 reg_idle_indication_cfg_fmask[] = { [ENTER_IDLE_DEBOUNCE_THRESH] = GENMASK(15, 0), [CONST_NON_IDLE_ENABLE] = BIT(16), /* Bits 17-31 reserved */ }; -IPA_REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000220); +REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000220); -static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -172,10 +172,10 @@ static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, - 0x00000400, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, + 0x00000400, 0x0020); -static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -186,10 +186,10 @@ static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, - 0x00000404, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, + 0x00000404, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -200,10 +200,10 @@ static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, - 0x00000500, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, + 0x00000500, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -214,18 +214,18 @@ static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, - 0x00000504, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, + 0x00000504, 0x0020); -static const u32 ipa_reg_endp_init_ctrl_fmask[] = { +static const u32 reg_endp_init_ctrl_fmask[] = { [ENDP_SUSPEND] = BIT(0), [ENDP_DELAY] = BIT(1), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_CTRL, endp_init_ctrl, 0x00000800, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_CTRL, endp_init_ctrl, 0x00000800, 0x0070); -static const u32 ipa_reg_endp_init_cfg_fmask[] = { +static const u32 reg_endp_init_cfg_fmask[] = { [FRAG_OFFLOAD_EN] = BIT(0), [CS_OFFLOAD_EN] = GENMASK(2, 1), [CS_METADATA_HDR_OFFSET] = GENMASK(6, 3), @@ -234,16 +234,16 @@ static const u32 ipa_reg_endp_init_cfg_fmask[] = { /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); -static const u32 ipa_reg_endp_init_nat_fmask[] = { +static const u32 reg_endp_init_nat_fmask[] = { [NAT_EN] = GENMASK(1, 0), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); -static const u32 ipa_reg_endp_init_hdr_fmask[] = { +static const u32 reg_endp_init_hdr_fmask[] = { [HDR_LEN] = GENMASK(5, 0), [HDR_OFST_METADATA_VALID] = BIT(6), [HDR_OFST_METADATA] = GENMASK(12, 7), @@ -256,9 +256,9 @@ static const u32 ipa_reg_endp_init_hdr_fmask[] = { /* Bits 29-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); -static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { +static const u32 reg_endp_init_hdr_ext_fmask[] = { [HDR_ENDIANNESS] = BIT(0), [HDR_TOTAL_LEN_OR_PAD_VALID] = BIT(1), [HDR_TOTAL_LEN_OR_PAD] = BIT(2), @@ -268,12 +268,12 @@ static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { /* Bits 14-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); -IPA_REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, - 0x00000818, 0x0070); +REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, + 0x00000818, 0x0070); -static const u32 ipa_reg_endp_init_mode_fmask[] = { +static const u32 reg_endp_init_mode_fmask[] = { [ENDP_MODE] = GENMASK(2, 0), /* Bit 3 reserved */ [DEST_PIPE_INDEX] = GENMASK(8, 4), @@ -285,9 +285,9 @@ static const u32 ipa_reg_endp_init_mode_fmask[] = { /* Bit 31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); -static const u32 ipa_reg_endp_init_aggr_fmask[] = { +static const u32 reg_endp_init_aggr_fmask[] = { [AGGR_EN] = GENMASK(1, 0), [AGGR_TYPE] = GENMASK(4, 2), [BYTE_LIMIT] = GENMASK(9, 5), @@ -300,25 +300,25 @@ static const u32 ipa_reg_endp_init_aggr_fmask[] = { /* Bits 25-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_en_fmask[] = { +static const u32 reg_endp_init_hol_block_en_fmask[] = { [HOL_BLOCK_EN] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, - 0x0000082c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, + 0x0000082c, 0x0070); /* Entire register is a tick count */ -static const u32 ipa_reg_endp_init_hol_block_timer_fmask[] = { +static const u32 reg_endp_init_hol_block_timer_fmask[] = { [TIMER_BASE_VALUE] = GENMASK(31, 0), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, - 0x00000830, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, + 0x00000830, 0x0070); -static const u32 ipa_reg_endp_init_deaggr_fmask[] = { +static const u32 reg_endp_init_deaggr_fmask[] = { [DEAGGR_HDR_LEN] = GENMASK(5, 0), [SYSPIPE_ERR_DETECTION] = BIT(6), [PACKET_OFFSET_VALID] = BIT(7), @@ -328,25 +328,24 @@ static const u32 ipa_reg_endp_init_deaggr_fmask[] = { [MAX_PACKET_LEN] = GENMASK(31, 16), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); -static const u32 ipa_reg_endp_init_rsrc_grp_fmask[] = { +static const u32 reg_endp_init_rsrc_grp_fmask[] = { [ENDP_RSRC_GRP] = GENMASK(1, 0), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, - 0x00000838, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, 0x00000838, 0x0070); -static const u32 ipa_reg_endp_init_seq_fmask[] = { +static const u32 reg_endp_init_seq_fmask[] = { [SEQ_TYPE] = GENMASK(7, 0), [SEQ_REP_TYPE] = GENMASK(15, 8), /* Bits 16-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); -static const u32 ipa_reg_endp_status_fmask[] = { +static const u32 reg_endp_status_fmask[] = { [STATUS_EN] = BIT(0), [STATUS_ENDP] = GENMASK(5, 1), /* Bits 6-7 reserved */ @@ -354,9 +353,9 @@ static const u32 ipa_reg_endp_status_fmask[] = { /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); +REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); -static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { +static const u32 reg_endp_filter_router_hsh_cfg_fmask[] = { [FILTER_HASH_MSK_SRC_ID] = BIT(0), [FILTER_HASH_MSK_SRC_IP] = BIT(1), [FILTER_HASH_MSK_DST_IP] = BIT(2), @@ -377,83 +376,83 @@ static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { /* Bits 23-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, - 0x0000085c, 0x0070); +REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, + 0x0000085c, 0x0070); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00003008 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00003008 + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_EN, ipa_irq_en, 0x0000300c + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_EN, ipa_irq_en, 0x0000300c + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00003010 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00003010 + 0x1000 * GSI_EE_AP); -static const u32 ipa_reg_ipa_irq_uc_fmask[] = { +static const u32 reg_ipa_irq_uc_fmask[] = { [UC_INTR] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); +REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, - 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, + 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, - 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, + 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, - 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); - -static const struct ipa_reg *ipa_reg_array[] = { - [COMP_CFG] = &ipa_reg_comp_cfg, - [CLKON_CFG] = &ipa_reg_clkon_cfg, - [ROUTE] = &ipa_reg_route, - [SHARED_MEM_SIZE] = &ipa_reg_shared_mem_size, - [QSB_MAX_WRITES] = &ipa_reg_qsb_max_writes, - [QSB_MAX_READS] = &ipa_reg_qsb_max_reads, - [FILT_ROUT_HASH_EN] = &ipa_reg_filt_rout_hash_en, - [FILT_ROUT_HASH_FLUSH] = &ipa_reg_filt_rout_hash_flush, - [STATE_AGGR_ACTIVE] = &ipa_reg_state_aggr_active, - [IPA_BCR] = &ipa_reg_ipa_bcr, - [LOCAL_PKT_PROC_CNTXT] = &ipa_reg_local_pkt_proc_cntxt, - [AGGR_FORCE_CLOSE] = &ipa_reg_aggr_force_close, - [COUNTER_CFG] = &ipa_reg_counter_cfg, - [IPA_TX_CFG] = &ipa_reg_ipa_tx_cfg, - [FLAVOR_0] = &ipa_reg_flavor_0, - [IDLE_INDICATION_CFG] = &ipa_reg_idle_indication_cfg, - [SRC_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_01_rsrc_type, - [SRC_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_23_rsrc_type, - [DST_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_01_rsrc_type, - [DST_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_23_rsrc_type, - [ENDP_INIT_CTRL] = &ipa_reg_endp_init_ctrl, - [ENDP_INIT_CFG] = &ipa_reg_endp_init_cfg, - [ENDP_INIT_NAT] = &ipa_reg_endp_init_nat, - [ENDP_INIT_HDR] = &ipa_reg_endp_init_hdr, - [ENDP_INIT_HDR_EXT] = &ipa_reg_endp_init_hdr_ext, - [ENDP_INIT_HDR_METADATA_MASK] = &ipa_reg_endp_init_hdr_metadata_mask, - [ENDP_INIT_MODE] = &ipa_reg_endp_init_mode, - [ENDP_INIT_AGGR] = &ipa_reg_endp_init_aggr, - [ENDP_INIT_HOL_BLOCK_EN] = &ipa_reg_endp_init_hol_block_en, - [ENDP_INIT_HOL_BLOCK_TIMER] = &ipa_reg_endp_init_hol_block_timer, - [ENDP_INIT_DEAGGR] = &ipa_reg_endp_init_deaggr, - [ENDP_INIT_RSRC_GRP] = &ipa_reg_endp_init_rsrc_grp, - [ENDP_INIT_SEQ] = &ipa_reg_endp_init_seq, - [ENDP_STATUS] = &ipa_reg_endp_status, - [ENDP_FILTER_ROUTER_HSH_CFG] = &ipa_reg_endp_filter_router_hsh_cfg, - [IPA_IRQ_STTS] = &ipa_reg_ipa_irq_stts, - [IPA_IRQ_EN] = &ipa_reg_ipa_irq_en, - [IPA_IRQ_CLR] = &ipa_reg_ipa_irq_clr, - [IPA_IRQ_UC] = &ipa_reg_ipa_irq_uc, - [IRQ_SUSPEND_INFO] = &ipa_reg_irq_suspend_info, - [IRQ_SUSPEND_EN] = &ipa_reg_irq_suspend_en, - [IRQ_SUSPEND_CLR] = &ipa_reg_irq_suspend_clr, -}; - -const struct ipa_regs ipa_regs_v3_5_1 = { - .reg_count = ARRAY_SIZE(ipa_reg_array), - .reg = ipa_reg_array, +REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, + 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); + +static const struct reg *reg_array[] = { + [COMP_CFG] = ®_comp_cfg, + [CLKON_CFG] = ®_clkon_cfg, + [ROUTE] = ®_route, + [SHARED_MEM_SIZE] = ®_shared_mem_size, + [QSB_MAX_WRITES] = ®_qsb_max_writes, + [QSB_MAX_READS] = ®_qsb_max_reads, + [FILT_ROUT_HASH_EN] = ®_filt_rout_hash_en, + [FILT_ROUT_HASH_FLUSH] = ®_filt_rout_hash_flush, + [STATE_AGGR_ACTIVE] = ®_state_aggr_active, + [IPA_BCR] = ®_ipa_bcr, + [LOCAL_PKT_PROC_CNTXT] = ®_local_pkt_proc_cntxt, + [AGGR_FORCE_CLOSE] = ®_aggr_force_close, + [COUNTER_CFG] = ®_counter_cfg, + [IPA_TX_CFG] = ®_ipa_tx_cfg, + [FLAVOR_0] = ®_flavor_0, + [IDLE_INDICATION_CFG] = ®_idle_indication_cfg, + [SRC_RSRC_GRP_01_RSRC_TYPE] = ®_src_rsrc_grp_01_rsrc_type, + [SRC_RSRC_GRP_23_RSRC_TYPE] = ®_src_rsrc_grp_23_rsrc_type, + [DST_RSRC_GRP_01_RSRC_TYPE] = ®_dst_rsrc_grp_01_rsrc_type, + [DST_RSRC_GRP_23_RSRC_TYPE] = ®_dst_rsrc_grp_23_rsrc_type, + [ENDP_INIT_CTRL] = ®_endp_init_ctrl, + [ENDP_INIT_CFG] = ®_endp_init_cfg, + [ENDP_INIT_NAT] = ®_endp_init_nat, + [ENDP_INIT_HDR] = ®_endp_init_hdr, + [ENDP_INIT_HDR_EXT] = ®_endp_init_hdr_ext, + [ENDP_INIT_HDR_METADATA_MASK] = ®_endp_init_hdr_metadata_mask, + [ENDP_INIT_MODE] = ®_endp_init_mode, + [ENDP_INIT_AGGR] = ®_endp_init_aggr, + [ENDP_INIT_HOL_BLOCK_EN] = ®_endp_init_hol_block_en, + [ENDP_INIT_HOL_BLOCK_TIMER] = ®_endp_init_hol_block_timer, + [ENDP_INIT_DEAGGR] = ®_endp_init_deaggr, + [ENDP_INIT_RSRC_GRP] = ®_endp_init_rsrc_grp, + [ENDP_INIT_SEQ] = ®_endp_init_seq, + [ENDP_STATUS] = ®_endp_status, + [ENDP_FILTER_ROUTER_HSH_CFG] = ®_endp_filter_router_hsh_cfg, + [IPA_IRQ_STTS] = ®_ipa_irq_stts, + [IPA_IRQ_EN] = ®_ipa_irq_en, + [IPA_IRQ_CLR] = ®_ipa_irq_clr, + [IPA_IRQ_UC] = ®_ipa_irq_uc, + [IRQ_SUSPEND_INFO] = ®_irq_suspend_info, + [IRQ_SUSPEND_EN] = ®_irq_suspend_en, + [IRQ_SUSPEND_CLR] = ®_irq_suspend_clr, +}; + +const struct regs ipa_regs_v3_5_1 = { + .reg_count = ARRAY_SIZE(reg_array), + .reg = reg_array, }; diff --git a/drivers/net/ipa/reg/ipa_reg-v4.11.c b/drivers/net/ipa/reg/ipa_reg-v4.11.c index 9a315130530d..29e71cce4a84 100644 --- a/drivers/net/ipa/reg/ipa_reg-v4.11.c +++ b/drivers/net/ipa/reg/ipa_reg-v4.11.c @@ -7,7 +7,7 @@ #include "../ipa.h" #include "../ipa_reg.h" -static const u32 ipa_reg_comp_cfg_fmask[] = { +static const u32 reg_comp_cfg_fmask[] = { [RAM_ARB_PRI_CLIENT_SAMP_FIX_DIS] = BIT(0), [GSI_SNOC_BYPASS_DIS] = BIT(1), [GEN_QMB_0_SNOC_BYPASS_DIS] = BIT(2), @@ -36,9 +36,9 @@ static const u32 ipa_reg_comp_cfg_fmask[] = { [GEN_QMB_0_DYNAMIC_ASIZE] = BIT(31), }; -IPA_REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); +REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); -static const u32 ipa_reg_clkon_cfg_fmask[] = { +static const u32 reg_clkon_cfg_fmask[] = { [CLKON_RX] = BIT(0), [CLKON_PROC] = BIT(1), [TX_WRAPPER] = BIT(2), @@ -73,9 +73,9 @@ static const u32 ipa_reg_clkon_cfg_fmask[] = { [DRBIP] = BIT(31), }; -IPA_REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); +REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); -static const u32 ipa_reg_route_fmask[] = { +static const u32 reg_route_fmask[] = { [ROUTE_DIS] = BIT(0), [ROUTE_DEF_PIPE] = GENMASK(5, 1), [ROUTE_DEF_HDR_TABLE] = BIT(6), @@ -86,24 +86,24 @@ static const u32 ipa_reg_route_fmask[] = { /* Bits 25-31 reserved */ }; -IPA_REG_FIELDS(ROUTE, route, 0x00000048); +REG_FIELDS(ROUTE, route, 0x00000048); -static const u32 ipa_reg_shared_mem_size_fmask[] = { +static const u32 reg_shared_mem_size_fmask[] = { [MEM_SIZE] = GENMASK(15, 0), [MEM_BADDR] = GENMASK(31, 16), }; -IPA_REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); +REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); -static const u32 ipa_reg_qsb_max_writes_fmask[] = { +static const u32 reg_qsb_max_writes_fmask[] = { [GEN_QMB_0_MAX_WRITES] = GENMASK(3, 0), [GEN_QMB_1_MAX_WRITES] = GENMASK(7, 4), /* Bits 8-31 reserved */ }; -IPA_REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); +REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); -static const u32 ipa_reg_qsb_max_reads_fmask[] = { +static const u32 reg_qsb_max_reads_fmask[] = { [GEN_QMB_0_MAX_READS] = GENMASK(3, 0), [GEN_QMB_1_MAX_READS] = GENMASK(7, 4), /* Bits 8-15 reserved */ @@ -111,9 +111,9 @@ static const u32 ipa_reg_qsb_max_reads_fmask[] = { [GEN_QMB_1_MAX_READS_BEATS] = GENMASK(31, 24), }; -IPA_REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); +REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); -static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { +static const u32 reg_filt_rout_hash_en_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -124,9 +124,9 @@ static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x0000148); +REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x0000148); -static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { +static const u32 reg_filt_rout_hash_flush_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -137,23 +137,23 @@ static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); +REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); +REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); -static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { +static const u32 reg_local_pkt_proc_cntxt_fmask[] = { [IPA_BASE_ADDR] = GENMASK(17, 0), /* Bits 18-31 reserved */ }; /* Offset must be a multiple of 8 */ -IPA_REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); +REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); +REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); -static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { +static const u32 reg_ipa_tx_cfg_fmask[] = { /* Bits 0-1 reserved */ [PREFETCH_ALMOST_EMPTY_SIZE_TX0] = GENMASK(5, 2), [DMAW_SCND_OUTSD_PRED_THRESHOLD] = GENMASK(9, 6), @@ -166,9 +166,9 @@ static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { /* Bits 19-31 reserved */ }; -IPA_REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); +REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); -static const u32 ipa_reg_flavor_0_fmask[] = { +static const u32 reg_flavor_0_fmask[] = { [MAX_PIPES] = GENMASK(4, 0), /* Bits 5-7 reserved */ [MAX_CONS_PIPES] = GENMASK(12, 8), @@ -179,17 +179,17 @@ static const u32 ipa_reg_flavor_0_fmask[] = { /* Bits 28-31 reserved */ }; -IPA_REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); +REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); -static const u32 ipa_reg_idle_indication_cfg_fmask[] = { +static const u32 reg_idle_indication_cfg_fmask[] = { [ENTER_IDLE_DEBOUNCE_THRESH] = GENMASK(15, 0), [CONST_NON_IDLE_ENABLE] = BIT(16), /* Bits 17-31 reserved */ }; -IPA_REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000240); +REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000240); -static const u32 ipa_reg_qtime_timestamp_cfg_fmask[] = { +static const u32 reg_qtime_timestamp_cfg_fmask[] = { [DPL_TIMESTAMP_LSB] = GENMASK(4, 0), /* Bits 5-6 reserved */ [DPL_TIMESTAMP_SEL] = BIT(7), @@ -199,26 +199,26 @@ static const u32 ipa_reg_qtime_timestamp_cfg_fmask[] = { /* Bits 21-31 reserved */ }; -IPA_REG_FIELDS(QTIME_TIMESTAMP_CFG, qtime_timestamp_cfg, 0x0000024c); +REG_FIELDS(QTIME_TIMESTAMP_CFG, qtime_timestamp_cfg, 0x0000024c); -static const u32 ipa_reg_timers_xo_clk_div_cfg_fmask[] = { +static const u32 reg_timers_xo_clk_div_cfg_fmask[] = { [DIV_VALUE] = GENMASK(8, 0), /* Bits 9-30 reserved */ [DIV_ENABLE] = BIT(31), }; -IPA_REG_FIELDS(TIMERS_XO_CLK_DIV_CFG, timers_xo_clk_div_cfg, 0x00000250); +REG_FIELDS(TIMERS_XO_CLK_DIV_CFG, timers_xo_clk_div_cfg, 0x00000250); -static const u32 ipa_reg_timers_pulse_gran_cfg_fmask[] = { +static const u32 reg_timers_pulse_gran_cfg_fmask[] = { [PULSE_GRAN_0] = GENMASK(2, 0), [PULSE_GRAN_1] = GENMASK(5, 3), [PULSE_GRAN_2] = GENMASK(8, 6), /* Bits 9-31 reserved */ }; -IPA_REG_FIELDS(TIMERS_PULSE_GRAN_CFG, timers_pulse_gran_cfg, 0x00000254); +REG_FIELDS(TIMERS_PULSE_GRAN_CFG, timers_pulse_gran_cfg, 0x00000254); -static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -229,10 +229,10 @@ static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, - 0x00000400, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, + 0x00000400, 0x0020); -static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -243,10 +243,10 @@ static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, - 0x00000404, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, + 0x00000404, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -257,10 +257,10 @@ static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, - 0x00000500, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, + 0x00000500, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -271,10 +271,10 @@ static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, - 0x00000504, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, + 0x00000504, 0x0020); -static const u32 ipa_reg_endp_init_cfg_fmask[] = { +static const u32 reg_endp_init_cfg_fmask[] = { [FRAG_OFFLOAD_EN] = BIT(0), [CS_OFFLOAD_EN] = GENMASK(2, 1), [CS_METADATA_HDR_OFFSET] = GENMASK(6, 3), @@ -283,16 +283,16 @@ static const u32 ipa_reg_endp_init_cfg_fmask[] = { /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); -static const u32 ipa_reg_endp_init_nat_fmask[] = { +static const u32 reg_endp_init_nat_fmask[] = { [NAT_EN] = GENMASK(1, 0), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); -static const u32 ipa_reg_endp_init_hdr_fmask[] = { +static const u32 reg_endp_init_hdr_fmask[] = { [HDR_LEN] = GENMASK(5, 0), [HDR_OFST_METADATA_VALID] = BIT(6), [HDR_OFST_METADATA] = GENMASK(12, 7), @@ -305,9 +305,9 @@ static const u32 ipa_reg_endp_init_hdr_fmask[] = { [HDR_OFST_METADATA_MSB] = GENMASK(31, 30), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); -static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { +static const u32 reg_endp_init_hdr_ext_fmask[] = { [HDR_ENDIANNESS] = BIT(0), [HDR_TOTAL_LEN_OR_PAD_VALID] = BIT(1), [HDR_TOTAL_LEN_OR_PAD] = BIT(2), @@ -321,12 +321,12 @@ static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { /* Bits 22-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); -IPA_REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, - 0x00000818, 0x0070); +REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, + 0x00000818, 0x0070); -static const u32 ipa_reg_endp_init_mode_fmask[] = { +static const u32 reg_endp_init_mode_fmask[] = { [ENDP_MODE] = GENMASK(2, 0), [DCPH_ENABLE] = BIT(3), [DEST_PIPE_INDEX] = GENMASK(8, 4), @@ -338,9 +338,9 @@ static const u32 ipa_reg_endp_init_mode_fmask[] = { /* Bit 31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); -static const u32 ipa_reg_endp_init_aggr_fmask[] = { +static const u32 reg_endp_init_aggr_fmask[] = { [AGGR_EN] = GENMASK(1, 0), [AGGR_TYPE] = GENMASK(4, 2), [BYTE_LIMIT] = GENMASK(10, 5), @@ -355,27 +355,27 @@ static const u32 ipa_reg_endp_init_aggr_fmask[] = { /* Bits 28-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_en_fmask[] = { +static const u32 reg_endp_init_hol_block_en_fmask[] = { [HOL_BLOCK_EN] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, - 0x0000082c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, + 0x0000082c, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_timer_fmask[] = { +static const u32 reg_endp_init_hol_block_timer_fmask[] = { [TIMER_LIMIT] = GENMASK(4, 0), /* Bits 5-7 reserved */ [TIMER_GRAN_SEL] = BIT(8), /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, - 0x00000830, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, + 0x00000830, 0x0070); -static const u32 ipa_reg_endp_init_deaggr_fmask[] = { +static const u32 reg_endp_init_deaggr_fmask[] = { [DEAGGR_HDR_LEN] = GENMASK(5, 0), [SYSPIPE_ERR_DETECTION] = BIT(6), [PACKET_OFFSET_VALID] = BIT(7), @@ -385,24 +385,23 @@ static const u32 ipa_reg_endp_init_deaggr_fmask[] = { [MAX_PACKET_LEN] = GENMASK(31, 16), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); -static const u32 ipa_reg_endp_init_rsrc_grp_fmask[] = { +static const u32 reg_endp_init_rsrc_grp_fmask[] = { [ENDP_RSRC_GRP] = GENMASK(1, 0), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, - 0x00000838, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, 0x00000838, 0x0070); -static const u32 ipa_reg_endp_init_seq_fmask[] = { +static const u32 reg_endp_init_seq_fmask[] = { [SEQ_TYPE] = GENMASK(7, 0), /* Bits 8-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); -static const u32 ipa_reg_endp_status_fmask[] = { +static const u32 reg_endp_status_fmask[] = { [STATUS_EN] = BIT(0), [STATUS_ENDP] = GENMASK(5, 1), /* Bits 6-8 reserved */ @@ -410,9 +409,9 @@ static const u32 ipa_reg_endp_status_fmask[] = { /* Bits 10-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); +REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); -static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { +static const u32 reg_endp_filter_router_hsh_cfg_fmask[] = { [FILTER_HASH_MSK_SRC_ID] = BIT(0), [FILTER_HASH_MSK_SRC_IP] = BIT(1), [FILTER_HASH_MSK_DST_IP] = BIT(2), @@ -433,83 +432,83 @@ static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { /* Bits 23-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, - 0x0000085c, 0x0070); +REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, + 0x0000085c, 0x0070); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00004008 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00004008 + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_EN, ipa_irq_en, 0x0000400c + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_EN, ipa_irq_en, 0x0000400c + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00004010 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00004010 + 0x1000 * GSI_EE_AP); -static const u32 ipa_reg_ipa_irq_uc_fmask[] = { +static const u32 reg_ipa_irq_uc_fmask[] = { [UC_INTR] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000401c + 0x1000 * GSI_EE_AP); +REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000401c + 0x1000 * GSI_EE_AP); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, - 0x00004030 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, + 0x00004030 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, - 0x00004034 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, + 0x00004034 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, - 0x00004038 + 0x1000 * GSI_EE_AP, 0x0004); - -static const struct ipa_reg *ipa_reg_array[] = { - [COMP_CFG] = &ipa_reg_comp_cfg, - [CLKON_CFG] = &ipa_reg_clkon_cfg, - [ROUTE] = &ipa_reg_route, - [SHARED_MEM_SIZE] = &ipa_reg_shared_mem_size, - [QSB_MAX_WRITES] = &ipa_reg_qsb_max_writes, - [QSB_MAX_READS] = &ipa_reg_qsb_max_reads, - [FILT_ROUT_HASH_EN] = &ipa_reg_filt_rout_hash_en, - [FILT_ROUT_HASH_FLUSH] = &ipa_reg_filt_rout_hash_flush, - [STATE_AGGR_ACTIVE] = &ipa_reg_state_aggr_active, - [LOCAL_PKT_PROC_CNTXT] = &ipa_reg_local_pkt_proc_cntxt, - [AGGR_FORCE_CLOSE] = &ipa_reg_aggr_force_close, - [IPA_TX_CFG] = &ipa_reg_ipa_tx_cfg, - [FLAVOR_0] = &ipa_reg_flavor_0, - [IDLE_INDICATION_CFG] = &ipa_reg_idle_indication_cfg, - [QTIME_TIMESTAMP_CFG] = &ipa_reg_qtime_timestamp_cfg, - [TIMERS_XO_CLK_DIV_CFG] = &ipa_reg_timers_xo_clk_div_cfg, - [TIMERS_PULSE_GRAN_CFG] = &ipa_reg_timers_pulse_gran_cfg, - [SRC_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_01_rsrc_type, - [SRC_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_23_rsrc_type, - [DST_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_01_rsrc_type, - [DST_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_23_rsrc_type, - [ENDP_INIT_CFG] = &ipa_reg_endp_init_cfg, - [ENDP_INIT_NAT] = &ipa_reg_endp_init_nat, - [ENDP_INIT_HDR] = &ipa_reg_endp_init_hdr, - [ENDP_INIT_HDR_EXT] = &ipa_reg_endp_init_hdr_ext, - [ENDP_INIT_HDR_METADATA_MASK] = &ipa_reg_endp_init_hdr_metadata_mask, - [ENDP_INIT_MODE] = &ipa_reg_endp_init_mode, - [ENDP_INIT_AGGR] = &ipa_reg_endp_init_aggr, - [ENDP_INIT_HOL_BLOCK_EN] = &ipa_reg_endp_init_hol_block_en, - [ENDP_INIT_HOL_BLOCK_TIMER] = &ipa_reg_endp_init_hol_block_timer, - [ENDP_INIT_DEAGGR] = &ipa_reg_endp_init_deaggr, - [ENDP_INIT_RSRC_GRP] = &ipa_reg_endp_init_rsrc_grp, - [ENDP_INIT_SEQ] = &ipa_reg_endp_init_seq, - [ENDP_STATUS] = &ipa_reg_endp_status, - [ENDP_FILTER_ROUTER_HSH_CFG] = &ipa_reg_endp_filter_router_hsh_cfg, - [IPA_IRQ_STTS] = &ipa_reg_ipa_irq_stts, - [IPA_IRQ_EN] = &ipa_reg_ipa_irq_en, - [IPA_IRQ_CLR] = &ipa_reg_ipa_irq_clr, - [IPA_IRQ_UC] = &ipa_reg_ipa_irq_uc, - [IRQ_SUSPEND_INFO] = &ipa_reg_irq_suspend_info, - [IRQ_SUSPEND_EN] = &ipa_reg_irq_suspend_en, - [IRQ_SUSPEND_CLR] = &ipa_reg_irq_suspend_clr, -}; - -const struct ipa_regs ipa_regs_v4_11 = { - .reg_count = ARRAY_SIZE(ipa_reg_array), - .reg = ipa_reg_array, +REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, + 0x00004038 + 0x1000 * GSI_EE_AP, 0x0004); + +static const struct reg *reg_array[] = { + [COMP_CFG] = ®_comp_cfg, + [CLKON_CFG] = ®_clkon_cfg, + [ROUTE] = ®_route, + [SHARED_MEM_SIZE] = ®_shared_mem_size, + [QSB_MAX_WRITES] = ®_qsb_max_writes, + [QSB_MAX_READS] = ®_qsb_max_reads, + [FILT_ROUT_HASH_EN] = ®_filt_rout_hash_en, + [FILT_ROUT_HASH_FLUSH] = ®_filt_rout_hash_flush, + [STATE_AGGR_ACTIVE] = ®_state_aggr_active, + [LOCAL_PKT_PROC_CNTXT] = ®_local_pkt_proc_cntxt, + [AGGR_FORCE_CLOSE] = ®_aggr_force_close, + [IPA_TX_CFG] = ®_ipa_tx_cfg, + [FLAVOR_0] = ®_flavor_0, + [IDLE_INDICATION_CFG] = ®_idle_indication_cfg, + [QTIME_TIMESTAMP_CFG] = ®_qtime_timestamp_cfg, + [TIMERS_XO_CLK_DIV_CFG] = ®_timers_xo_clk_div_cfg, + [TIMERS_PULSE_GRAN_CFG] = ®_timers_pulse_gran_cfg, + [SRC_RSRC_GRP_01_RSRC_TYPE] = ®_src_rsrc_grp_01_rsrc_type, + [SRC_RSRC_GRP_23_RSRC_TYPE] = ®_src_rsrc_grp_23_rsrc_type, + [DST_RSRC_GRP_01_RSRC_TYPE] = ®_dst_rsrc_grp_01_rsrc_type, + [DST_RSRC_GRP_23_RSRC_TYPE] = ®_dst_rsrc_grp_23_rsrc_type, + [ENDP_INIT_CFG] = ®_endp_init_cfg, + [ENDP_INIT_NAT] = ®_endp_init_nat, + [ENDP_INIT_HDR] = ®_endp_init_hdr, + [ENDP_INIT_HDR_EXT] = ®_endp_init_hdr_ext, + [ENDP_INIT_HDR_METADATA_MASK] = ®_endp_init_hdr_metadata_mask, + [ENDP_INIT_MODE] = ®_endp_init_mode, + [ENDP_INIT_AGGR] = ®_endp_init_aggr, + [ENDP_INIT_HOL_BLOCK_EN] = ®_endp_init_hol_block_en, + [ENDP_INIT_HOL_BLOCK_TIMER] = ®_endp_init_hol_block_timer, + [ENDP_INIT_DEAGGR] = ®_endp_init_deaggr, + [ENDP_INIT_RSRC_GRP] = ®_endp_init_rsrc_grp, + [ENDP_INIT_SEQ] = ®_endp_init_seq, + [ENDP_STATUS] = ®_endp_status, + [ENDP_FILTER_ROUTER_HSH_CFG] = ®_endp_filter_router_hsh_cfg, + [IPA_IRQ_STTS] = ®_ipa_irq_stts, + [IPA_IRQ_EN] = ®_ipa_irq_en, + [IPA_IRQ_CLR] = ®_ipa_irq_clr, + [IPA_IRQ_UC] = ®_ipa_irq_uc, + [IRQ_SUSPEND_INFO] = ®_irq_suspend_info, + [IRQ_SUSPEND_EN] = ®_irq_suspend_en, + [IRQ_SUSPEND_CLR] = ®_irq_suspend_clr, +}; + +const struct regs ipa_regs_v4_11 = { + .reg_count = ARRAY_SIZE(reg_array), + .reg = reg_array, }; diff --git a/drivers/net/ipa/reg/ipa_reg-v4.2.c b/drivers/net/ipa/reg/ipa_reg-v4.2.c index 7a95149f8ec7..bb7cf488144d 100644 --- a/drivers/net/ipa/reg/ipa_reg-v4.2.c +++ b/drivers/net/ipa/reg/ipa_reg-v4.2.c @@ -7,7 +7,7 @@ #include "../ipa.h" #include "../ipa_reg.h" -static const u32 ipa_reg_comp_cfg_fmask[] = { +static const u32 reg_comp_cfg_fmask[] = { /* Bit 0 reserved */ [GSI_SNOC_BYPASS_DIS] = BIT(1), [GEN_QMB_0_SNOC_BYPASS_DIS] = BIT(2), @@ -29,9 +29,9 @@ static const u32 ipa_reg_comp_cfg_fmask[] = { /* Bits 21-31 reserved */ }; -IPA_REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); +REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); -static const u32 ipa_reg_clkon_cfg_fmask[] = { +static const u32 reg_clkon_cfg_fmask[] = { [CLKON_RX] = BIT(0), [CLKON_PROC] = BIT(1), [TX_WRAPPER] = BIT(2), @@ -65,9 +65,9 @@ static const u32 ipa_reg_clkon_cfg_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); +REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); -static const u32 ipa_reg_route_fmask[] = { +static const u32 reg_route_fmask[] = { [ROUTE_DIS] = BIT(0), [ROUTE_DEF_PIPE] = GENMASK(5, 1), [ROUTE_DEF_HDR_TABLE] = BIT(6), @@ -78,24 +78,24 @@ static const u32 ipa_reg_route_fmask[] = { /* Bits 25-31 reserved */ }; -IPA_REG_FIELDS(ROUTE, route, 0x00000048); +REG_FIELDS(ROUTE, route, 0x00000048); -static const u32 ipa_reg_shared_mem_size_fmask[] = { +static const u32 reg_shared_mem_size_fmask[] = { [MEM_SIZE] = GENMASK(15, 0), [MEM_BADDR] = GENMASK(31, 16), }; -IPA_REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); +REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); -static const u32 ipa_reg_qsb_max_writes_fmask[] = { +static const u32 reg_qsb_max_writes_fmask[] = { [GEN_QMB_0_MAX_WRITES] = GENMASK(3, 0), [GEN_QMB_1_MAX_WRITES] = GENMASK(7, 4), /* Bits 8-31 reserved */ }; -IPA_REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); +REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); -static const u32 ipa_reg_qsb_max_reads_fmask[] = { +static const u32 reg_qsb_max_reads_fmask[] = { [GEN_QMB_0_MAX_READS] = GENMASK(3, 0), [GEN_QMB_1_MAX_READS] = GENMASK(7, 4), /* Bits 8-15 reserved */ @@ -103,9 +103,9 @@ static const u32 ipa_reg_qsb_max_reads_fmask[] = { [GEN_QMB_1_MAX_READS_BEATS] = GENMASK(31, 24), }; -IPA_REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); +REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); -static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { +static const u32 reg_filt_rout_hash_en_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -116,9 +116,9 @@ static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x0000148); +REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x0000148); -static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { +static const u32 reg_filt_rout_hash_flush_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -129,33 +129,33 @@ static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); +REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); +REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); -IPA_REG(IPA_BCR, ipa_bcr, 0x000001d0); +REG(IPA_BCR, ipa_bcr, 0x000001d0); -static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { +static const u32 reg_local_pkt_proc_cntxt_fmask[] = { [IPA_BASE_ADDR] = GENMASK(16, 0), /* Bits 17-31 reserved */ }; /* Offset must be a multiple of 8 */ -IPA_REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); +REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); +REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); -static const u32 ipa_reg_counter_cfg_fmask[] = { +static const u32 reg_counter_cfg_fmask[] = { /* Bits 0-3 reserved */ [AGGR_GRANULARITY] = GENMASK(8, 4), /* Bits 9-31 reserved */ }; -IPA_REG_FIELDS(COUNTER_CFG, counter_cfg, 0x000001f0); +REG_FIELDS(COUNTER_CFG, counter_cfg, 0x000001f0); -static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { +static const u32 reg_ipa_tx_cfg_fmask[] = { /* Bits 0-1 reserved */ [PREFETCH_ALMOST_EMPTY_SIZE_TX0] = GENMASK(5, 2), [DMAW_SCND_OUTSD_PRED_THRESHOLD] = GENMASK(9, 6), @@ -169,9 +169,9 @@ static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { /* Bits 20-31 reserved */ }; -IPA_REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); +REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); -static const u32 ipa_reg_flavor_0_fmask[] = { +static const u32 reg_flavor_0_fmask[] = { [MAX_PIPES] = GENMASK(3, 0), /* Bits 4-7 reserved */ [MAX_CONS_PIPES] = GENMASK(12, 8), @@ -182,17 +182,17 @@ static const u32 ipa_reg_flavor_0_fmask[] = { /* Bits 28-31 reserved */ }; -IPA_REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); +REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); -static const u32 ipa_reg_idle_indication_cfg_fmask[] = { +static const u32 reg_idle_indication_cfg_fmask[] = { [ENTER_IDLE_DEBOUNCE_THRESH] = GENMASK(15, 0), [CONST_NON_IDLE_ENABLE] = BIT(16), /* Bits 17-31 reserved */ }; -IPA_REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000240); +REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000240); -static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -203,10 +203,10 @@ static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, - 0x00000400, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, + 0x00000400, 0x0020); -static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -217,10 +217,10 @@ static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, - 0x00000404, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, + 0x00000404, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -231,10 +231,10 @@ static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, - 0x00000500, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, + 0x00000500, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -245,10 +245,10 @@ static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, - 0x00000504, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, + 0x00000504, 0x0020); -static const u32 ipa_reg_endp_init_cfg_fmask[] = { +static const u32 reg_endp_init_cfg_fmask[] = { [FRAG_OFFLOAD_EN] = BIT(0), [CS_OFFLOAD_EN] = GENMASK(2, 1), [CS_METADATA_HDR_OFFSET] = GENMASK(6, 3), @@ -257,16 +257,16 @@ static const u32 ipa_reg_endp_init_cfg_fmask[] = { /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); -static const u32 ipa_reg_endp_init_nat_fmask[] = { +static const u32 reg_endp_init_nat_fmask[] = { [NAT_EN] = GENMASK(1, 0), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); -static const u32 ipa_reg_endp_init_hdr_fmask[] = { +static const u32 reg_endp_init_hdr_fmask[] = { [HDR_LEN] = GENMASK(5, 0), [HDR_OFST_METADATA_VALID] = BIT(6), [HDR_OFST_METADATA] = GENMASK(12, 7), @@ -279,9 +279,9 @@ static const u32 ipa_reg_endp_init_hdr_fmask[] = { /* Bits 29-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); -static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { +static const u32 reg_endp_init_hdr_ext_fmask[] = { [HDR_ENDIANNESS] = BIT(0), [HDR_TOTAL_LEN_OR_PAD_VALID] = BIT(1), [HDR_TOTAL_LEN_OR_PAD] = BIT(2), @@ -291,12 +291,12 @@ static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { /* Bits 14-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); -IPA_REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, - 0x00000818, 0x0070); +REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, + 0x00000818, 0x0070); -static const u32 ipa_reg_endp_init_mode_fmask[] = { +static const u32 reg_endp_init_mode_fmask[] = { [ENDP_MODE] = GENMASK(2, 0), /* Bit 3 reserved */ [DEST_PIPE_INDEX] = GENMASK(8, 4), @@ -308,9 +308,9 @@ static const u32 ipa_reg_endp_init_mode_fmask[] = { /* Bit 31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); -static const u32 ipa_reg_endp_init_aggr_fmask[] = { +static const u32 reg_endp_init_aggr_fmask[] = { [AGGR_EN] = GENMASK(1, 0), [AGGR_TYPE] = GENMASK(4, 2), [BYTE_LIMIT] = GENMASK(9, 5), @@ -323,27 +323,27 @@ static const u32 ipa_reg_endp_init_aggr_fmask[] = { /* Bits 25-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_en_fmask[] = { +static const u32 reg_endp_init_hol_block_en_fmask[] = { [HOL_BLOCK_EN] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, - 0x0000082c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, + 0x0000082c, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_timer_fmask[] = { +static const u32 reg_endp_init_hol_block_timer_fmask[] = { [TIMER_BASE_VALUE] = GENMASK(4, 0), /* Bits 5-7 reserved */ [TIMER_SCALE] = GENMASK(12, 8), /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, - 0x00000830, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, + 0x00000830, 0x0070); -static const u32 ipa_reg_endp_init_deaggr_fmask[] = { +static const u32 reg_endp_init_deaggr_fmask[] = { [DEAGGR_HDR_LEN] = GENMASK(5, 0), [SYSPIPE_ERR_DETECTION] = BIT(6), [PACKET_OFFSET_VALID] = BIT(7), @@ -353,25 +353,24 @@ static const u32 ipa_reg_endp_init_deaggr_fmask[] = { [MAX_PACKET_LEN] = GENMASK(31, 16), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); -static const u32 ipa_reg_endp_init_rsrc_grp_fmask[] = { +static const u32 reg_endp_init_rsrc_grp_fmask[] = { [ENDP_RSRC_GRP] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, - 0x00000838, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, 0x00000838, 0x0070); -static const u32 ipa_reg_endp_init_seq_fmask[] = { +static const u32 reg_endp_init_seq_fmask[] = { [SEQ_TYPE] = GENMASK(7, 0), [SEQ_REP_TYPE] = GENMASK(15, 8), /* Bits 16-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); -static const u32 ipa_reg_endp_status_fmask[] = { +static const u32 reg_endp_status_fmask[] = { [STATUS_EN] = BIT(0), [STATUS_ENDP] = GENMASK(5, 1), /* Bits 6-7 reserved */ @@ -380,80 +379,80 @@ static const u32 ipa_reg_endp_status_fmask[] = { /* Bits 10-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); +REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00003008 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00003008 + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_EN, ipa_irq_en, 0x0000300c + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_EN, ipa_irq_en, 0x0000300c + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00003010 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00003010 + 0x1000 * GSI_EE_AP); -static const u32 ipa_reg_ipa_irq_uc_fmask[] = { +static const u32 reg_ipa_irq_uc_fmask[] = { [UC_INTR] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); +REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, - 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, + 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, - 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, + 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, - 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); - -static const struct ipa_reg *ipa_reg_array[] = { - [COMP_CFG] = &ipa_reg_comp_cfg, - [CLKON_CFG] = &ipa_reg_clkon_cfg, - [ROUTE] = &ipa_reg_route, - [SHARED_MEM_SIZE] = &ipa_reg_shared_mem_size, - [QSB_MAX_WRITES] = &ipa_reg_qsb_max_writes, - [QSB_MAX_READS] = &ipa_reg_qsb_max_reads, - [FILT_ROUT_HASH_EN] = &ipa_reg_filt_rout_hash_en, - [FILT_ROUT_HASH_FLUSH] = &ipa_reg_filt_rout_hash_flush, - [STATE_AGGR_ACTIVE] = &ipa_reg_state_aggr_active, - [IPA_BCR] = &ipa_reg_ipa_bcr, - [LOCAL_PKT_PROC_CNTXT] = &ipa_reg_local_pkt_proc_cntxt, - [AGGR_FORCE_CLOSE] = &ipa_reg_aggr_force_close, - [COUNTER_CFG] = &ipa_reg_counter_cfg, - [IPA_TX_CFG] = &ipa_reg_ipa_tx_cfg, - [FLAVOR_0] = &ipa_reg_flavor_0, - [IDLE_INDICATION_CFG] = &ipa_reg_idle_indication_cfg, - [SRC_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_01_rsrc_type, - [SRC_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_23_rsrc_type, - [DST_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_01_rsrc_type, - [DST_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_23_rsrc_type, - [ENDP_INIT_CFG] = &ipa_reg_endp_init_cfg, - [ENDP_INIT_NAT] = &ipa_reg_endp_init_nat, - [ENDP_INIT_HDR] = &ipa_reg_endp_init_hdr, - [ENDP_INIT_HDR_EXT] = &ipa_reg_endp_init_hdr_ext, - [ENDP_INIT_HDR_METADATA_MASK] = &ipa_reg_endp_init_hdr_metadata_mask, - [ENDP_INIT_MODE] = &ipa_reg_endp_init_mode, - [ENDP_INIT_AGGR] = &ipa_reg_endp_init_aggr, - [ENDP_INIT_HOL_BLOCK_EN] = &ipa_reg_endp_init_hol_block_en, - [ENDP_INIT_HOL_BLOCK_TIMER] = &ipa_reg_endp_init_hol_block_timer, - [ENDP_INIT_DEAGGR] = &ipa_reg_endp_init_deaggr, - [ENDP_INIT_RSRC_GRP] = &ipa_reg_endp_init_rsrc_grp, - [ENDP_INIT_SEQ] = &ipa_reg_endp_init_seq, - [ENDP_STATUS] = &ipa_reg_endp_status, - [IPA_IRQ_STTS] = &ipa_reg_ipa_irq_stts, - [IPA_IRQ_EN] = &ipa_reg_ipa_irq_en, - [IPA_IRQ_CLR] = &ipa_reg_ipa_irq_clr, - [IPA_IRQ_UC] = &ipa_reg_ipa_irq_uc, - [IRQ_SUSPEND_INFO] = &ipa_reg_irq_suspend_info, - [IRQ_SUSPEND_EN] = &ipa_reg_irq_suspend_en, - [IRQ_SUSPEND_CLR] = &ipa_reg_irq_suspend_clr, -}; - -const struct ipa_regs ipa_regs_v4_2 = { - .reg_count = ARRAY_SIZE(ipa_reg_array), - .reg = ipa_reg_array, +REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, + 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); + +static const struct reg *reg_array[] = { + [COMP_CFG] = ®_comp_cfg, + [CLKON_CFG] = ®_clkon_cfg, + [ROUTE] = ®_route, + [SHARED_MEM_SIZE] = ®_shared_mem_size, + [QSB_MAX_WRITES] = ®_qsb_max_writes, + [QSB_MAX_READS] = ®_qsb_max_reads, + [FILT_ROUT_HASH_EN] = ®_filt_rout_hash_en, + [FILT_ROUT_HASH_FLUSH] = ®_filt_rout_hash_flush, + [STATE_AGGR_ACTIVE] = ®_state_aggr_active, + [IPA_BCR] = ®_ipa_bcr, + [LOCAL_PKT_PROC_CNTXT] = ®_local_pkt_proc_cntxt, + [AGGR_FORCE_CLOSE] = ®_aggr_force_close, + [COUNTER_CFG] = ®_counter_cfg, + [IPA_TX_CFG] = ®_ipa_tx_cfg, + [FLAVOR_0] = ®_flavor_0, + [IDLE_INDICATION_CFG] = ®_idle_indication_cfg, + [SRC_RSRC_GRP_01_RSRC_TYPE] = ®_src_rsrc_grp_01_rsrc_type, + [SRC_RSRC_GRP_23_RSRC_TYPE] = ®_src_rsrc_grp_23_rsrc_type, + [DST_RSRC_GRP_01_RSRC_TYPE] = ®_dst_rsrc_grp_01_rsrc_type, + [DST_RSRC_GRP_23_RSRC_TYPE] = ®_dst_rsrc_grp_23_rsrc_type, + [ENDP_INIT_CFG] = ®_endp_init_cfg, + [ENDP_INIT_NAT] = ®_endp_init_nat, + [ENDP_INIT_HDR] = ®_endp_init_hdr, + [ENDP_INIT_HDR_EXT] = ®_endp_init_hdr_ext, + [ENDP_INIT_HDR_METADATA_MASK] = ®_endp_init_hdr_metadata_mask, + [ENDP_INIT_MODE] = ®_endp_init_mode, + [ENDP_INIT_AGGR] = ®_endp_init_aggr, + [ENDP_INIT_HOL_BLOCK_EN] = ®_endp_init_hol_block_en, + [ENDP_INIT_HOL_BLOCK_TIMER] = ®_endp_init_hol_block_timer, + [ENDP_INIT_DEAGGR] = ®_endp_init_deaggr, + [ENDP_INIT_RSRC_GRP] = ®_endp_init_rsrc_grp, + [ENDP_INIT_SEQ] = ®_endp_init_seq, + [ENDP_STATUS] = ®_endp_status, + [IPA_IRQ_STTS] = ®_ipa_irq_stts, + [IPA_IRQ_EN] = ®_ipa_irq_en, + [IPA_IRQ_CLR] = ®_ipa_irq_clr, + [IPA_IRQ_UC] = ®_ipa_irq_uc, + [IRQ_SUSPEND_INFO] = ®_irq_suspend_info, + [IRQ_SUSPEND_EN] = ®_irq_suspend_en, + [IRQ_SUSPEND_CLR] = ®_irq_suspend_clr, +}; + +const struct regs ipa_regs_v4_2 = { + .reg_count = ARRAY_SIZE(reg_array), + .reg = reg_array, }; diff --git a/drivers/net/ipa/reg/ipa_reg-v4.5.c b/drivers/net/ipa/reg/ipa_reg-v4.5.c index 587eb8d4e00f..1c58f78851c2 100644 --- a/drivers/net/ipa/reg/ipa_reg-v4.5.c +++ b/drivers/net/ipa/reg/ipa_reg-v4.5.c @@ -7,7 +7,7 @@ #include "../ipa.h" #include "../ipa_reg.h" -static const u32 ipa_reg_comp_cfg_fmask[] = { +static const u32 reg_comp_cfg_fmask[] = { /* Bit 0 reserved */ [GSI_SNOC_BYPASS_DIS] = BIT(1), [GEN_QMB_0_SNOC_BYPASS_DIS] = BIT(2), @@ -30,9 +30,9 @@ static const u32 ipa_reg_comp_cfg_fmask[] = { /* Bits 22-31 reserved */ }; -IPA_REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); +REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); -static const u32 ipa_reg_clkon_cfg_fmask[] = { +static const u32 reg_clkon_cfg_fmask[] = { [CLKON_RX] = BIT(0), [CLKON_PROC] = BIT(1), [TX_WRAPPER] = BIT(2), @@ -67,9 +67,9 @@ static const u32 ipa_reg_clkon_cfg_fmask[] = { /* Bit 31 reserved */ }; -IPA_REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); +REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); -static const u32 ipa_reg_route_fmask[] = { +static const u32 reg_route_fmask[] = { [ROUTE_DIS] = BIT(0), [ROUTE_DEF_PIPE] = GENMASK(5, 1), [ROUTE_DEF_HDR_TABLE] = BIT(6), @@ -80,24 +80,24 @@ static const u32 ipa_reg_route_fmask[] = { /* Bits 25-31 reserved */ }; -IPA_REG_FIELDS(ROUTE, route, 0x00000048); +REG_FIELDS(ROUTE, route, 0x00000048); -static const u32 ipa_reg_shared_mem_size_fmask[] = { +static const u32 reg_shared_mem_size_fmask[] = { [MEM_SIZE] = GENMASK(15, 0), [MEM_BADDR] = GENMASK(31, 16), }; -IPA_REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); +REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); -static const u32 ipa_reg_qsb_max_writes_fmask[] = { +static const u32 reg_qsb_max_writes_fmask[] = { [GEN_QMB_0_MAX_WRITES] = GENMASK(3, 0), [GEN_QMB_1_MAX_WRITES] = GENMASK(7, 4), /* Bits 8-31 reserved */ }; -IPA_REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); +REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); -static const u32 ipa_reg_qsb_max_reads_fmask[] = { +static const u32 reg_qsb_max_reads_fmask[] = { [GEN_QMB_0_MAX_READS] = GENMASK(3, 0), [GEN_QMB_1_MAX_READS] = GENMASK(7, 4), /* Bits 8-15 reserved */ @@ -105,9 +105,9 @@ static const u32 ipa_reg_qsb_max_reads_fmask[] = { [GEN_QMB_1_MAX_READS_BEATS] = GENMASK(31, 24), }; -IPA_REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); +REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); -static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { +static const u32 reg_filt_rout_hash_en_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -118,9 +118,9 @@ static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x0000148); +REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x0000148); -static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { +static const u32 reg_filt_rout_hash_flush_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -131,23 +131,23 @@ static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); +REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); +REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); -static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { +static const u32 reg_local_pkt_proc_cntxt_fmask[] = { [IPA_BASE_ADDR] = GENMASK(17, 0), /* Bits 18-31 reserved */ }; /* Offset must be a multiple of 8 */ -IPA_REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); +REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); +REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); -static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { +static const u32 reg_ipa_tx_cfg_fmask[] = { /* Bits 0-1 reserved */ [PREFETCH_ALMOST_EMPTY_SIZE_TX0] = GENMASK(5, 2), [DMAW_SCND_OUTSD_PRED_THRESHOLD] = GENMASK(9, 6), @@ -159,9 +159,9 @@ static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { /* Bits 18-31 reserved */ }; -IPA_REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); +REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); -static const u32 ipa_reg_flavor_0_fmask[] = { +static const u32 reg_flavor_0_fmask[] = { [MAX_PIPES] = GENMASK(3, 0), /* Bits 4-7 reserved */ [MAX_CONS_PIPES] = GENMASK(12, 8), @@ -172,17 +172,17 @@ static const u32 ipa_reg_flavor_0_fmask[] = { /* Bits 28-31 reserved */ }; -IPA_REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); +REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); -static const u32 ipa_reg_idle_indication_cfg_fmask[] = { +static const u32 reg_idle_indication_cfg_fmask[] = { [ENTER_IDLE_DEBOUNCE_THRESH] = GENMASK(15, 0), [CONST_NON_IDLE_ENABLE] = BIT(16), /* Bits 17-31 reserved */ }; -IPA_REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000240); +REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000240); -static const u32 ipa_reg_qtime_timestamp_cfg_fmask[] = { +static const u32 reg_qtime_timestamp_cfg_fmask[] = { [DPL_TIMESTAMP_LSB] = GENMASK(4, 0), /* Bits 5-6 reserved */ [DPL_TIMESTAMP_SEL] = BIT(7), @@ -192,25 +192,25 @@ static const u32 ipa_reg_qtime_timestamp_cfg_fmask[] = { /* Bits 21-31 reserved */ }; -IPA_REG_FIELDS(QTIME_TIMESTAMP_CFG, qtime_timestamp_cfg, 0x0000024c); +REG_FIELDS(QTIME_TIMESTAMP_CFG, qtime_timestamp_cfg, 0x0000024c); -static const u32 ipa_reg_timers_xo_clk_div_cfg_fmask[] = { +static const u32 reg_timers_xo_clk_div_cfg_fmask[] = { [DIV_VALUE] = GENMASK(8, 0), /* Bits 9-30 reserved */ [DIV_ENABLE] = BIT(31), }; -IPA_REG_FIELDS(TIMERS_XO_CLK_DIV_CFG, timers_xo_clk_div_cfg, 0x00000250); +REG_FIELDS(TIMERS_XO_CLK_DIV_CFG, timers_xo_clk_div_cfg, 0x00000250); -static const u32 ipa_reg_timers_pulse_gran_cfg_fmask[] = { +static const u32 reg_timers_pulse_gran_cfg_fmask[] = { [PULSE_GRAN_0] = GENMASK(2, 0), [PULSE_GRAN_1] = GENMASK(5, 3), [PULSE_GRAN_2] = GENMASK(8, 6), }; -IPA_REG_FIELDS(TIMERS_PULSE_GRAN_CFG, timers_pulse_gran_cfg, 0x00000254); +REG_FIELDS(TIMERS_PULSE_GRAN_CFG, timers_pulse_gran_cfg, 0x00000254); -static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -221,10 +221,10 @@ static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, - 0x00000400, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, + 0x00000400, 0x0020); -static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -235,10 +235,10 @@ static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, - 0x00000404, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, + 0x00000404, 0x0020); -static const u32 ipa_reg_src_rsrc_grp_45_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_45_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -249,10 +249,10 @@ static const u32 ipa_reg_src_rsrc_grp_45_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_45_RSRC_TYPE, src_rsrc_grp_45_rsrc_type, - 0x00000408, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_45_RSRC_TYPE, src_rsrc_grp_45_rsrc_type, + 0x00000408, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -263,10 +263,10 @@ static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, - 0x00000500, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, + 0x00000500, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -277,10 +277,10 @@ static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, - 0x00000504, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, + 0x00000504, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_45_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_45_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -291,10 +291,10 @@ static const u32 ipa_reg_dst_rsrc_grp_45_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_45_RSRC_TYPE, dst_rsrc_grp_45_rsrc_type, - 0x00000508, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_45_RSRC_TYPE, dst_rsrc_grp_45_rsrc_type, + 0x00000508, 0x0020); -static const u32 ipa_reg_endp_init_cfg_fmask[] = { +static const u32 reg_endp_init_cfg_fmask[] = { [FRAG_OFFLOAD_EN] = BIT(0), [CS_OFFLOAD_EN] = GENMASK(2, 1), [CS_METADATA_HDR_OFFSET] = GENMASK(6, 3), @@ -303,16 +303,16 @@ static const u32 ipa_reg_endp_init_cfg_fmask[] = { /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); -static const u32 ipa_reg_endp_init_nat_fmask[] = { +static const u32 reg_endp_init_nat_fmask[] = { [NAT_EN] = GENMASK(1, 0), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); -static const u32 ipa_reg_endp_init_hdr_fmask[] = { +static const u32 reg_endp_init_hdr_fmask[] = { [HDR_LEN] = GENMASK(5, 0), [HDR_OFST_METADATA_VALID] = BIT(6), [HDR_OFST_METADATA] = GENMASK(12, 7), @@ -325,9 +325,9 @@ static const u32 ipa_reg_endp_init_hdr_fmask[] = { [HDR_OFST_METADATA_MSB] = GENMASK(31, 30), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); -static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { +static const u32 reg_endp_init_hdr_ext_fmask[] = { [HDR_ENDIANNESS] = BIT(0), [HDR_TOTAL_LEN_OR_PAD_VALID] = BIT(1), [HDR_TOTAL_LEN_OR_PAD] = BIT(2), @@ -341,12 +341,12 @@ static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { /* Bits 22-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); -IPA_REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, - 0x00000818, 0x0070); +REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, + 0x00000818, 0x0070); -static const u32 ipa_reg_endp_init_mode_fmask[] = { +static const u32 reg_endp_init_mode_fmask[] = { [ENDP_MODE] = GENMASK(2, 0), [DCPH_ENABLE] = BIT(3), [DEST_PIPE_INDEX] = GENMASK(8, 4), @@ -357,9 +357,9 @@ static const u32 ipa_reg_endp_init_mode_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); -static const u32 ipa_reg_endp_init_aggr_fmask[] = { +static const u32 reg_endp_init_aggr_fmask[] = { [AGGR_EN] = GENMASK(1, 0), [AGGR_TYPE] = GENMASK(4, 2), [BYTE_LIMIT] = GENMASK(10, 5), @@ -374,27 +374,27 @@ static const u32 ipa_reg_endp_init_aggr_fmask[] = { /* Bits 28-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_en_fmask[] = { +static const u32 reg_endp_init_hol_block_en_fmask[] = { [HOL_BLOCK_EN] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, - 0x0000082c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, + 0x0000082c, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_timer_fmask[] = { +static const u32 reg_endp_init_hol_block_timer_fmask[] = { [TIMER_LIMIT] = GENMASK(4, 0), /* Bits 5-7 reserved */ [TIMER_GRAN_SEL] = BIT(8), /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, - 0x00000830, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, + 0x00000830, 0x0070); -static const u32 ipa_reg_endp_init_deaggr_fmask[] = { +static const u32 reg_endp_init_deaggr_fmask[] = { [DEAGGR_HDR_LEN] = GENMASK(5, 0), [SYSPIPE_ERR_DETECTION] = BIT(6), [PACKET_OFFSET_VALID] = BIT(7), @@ -404,24 +404,23 @@ static const u32 ipa_reg_endp_init_deaggr_fmask[] = { [MAX_PACKET_LEN] = GENMASK(31, 16), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); -static const u32 ipa_reg_endp_init_rsrc_grp_fmask[] = { +static const u32 reg_endp_init_rsrc_grp_fmask[] = { [ENDP_RSRC_GRP] = GENMASK(2, 0), /* Bits 3-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, - 0x00000838, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, 0x00000838, 0x0070); -static const u32 ipa_reg_endp_init_seq_fmask[] = { +static const u32 reg_endp_init_seq_fmask[] = { [SEQ_TYPE] = GENMASK(7, 0), /* Bits 8-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); -static const u32 ipa_reg_endp_status_fmask[] = { +static const u32 reg_endp_status_fmask[] = { [STATUS_EN] = BIT(0), [STATUS_ENDP] = GENMASK(5, 1), /* Bits 6-8 reserved */ @@ -429,9 +428,9 @@ static const u32 ipa_reg_endp_status_fmask[] = { /* Bits 10-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); +REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); -static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { +static const u32 reg_endp_filter_router_hsh_cfg_fmask[] = { [FILTER_HASH_MSK_SRC_ID] = BIT(0), [FILTER_HASH_MSK_SRC_IP] = BIT(1), [FILTER_HASH_MSK_DST_IP] = BIT(2), @@ -452,85 +451,85 @@ static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { /* Bits 23-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, - 0x0000085c, 0x0070); +REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, + 0x0000085c, 0x0070); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00003008 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00003008 + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_EN, ipa_irq_en, 0x0000300c + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_EN, ipa_irq_en, 0x0000300c + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00003010 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00003010 + 0x1000 * GSI_EE_AP); -static const u32 ipa_reg_ipa_irq_uc_fmask[] = { +static const u32 reg_ipa_irq_uc_fmask[] = { [UC_INTR] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); +REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, - 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, + 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, - 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, + 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, - 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); - -static const struct ipa_reg *ipa_reg_array[] = { - [COMP_CFG] = &ipa_reg_comp_cfg, - [CLKON_CFG] = &ipa_reg_clkon_cfg, - [ROUTE] = &ipa_reg_route, - [SHARED_MEM_SIZE] = &ipa_reg_shared_mem_size, - [QSB_MAX_WRITES] = &ipa_reg_qsb_max_writes, - [QSB_MAX_READS] = &ipa_reg_qsb_max_reads, - [FILT_ROUT_HASH_EN] = &ipa_reg_filt_rout_hash_en, - [FILT_ROUT_HASH_FLUSH] = &ipa_reg_filt_rout_hash_flush, - [STATE_AGGR_ACTIVE] = &ipa_reg_state_aggr_active, - [LOCAL_PKT_PROC_CNTXT] = &ipa_reg_local_pkt_proc_cntxt, - [AGGR_FORCE_CLOSE] = &ipa_reg_aggr_force_close, - [IPA_TX_CFG] = &ipa_reg_ipa_tx_cfg, - [FLAVOR_0] = &ipa_reg_flavor_0, - [IDLE_INDICATION_CFG] = &ipa_reg_idle_indication_cfg, - [QTIME_TIMESTAMP_CFG] = &ipa_reg_qtime_timestamp_cfg, - [TIMERS_XO_CLK_DIV_CFG] = &ipa_reg_timers_xo_clk_div_cfg, - [TIMERS_PULSE_GRAN_CFG] = &ipa_reg_timers_pulse_gran_cfg, - [SRC_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_01_rsrc_type, - [SRC_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_23_rsrc_type, - [SRC_RSRC_GRP_45_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_45_rsrc_type, - [DST_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_01_rsrc_type, - [DST_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_23_rsrc_type, - [DST_RSRC_GRP_45_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_45_rsrc_type, - [ENDP_INIT_CFG] = &ipa_reg_endp_init_cfg, - [ENDP_INIT_NAT] = &ipa_reg_endp_init_nat, - [ENDP_INIT_HDR] = &ipa_reg_endp_init_hdr, - [ENDP_INIT_HDR_EXT] = &ipa_reg_endp_init_hdr_ext, - [ENDP_INIT_HDR_METADATA_MASK] = &ipa_reg_endp_init_hdr_metadata_mask, - [ENDP_INIT_MODE] = &ipa_reg_endp_init_mode, - [ENDP_INIT_AGGR] = &ipa_reg_endp_init_aggr, - [ENDP_INIT_HOL_BLOCK_EN] = &ipa_reg_endp_init_hol_block_en, - [ENDP_INIT_HOL_BLOCK_TIMER] = &ipa_reg_endp_init_hol_block_timer, - [ENDP_INIT_DEAGGR] = &ipa_reg_endp_init_deaggr, - [ENDP_INIT_RSRC_GRP] = &ipa_reg_endp_init_rsrc_grp, - [ENDP_INIT_SEQ] = &ipa_reg_endp_init_seq, - [ENDP_STATUS] = &ipa_reg_endp_status, - [ENDP_FILTER_ROUTER_HSH_CFG] = &ipa_reg_endp_filter_router_hsh_cfg, - [IPA_IRQ_STTS] = &ipa_reg_ipa_irq_stts, - [IPA_IRQ_EN] = &ipa_reg_ipa_irq_en, - [IPA_IRQ_CLR] = &ipa_reg_ipa_irq_clr, - [IPA_IRQ_UC] = &ipa_reg_ipa_irq_uc, - [IRQ_SUSPEND_INFO] = &ipa_reg_irq_suspend_info, - [IRQ_SUSPEND_EN] = &ipa_reg_irq_suspend_en, - [IRQ_SUSPEND_CLR] = &ipa_reg_irq_suspend_clr, -}; - -const struct ipa_regs ipa_regs_v4_5 = { - .reg_count = ARRAY_SIZE(ipa_reg_array), - .reg = ipa_reg_array, +REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, + 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); + +static const struct reg *reg_array[] = { + [COMP_CFG] = ®_comp_cfg, + [CLKON_CFG] = ®_clkon_cfg, + [ROUTE] = ®_route, + [SHARED_MEM_SIZE] = ®_shared_mem_size, + [QSB_MAX_WRITES] = ®_qsb_max_writes, + [QSB_MAX_READS] = ®_qsb_max_reads, + [FILT_ROUT_HASH_EN] = ®_filt_rout_hash_en, + [FILT_ROUT_HASH_FLUSH] = ®_filt_rout_hash_flush, + [STATE_AGGR_ACTIVE] = ®_state_aggr_active, + [LOCAL_PKT_PROC_CNTXT] = ®_local_pkt_proc_cntxt, + [AGGR_FORCE_CLOSE] = ®_aggr_force_close, + [IPA_TX_CFG] = ®_ipa_tx_cfg, + [FLAVOR_0] = ®_flavor_0, + [IDLE_INDICATION_CFG] = ®_idle_indication_cfg, + [QTIME_TIMESTAMP_CFG] = ®_qtime_timestamp_cfg, + [TIMERS_XO_CLK_DIV_CFG] = ®_timers_xo_clk_div_cfg, + [TIMERS_PULSE_GRAN_CFG] = ®_timers_pulse_gran_cfg, + [SRC_RSRC_GRP_01_RSRC_TYPE] = ®_src_rsrc_grp_01_rsrc_type, + [SRC_RSRC_GRP_23_RSRC_TYPE] = ®_src_rsrc_grp_23_rsrc_type, + [SRC_RSRC_GRP_45_RSRC_TYPE] = ®_src_rsrc_grp_45_rsrc_type, + [DST_RSRC_GRP_01_RSRC_TYPE] = ®_dst_rsrc_grp_01_rsrc_type, + [DST_RSRC_GRP_23_RSRC_TYPE] = ®_dst_rsrc_grp_23_rsrc_type, + [DST_RSRC_GRP_45_RSRC_TYPE] = ®_dst_rsrc_grp_45_rsrc_type, + [ENDP_INIT_CFG] = ®_endp_init_cfg, + [ENDP_INIT_NAT] = ®_endp_init_nat, + [ENDP_INIT_HDR] = ®_endp_init_hdr, + [ENDP_INIT_HDR_EXT] = ®_endp_init_hdr_ext, + [ENDP_INIT_HDR_METADATA_MASK] = ®_endp_init_hdr_metadata_mask, + [ENDP_INIT_MODE] = ®_endp_init_mode, + [ENDP_INIT_AGGR] = ®_endp_init_aggr, + [ENDP_INIT_HOL_BLOCK_EN] = ®_endp_init_hol_block_en, + [ENDP_INIT_HOL_BLOCK_TIMER] = ®_endp_init_hol_block_timer, + [ENDP_INIT_DEAGGR] = ®_endp_init_deaggr, + [ENDP_INIT_RSRC_GRP] = ®_endp_init_rsrc_grp, + [ENDP_INIT_SEQ] = ®_endp_init_seq, + [ENDP_STATUS] = ®_endp_status, + [ENDP_FILTER_ROUTER_HSH_CFG] = ®_endp_filter_router_hsh_cfg, + [IPA_IRQ_STTS] = ®_ipa_irq_stts, + [IPA_IRQ_EN] = ®_ipa_irq_en, + [IPA_IRQ_CLR] = ®_ipa_irq_clr, + [IPA_IRQ_UC] = ®_ipa_irq_uc, + [IRQ_SUSPEND_INFO] = ®_irq_suspend_info, + [IRQ_SUSPEND_EN] = ®_irq_suspend_en, + [IRQ_SUSPEND_CLR] = ®_irq_suspend_clr, +}; + +const struct regs ipa_regs_v4_5 = { + .reg_count = ARRAY_SIZE(reg_array), + .reg = reg_array, }; diff --git a/drivers/net/ipa/reg/ipa_reg-v4.7.c b/drivers/net/ipa/reg/ipa_reg-v4.7.c index 21f8a58e59a0..731824fce1d4 100644 --- a/drivers/net/ipa/reg/ipa_reg-v4.7.c +++ b/drivers/net/ipa/reg/ipa_reg-v4.7.c @@ -7,7 +7,7 @@ #include "../ipa.h" #include "../ipa_reg.h" -static const u32 ipa_reg_comp_cfg_fmask[] = { +static const u32 reg_comp_cfg_fmask[] = { [RAM_ARB_PRI_CLIENT_SAMP_FIX_DIS] = BIT(0), [GSI_SNOC_BYPASS_DIS] = BIT(1), [GEN_QMB_0_SNOC_BYPASS_DIS] = BIT(2), @@ -30,9 +30,9 @@ static const u32 ipa_reg_comp_cfg_fmask[] = { /* Bits 22-31 reserved */ }; -IPA_REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); +REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); -static const u32 ipa_reg_clkon_cfg_fmask[] = { +static const u32 reg_clkon_cfg_fmask[] = { [CLKON_RX] = BIT(0), [CLKON_PROC] = BIT(1), [TX_WRAPPER] = BIT(2), @@ -67,9 +67,9 @@ static const u32 ipa_reg_clkon_cfg_fmask[] = { [DRBIP] = BIT(31), }; -IPA_REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); +REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); -static const u32 ipa_reg_route_fmask[] = { +static const u32 reg_route_fmask[] = { [ROUTE_DIS] = BIT(0), [ROUTE_DEF_PIPE] = GENMASK(5, 1), [ROUTE_DEF_HDR_TABLE] = BIT(6), @@ -80,24 +80,24 @@ static const u32 ipa_reg_route_fmask[] = { /* Bits 25-31 reserved */ }; -IPA_REG_FIELDS(ROUTE, route, 0x00000048); +REG_FIELDS(ROUTE, route, 0x00000048); -static const u32 ipa_reg_shared_mem_size_fmask[] = { +static const u32 reg_shared_mem_size_fmask[] = { [MEM_SIZE] = GENMASK(15, 0), [MEM_BADDR] = GENMASK(31, 16), }; -IPA_REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); +REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); -static const u32 ipa_reg_qsb_max_writes_fmask[] = { +static const u32 reg_qsb_max_writes_fmask[] = { [GEN_QMB_0_MAX_WRITES] = GENMASK(3, 0), [GEN_QMB_1_MAX_WRITES] = GENMASK(7, 4), /* Bits 8-31 reserved */ }; -IPA_REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); +REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); -static const u32 ipa_reg_qsb_max_reads_fmask[] = { +static const u32 reg_qsb_max_reads_fmask[] = { [GEN_QMB_0_MAX_READS] = GENMASK(3, 0), [GEN_QMB_1_MAX_READS] = GENMASK(7, 4), /* Bits 8-15 reserved */ @@ -105,9 +105,9 @@ static const u32 ipa_reg_qsb_max_reads_fmask[] = { [GEN_QMB_1_MAX_READS_BEATS] = GENMASK(31, 24), }; -IPA_REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); +REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); -static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { +static const u32 reg_filt_rout_hash_en_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -118,9 +118,9 @@ static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x0000148); +REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x0000148); -static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { +static const u32 reg_filt_rout_hash_flush_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -131,23 +131,23 @@ static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); +REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); +REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); -static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { +static const u32 reg_local_pkt_proc_cntxt_fmask[] = { [IPA_BASE_ADDR] = GENMASK(17, 0), /* Bits 18-31 reserved */ }; /* Offset must be a multiple of 8 */ -IPA_REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); +REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); +REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); -static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { +static const u32 reg_ipa_tx_cfg_fmask[] = { /* Bits 0-1 reserved */ [PREFETCH_ALMOST_EMPTY_SIZE_TX0] = GENMASK(5, 2), [DMAW_SCND_OUTSD_PRED_THRESHOLD] = GENMASK(9, 6), @@ -160,9 +160,9 @@ static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { /* Bits 19-31 reserved */ }; -IPA_REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); +REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); -static const u32 ipa_reg_flavor_0_fmask[] = { +static const u32 reg_flavor_0_fmask[] = { [MAX_PIPES] = GENMASK(3, 0), /* Bits 4-7 reserved */ [MAX_CONS_PIPES] = GENMASK(12, 8), @@ -173,17 +173,17 @@ static const u32 ipa_reg_flavor_0_fmask[] = { /* Bits 28-31 reserved */ }; -IPA_REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); +REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); -static const u32 ipa_reg_idle_indication_cfg_fmask[] = { +static const u32 reg_idle_indication_cfg_fmask[] = { [ENTER_IDLE_DEBOUNCE_THRESH] = GENMASK(15, 0), [CONST_NON_IDLE_ENABLE] = BIT(16), /* Bits 17-31 reserved */ }; -IPA_REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000240); +REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000240); -static const u32 ipa_reg_qtime_timestamp_cfg_fmask[] = { +static const u32 reg_qtime_timestamp_cfg_fmask[] = { [DPL_TIMESTAMP_LSB] = GENMASK(4, 0), /* Bits 5-6 reserved */ [DPL_TIMESTAMP_SEL] = BIT(7), @@ -193,25 +193,25 @@ static const u32 ipa_reg_qtime_timestamp_cfg_fmask[] = { /* Bits 21-31 reserved */ }; -IPA_REG_FIELDS(QTIME_TIMESTAMP_CFG, qtime_timestamp_cfg, 0x0000024c); +REG_FIELDS(QTIME_TIMESTAMP_CFG, qtime_timestamp_cfg, 0x0000024c); -static const u32 ipa_reg_timers_xo_clk_div_cfg_fmask[] = { +static const u32 reg_timers_xo_clk_div_cfg_fmask[] = { [DIV_VALUE] = GENMASK(8, 0), /* Bits 9-30 reserved */ [DIV_ENABLE] = BIT(31), }; -IPA_REG_FIELDS(TIMERS_XO_CLK_DIV_CFG, timers_xo_clk_div_cfg, 0x00000250); +REG_FIELDS(TIMERS_XO_CLK_DIV_CFG, timers_xo_clk_div_cfg, 0x00000250); -static const u32 ipa_reg_timers_pulse_gran_cfg_fmask[] = { +static const u32 reg_timers_pulse_gran_cfg_fmask[] = { [PULSE_GRAN_0] = GENMASK(2, 0), [PULSE_GRAN_1] = GENMASK(5, 3), [PULSE_GRAN_2] = GENMASK(8, 6), }; -IPA_REG_FIELDS(TIMERS_PULSE_GRAN_CFG, timers_pulse_gran_cfg, 0x00000254); +REG_FIELDS(TIMERS_PULSE_GRAN_CFG, timers_pulse_gran_cfg, 0x00000254); -static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -222,10 +222,10 @@ static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, - 0x00000400, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, + 0x00000400, 0x0020); -static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -236,10 +236,10 @@ static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, - 0x00000404, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, + 0x00000404, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -250,10 +250,10 @@ static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, - 0x00000500, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, + 0x00000500, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -264,10 +264,10 @@ static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, - 0x00000504, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, + 0x00000504, 0x0020); -static const u32 ipa_reg_endp_init_cfg_fmask[] = { +static const u32 reg_endp_init_cfg_fmask[] = { [FRAG_OFFLOAD_EN] = BIT(0), [CS_OFFLOAD_EN] = GENMASK(2, 1), [CS_METADATA_HDR_OFFSET] = GENMASK(6, 3), @@ -276,16 +276,16 @@ static const u32 ipa_reg_endp_init_cfg_fmask[] = { /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); -static const u32 ipa_reg_endp_init_nat_fmask[] = { +static const u32 reg_endp_init_nat_fmask[] = { [NAT_EN] = GENMASK(1, 0), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); -static const u32 ipa_reg_endp_init_hdr_fmask[] = { +static const u32 reg_endp_init_hdr_fmask[] = { [HDR_LEN] = GENMASK(5, 0), [HDR_OFST_METADATA_VALID] = BIT(6), [HDR_OFST_METADATA] = GENMASK(12, 7), @@ -298,9 +298,9 @@ static const u32 ipa_reg_endp_init_hdr_fmask[] = { [HDR_OFST_METADATA_MSB] = GENMASK(31, 30), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); -static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { +static const u32 reg_endp_init_hdr_ext_fmask[] = { [HDR_ENDIANNESS] = BIT(0), [HDR_TOTAL_LEN_OR_PAD_VALID] = BIT(1), [HDR_TOTAL_LEN_OR_PAD] = BIT(2), @@ -314,12 +314,12 @@ static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { /* Bits 22-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); -IPA_REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, - 0x00000818, 0x0070); +REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, + 0x00000818, 0x0070); -static const u32 ipa_reg_endp_init_mode_fmask[] = { +static const u32 reg_endp_init_mode_fmask[] = { [ENDP_MODE] = GENMASK(2, 0), [DCPH_ENABLE] = BIT(3), [DEST_PIPE_INDEX] = GENMASK(8, 4), @@ -330,9 +330,9 @@ static const u32 ipa_reg_endp_init_mode_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); -static const u32 ipa_reg_endp_init_aggr_fmask[] = { +static const u32 reg_endp_init_aggr_fmask[] = { [AGGR_EN] = GENMASK(1, 0), [AGGR_TYPE] = GENMASK(4, 2), [BYTE_LIMIT] = GENMASK(10, 5), @@ -347,27 +347,27 @@ static const u32 ipa_reg_endp_init_aggr_fmask[] = { /* Bits 28-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_en_fmask[] = { +static const u32 reg_endp_init_hol_block_en_fmask[] = { [HOL_BLOCK_EN] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, - 0x0000082c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, + 0x0000082c, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_timer_fmask[] = { +static const u32 reg_endp_init_hol_block_timer_fmask[] = { [TIMER_LIMIT] = GENMASK(4, 0), /* Bits 5-7 reserved */ [TIMER_GRAN_SEL] = BIT(8), /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, - 0x00000830, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, + 0x00000830, 0x0070); -static const u32 ipa_reg_endp_init_deaggr_fmask[] = { +static const u32 reg_endp_init_deaggr_fmask[] = { [DEAGGR_HDR_LEN] = GENMASK(5, 0), [SYSPIPE_ERR_DETECTION] = BIT(6), [PACKET_OFFSET_VALID] = BIT(7), @@ -377,24 +377,23 @@ static const u32 ipa_reg_endp_init_deaggr_fmask[] = { [MAX_PACKET_LEN] = GENMASK(31, 16), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); -static const u32 ipa_reg_endp_init_rsrc_grp_fmask[] = { +static const u32 reg_endp_init_rsrc_grp_fmask[] = { [ENDP_RSRC_GRP] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, - 0x00000838, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, 0x00000838, 0x0070); -static const u32 ipa_reg_endp_init_seq_fmask[] = { +static const u32 reg_endp_init_seq_fmask[] = { [SEQ_TYPE] = GENMASK(7, 0), /* Bits 8-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); -static const u32 ipa_reg_endp_status_fmask[] = { +static const u32 reg_endp_status_fmask[] = { [STATUS_EN] = BIT(0), [STATUS_ENDP] = GENMASK(5, 1), /* Bits 6-8 reserved */ @@ -402,9 +401,9 @@ static const u32 ipa_reg_endp_status_fmask[] = { /* Bits 10-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); +REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); -static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { +static const u32 reg_endp_filter_router_hsh_cfg_fmask[] = { [FILTER_HASH_MSK_SRC_ID] = BIT(0), [FILTER_HASH_MSK_SRC_IP] = BIT(1), [FILTER_HASH_MSK_DST_IP] = BIT(2), @@ -425,83 +424,83 @@ static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { /* Bits 23-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, - 0x0000085c, 0x0070); +REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, + 0x0000085c, 0x0070); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00003008 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00003008 + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_EN, ipa_irq_en, 0x0000300c + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_EN, ipa_irq_en, 0x0000300c + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00003010 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00003010 + 0x1000 * GSI_EE_AP); -static const u32 ipa_reg_ipa_irq_uc_fmask[] = { +static const u32 reg_ipa_irq_uc_fmask[] = { [UC_INTR] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); +REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, - 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, + 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, - 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, + 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, - 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); - -static const struct ipa_reg *ipa_reg_array[] = { - [COMP_CFG] = &ipa_reg_comp_cfg, - [CLKON_CFG] = &ipa_reg_clkon_cfg, - [ROUTE] = &ipa_reg_route, - [SHARED_MEM_SIZE] = &ipa_reg_shared_mem_size, - [QSB_MAX_WRITES] = &ipa_reg_qsb_max_writes, - [QSB_MAX_READS] = &ipa_reg_qsb_max_reads, - [FILT_ROUT_HASH_EN] = &ipa_reg_filt_rout_hash_en, - [FILT_ROUT_HASH_FLUSH] = &ipa_reg_filt_rout_hash_flush, - [STATE_AGGR_ACTIVE] = &ipa_reg_state_aggr_active, - [LOCAL_PKT_PROC_CNTXT] = &ipa_reg_local_pkt_proc_cntxt, - [AGGR_FORCE_CLOSE] = &ipa_reg_aggr_force_close, - [IPA_TX_CFG] = &ipa_reg_ipa_tx_cfg, - [FLAVOR_0] = &ipa_reg_flavor_0, - [IDLE_INDICATION_CFG] = &ipa_reg_idle_indication_cfg, - [QTIME_TIMESTAMP_CFG] = &ipa_reg_qtime_timestamp_cfg, - [TIMERS_XO_CLK_DIV_CFG] = &ipa_reg_timers_xo_clk_div_cfg, - [TIMERS_PULSE_GRAN_CFG] = &ipa_reg_timers_pulse_gran_cfg, - [SRC_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_01_rsrc_type, - [SRC_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_23_rsrc_type, - [DST_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_01_rsrc_type, - [DST_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_23_rsrc_type, - [ENDP_INIT_CFG] = &ipa_reg_endp_init_cfg, - [ENDP_INIT_NAT] = &ipa_reg_endp_init_nat, - [ENDP_INIT_HDR] = &ipa_reg_endp_init_hdr, - [ENDP_INIT_HDR_EXT] = &ipa_reg_endp_init_hdr_ext, - [ENDP_INIT_HDR_METADATA_MASK] = &ipa_reg_endp_init_hdr_metadata_mask, - [ENDP_INIT_MODE] = &ipa_reg_endp_init_mode, - [ENDP_INIT_AGGR] = &ipa_reg_endp_init_aggr, - [ENDP_INIT_HOL_BLOCK_EN] = &ipa_reg_endp_init_hol_block_en, - [ENDP_INIT_HOL_BLOCK_TIMER] = &ipa_reg_endp_init_hol_block_timer, - [ENDP_INIT_DEAGGR] = &ipa_reg_endp_init_deaggr, - [ENDP_INIT_RSRC_GRP] = &ipa_reg_endp_init_rsrc_grp, - [ENDP_INIT_SEQ] = &ipa_reg_endp_init_seq, - [ENDP_STATUS] = &ipa_reg_endp_status, - [ENDP_FILTER_ROUTER_HSH_CFG] = &ipa_reg_endp_filter_router_hsh_cfg, - [IPA_IRQ_STTS] = &ipa_reg_ipa_irq_stts, - [IPA_IRQ_EN] = &ipa_reg_ipa_irq_en, - [IPA_IRQ_CLR] = &ipa_reg_ipa_irq_clr, - [IPA_IRQ_UC] = &ipa_reg_ipa_irq_uc, - [IRQ_SUSPEND_INFO] = &ipa_reg_irq_suspend_info, - [IRQ_SUSPEND_EN] = &ipa_reg_irq_suspend_en, - [IRQ_SUSPEND_CLR] = &ipa_reg_irq_suspend_clr, -}; - -const struct ipa_regs ipa_regs_v4_7 = { - .reg_count = ARRAY_SIZE(ipa_reg_array), - .reg = ipa_reg_array, +REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, + 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); + +static const struct reg *reg_array[] = { + [COMP_CFG] = ®_comp_cfg, + [CLKON_CFG] = ®_clkon_cfg, + [ROUTE] = ®_route, + [SHARED_MEM_SIZE] = ®_shared_mem_size, + [QSB_MAX_WRITES] = ®_qsb_max_writes, + [QSB_MAX_READS] = ®_qsb_max_reads, + [FILT_ROUT_HASH_EN] = ®_filt_rout_hash_en, + [FILT_ROUT_HASH_FLUSH] = ®_filt_rout_hash_flush, + [STATE_AGGR_ACTIVE] = ®_state_aggr_active, + [LOCAL_PKT_PROC_CNTXT] = ®_local_pkt_proc_cntxt, + [AGGR_FORCE_CLOSE] = ®_aggr_force_close, + [IPA_TX_CFG] = ®_ipa_tx_cfg, + [FLAVOR_0] = ®_flavor_0, + [IDLE_INDICATION_CFG] = ®_idle_indication_cfg, + [QTIME_TIMESTAMP_CFG] = ®_qtime_timestamp_cfg, + [TIMERS_XO_CLK_DIV_CFG] = ®_timers_xo_clk_div_cfg, + [TIMERS_PULSE_GRAN_CFG] = ®_timers_pulse_gran_cfg, + [SRC_RSRC_GRP_01_RSRC_TYPE] = ®_src_rsrc_grp_01_rsrc_type, + [SRC_RSRC_GRP_23_RSRC_TYPE] = ®_src_rsrc_grp_23_rsrc_type, + [DST_RSRC_GRP_01_RSRC_TYPE] = ®_dst_rsrc_grp_01_rsrc_type, + [DST_RSRC_GRP_23_RSRC_TYPE] = ®_dst_rsrc_grp_23_rsrc_type, + [ENDP_INIT_CFG] = ®_endp_init_cfg, + [ENDP_INIT_NAT] = ®_endp_init_nat, + [ENDP_INIT_HDR] = ®_endp_init_hdr, + [ENDP_INIT_HDR_EXT] = ®_endp_init_hdr_ext, + [ENDP_INIT_HDR_METADATA_MASK] = ®_endp_init_hdr_metadata_mask, + [ENDP_INIT_MODE] = ®_endp_init_mode, + [ENDP_INIT_AGGR] = ®_endp_init_aggr, + [ENDP_INIT_HOL_BLOCK_EN] = ®_endp_init_hol_block_en, + [ENDP_INIT_HOL_BLOCK_TIMER] = ®_endp_init_hol_block_timer, + [ENDP_INIT_DEAGGR] = ®_endp_init_deaggr, + [ENDP_INIT_RSRC_GRP] = ®_endp_init_rsrc_grp, + [ENDP_INIT_SEQ] = ®_endp_init_seq, + [ENDP_STATUS] = ®_endp_status, + [ENDP_FILTER_ROUTER_HSH_CFG] = ®_endp_filter_router_hsh_cfg, + [IPA_IRQ_STTS] = ®_ipa_irq_stts, + [IPA_IRQ_EN] = ®_ipa_irq_en, + [IPA_IRQ_CLR] = ®_ipa_irq_clr, + [IPA_IRQ_UC] = ®_ipa_irq_uc, + [IRQ_SUSPEND_INFO] = ®_irq_suspend_info, + [IRQ_SUSPEND_EN] = ®_irq_suspend_en, + [IRQ_SUSPEND_CLR] = ®_irq_suspend_clr, +}; + +const struct regs ipa_regs_v4_7 = { + .reg_count = ARRAY_SIZE(reg_array), + .reg = reg_array, }; diff --git a/drivers/net/ipa/reg/ipa_reg-v4.9.c b/drivers/net/ipa/reg/ipa_reg-v4.9.c index 1f67a03fe599..01f87b5290e0 100644 --- a/drivers/net/ipa/reg/ipa_reg-v4.9.c +++ b/drivers/net/ipa/reg/ipa_reg-v4.9.c @@ -7,7 +7,7 @@ #include "../ipa.h" #include "../ipa_reg.h" -static const u32 ipa_reg_comp_cfg_fmask[] = { +static const u32 reg_comp_cfg_fmask[] = { [RAM_ARB_PRI_CLIENT_SAMP_FIX_DIS] = BIT(0), [GSI_SNOC_BYPASS_DIS] = BIT(1), [GEN_QMB_0_SNOC_BYPASS_DIS] = BIT(2), @@ -35,9 +35,9 @@ static const u32 ipa_reg_comp_cfg_fmask[] = { [GEN_QMB_0_DYNAMIC_ASIZE] = BIT(31), }; -IPA_REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); +REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); -static const u32 ipa_reg_clkon_cfg_fmask[] = { +static const u32 reg_clkon_cfg_fmask[] = { [CLKON_RX] = BIT(0), [CLKON_PROC] = BIT(1), [TX_WRAPPER] = BIT(2), @@ -72,9 +72,9 @@ static const u32 ipa_reg_clkon_cfg_fmask[] = { [DRBIP] = BIT(31), }; -IPA_REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); +REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); -static const u32 ipa_reg_route_fmask[] = { +static const u32 reg_route_fmask[] = { [ROUTE_DIS] = BIT(0), [ROUTE_DEF_PIPE] = GENMASK(5, 1), [ROUTE_DEF_HDR_TABLE] = BIT(6), @@ -85,24 +85,24 @@ static const u32 ipa_reg_route_fmask[] = { /* Bits 25-31 reserved */ }; -IPA_REG_FIELDS(ROUTE, route, 0x00000048); +REG_FIELDS(ROUTE, route, 0x00000048); -static const u32 ipa_reg_shared_mem_size_fmask[] = { +static const u32 reg_shared_mem_size_fmask[] = { [MEM_SIZE] = GENMASK(15, 0), [MEM_BADDR] = GENMASK(31, 16), }; -IPA_REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); +REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); -static const u32 ipa_reg_qsb_max_writes_fmask[] = { +static const u32 reg_qsb_max_writes_fmask[] = { [GEN_QMB_0_MAX_WRITES] = GENMASK(3, 0), [GEN_QMB_1_MAX_WRITES] = GENMASK(7, 4), /* Bits 8-31 reserved */ }; -IPA_REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); +REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); -static const u32 ipa_reg_qsb_max_reads_fmask[] = { +static const u32 reg_qsb_max_reads_fmask[] = { [GEN_QMB_0_MAX_READS] = GENMASK(3, 0), [GEN_QMB_1_MAX_READS] = GENMASK(7, 4), /* Bits 8-15 reserved */ @@ -110,9 +110,9 @@ static const u32 ipa_reg_qsb_max_reads_fmask[] = { [GEN_QMB_1_MAX_READS_BEATS] = GENMASK(31, 24), }; -IPA_REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); +REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); -static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { +static const u32 reg_filt_rout_hash_en_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -123,9 +123,9 @@ static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x0000148); +REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x0000148); -static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { +static const u32 reg_filt_rout_hash_flush_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -136,23 +136,23 @@ static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); +REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); +REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); -static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { +static const u32 reg_local_pkt_proc_cntxt_fmask[] = { [IPA_BASE_ADDR] = GENMASK(17, 0), /* Bits 18-31 reserved */ }; /* Offset must be a multiple of 8 */ -IPA_REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); +REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); +REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); -static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { +static const u32 reg_ipa_tx_cfg_fmask[] = { /* Bits 0-1 reserved */ [PREFETCH_ALMOST_EMPTY_SIZE_TX0] = GENMASK(5, 2), [DMAW_SCND_OUTSD_PRED_THRESHOLD] = GENMASK(9, 6), @@ -165,9 +165,9 @@ static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { /* Bits 19-31 reserved */ }; -IPA_REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); +REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); -static const u32 ipa_reg_flavor_0_fmask[] = { +static const u32 reg_flavor_0_fmask[] = { [MAX_PIPES] = GENMASK(3, 0), /* Bits 4-7 reserved */ [MAX_CONS_PIPES] = GENMASK(12, 8), @@ -178,17 +178,17 @@ static const u32 ipa_reg_flavor_0_fmask[] = { /* Bits 28-31 reserved */ }; -IPA_REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); +REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); -static const u32 ipa_reg_idle_indication_cfg_fmask[] = { +static const u32 reg_idle_indication_cfg_fmask[] = { [ENTER_IDLE_DEBOUNCE_THRESH] = GENMASK(15, 0), [CONST_NON_IDLE_ENABLE] = BIT(16), /* Bits 17-31 reserved */ }; -IPA_REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000240); +REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000240); -static const u32 ipa_reg_qtime_timestamp_cfg_fmask[] = { +static const u32 reg_qtime_timestamp_cfg_fmask[] = { [DPL_TIMESTAMP_LSB] = GENMASK(4, 0), /* Bits 5-6 reserved */ [DPL_TIMESTAMP_SEL] = BIT(7), @@ -198,25 +198,25 @@ static const u32 ipa_reg_qtime_timestamp_cfg_fmask[] = { /* Bits 21-31 reserved */ }; -IPA_REG_FIELDS(QTIME_TIMESTAMP_CFG, qtime_timestamp_cfg, 0x0000024c); +REG_FIELDS(QTIME_TIMESTAMP_CFG, qtime_timestamp_cfg, 0x0000024c); -static const u32 ipa_reg_timers_xo_clk_div_cfg_fmask[] = { +static const u32 reg_timers_xo_clk_div_cfg_fmask[] = { [DIV_VALUE] = GENMASK(8, 0), /* Bits 9-30 reserved */ [DIV_ENABLE] = BIT(31), }; -IPA_REG_FIELDS(TIMERS_XO_CLK_DIV_CFG, timers_xo_clk_div_cfg, 0x00000250); +REG_FIELDS(TIMERS_XO_CLK_DIV_CFG, timers_xo_clk_div_cfg, 0x00000250); -static const u32 ipa_reg_timers_pulse_gran_cfg_fmask[] = { +static const u32 reg_timers_pulse_gran_cfg_fmask[] = { [PULSE_GRAN_0] = GENMASK(2, 0), [PULSE_GRAN_1] = GENMASK(5, 3), [PULSE_GRAN_2] = GENMASK(8, 6), }; -IPA_REG_FIELDS(TIMERS_PULSE_GRAN_CFG, timers_pulse_gran_cfg, 0x00000254); +REG_FIELDS(TIMERS_PULSE_GRAN_CFG, timers_pulse_gran_cfg, 0x00000254); -static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -227,10 +227,10 @@ static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, - 0x00000400, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, + 0x00000400, 0x0020); -static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -241,10 +241,10 @@ static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, - 0x00000404, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, + 0x00000404, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -255,10 +255,10 @@ static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, - 0x00000500, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, + 0x00000500, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -269,10 +269,10 @@ static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, - 0x00000504, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, + 0x00000504, 0x0020); -static const u32 ipa_reg_endp_init_cfg_fmask[] = { +static const u32 reg_endp_init_cfg_fmask[] = { [FRAG_OFFLOAD_EN] = BIT(0), [CS_OFFLOAD_EN] = GENMASK(2, 1), [CS_METADATA_HDR_OFFSET] = GENMASK(6, 3), @@ -281,16 +281,16 @@ static const u32 ipa_reg_endp_init_cfg_fmask[] = { /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); -static const u32 ipa_reg_endp_init_nat_fmask[] = { +static const u32 reg_endp_init_nat_fmask[] = { [NAT_EN] = GENMASK(1, 0), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); -static const u32 ipa_reg_endp_init_hdr_fmask[] = { +static const u32 reg_endp_init_hdr_fmask[] = { [HDR_LEN] = GENMASK(5, 0), [HDR_OFST_METADATA_VALID] = BIT(6), [HDR_OFST_METADATA] = GENMASK(12, 7), @@ -302,9 +302,9 @@ static const u32 ipa_reg_endp_init_hdr_fmask[] = { [HDR_OFST_METADATA_MSB] = GENMASK(31, 30), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); -static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { +static const u32 reg_endp_init_hdr_ext_fmask[] = { [HDR_ENDIANNESS] = BIT(0), [HDR_TOTAL_LEN_OR_PAD_VALID] = BIT(1), [HDR_TOTAL_LEN_OR_PAD] = BIT(2), @@ -318,12 +318,12 @@ static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { /* Bits 22-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); -IPA_REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, - 0x00000818, 0x0070); +REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, + 0x00000818, 0x0070); -static const u32 ipa_reg_endp_init_mode_fmask[] = { +static const u32 reg_endp_init_mode_fmask[] = { [ENDP_MODE] = GENMASK(2, 0), [DCPH_ENABLE] = BIT(3), [DEST_PIPE_INDEX] = GENMASK(8, 4), @@ -335,9 +335,9 @@ static const u32 ipa_reg_endp_init_mode_fmask[] = { /* Bit 31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); -static const u32 ipa_reg_endp_init_aggr_fmask[] = { +static const u32 reg_endp_init_aggr_fmask[] = { [AGGR_EN] = GENMASK(1, 0), [AGGR_TYPE] = GENMASK(4, 2), [BYTE_LIMIT] = GENMASK(10, 5), @@ -352,27 +352,27 @@ static const u32 ipa_reg_endp_init_aggr_fmask[] = { /* Bits 28-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_en_fmask[] = { +static const u32 reg_endp_init_hol_block_en_fmask[] = { [HOL_BLOCK_EN] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, - 0x0000082c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, + 0x0000082c, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_timer_fmask[] = { +static const u32 reg_endp_init_hol_block_timer_fmask[] = { [TIMER_LIMIT] = GENMASK(4, 0), /* Bits 5-7 reserved */ [TIMER_GRAN_SEL] = BIT(8), /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, - 0x00000830, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, + 0x00000830, 0x0070); -static const u32 ipa_reg_endp_init_deaggr_fmask[] = { +static const u32 reg_endp_init_deaggr_fmask[] = { [DEAGGR_HDR_LEN] = GENMASK(5, 0), [SYSPIPE_ERR_DETECTION] = BIT(6), [PACKET_OFFSET_VALID] = BIT(7), @@ -382,24 +382,23 @@ static const u32 ipa_reg_endp_init_deaggr_fmask[] = { [MAX_PACKET_LEN] = GENMASK(31, 16), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); -static const u32 ipa_reg_endp_init_rsrc_grp_fmask[] = { +static const u32 reg_endp_init_rsrc_grp_fmask[] = { [ENDP_RSRC_GRP] = GENMASK(1, 0), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, - 0x00000838, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, 0x00000838, 0x0070); -static const u32 ipa_reg_endp_init_seq_fmask[] = { +static const u32 reg_endp_init_seq_fmask[] = { [SEQ_TYPE] = GENMASK(7, 0), /* Bits 8-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); -static const u32 ipa_reg_endp_status_fmask[] = { +static const u32 reg_endp_status_fmask[] = { [STATUS_EN] = BIT(0), [STATUS_ENDP] = GENMASK(5, 1), /* Bits 6-8 reserved */ @@ -407,9 +406,9 @@ static const u32 ipa_reg_endp_status_fmask[] = { /* Bits 10-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); +REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); -static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { +static const u32 reg_endp_filter_router_hsh_cfg_fmask[] = { [FILTER_HASH_MSK_SRC_ID] = BIT(0), [FILTER_HASH_MSK_SRC_IP] = BIT(1), [FILTER_HASH_MSK_DST_IP] = BIT(2), @@ -430,83 +429,83 @@ static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { /* Bits 23-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, - 0x0000085c, 0x0070); +REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, + 0x0000085c, 0x0070); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00004008 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00004008 + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_EN, ipa_irq_en, 0x0000400c + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_EN, ipa_irq_en, 0x0000400c + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00004010 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00004010 + 0x1000 * GSI_EE_AP); -static const u32 ipa_reg_ipa_irq_uc_fmask[] = { +static const u32 reg_ipa_irq_uc_fmask[] = { [UC_INTR] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000401c + 0x1000 * GSI_EE_AP); +REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000401c + 0x1000 * GSI_EE_AP); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, - 0x00004030 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, + 0x00004030 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, - 0x00004034 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, + 0x00004034 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, - 0x00004038 + 0x1000 * GSI_EE_AP, 0x0004); - -static const struct ipa_reg *ipa_reg_array[] = { - [COMP_CFG] = &ipa_reg_comp_cfg, - [CLKON_CFG] = &ipa_reg_clkon_cfg, - [ROUTE] = &ipa_reg_route, - [SHARED_MEM_SIZE] = &ipa_reg_shared_mem_size, - [QSB_MAX_WRITES] = &ipa_reg_qsb_max_writes, - [QSB_MAX_READS] = &ipa_reg_qsb_max_reads, - [FILT_ROUT_HASH_EN] = &ipa_reg_filt_rout_hash_en, - [FILT_ROUT_HASH_FLUSH] = &ipa_reg_filt_rout_hash_flush, - [STATE_AGGR_ACTIVE] = &ipa_reg_state_aggr_active, - [LOCAL_PKT_PROC_CNTXT] = &ipa_reg_local_pkt_proc_cntxt, - [AGGR_FORCE_CLOSE] = &ipa_reg_aggr_force_close, - [IPA_TX_CFG] = &ipa_reg_ipa_tx_cfg, - [FLAVOR_0] = &ipa_reg_flavor_0, - [IDLE_INDICATION_CFG] = &ipa_reg_idle_indication_cfg, - [QTIME_TIMESTAMP_CFG] = &ipa_reg_qtime_timestamp_cfg, - [TIMERS_XO_CLK_DIV_CFG] = &ipa_reg_timers_xo_clk_div_cfg, - [TIMERS_PULSE_GRAN_CFG] = &ipa_reg_timers_pulse_gran_cfg, - [SRC_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_01_rsrc_type, - [SRC_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_23_rsrc_type, - [DST_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_01_rsrc_type, - [DST_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_23_rsrc_type, - [ENDP_INIT_CFG] = &ipa_reg_endp_init_cfg, - [ENDP_INIT_NAT] = &ipa_reg_endp_init_nat, - [ENDP_INIT_HDR] = &ipa_reg_endp_init_hdr, - [ENDP_INIT_HDR_EXT] = &ipa_reg_endp_init_hdr_ext, - [ENDP_INIT_HDR_METADATA_MASK] = &ipa_reg_endp_init_hdr_metadata_mask, - [ENDP_INIT_MODE] = &ipa_reg_endp_init_mode, - [ENDP_INIT_AGGR] = &ipa_reg_endp_init_aggr, - [ENDP_INIT_HOL_BLOCK_EN] = &ipa_reg_endp_init_hol_block_en, - [ENDP_INIT_HOL_BLOCK_TIMER] = &ipa_reg_endp_init_hol_block_timer, - [ENDP_INIT_DEAGGR] = &ipa_reg_endp_init_deaggr, - [ENDP_INIT_RSRC_GRP] = &ipa_reg_endp_init_rsrc_grp, - [ENDP_INIT_SEQ] = &ipa_reg_endp_init_seq, - [ENDP_STATUS] = &ipa_reg_endp_status, - [ENDP_FILTER_ROUTER_HSH_CFG] = &ipa_reg_endp_filter_router_hsh_cfg, - [IPA_IRQ_STTS] = &ipa_reg_ipa_irq_stts, - [IPA_IRQ_EN] = &ipa_reg_ipa_irq_en, - [IPA_IRQ_CLR] = &ipa_reg_ipa_irq_clr, - [IPA_IRQ_UC] = &ipa_reg_ipa_irq_uc, - [IRQ_SUSPEND_INFO] = &ipa_reg_irq_suspend_info, - [IRQ_SUSPEND_EN] = &ipa_reg_irq_suspend_en, - [IRQ_SUSPEND_CLR] = &ipa_reg_irq_suspend_clr, -}; - -const struct ipa_regs ipa_regs_v4_9 = { - .reg_count = ARRAY_SIZE(ipa_reg_array), - .reg = ipa_reg_array, +REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, + 0x00004038 + 0x1000 * GSI_EE_AP, 0x0004); + +static const struct reg *reg_array[] = { + [COMP_CFG] = ®_comp_cfg, + [CLKON_CFG] = ®_clkon_cfg, + [ROUTE] = ®_route, + [SHARED_MEM_SIZE] = ®_shared_mem_size, + [QSB_MAX_WRITES] = ®_qsb_max_writes, + [QSB_MAX_READS] = ®_qsb_max_reads, + [FILT_ROUT_HASH_EN] = ®_filt_rout_hash_en, + [FILT_ROUT_HASH_FLUSH] = ®_filt_rout_hash_flush, + [STATE_AGGR_ACTIVE] = ®_state_aggr_active, + [LOCAL_PKT_PROC_CNTXT] = ®_local_pkt_proc_cntxt, + [AGGR_FORCE_CLOSE] = ®_aggr_force_close, + [IPA_TX_CFG] = ®_ipa_tx_cfg, + [FLAVOR_0] = ®_flavor_0, + [IDLE_INDICATION_CFG] = ®_idle_indication_cfg, + [QTIME_TIMESTAMP_CFG] = ®_qtime_timestamp_cfg, + [TIMERS_XO_CLK_DIV_CFG] = ®_timers_xo_clk_div_cfg, + [TIMERS_PULSE_GRAN_CFG] = ®_timers_pulse_gran_cfg, + [SRC_RSRC_GRP_01_RSRC_TYPE] = ®_src_rsrc_grp_01_rsrc_type, + [SRC_RSRC_GRP_23_RSRC_TYPE] = ®_src_rsrc_grp_23_rsrc_type, + [DST_RSRC_GRP_01_RSRC_TYPE] = ®_dst_rsrc_grp_01_rsrc_type, + [DST_RSRC_GRP_23_RSRC_TYPE] = ®_dst_rsrc_grp_23_rsrc_type, + [ENDP_INIT_CFG] = ®_endp_init_cfg, + [ENDP_INIT_NAT] = ®_endp_init_nat, + [ENDP_INIT_HDR] = ®_endp_init_hdr, + [ENDP_INIT_HDR_EXT] = ®_endp_init_hdr_ext, + [ENDP_INIT_HDR_METADATA_MASK] = ®_endp_init_hdr_metadata_mask, + [ENDP_INIT_MODE] = ®_endp_init_mode, + [ENDP_INIT_AGGR] = ®_endp_init_aggr, + [ENDP_INIT_HOL_BLOCK_EN] = ®_endp_init_hol_block_en, + [ENDP_INIT_HOL_BLOCK_TIMER] = ®_endp_init_hol_block_timer, + [ENDP_INIT_DEAGGR] = ®_endp_init_deaggr, + [ENDP_INIT_RSRC_GRP] = ®_endp_init_rsrc_grp, + [ENDP_INIT_SEQ] = ®_endp_init_seq, + [ENDP_STATUS] = ®_endp_status, + [ENDP_FILTER_ROUTER_HSH_CFG] = ®_endp_filter_router_hsh_cfg, + [IPA_IRQ_STTS] = ®_ipa_irq_stts, + [IPA_IRQ_EN] = ®_ipa_irq_en, + [IPA_IRQ_CLR] = ®_ipa_irq_clr, + [IPA_IRQ_UC] = ®_ipa_irq_uc, + [IRQ_SUSPEND_INFO] = ®_irq_suspend_info, + [IRQ_SUSPEND_EN] = ®_irq_suspend_en, + [IRQ_SUSPEND_CLR] = ®_irq_suspend_clr, +}; + +const struct regs ipa_regs_v4_9 = { + .reg_count = ARRAY_SIZE(reg_array), + .reg = reg_array, }; diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index bb1c298c1e78..460b3d4f2245 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -157,7 +157,7 @@ void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type) return NULL; ip4h = ip_hdr(skb); - pktlen = ntohs(ip4h->tot_len); + pktlen = skb_ip_totlen(skb); if (ip4h->ihl < 5 || ip4h->version != 4) return NULL; if (skb->len < pktlen || pktlen < (ip4h->ihl * 4)) diff --git a/drivers/net/mdio/Kconfig b/drivers/net/mdio/Kconfig index bfa16826a6e1..90309980686e 100644 --- a/drivers/net/mdio/Kconfig +++ b/drivers/net/mdio/Kconfig @@ -215,6 +215,17 @@ config MDIO_BUS_MUX_MESON_G12A the amlogic g12a SoC. The multiplexers connects either the external or the internal MDIO bus to the parent bus. +config MDIO_BUS_MUX_MESON_GXL + tristate "Amlogic GXL based MDIO bus multiplexer" + depends on ARCH_MESON || COMPILE_TEST + depends on OF_MDIO && HAS_IOMEM && COMMON_CLK + select MDIO_BUS_MUX + default m if ARCH_MESON + help + This module provides a driver for the MDIO multiplexer/glue of + the amlogic GXL SoC. The multiplexer connects either the external + or the internal MDIO bus to the parent bus. + config MDIO_BUS_MUX_BCM6368 tristate "Broadcom BCM6368 MDIO bus multiplexers" depends on OF && OF_MDIO && (BMIPS_GENERIC || COMPILE_TEST) diff --git a/drivers/net/mdio/Makefile b/drivers/net/mdio/Makefile index 15f8dc4042ce..7d4cb4c11e4e 100644 --- a/drivers/net/mdio/Makefile +++ b/drivers/net/mdio/Makefile @@ -28,5 +28,6 @@ obj-$(CONFIG_MDIO_BUS_MUX_BCM6368) += mdio-mux-bcm6368.o obj-$(CONFIG_MDIO_BUS_MUX_BCM_IPROC) += mdio-mux-bcm-iproc.o obj-$(CONFIG_MDIO_BUS_MUX_GPIO) += mdio-mux-gpio.o obj-$(CONFIG_MDIO_BUS_MUX_MESON_G12A) += mdio-mux-meson-g12a.o +obj-$(CONFIG_MDIO_BUS_MUX_MESON_GXL) += mdio-mux-meson-gxl.o obj-$(CONFIG_MDIO_BUS_MUX_MMIOREG) += mdio-mux-mmioreg.o obj-$(CONFIG_MDIO_BUS_MUX_MULTIPLEXER) += mdio-mux-multiplexer.o diff --git a/drivers/net/mdio/mdio-mux-meson-g12a.c b/drivers/net/mdio/mdio-mux-meson-g12a.c index f0b554df62a9..910e5cf74e89 100644 --- a/drivers/net/mdio/mdio-mux-meson-g12a.c +++ b/drivers/net/mdio/mdio-mux-meson-g12a.c @@ -53,7 +53,6 @@ #define MESON_G12A_MDIO_INTERNAL_ID 1 struct g12a_mdio_mux { - bool pll_is_enabled; void __iomem *regs; void *mux_handle; struct clk *pll; @@ -154,14 +153,12 @@ static int g12a_enable_internal_mdio(struct g12a_mdio_mux *priv) int ret; /* Enable the phy clock */ - if (!priv->pll_is_enabled) { + if (!__clk_is_enabled(priv->pll)) { ret = clk_prepare_enable(priv->pll); if (ret) return ret; } - priv->pll_is_enabled = true; - /* Initialize ephy control */ writel(EPHY_G12A_ID, priv->regs + ETH_PHY_CNTL0); @@ -192,10 +189,8 @@ static int g12a_enable_external_mdio(struct g12a_mdio_mux *priv) writel_relaxed(0x0, priv->regs + ETH_PHY_CNTL2); /* Disable the phy clock if enabled */ - if (priv->pll_is_enabled) { + if (__clk_is_enabled(priv->pll)) clk_disable_unprepare(priv->pll); - priv->pll_is_enabled = false; - } return 0; } @@ -347,7 +342,7 @@ static int g12a_mdio_mux_remove(struct platform_device *pdev) mdio_mux_uninit(priv->mux_handle); - if (priv->pll_is_enabled) + if (__clk_is_enabled(priv->pll)) clk_disable_unprepare(priv->pll); return 0; diff --git a/drivers/net/mdio/mdio-mux-meson-gxl.c b/drivers/net/mdio/mdio-mux-meson-gxl.c new file mode 100644 index 000000000000..76188575ca1f --- /dev/null +++ b/drivers/net/mdio/mdio-mux-meson-gxl.c @@ -0,0 +1,164 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Baylibre, SAS. + * Author: Jerome Brunet <jbrunet@baylibre.com> + */ + +#include <linux/bitfield.h> +#include <linux/delay.h> +#include <linux/clk.h> +#include <linux/io.h> +#include <linux/mdio-mux.h> +#include <linux/module.h> +#include <linux/platform_device.h> + +#define ETH_REG2 0x0 +#define REG2_PHYID GENMASK(21, 0) +#define EPHY_GXL_ID 0x110181 +#define REG2_LEDACT GENMASK(23, 22) +#define REG2_LEDLINK GENMASK(25, 24) +#define REG2_DIV4SEL BIT(27) +#define REG2_ADCBYPASS BIT(30) +#define REG2_CLKINSEL BIT(31) +#define ETH_REG3 0x4 +#define REG3_ENH BIT(3) +#define REG3_CFGMODE GENMASK(6, 4) +#define REG3_AUTOMDIX BIT(7) +#define REG3_PHYADDR GENMASK(12, 8) +#define REG3_PWRUPRST BIT(21) +#define REG3_PWRDOWN BIT(22) +#define REG3_LEDPOL BIT(23) +#define REG3_PHYMDI BIT(26) +#define REG3_CLKINEN BIT(29) +#define REG3_PHYIP BIT(30) +#define REG3_PHYEN BIT(31) +#define ETH_REG4 0x8 +#define REG4_PWRUPRSTSIG BIT(0) + +#define MESON_GXL_MDIO_EXTERNAL_ID 0 +#define MESON_GXL_MDIO_INTERNAL_ID 1 + +struct gxl_mdio_mux { + void __iomem *regs; + void *mux_handle; +}; + +static void gxl_enable_internal_mdio(struct gxl_mdio_mux *priv) +{ + u32 val; + + /* Setup the internal phy */ + val = (REG3_ENH | + FIELD_PREP(REG3_CFGMODE, 0x7) | + REG3_AUTOMDIX | + FIELD_PREP(REG3_PHYADDR, 8) | + REG3_LEDPOL | + REG3_PHYMDI | + REG3_CLKINEN | + REG3_PHYIP); + + writel(REG4_PWRUPRSTSIG, priv->regs + ETH_REG4); + writel(val, priv->regs + ETH_REG3); + mdelay(10); + + /* NOTE: The HW kept the phy id configurable at runtime. + * The id below is arbitrary. It is the one used in the vendor code. + * The only constraint is that it must match the one in + * drivers/net/phy/meson-gxl.c to properly match the PHY. + */ + writel(FIELD_PREP(REG2_PHYID, EPHY_GXL_ID), + priv->regs + ETH_REG2); + + /* Enable the internal phy */ + val |= REG3_PHYEN; + writel(val, priv->regs + ETH_REG3); + writel(0, priv->regs + ETH_REG4); + + /* The phy needs a bit of time to power up */ + mdelay(10); +} + +static void gxl_enable_external_mdio(struct gxl_mdio_mux *priv) +{ + /* Reset the mdio bus mux to the external phy */ + writel(0, priv->regs + ETH_REG3); +} + +static int gxl_mdio_switch_fn(int current_child, int desired_child, + void *data) +{ + struct gxl_mdio_mux *priv = dev_get_drvdata(data); + + if (current_child == desired_child) + return 0; + + switch (desired_child) { + case MESON_GXL_MDIO_EXTERNAL_ID: + gxl_enable_external_mdio(priv); + break; + case MESON_GXL_MDIO_INTERNAL_ID: + gxl_enable_internal_mdio(priv); + break; + default: + return -EINVAL; + } + + return 0; +} + +static const struct of_device_id gxl_mdio_mux_match[] = { + { .compatible = "amlogic,gxl-mdio-mux", }, + {}, +}; +MODULE_DEVICE_TABLE(of, gxl_mdio_mux_match); + +static int gxl_mdio_mux_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct gxl_mdio_mux *priv; + struct clk *rclk; + int ret; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + platform_set_drvdata(pdev, priv); + + priv->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(priv->regs)) + return PTR_ERR(priv->regs); + + rclk = devm_clk_get_enabled(dev, "ref"); + if (IS_ERR(rclk)) + return dev_err_probe(dev, PTR_ERR(rclk), + "failed to get reference clock\n"); + + ret = mdio_mux_init(dev, dev->of_node, gxl_mdio_switch_fn, + &priv->mux_handle, dev, NULL); + if (ret) + dev_err_probe(dev, ret, "mdio multiplexer init failed\n"); + + return ret; +} + +static int gxl_mdio_mux_remove(struct platform_device *pdev) +{ + struct gxl_mdio_mux *priv = platform_get_drvdata(pdev); + + mdio_mux_uninit(priv->mux_handle); + + return 0; +} + +static struct platform_driver gxl_mdio_mux_driver = { + .probe = gxl_mdio_mux_probe, + .remove = gxl_mdio_mux_remove, + .driver = { + .name = "gxl-mdio-mux", + .of_match_table = gxl_mdio_mux_match, + }, +}; +module_platform_driver(gxl_mdio_mux_driver); + +MODULE_DESCRIPTION("Amlogic GXL MDIO multiplexer driver"); +MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index f88095b0f836..6045bece2654 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -1609,7 +1609,6 @@ int nsim_drv_probe(struct nsim_bus_dev *nsim_bus_dev) goto err_hwstats_exit; nsim_dev->esw_mode = DEVLINK_ESWITCH_MODE_LEGACY; - devlink_set_features(devlink, DEVLINK_F_RELOAD); devl_unlock(devlink); return 0; diff --git a/drivers/net/pcs/pcs-rzn1-miic.c b/drivers/net/pcs/pcs-rzn1-miic.c index c1424119e821..323bec5e57f8 100644 --- a/drivers/net/pcs/pcs-rzn1-miic.c +++ b/drivers/net/pcs/pcs-rzn1-miic.c @@ -121,15 +121,11 @@ static const char *index_to_string[MIIC_MODCTRL_CONF_CONV_NUM] = { * struct miic - MII converter structure * @base: base address of the MII converter * @dev: Device associated to the MII converter - * @clks: Clocks used for this device - * @nclk: Number of clocks * @lock: Lock used for read-modify-write access */ struct miic { void __iomem *base; struct device *dev; - struct clk_bulk_data *clks; - int nclk; spinlock_t lock; }; @@ -232,7 +228,7 @@ static int miic_config(struct phylink_pcs *pcs, unsigned int mode, } miic_reg_rmw(miic, MIIC_CONVCTRL(port), mask, val); - miic_converter_enable(miic_port->miic, miic_port->port, 1); + miic_converter_enable(miic, miic_port->port, 1); return 0; } diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index f5df2edc94a5..54874555c921 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -257,7 +257,7 @@ config MOTORCOMM_PHY tristate "Motorcomm PHYs" help Enables support for Motorcomm network PHYs. - Currently supports the YT8511, YT8521, YT8531S Gigabit Ethernet PHYs. + Currently supports YT85xx Gigabit Ethernet PHYs. config NATIONAL_PHY tristate "National Semiconductor PHYs" diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index a6f05e35d91f..b7cb71817780 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -233,7 +233,8 @@ static int dp83822_config_intr(struct phy_device *phydev) DP83822_ENERGY_DET_INT_EN | DP83822_LINK_QUAL_INT_EN); - if (!dp83822->fx_enabled) + /* Private data pointer is NULL on DP83825/26 */ + if (!dp83822 || !dp83822->fx_enabled) misr_status |= DP83822_ANEG_COMPLETE_INT_EN | DP83822_DUP_MODE_CHANGE_INT_EN | DP83822_SPEED_CHANGED_INT_EN; @@ -253,7 +254,8 @@ static int dp83822_config_intr(struct phy_device *phydev) DP83822_PAGE_RX_INT_EN | DP83822_EEE_ERROR_CHANGE_INT_EN); - if (!dp83822->fx_enabled) + /* Private data pointer is NULL on DP83825/26 */ + if (!dp83822 || !dp83822->fx_enabled) misr_status |= DP83822_ANEG_ERR_INT_EN | DP83822_WOL_PKT_INT_EN; diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c index c49062ad72c6..a6015cd03bff 100644 --- a/drivers/net/phy/meson-gxl.c +++ b/drivers/net/phy/meson-gxl.c @@ -261,6 +261,8 @@ static struct phy_driver meson_gxl_phy[] = { .handle_interrupt = meson_gxl_handle_interrupt, .suspend = genphy_suspend, .resume = genphy_resume, + .read_mmd = genphy_read_mmd_unsupported, + .write_mmd = genphy_write_mmd_unsupported, }, { PHY_ID_MATCH_EXACT(0x01803301), .name = "Meson G12A Internal PHY", @@ -271,6 +273,8 @@ static struct phy_driver meson_gxl_phy[] = { .handle_interrupt = meson_gxl_handle_interrupt, .suspend = genphy_suspend, .resume = genphy_resume, + .read_mmd = genphy_read_mmd_unsupported, + .write_mmd = genphy_write_mmd_unsupported, }, }; diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index d5b80c31ab91..727de4f4a14d 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -268,6 +268,9 @@ struct kszphy_type { u16 interrupt_level_mask; u16 cable_diag_reg; unsigned long pair_mask; + u16 disable_dll_tx_bit; + u16 disable_dll_rx_bit; + u16 disable_dll_mask; bool has_broadcast_disable; bool has_nand_tree_disable; bool has_rmii_ref_clk_sel; @@ -364,6 +367,21 @@ static const struct kszphy_type ksz9021_type = { .interrupt_level_mask = BIT(14), }; +static const struct kszphy_type ksz9131_type = { + .interrupt_level_mask = BIT(14), + .disable_dll_tx_bit = BIT(12), + .disable_dll_rx_bit = BIT(12), + .disable_dll_mask = BIT_MASK(12), +}; + +static const struct kszphy_type lan8841_type = { + .disable_dll_tx_bit = BIT(14), + .disable_dll_rx_bit = BIT(14), + .disable_dll_mask = BIT_MASK(14), + .cable_diag_reg = LAN8814_CABLE_DIAG, + .pair_mask = LAN8814_WIRE_PAIR_MASK, +}; + static int kszphy_extended_write(struct phy_device *phydev, u32 regnum, u16 val) { @@ -1172,19 +1190,18 @@ static int ksz9131_of_load_skew_values(struct phy_device *phydev, #define KSZ9131RN_MMD_COMMON_CTRL_REG 2 #define KSZ9131RN_RXC_DLL_CTRL 76 #define KSZ9131RN_TXC_DLL_CTRL 77 -#define KSZ9131RN_DLL_CTRL_BYPASS BIT_MASK(12) #define KSZ9131RN_DLL_ENABLE_DELAY 0 -#define KSZ9131RN_DLL_DISABLE_DELAY BIT(12) static int ksz9131_config_rgmii_delay(struct phy_device *phydev) { + const struct kszphy_type *type = phydev->drv->driver_data; u16 rxcdll_val, txcdll_val; int ret; switch (phydev->interface) { case PHY_INTERFACE_MODE_RGMII: - rxcdll_val = KSZ9131RN_DLL_DISABLE_DELAY; - txcdll_val = KSZ9131RN_DLL_DISABLE_DELAY; + rxcdll_val = type->disable_dll_rx_bit; + txcdll_val = type->disable_dll_tx_bit; break; case PHY_INTERFACE_MODE_RGMII_ID: rxcdll_val = KSZ9131RN_DLL_ENABLE_DELAY; @@ -1192,10 +1209,10 @@ static int ksz9131_config_rgmii_delay(struct phy_device *phydev) break; case PHY_INTERFACE_MODE_RGMII_RXID: rxcdll_val = KSZ9131RN_DLL_ENABLE_DELAY; - txcdll_val = KSZ9131RN_DLL_DISABLE_DELAY; + txcdll_val = type->disable_dll_tx_bit; break; case PHY_INTERFACE_MODE_RGMII_TXID: - rxcdll_val = KSZ9131RN_DLL_DISABLE_DELAY; + rxcdll_val = type->disable_dll_rx_bit; txcdll_val = KSZ9131RN_DLL_ENABLE_DELAY; break; default: @@ -1203,13 +1220,13 @@ static int ksz9131_config_rgmii_delay(struct phy_device *phydev) } ret = phy_modify_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG, - KSZ9131RN_RXC_DLL_CTRL, KSZ9131RN_DLL_CTRL_BYPASS, + KSZ9131RN_RXC_DLL_CTRL, type->disable_dll_mask, rxcdll_val); if (ret < 0) return ret; return phy_modify_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG, - KSZ9131RN_TXC_DLL_CTRL, KSZ9131RN_DLL_CTRL_BYPASS, + KSZ9131RN_TXC_DLL_CTRL, type->disable_dll_mask, txcdll_val); } @@ -3152,6 +3169,146 @@ static int lan8814_probe(struct phy_device *phydev) return 0; } +#define LAN8841_MMD_TIMER_REG 0 +#define LAN8841_MMD0_REGISTER_17 17 +#define LAN8841_MMD0_REGISTER_17_DROP_OPT(x) ((x) & 0x3) +#define LAN8841_MMD0_REGISTER_17_XMIT_TOG_TX_DIS BIT(3) +#define LAN8841_OPERATION_MODE_STRAP_OVERRIDE_LOW_REG 2 +#define LAN8841_OPERATION_MODE_STRAP_OVERRIDE_LOW_REG_MAGJACK BIT(14) +#define LAN8841_MMD_ANALOG_REG 28 +#define LAN8841_ANALOG_CONTROL_1 1 +#define LAN8841_ANALOG_CONTROL_1_PLL_TRIM(x) (((x) & 0x3) << 5) +#define LAN8841_ANALOG_CONTROL_10 13 +#define LAN8841_ANALOG_CONTROL_10_PLL_DIV(x) ((x) & 0x3) +#define LAN8841_ANALOG_CONTROL_11 14 +#define LAN8841_ANALOG_CONTROL_11_LDO_REF(x) (((x) & 0x7) << 12) +#define LAN8841_TX_LOW_I_CH_C_D_POWER_MANAGMENT 69 +#define LAN8841_TX_LOW_I_CH_C_D_POWER_MANAGMENT_VAL 0xbffc +#define LAN8841_BTRX_POWER_DOWN 70 +#define LAN8841_BTRX_POWER_DOWN_QBIAS_CH_A BIT(0) +#define LAN8841_BTRX_POWER_DOWN_BTRX_CH_A BIT(1) +#define LAN8841_BTRX_POWER_DOWN_QBIAS_CH_B BIT(2) +#define LAN8841_BTRX_POWER_DOWN_BTRX_CH_B BIT(3) +#define LAN8841_BTRX_POWER_DOWN_BTRX_CH_C BIT(5) +#define LAN8841_BTRX_POWER_DOWN_BTRX_CH_D BIT(7) +#define LAN8841_ADC_CHANNEL_MASK 198 + +static int lan8841_config_init(struct phy_device *phydev) +{ + int ret; + + ret = ksz9131_config_init(phydev); + if (ret) + return ret; + + /* 100BT Clause 40 improvenent errata */ + phy_write_mmd(phydev, LAN8841_MMD_ANALOG_REG, + LAN8841_ANALOG_CONTROL_1, + LAN8841_ANALOG_CONTROL_1_PLL_TRIM(0x2)); + phy_write_mmd(phydev, LAN8841_MMD_ANALOG_REG, + LAN8841_ANALOG_CONTROL_10, + LAN8841_ANALOG_CONTROL_10_PLL_DIV(0x1)); + + /* 10M/100M Ethernet Signal Tuning Errata for Shorted-Center Tap + * Magnetics + */ + ret = phy_read_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG, + LAN8841_OPERATION_MODE_STRAP_OVERRIDE_LOW_REG); + if (ret & LAN8841_OPERATION_MODE_STRAP_OVERRIDE_LOW_REG_MAGJACK) { + phy_write_mmd(phydev, LAN8841_MMD_ANALOG_REG, + LAN8841_TX_LOW_I_CH_C_D_POWER_MANAGMENT, + LAN8841_TX_LOW_I_CH_C_D_POWER_MANAGMENT_VAL); + phy_write_mmd(phydev, LAN8841_MMD_ANALOG_REG, + LAN8841_BTRX_POWER_DOWN, + LAN8841_BTRX_POWER_DOWN_QBIAS_CH_A | + LAN8841_BTRX_POWER_DOWN_BTRX_CH_A | + LAN8841_BTRX_POWER_DOWN_QBIAS_CH_B | + LAN8841_BTRX_POWER_DOWN_BTRX_CH_B | + LAN8841_BTRX_POWER_DOWN_BTRX_CH_C | + LAN8841_BTRX_POWER_DOWN_BTRX_CH_D); + } + + /* LDO Adjustment errata */ + phy_write_mmd(phydev, LAN8841_MMD_ANALOG_REG, + LAN8841_ANALOG_CONTROL_11, + LAN8841_ANALOG_CONTROL_11_LDO_REF(1)); + + /* 100BT RGMII latency tuning errata */ + phy_write_mmd(phydev, MDIO_MMD_PMAPMD, + LAN8841_ADC_CHANNEL_MASK, 0x0); + phy_write_mmd(phydev, LAN8841_MMD_TIMER_REG, + LAN8841_MMD0_REGISTER_17, + LAN8841_MMD0_REGISTER_17_DROP_OPT(2) | + LAN8841_MMD0_REGISTER_17_XMIT_TOG_TX_DIS); + + return 0; +} + +#define LAN8841_OUTPUT_CTRL 25 +#define LAN8841_OUTPUT_CTRL_INT_BUFFER BIT(14) + +static int lan8841_config_intr(struct phy_device *phydev) +{ + int err; + + phy_modify(phydev, LAN8841_OUTPUT_CTRL, + LAN8841_OUTPUT_CTRL_INT_BUFFER, 0); + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + err = phy_read(phydev, LAN8814_INTS); + if (err) + return err; + + err = phy_write(phydev, LAN8814_INTC, + LAN8814_INT_LINK); + } else { + err = phy_write(phydev, LAN8814_INTC, 0); + if (err) + return err; + + err = phy_read(phydev, LAN8814_INTS); + } + + return err; +} + +static irqreturn_t lan8841_handle_interrupt(struct phy_device *phydev) +{ + int irq_status; + + irq_status = phy_read(phydev, LAN8814_INTS); + if (irq_status < 0) { + phy_error(phydev); + return IRQ_NONE; + } + + if (irq_status & LAN8814_INT_LINK) { + phy_trigger_machine(phydev); + return IRQ_HANDLED; + } + + return IRQ_NONE; +} + +#define LAN8841_OPERATION_MODE_STRAP_LOW_REGISTER 3 +#define LAN8841_OPERATION_MODE_STRAP_LOW_REGISTER_STRAP_RGMII_EN BIT(0) + +static int lan8841_probe(struct phy_device *phydev) +{ + int err; + + err = kszphy_probe(phydev); + if (err) + return err; + + if (phy_read_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG, + LAN8841_OPERATION_MODE_STRAP_LOW_REGISTER) & + LAN8841_OPERATION_MODE_STRAP_LOW_REGISTER_STRAP_RGMII_EN) + phydev->interface = PHY_INTERFACE_MODE_RGMII_RXID; + + return 0; +} + static struct phy_driver ksphy_driver[] = { { .phy_id = PHY_ID_KS8737, @@ -3362,12 +3519,30 @@ static struct phy_driver ksphy_driver[] = { .config_intr = lan8804_config_intr, .handle_interrupt = lan8804_handle_interrupt, }, { + .phy_id = PHY_ID_LAN8841, + .phy_id_mask = MICREL_PHY_ID_MASK, + .name = "Microchip LAN8841 Gigabit PHY", + .flags = PHY_POLL_CABLE_TEST, + .driver_data = &lan8841_type, + .config_init = lan8841_config_init, + .probe = lan8841_probe, + .soft_reset = genphy_soft_reset, + .config_intr = lan8841_config_intr, + .handle_interrupt = lan8841_handle_interrupt, + .get_sset_count = kszphy_get_sset_count, + .get_strings = kszphy_get_strings, + .get_stats = kszphy_get_stats, + .suspend = genphy_suspend, + .resume = genphy_resume, + .cable_test_start = lan8814_cable_test_start, + .cable_test_get_status = ksz886x_cable_test_get_status, +}, { .phy_id = PHY_ID_KSZ9131, .phy_id_mask = MICREL_PHY_ID_MASK, .name = "Microchip KSZ9131 Gigabit PHY", /* PHY_GBIT_FEATURES */ .flags = PHY_POLL_CABLE_TEST, - .driver_data = &ksz9021_type, + .driver_data = &ksz9131_type, .probe = kszphy_probe, .config_init = ksz9131_config_init, .config_intr = kszphy_config_intr, @@ -3446,6 +3621,7 @@ static struct mdio_device_id __maybe_unused micrel_tbl[] = { { PHY_ID_KSZ886X, MICREL_PHY_ID_MASK }, { PHY_ID_LAN8814, MICREL_PHY_ID_MASK }, { PHY_ID_LAN8804, MICREL_PHY_ID_MASK }, + { PHY_ID_LAN8841, MICREL_PHY_ID_MASK }, { } }; diff --git a/drivers/net/phy/motorcomm.c b/drivers/net/phy/motorcomm.c index 685190db72de..ee7c37dfdca0 100644 --- a/drivers/net/phy/motorcomm.c +++ b/drivers/net/phy/motorcomm.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0+ /* - * Motorcomm 8511/8521/8531S PHY driver. + * Motorcomm 8511/8521/8531/8531S PHY driver. * * Author: Peter Geis <pgwipeout@gmail.com> * Author: Frank <Frank.Sae@motor-comm.com> @@ -10,10 +10,12 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/phy.h> +#include <linux/of.h> #define PHY_ID_YT8511 0x0000010a -#define PHY_ID_YT8521 0x0000011A -#define PHY_ID_YT8531S 0x4F51E91A +#define PHY_ID_YT8521 0x0000011a +#define PHY_ID_YT8531 0x4f51e91b +#define PHY_ID_YT8531S 0x4f51e91a /* YT8521/YT8531S Register Overview * UTP Register space | FIBER Register space @@ -161,6 +163,11 @@ #define YT8521_CHIP_CONFIG_REG 0xA001 #define YT8521_CCR_SW_RST BIT(15) +/* 1b0 disable 1.9ns rxc clock delay *default* + * 1b1 enable 1.9ns rxc clock delay + */ +#define YT8521_CCR_RXC_DLY_EN BIT(8) +#define YT8521_CCR_RXC_DLY_1_900_NS 1900 #define YT8521_CCR_MODE_SEL_MASK (BIT(2) | BIT(1) | BIT(0)) #define YT8521_CCR_MODE_UTP_TO_RGMII 0 @@ -178,22 +185,29 @@ #define YT8521_MODE_POLL 0x3 #define YT8521_RGMII_CONFIG1_REG 0xA003 - -/* TX Gig-E Delay is bits 3:0, default 0x1 - * TX Fast-E Delay is bits 7:4, default 0xf - * RX Delay is bits 13:10, default 0x0 - * Delay = 150ps * N - * On = 2250ps, off = 0ps +/* 1b0 use original tx_clk_rgmii *default* + * 1b1 use inverted tx_clk_rgmii. */ -#define YT8521_RC1R_RX_DELAY_MASK (0xF << 10) -#define YT8521_RC1R_RX_DELAY_EN (0xF << 10) -#define YT8521_RC1R_RX_DELAY_DIS (0x0 << 10) -#define YT8521_RC1R_FE_TX_DELAY_MASK (0xF << 4) -#define YT8521_RC1R_FE_TX_DELAY_EN (0xF << 4) -#define YT8521_RC1R_FE_TX_DELAY_DIS (0x0 << 4) -#define YT8521_RC1R_GE_TX_DELAY_MASK (0xF << 0) -#define YT8521_RC1R_GE_TX_DELAY_EN (0xF << 0) -#define YT8521_RC1R_GE_TX_DELAY_DIS (0x0 << 0) +#define YT8521_RC1R_TX_CLK_SEL_INVERTED BIT(14) +#define YT8521_RC1R_RX_DELAY_MASK GENMASK(13, 10) +#define YT8521_RC1R_FE_TX_DELAY_MASK GENMASK(7, 4) +#define YT8521_RC1R_GE_TX_DELAY_MASK GENMASK(3, 0) +#define YT8521_RC1R_RGMII_0_000_NS 0 +#define YT8521_RC1R_RGMII_0_150_NS 1 +#define YT8521_RC1R_RGMII_0_300_NS 2 +#define YT8521_RC1R_RGMII_0_450_NS 3 +#define YT8521_RC1R_RGMII_0_600_NS 4 +#define YT8521_RC1R_RGMII_0_750_NS 5 +#define YT8521_RC1R_RGMII_0_900_NS 6 +#define YT8521_RC1R_RGMII_1_050_NS 7 +#define YT8521_RC1R_RGMII_1_200_NS 8 +#define YT8521_RC1R_RGMII_1_350_NS 9 +#define YT8521_RC1R_RGMII_1_500_NS 10 +#define YT8521_RC1R_RGMII_1_650_NS 11 +#define YT8521_RC1R_RGMII_1_800_NS 12 +#define YT8521_RC1R_RGMII_1_950_NS 13 +#define YT8521_RC1R_RGMII_2_100_NS 14 +#define YT8521_RC1R_RGMII_2_250_NS 15 #define YTPHY_MISC_CONFIG_REG 0xA006 #define YTPHY_MCR_FIBER_SPEED_MASK BIT(0) @@ -222,11 +236,36 @@ */ #define YTPHY_WCR_TYPE_PULSE BIT(0) -#define YT8531S_SYNCE_CFG_REG 0xA012 -#define YT8531S_SCR_SYNCE_ENABLE BIT(6) +#define YTPHY_SYNCE_CFG_REG 0xA012 +#define YT8521_SCR_SYNCE_ENABLE BIT(5) +/* 1b0 output 25m clock + * 1b1 output 125m clock *default* + */ +#define YT8521_SCR_CLK_FRE_SEL_125M BIT(3) +#define YT8521_SCR_CLK_SRC_MASK GENMASK(2, 1) +#define YT8521_SCR_CLK_SRC_PLL_125M 0 +#define YT8521_SCR_CLK_SRC_UTP_RX 1 +#define YT8521_SCR_CLK_SRC_SDS_RX 2 +#define YT8521_SCR_CLK_SRC_REF_25M 3 +#define YT8531_SCR_SYNCE_ENABLE BIT(6) +/* 1b0 output 25m clock *default* + * 1b1 output 125m clock + */ +#define YT8531_SCR_CLK_FRE_SEL_125M BIT(4) +#define YT8531_SCR_CLK_SRC_MASK GENMASK(3, 1) +#define YT8531_SCR_CLK_SRC_PLL_125M 0 +#define YT8531_SCR_CLK_SRC_UTP_RX 1 +#define YT8531_SCR_CLK_SRC_SDS_RX 2 +#define YT8531_SCR_CLK_SRC_CLOCK_FROM_DIGITAL 3 +#define YT8531_SCR_CLK_SRC_REF_25M 4 +#define YT8531_SCR_CLK_SRC_SSC_25M 5 /* Extended Register end */ +#define YTPHY_DTS_OUTPUT_CLK_DIS 0 +#define YTPHY_DTS_OUTPUT_CLK_25M 25000000 +#define YTPHY_DTS_OUTPUT_CLK_125M 125000000 + struct yt8521_priv { /* combo_advertising is used for case of YT8521 in combo mode, * this means that yt8521 may work in utp or fiber mode which depends @@ -479,6 +518,61 @@ err_restore_page: return phy_restore_page(phydev, old_page, ret); } +static int yt8531_set_wol(struct phy_device *phydev, + struct ethtool_wolinfo *wol) +{ + const u16 mac_addr_reg[] = { + YTPHY_WOL_MACADDR2_REG, + YTPHY_WOL_MACADDR1_REG, + YTPHY_WOL_MACADDR0_REG, + }; + const u8 *mac_addr; + u16 mask, val; + int ret; + u8 i; + + if (wol->wolopts & WAKE_MAGIC) { + mac_addr = phydev->attached_dev->dev_addr; + + /* Store the device address for the magic packet */ + for (i = 0; i < 3; i++) { + ret = ytphy_write_ext_with_lock(phydev, mac_addr_reg[i], + ((mac_addr[i * 2] << 8)) | + (mac_addr[i * 2 + 1])); + if (ret < 0) + return ret; + } + + /* Enable WOL feature */ + mask = YTPHY_WCR_PULSE_WIDTH_MASK | YTPHY_WCR_INTR_SEL; + val = YTPHY_WCR_ENABLE | YTPHY_WCR_INTR_SEL; + val |= YTPHY_WCR_TYPE_PULSE | YTPHY_WCR_PULSE_WIDTH_672MS; + ret = ytphy_modify_ext_with_lock(phydev, YTPHY_WOL_CONFIG_REG, + mask, val); + if (ret < 0) + return ret; + + /* Enable WOL interrupt */ + ret = phy_modify(phydev, YTPHY_INTERRUPT_ENABLE_REG, 0, + YTPHY_IER_WOL); + if (ret < 0) + return ret; + } else { + /* Disable WOL feature */ + mask = YTPHY_WCR_ENABLE | YTPHY_WCR_INTR_SEL; + ret = ytphy_modify_ext_with_lock(phydev, YTPHY_WOL_CONFIG_REG, + mask, 0); + + /* Disable WOL interrupt */ + ret = phy_modify(phydev, YTPHY_INTERRUPT_ENABLE_REG, + YTPHY_IER_WOL, 0); + if (ret < 0) + return ret; + } + + return 0; +} + static int yt8511_read_page(struct phy_device *phydev) { return __phy_read(phydev, YT8511_PAGE_SELECT); @@ -594,6 +688,153 @@ static int yt8521_write_page(struct phy_device *phydev, int page) }; /** + * struct ytphy_cfg_reg_map - map a config value to a register value + * @cfg: value in device configuration + * @reg: value in the register + */ +struct ytphy_cfg_reg_map { + u32 cfg; + u32 reg; +}; + +static const struct ytphy_cfg_reg_map ytphy_rgmii_delays[] = { + /* for tx delay / rx delay with YT8521_CCR_RXC_DLY_EN is not set. */ + { 0, YT8521_RC1R_RGMII_0_000_NS }, + { 150, YT8521_RC1R_RGMII_0_150_NS }, + { 300, YT8521_RC1R_RGMII_0_300_NS }, + { 450, YT8521_RC1R_RGMII_0_450_NS }, + { 600, YT8521_RC1R_RGMII_0_600_NS }, + { 750, YT8521_RC1R_RGMII_0_750_NS }, + { 900, YT8521_RC1R_RGMII_0_900_NS }, + { 1050, YT8521_RC1R_RGMII_1_050_NS }, + { 1200, YT8521_RC1R_RGMII_1_200_NS }, + { 1350, YT8521_RC1R_RGMII_1_350_NS }, + { 1500, YT8521_RC1R_RGMII_1_500_NS }, + { 1650, YT8521_RC1R_RGMII_1_650_NS }, + { 1800, YT8521_RC1R_RGMII_1_800_NS }, + { 1950, YT8521_RC1R_RGMII_1_950_NS }, /* default tx/rx delay */ + { 2100, YT8521_RC1R_RGMII_2_100_NS }, + { 2250, YT8521_RC1R_RGMII_2_250_NS }, + + /* only for rx delay with YT8521_CCR_RXC_DLY_EN is set. */ + { 0 + YT8521_CCR_RXC_DLY_1_900_NS, YT8521_RC1R_RGMII_0_000_NS }, + { 150 + YT8521_CCR_RXC_DLY_1_900_NS, YT8521_RC1R_RGMII_0_150_NS }, + { 300 + YT8521_CCR_RXC_DLY_1_900_NS, YT8521_RC1R_RGMII_0_300_NS }, + { 450 + YT8521_CCR_RXC_DLY_1_900_NS, YT8521_RC1R_RGMII_0_450_NS }, + { 600 + YT8521_CCR_RXC_DLY_1_900_NS, YT8521_RC1R_RGMII_0_600_NS }, + { 750 + YT8521_CCR_RXC_DLY_1_900_NS, YT8521_RC1R_RGMII_0_750_NS }, + { 900 + YT8521_CCR_RXC_DLY_1_900_NS, YT8521_RC1R_RGMII_0_900_NS }, + { 1050 + YT8521_CCR_RXC_DLY_1_900_NS, YT8521_RC1R_RGMII_1_050_NS }, + { 1200 + YT8521_CCR_RXC_DLY_1_900_NS, YT8521_RC1R_RGMII_1_200_NS }, + { 1350 + YT8521_CCR_RXC_DLY_1_900_NS, YT8521_RC1R_RGMII_1_350_NS }, + { 1500 + YT8521_CCR_RXC_DLY_1_900_NS, YT8521_RC1R_RGMII_1_500_NS }, + { 1650 + YT8521_CCR_RXC_DLY_1_900_NS, YT8521_RC1R_RGMII_1_650_NS }, + { 1800 + YT8521_CCR_RXC_DLY_1_900_NS, YT8521_RC1R_RGMII_1_800_NS }, + { 1950 + YT8521_CCR_RXC_DLY_1_900_NS, YT8521_RC1R_RGMII_1_950_NS }, + { 2100 + YT8521_CCR_RXC_DLY_1_900_NS, YT8521_RC1R_RGMII_2_100_NS }, + { 2250 + YT8521_CCR_RXC_DLY_1_900_NS, YT8521_RC1R_RGMII_2_250_NS } +}; + +static u32 ytphy_get_delay_reg_value(struct phy_device *phydev, + const char *prop_name, + const struct ytphy_cfg_reg_map *tbl, + int tb_size, + u16 *rxc_dly_en, + u32 dflt) +{ + struct device_node *node = phydev->mdio.dev.of_node; + int tb_size_half = tb_size / 2; + u32 val; + int i; + + if (of_property_read_u32(node, prop_name, &val)) + goto err_dts_val; + + /* when rxc_dly_en is NULL, it is get the delay for tx, only half of + * tb_size is valid. + */ + if (!rxc_dly_en) + tb_size = tb_size_half; + + for (i = 0; i < tb_size; i++) { + if (tbl[i].cfg == val) { + if (rxc_dly_en && i < tb_size_half) + *rxc_dly_en = 0; + return tbl[i].reg; + } + } + + phydev_warn(phydev, "Unsupported value %d for %s using default (%u)\n", + val, prop_name, dflt); + +err_dts_val: + /* when rxc_dly_en is not NULL, it is get the delay for rx. + * The rx default in dts and ytphy_rgmii_clk_delay_config is 1950 ps, + * so YT8521_CCR_RXC_DLY_EN should not be set. + */ + if (rxc_dly_en) + *rxc_dly_en = 0; + + return dflt; +} + +static int ytphy_rgmii_clk_delay_config(struct phy_device *phydev) +{ + int tb_size = ARRAY_SIZE(ytphy_rgmii_delays); + u16 rxc_dly_en = YT8521_CCR_RXC_DLY_EN; + u32 rx_reg, tx_reg; + u16 mask, val = 0; + int ret; + + rx_reg = ytphy_get_delay_reg_value(phydev, "rx-internal-delay-ps", + ytphy_rgmii_delays, tb_size, + &rxc_dly_en, + YT8521_RC1R_RGMII_1_950_NS); + tx_reg = ytphy_get_delay_reg_value(phydev, "tx-internal-delay-ps", + ytphy_rgmii_delays, tb_size, NULL, + YT8521_RC1R_RGMII_1_950_NS); + + switch (phydev->interface) { + case PHY_INTERFACE_MODE_RGMII: + rxc_dly_en = 0; + break; + case PHY_INTERFACE_MODE_RGMII_RXID: + val |= FIELD_PREP(YT8521_RC1R_RX_DELAY_MASK, rx_reg); + break; + case PHY_INTERFACE_MODE_RGMII_TXID: + rxc_dly_en = 0; + val |= FIELD_PREP(YT8521_RC1R_GE_TX_DELAY_MASK, tx_reg); + break; + case PHY_INTERFACE_MODE_RGMII_ID: + val |= FIELD_PREP(YT8521_RC1R_RX_DELAY_MASK, rx_reg) | + FIELD_PREP(YT8521_RC1R_GE_TX_DELAY_MASK, tx_reg); + break; + default: /* do not support other modes */ + return -EOPNOTSUPP; + } + + ret = ytphy_modify_ext(phydev, YT8521_CHIP_CONFIG_REG, + YT8521_CCR_RXC_DLY_EN, rxc_dly_en); + if (ret < 0) + return ret; + + /* Generally, it is not necessary to adjust YT8521_RC1R_FE_TX_DELAY */ + mask = YT8521_RC1R_RX_DELAY_MASK | YT8521_RC1R_GE_TX_DELAY_MASK; + return ytphy_modify_ext(phydev, YT8521_RGMII_CONFIG1_REG, mask, val); +} + +static int ytphy_rgmii_clk_delay_config_with_lock(struct phy_device *phydev) +{ + int ret; + + phy_lock_mdio_bus(phydev); + ret = ytphy_rgmii_clk_delay_config(phydev); + phy_unlock_mdio_bus(phydev); + + return ret; +} + +/** * yt8521_probe() - read chip config then set suitable polling_mode * @phydev: a pointer to a &struct phy_device * @@ -601,9 +842,12 @@ static int yt8521_write_page(struct phy_device *phydev, int page) */ static int yt8521_probe(struct phy_device *phydev) { + struct device_node *node = phydev->mdio.dev.of_node; struct device *dev = &phydev->mdio.dev; struct yt8521_priv *priv; int chip_config; + u16 mask, val; + u32 freq; int ret; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); @@ -648,27 +892,107 @@ static int yt8521_probe(struct phy_device *phydev) return ret; } - return 0; + if (of_property_read_u32(node, "motorcomm,clk-out-frequency-hz", &freq)) + freq = YTPHY_DTS_OUTPUT_CLK_DIS; + + if (phydev->drv->phy_id == PHY_ID_YT8521) { + switch (freq) { + case YTPHY_DTS_OUTPUT_CLK_DIS: + mask = YT8521_SCR_SYNCE_ENABLE; + val = 0; + break; + case YTPHY_DTS_OUTPUT_CLK_25M: + mask = YT8521_SCR_SYNCE_ENABLE | + YT8521_SCR_CLK_SRC_MASK | + YT8521_SCR_CLK_FRE_SEL_125M; + val = YT8521_SCR_SYNCE_ENABLE | + FIELD_PREP(YT8521_SCR_CLK_SRC_MASK, + YT8521_SCR_CLK_SRC_REF_25M); + break; + case YTPHY_DTS_OUTPUT_CLK_125M: + mask = YT8521_SCR_SYNCE_ENABLE | + YT8521_SCR_CLK_SRC_MASK | + YT8521_SCR_CLK_FRE_SEL_125M; + val = YT8521_SCR_SYNCE_ENABLE | + YT8521_SCR_CLK_FRE_SEL_125M | + FIELD_PREP(YT8521_SCR_CLK_SRC_MASK, + YT8521_SCR_CLK_SRC_PLL_125M); + break; + default: + phydev_warn(phydev, "Freq err:%u\n", freq); + return -EINVAL; + } + } else if (phydev->drv->phy_id == PHY_ID_YT8531S) { + switch (freq) { + case YTPHY_DTS_OUTPUT_CLK_DIS: + mask = YT8531_SCR_SYNCE_ENABLE; + val = 0; + break; + case YTPHY_DTS_OUTPUT_CLK_25M: + mask = YT8531_SCR_SYNCE_ENABLE | + YT8531_SCR_CLK_SRC_MASK | + YT8531_SCR_CLK_FRE_SEL_125M; + val = YT8531_SCR_SYNCE_ENABLE | + FIELD_PREP(YT8531_SCR_CLK_SRC_MASK, + YT8531_SCR_CLK_SRC_REF_25M); + break; + case YTPHY_DTS_OUTPUT_CLK_125M: + mask = YT8531_SCR_SYNCE_ENABLE | + YT8531_SCR_CLK_SRC_MASK | + YT8531_SCR_CLK_FRE_SEL_125M; + val = YT8531_SCR_SYNCE_ENABLE | + YT8531_SCR_CLK_FRE_SEL_125M | + FIELD_PREP(YT8531_SCR_CLK_SRC_MASK, + YT8531_SCR_CLK_SRC_PLL_125M); + break; + default: + phydev_warn(phydev, "Freq err:%u\n", freq); + return -EINVAL; + } + } else { + phydev_warn(phydev, "PHY id err\n"); + return -EINVAL; + } + + return ytphy_modify_ext_with_lock(phydev, YTPHY_SYNCE_CFG_REG, mask, + val); } -/** - * yt8531s_probe() - read chip config then set suitable polling_mode - * @phydev: a pointer to a &struct phy_device - * - * returns 0 or negative errno code - */ -static int yt8531s_probe(struct phy_device *phydev) +static int yt8531_probe(struct phy_device *phydev) { - int ret; + struct device_node *node = phydev->mdio.dev.of_node; + u16 mask, val; + u32 freq; - /* Disable SyncE clock output by default */ - ret = ytphy_modify_ext_with_lock(phydev, YT8531S_SYNCE_CFG_REG, - YT8531S_SCR_SYNCE_ENABLE, 0); - if (ret < 0) - return ret; + if (of_property_read_u32(node, "motorcomm,clk-out-frequency-hz", &freq)) + freq = YTPHY_DTS_OUTPUT_CLK_DIS; + + switch (freq) { + case YTPHY_DTS_OUTPUT_CLK_DIS: + mask = YT8531_SCR_SYNCE_ENABLE; + val = 0; + break; + case YTPHY_DTS_OUTPUT_CLK_25M: + mask = YT8531_SCR_SYNCE_ENABLE | YT8531_SCR_CLK_SRC_MASK | + YT8531_SCR_CLK_FRE_SEL_125M; + val = YT8531_SCR_SYNCE_ENABLE | + FIELD_PREP(YT8531_SCR_CLK_SRC_MASK, + YT8531_SCR_CLK_SRC_REF_25M); + break; + case YTPHY_DTS_OUTPUT_CLK_125M: + mask = YT8531_SCR_SYNCE_ENABLE | YT8531_SCR_CLK_SRC_MASK | + YT8531_SCR_CLK_FRE_SEL_125M; + val = YT8531_SCR_SYNCE_ENABLE | YT8531_SCR_CLK_FRE_SEL_125M | + FIELD_PREP(YT8531_SCR_CLK_SRC_MASK, + YT8531_SCR_CLK_SRC_PLL_125M); + break; + default: + phydev_warn(phydev, "Freq err:%u\n", freq); + return -EINVAL; + } - /* same as yt8521_probe */ - return yt8521_probe(phydev); + return ytphy_modify_ext_with_lock(phydev, YTPHY_SYNCE_CFG_REG, mask, + val); } /** @@ -1133,65 +1457,128 @@ static int yt8521_resume(struct phy_device *phydev) */ static int yt8521_config_init(struct phy_device *phydev) { + struct device_node *node = phydev->mdio.dev.of_node; int old_page; int ret = 0; - u16 val; old_page = phy_select_page(phydev, YT8521_RSSR_UTP_SPACE); if (old_page < 0) goto err_restore_page; - switch (phydev->interface) { - case PHY_INTERFACE_MODE_RGMII: - val = YT8521_RC1R_GE_TX_DELAY_DIS | YT8521_RC1R_FE_TX_DELAY_DIS; - val |= YT8521_RC1R_RX_DELAY_DIS; - break; - case PHY_INTERFACE_MODE_RGMII_RXID: - val = YT8521_RC1R_GE_TX_DELAY_DIS | YT8521_RC1R_FE_TX_DELAY_DIS; - val |= YT8521_RC1R_RX_DELAY_EN; - break; - case PHY_INTERFACE_MODE_RGMII_TXID: - val = YT8521_RC1R_GE_TX_DELAY_EN | YT8521_RC1R_FE_TX_DELAY_EN; - val |= YT8521_RC1R_RX_DELAY_DIS; - break; - case PHY_INTERFACE_MODE_RGMII_ID: - val = YT8521_RC1R_GE_TX_DELAY_EN | YT8521_RC1R_FE_TX_DELAY_EN; - val |= YT8521_RC1R_RX_DELAY_EN; - break; - case PHY_INTERFACE_MODE_SGMII: - break; - default: /* do not support other modes */ - ret = -EOPNOTSUPP; - goto err_restore_page; - } - /* set rgmii delay mode */ if (phydev->interface != PHY_INTERFACE_MODE_SGMII) { - ret = ytphy_modify_ext(phydev, YT8521_RGMII_CONFIG1_REG, - (YT8521_RC1R_RX_DELAY_MASK | - YT8521_RC1R_FE_TX_DELAY_MASK | - YT8521_RC1R_GE_TX_DELAY_MASK), - val); + ret = ytphy_rgmii_clk_delay_config(phydev); if (ret < 0) goto err_restore_page; } - /* disable auto sleep */ - ret = ytphy_modify_ext(phydev, YT8521_EXTREG_SLEEP_CONTROL1_REG, - YT8521_ESC1R_SLEEP_SW, 0); - if (ret < 0) - goto err_restore_page; - - /* enable RXC clock when no wire plug */ - ret = ytphy_modify_ext(phydev, YT8521_CLOCK_GATING_REG, - YT8521_CGR_RX_CLK_EN, 0); - if (ret < 0) - goto err_restore_page; + if (of_property_read_bool(node, "motorcomm,auto-sleep-disabled")) { + /* disable auto sleep */ + ret = ytphy_modify_ext(phydev, YT8521_EXTREG_SLEEP_CONTROL1_REG, + YT8521_ESC1R_SLEEP_SW, 0); + if (ret < 0) + goto err_restore_page; + } + if (of_property_read_bool(node, "motorcomm,keep-pll-enabled")) { + /* enable RXC clock when no wire plug */ + ret = ytphy_modify_ext(phydev, YT8521_CLOCK_GATING_REG, + YT8521_CGR_RX_CLK_EN, 0); + if (ret < 0) + goto err_restore_page; + } err_restore_page: return phy_restore_page(phydev, old_page, ret); } +static int yt8531_config_init(struct phy_device *phydev) +{ + struct device_node *node = phydev->mdio.dev.of_node; + int ret; + + ret = ytphy_rgmii_clk_delay_config_with_lock(phydev); + if (ret < 0) + return ret; + + if (of_property_read_bool(node, "motorcomm,auto-sleep-disabled")) { + /* disable auto sleep */ + ret = ytphy_modify_ext_with_lock(phydev, + YT8521_EXTREG_SLEEP_CONTROL1_REG, + YT8521_ESC1R_SLEEP_SW, 0); + if (ret < 0) + return ret; + } + + if (of_property_read_bool(node, "motorcomm,keep-pll-enabled")) { + /* enable RXC clock when no wire plug */ + ret = ytphy_modify_ext_with_lock(phydev, + YT8521_CLOCK_GATING_REG, + YT8521_CGR_RX_CLK_EN, 0); + if (ret < 0) + return ret; + } + + return 0; +} + +/** + * yt8531_link_change_notify() - Adjust the tx clock direction according to + * the current speed and dts config. + * @phydev: a pointer to a &struct phy_device + * + * NOTE: This function is only used to adapt to VF2 with JH7110 SoC. Please + * keep "motorcomm,tx-clk-adj-enabled" not exist in dts when the soc is not + * JH7110. + */ +static void yt8531_link_change_notify(struct phy_device *phydev) +{ + struct device_node *node = phydev->mdio.dev.of_node; + bool tx_clk_adj_enabled = false; + bool tx_clk_1000_inverted; + bool tx_clk_100_inverted; + bool tx_clk_10_inverted; + u16 val = 0; + int ret; + + if (of_property_read_bool(node, "motorcomm,tx-clk-adj-enabled")) + tx_clk_adj_enabled = true; + + if (!tx_clk_adj_enabled) + return; + + if (of_property_read_bool(node, "motorcomm,tx-clk-10-inverted")) + tx_clk_10_inverted = true; + if (of_property_read_bool(node, "motorcomm,tx-clk-100-inverted")) + tx_clk_100_inverted = true; + if (of_property_read_bool(node, "motorcomm,tx-clk-1000-inverted")) + tx_clk_1000_inverted = true; + + if (phydev->speed < 0) + return; + + switch (phydev->speed) { + case SPEED_1000: + if (tx_clk_1000_inverted) + val = YT8521_RC1R_TX_CLK_SEL_INVERTED; + break; + case SPEED_100: + if (tx_clk_100_inverted) + val = YT8521_RC1R_TX_CLK_SEL_INVERTED; + break; + case SPEED_10: + if (tx_clk_10_inverted) + val = YT8521_RC1R_TX_CLK_SEL_INVERTED; + break; + default: + return; + } + + ret = ytphy_modify_ext_with_lock(phydev, YT8521_RGMII_CONFIG1_REG, + YT8521_RC1R_TX_CLK_SEL_INVERTED, val); + if (ret < 0) + phydev_warn(phydev, "Modify TX_CLK_SEL err:%d\n", ret); +} + /** * yt8521_prepare_fiber_features() - A small helper function that setup * fiber's features. @@ -1775,10 +2162,21 @@ static struct phy_driver motorcomm_phy_drvs[] = { .resume = yt8521_resume, }, { + PHY_ID_MATCH_EXACT(PHY_ID_YT8531), + .name = "YT8531 Gigabit Ethernet", + .probe = yt8531_probe, + .config_init = yt8531_config_init, + .suspend = genphy_suspend, + .resume = genphy_resume, + .get_wol = ytphy_get_wol, + .set_wol = yt8531_set_wol, + .link_change_notify = yt8531_link_change_notify, + }, + { PHY_ID_MATCH_EXACT(PHY_ID_YT8531S), .name = "YT8531S Gigabit Ethernet", .get_features = yt8521_get_features, - .probe = yt8531s_probe, + .probe = yt8521_probe, .read_page = yt8521_read_page, .write_page = yt8521_write_page, .get_wol = ytphy_get_wol, @@ -1795,7 +2193,7 @@ static struct phy_driver motorcomm_phy_drvs[] = { module_phy_driver(motorcomm_phy_drvs); -MODULE_DESCRIPTION("Motorcomm 8511/8521/8531S PHY driver"); +MODULE_DESCRIPTION("Motorcomm 8511/8521/8531/8531S PHY driver"); MODULE_AUTHOR("Peter Geis"); MODULE_AUTHOR("Frank"); MODULE_LICENSE("GPL"); @@ -1803,8 +2201,9 @@ MODULE_LICENSE("GPL"); static const struct mdio_device_id __maybe_unused motorcomm_tbl[] = { { PHY_ID_MATCH_EXACT(PHY_ID_YT8511) }, { PHY_ID_MATCH_EXACT(PHY_ID_YT8521) }, + { PHY_ID_MATCH_EXACT(PHY_ID_YT8531) }, { PHY_ID_MATCH_EXACT(PHY_ID_YT8531S) }, - { /* sentinal */ } + { /* sentinel */ } }; MODULE_DEVICE_TABLE(mdio, motorcomm_tbl); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 9ba8f973f26f..a3917c7acbd3 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1538,7 +1538,7 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, * another mac interface, so we should create a device link between * phy dev and mac dev. */ - if (phydev->mdio.bus->parent && dev->dev.parent != phydev->mdio.bus->parent) + if (dev && phydev->mdio.bus->parent && dev->dev.parent != phydev->mdio.bus->parent) phydev->devlink = device_link_add(dev->dev.parent, &phydev->mdio.dev, DL_FLAG_PM_RUNTIME | DL_FLAG_STATELESS); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 319790221d7f..ea8fcce5b2d9 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1816,10 +1816,9 @@ int phylink_fwnode_phy_connect(struct phylink *pl, ret = phy_attach_direct(pl->netdev, phy_dev, flags, pl->link_interface); - if (ret) { - phy_device_free(phy_dev); + phy_device_free(phy_dev); + if (ret) return ret; - } ret = phylink_bringup_phy(pl, phy_dev, pl->link_config.interface); if (ret) diff --git a/drivers/net/tap.c b/drivers/net/tap.c index a2be1994b389..8941aa199ea3 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -533,7 +533,7 @@ static int tap_open(struct inode *inode, struct file *file) q->sock.state = SS_CONNECTED; q->sock.file = file; q->sock.ops = &tap_socket_ops; - sock_init_data(&q->sock, &q->sk); + sock_init_data_uid(&q->sock, &q->sk, inode->i_uid); q->sk.sk_write_space = tap_sock_write_space; q->sk.sk_destruct = tap_sock_destruct; q->flags = IFF_VNET_HDR | IFF_NO_PI | IFF_TAP; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 36620afde373..ad653b32b2f0 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -3453,7 +3453,7 @@ static int tun_chr_open(struct inode *inode, struct file * file) tfile->socket.file = file; tfile->socket.ops = &tun_socket_ops; - sock_init_data(&tfile->socket, &tfile->sk); + sock_init_data_uid(&tfile->socket, &tfile->sk, inode->i_uid); tfile->sk.sk_write_space = tun_sock_write_space; tfile->sk.sk_sndbuf = INT_MAX; diff --git a/drivers/net/usb/plusb.c b/drivers/net/usb/plusb.c index 2c82fbcaab22..7a2b0094de51 100644 --- a/drivers/net/usb/plusb.c +++ b/drivers/net/usb/plusb.c @@ -57,9 +57,7 @@ static inline int pl_vendor_req(struct usbnet *dev, u8 req, u8 val, u8 index) { - return usbnet_read_cmd(dev, req, - USB_DIR_IN | USB_TYPE_VENDOR | - USB_RECIP_DEVICE, + return usbnet_write_cmd(dev, req, USB_TYPE_VENDOR | USB_RECIP_DEVICE, val, index, NULL, 0); } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index ddc3dc7ea73c..fb5e68ed3ec2 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -723,7 +723,7 @@ static unsigned int virtnet_get_headroom(struct virtnet_info *vi) * have enough headroom. */ static struct page *xdp_linearize_page(struct receive_queue *rq, - u16 *num_buf, + int *num_buf, struct page *p, int offset, int page_off, @@ -823,7 +823,7 @@ static struct sk_buff *receive_small(struct net_device *dev, if (unlikely(xdp_headroom < virtnet_get_headroom(vi))) { int offset = buf - page_address(page) + header_offset; unsigned int tlen = len + vi->hdr_len; - u16 num_buf = 1; + int num_buf = 1; xdp_headroom = virtnet_get_headroom(vi); header_offset = VIRTNET_RX_PAD + xdp_headroom; @@ -996,7 +996,7 @@ static int virtnet_build_xdp_buff_mrg(struct net_device *dev, void *buf, unsigned int len, unsigned int frame_sz, - u16 *num_buf, + int *num_buf, unsigned int *xdp_frags_truesize, struct virtnet_rq_stats *stats) { @@ -1014,6 +1014,9 @@ static int virtnet_build_xdp_buff_mrg(struct net_device *dev, xdp_prepare_buff(xdp, buf - VIRTIO_XDP_HEADROOM, VIRTIO_XDP_HEADROOM + vi->hdr_len, len - vi->hdr_len, true); + if (!*num_buf) + return 0; + if (*num_buf > 1) { /* If we want to build multi-buffer xdp, we need * to specify that the flags of xdp_buff have the @@ -1027,10 +1030,10 @@ static int virtnet_build_xdp_buff_mrg(struct net_device *dev, shinfo->xdp_frags_size = 0; } - if ((*num_buf - 1) > MAX_SKB_FRAGS) + if (*num_buf > MAX_SKB_FRAGS + 1) return -EINVAL; - while ((--*num_buf) >= 1) { + while (--*num_buf > 0) { buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx); if (unlikely(!buf)) { pr_debug("%s: rx error: %d buffers out of %d missing\n", @@ -1083,7 +1086,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, struct virtnet_rq_stats *stats) { struct virtio_net_hdr_mrg_rxbuf *hdr = buf; - u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers); + int num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers); struct page *page = virt_to_head_page(buf); int offset = buf - page_address(page); struct sk_buff *head_skb, *curr_skb; @@ -2279,9 +2282,9 @@ static int virtnet_close(struct net_device *dev) cancel_delayed_work_sync(&vi->refill); for (i = 0; i < vi->max_queue_pairs; i++) { - xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); - napi_disable(&vi->rq[i].napi); virtnet_napi_tx_disable(&vi->sq[i].napi); + napi_disable(&vi->rq[i].napi); + xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); } return 0; @@ -3816,6 +3819,12 @@ static int virtnet_validate(struct virtio_device *vdev) __virtio_clear_bit(vdev, VIRTIO_NET_F_MTU); } + if (virtio_has_feature(vdev, VIRTIO_NET_F_STANDBY) && + !virtio_has_feature(vdev, VIRTIO_NET_F_MAC)) { + dev_warn(&vdev->dev, "device advertises feature VIRTIO_NET_F_STANDBY but not VIRTIO_NET_F_MAC, disabling standby"); + __virtio_clear_bit(vdev, VIRTIO_NET_F_STANDBY); + } + return 0; } @@ -3929,6 +3938,8 @@ static int virtnet_probe(struct virtio_device *vdev) eth_hw_addr_set(dev, addr); } else { eth_hw_addr_random(dev); + dev_info(&vdev->dev, "Assigned random MAC address %pM\n", + dev->dev_addr); } /* Set up our device-specific information */ @@ -4058,6 +4069,24 @@ static int virtnet_probe(struct virtio_device *vdev) virtio_device_ready(vdev); + /* a random MAC address has been assigned, notify the device. + * We don't fail probe if VIRTIO_NET_F_CTRL_MAC_ADDR is not there + * because many devices work fine without getting MAC explicitly + */ + if (!virtio_has_feature(vdev, VIRTIO_NET_F_MAC) && + virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_MAC_ADDR)) { + struct scatterlist sg; + + sg_init_one(&sg, dev->dev_addr, dev->addr_len); + if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC, + VIRTIO_NET_CTRL_MAC_ADDR_SET, &sg)) { + pr_debug("virtio_net: setting MAC address failed\n"); + rtnl_unlock(); + err = -EINVAL; + goto free_unregister_netdev; + } + } + rtnl_unlock(); err = virtnet_cpu_notif_add(vi); diff --git a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif.c b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif.c index 7eff3531b9a5..7ff33c1d6ac7 100644 --- a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif.c +++ b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif.c @@ -152,6 +152,15 @@ static irqreturn_t t7xx_dpmaif_isr_handler(int irq, void *data) } t7xx_pcie_mac_clear_int(dpmaif_ctrl->t7xx_dev, isr_para->pcie_int); + + return IRQ_WAKE_THREAD; +} + +static irqreturn_t t7xx_dpmaif_isr_thread(int irq, void *data) +{ + struct dpmaif_isr_para *isr_para = data; + struct dpmaif_ctrl *dpmaif_ctrl = isr_para->dpmaif_ctrl; + t7xx_dpmaif_irq_cb(isr_para); t7xx_pcie_mac_set_int(dpmaif_ctrl->t7xx_dev, isr_para->pcie_int); return IRQ_HANDLED; @@ -188,7 +197,7 @@ static void t7xx_dpmaif_register_pcie_irq(struct dpmaif_ctrl *dpmaif_ctrl) t7xx_pcie_mac_clear_int(t7xx_dev, int_type); t7xx_dev->intr_handler[int_type] = t7xx_dpmaif_isr_handler; - t7xx_dev->intr_thread[int_type] = NULL; + t7xx_dev->intr_thread[int_type] = t7xx_dpmaif_isr_thread; t7xx_dev->callback_param[int_type] = isr_para; t7xx_pcie_mac_clear_int_status(t7xx_dev, int_type); diff --git a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c index aa2174a10437..f4ff2198b5ef 100644 --- a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c +++ b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c @@ -840,14 +840,13 @@ int t7xx_dpmaif_napi_rx_poll(struct napi_struct *napi, const int budget) if (!rxq->que_started) { atomic_set(&rxq->rx_processing, 0); + pm_runtime_put_autosuspend(rxq->dpmaif_ctrl->dev); dev_err(rxq->dpmaif_ctrl->dev, "Work RXQ: %d has not been started\n", rxq->index); return work_done; } - if (!rxq->sleep_lock_pending) { - pm_runtime_get_noresume(rxq->dpmaif_ctrl->dev); + if (!rxq->sleep_lock_pending) t7xx_pci_disable_sleep(t7xx_dev); - } ret = try_wait_for_completion(&t7xx_dev->sleep_lock_acquire); if (!ret) { @@ -876,22 +875,22 @@ int t7xx_dpmaif_napi_rx_poll(struct napi_struct *napi, const int budget) napi_complete_done(napi, work_done); t7xx_dpmaif_clr_ip_busy_sts(&rxq->dpmaif_ctrl->hw_info); t7xx_dpmaif_dlq_unmask_rx_done(&rxq->dpmaif_ctrl->hw_info, rxq->index); + t7xx_pci_enable_sleep(rxq->dpmaif_ctrl->t7xx_dev); + pm_runtime_mark_last_busy(rxq->dpmaif_ctrl->dev); + pm_runtime_put_autosuspend(rxq->dpmaif_ctrl->dev); + atomic_set(&rxq->rx_processing, 0); } else { t7xx_dpmaif_clr_ip_busy_sts(&rxq->dpmaif_ctrl->hw_info); } - t7xx_pci_enable_sleep(rxq->dpmaif_ctrl->t7xx_dev); - pm_runtime_mark_last_busy(rxq->dpmaif_ctrl->dev); - pm_runtime_put_noidle(rxq->dpmaif_ctrl->dev); - atomic_set(&rxq->rx_processing, 0); - return work_done; } void t7xx_dpmaif_irq_rx_done(struct dpmaif_ctrl *dpmaif_ctrl, const unsigned int que_mask) { struct dpmaif_rx_queue *rxq; - int qno; + struct dpmaif_ctrl *ctrl; + int qno, ret; qno = ffs(que_mask) - 1; if (qno < 0 || qno > DPMAIF_RXQ_NUM - 1) { @@ -900,6 +899,18 @@ void t7xx_dpmaif_irq_rx_done(struct dpmaif_ctrl *dpmaif_ctrl, const unsigned int } rxq = &dpmaif_ctrl->rxq[qno]; + ctrl = rxq->dpmaif_ctrl; + /* We need to make sure that the modem has been resumed before + * calling napi. This can't be done inside the polling function + * as we could be blocked waiting for device to be resumed, + * which can't be done from softirq context the poll function + * is running in. + */ + ret = pm_runtime_resume_and_get(ctrl->dev); + if (ret < 0 && ret != -EACCES) { + dev_err(ctrl->dev, "Failed to resume device: %d\n", ret); + return; + } napi_schedule(&rxq->napi); } diff --git a/drivers/net/wwan/t7xx/t7xx_netdev.c b/drivers/net/wwan/t7xx/t7xx_netdev.c index 494a28e386a3..3ef4a8a4f8fd 100644 --- a/drivers/net/wwan/t7xx/t7xx_netdev.c +++ b/drivers/net/wwan/t7xx/t7xx_netdev.c @@ -27,6 +27,7 @@ #include <linux/list.h> #include <linux/netdev_features.h> #include <linux/netdevice.h> +#include <linux/pm_runtime.h> #include <linux/skbuff.h> #include <linux/types.h> #include <linux/wwan.h> @@ -45,12 +46,25 @@ static void t7xx_ccmni_enable_napi(struct t7xx_ccmni_ctrl *ctlb) { - int i; + struct dpmaif_ctrl *ctrl; + int i, ret; + + ctrl = ctlb->hif_ctrl; if (ctlb->is_napi_en) return; for (i = 0; i < RXQ_NUM; i++) { + /* The usage count has to be bumped every time before calling + * napi_schedule. It will be decresed in the poll routine, + * right after napi_complete_done is called. + */ + ret = pm_runtime_resume_and_get(ctrl->dev); + if (ret < 0) { + dev_err(ctrl->dev, "Failed to resume device: %d\n", + ret); + return; + } napi_enable(ctlb->napi[i]); napi_schedule(ctlb->napi[i]); } diff --git a/drivers/net/wwan/t7xx/t7xx_pci.c b/drivers/net/wwan/t7xx/t7xx_pci.c index 871f2a27a398..226fc1703e90 100644 --- a/drivers/net/wwan/t7xx/t7xx_pci.c +++ b/drivers/net/wwan/t7xx/t7xx_pci.c @@ -121,6 +121,8 @@ void t7xx_pci_pm_init_late(struct t7xx_pci_dev *t7xx_dev) iowrite32(T7XX_L1_BIT(0), IREG_BASE(t7xx_dev) + ENABLE_ASPM_LOWPWR); atomic_set(&t7xx_dev->md_pm_state, MTK_PM_RESUMED); + pm_runtime_mark_last_busy(&t7xx_dev->pdev->dev); + pm_runtime_allow(&t7xx_dev->pdev->dev); pm_runtime_put_noidle(&t7xx_dev->pdev->dev); } diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c index 4424f53a8a0a..b57630d1d3b8 100644 --- a/drivers/nvme/host/auth.c +++ b/drivers/nvme/host/auth.c @@ -45,6 +45,8 @@ struct nvme_dhchap_queue_context { int sess_key_len; }; +struct workqueue_struct *nvme_auth_wq; + #define nvme_auth_flags_from_qid(qid) \ (qid == 0) ? 0 : BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_RESERVED #define nvme_auth_queue_from_qid(ctrl, qid) \ @@ -866,7 +868,7 @@ int nvme_auth_negotiate(struct nvme_ctrl *ctrl, int qid) chap = &ctrl->dhchap_ctxs[qid]; cancel_work_sync(&chap->auth_work); - queue_work(nvme_wq, &chap->auth_work); + queue_work(nvme_auth_wq, &chap->auth_work); return 0; } EXPORT_SYMBOL_GPL(nvme_auth_negotiate); @@ -1008,10 +1010,15 @@ EXPORT_SYMBOL_GPL(nvme_auth_free); int __init nvme_init_auth(void) { + nvme_auth_wq = alloc_workqueue("nvme-auth-wq", + WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0); + if (!nvme_auth_wq) + return -ENOMEM; + nvme_chap_buf_cache = kmem_cache_create("nvme-chap-buf-cache", CHAP_BUF_SIZE, 0, SLAB_HWCACHE_ALIGN, NULL); if (!nvme_chap_buf_cache) - return -ENOMEM; + goto err_destroy_workqueue; nvme_chap_buf_pool = mempool_create(16, mempool_alloc_slab, mempool_free_slab, nvme_chap_buf_cache); @@ -1021,6 +1028,8 @@ int __init nvme_init_auth(void) return 0; err_destroy_chap_buf_cache: kmem_cache_destroy(nvme_chap_buf_cache); +err_destroy_workqueue: + destroy_workqueue(nvme_auth_wq); return -ENOMEM; } @@ -1028,4 +1037,5 @@ void __exit nvme_exit_auth(void) { mempool_destroy(nvme_chap_buf_pool); kmem_cache_destroy(nvme_chap_buf_cache); + destroy_workqueue(nvme_auth_wq); } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 7be562a4e1aa..8b6421141162 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1093,7 +1093,7 @@ u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode) if (ns) { if (ns->head->effects) effects = le32_to_cpu(ns->head->effects->iocs[opcode]); - if (ns->head->ids.csi == NVME_CAP_CSS_NVM) + if (ns->head->ids.csi == NVME_CSI_NVM) effects |= nvme_known_nvm_effects(opcode); if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC)) dev_warn_once(ctrl->device, @@ -4921,7 +4921,9 @@ out_cleanup_admin_q: blk_mq_destroy_queue(ctrl->admin_q); blk_put_queue(ctrl->admin_q); out_free_tagset: - blk_mq_free_tag_set(ctrl->admin_tagset); + blk_mq_free_tag_set(set); + ctrl->admin_q = NULL; + ctrl->fabrics_q = NULL; return ret; } EXPORT_SYMBOL_GPL(nvme_alloc_admin_tag_set); @@ -4983,6 +4985,7 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, out_free_tag_set: blk_mq_free_tag_set(set); + ctrl->connect_q = NULL; return ret; } EXPORT_SYMBOL_GPL(nvme_alloc_io_tag_set); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 4564f16a0b20..456ee42a6133 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -3521,13 +3521,6 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, nvme_fc_init_queue(ctrl, 0); - ret = nvme_alloc_admin_tag_set(&ctrl->ctrl, &ctrl->admin_tag_set, - &nvme_fc_admin_mq_ops, - struct_size((struct nvme_fcp_op_w_sgl *)NULL, priv, - ctrl->lport->ops->fcprqst_priv_sz)); - if (ret) - goto out_free_queues; - /* * Would have been nice to init io queues tag set as well. * However, we require interaction from the controller @@ -3537,10 +3530,17 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_fc_ctrl_ops, 0); if (ret) - goto out_cleanup_tagset; + goto out_free_queues; /* at this point, teardown path changes to ref counting on nvme ctrl */ + ret = nvme_alloc_admin_tag_set(&ctrl->ctrl, &ctrl->admin_tag_set, + &nvme_fc_admin_mq_ops, + struct_size((struct nvme_fcp_op_w_sgl *)NULL, priv, + ctrl->lport->ops->fcprqst_priv_sz)); + if (ret) + goto fail_ctrl; + spin_lock_irqsave(&rport->lock, flags); list_add_tail(&ctrl->ctrl_list, &rport->ctrl_list); spin_unlock_irqrestore(&rport->lock, flags); @@ -3592,8 +3592,6 @@ fail_ctrl: return ERR_PTR(-EIO); -out_cleanup_tagset: - nvme_remove_admin_tag_set(&ctrl->ctrl); out_free_queues: kfree(ctrl->queues); out_free_ida: diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 1ff8843bc4b3..c734934c407c 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3102,6 +3102,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) nvme_start_ctrl(&dev->ctrl); nvme_put_ctrl(&dev->ctrl); + flush_work(&dev->ctrl.scan_work); return 0; out_disable: diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index ab2627e17bb9..1ab6601fdd5c 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -1685,8 +1685,10 @@ nvmet_fc_ls_create_association(struct nvmet_fc_tgtport *tgtport, else { queue = nvmet_fc_alloc_target_queue(iod->assoc, 0, be16_to_cpu(rqst->assoc_cmd.sqsize)); - if (!queue) + if (!queue) { ret = VERR_QUEUE_ALLOC_FAIL; + nvmet_fc_tgt_a_put(iod->assoc); + } } } diff --git a/drivers/nvmem/brcm_nvram.c b/drivers/nvmem/brcm_nvram.c index 34130449f2d2..39aa27942f28 100644 --- a/drivers/nvmem/brcm_nvram.c +++ b/drivers/nvmem/brcm_nvram.c @@ -98,6 +98,9 @@ static int brcm_nvram_parse(struct brcm_nvram *priv) len = le32_to_cpu(header.len); data = kzalloc(len, GFP_KERNEL); + if (!data) + return -ENOMEM; + memcpy_fromio(data, priv->base, len); data[len - 1] = '\0'; diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 321d7d63e068..34ee9d36ee7b 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -770,31 +770,32 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) return ERR_PTR(rval); } - if (config->wp_gpio) - nvmem->wp_gpio = config->wp_gpio; - else if (!config->ignore_wp) + nvmem->id = rval; + + nvmem->dev.type = &nvmem_provider_type; + nvmem->dev.bus = &nvmem_bus_type; + nvmem->dev.parent = config->dev; + + device_initialize(&nvmem->dev); + + if (!config->ignore_wp) nvmem->wp_gpio = gpiod_get_optional(config->dev, "wp", GPIOD_OUT_HIGH); if (IS_ERR(nvmem->wp_gpio)) { - ida_free(&nvmem_ida, nvmem->id); rval = PTR_ERR(nvmem->wp_gpio); - kfree(nvmem); - return ERR_PTR(rval); + nvmem->wp_gpio = NULL; + goto err_put_device; } kref_init(&nvmem->refcnt); INIT_LIST_HEAD(&nvmem->cells); - nvmem->id = rval; nvmem->owner = config->owner; if (!nvmem->owner && config->dev->driver) nvmem->owner = config->dev->driver->owner; nvmem->stride = config->stride ?: 1; nvmem->word_size = config->word_size ?: 1; nvmem->size = config->size; - nvmem->dev.type = &nvmem_provider_type; - nvmem->dev.bus = &nvmem_bus_type; - nvmem->dev.parent = config->dev; nvmem->root_only = config->root_only; nvmem->priv = config->priv; nvmem->type = config->type; @@ -822,11 +823,8 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) break; } - if (rval) { - ida_free(&nvmem_ida, nvmem->id); - kfree(nvmem); - return ERR_PTR(rval); - } + if (rval) + goto err_put_device; nvmem->read_only = device_property_present(config->dev, "read-only") || config->read_only || !nvmem->reg_write; @@ -835,28 +833,22 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) nvmem->dev.groups = nvmem_dev_groups; #endif - dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name); - - rval = device_register(&nvmem->dev); - if (rval) - goto err_put_device; - if (nvmem->nkeepout) { rval = nvmem_validate_keepouts(nvmem); if (rval) - goto err_device_del; + goto err_put_device; } if (config->compat) { rval = nvmem_sysfs_setup_compat(nvmem, config); if (rval) - goto err_device_del; + goto err_put_device; } if (config->cells) { rval = nvmem_add_cells(nvmem, config->cells, config->ncells); if (rval) - goto err_teardown_compat; + goto err_remove_cells; } rval = nvmem_add_cells_from_table(nvmem); @@ -867,17 +859,20 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) if (rval) goto err_remove_cells; + dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name); + + rval = device_add(&nvmem->dev); + if (rval) + goto err_remove_cells; + blocking_notifier_call_chain(&nvmem_notifier, NVMEM_ADD, nvmem); return nvmem; err_remove_cells: nvmem_device_remove_all_cells(nvmem); -err_teardown_compat: if (config->compat) nvmem_sysfs_remove_compat(nvmem, config); -err_device_del: - device_del(&nvmem->dev); err_put_device: put_device(&nvmem->dev); @@ -1242,16 +1237,21 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id) if (!cell_np) return ERR_PTR(-ENOENT); - nvmem_np = of_get_next_parent(cell_np); - if (!nvmem_np) + nvmem_np = of_get_parent(cell_np); + if (!nvmem_np) { + of_node_put(cell_np); return ERR_PTR(-EINVAL); + } nvmem = __nvmem_device_get(nvmem_np, device_match_of_node); of_node_put(nvmem_np); - if (IS_ERR(nvmem)) + if (IS_ERR(nvmem)) { + of_node_put(cell_np); return ERR_CAST(nvmem); + } cell_entry = nvmem_find_cell_entry_by_node(nvmem, cell_np); + of_node_put(cell_np); if (!cell_entry) { __nvmem_device_put(nvmem); return ERR_PTR(-ENOENT); diff --git a/drivers/nvmem/qcom-spmi-sdam.c b/drivers/nvmem/qcom-spmi-sdam.c index 4fcb63507ecd..8499892044b7 100644 --- a/drivers/nvmem/qcom-spmi-sdam.c +++ b/drivers/nvmem/qcom-spmi-sdam.c @@ -166,6 +166,7 @@ static const struct of_device_id sdam_match_table[] = { { .compatible = "qcom,spmi-sdam" }, {}, }; +MODULE_DEVICE_TABLE(of, sdam_match_table); static struct platform_driver sdam_driver = { .driver = { diff --git a/drivers/nvmem/sunxi_sid.c b/drivers/nvmem/sunxi_sid.c index 5750e1f4bcdb..92dfe4cb10e3 100644 --- a/drivers/nvmem/sunxi_sid.c +++ b/drivers/nvmem/sunxi_sid.c @@ -41,8 +41,21 @@ static int sunxi_sid_read(void *context, unsigned int offset, void *val, size_t bytes) { struct sunxi_sid *sid = context; + u32 word; + + /* .stride = 4 so offset is guaranteed to be aligned */ + __ioread32_copy(val, sid->base + sid->value_offset + offset, bytes / 4); - memcpy_fromio(val, sid->base + sid->value_offset + offset, bytes); + val += round_down(bytes, 4); + offset += round_down(bytes, 4); + bytes = bytes % 4; + + if (!bytes) + return 0; + + /* Handle any trailing bytes */ + word = readl_relaxed(sid->base + sid->value_offset + offset); + memcpy(val, &word, bytes); return 0; } diff --git a/drivers/of/address.c b/drivers/of/address.c index c34ac33b7338..67763e5b8c0e 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -965,8 +965,19 @@ int of_dma_get_range(struct device_node *np, const struct bus_dma_region **map) } of_dma_range_parser_init(&parser, node); - for_each_of_range(&parser, &range) + for_each_of_range(&parser, &range) { + if (range.cpu_addr == OF_BAD_ADDR) { + pr_err("translation of DMA address(%llx) to CPU address failed node(%pOF)\n", + range.bus_addr, node); + continue; + } num_ranges++; + } + + if (!num_ranges) { + ret = -EINVAL; + goto out; + } r = kcalloc(num_ranges + 1, sizeof(*r), GFP_KERNEL); if (!r) { @@ -975,18 +986,16 @@ int of_dma_get_range(struct device_node *np, const struct bus_dma_region **map) } /* - * Record all info in the generic DMA ranges array for struct device. + * Record all info in the generic DMA ranges array for struct device, + * returning an error if we don't find any parsable ranges. */ *map = r; of_dma_range_parser_init(&parser, node); for_each_of_range(&parser, &range) { pr_debug("dma_addr(%llx) cpu_addr(%llx) size(%llx)\n", range.bus_addr, range.cpu_addr, range.size); - if (range.cpu_addr == OF_BAD_ADDR) { - pr_err("translation of DMA address(%llx) to CPU address failed node(%pOF)\n", - range.bus_addr, node); + if (range.cpu_addr == OF_BAD_ADDR) continue; - } r->cpu_start = range.cpu_addr; r->dma_start = range.bus_addr; r->size = range.size; diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index f08b25195ae7..d1a68b6d03b3 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -26,7 +26,6 @@ #include <linux/serial_core.h> #include <linux/sysfs.h> #include <linux/random.h> -#include <linux/kmemleak.h> #include <asm/setup.h> /* for COMMAND_LINE_SIZE */ #include <asm/page.h> @@ -525,12 +524,9 @@ static int __init __reserved_mem_reserve_reg(unsigned long node, size = dt_mem_next_cell(dt_root_size_cells, &prop); if (size && - early_init_dt_reserve_memory(base, size, nomap) == 0) { + early_init_dt_reserve_memory(base, size, nomap) == 0) pr_debug("Reserved memory: reserved region for node '%s': base %pa, size %lu MiB\n", uname, &base, (unsigned long)(size / SZ_1M)); - if (!nomap) - kmemleak_alloc_phys(base, size, 0); - } else pr_err("Reserved memory: failed to reserve memory for node '%s': base %pa, size %lu MiB\n", uname, &base, (unsigned long)(size / SZ_1M)); diff --git a/drivers/of/platform.c b/drivers/of/platform.c index 81c8c227ab6b..b3878a98d27f 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -525,6 +525,7 @@ static int __init of_platform_default_populate_init(void) if (IS_ENABLED(CONFIG_PPC)) { struct device_node *boot_display = NULL; struct platform_device *dev; + int display_number = 0; int ret; /* Check if we have a MacOS display without a node spec */ @@ -555,16 +556,23 @@ static int __init of_platform_default_populate_init(void) if (!of_get_property(node, "linux,opened", NULL) || !of_get_property(node, "linux,boot-display", NULL)) continue; - dev = of_platform_device_create(node, "of-display", NULL); + dev = of_platform_device_create(node, "of-display.0", NULL); + of_node_put(node); if (WARN_ON(!dev)) return -ENOMEM; boot_display = node; + display_number++; break; } for_each_node_by_type(node, "display") { + char buf[14]; + const char *of_display_format = "of-display.%d"; + if (!of_get_property(node, "linux,opened", NULL) || node == boot_display) continue; - of_platform_device_create(node, "of-display", NULL); + ret = snprintf(buf, sizeof(buf), of_display_format, display_number++); + if (ret < sizeof(buf)) + of_platform_device_create(node, buf, NULL); } } else { diff --git a/drivers/parisc/pdc_stable.c b/drivers/parisc/pdc_stable.c index d6af5726ddf3..2a18f7ba2398 100644 --- a/drivers/parisc/pdc_stable.c +++ b/drivers/parisc/pdc_stable.c @@ -274,8 +274,7 @@ pdcspath_hwpath_write(struct pdcspath_entry *entry, const char *buf, size_t coun /* We'll use a local copy of buf */ count = min_t(size_t, count, sizeof(in)-1); - strncpy(in, buf, count); - in[count] = '\0'; + strscpy(in, buf, count + 1); /* Let's clean up the target. 0xff is a blank pattern */ memset(&hwpath, 0xff, sizeof(hwpath)); @@ -388,8 +387,7 @@ pdcspath_layer_write(struct pdcspath_entry *entry, const char *buf, size_t count /* We'll use a local copy of buf */ count = min_t(size_t, count, sizeof(in)-1); - strncpy(in, buf, count); - in[count] = '\0'; + strscpy(in, buf, count + 1); /* Let's clean up the target. 0 is a blank pattern */ memset(&layers, 0, sizeof(layers)); @@ -756,8 +754,7 @@ static ssize_t pdcs_auto_write(struct kobject *kobj, /* We'll use a local copy of buf */ count = min_t(size_t, count, sizeof(in)-1); - strncpy(in, buf, count); - in[count] = '\0'; + strscpy(in, buf, count + 1); /* Current flags are stored in primary boot path entry */ pathentry = &pdcspath_entry_primary; diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c index b80a9b74662b..1deb61b22bc7 100644 --- a/drivers/perf/arm-cmn.c +++ b/drivers/perf/arm-cmn.c @@ -1576,7 +1576,6 @@ static int arm_cmn_event_init(struct perf_event *event) hw->dn++; continue; } - hw->dtcs_used |= arm_cmn_node_to_xp(cmn, dn)->dtc; hw->num_dns++; if (bynodeid) break; @@ -1589,6 +1588,12 @@ static int arm_cmn_event_init(struct perf_event *event) nodeid, nid.x, nid.y, nid.port, nid.dev, type); return -EINVAL; } + /* + * Keep assuming non-cycles events count in all DTC domains; turns out + * it's hard to make a worthwhile optimisation around this, short of + * going all-in with domain-local counter allocation as well. + */ + hw->dtcs_used = (1U << cmn->num_dtcs) - 1; return arm_cmn_validate_group(cmn, event); } diff --git a/drivers/platform/x86/amd/Kconfig b/drivers/platform/x86/amd/Kconfig index a825af8126c8..2ce8cb2170df 100644 --- a/drivers/platform/x86/amd/Kconfig +++ b/drivers/platform/x86/amd/Kconfig @@ -8,6 +8,7 @@ source "drivers/platform/x86/amd/pmf/Kconfig" config AMD_PMC tristate "AMD SoC PMC driver" depends on ACPI && PCI && RTC_CLASS + select SERIO help The driver provides support for AMD Power Management Controller primarily responsible for S2Idle transactions that are driven from diff --git a/drivers/platform/x86/amd/pmc.c b/drivers/platform/x86/amd/pmc.c index 8d924986381b..3cbb01ec10e3 100644 --- a/drivers/platform/x86/amd/pmc.c +++ b/drivers/platform/x86/amd/pmc.c @@ -22,6 +22,7 @@ #include <linux/pci.h> #include <linux/platform_device.h> #include <linux/rtc.h> +#include <linux/serio.h> #include <linux/suspend.h> #include <linux/seq_file.h> #include <linux/uaccess.h> @@ -160,6 +161,10 @@ static bool enable_stb; module_param(enable_stb, bool, 0644); MODULE_PARM_DESC(enable_stb, "Enable the STB debug mechanism"); +static bool disable_workarounds; +module_param(disable_workarounds, bool, 0644); +MODULE_PARM_DESC(disable_workarounds, "Disable workarounds for platform bugs"); + static struct amd_pmc_dev pmc; static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, u32 arg, u32 *data, u8 msg, bool ret); static int amd_pmc_read_stb(struct amd_pmc_dev *dev, u32 *buf); @@ -653,6 +658,33 @@ static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev) return -EINVAL; } +static int amd_pmc_czn_wa_irq1(struct amd_pmc_dev *pdev) +{ + struct device *d; + int rc; + + if (!pdev->major) { + rc = amd_pmc_get_smu_version(pdev); + if (rc) + return rc; + } + + if (pdev->major > 64 || (pdev->major == 64 && pdev->minor > 65)) + return 0; + + d = bus_find_device_by_name(&serio_bus, NULL, "serio0"); + if (!d) + return 0; + if (device_may_wakeup(d)) { + dev_info_once(d, "Disabling IRQ1 wakeup source to avoid platform firmware bug\n"); + disable_irq_wake(1); + device_set_wakeup_enable(d, false); + } + put_device(d); + + return 0; +} + static int amd_pmc_verify_czn_rtc(struct amd_pmc_dev *pdev, u32 *arg) { struct rtc_device *rtc_device; @@ -715,8 +747,8 @@ static void amd_pmc_s2idle_prepare(void) /* Reset and Start SMU logging - to monitor the s0i3 stats */ amd_pmc_setup_smu_logging(pdev); - /* Activate CZN specific RTC functionality */ - if (pdev->cpu_id == AMD_CPU_ID_CZN) { + /* Activate CZN specific platform bug workarounds */ + if (pdev->cpu_id == AMD_CPU_ID_CZN && !disable_workarounds) { rc = amd_pmc_verify_czn_rtc(pdev, &arg); if (rc) { dev_err(pdev->dev, "failed to set RTC: %d\n", rc); @@ -782,6 +814,25 @@ static struct acpi_s2idle_dev_ops amd_pmc_s2idle_dev_ops = { .check = amd_pmc_s2idle_check, .restore = amd_pmc_s2idle_restore, }; + +static int __maybe_unused amd_pmc_suspend_handler(struct device *dev) +{ + struct amd_pmc_dev *pdev = dev_get_drvdata(dev); + + if (pdev->cpu_id == AMD_CPU_ID_CZN && !disable_workarounds) { + int rc = amd_pmc_czn_wa_irq1(pdev); + + if (rc) { + dev_err(pdev->dev, "failed to adjust keyboard wakeup: %d\n", rc); + return rc; + } + } + + return 0; +} + +static SIMPLE_DEV_PM_OPS(amd_pmc_pm, amd_pmc_suspend_handler, NULL); + #endif static const struct pci_device_id pmc_pci_ids[] = { @@ -980,6 +1031,9 @@ static struct platform_driver amd_pmc_driver = { .name = "amd_pmc", .acpi_match_table = amd_pmc_acpi_ids, .dev_groups = pmc_groups, +#ifdef CONFIG_SUSPEND + .pm = &amd_pmc_pm, +#endif }, .probe = amd_pmc_probe, .remove = amd_pmc_remove, diff --git a/drivers/platform/x86/amd/pmf/auto-mode.c b/drivers/platform/x86/amd/pmf/auto-mode.c index 644af42e07cf..96a8e1832c05 100644 --- a/drivers/platform/x86/amd/pmf/auto-mode.c +++ b/drivers/platform/x86/amd/pmf/auto-mode.c @@ -275,13 +275,8 @@ int amd_pmf_reset_amt(struct amd_pmf_dev *dev) */ if (is_apmf_func_supported(dev, APMF_FUNC_STATIC_SLIDER_GRANULAR)) { - int mode = amd_pmf_get_pprof_modes(dev); - - if (mode < 0) - return mode; - dev_dbg(dev->dev, "resetting AMT thermals\n"); - amd_pmf_update_slider(dev, SLIDER_OP_SET, mode, NULL); + amd_pmf_set_sps_power_limits(dev); } return 0; } @@ -299,7 +294,5 @@ void amd_pmf_deinit_auto_mode(struct amd_pmf_dev *dev) void amd_pmf_init_auto_mode(struct amd_pmf_dev *dev) { amd_pmf_load_defaults_auto_mode(dev); - /* update the thermal limits for Automode */ - amd_pmf_set_automode(dev, config_store.current_mode, NULL); amd_pmf_init_metrics_table(dev); } diff --git a/drivers/platform/x86/amd/pmf/cnqf.c b/drivers/platform/x86/amd/pmf/cnqf.c index 3f9731a2ac28..4beb22a19466 100644 --- a/drivers/platform/x86/amd/pmf/cnqf.c +++ b/drivers/platform/x86/amd/pmf/cnqf.c @@ -103,7 +103,7 @@ int amd_pmf_trans_cnqf(struct amd_pmf_dev *dev, int socket_power, ktime_t time_l src = amd_pmf_cnqf_get_power_source(dev); - if (dev->current_profile == PLATFORM_PROFILE_BALANCED) { + if (is_pprof_balanced(dev)) { amd_pmf_set_cnqf(dev, src, config_store.current_mode, NULL); } else { /* @@ -307,13 +307,9 @@ static ssize_t cnqf_enable_store(struct device *dev, const char *buf, size_t count) { struct amd_pmf_dev *pdev = dev_get_drvdata(dev); - int mode, result, src; + int result, src; bool input; - mode = amd_pmf_get_pprof_modes(pdev); - if (mode < 0) - return mode; - result = kstrtobool(buf, &input); if (result) return result; @@ -321,11 +317,11 @@ static ssize_t cnqf_enable_store(struct device *dev, src = amd_pmf_cnqf_get_power_source(pdev); pdev->cnqf_enabled = input; - if (pdev->cnqf_enabled && pdev->current_profile == PLATFORM_PROFILE_BALANCED) { + if (pdev->cnqf_enabled && is_pprof_balanced(pdev)) { amd_pmf_set_cnqf(pdev, src, config_store.current_mode, NULL); } else { if (is_apmf_func_supported(pdev, APMF_FUNC_STATIC_SLIDER_GRANULAR)) - amd_pmf_update_slider(pdev, SLIDER_OP_SET, mode, NULL); + amd_pmf_set_sps_power_limits(pdev); } dev_dbg(pdev->dev, "Received CnQF %s\n", input ? "on" : "off"); @@ -386,7 +382,7 @@ int amd_pmf_init_cnqf(struct amd_pmf_dev *dev) dev->cnqf_enabled = amd_pmf_check_flags(dev); /* update the thermal for CnQF */ - if (dev->cnqf_enabled && dev->current_profile == PLATFORM_PROFILE_BALANCED) { + if (dev->cnqf_enabled && is_pprof_balanced(dev)) { src = amd_pmf_cnqf_get_power_source(dev); amd_pmf_set_cnqf(dev, src, config_store.current_mode, NULL); } diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c index a5f5a4bcff6d..da23639071d7 100644 --- a/drivers/platform/x86/amd/pmf/core.c +++ b/drivers/platform/x86/amd/pmf/core.c @@ -58,6 +58,25 @@ static bool force_load; module_param(force_load, bool, 0444); MODULE_PARM_DESC(force_load, "Force load this driver on supported older platforms (experimental)"); +static int amd_pmf_pwr_src_notify_call(struct notifier_block *nb, unsigned long event, void *data) +{ + struct amd_pmf_dev *pmf = container_of(nb, struct amd_pmf_dev, pwr_src_notifier); + + if (event != PSY_EVENT_PROP_CHANGED) + return NOTIFY_OK; + + if (is_apmf_func_supported(pmf, APMF_FUNC_AUTO_MODE) || + is_apmf_func_supported(pmf, APMF_FUNC_DYN_SLIDER_DC) || + is_apmf_func_supported(pmf, APMF_FUNC_DYN_SLIDER_AC)) { + if ((pmf->amt_enabled || pmf->cnqf_enabled) && is_pprof_balanced(pmf)) + return NOTIFY_DONE; + } + + amd_pmf_set_sps_power_limits(pmf); + + return NOTIFY_OK; +} + static int current_power_limits_show(struct seq_file *seq, void *unused) { struct amd_pmf_dev *dev = seq->private; @@ -366,14 +385,18 @@ static int amd_pmf_probe(struct platform_device *pdev) if (!dev->regbase) return -ENOMEM; + mutex_init(&dev->lock); + mutex_init(&dev->update_mutex); + apmf_acpi_init(dev); platform_set_drvdata(pdev, dev); amd_pmf_init_features(dev); apmf_install_handler(dev); amd_pmf_dbgfs_register(dev); - mutex_init(&dev->lock); - mutex_init(&dev->update_mutex); + dev->pwr_src_notifier.notifier_call = amd_pmf_pwr_src_notify_call; + power_supply_reg_notifier(&dev->pwr_src_notifier); + dev_info(dev->dev, "registered PMF device successfully\n"); return 0; @@ -383,11 +406,12 @@ static int amd_pmf_remove(struct platform_device *pdev) { struct amd_pmf_dev *dev = platform_get_drvdata(pdev); - mutex_destroy(&dev->lock); - mutex_destroy(&dev->update_mutex); + power_supply_unreg_notifier(&dev->pwr_src_notifier); amd_pmf_deinit_features(dev); apmf_acpi_deinit(dev); amd_pmf_dbgfs_unregister(dev); + mutex_destroy(&dev->lock); + mutex_destroy(&dev->update_mutex); kfree(dev->buf); return 0; } diff --git a/drivers/platform/x86/amd/pmf/pmf.h b/drivers/platform/x86/amd/pmf/pmf.h index 84bbe2c6ea61..06c30cdc0573 100644 --- a/drivers/platform/x86/amd/pmf/pmf.h +++ b/drivers/platform/x86/amd/pmf/pmf.h @@ -169,6 +169,7 @@ struct amd_pmf_dev { struct mutex update_mutex; /* protects race between ACPI handler and metrics thread */ bool cnqf_enabled; bool cnqf_supported; + struct notifier_block pwr_src_notifier; }; struct apmf_sps_prop_granular { @@ -391,9 +392,11 @@ int amd_pmf_init_sps(struct amd_pmf_dev *dev); void amd_pmf_deinit_sps(struct amd_pmf_dev *dev); int apmf_get_static_slider_granular(struct amd_pmf_dev *pdev, struct apmf_static_slider_granular_output *output); +bool is_pprof_balanced(struct amd_pmf_dev *pmf); int apmf_update_fan_idx(struct amd_pmf_dev *pdev, bool manual, u32 idx); +int amd_pmf_set_sps_power_limits(struct amd_pmf_dev *pmf); /* Auto Mode Layer */ int apmf_get_auto_mode_def(struct amd_pmf_dev *pdev, struct apmf_auto_mode *data); diff --git a/drivers/platform/x86/amd/pmf/sps.c b/drivers/platform/x86/amd/pmf/sps.c index dba7e36962dc..bed762d47a14 100644 --- a/drivers/platform/x86/amd/pmf/sps.c +++ b/drivers/platform/x86/amd/pmf/sps.c @@ -70,6 +70,24 @@ void amd_pmf_update_slider(struct amd_pmf_dev *dev, bool op, int idx, } } +int amd_pmf_set_sps_power_limits(struct amd_pmf_dev *pmf) +{ + int mode; + + mode = amd_pmf_get_pprof_modes(pmf); + if (mode < 0) + return mode; + + amd_pmf_update_slider(pmf, SLIDER_OP_SET, mode, NULL); + + return 0; +} + +bool is_pprof_balanced(struct amd_pmf_dev *pmf) +{ + return (pmf->current_profile == PLATFORM_PROFILE_BALANCED) ? true : false; +} + static int amd_pmf_profile_get(struct platform_profile_handler *pprof, enum platform_profile_option *profile) { @@ -105,15 +123,10 @@ static int amd_pmf_profile_set(struct platform_profile_handler *pprof, enum platform_profile_option profile) { struct amd_pmf_dev *pmf = container_of(pprof, struct amd_pmf_dev, pprof); - int mode; pmf->current_profile = profile; - mode = amd_pmf_get_pprof_modes(pmf); - if (mode < 0) - return mode; - amd_pmf_update_slider(pmf, SLIDER_OP_SET, mode, NULL); - return 0; + return amd_pmf_set_sps_power_limits(pmf); } int amd_pmf_init_sps(struct amd_pmf_dev *dev) @@ -123,6 +136,9 @@ int amd_pmf_init_sps(struct amd_pmf_dev *dev) dev->current_profile = PLATFORM_PROFILE_BALANCED; amd_pmf_load_defaults_sps(dev); + /* update SPS balanced power mode thermals */ + amd_pmf_set_sps_power_limits(dev); + dev->pprof.profile_get = amd_pmf_profile_get; dev->pprof.profile_set = amd_pmf_profile_set; diff --git a/drivers/platform/x86/apple-gmux.c b/drivers/platform/x86/apple-gmux.c index ca33df7ea550..9333f82cfa8a 100644 --- a/drivers/platform/x86/apple-gmux.c +++ b/drivers/platform/x86/apple-gmux.c @@ -64,29 +64,6 @@ struct apple_gmux_data { static struct apple_gmux_data *apple_gmux_data; -/* - * gmux port offsets. Many of these are not yet used, but may be in the - * future, and it's useful to have them documented here anyhow. - */ -#define GMUX_PORT_VERSION_MAJOR 0x04 -#define GMUX_PORT_VERSION_MINOR 0x05 -#define GMUX_PORT_VERSION_RELEASE 0x06 -#define GMUX_PORT_SWITCH_DISPLAY 0x10 -#define GMUX_PORT_SWITCH_GET_DISPLAY 0x11 -#define GMUX_PORT_INTERRUPT_ENABLE 0x14 -#define GMUX_PORT_INTERRUPT_STATUS 0x16 -#define GMUX_PORT_SWITCH_DDC 0x28 -#define GMUX_PORT_SWITCH_EXTERNAL 0x40 -#define GMUX_PORT_SWITCH_GET_EXTERNAL 0x41 -#define GMUX_PORT_DISCRETE_POWER 0x50 -#define GMUX_PORT_MAX_BRIGHTNESS 0x70 -#define GMUX_PORT_BRIGHTNESS 0x74 -#define GMUX_PORT_VALUE 0xc2 -#define GMUX_PORT_READ 0xd0 -#define GMUX_PORT_WRITE 0xd4 - -#define GMUX_MIN_IO_LEN (GMUX_PORT_BRIGHTNESS + 4) - #define GMUX_INTERRUPT_ENABLE 0xff #define GMUX_INTERRUPT_DISABLE 0x00 @@ -249,23 +226,6 @@ static void gmux_write32(struct apple_gmux_data *gmux_data, int port, gmux_pio_write32(gmux_data, port, val); } -static bool gmux_is_indexed(struct apple_gmux_data *gmux_data) -{ - u16 val; - - outb(0xaa, gmux_data->iostart + 0xcc); - outb(0x55, gmux_data->iostart + 0xcd); - outb(0x00, gmux_data->iostart + 0xce); - - val = inb(gmux_data->iostart + 0xcc) | - (inb(gmux_data->iostart + 0xcd) << 8); - - if (val == 0x55aa) - return true; - - return false; -} - /** * DOC: Backlight control * @@ -605,60 +565,43 @@ static int gmux_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) int ret = -ENXIO; acpi_status status; unsigned long long gpe; + bool indexed = false; + u32 version; if (apple_gmux_data) return -EBUSY; + if (!apple_gmux_detect(pnp, &indexed)) { + pr_info("gmux device not present\n"); + return -ENODEV; + } + gmux_data = kzalloc(sizeof(*gmux_data), GFP_KERNEL); if (!gmux_data) return -ENOMEM; pnp_set_drvdata(pnp, gmux_data); res = pnp_get_resource(pnp, IORESOURCE_IO, 0); - if (!res) { - pr_err("Failed to find gmux I/O resource\n"); - goto err_free; - } - gmux_data->iostart = res->start; gmux_data->iolen = resource_size(res); - if (gmux_data->iolen < GMUX_MIN_IO_LEN) { - pr_err("gmux I/O region too small (%lu < %u)\n", - gmux_data->iolen, GMUX_MIN_IO_LEN); - goto err_free; - } - if (!request_region(gmux_data->iostart, gmux_data->iolen, "Apple gmux")) { pr_err("gmux I/O already in use\n"); goto err_free; } - /* - * Invalid version information may indicate either that the gmux - * device isn't present or that it's a new one that uses indexed - * io - */ - - ver_major = gmux_read8(gmux_data, GMUX_PORT_VERSION_MAJOR); - ver_minor = gmux_read8(gmux_data, GMUX_PORT_VERSION_MINOR); - ver_release = gmux_read8(gmux_data, GMUX_PORT_VERSION_RELEASE); - if (ver_major == 0xff && ver_minor == 0xff && ver_release == 0xff) { - if (gmux_is_indexed(gmux_data)) { - u32 version; - mutex_init(&gmux_data->index_lock); - gmux_data->indexed = true; - version = gmux_read32(gmux_data, - GMUX_PORT_VERSION_MAJOR); - ver_major = (version >> 24) & 0xff; - ver_minor = (version >> 16) & 0xff; - ver_release = (version >> 8) & 0xff; - } else { - pr_info("gmux device not present\n"); - ret = -ENODEV; - goto err_release; - } + if (indexed) { + mutex_init(&gmux_data->index_lock); + gmux_data->indexed = true; + version = gmux_read32(gmux_data, GMUX_PORT_VERSION_MAJOR); + ver_major = (version >> 24) & 0xff; + ver_minor = (version >> 16) & 0xff; + ver_release = (version >> 8) & 0xff; + } else { + ver_major = gmux_read8(gmux_data, GMUX_PORT_VERSION_MAJOR); + ver_minor = gmux_read8(gmux_data, GMUX_PORT_VERSION_MINOR); + ver_release = gmux_read8(gmux_data, GMUX_PORT_VERSION_RELEASE); } pr_info("Found gmux version %d.%d.%d [%s]\n", ver_major, ver_minor, ver_release, (gmux_data->indexed ? "indexed" : "classic")); diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 104188d70988..1038dfdcdd32 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -225,6 +225,7 @@ struct asus_wmi { int tablet_switch_event_code; u32 tablet_switch_dev_id; + bool tablet_switch_inverted; enum fan_type fan_type; enum fan_type gpu_fan_type; @@ -493,6 +494,13 @@ static bool asus_wmi_dev_is_present(struct asus_wmi *asus, u32 dev_id) } /* Input **********************************************************************/ +static void asus_wmi_tablet_sw_report(struct asus_wmi *asus, bool value) +{ + input_report_switch(asus->inputdev, SW_TABLET_MODE, + asus->tablet_switch_inverted ? !value : value); + input_sync(asus->inputdev); +} + static void asus_wmi_tablet_sw_init(struct asus_wmi *asus, u32 dev_id, int event_code) { struct device *dev = &asus->platform_device->dev; @@ -501,7 +509,7 @@ static void asus_wmi_tablet_sw_init(struct asus_wmi *asus, u32 dev_id, int event result = asus_wmi_get_devstate_simple(asus, dev_id); if (result >= 0) { input_set_capability(asus->inputdev, EV_SW, SW_TABLET_MODE); - input_report_switch(asus->inputdev, SW_TABLET_MODE, result); + asus_wmi_tablet_sw_report(asus, result); asus->tablet_switch_dev_id = dev_id; asus->tablet_switch_event_code = event_code; } else if (result == -ENODEV) { @@ -534,6 +542,7 @@ static int asus_wmi_input_init(struct asus_wmi *asus) case asus_wmi_no_tablet_switch: break; case asus_wmi_kbd_dock_devid: + asus->tablet_switch_inverted = true; asus_wmi_tablet_sw_init(asus, ASUS_WMI_DEVID_KBD_DOCK, NOTIFY_KBD_DOCK_CHANGE); break; case asus_wmi_lid_flip_devid: @@ -573,10 +582,8 @@ static void asus_wmi_tablet_mode_get_state(struct asus_wmi *asus) return; result = asus_wmi_get_devstate_simple(asus, asus->tablet_switch_dev_id); - if (result >= 0) { - input_report_switch(asus->inputdev, SW_TABLET_MODE, result); - input_sync(asus->inputdev); - } + if (result >= 0) + asus_wmi_tablet_sw_report(asus, result); } /* dGPU ********************************************************************/ diff --git a/drivers/platform/x86/dell/dell-wmi-base.c b/drivers/platform/x86/dell/dell-wmi-base.c index 0a259a27459f..502783a7adb1 100644 --- a/drivers/platform/x86/dell/dell-wmi-base.c +++ b/drivers/platform/x86/dell/dell-wmi-base.c @@ -261,6 +261,9 @@ static const struct key_entry dell_wmi_keymap_type_0010[] = { { KE_KEY, 0x57, { KEY_BRIGHTNESSDOWN } }, { KE_KEY, 0x58, { KEY_BRIGHTNESSUP } }, + /*Speaker Mute*/ + { KE_KEY, 0x109, { KEY_MUTE} }, + /* Mic mute */ { KE_KEY, 0x150, { KEY_MICMUTE } }, diff --git a/drivers/platform/x86/gigabyte-wmi.c b/drivers/platform/x86/gigabyte-wmi.c index 5e7e6659a849..322cfaeda17b 100644 --- a/drivers/platform/x86/gigabyte-wmi.c +++ b/drivers/platform/x86/gigabyte-wmi.c @@ -141,6 +141,7 @@ static u8 gigabyte_wmi_detect_sensor_usability(struct wmi_device *wdev) static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = { DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M DS3H-CF"), + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M DS3H WIFI-CF"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M S2H V2"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE AX V2"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE"), diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c index 0a99058be813..2ef201b625b3 100644 --- a/drivers/platform/x86/hp/hp-wmi.c +++ b/drivers/platform/x86/hp/hp-wmi.c @@ -90,6 +90,7 @@ enum hp_wmi_event_ids { HPWMI_PEAKSHIFT_PERIOD = 0x0F, HPWMI_BATTERY_CHARGE_PERIOD = 0x10, HPWMI_SANITIZATION_MODE = 0x17, + HPWMI_OMEN_KEY = 0x1D, HPWMI_SMART_EXPERIENCE_APP = 0x21, }; @@ -216,6 +217,8 @@ static const struct key_entry hp_wmi_keymap[] = { { KE_KEY, 0x213b, { KEY_INFO } }, { KE_KEY, 0x2169, { KEY_ROTATE_DISPLAY } }, { KE_KEY, 0x216a, { KEY_SETUP } }, + { KE_KEY, 0x21a5, { KEY_PROG2 } }, /* HP Omen Key */ + { KE_KEY, 0x21a7, { KEY_FN_ESC } }, { KE_KEY, 0x21a9, { KEY_TOUCHPAD_OFF } }, { KE_KEY, 0x121a9, { KEY_TOUCHPAD_ON } }, { KE_KEY, 0x231b, { KEY_HELP } }, @@ -548,7 +551,7 @@ static int __init hp_wmi_enable_hotkeys(void) static int hp_wmi_set_block(void *data, bool blocked) { - enum hp_wmi_radio r = (enum hp_wmi_radio) data; + enum hp_wmi_radio r = (long)data; int query = BIT(r + 8) | ((!blocked) << r); int ret; @@ -810,6 +813,7 @@ static void hp_wmi_notify(u32 value, void *context) case HPWMI_SMART_ADAPTER: break; case HPWMI_BEZEL_BUTTON: + case HPWMI_OMEN_KEY: key_code = hp_wmi_read_int(HPWMI_HOTKEY_QUERY); if (key_code < 0) break; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index a95946800ae9..32c10457399e 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -5563,7 +5563,7 @@ static int light_sysfs_set(struct led_classdev *led_cdev, static enum led_brightness light_sysfs_get(struct led_classdev *led_cdev) { - return (light_get_status() == 1) ? LED_FULL : LED_OFF; + return (light_get_status() == 1) ? LED_ON : LED_OFF; } static struct tpacpi_led_classdev tpacpi_led_thinklight = { @@ -10496,8 +10496,7 @@ static int dytc_profile_set(struct platform_profile_handler *pprof, if (err) goto unlock; } - } - if (dytc_capabilities & BIT(DYTC_FC_PSC)) { + } else if (dytc_capabilities & BIT(DYTC_FC_PSC)) { err = dytc_command(DYTC_SET_COMMAND(DYTC_FUNCTION_PSC, perfmode, 1), &output); if (err) goto unlock; @@ -10525,14 +10524,16 @@ static void dytc_profile_refresh(void) err = dytc_command(DYTC_CMD_MMC_GET, &output); else err = dytc_cql_command(DYTC_CMD_GET, &output); - } else if (dytc_capabilities & BIT(DYTC_FC_PSC)) + funcmode = DYTC_FUNCTION_MMC; + } else if (dytc_capabilities & BIT(DYTC_FC_PSC)) { err = dytc_command(DYTC_CMD_GET, &output); - + /* Check if we are PSC mode, or have AMT enabled */ + funcmode = (output >> DYTC_GET_FUNCTION_BIT) & 0xF; + } mutex_unlock(&dytc_mutex); if (err) return; - funcmode = (output >> DYTC_GET_FUNCTION_BIT) & 0xF; perfmode = (output >> DYTC_GET_MODE_BIT) & 0xF; convert_dytc_to_profile(funcmode, perfmode, &profile); if (profile != dytc_current_profile) { diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index f00995390fdf..13802a3c3591 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -1098,6 +1098,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* Chuwi Vi8 (CWI501) */ + .driver_data = (void *)&chuwi_vi8_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Insyde"), + DMI_MATCH(DMI_PRODUCT_NAME, "i86"), + DMI_MATCH(DMI_BIOS_VERSION, "CHUWI.W86JLBNR01"), + }, + }, + { /* Chuwi Vi8 (CWI506) */ .driver_data = (void *)&chuwi_vi8_data, .matches = { diff --git a/drivers/rtc/rtc-efi.c b/drivers/rtc/rtc-efi.c index e991cccdb6e9..1e8bc6cc1e12 100644 --- a/drivers/rtc/rtc-efi.c +++ b/drivers/rtc/rtc-efi.c @@ -188,9 +188,10 @@ static int efi_set_time(struct device *dev, struct rtc_time *tm) static int efi_procfs(struct device *dev, struct seq_file *seq) { - efi_time_t eft, alm; - efi_time_cap_t cap; - efi_bool_t enabled, pending; + efi_time_t eft, alm; + efi_time_cap_t cap; + efi_bool_t enabled, pending; + struct rtc_device *rtc = dev_get_drvdata(dev); memset(&eft, 0, sizeof(eft)); memset(&alm, 0, sizeof(alm)); @@ -213,23 +214,25 @@ static int efi_procfs(struct device *dev, struct seq_file *seq) /* XXX fixme: convert to string? */ seq_printf(seq, "Timezone\t: %u\n", eft.timezone); - seq_printf(seq, - "Alarm Time\t: %u:%u:%u.%09u\n" - "Alarm Date\t: %u-%u-%u\n" - "Alarm Daylight\t: %u\n" - "Enabled\t\t: %s\n" - "Pending\t\t: %s\n", - alm.hour, alm.minute, alm.second, alm.nanosecond, - alm.year, alm.month, alm.day, - alm.daylight, - enabled == 1 ? "yes" : "no", - pending == 1 ? "yes" : "no"); - - if (eft.timezone == EFI_UNSPECIFIED_TIMEZONE) - seq_puts(seq, "Timezone\t: unspecified\n"); - else - /* XXX fixme: convert to string? */ - seq_printf(seq, "Timezone\t: %u\n", alm.timezone); + if (test_bit(RTC_FEATURE_ALARM, rtc->features)) { + seq_printf(seq, + "Alarm Time\t: %u:%u:%u.%09u\n" + "Alarm Date\t: %u-%u-%u\n" + "Alarm Daylight\t: %u\n" + "Enabled\t\t: %s\n" + "Pending\t\t: %s\n", + alm.hour, alm.minute, alm.second, alm.nanosecond, + alm.year, alm.month, alm.day, + alm.daylight, + enabled == 1 ? "yes" : "no", + pending == 1 ? "yes" : "no"); + + if (eft.timezone == EFI_UNSPECIFIED_TIMEZONE) + seq_puts(seq, "Timezone\t: unspecified\n"); + else + /* XXX fixme: convert to string? */ + seq_printf(seq, "Timezone\t: %u\n", alm.timezone); + } /* * now prints the capabilities @@ -269,7 +272,10 @@ static int __init efi_rtc_probe(struct platform_device *dev) rtc->ops = &efi_rtc_ops; clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features); - set_bit(RTC_FEATURE_ALARM_WAKEUP_ONLY, rtc->features); + if (efi_rt_services_supported(EFI_RT_SUPPORTED_WAKEUP_SERVICES)) + set_bit(RTC_FEATURE_ALARM_WAKEUP_ONLY, rtc->features); + else + clear_bit(RTC_FEATURE_ALARM, rtc->features); device_init_wakeup(&dev->dev, true); diff --git a/drivers/rtc/rtc-sunplus.c b/drivers/rtc/rtc-sunplus.c index e8e2ab1103fc..4b578e4d44f6 100644 --- a/drivers/rtc/rtc-sunplus.c +++ b/drivers/rtc/rtc-sunplus.c @@ -240,8 +240,8 @@ static int sp_rtc_probe(struct platform_device *plat_dev) if (IS_ERR(sp_rtc->reg_base)) return dev_err_probe(&plat_dev->dev, PTR_ERR(sp_rtc->reg_base), "%s devm_ioremap_resource fail\n", RTC_REG_NAME); - dev_dbg(&plat_dev->dev, "res = 0x%x, reg_base = 0x%lx\n", - sp_rtc->res->start, (unsigned long)sp_rtc->reg_base); + dev_dbg(&plat_dev->dev, "res = %pR, reg_base = %p\n", + sp_rtc->res, sp_rtc->reg_base); sp_rtc->irq = platform_get_irq(plat_dev, 0); if (sp_rtc->irq < 0) diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 1426b9b03612..9feb0323bc44 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -588,8 +588,6 @@ void scsi_device_put(struct scsi_device *sdev) { struct module *mod = sdev->host->hostt->module; - might_sleep(); - put_device(&sdev->sdev_gendev); module_put(mod); } diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 7a6904a3928e..f9b18fdc7b3c 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -1232,8 +1232,7 @@ static int scsi_probe_and_add_lun(struct scsi_target *starget, * that no LUN is present, so don't add sdev in these cases. * Two specific examples are: * 1) NetApp targets: return PQ=1, PDT=0x1f - * 2) IBM/2145 targets: return PQ=1, PDT=0 - * 3) USB UFI: returns PDT=0x1f, with the PQ bits being "reserved" + * 2) USB UFI: returns PDT=0x1f, with the PQ bits being "reserved" * in the UFI 1.0 spec (we cannot rely on reserved bits). * * References: @@ -1247,8 +1246,8 @@ static int scsi_probe_and_add_lun(struct scsi_target *starget, * PDT=00h Direct-access device (floppy) * PDT=1Fh none (no FDD connected to the requested logical unit) */ - if (((result[0] >> 5) == 1 || - (starget->pdt_1f_for_no_lun && (result[0] & 0x1f) == 0x1f)) && + if (((result[0] >> 5) == 1 || starget->pdt_1f_for_no_lun) && + (result[0] & 0x1f) == 0x1f && !scsi_is_wlun(lun)) { SCSI_LOG_SCAN_BUS(3, sdev_printk(KERN_INFO, sdev, "scsi scan: peripheral device type" diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 981d1bab2120..8ef9a5494340 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -451,6 +451,8 @@ static void scsi_device_dev_release(struct device *dev) struct scsi_vpd *vpd_pgb0 = NULL, *vpd_pgb1 = NULL, *vpd_pgb2 = NULL; unsigned long flags; + might_sleep(); + scsi_dh_release_device(sdev); parent = sdev->sdev_gendev.parent; diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c index 62c0aa5d0783..0a4eaa307156 100644 --- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c +++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c @@ -44,11 +44,13 @@ static int int340x_thermal_get_trip_temp(struct thermal_zone_device *zone, int trip, int *temp) { struct int34x_thermal_zone *d = zone->devdata; - int i; + int i, ret = 0; if (d->override_ops && d->override_ops->get_trip_temp) return d->override_ops->get_trip_temp(zone, trip, temp); + mutex_lock(&d->trip_mutex); + if (trip < d->aux_trip_nr) *temp = d->aux_trips[trip]; else if (trip == d->crt_trip_id) @@ -66,10 +68,12 @@ static int int340x_thermal_get_trip_temp(struct thermal_zone_device *zone, } } if (i == INT340X_THERMAL_MAX_ACT_TRIP_COUNT) - return -EINVAL; + ret = -EINVAL; } - return 0; + mutex_unlock(&d->trip_mutex); + + return ret; } static int int340x_thermal_get_trip_type(struct thermal_zone_device *zone, @@ -77,11 +81,13 @@ static int int340x_thermal_get_trip_type(struct thermal_zone_device *zone, enum thermal_trip_type *type) { struct int34x_thermal_zone *d = zone->devdata; - int i; + int i, ret = 0; if (d->override_ops && d->override_ops->get_trip_type) return d->override_ops->get_trip_type(zone, trip, type); + mutex_lock(&d->trip_mutex); + if (trip < d->aux_trip_nr) *type = THERMAL_TRIP_PASSIVE; else if (trip == d->crt_trip_id) @@ -99,10 +105,12 @@ static int int340x_thermal_get_trip_type(struct thermal_zone_device *zone, } } if (i == INT340X_THERMAL_MAX_ACT_TRIP_COUNT) - return -EINVAL; + ret = -EINVAL; } - return 0; + mutex_unlock(&d->trip_mutex); + + return ret; } static int int340x_thermal_set_trip_temp(struct thermal_zone_device *zone, @@ -180,6 +188,8 @@ int int340x_thermal_read_trips(struct int34x_thermal_zone *int34x_zone) int trip_cnt = int34x_zone->aux_trip_nr; int i; + mutex_lock(&int34x_zone->trip_mutex); + int34x_zone->crt_trip_id = -1; if (!int340x_thermal_get_trip_config(int34x_zone->adev->handle, "_CRT", &int34x_zone->crt_temp)) @@ -207,6 +217,8 @@ int int340x_thermal_read_trips(struct int34x_thermal_zone *int34x_zone) int34x_zone->act_trips[i].valid = true; } + mutex_unlock(&int34x_zone->trip_mutex); + return trip_cnt; } EXPORT_SYMBOL_GPL(int340x_thermal_read_trips); @@ -230,6 +242,8 @@ struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *adev, if (!int34x_thermal_zone) return ERR_PTR(-ENOMEM); + mutex_init(&int34x_thermal_zone->trip_mutex); + int34x_thermal_zone->adev = adev; int34x_thermal_zone->override_ops = override_ops; @@ -281,6 +295,7 @@ err_thermal_zone: acpi_lpat_free_conversion_table(int34x_thermal_zone->lpat_table); kfree(int34x_thermal_zone->aux_trips); err_trip_alloc: + mutex_destroy(&int34x_thermal_zone->trip_mutex); kfree(int34x_thermal_zone); return ERR_PTR(ret); } @@ -292,6 +307,7 @@ void int340x_thermal_zone_remove(struct int34x_thermal_zone thermal_zone_device_unregister(int34x_thermal_zone->zone); acpi_lpat_free_conversion_table(int34x_thermal_zone->lpat_table); kfree(int34x_thermal_zone->aux_trips); + mutex_destroy(&int34x_thermal_zone->trip_mutex); kfree(int34x_thermal_zone); } EXPORT_SYMBOL_GPL(int340x_thermal_zone_remove); diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h index 3b4971df1b33..8f9872afd0d3 100644 --- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h +++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h @@ -32,6 +32,7 @@ struct int34x_thermal_zone { struct thermal_zone_device_ops *override_ops; void *priv_data; struct acpi_lpat_conversion_table *lpat_table; + struct mutex trip_mutex; }; struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *, diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c index 37d6af2ec427..7fa66501792d 100644 --- a/drivers/tty/serial/8250/8250_dma.c +++ b/drivers/tty/serial/8250/8250_dma.c @@ -43,15 +43,23 @@ static void __dma_rx_complete(struct uart_8250_port *p) struct uart_8250_dma *dma = p->dma; struct tty_port *tty_port = &p->port.state->port; struct dma_tx_state state; + enum dma_status dma_status; int count; - dma->rx_running = 0; - dmaengine_tx_status(dma->rxchan, dma->rx_cookie, &state); + /* + * New DMA Rx can be started during the completion handler before it + * could acquire port's lock and it might still be ongoing. Don't to + * anything in such case. + */ + dma_status = dmaengine_tx_status(dma->rxchan, dma->rx_cookie, &state); + if (dma_status == DMA_IN_PROGRESS) + return; count = dma->rx_size - state.residue; tty_insert_flip_string(tty_port, dma->rx_buf, count); p->port.icount.rx += count; + dma->rx_running = 0; tty_flip_buffer_push(tty_port); } @@ -62,9 +70,14 @@ static void dma_rx_complete(void *param) struct uart_8250_dma *dma = p->dma; unsigned long flags; - __dma_rx_complete(p); - spin_lock_irqsave(&p->port.lock, flags); + if (dma->rx_running) + __dma_rx_complete(p); + + /* + * Cannot be combined with the previous check because __dma_rx_complete() + * changes dma->rx_running. + */ if (!dma->rx_running && (serial_lsr_in(p) & UART_LSR_DR)) p->dma->rx_dma(p); spin_unlock_irqrestore(&p->port.lock, flags); diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c index a1490033aa16..409e91d6829a 100644 --- a/drivers/tty/serial/stm32-usart.c +++ b/drivers/tty/serial/stm32-usart.c @@ -797,25 +797,11 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) spin_unlock(&port->lock); } - if (stm32_usart_rx_dma_enabled(port)) - return IRQ_WAKE_THREAD; - else - return IRQ_HANDLED; -} - -static irqreturn_t stm32_usart_threaded_interrupt(int irq, void *ptr) -{ - struct uart_port *port = ptr; - struct tty_port *tport = &port->state->port; - struct stm32_port *stm32_port = to_stm32_port(port); - unsigned int size; - unsigned long flags; - /* Receiver timeout irq for DMA RX */ - if (!stm32_port->throttled) { - spin_lock_irqsave(&port->lock, flags); + if (stm32_usart_rx_dma_enabled(port) && !stm32_port->throttled) { + spin_lock(&port->lock); size = stm32_usart_receive_chars(port, false); - uart_unlock_and_check_sysrq_irqrestore(port, flags); + uart_unlock_and_check_sysrq(port); if (size) tty_flip_buffer_push(tport); } @@ -1015,10 +1001,8 @@ static int stm32_usart_startup(struct uart_port *port) u32 val; int ret; - ret = request_threaded_irq(port->irq, stm32_usart_interrupt, - stm32_usart_threaded_interrupt, - IRQF_ONESHOT | IRQF_NO_SUSPEND, - name, port); + ret = request_irq(port->irq, stm32_usart_interrupt, + IRQF_NO_SUSPEND, name, port); if (ret) return ret; @@ -1601,13 +1585,6 @@ static int stm32_usart_of_dma_rx_probe(struct stm32_port *stm32port, struct dma_slave_config config; int ret; - /* - * Using DMA and threaded handler for the console could lead to - * deadlocks. - */ - if (uart_console(port)) - return -ENODEV; - stm32port->rx_buf = dma_alloc_coherent(dev, RX_BUF_L, &stm32port->rx_dma_buf, GFP_KERNEL); diff --git a/drivers/tty/vt/vc_screen.c b/drivers/tty/vt/vc_screen.c index 1850bacdb5b0..f566eb1839dc 100644 --- a/drivers/tty/vt/vc_screen.c +++ b/drivers/tty/vt/vc_screen.c @@ -386,10 +386,6 @@ vcs_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) uni_mode = use_unicode(inode); attr = use_attributes(inode); - ret = -ENXIO; - vc = vcs_vc(inode, &viewed); - if (!vc) - goto unlock_out; ret = -EINVAL; if (pos < 0) @@ -407,6 +403,11 @@ vcs_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) unsigned int this_round, skip = 0; int size; + ret = -ENXIO; + vc = vcs_vc(inode, &viewed); + if (!vc) + goto unlock_out; + /* Check whether we are above size each round, * as copy_to_user at the end of this loop * could sleep. diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c index b0a0351d2d8b..959fc925ca7c 100644 --- a/drivers/usb/dwc3/dwc3-qcom.c +++ b/drivers/usb/dwc3/dwc3-qcom.c @@ -901,7 +901,7 @@ static int dwc3_qcom_probe(struct platform_device *pdev) qcom->mode = usb_get_dr_mode(&qcom->dwc3->dev); /* enable vbus override for device mode */ - if (qcom->mode == USB_DR_MODE_PERIPHERAL) + if (qcom->mode != USB_DR_MODE_HOST) dwc3_qcom_vbus_override_enable(qcom, true); /* register extcon to override sw_vbus on Vbus change later */ diff --git a/drivers/usb/fotg210/fotg210-udc.c b/drivers/usb/fotg210/fotg210-udc.c index 87cca81bf4ac..eb076746f032 100644 --- a/drivers/usb/fotg210/fotg210-udc.c +++ b/drivers/usb/fotg210/fotg210-udc.c @@ -1014,7 +1014,6 @@ static int fotg210_udc_start(struct usb_gadget *g, int ret; /* hook up the driver */ - driver->driver.bus = NULL; fotg210->driver = driver; if (!IS_ERR_OR_NULL(fotg210->phy)) { diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 523a961b910b..8ad354741380 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -279,8 +279,10 @@ static int __ffs_ep0_queue_wait(struct ffs_data *ffs, char *data, size_t len) struct usb_request *req = ffs->ep0req; int ret; - if (!req) + if (!req) { + spin_unlock_irq(&ffs->ev.waitq.lock); return -EINVAL; + } req->zero = len < le16_to_cpu(ffs->ev.setup.wLength); diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c index 08726e4c68a5..0219cd79493a 100644 --- a/drivers/usb/gadget/function/f_uac2.c +++ b/drivers/usb/gadget/function/f_uac2.c @@ -1142,6 +1142,7 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn) } std_as_out_if0_desc.bInterfaceNumber = ret; std_as_out_if1_desc.bInterfaceNumber = ret; + std_as_out_if1_desc.bNumEndpoints = 1; uac2->as_out_intf = ret; uac2->as_out_alt = 0; diff --git a/drivers/usb/gadget/udc/bcm63xx_udc.c b/drivers/usb/gadget/udc/bcm63xx_udc.c index 2cdb07905bde..d04d72f5816e 100644 --- a/drivers/usb/gadget/udc/bcm63xx_udc.c +++ b/drivers/usb/gadget/udc/bcm63xx_udc.c @@ -1830,7 +1830,6 @@ static int bcm63xx_udc_start(struct usb_gadget *gadget, bcm63xx_select_phy_mode(udc, true); udc->driver = driver; - driver->driver.bus = NULL; udc->gadget.dev.of_node = udc->dev->of_node; spin_unlock_irqrestore(&udc->lock, flags); diff --git a/drivers/usb/gadget/udc/fsl_qe_udc.c b/drivers/usb/gadget/udc/fsl_qe_udc.c index bf745358e28e..3b1cc8fa30c8 100644 --- a/drivers/usb/gadget/udc/fsl_qe_udc.c +++ b/drivers/usb/gadget/udc/fsl_qe_udc.c @@ -2285,7 +2285,6 @@ static int fsl_qe_start(struct usb_gadget *gadget, /* lock is needed but whether should use this lock or another */ spin_lock_irqsave(&udc->lock, flags); - driver->driver.bus = NULL; /* hook up the driver */ udc->driver = driver; udc->gadget.speed = driver->max_speed; diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c index 50435e804118..a67873a074b7 100644 --- a/drivers/usb/gadget/udc/fsl_udc_core.c +++ b/drivers/usb/gadget/udc/fsl_udc_core.c @@ -1943,7 +1943,6 @@ static int fsl_udc_start(struct usb_gadget *g, /* lock is needed but whether should use this lock or another */ spin_lock_irqsave(&udc_controller->lock, flags); - driver->driver.bus = NULL; /* hook up the driver */ udc_controller->driver = driver; spin_unlock_irqrestore(&udc_controller->lock, flags); diff --git a/drivers/usb/gadget/udc/fusb300_udc.c b/drivers/usb/gadget/udc/fusb300_udc.c index 9af8b415f303..5954800d652c 100644 --- a/drivers/usb/gadget/udc/fusb300_udc.c +++ b/drivers/usb/gadget/udc/fusb300_udc.c @@ -1311,7 +1311,6 @@ static int fusb300_udc_start(struct usb_gadget *g, struct fusb300 *fusb300 = to_fusb300(g); /* hook up the driver */ - driver->driver.bus = NULL; fusb300->driver = driver; return 0; diff --git a/drivers/usb/gadget/udc/goku_udc.c b/drivers/usb/gadget/udc/goku_udc.c index bdc56b24b5c9..5ffb3d5c635b 100644 --- a/drivers/usb/gadget/udc/goku_udc.c +++ b/drivers/usb/gadget/udc/goku_udc.c @@ -1375,7 +1375,6 @@ static int goku_udc_start(struct usb_gadget *g, struct goku_udc *dev = to_goku_udc(g); /* hook up the driver */ - driver->driver.bus = NULL; dev->driver = driver; /* diff --git a/drivers/usb/gadget/udc/gr_udc.c b/drivers/usb/gadget/udc/gr_udc.c index 22096f8505de..85cdc0af3bf9 100644 --- a/drivers/usb/gadget/udc/gr_udc.c +++ b/drivers/usb/gadget/udc/gr_udc.c @@ -1906,7 +1906,6 @@ static int gr_udc_start(struct usb_gadget *gadget, spin_lock(&dev->lock); /* Hook up the driver */ - driver->driver.bus = NULL; dev->driver = driver; /* Get ready for host detection */ diff --git a/drivers/usb/gadget/udc/m66592-udc.c b/drivers/usb/gadget/udc/m66592-udc.c index c7e421b449f3..06e21cee431b 100644 --- a/drivers/usb/gadget/udc/m66592-udc.c +++ b/drivers/usb/gadget/udc/m66592-udc.c @@ -1454,7 +1454,6 @@ static int m66592_udc_start(struct usb_gadget *g, struct m66592 *m66592 = to_m66592(g); /* hook up the driver */ - driver->driver.bus = NULL; m66592->driver = driver; m66592_bset(m66592, M66592_VBSE | M66592_URST, M66592_INTENB0); diff --git a/drivers/usb/gadget/udc/max3420_udc.c b/drivers/usb/gadget/udc/max3420_udc.c index 3074da00c3df..ddf0ed3eb4f2 100644 --- a/drivers/usb/gadget/udc/max3420_udc.c +++ b/drivers/usb/gadget/udc/max3420_udc.c @@ -1108,7 +1108,6 @@ static int max3420_udc_start(struct usb_gadget *gadget, spin_lock_irqsave(&udc->lock, flags); /* hook up the driver */ - driver->driver.bus = NULL; udc->driver = driver; udc->gadget.speed = USB_SPEED_FULL; diff --git a/drivers/usb/gadget/udc/mv_u3d_core.c b/drivers/usb/gadget/udc/mv_u3d_core.c index 598654a3cb41..411b6179782c 100644 --- a/drivers/usb/gadget/udc/mv_u3d_core.c +++ b/drivers/usb/gadget/udc/mv_u3d_core.c @@ -1243,7 +1243,6 @@ static int mv_u3d_start(struct usb_gadget *g, } /* hook up the driver ... */ - driver->driver.bus = NULL; u3d->driver = driver; u3d->ep0_dir = USB_DIR_OUT; diff --git a/drivers/usb/gadget/udc/mv_udc_core.c b/drivers/usb/gadget/udc/mv_udc_core.c index fdb17d86cd65..b397f3a848cf 100644 --- a/drivers/usb/gadget/udc/mv_udc_core.c +++ b/drivers/usb/gadget/udc/mv_udc_core.c @@ -1359,7 +1359,6 @@ static int mv_udc_start(struct usb_gadget *gadget, spin_lock_irqsave(&udc->lock, flags); /* hook up the driver ... */ - driver->driver.bus = NULL; udc->driver = driver; udc->usb_state = USB_STATE_ATTACHED; diff --git a/drivers/usb/gadget/udc/net2272.c b/drivers/usb/gadget/udc/net2272.c index 84605a4d0715..538c1b9a2883 100644 --- a/drivers/usb/gadget/udc/net2272.c +++ b/drivers/usb/gadget/udc/net2272.c @@ -1451,7 +1451,6 @@ static int net2272_start(struct usb_gadget *_gadget, dev->ep[i].irqs = 0; /* hook up the driver ... */ dev->softconnect = 1; - driver->driver.bus = NULL; dev->driver = driver; /* ... then enable host detection and ep0; and we're ready diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c index d6a68631354a..1b929c519cd7 100644 --- a/drivers/usb/gadget/udc/net2280.c +++ b/drivers/usb/gadget/udc/net2280.c @@ -2423,7 +2423,6 @@ static int net2280_start(struct usb_gadget *_gadget, dev->ep[i].irqs = 0; /* hook up the driver ... */ - driver->driver.bus = NULL; dev->driver = driver; retval = device_create_file(&dev->pdev->dev, &dev_attr_function); diff --git a/drivers/usb/gadget/udc/omap_udc.c b/drivers/usb/gadget/udc/omap_udc.c index bea346e362b2..f660ebfa1379 100644 --- a/drivers/usb/gadget/udc/omap_udc.c +++ b/drivers/usb/gadget/udc/omap_udc.c @@ -2066,7 +2066,6 @@ static int omap_udc_start(struct usb_gadget *g, udc->softconnect = 1; /* hook up the driver */ - driver->driver.bus = NULL; udc->driver = driver; spin_unlock_irqrestore(&udc->lock, flags); diff --git a/drivers/usb/gadget/udc/pch_udc.c b/drivers/usb/gadget/udc/pch_udc.c index 9bb7a9d7a2fb..4f8617210d85 100644 --- a/drivers/usb/gadget/udc/pch_udc.c +++ b/drivers/usb/gadget/udc/pch_udc.c @@ -2908,7 +2908,6 @@ static int pch_udc_start(struct usb_gadget *g, { struct pch_udc_dev *dev = to_pch_udc(g); - driver->driver.bus = NULL; dev->driver = driver; /* get ready for ep0 traffic */ diff --git a/drivers/usb/gadget/udc/snps_udc_core.c b/drivers/usb/gadget/udc/snps_udc_core.c index 52ea4dcf6a92..2fc5d4d277bc 100644 --- a/drivers/usb/gadget/udc/snps_udc_core.c +++ b/drivers/usb/gadget/udc/snps_udc_core.c @@ -1933,7 +1933,6 @@ static int amd5536_udc_start(struct usb_gadget *g, struct udc *dev = to_amd5536_udc(g); u32 tmp; - driver->driver.bus = NULL; dev->driver = driver; /* Some gadget drivers use both ep0 directions. diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 1292241d581a..1cf8947c6d66 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -1269,6 +1269,9 @@ err_unregister: con->port = NULL; } + kfree(ucsi->connector); + ucsi->connector = NULL; + err_reset: memset(&ucsi->cap, 0, sizeof(ucsi->cap)); ucsi_reset_ppm(ucsi); @@ -1300,7 +1303,8 @@ static void ucsi_resume_work(struct work_struct *work) int ucsi_resume(struct ucsi *ucsi) { - queue_work(system_long_wq, &ucsi->resume_work); + if (ucsi->connector) + queue_work(system_long_wq, &ucsi->resume_work); return 0; } EXPORT_SYMBOL_GPL(ucsi_resume); @@ -1420,6 +1424,9 @@ void ucsi_unregister(struct ucsi *ucsi) /* Disable notifications */ ucsi->ops->async_write(ucsi, UCSI_CONTROL, &cmd, sizeof(cmd)); + if (!ucsi->connector) + return; + for (i = 0; i < ucsi->cap.num_connectors; i++) { cancel_work_sync(&ucsi->connector[i].work); ucsi_unregister_partner(&ucsi->connector[i]); diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index f9c0044c6442..44b29289aa19 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -849,7 +849,7 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = ifcvf_init_hw(vf, pdev); if (ret) { IFCVF_ERR(pdev, "Failed to init IFCVF hw\n"); - return ret; + goto err; } for (i = 0; i < vf->nr_vring; i++) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 9af19b0cf3b7..4c538b30fd76 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1511,6 +1511,9 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) nvq = &n->vqs[index]; mutex_lock(&vq->mutex); + if (fd == -1) + vhost_clear_msg(&n->dev); + /* Verify that ring has been setup correctly. */ if (!vhost_vq_access_ok(vq)) { r = -EFAULT; diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index dca6346d75b3..d5ecb8876fc9 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -80,7 +80,7 @@ struct vhost_scsi_cmd { struct scatterlist *tvc_prot_sgl; struct page **tvc_upages; /* Pointer to response header iovec */ - struct iovec tvc_resp_iov; + struct iovec *tvc_resp_iov; /* Pointer to vhost_scsi for our device */ struct vhost_scsi *tvc_vhost; /* Pointer to vhost_virtqueue for the cmd */ @@ -563,7 +563,7 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work) memcpy(v_rsp.sense, cmd->tvc_sense_buf, se_cmd->scsi_sense_length); - iov_iter_init(&iov_iter, ITER_DEST, &cmd->tvc_resp_iov, + iov_iter_init(&iov_iter, ITER_DEST, cmd->tvc_resp_iov, cmd->tvc_in_iovs, sizeof(v_rsp)); ret = copy_to_iter(&v_rsp, sizeof(v_rsp), &iov_iter); if (likely(ret == sizeof(v_rsp))) { @@ -594,6 +594,7 @@ vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, struct vhost_scsi_cmd *cmd; struct vhost_scsi_nexus *tv_nexus; struct scatterlist *sg, *prot_sg; + struct iovec *tvc_resp_iov; struct page **pages; int tag; @@ -613,6 +614,7 @@ vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, sg = cmd->tvc_sgl; prot_sg = cmd->tvc_prot_sgl; pages = cmd->tvc_upages; + tvc_resp_iov = cmd->tvc_resp_iov; memset(cmd, 0, sizeof(*cmd)); cmd->tvc_sgl = sg; cmd->tvc_prot_sgl = prot_sg; @@ -625,6 +627,7 @@ vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, cmd->tvc_data_direction = data_direction; cmd->tvc_nexus = tv_nexus; cmd->inflight = vhost_scsi_get_inflight(vq); + cmd->tvc_resp_iov = tvc_resp_iov; memcpy(cmd->tvc_cdb, cdb, VHOST_SCSI_MAX_CDB_SIZE); @@ -935,7 +938,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) struct iov_iter in_iter, prot_iter, data_iter; u64 tag; u32 exp_data_len, data_direction; - int ret, prot_bytes, c = 0; + int ret, prot_bytes, i, c = 0; u16 lun; u8 task_attr; bool t10_pi = vhost_has_feature(vq, VIRTIO_SCSI_F_T10_PI); @@ -1092,7 +1095,8 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) } cmd->tvc_vhost = vs; cmd->tvc_vq = vq; - cmd->tvc_resp_iov = vq->iov[vc.out]; + for (i = 0; i < vc.in ; i++) + cmd->tvc_resp_iov[i] = vq->iov[vc.out + i]; cmd->tvc_in_iovs = vc.in; pr_debug("vhost_scsi got command opcode: %#02x, lun: %d\n", @@ -1461,6 +1465,7 @@ static void vhost_scsi_destroy_vq_cmds(struct vhost_virtqueue *vq) kfree(tv_cmd->tvc_sgl); kfree(tv_cmd->tvc_prot_sgl); kfree(tv_cmd->tvc_upages); + kfree(tv_cmd->tvc_resp_iov); } sbitmap_free(&svq->scsi_tags); @@ -1508,6 +1513,14 @@ static int vhost_scsi_setup_vq_cmds(struct vhost_virtqueue *vq, int max_cmds) goto out; } + tv_cmd->tvc_resp_iov = kcalloc(UIO_MAXIOV, + sizeof(struct iovec), + GFP_KERNEL); + if (!tv_cmd->tvc_resp_iov) { + pr_err("Unable to allocate tv_cmd->tvc_resp_iov\n"); + goto out; + } + tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS, sizeof(struct scatterlist), GFP_KERNEL); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index cbe72bfd2f1f..43c9770b86e5 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -661,7 +661,7 @@ void vhost_dev_stop(struct vhost_dev *dev) } EXPORT_SYMBOL_GPL(vhost_dev_stop); -static void vhost_clear_msg(struct vhost_dev *dev) +void vhost_clear_msg(struct vhost_dev *dev) { struct vhost_msg_node *node, *n; @@ -679,6 +679,7 @@ static void vhost_clear_msg(struct vhost_dev *dev) spin_unlock(&dev->iotlb_lock); } +EXPORT_SYMBOL_GPL(vhost_clear_msg); void vhost_dev_cleanup(struct vhost_dev *dev) { diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index d9109107af08..790b296271f1 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -181,6 +181,7 @@ long vhost_dev_ioctl(struct vhost_dev *, unsigned int ioctl, void __user *argp); long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp); bool vhost_vq_access_ok(struct vhost_virtqueue *vq); bool vhost_log_access_ok(struct vhost_dev *); +void vhost_clear_msg(struct vhost_dev *dev); int vhost_get_vq_desc(struct vhost_virtqueue *, struct iovec iov[], unsigned int iov_count, diff --git a/drivers/video/fbdev/atmel_lcdfb.c b/drivers/video/fbdev/atmel_lcdfb.c index 1fc8de4ecbeb..8187a7c4f910 100644 --- a/drivers/video/fbdev/atmel_lcdfb.c +++ b/drivers/video/fbdev/atmel_lcdfb.c @@ -49,7 +49,6 @@ struct atmel_lcdfb_info { struct clk *lcdc_clk; struct backlight_device *backlight; - u8 bl_power; u8 saved_lcdcon; u32 pseudo_palette[16]; @@ -109,22 +108,7 @@ static u32 contrast_ctr = ATMEL_LCDC_PS_DIV8 static int atmel_bl_update_status(struct backlight_device *bl) { struct atmel_lcdfb_info *sinfo = bl_get_data(bl); - int power = sinfo->bl_power; - int brightness = bl->props.brightness; - - /* REVISIT there may be a meaningful difference between - * fb_blank and power ... there seem to be some cases - * this doesn't handle correctly. - */ - if (bl->props.fb_blank != sinfo->bl_power) - power = bl->props.fb_blank; - else if (bl->props.power != sinfo->bl_power) - power = bl->props.power; - - if (brightness < 0 && power == FB_BLANK_UNBLANK) - brightness = lcdc_readl(sinfo, ATMEL_LCDC_CONTRAST_VAL); - else if (power != FB_BLANK_UNBLANK) - brightness = 0; + int brightness = backlight_get_brightness(bl); lcdc_writel(sinfo, ATMEL_LCDC_CONTRAST_VAL, brightness); if (contrast_ctr & ATMEL_LCDC_POL_POSITIVE) @@ -133,8 +117,6 @@ static int atmel_bl_update_status(struct backlight_device *bl) else lcdc_writel(sinfo, ATMEL_LCDC_CONTRAST_CTR, contrast_ctr); - bl->props.fb_blank = bl->props.power = sinfo->bl_power = power; - return 0; } @@ -155,8 +137,6 @@ static void init_backlight(struct atmel_lcdfb_info *sinfo) struct backlight_properties props; struct backlight_device *bl; - sinfo->bl_power = FB_BLANK_UNBLANK; - if (sinfo->backlight) return; diff --git a/drivers/video/fbdev/aty/aty128fb.c b/drivers/video/fbdev/aty/aty128fb.c index dd31b9d7d337..36a9ac05a340 100644 --- a/drivers/video/fbdev/aty/aty128fb.c +++ b/drivers/video/fbdev/aty/aty128fb.c @@ -1766,12 +1766,10 @@ static int aty128_bl_update_status(struct backlight_device *bd) unsigned int reg = aty_ld_le32(LVDS_GEN_CNTL); int level; - if (bd->props.power != FB_BLANK_UNBLANK || - bd->props.fb_blank != FB_BLANK_UNBLANK || - !par->lcd_on) + if (!par->lcd_on) level = 0; else - level = bd->props.brightness; + level = backlight_get_brightness(bd); reg |= LVDS_BL_MOD_EN | LVDS_BLON; if (level > 0) { diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c index d59215a4992e..b02e4e645035 100644 --- a/drivers/video/fbdev/aty/atyfb_base.c +++ b/drivers/video/fbdev/aty/atyfb_base.c @@ -2219,13 +2219,7 @@ static int aty_bl_update_status(struct backlight_device *bd) { struct atyfb_par *par = bl_get_data(bd); unsigned int reg = aty_ld_lcd(LCD_MISC_CNTL, par); - int level; - - if (bd->props.power != FB_BLANK_UNBLANK || - bd->props.fb_blank != FB_BLANK_UNBLANK) - level = 0; - else - level = bd->props.brightness; + int level = backlight_get_brightness(bd); reg |= (BLMOD_EN | BIASMOD_EN); if (level > 0) { diff --git a/drivers/video/fbdev/aty/radeon_backlight.c b/drivers/video/fbdev/aty/radeon_backlight.c index d2c1263ad260..427adc838f77 100644 --- a/drivers/video/fbdev/aty/radeon_backlight.c +++ b/drivers/video/fbdev/aty/radeon_backlight.c @@ -57,11 +57,7 @@ static int radeon_bl_update_status(struct backlight_device *bd) * backlight. This provides some greater power saving and the display * is useless without backlight anyway. */ - if (bd->props.power != FB_BLANK_UNBLANK || - bd->props.fb_blank != FB_BLANK_UNBLANK) - level = 0; - else - level = bd->props.brightness; + level = backlight_get_brightness(bd); del_timer_sync(&rinfo->lvds_timer); radeon_engine_idle(); diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 14a7d404062c..1b14c21af2b7 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2495,9 +2495,12 @@ static int fbcon_set_font(struct vc_data *vc, struct console_font *font, h > FBCON_SWAP(info->var.rotate, info->var.yres, info->var.xres)) return -EINVAL; + if (font->width > 32 || font->height > 32) + return -EINVAL; + /* Make sure drawing engine can handle the font */ - if (!(info->pixmap.blit_x & (1 << (font->width - 1))) || - !(info->pixmap.blit_y & (1 << (font->height - 1)))) + if (!(info->pixmap.blit_x & BIT(font->width - 1)) || + !(info->pixmap.blit_y & BIT(font->height - 1))) return -EINVAL; /* Make sure driver can handle the font length */ diff --git a/drivers/video/fbdev/core/fbmon.c b/drivers/video/fbdev/core/fbmon.c index b0e690f41025..79e5bfbdd34c 100644 --- a/drivers/video/fbdev/core/fbmon.c +++ b/drivers/video/fbdev/core/fbmon.c @@ -1050,7 +1050,7 @@ static u32 fb_get_vblank(u32 hfreq) } /** - * fb_get_hblank_by_freq - get horizontal blank time given hfreq + * fb_get_hblank_by_hfreq - get horizontal blank time given hfreq * @hfreq: horizontal freq * @xres: horizontal resolution in pixels * diff --git a/drivers/video/fbdev/mx3fb.c b/drivers/video/fbdev/mx3fb.c index b945b68984b9..76771e126d0a 100644 --- a/drivers/video/fbdev/mx3fb.c +++ b/drivers/video/fbdev/mx3fb.c @@ -283,12 +283,7 @@ static int mx3fb_bl_get_brightness(struct backlight_device *bl) static int mx3fb_bl_update_status(struct backlight_device *bl) { struct mx3fb_data *fbd = bl_get_data(bl); - int brightness = bl->props.brightness; - - if (bl->props.power != FB_BLANK_UNBLANK) - brightness = 0; - if (bl->props.fb_blank != FB_BLANK_UNBLANK) - brightness = 0; + int brightness = backlight_get_brightness(bl); fbd->backlight_level = (fbd->backlight_level & ~0xFF) | brightness; diff --git a/drivers/video/fbdev/nvidia/nv_backlight.c b/drivers/video/fbdev/nvidia/nv_backlight.c index 2ce53529f636..503a7a683855 100644 --- a/drivers/video/fbdev/nvidia/nv_backlight.c +++ b/drivers/video/fbdev/nvidia/nv_backlight.c @@ -49,17 +49,11 @@ static int nvidia_bl_update_status(struct backlight_device *bd) { struct nvidia_par *par = bl_get_data(bd); u32 tmp_pcrt, tmp_pmc, fpcontrol; - int level; + int level = backlight_get_brightness(bd); if (!par->FlatPanel) return 0; - if (bd->props.power != FB_BLANK_UNBLANK || - bd->props.fb_blank != FB_BLANK_UNBLANK) - level = 0; - else - level = bd->props.brightness; - tmp_pmc = NV_RD32(par->PMC, 0x10F0) & 0x0000FFFF; tmp_pcrt = NV_RD32(par->PCRTC0, 0x081C) & 0xFFFFFFFC; fpcontrol = NV_RD32(par->PRAMDAC, 0x0848) & 0xCFFFFFCC; diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c index 4fc4b26a8d30..ba94a0a7bd4f 100644 --- a/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c +++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c @@ -331,13 +331,7 @@ static int dsicm_bl_update_status(struct backlight_device *dev) struct panel_drv_data *ddata = dev_get_drvdata(&dev->dev); struct omap_dss_device *in = ddata->in; int r; - int level; - - if (dev->props.fb_blank == FB_BLANK_UNBLANK && - dev->props.power == FB_BLANK_UNBLANK) - level = dev->props.brightness; - else - level = 0; + int level = backlight_get_brightness(dev); dev_dbg(&ddata->pdev->dev, "update brightness to %d\n", level); diff --git a/drivers/video/fbdev/omap2/omapfb/dss/display-sysfs.c b/drivers/video/fbdev/omap2/omapfb/dss/display-sysfs.c index bc5a44c2a144..ae937854403b 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/display-sysfs.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/display-sysfs.c @@ -10,6 +10,7 @@ #define DSS_SUBSYS_NAME "DISPLAY" #include <linux/kernel.h> +#include <linux/kstrtox.h> #include <linux/module.h> #include <linux/platform_device.h> #include <linux/sysfs.h> @@ -36,7 +37,7 @@ static ssize_t display_enabled_store(struct omap_dss_device *dssdev, int r; bool enable; - r = strtobool(buf, &enable); + r = kstrtobool(buf, &enable); if (r) return r; @@ -73,7 +74,7 @@ static ssize_t display_tear_store(struct omap_dss_device *dssdev, if (!dssdev->driver->enable_te || !dssdev->driver->get_te) return -ENOENT; - r = strtobool(buf, &te); + r = kstrtobool(buf, &te); if (r) return r; @@ -183,7 +184,7 @@ static ssize_t display_mirror_store(struct omap_dss_device *dssdev, if (!dssdev->driver->set_mirror || !dssdev->driver->get_mirror) return -ENOENT; - r = strtobool(buf, &mirror); + r = kstrtobool(buf, &mirror); if (r) return r; diff --git a/drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c b/drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c index ba21c4a2633d..1b644be5fe2e 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c @@ -10,6 +10,7 @@ #define DSS_SUBSYS_NAME "MANAGER" #include <linux/kernel.h> +#include <linux/kstrtox.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/platform_device.h> @@ -246,7 +247,7 @@ static ssize_t manager_trans_key_enabled_store(struct omap_overlay_manager *mgr, bool enable; int r; - r = strtobool(buf, &enable); + r = kstrtobool(buf, &enable); if (r) return r; @@ -290,7 +291,7 @@ static ssize_t manager_alpha_blending_enabled_store( if(!dss_has_feature(FEAT_ALPHA_FIXED_ZORDER)) return -ENODEV; - r = strtobool(buf, &enable); + r = kstrtobool(buf, &enable); if (r) return r; @@ -329,7 +330,7 @@ static ssize_t manager_cpr_enable_store(struct omap_overlay_manager *mgr, if (!dss_has_feature(FEAT_CPR)) return -ENODEV; - r = strtobool(buf, &enable); + r = kstrtobool(buf, &enable); if (r) return r; diff --git a/drivers/video/fbdev/omap2/omapfb/dss/overlay-sysfs.c b/drivers/video/fbdev/omap2/omapfb/dss/overlay-sysfs.c index 601c0beb6de9..1da4fb1c77b4 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/overlay-sysfs.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/overlay-sysfs.c @@ -13,6 +13,7 @@ #include <linux/err.h> #include <linux/sysfs.h> #include <linux/kobject.h> +#include <linux/kstrtox.h> #include <linux/platform_device.h> #include <video/omapfb_dss.h> @@ -210,7 +211,7 @@ static ssize_t overlay_enabled_store(struct omap_overlay *ovl, const char *buf, int r; bool enable; - r = strtobool(buf, &enable); + r = kstrtobool(buf, &enable); if (r) return r; diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-sysfs.c b/drivers/video/fbdev/omap2/omapfb/omapfb-sysfs.c index 06dc41aa0354..831b2c2fbdf9 100644 --- a/drivers/video/fbdev/omap2/omapfb/omapfb-sysfs.c +++ b/drivers/video/fbdev/omap2/omapfb/omapfb-sysfs.c @@ -15,6 +15,7 @@ #include <linux/uaccess.h> #include <linux/platform_device.h> #include <linux/kernel.h> +#include <linux/kstrtox.h> #include <linux/mm.h> #include <linux/omapfb.h> @@ -96,7 +97,7 @@ static ssize_t store_mirror(struct device *dev, int r; struct fb_var_screeninfo new_var; - r = strtobool(buf, &mirror); + r = kstrtobool(buf, &mirror); if (r) return r; diff --git a/drivers/video/fbdev/riva/fbdev.c b/drivers/video/fbdev/riva/fbdev.c index 644278146d3b..41edc6e79460 100644 --- a/drivers/video/fbdev/riva/fbdev.c +++ b/drivers/video/fbdev/riva/fbdev.c @@ -293,13 +293,7 @@ static int riva_bl_update_status(struct backlight_device *bd) { struct riva_par *par = bl_get_data(bd); U032 tmp_pcrt, tmp_pmc; - int level; - - if (bd->props.power != FB_BLANK_UNBLANK || - bd->props.fb_blank != FB_BLANK_UNBLANK) - level = 0; - else - level = bd->props.brightness; + int level = backlight_get_brightness(bd); tmp_pmc = NV_RD32(par->riva.PMC, 0x10F0) & 0x0000FFFF; tmp_pcrt = NV_RD32(par->riva.PCRTC0, 0x081C) & 0xFFFFFFFC; diff --git a/drivers/watchdog/diag288_wdt.c b/drivers/watchdog/diag288_wdt.c index 4cb10877017c..6ca5d9515d85 100644 --- a/drivers/watchdog/diag288_wdt.c +++ b/drivers/watchdog/diag288_wdt.c @@ -86,7 +86,7 @@ static int __diag288(unsigned int func, unsigned int timeout, "1:\n" EX_TABLE(0b, 1b) : "+d" (err) : "d"(__func), "d"(__timeout), - "d"(__action), "d"(__len) : "1", "cc"); + "d"(__action), "d"(__len) : "1", "cc", "memory"); return err; } @@ -268,12 +268,21 @@ static int __init diag288_init(void) char ebc_begin[] = { 194, 197, 199, 201, 213 }; + char *ebc_cmd; watchdog_set_nowayout(&wdt_dev, nowayout_info); if (MACHINE_IS_VM) { - if (__diag288_vm(WDT_FUNC_INIT, 15, - ebc_begin, sizeof(ebc_begin)) != 0) { + ebc_cmd = kmalloc(sizeof(ebc_begin), GFP_KERNEL); + if (!ebc_cmd) { + pr_err("The watchdog cannot be initialized\n"); + return -ENOMEM; + } + memcpy(ebc_cmd, ebc_begin, sizeof(ebc_begin)); + ret = __diag288_vm(WDT_FUNC_INIT, 15, + ebc_cmd, sizeof(ebc_begin)); + kfree(ebc_cmd); + if (ret != 0) { pr_err("The watchdog cannot be initialized\n"); return -EINVAL; } diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 6a2cf754912d..ff4b1d583788 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -1426,12 +1426,20 @@ static void rbio_update_error_bitmap(struct btrfs_raid_bio *rbio, struct bio *bi u32 bio_size = 0; struct bio_vec *bvec; struct bvec_iter_all iter_all; + int i; bio_for_each_segment_all(bvec, bio, iter_all) bio_size += bvec->bv_len; - bitmap_set(rbio->error_bitmap, total_sector_nr, - bio_size >> rbio->bioc->fs_info->sectorsize_bits); + /* + * Since we can have multiple bios touching the error_bitmap, we cannot + * call bitmap_set() without protection. + * + * Instead use set_bit() for each bit, as set_bit() itself is atomic. + */ + for (i = total_sector_nr; i < total_sector_nr + + (bio_size >> rbio->bioc->fs_info->sectorsize_bits); i++) + set_bit(i, rbio->error_bitmap); } /* Verify the data sectors at read time. */ @@ -1886,7 +1894,7 @@ pstripe: sector->uptodate = 1; } if (failb >= 0) { - ret = verify_one_sector(rbio, faila, sector_nr); + ret = verify_one_sector(rbio, failb, sector_nr); if (ret < 0) goto cleanup; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index e65e6b6600a7..d50182b6deec 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -8073,10 +8073,10 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg) /* * Check that we don't overflow at later allocations, we request * clone_sources_count + 1 items, and compare to unsigned long inside - * access_ok. + * access_ok. Also set an upper limit for allocation size so this can't + * easily exhaust memory. Max number of clone sources is about 200K. */ - if (arg->clone_sources_count > - ULONG_MAX / sizeof(struct clone_root) - 1) { + if (arg->clone_sources_count > SZ_8M / sizeof(struct clone_root)) { ret = -EINVAL; goto out; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index bcfef75b97da..4cdadf30163d 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1600,7 +1600,7 @@ again: if (ret < 0) goto out; - while (1) { + while (search_start < search_end) { l = path->nodes[0]; slot = path->slots[0]; if (slot >= btrfs_header_nritems(l)) { @@ -1623,6 +1623,9 @@ again: if (key.type != BTRFS_DEV_EXTENT_KEY) goto next; + if (key.offset > search_end) + break; + if (key.offset > search_start) { hole_size = key.offset - search_start; dev_extent_hole_check(device, &search_start, &hole_size, @@ -1683,6 +1686,7 @@ next: else ret = 0; + ASSERT(max_hole_start + max_hole_size <= search_end); out: btrfs_free_path(path); *start = max_hole_start; diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index 01a13de11832..da7bb9187b68 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -63,7 +63,7 @@ struct list_head *zlib_alloc_workspace(unsigned int level) workspacesize = max(zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL), zlib_inflate_workspacesize()); - workspace->strm.workspace = kvmalloc(workspacesize, GFP_KERNEL); + workspace->strm.workspace = kvzalloc(workspacesize, GFP_KERNEL); workspace->level = level; workspace->buf = NULL; /* diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 8c74871e37c9..cac4083e387a 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -305,7 +305,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) struct inode *inode = rreq->inode; struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_fs_client *fsc = ceph_inode_to_client(inode); - struct ceph_osd_request *req; + struct ceph_osd_request *req = NULL; struct ceph_vino vino = ceph_vino(inode); struct iov_iter iter; struct page **pages; @@ -313,6 +313,11 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) int err = 0; u64 len = subreq->len; + if (ceph_inode_is_shutdown(inode)) { + err = -EIO; + goto out; + } + if (ceph_has_inline_data(ci) && ceph_netfs_issue_op_inline(subreq)) return; @@ -563,6 +568,9 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) dout("writepage %p idx %lu\n", page, page->index); + if (ceph_inode_is_shutdown(inode)) + return -EIO; + /* verify this is a writeable snap context */ snapc = page_snap_context(page); if (!snapc) { @@ -1643,7 +1651,7 @@ int ceph_uninline_data(struct file *file) struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_fs_client *fsc = ceph_inode_to_client(inode); struct ceph_osd_request *req = NULL; - struct ceph_cap_flush *prealloc_cf; + struct ceph_cap_flush *prealloc_cf = NULL; struct folio *folio = NULL; u64 inline_version = CEPH_INLINE_NONE; struct page *pages[1]; @@ -1657,6 +1665,11 @@ int ceph_uninline_data(struct file *file) dout("uninline_data %p %llx.%llx inline_version %llu\n", inode, ceph_vinop(inode), inline_version); + if (ceph_inode_is_shutdown(inode)) { + err = -EIO; + goto out; + } + if (inline_version == CEPH_INLINE_NONE) return 0; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index f75ad432f375..210e40037881 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -4078,6 +4078,7 @@ void ceph_handle_caps(struct ceph_mds_session *session, void *p, *end; struct cap_extra_info extra_info = {}; bool queue_trunc; + bool close_sessions = false; dout("handle_caps from mds%d\n", session->s_mds); @@ -4215,9 +4216,13 @@ void ceph_handle_caps(struct ceph_mds_session *session, realm = NULL; if (snaptrace_len) { down_write(&mdsc->snap_rwsem); - ceph_update_snap_trace(mdsc, snaptrace, - snaptrace + snaptrace_len, - false, &realm); + if (ceph_update_snap_trace(mdsc, snaptrace, + snaptrace + snaptrace_len, + false, &realm)) { + up_write(&mdsc->snap_rwsem); + close_sessions = true; + goto done; + } downgrade_write(&mdsc->snap_rwsem); } else { down_read(&mdsc->snap_rwsem); @@ -4277,6 +4282,11 @@ done_unlocked: iput(inode); out: ceph_put_string(extra_info.pool_ns); + + /* Defer closing the sessions after s_mutex lock being released */ + if (close_sessions) + ceph_mdsc_close_sessions(mdsc); + return; flush_cap_releases: diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 764598e1efd9..b5cff85925a1 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -2011,6 +2011,9 @@ static int ceph_zero_partial_object(struct inode *inode, loff_t zero = 0; int op; + if (ceph_inode_is_shutdown(inode)) + return -EIO; + if (!length) { op = offset ? CEPH_OSD_OP_DELETE : CEPH_OSD_OP_TRUNCATE; length = &zero; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 26a0a8b9975e..e163f58ff3c5 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -806,6 +806,9 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc, { struct ceph_mds_session *s; + if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_FENCE_IO) + return ERR_PTR(-EIO); + if (mds >= mdsc->mdsmap->possible_max_rank) return ERR_PTR(-EINVAL); @@ -1478,6 +1481,9 @@ static int __open_session(struct ceph_mds_client *mdsc, int mstate; int mds = session->s_mds; + if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_FENCE_IO) + return -EIO; + /* wait for mds to go active? */ mstate = ceph_mdsmap_get_state(mdsc->mdsmap, mds); dout("open_session to mds%d (%s)\n", mds, @@ -2860,6 +2866,11 @@ static void __do_request(struct ceph_mds_client *mdsc, return; } + if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_FENCE_IO) { + dout("do_request metadata corrupted\n"); + err = -EIO; + goto finish; + } if (req->r_timeout && time_after_eq(jiffies, req->r_started + req->r_timeout)) { dout("do_request timed out\n"); @@ -3245,6 +3256,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) u64 tid; int err, result; int mds = session->s_mds; + bool close_sessions = false; if (msg->front.iov_len < sizeof(*head)) { pr_err("mdsc_handle_reply got corrupt (short) reply\n"); @@ -3351,10 +3363,17 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) realm = NULL; if (rinfo->snapblob_len) { down_write(&mdsc->snap_rwsem); - ceph_update_snap_trace(mdsc, rinfo->snapblob, + err = ceph_update_snap_trace(mdsc, rinfo->snapblob, rinfo->snapblob + rinfo->snapblob_len, le32_to_cpu(head->op) == CEPH_MDS_OP_RMSNAP, &realm); + if (err) { + up_write(&mdsc->snap_rwsem); + close_sessions = true; + if (err == -EIO) + ceph_msg_dump(msg); + goto out_err; + } downgrade_write(&mdsc->snap_rwsem); } else { down_read(&mdsc->snap_rwsem); @@ -3412,6 +3431,10 @@ out_err: req->r_end_latency, err); out: ceph_mdsc_put_request(req); + + /* Defer closing the sessions after s_mutex lock being released */ + if (close_sessions) + ceph_mdsc_close_sessions(mdsc); return; } @@ -5011,7 +5034,7 @@ static bool done_closing_sessions(struct ceph_mds_client *mdsc, int skipped) } /* - * called after sb is ro. + * called after sb is ro or when metadata corrupted. */ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc) { @@ -5301,7 +5324,8 @@ static void mds_peer_reset(struct ceph_connection *con) struct ceph_mds_client *mdsc = s->s_mdsc; pr_warn("mds%d closed our session\n", s->s_mds); - send_mds_reconnect(mdsc, s); + if (READ_ONCE(mdsc->fsc->mount_state) != CEPH_MOUNT_FENCE_IO) + send_mds_reconnect(mdsc, s); } static void mds_dispatch(struct ceph_connection *con, struct ceph_msg *msg) diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index e4151852184e..87007203f130 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/ceph/ceph_debug.h> +#include <linux/fs.h> #include <linux/sort.h> #include <linux/slab.h> #include <linux/iversion.h> @@ -766,8 +767,10 @@ int ceph_update_snap_trace(struct ceph_mds_client *mdsc, struct ceph_snap_realm *realm; struct ceph_snap_realm *first_realm = NULL; struct ceph_snap_realm *realm_to_rebuild = NULL; + struct ceph_client *client = mdsc->fsc->client; int rebuild_snapcs; int err = -ENOMEM; + int ret; LIST_HEAD(dirty_realms); lockdep_assert_held_write(&mdsc->snap_rwsem); @@ -884,6 +887,27 @@ fail: if (first_realm) ceph_put_snap_realm(mdsc, first_realm); pr_err("%s error %d\n", __func__, err); + + /* + * When receiving a corrupted snap trace we don't know what + * exactly has happened in MDS side. And we shouldn't continue + * writing to OSD, which may corrupt the snapshot contents. + * + * Just try to blocklist this kclient and then this kclient + * must be remounted to continue after the corrupted metadata + * fixed in the MDS side. + */ + WRITE_ONCE(mdsc->fsc->mount_state, CEPH_MOUNT_FENCE_IO); + ret = ceph_monc_blocklist_add(&client->monc, &client->msgr.inst.addr); + if (ret) + pr_err("%s failed to blocklist %s: %d\n", __func__, + ceph_pr_addr(&client->msgr.inst.addr), ret); + + WARN(1, "%s: %s%sdo remount to continue%s", + __func__, ret ? "" : ceph_pr_addr(&client->msgr.inst.addr), + ret ? "" : " was blocklisted, ", + err == -EIO ? " after corrupted snaptrace is fixed" : ""); + return err; } @@ -984,6 +1008,7 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc, __le64 *split_inos = NULL, *split_realms = NULL; int i; int locked_rwsem = 0; + bool close_sessions = false; /* decode */ if (msg->front.iov_len < sizeof(*h)) @@ -1092,8 +1117,12 @@ skip_inode: * update using the provided snap trace. if we are deleting a * snap, we can avoid queueing cap_snaps. */ - ceph_update_snap_trace(mdsc, p, e, - op == CEPH_SNAP_OP_DESTROY, NULL); + if (ceph_update_snap_trace(mdsc, p, e, + op == CEPH_SNAP_OP_DESTROY, + NULL)) { + close_sessions = true; + goto bad; + } if (op == CEPH_SNAP_OP_SPLIT) /* we took a reference when we created the realm, above */ @@ -1112,6 +1141,9 @@ bad: out: if (locked_rwsem) up_write(&mdsc->snap_rwsem); + + if (close_sessions) + ceph_mdsc_close_sessions(mdsc); return; } diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 0ed3be75bb9a..07c6906cda70 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -100,6 +100,17 @@ struct ceph_mount_options { char *mon_addr; }; +/* mount state */ +enum { + CEPH_MOUNT_MOUNTING, + CEPH_MOUNT_MOUNTED, + CEPH_MOUNT_UNMOUNTING, + CEPH_MOUNT_UNMOUNTED, + CEPH_MOUNT_SHUTDOWN, + CEPH_MOUNT_RECOVER, + CEPH_MOUNT_FENCE_IO, +}; + #define CEPH_ASYNC_CREATE_CONFLICT_BITS 8 struct ceph_fs_client { diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 22dfc1f8b4f1..b8d1cbadb689 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3889,7 +3889,7 @@ uncached_fill_pages(struct TCP_Server_Info *server, rdata->got_bytes += result; } - return rdata->got_bytes > 0 && result != -ECONNABORTED ? + return result != -ECONNABORTED && rdata->got_bytes > 0 ? rdata->got_bytes : result; } @@ -4665,7 +4665,7 @@ readpages_fill_pages(struct TCP_Server_Info *server, rdata->got_bytes += result; } - return rdata->got_bytes > 0 && result != -ECONNABORTED ? + return result != -ECONNABORTED && rdata->got_bytes > 0 ? rdata->got_bytes : result; } diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index 90789aaa6567..8c816b25ce7c 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -1405,6 +1405,7 @@ void smbd_destroy(struct TCP_Server_Info *server) destroy_workqueue(info->workqueue); log_rdma_event(INFO, "rdma session destroyed\n"); kfree(info); + server->smbd_conn = NULL; } /* diff --git a/fs/coredump.c b/fs/coredump.c index de78bde2991b..a25ecec9ca7c 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -838,6 +838,30 @@ static int __dump_skip(struct coredump_params *cprm, size_t nr) } } +int dump_emit(struct coredump_params *cprm, const void *addr, int nr) +{ + if (cprm->to_skip) { + if (!__dump_skip(cprm, cprm->to_skip)) + return 0; + cprm->to_skip = 0; + } + return __dump_emit(cprm, addr, nr); +} +EXPORT_SYMBOL(dump_emit); + +void dump_skip_to(struct coredump_params *cprm, unsigned long pos) +{ + cprm->to_skip = pos - cprm->pos; +} +EXPORT_SYMBOL(dump_skip_to); + +void dump_skip(struct coredump_params *cprm, size_t nr) +{ + cprm->to_skip += nr; +} +EXPORT_SYMBOL(dump_skip); + +#ifdef CONFIG_ELF_CORE static int dump_emit_page(struct coredump_params *cprm, struct page *page) { struct bio_vec bvec = { @@ -871,30 +895,6 @@ static int dump_emit_page(struct coredump_params *cprm, struct page *page) return 1; } -int dump_emit(struct coredump_params *cprm, const void *addr, int nr) -{ - if (cprm->to_skip) { - if (!__dump_skip(cprm, cprm->to_skip)) - return 0; - cprm->to_skip = 0; - } - return __dump_emit(cprm, addr, nr); -} -EXPORT_SYMBOL(dump_emit); - -void dump_skip_to(struct coredump_params *cprm, unsigned long pos) -{ - cprm->to_skip = pos - cprm->pos; -} -EXPORT_SYMBOL(dump_skip_to); - -void dump_skip(struct coredump_params *cprm, size_t nr) -{ - cprm->to_skip += nr; -} -EXPORT_SYMBOL(dump_skip); - -#ifdef CONFIG_ELF_CORE int dump_user_range(struct coredump_params *cprm, unsigned long start, unsigned long len) { diff --git a/fs/freevxfs/Kconfig b/fs/freevxfs/Kconfig index c05c71d57291..0e2fc08f7de4 100644 --- a/fs/freevxfs/Kconfig +++ b/fs/freevxfs/Kconfig @@ -8,7 +8,7 @@ config VXFS_FS of SCO UnixWare (and possibly others) and optionally available for Sunsoft Solaris, HP-UX and many other operating systems. However these particular OS implementations of vxfs may differ in on-disk - data endianess and/or superblock offset. The vxfs module has been + data endianness and/or superblock offset. The vxfs module has been tested with SCO UnixWare and HP-UX B.10.20 (pa-risc 1.1 arch.) Currently only readonly access is supported and VxFX versions 2, 3 and 4. Tests were performed with HP-UX VxFS version 3. diff --git a/fs/fscache/volume.c b/fs/fscache/volume.c index ab8ceddf9efa..cdf991bdd9de 100644 --- a/fs/fscache/volume.c +++ b/fs/fscache/volume.c @@ -141,13 +141,14 @@ static bool fscache_is_acquire_pending(struct fscache_volume *volume) static void fscache_wait_on_volume_collision(struct fscache_volume *candidate, unsigned int collidee_debug_id) { - wait_var_event_timeout(&candidate->flags, - !fscache_is_acquire_pending(candidate), 20 * HZ); + wait_on_bit_timeout(&candidate->flags, FSCACHE_VOLUME_ACQUIRE_PENDING, + TASK_UNINTERRUPTIBLE, 20 * HZ); if (fscache_is_acquire_pending(candidate)) { pr_notice("Potential volume collision new=%08x old=%08x", candidate->debug_id, collidee_debug_id); fscache_stat(&fscache_n_volumes_collision); - wait_var_event(&candidate->flags, !fscache_is_acquire_pending(candidate)); + wait_on_bit(&candidate->flags, FSCACHE_VOLUME_ACQUIRE_PENDING, + TASK_UNINTERRUPTIBLE); } } @@ -279,8 +280,7 @@ static void fscache_create_volume_work(struct work_struct *work) fscache_end_cache_access(volume->cache, fscache_access_acquire_volume_end); - clear_bit_unlock(FSCACHE_VOLUME_CREATING, &volume->flags); - wake_up_bit(&volume->flags, FSCACHE_VOLUME_CREATING); + clear_and_wake_up_bit(FSCACHE_VOLUME_CREATING, &volume->flags); fscache_put_volume(volume, fscache_volume_put_create_work); } @@ -347,8 +347,8 @@ static void fscache_wake_pending_volume(struct fscache_volume *volume, hlist_bl_for_each_entry(cursor, p, h, hash_link) { if (fscache_volume_same(cursor, volume)) { fscache_see_volume(cursor, fscache_volume_see_hash_wake); - clear_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &cursor->flags); - wake_up_bit(&cursor->flags, FSCACHE_VOLUME_ACQUIRE_PENDING); + clear_and_wake_up_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, + &cursor->flags); return; } } diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c index fd0a288af299..56be077e5d8a 100644 --- a/fs/ksmbd/connection.c +++ b/fs/ksmbd/connection.c @@ -280,7 +280,7 @@ int ksmbd_conn_handler_loop(void *p) { struct ksmbd_conn *conn = (struct ksmbd_conn *)p; struct ksmbd_transport *t = conn->transport; - unsigned int pdu_size; + unsigned int pdu_size, max_allowed_pdu_size; char hdr_buf[4] = {0,}; int size; @@ -305,13 +305,26 @@ int ksmbd_conn_handler_loop(void *p) pdu_size = get_rfc1002_len(hdr_buf); ksmbd_debug(CONN, "RFC1002 header %u bytes\n", pdu_size); + if (conn->status == KSMBD_SESS_GOOD) + max_allowed_pdu_size = + SMB3_MAX_MSGSIZE + conn->vals->max_write_size; + else + max_allowed_pdu_size = SMB3_MAX_MSGSIZE; + + if (pdu_size > max_allowed_pdu_size) { + pr_err_ratelimited("PDU length(%u) excceed maximum allowed pdu size(%u) on connection(%d)\n", + pdu_size, max_allowed_pdu_size, + conn->status); + break; + } + /* * Check if pdu size is valid (min : smb header size, * max : 0x00FFFFFF). */ if (pdu_size < __SMB2_HEADER_STRUCTURE_SIZE || pdu_size > MAX_STREAM_PROT_LEN) { - continue; + break; } /* 4 for rfc1002 length field */ diff --git a/fs/ksmbd/ksmbd_netlink.h b/fs/ksmbd/ksmbd_netlink.h index b6bd8311e6b4..fb8b2d566efb 100644 --- a/fs/ksmbd/ksmbd_netlink.h +++ b/fs/ksmbd/ksmbd_netlink.h @@ -106,7 +106,8 @@ struct ksmbd_startup_request { __u32 sub_auth[3]; /* Subauth value for Security ID */ __u32 smb2_max_credits; /* MAX credits */ __u32 smbd_max_io_size; /* smbd read write size */ - __u32 reserved[127]; /* Reserved room */ + __u32 max_connections; /* Number of maximum simultaneous connections */ + __u32 reserved[126]; /* Reserved room */ __u32 ifc_list_sz; /* interfaces list size */ __s8 ____payload[]; }; diff --git a/fs/ksmbd/ndr.c b/fs/ksmbd/ndr.c index 0ae8d08d85a8..4d9e0b54e3db 100644 --- a/fs/ksmbd/ndr.c +++ b/fs/ksmbd/ndr.c @@ -242,7 +242,7 @@ int ndr_decode_dos_attr(struct ndr *n, struct xattr_dos_attrib *da) return ret; if (da->version != 3 && da->version != 4) { - pr_err("v%d version is not supported\n", da->version); + ksmbd_debug(VFS, "v%d version is not supported\n", da->version); return -EINVAL; } @@ -251,7 +251,7 @@ int ndr_decode_dos_attr(struct ndr *n, struct xattr_dos_attrib *da) return ret; if (da->version != version2) { - pr_err("ndr version mismatched(version: %d, version2: %d)\n", + ksmbd_debug(VFS, "ndr version mismatched(version: %d, version2: %d)\n", da->version, version2); return -EINVAL; } @@ -457,7 +457,7 @@ int ndr_decode_v4_ntacl(struct ndr *n, struct xattr_ntacl *acl) if (ret) return ret; if (acl->version != 4) { - pr_err("v%d version is not supported\n", acl->version); + ksmbd_debug(VFS, "v%d version is not supported\n", acl->version); return -EINVAL; } @@ -465,7 +465,7 @@ int ndr_decode_v4_ntacl(struct ndr *n, struct xattr_ntacl *acl) if (ret) return ret; if (acl->version != version2) { - pr_err("ndr version mismatched(version: %d, version2: %d)\n", + ksmbd_debug(VFS, "ndr version mismatched(version: %d, version2: %d)\n", acl->version, version2); return -EINVAL; } diff --git a/fs/ksmbd/server.h b/fs/ksmbd/server.h index ac9d932f8c8a..db7278181760 100644 --- a/fs/ksmbd/server.h +++ b/fs/ksmbd/server.h @@ -41,6 +41,7 @@ struct ksmbd_server_config { unsigned int share_fake_fscaps; struct smb_sid domain_sid; unsigned int auth_mechs; + unsigned int max_connections; char *conf[SERVER_CONF_WORK_GROUP + 1]; }; diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 38fbda52e06f..d681f91947d9 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -8663,6 +8663,7 @@ int smb3_decrypt_req(struct ksmbd_work *work) bool smb3_11_final_sess_setup_resp(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; + struct ksmbd_session *sess = work->sess; struct smb2_hdr *rsp = smb2_get_msg(work->response_buf); if (conn->dialect < SMB30_PROT_ID) @@ -8672,6 +8673,7 @@ bool smb3_11_final_sess_setup_resp(struct ksmbd_work *work) rsp = ksmbd_resp_buf_next(work); if (le16_to_cpu(rsp->Command) == SMB2_SESSION_SETUP_HE && + sess->user && !user_guest(sess->user) && rsp->Status == STATUS_SUCCESS) return true; return false; diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h index aa5dbe54f5a1..0c8a770fe318 100644 --- a/fs/ksmbd/smb2pdu.h +++ b/fs/ksmbd/smb2pdu.h @@ -24,8 +24,9 @@ #define SMB21_DEFAULT_IOSIZE (1024 * 1024) #define SMB3_DEFAULT_TRANS_SIZE (1024 * 1024) -#define SMB3_MIN_IOSIZE (64 * 1024) -#define SMB3_MAX_IOSIZE (8 * 1024 * 1024) +#define SMB3_MIN_IOSIZE (64 * 1024) +#define SMB3_MAX_IOSIZE (8 * 1024 * 1024) +#define SMB3_MAX_MSGSIZE (4 * 4096) /* * Definitions for SMB2 Protocol Data Units (network frames) diff --git a/fs/ksmbd/transport_ipc.c b/fs/ksmbd/transport_ipc.c index c9aca21637d5..40c721f9227e 100644 --- a/fs/ksmbd/transport_ipc.c +++ b/fs/ksmbd/transport_ipc.c @@ -308,6 +308,9 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req) if (req->smbd_max_io_size) init_smbd_max_io_size(req->smbd_max_io_size); + if (req->max_connections) + server_conf.max_connections = req->max_connections; + ret = ksmbd_set_netbios_name(req->netbios_name); ret |= ksmbd_set_server_string(req->server_string); ret |= ksmbd_set_work_group(req->work_group); diff --git a/fs/ksmbd/transport_tcp.c b/fs/ksmbd/transport_tcp.c index 4c6bd0b69979..603893fd87f5 100644 --- a/fs/ksmbd/transport_tcp.c +++ b/fs/ksmbd/transport_tcp.c @@ -15,6 +15,8 @@ #define IFACE_STATE_DOWN BIT(0) #define IFACE_STATE_CONFIGURED BIT(1) +static atomic_t active_num_conn; + struct interface { struct task_struct *ksmbd_kthread; struct socket *ksmbd_socket; @@ -185,8 +187,10 @@ static int ksmbd_tcp_new_connection(struct socket *client_sk) struct tcp_transport *t; t = alloc_transport(client_sk); - if (!t) + if (!t) { + sock_release(client_sk); return -ENOMEM; + } csin = KSMBD_TCP_PEER_SOCKADDR(KSMBD_TRANS(t)->conn); if (kernel_getpeername(client_sk, csin) < 0) { @@ -239,6 +243,15 @@ static int ksmbd_kthread_fn(void *p) continue; } + if (server_conf.max_connections && + atomic_inc_return(&active_num_conn) >= server_conf.max_connections) { + pr_info_ratelimited("Limit the maximum number of connections(%u)\n", + atomic_read(&active_num_conn)); + atomic_dec(&active_num_conn); + sock_release(client_sk); + continue; + } + ksmbd_debug(CONN, "connect success: accepted new connection\n"); client_sk->sk->sk_rcvtimeo = KSMBD_TCP_RECV_TIMEOUT; client_sk->sk->sk_sndtimeo = KSMBD_TCP_SEND_TIMEOUT; @@ -368,6 +381,8 @@ static int ksmbd_tcp_writev(struct ksmbd_transport *t, struct kvec *iov, static void ksmbd_tcp_disconnect(struct ksmbd_transport *t) { free_transport(TCP_TRANS(t)); + if (server_conf.max_connections) + atomic_dec(&active_num_conn); } static void tcp_destroy_socket(struct socket *ksmbd_socket) diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 6e4e65ee050d..c14e90764e35 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -792,7 +792,7 @@ static int ovl_copy_up_tmpfile(struct ovl_copy_up_ctx *c) if (!c->metacopy && c->stat.size) { err = ovl_copy_up_file(ofs, c->dentry, tmpfile, c->stat.size); if (err) - return err; + goto out_fput; } err = ovl_copy_up_metadata(c, temp); @@ -1011,6 +1011,10 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, if (err) return err; + if (!kuid_has_mapping(current_user_ns(), ctx.stat.uid) || + !kgid_has_mapping(current_user_ns(), ctx.stat.gid)) + return -EOVERFLOW; + ctx.metacopy = ovl_need_meta_copy_up(dentry, ctx.stat.mode, flags); if (parent) { diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index e35a0398db63..af1c49ae11b1 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -745,9 +745,7 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, page = pfn_swap_entry_to_page(swpent); } if (page) { - int mapcount = page_mapcount(page); - - if (mapcount >= 2) + if (page_mapcount(page) >= 2 || hugetlb_pmd_shared(pte)) mss->shared_hugetlb += huge_page_size(hstate_vma(vma)); else mss->private_hugetlb += huge_page_size(hstate_vma(vma)); diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h index b3fdc8212c5f..95f8e8901768 100644 --- a/fs/squashfs/squashfs_fs.h +++ b/fs/squashfs/squashfs_fs.h @@ -183,7 +183,7 @@ static inline int squashfs_block_size(__le32 raw) #define SQUASHFS_ID_BLOCK_BYTES(A) (SQUASHFS_ID_BLOCKS(A) *\ sizeof(u64)) /* xattr id lookup table defines */ -#define SQUASHFS_XATTR_BYTES(A) ((A) * sizeof(struct squashfs_xattr_id)) +#define SQUASHFS_XATTR_BYTES(A) (((u64) (A)) * sizeof(struct squashfs_xattr_id)) #define SQUASHFS_XATTR_BLOCK(A) (SQUASHFS_XATTR_BYTES(A) / \ SQUASHFS_METADATA_SIZE) diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h index 659082e9e51d..72f6f4b37863 100644 --- a/fs/squashfs/squashfs_fs_sb.h +++ b/fs/squashfs/squashfs_fs_sb.h @@ -63,7 +63,7 @@ struct squashfs_sb_info { long long bytes_used; unsigned int inodes; unsigned int fragments; - int xattr_ids; + unsigned int xattr_ids; unsigned int ids; bool panic_on_errors; const struct squashfs_decompressor_thread_ops *thread_ops; diff --git a/fs/squashfs/xattr.h b/fs/squashfs/xattr.h index d8a270d3ac4c..f1a463d8bfa0 100644 --- a/fs/squashfs/xattr.h +++ b/fs/squashfs/xattr.h @@ -10,12 +10,12 @@ #ifdef CONFIG_SQUASHFS_XATTR extern __le64 *squashfs_read_xattr_id_table(struct super_block *, u64, - u64 *, int *); + u64 *, unsigned int *); extern int squashfs_xattr_lookup(struct super_block *, unsigned int, int *, unsigned int *, unsigned long long *); #else static inline __le64 *squashfs_read_xattr_id_table(struct super_block *sb, - u64 start, u64 *xattr_table_start, int *xattr_ids) + u64 start, u64 *xattr_table_start, unsigned int *xattr_ids) { struct squashfs_xattr_id_table *id_table; diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c index 087cab8c78f4..b88d19e9581e 100644 --- a/fs/squashfs/xattr_id.c +++ b/fs/squashfs/xattr_id.c @@ -56,7 +56,7 @@ int squashfs_xattr_lookup(struct super_block *sb, unsigned int index, * Read uncompressed xattr id lookup table indexes from disk into memory */ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start, - u64 *xattr_table_start, int *xattr_ids) + u64 *xattr_table_start, unsigned int *xattr_ids) { struct squashfs_sb_info *msblk = sb->s_fs_info; unsigned int len, indexes; @@ -76,7 +76,7 @@ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start, /* Sanity check values */ /* there is always at least one xattr id */ - if (*xattr_ids == 0) + if (*xattr_ids <= 0) return ERR_PTR(-EINVAL); len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids); diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h index b111dc7ada78..095370ef029d 100644 --- a/include/drm/drm_fb_helper.h +++ b/include/drm/drm_fb_helper.h @@ -208,6 +208,18 @@ struct drm_fb_helper { * the smem_start field should always be cleared to zero. */ bool hint_leak_smem_start; + +#ifdef CONFIG_FB_DEFERRED_IO + /** + * @fbdefio: + * + * Temporary storage for the driver's FB deferred I/O handler. If the + * driver uses the DRM fbdev emulation layer, this is set by the core + * to a generic deferred I/O handler if a driver is preferring to use + * a shadow buffer. + */ + struct fb_deferred_io fbdefio; +#endif }; static inline struct drm_fb_helper * diff --git a/include/drm/drm_vma_manager.h b/include/drm/drm_vma_manager.h index 4f8c35206f7c..6c2a2f21dbf0 100644 --- a/include/drm/drm_vma_manager.h +++ b/include/drm/drm_vma_manager.h @@ -74,6 +74,7 @@ void drm_vma_offset_remove(struct drm_vma_offset_manager *mgr, struct drm_vma_offset_node *node); int drm_vma_node_allow(struct drm_vma_offset_node *node, struct drm_file *tag); +int drm_vma_node_allow_once(struct drm_vma_offset_node *node, struct drm_file *tag); void drm_vma_node_revoke(struct drm_vma_offset_node *node, struct drm_file *tag); bool drm_vma_node_is_allowed(struct drm_vma_offset_node *node, diff --git a/include/kunit/test.h b/include/kunit/test.h index 87ea90576b50..08d3559dd703 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -303,7 +303,6 @@ static inline int kunit_run_all_tests(void) */ #define kunit_test_init_section_suites(__suites...) \ __kunit_test_suites(CONCATENATE(__UNIQUE_ID(array), _probe), \ - CONCATENATE(__UNIQUE_ID(suites), _probe), \ ##__suites) #define kunit_test_init_section_suite(suite) \ @@ -683,8 +682,9 @@ do { \ .right_text = #right, \ }; \ \ - if (likely(memcmp(__left, __right, __size) op 0)) \ - break; \ + if (likely(__left && __right)) \ + if (likely(memcmp(__left, __right, __size) op 0)) \ + break; \ \ _KUNIT_FAILED(test, \ assert_type, \ diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 9270cd87da3f..6470f67e63c4 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -263,7 +263,7 @@ struct vgic_dist { struct vgic_io_device dist_iodev; bool has_its; - bool save_its_tables_in_progress; + bool table_write_in_progress; /* * Contains the attributes and gpa of the LPI configuration table. diff --git a/include/linux/apple-gmux.h b/include/linux/apple-gmux.h index ddb10aa67b14..1f68b49bcd68 100644 --- a/include/linux/apple-gmux.h +++ b/include/linux/apple-gmux.h @@ -8,18 +8,118 @@ #define LINUX_APPLE_GMUX_H #include <linux/acpi.h> +#include <linux/io.h> +#include <linux/pnp.h> #define GMUX_ACPI_HID "APP000B" +/* + * gmux port offsets. Many of these are not yet used, but may be in the + * future, and it's useful to have them documented here anyhow. + */ +#define GMUX_PORT_VERSION_MAJOR 0x04 +#define GMUX_PORT_VERSION_MINOR 0x05 +#define GMUX_PORT_VERSION_RELEASE 0x06 +#define GMUX_PORT_SWITCH_DISPLAY 0x10 +#define GMUX_PORT_SWITCH_GET_DISPLAY 0x11 +#define GMUX_PORT_INTERRUPT_ENABLE 0x14 +#define GMUX_PORT_INTERRUPT_STATUS 0x16 +#define GMUX_PORT_SWITCH_DDC 0x28 +#define GMUX_PORT_SWITCH_EXTERNAL 0x40 +#define GMUX_PORT_SWITCH_GET_EXTERNAL 0x41 +#define GMUX_PORT_DISCRETE_POWER 0x50 +#define GMUX_PORT_MAX_BRIGHTNESS 0x70 +#define GMUX_PORT_BRIGHTNESS 0x74 +#define GMUX_PORT_VALUE 0xc2 +#define GMUX_PORT_READ 0xd0 +#define GMUX_PORT_WRITE 0xd4 + +#define GMUX_MIN_IO_LEN (GMUX_PORT_BRIGHTNESS + 4) + #if IS_ENABLED(CONFIG_APPLE_GMUX) +static inline bool apple_gmux_is_indexed(unsigned long iostart) +{ + u16 val; + + outb(0xaa, iostart + 0xcc); + outb(0x55, iostart + 0xcd); + outb(0x00, iostart + 0xce); + + val = inb(iostart + 0xcc) | (inb(iostart + 0xcd) << 8); + if (val == 0x55aa) + return true; + + return false; +} /** - * apple_gmux_present() - detect if gmux is built into the machine + * apple_gmux_detect() - detect if gmux is built into the machine + * + * @pnp_dev: Device to probe or NULL to use the first matching device + * @indexed_ret: Returns (by reference) if the gmux is indexed or not + * + * Detect if a supported gmux device is present by actually probing it. + * This avoids the false positives returned on some models by + * apple_gmux_present(). + * + * Return: %true if a supported gmux ACPI device is detected and the kernel + * was configured with CONFIG_APPLE_GMUX, %false otherwise. + */ +static inline bool apple_gmux_detect(struct pnp_dev *pnp_dev, bool *indexed_ret) +{ + u8 ver_major, ver_minor, ver_release; + struct device *dev = NULL; + struct acpi_device *adev; + struct resource *res; + bool indexed = false; + bool ret = false; + + if (!pnp_dev) { + adev = acpi_dev_get_first_match_dev(GMUX_ACPI_HID, NULL, -1); + if (!adev) + return false; + + dev = get_device(acpi_get_first_physical_node(adev)); + acpi_dev_put(adev); + if (!dev) + return false; + + pnp_dev = to_pnp_dev(dev); + } + + res = pnp_get_resource(pnp_dev, IORESOURCE_IO, 0); + if (!res || resource_size(res) < GMUX_MIN_IO_LEN) + goto out; + + /* + * Invalid version information may indicate either that the gmux + * device isn't present or that it's a new one that uses indexed io. + */ + ver_major = inb(res->start + GMUX_PORT_VERSION_MAJOR); + ver_minor = inb(res->start + GMUX_PORT_VERSION_MINOR); + ver_release = inb(res->start + GMUX_PORT_VERSION_RELEASE); + if (ver_major == 0xff && ver_minor == 0xff && ver_release == 0xff) { + indexed = apple_gmux_is_indexed(res->start); + if (!indexed) + goto out; + } + + if (indexed_ret) + *indexed_ret = indexed; + + ret = true; +out: + put_device(dev); + return ret; +} + +/** + * apple_gmux_present() - check if gmux ACPI device is present * * Drivers may use this to activate quirks specific to dual GPU MacBook Pros * and Mac Pros, e.g. for deferred probing, runtime pm and backlight. * - * Return: %true if gmux is present and the kernel was configured + * Return: %true if gmux ACPI device is present and the kernel was configured * with CONFIG_APPLE_GMUX, %false otherwise. */ static inline bool apple_gmux_present(void) @@ -34,6 +134,11 @@ static inline bool apple_gmux_present(void) return false; } +static inline bool apple_gmux_detect(struct pnp_dev *pnp_dev, bool *indexed_ret) +{ + return false; +} + #endif /* !CONFIG_APPLE_GMUX */ #endif /* LINUX_APPLE_GMUX_H */ diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h index ef0a77173e3c..9b8a9c39614b 100644 --- a/include/linux/can/bittiming.h +++ b/include/linux/can/bittiming.h @@ -116,7 +116,7 @@ struct can_tdc_const { #ifdef CONFIG_CAN_CALC_BITTIMING int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, - const struct can_bittiming_const *btc); + const struct can_bittiming_const *btc, struct netlink_ext_ack *extack); void can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, const struct can_bittiming *dbt, @@ -124,7 +124,7 @@ void can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, #else /* !CONFIG_CAN_CALC_BITTIMING */ static inline int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, - const struct can_bittiming_const *btc) + const struct can_bittiming_const *btc, struct netlink_ext_ack *extack) { netdev_err(dev, "bit-timing calculation not available\n"); return -EINVAL; @@ -138,10 +138,16 @@ can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, } #endif /* CONFIG_CAN_CALC_BITTIMING */ +void can_sjw_set_default(struct can_bittiming *bt); + +int can_sjw_check(const struct net_device *dev, const struct can_bittiming *bt, + const struct can_bittiming_const *btc, struct netlink_ext_ack *extack); + int can_get_bittiming(const struct net_device *dev, struct can_bittiming *bt, const struct can_bittiming_const *btc, const u32 *bitrate_const, - const unsigned int bitrate_const_cnt); + const unsigned int bitrate_const_cnt, + struct netlink_ext_ack *extack); /* * can_bit_time() - Duration of one bit diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 00af2c98da75..4497d0a6772c 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -99,16 +99,6 @@ struct ceph_options { #define CEPH_AUTH_NAME_DEFAULT "guest" -/* mount state */ -enum { - CEPH_MOUNT_MOUNTING, - CEPH_MOUNT_MOUNTED, - CEPH_MOUNT_UNMOUNTING, - CEPH_MOUNT_UNMOUNTED, - CEPH_MOUNT_SHUTDOWN, - CEPH_MOUNT_RECOVER, -}; - static inline unsigned long ceph_timeout_jiffies(unsigned long timeout) { return timeout ?: MAX_SCHEDULE_TIMEOUT; diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index c2aa0aa26b45..7b16aede7ac5 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -391,6 +391,26 @@ unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1, nr_cpumask_bits, cpumask_check(cpu)); } +/** + * cpumask_nth_and_andnot - get the Nth cpu set in 1st and 2nd cpumask, and clear in 3rd. + * @srcp1: the cpumask pointer + * @srcp2: the cpumask pointer + * @srcp3: the cpumask pointer + * @cpu: the N'th cpu to find, starting from 0 + * + * Returns >= nr_cpu_ids if such cpu doesn't exist. + */ +static __always_inline +unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp1, + const struct cpumask *srcp2, + const struct cpumask *srcp3) +{ + return find_nth_and_andnot_bit(cpumask_bits(srcp1), + cpumask_bits(srcp2), + cpumask_bits(srcp3), + nr_cpumask_bits, cpumask_check(cpu)); +} + #define CPU_BITS_NONE \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ diff --git a/include/linux/efi.h b/include/linux/efi.h index 4b27519143f5..98598bd1d2fa 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -668,7 +668,8 @@ extern struct efi { #define EFI_RT_SUPPORTED_ALL 0x3fff -#define EFI_RT_SUPPORTED_TIME_SERVICES 0x000f +#define EFI_RT_SUPPORTED_TIME_SERVICES 0x0003 +#define EFI_RT_SUPPORTED_WAKEUP_SERVICES 0x000c #define EFI_RT_SUPPORTED_VARIABLE_SERVICES 0x0070 extern struct mm_struct efi_mm; diff --git a/include/linux/find.h b/include/linux/find.h index ccaf61a0f5fd..4647864a5ffd 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -22,6 +22,9 @@ unsigned long __find_nth_and_bit(const unsigned long *addr1, const unsigned long unsigned long size, unsigned long n); unsigned long __find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n); +unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, + const unsigned long *addr3, unsigned long size, + unsigned long n); extern unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); @@ -255,6 +258,36 @@ unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned lon return __find_nth_andnot_bit(addr1, addr2, size, n); } +/** + * find_nth_and_andnot_bit - find N'th set bit in 2 memory regions, + * excluding those set in 3rd region + * @addr1: The 1st address to start the search at + * @addr2: The 2nd address to start the search at + * @addr3: The 3rd address to start the search at + * @size: The maximum number of bits to search + * @n: The number of set bit, which position is needed, counting from 0 + * + * Returns the bit number of the N'th set bit. + * If no such, returns @size. + */ +static __always_inline +unsigned long find_nth_and_andnot_bit(const unsigned long *addr1, + const unsigned long *addr2, + const unsigned long *addr3, + unsigned long size, unsigned long n) +{ + if (n >= size) + return size; + + if (small_const_nbits(size)) { + unsigned long val = *addr1 & *addr2 & (~*addr3) & GENMASK(size - 1, 0); + + return val ? fns(val, n) : size; + } + + return __find_nth_and_andnot_bit(addr1, addr2, addr3, size, n); +} + #ifndef find_first_and_bit /** * find_first_and_bit - find the first set bit in both memory regions diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index 034b1106d022..e098f38422af 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -200,7 +200,7 @@ static inline void *kmap_local_pfn(unsigned long pfn) static inline void __kunmap_local(const void *addr) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP - kunmap_flush_on_unmap(addr); + kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE)); #endif } @@ -227,7 +227,7 @@ static inline void *kmap_atomic_pfn(unsigned long pfn) static inline void __kunmap_atomic(const void *addr) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP - kunmap_flush_on_unmap(addr); + kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE)); #endif pagefault_enable(); if (IS_ENABLED(CONFIG_PREEMPT_RT)) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 551834cd5299..db194e2ba69f 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -7,6 +7,7 @@ #include <linux/fs.h> #include <linux/hugetlb_inline.h> #include <linux/cgroup.h> +#include <linux/page_ref.h> #include <linux/list.h> #include <linux/kref.h> #include <linux/pgtable.h> @@ -1187,6 +1188,18 @@ static inline __init void hugetlb_cma_reserve(int order) } #endif +#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +static inline bool hugetlb_pmd_shared(pte_t *pte) +{ + return page_count(virt_to_page(pte)) > 1; +} +#else +static inline bool hugetlb_pmd_shared(pte_t *pte) +{ + return false; +} +#endif + bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr); #ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE diff --git a/include/linux/ip.h b/include/linux/ip.h index 3d9c6750af62..d11c25f5030a 100644 --- a/include/linux/ip.h +++ b/include/linux/ip.h @@ -35,4 +35,25 @@ static inline unsigned int ip_transport_len(const struct sk_buff *skb) { return ntohs(ip_hdr(skb)->tot_len) - skb_network_header_len(skb); } + +static inline unsigned int iph_totlen(const struct sk_buff *skb, const struct iphdr *iph) +{ + u32 len = ntohs(iph->tot_len); + + return (len || !skb_is_gso(skb) || !skb_is_gso_tcp(skb)) ? + len : skb->len - skb_network_offset(skb); +} + +static inline unsigned int skb_ip_totlen(const struct sk_buff *skb) +{ + return iph_totlen(skb, ip_hdr(skb)); +} + +/* IPv4 datagram length is stored into 16bit field (tot_len) */ +#define IP_MAX_MTU 0xFFFFU + +static inline void iph_set_totlen(struct iphdr *iph, unsigned int len) +{ + iph->tot_len = len <= IP_MAX_MTU ? htons(len) : 0; +} #endif /* _LINUX_IP_H */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d3c8203cab6c..85dc9b88ea37 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1666,10 +1666,13 @@ void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio, static inline void mem_cgroup_track_foreign_dirty(struct folio *folio, struct bdi_writeback *wb) { + struct mem_cgroup *memcg; + if (mem_cgroup_disabled()) return; - if (unlikely(&folio_memcg(folio)->css != wb->memcg_css)) + memcg = folio_memcg(folio); + if (unlikely(memcg && &memcg->css != wb->memcg_css)) mem_cgroup_track_foreign_dirty_slowpath(folio, wb); } diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 771e050883db..8bef1ab62bba 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -31,6 +31,7 @@ #define PHY_ID_KSZ9131 0x00221640 #define PHY_ID_LAN8814 0x00221660 #define PHY_ID_LAN8804 0x00221670 +#define PHY_ID_LAN8841 0x00221650 #define PHY_ID_KSZ886X 0x00221430 #define PHY_ID_KSZ8863 0x00221435 diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 29d4b201c7b2..71b06ebad402 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -362,11 +362,13 @@ enum mlx5_event { enum mlx5_driver_event { MLX5_DRIVER_EVENT_TYPE_TRAP = 0, + MLX5_DRIVER_EVENT_UPLINK_NETDEV, }; enum { MLX5_TRACER_SUBTYPE_OWNERSHIP_CHANGE = 0x0, MLX5_TRACER_SUBTYPE_TRACES_AVAILABLE = 0x1, + MLX5_TRACER_SUBTYPE_STRINGS_DB_UPDATE = 0x2, }; enum { @@ -1204,6 +1206,7 @@ enum mlx5_cap_type { MLX5_CAP_VDPA_EMULATION = 0x13, MLX5_CAP_DEV_EVENT = 0x14, MLX5_CAP_IPSEC, + MLX5_CAP_CRYPTO = 0x1a, MLX5_CAP_DEV_SHAMPO = 0x1d, MLX5_CAP_MACSEC = 0x1f, MLX5_CAP_GENERAL_2 = 0x20, @@ -1460,6 +1463,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_IPSEC(mdev, cap)\ MLX5_GET(ipsec_cap, (mdev)->caps.hca[MLX5_CAP_IPSEC]->cur, cap) +#define MLX5_CAP_CRYPTO(mdev, cap)\ + MLX5_GET(crypto_cap, (mdev)->caps.hca[MLX5_CAP_CRYPTO]->cur, cap) + #define MLX5_CAP_DEV_SHAMPO(mdev, cap)\ MLX5_GET(shampo_cap, mdev->caps.hca_cur[MLX5_CAP_DEV_SHAMPO], cap) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 44167760ff29..ecd3b5448fe9 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -49,6 +49,7 @@ #include <linux/notifier.h> #include <linux/refcount.h> #include <linux/auxiliary_bus.h> +#include <linux/mutex.h> #include <linux/mlx5/device.h> #include <linux/mlx5/doorbell.h> @@ -430,8 +431,6 @@ struct mlx5_core_health { u8 synd; u32 fatal_error; u32 crdump_size; - /* wq spinlock to synchronize draining */ - spinlock_t wq_lock; struct workqueue_struct *wq; unsigned long flags; struct work_struct fatal_report_work; @@ -516,6 +515,7 @@ struct mlx5_vhca_state_notifier; struct mlx5_sf_dev_table; struct mlx5_sf_hw_table; struct mlx5_sf_table; +struct mlx5_crypto_dek_priv; struct mlx5_rate_limit { u32 rate; @@ -572,6 +572,14 @@ struct mlx5_debugfs_entries { struct dentry *lag_debugfs; }; +enum mlx5_func_type { + MLX5_PF, + MLX5_VF, + MLX5_SF, + MLX5_HOST_PF, + MLX5_FUNC_TYPE_NUM, +}; + struct mlx5_ft_pool; struct mlx5_priv { /* IRQ table valid only for real pci devices PF or VF */ @@ -582,11 +590,10 @@ struct mlx5_priv { struct mlx5_nb pg_nb; struct workqueue_struct *pg_wq; struct xarray page_root_xa; - u32 fw_pages; atomic_t reg_pages; struct list_head free_list; - u32 vfs_pages; - u32 host_pf_pages; + u32 fw_pages; + u32 page_counters[MLX5_FUNC_TYPE_NUM]; u32 fw_pages_alloc_failed; u32 give_pages_dropped; u32 reclaim_pages_discard; @@ -673,6 +680,8 @@ struct mlx5e_resources { } hw_objs; struct devlink_port dl_port; struct net_device *uplink_netdev; + struct mutex uplink_netdev_lock; + struct mlx5_crypto_dek_priv *dek_priv; }; enum mlx5_sw_icm_type { @@ -1010,6 +1019,9 @@ int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); bool mlx5_cmd_is_down(struct mlx5_core_dev *dev); +void mlx5_core_uplink_netdev_set(struct mlx5_core_dev *mdev, struct net_device *netdev); +void mlx5_core_uplink_netdev_event_replay(struct mlx5_core_dev *mdev); + int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 0b102c651fe2..1e530a8a2cf5 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -306,6 +306,7 @@ enum { MLX5_CMD_OP_SYNC_STEERING = 0xb00, MLX5_CMD_OP_QUERY_VHCA_STATE = 0xb0d, MLX5_CMD_OP_MODIFY_VHCA_STATE = 0xb0e, + MLX5_CMD_OP_SYNC_CRYPTO = 0xb12, MLX5_CMD_OP_MAX }; @@ -1112,6 +1113,30 @@ struct mlx5_ifc_sync_steering_out_bits { u8 reserved_at_40[0x40]; }; +struct mlx5_ifc_sync_crypto_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x20]; + + u8 reserved_at_60[0x10]; + u8 crypto_type[0x10]; + + u8 reserved_at_80[0x80]; +}; + +struct mlx5_ifc_sync_crypto_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + struct mlx5_ifc_device_mem_cap_bits { u8 memic[0x1]; u8 reserved_at_1[0x1f]; @@ -1496,7 +1521,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 null_mkey[0x1]; u8 log_max_klm_list_size[0x6]; - u8 reserved_at_120[0xa]; + u8 reserved_at_120[0x2]; + u8 qpc_extension[0x1]; + u8 reserved_at_123[0x7]; u8 log_max_ra_req_dc[0x6]; u8 reserved_at_130[0x2]; u8 eth_wqe_too_small[0x1]; @@ -1662,7 +1689,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_bf_reg_size[0x5]; - u8 reserved_at_270[0x6]; + u8 reserved_at_270[0x3]; + u8 qp_error_syndrome[0x1]; + u8 reserved_at_274[0x2]; u8 lag_dct[0x2]; u8 lag_tx_port_affinity[0x1]; u8 lag_native_fdb_selection[0x1]; @@ -1768,7 +1797,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 ats[0x1]; u8 reserved_at_462[0x1]; u8 log_max_uctx[0x5]; - u8 reserved_at_468[0x2]; + u8 reserved_at_468[0x1]; + u8 crypto[0x1]; u8 ipsec_offload[0x1]; u8 log_max_umem[0x5]; u8 max_num_eqs[0x10]; @@ -3351,6 +3381,30 @@ struct mlx5_ifc_shampo_cap_bits { u8 reserved_at_40[0x7c0]; }; +struct mlx5_ifc_crypto_cap_bits { + u8 reserved_at_0[0x3]; + u8 synchronize_dek[0x1]; + u8 int_kek_manual[0x1]; + u8 int_kek_auto[0x1]; + u8 reserved_at_6[0x1a]; + + u8 reserved_at_20[0x3]; + u8 log_dek_max_alloc[0x5]; + u8 reserved_at_28[0x3]; + u8 log_max_num_deks[0x5]; + u8 reserved_at_30[0x10]; + + u8 reserved_at_40[0x20]; + + u8 reserved_at_60[0x3]; + u8 log_dek_granularity[0x5]; + u8 reserved_at_68[0x3]; + u8 log_max_num_int_kek[0x5]; + u8 sw_wrapped_dek[0x10]; + + u8 reserved_at_80[0x780]; +}; + union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_cmd_hca_cap_bits cmd_hca_cap; struct mlx5_ifc_cmd_hca_cap_2_bits cmd_hca_cap_2; @@ -3371,6 +3425,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_virtio_emulation_cap_bits virtio_emulation_cap; struct mlx5_ifc_shampo_cap_bits shampo_cap; struct mlx5_ifc_macsec_cap_bits macsec_cap; + struct mlx5_ifc_crypto_cap_bits crypto_cap; u8 reserved_at_0[0x8000]; }; @@ -5342,6 +5397,37 @@ struct mlx5_ifc_query_rmp_in_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_cqe_error_syndrome_bits { + u8 hw_error_syndrome[0x8]; + u8 hw_syndrome_type[0x4]; + u8 reserved_at_c[0x4]; + u8 vendor_error_syndrome[0x8]; + u8 syndrome[0x8]; +}; + +struct mlx5_ifc_qp_context_extension_bits { + u8 reserved_at_0[0x60]; + + struct mlx5_ifc_cqe_error_syndrome_bits error_syndrome; + + u8 reserved_at_80[0x580]; +}; + +struct mlx5_ifc_qpc_extension_and_pas_list_in_bits { + struct mlx5_ifc_qp_context_extension_bits qpc_data_extension; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_qp_pas_list_in_bits { + struct mlx5_ifc_cmd_pas_bits pas[0]; +}; + +union mlx5_ifc_qp_pas_or_qpc_ext_and_pas_bits { + struct mlx5_ifc_qp_pas_list_in_bits qp_pas_list; + struct mlx5_ifc_qpc_extension_and_pas_list_in_bits qpc_ext_and_pas_list; +}; + struct mlx5_ifc_query_qp_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -5358,7 +5444,7 @@ struct mlx5_ifc_query_qp_out_bits { u8 reserved_at_800[0x80]; - u8 pas[][0x40]; + union mlx5_ifc_qp_pas_or_qpc_ext_and_pas_bits qp_pas_or_qpc_ext_and_pas; }; struct mlx5_ifc_query_qp_in_bits { @@ -5368,7 +5454,8 @@ struct mlx5_ifc_query_qp_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x8]; + u8 qpc_ext[0x1]; + u8 reserved_at_41[0x7]; u8 qpn[0x18]; u8 reserved_at_60[0x20]; @@ -6196,6 +6283,18 @@ struct mlx5_ifc_match_definer_bits { }; }; +struct mlx5_ifc_general_obj_create_param_bits { + u8 alias_object[0x1]; + u8 reserved_at_1[0x2]; + u8 log_obj_range[0x5]; + u8 reserved_at_8[0x18]; +}; + +struct mlx5_ifc_general_obj_query_param_bits { + u8 alias_object[0x1]; + u8 obj_offset[0x1f]; +}; + struct mlx5_ifc_general_obj_in_cmd_hdr_bits { u8 opcode[0x10]; u8 uid[0x10]; @@ -6205,9 +6304,10 @@ struct mlx5_ifc_general_obj_in_cmd_hdr_bits { u8 obj_id[0x20]; - u8 reserved_at_60[0x3]; - u8 log_obj_range[0x5]; - u8 reserved_at_68[0x18]; + union { + struct mlx5_ifc_general_obj_create_param_bits create; + struct mlx5_ifc_general_obj_query_param_bits query; + } op_param; }; struct mlx5_ifc_general_obj_out_cmd_hdr_bits { @@ -8571,7 +8671,8 @@ struct mlx5_ifc_create_qp_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x8]; + u8 qpc_ext[0x1]; + u8 reserved_at_41[0x7]; u8 input_qpn[0x18]; u8 reserved_at_60[0x20]; @@ -9862,13 +9963,20 @@ struct mlx5_ifc_mpegc_reg_bits { }; enum { + MLX5_MTUTC_FREQ_ADJ_UNITS_PPB = 0x0, + MLX5_MTUTC_FREQ_ADJ_UNITS_SCALED_PPM = 0x1, +}; + +enum { MLX5_MTUTC_OPERATION_SET_TIME_IMMEDIATE = 0x1, MLX5_MTUTC_OPERATION_ADJUST_TIME = 0x2, MLX5_MTUTC_OPERATION_ADJUST_FREQ_UTC = 0x3, }; struct mlx5_ifc_mtutc_reg_bits { - u8 reserved_at_0[0x1c]; + u8 reserved_at_0[0x5]; + u8 freq_adj_units[0x3]; + u8 reserved_at_8[0x14]; u8 operation[0x4]; u8 freq_adjustment[0x20]; @@ -9941,7 +10049,8 @@ struct mlx5_ifc_pcam_reg_bits { }; struct mlx5_ifc_mcam_enhanced_features_bits { - u8 reserved_at_0[0x51]; + u8 reserved_at_0[0x50]; + u8 mtutc_freq_adj_units[0x1]; u8 mtutc_time_adjustment_extended_range[0x1]; u8 reserved_at_52[0xb]; u8 mcia_32dwords[0x1]; @@ -11702,6 +11811,7 @@ enum { MLX5_GENERAL_OBJECT_TYPES_SAMPLER = 0x20, MLX5_GENERAL_OBJECT_TYPES_FLOW_METER_ASO = 0x24, MLX5_GENERAL_OBJECT_TYPES_MACSEC = 0x27, + MLX5_GENERAL_OBJECT_TYPES_INT_KEK = 0x47, }; enum { @@ -11881,21 +11991,62 @@ struct mlx5_ifc_query_macsec_obj_out_bits { struct mlx5_ifc_macsec_offload_obj_bits macsec_object; }; +struct mlx5_ifc_wrapped_dek_bits { + u8 gcm_iv[0x60]; + + u8 reserved_at_60[0x20]; + + u8 const0[0x1]; + u8 key_size[0x1]; + u8 reserved_at_82[0x2]; + u8 key2_invalid[0x1]; + u8 reserved_at_85[0x3]; + u8 pd[0x18]; + + u8 key_purpose[0x5]; + u8 reserved_at_a5[0x13]; + u8 kek_id[0x8]; + + u8 reserved_at_c0[0x40]; + + u8 key1[0x8][0x20]; + + u8 key2[0x8][0x20]; + + u8 reserved_at_300[0x40]; + + u8 const1[0x1]; + u8 reserved_at_341[0x1f]; + + u8 reserved_at_360[0x20]; + + u8 auth_tag[0x80]; +}; + struct mlx5_ifc_encryption_key_obj_bits { u8 modify_field_select[0x40]; - u8 reserved_at_40[0x14]; + u8 state[0x8]; + u8 sw_wrapped[0x1]; + u8 reserved_at_49[0xb]; u8 key_size[0x4]; u8 reserved_at_58[0x4]; - u8 key_type[0x4]; + u8 key_purpose[0x4]; u8 reserved_at_60[0x8]; u8 pd[0x18]; - u8 reserved_at_80[0x180]; - u8 key[8][0x20]; + u8 reserved_at_80[0x100]; + + u8 opaque[0x40]; + + u8 reserved_at_1c0[0x40]; + + u8 key[8][0x80]; + + u8 sw_wrapped_dek[8][0x80]; - u8 reserved_at_300[0x500]; + u8 reserved_at_a00[0x600]; }; struct mlx5_ifc_create_encryption_key_in_bits { @@ -11903,6 +12054,11 @@ struct mlx5_ifc_create_encryption_key_in_bits { struct mlx5_ifc_encryption_key_obj_bits encryption_key_object; }; +struct mlx5_ifc_modify_encryption_key_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; + struct mlx5_ifc_encryption_key_obj_bits encryption_key_object; +}; + enum { MLX5_FLOW_METER_MODE_BYTES_IP_LENGTH = 0x0, MLX5_FLOW_METER_MODE_BYTES_CALC_WITH_L2 = 0x1, @@ -11958,6 +12114,34 @@ struct mlx5_ifc_create_flow_meter_aso_obj_in_bits { struct mlx5_ifc_flow_meter_aso_obj_bits flow_meter_aso_obj; }; +struct mlx5_ifc_int_kek_obj_bits { + u8 modify_field_select[0x40]; + + u8 state[0x8]; + u8 auto_gen[0x1]; + u8 reserved_at_49[0xb]; + u8 key_size[0x4]; + u8 reserved_at_58[0x8]; + + u8 reserved_at_60[0x8]; + u8 pd[0x18]; + + u8 reserved_at_80[0x180]; + u8 key[8][0x80]; + + u8 reserved_at_600[0x200]; +}; + +struct mlx5_ifc_create_int_kek_obj_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; + struct mlx5_ifc_int_kek_obj_bits int_kek_object; +}; + +struct mlx5_ifc_create_int_kek_obj_out_bits { + struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; + struct mlx5_ifc_int_kek_obj_bits int_kek_object; +}; + struct mlx5_ifc_sampler_obj_bits { u8 modify_field_select[0x40]; @@ -11996,9 +12180,9 @@ enum { }; enum { - MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_TYPE_TLS = 0x1, - MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_TYPE_IPSEC = 0x2, - MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_TYPE_MACSEC = 0x4, + MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_PURPOSE_TLS = 0x1, + MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_PURPOSE_IPSEC = 0x2, + MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_PURPOSE_MACSEC = 0x4, }; struct mlx5_ifc_tls_static_params_bits { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9bb11da36ef0..d9cdbc047b49 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -224,6 +224,7 @@ struct net_device_core_stats { #include <linux/static_key.h> extern struct static_key_false rps_needed; extern struct static_key_false rfs_needed; +extern struct cpumask rps_default_mask; #endif struct neighbour; @@ -1966,6 +1967,8 @@ enum netdev_ml_priv_type { * @gso_max_segs: Maximum number of segments that can be passed to the * NIC for GSO * @tso_max_segs: Device (as in HW) limit on the max TSO segment count + * @gso_ipv4_max_size: Maximum size of generic segmentation offload, + * for IPv4. * * @dcbnl_ops: Data Center Bridging netlink ops * @num_tc: Number of traffic classes in the net device @@ -2006,6 +2009,8 @@ enum netdev_ml_priv_type { * keep a list of interfaces to be deleted. * @gro_max_size: Maximum size of aggregated packet in generic * receive offload (GRO) + * @gro_ipv4_max_size: Maximum size of aggregated packet in generic + * receive offload (GRO), for IPv4. * * @dev_addr_shadow: Copy of @dev_addr to catch direct writes. * @linkwatch_dev_tracker: refcount tracker used by linkwatch. @@ -2210,6 +2215,7 @@ struct net_device { */ #define GRO_MAX_SIZE (8 * 65535u) unsigned int gro_max_size; + unsigned int gro_ipv4_max_size; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; @@ -2333,6 +2339,7 @@ struct net_device { u16 gso_max_segs; #define TSO_MAX_SEGS U16_MAX u16 tso_max_segs; + unsigned int gso_ipv4_max_size; #ifdef CONFIG_DCB const struct dcbnl_rtnl_ops *dcbnl_ops; diff --git a/include/linux/netlink.h b/include/linux/netlink.h index fa4d86da0ec7..c43ac7690eca 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -130,6 +130,16 @@ struct netlink_ext_ack { #define NL_SET_ERR_MSG_FMT_MOD(extack, fmt, args...) \ NL_SET_ERR_MSG_FMT((extack), KBUILD_MODNAME ": " fmt, ##args) +#define NL_SET_ERR_MSG_WEAK(extack, msg) do { \ + if ((extack) && !(extack)->_msg) \ + NL_SET_ERR_MSG((extack), msg); \ +} while (0) + +#define NL_SET_ERR_MSG_WEAK_MOD(extack, msg) do { \ + if ((extack) && !(extack)->_msg) \ + NL_SET_ERR_MSG_MOD((extack), msg); \ +} while (0) + #define NL_SET_BAD_ATTR_POLICY(extack, attr, pol) do { \ if ((extack)) { \ (extack)->bad_attr = (attr); \ diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 50caa117cb62..bb15c9234e21 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -70,7 +70,6 @@ struct nvmem_keepout { * @word_size: Minimum read/write access granularity. * @stride: Minimum read/write access stride. * @priv: User context passed to read/write callbacks. - * @wp-gpio: Write protect pin * @ignore_wp: Write Protect pin is managed by the provider. * * Note: A default "nvmem<id>" name will be assigned to the device if @@ -85,7 +84,6 @@ struct nvmem_config { const char *name; int id; struct module *owner; - struct gpio_desc *wp_gpio; const struct nvmem_cell_info *cells; int ncells; const struct nvmem_keepout *keepout; diff --git a/include/linux/poison.h b/include/linux/poison.h index 2d3249eb0e62..2823f90fdab4 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -81,6 +81,9 @@ /********** net/core/page_pool.c **********/ #define PP_SIGNATURE (0x40 + POISON_POINTER_DELTA) +/********** net/core/skbuff.c **********/ +#define SKB_LIST_POISON_NEXT ((void *)(0x800 + POISON_POINTER_DELTA)) + /********** kernel/bpf/ **********/ #define BPF_PTR_POISON ((void *)(0xeB9FUL + POISON_POINTER_DELTA)) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5ba12185f43e..47ab28a37f2f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -255,6 +255,14 @@ #define SKB_DATA_ALIGN(X) ALIGN(X, SMP_CACHE_BYTES) #define SKB_WITH_OVERHEAD(X) \ ((X) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) + +/* For X bytes available in skb->head, what is the minimal + * allocation needed, knowing struct skb_shared_info needs + * to be aligned. + */ +#define SKB_HEAD_ALIGN(X) (SKB_DATA_ALIGN(X) + \ + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) + #define SKB_MAX_ORDER(X, ORDER) \ SKB_WITH_OVERHEAD((PAGE_SIZE << (ORDER)) - (X)) #define SKB_MAX_HEAD(X) (SKB_MAX_ORDER((X), 0)) @@ -1235,7 +1243,7 @@ static inline void consume_skb(struct sk_buff *skb) void __consume_stateless_skb(struct sk_buff *skb); void __kfree_skb(struct sk_buff *skb); -extern struct kmem_cache *skbuff_head_cache; +extern struct kmem_cache *skbuff_cache; void kfree_skb_partial(struct sk_buff *skb, bool head_stolen); bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, @@ -1738,6 +1746,13 @@ static inline void skb_mark_not_on_list(struct sk_buff *skb) skb->next = NULL; } +static inline void skb_poison_list(struct sk_buff *skb) +{ +#ifdef CONFIG_DEBUG_NET + skb->next = SKB_LIST_POISON_NEXT; +#endif +} + /* Iterate through singly-linked GSO fragments of an skb. */ #define skb_list_walk_safe(first, skb, next_skb) \ for ((skb) = (first), (next_skb) = (skb) ? (skb)->next : NULL; (skb); \ diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 1341f7d62da4..be48f1cb1878 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -476,6 +476,15 @@ extern int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, #define atomic_dec_and_lock_irqsave(atomic, lock, flags) \ __cond_lock(lock, _atomic_dec_and_lock_irqsave(atomic, lock, &(flags))) +extern int _atomic_dec_and_raw_lock(atomic_t *atomic, raw_spinlock_t *lock); +#define atomic_dec_and_raw_lock(atomic, lock) \ + __cond_lock(lock, _atomic_dec_and_raw_lock(atomic, lock)) + +extern int _atomic_dec_and_raw_lock_irqsave(atomic_t *atomic, raw_spinlock_t *lock, + unsigned long *flags); +#define atomic_dec_and_raw_lock_irqsave(atomic, lock, flags) \ + __cond_lock(lock, _atomic_dec_and_raw_lock_irqsave(atomic, lock, &(flags))) + int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask, size_t max_size, unsigned int cpu_mult, gfp_t gfp, const char *name, diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 83ca2e8eb6b5..a152678b82b7 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -252,6 +252,7 @@ struct plat_stmmacenet_data { int rss_en; int mac_port_sel_speed; bool en_tx_lpi_clockgating; + bool rx_clk_runs_in_lpi; int has_xgmac; bool vlan_fail_q_en; u8 vlan_fail_q; diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index 8530c7328269..fae6beaaa217 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -11,6 +11,11 @@ struct device; struct file; struct task_struct; +static inline bool string_is_terminated(const char *s, int len) +{ + return memchr(s, '\0', len) ? true : false; +} + /* Descriptions of the types of units to * print in */ enum string_size_units { diff --git a/include/linux/swap.h b/include/linux/swap.h index 2787b84eaf12..0ceed49516ad 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -418,8 +418,7 @@ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, - unsigned int reclaim_options, - nodemask_t *nodemask); + unsigned int reclaim_options); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, diff --git a/include/linux/topology.h b/include/linux/topology.h index 4564faafd0e1..fea32377f7c7 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -245,5 +245,38 @@ static inline const struct cpumask *cpu_cpu_mask(int cpu) return cpumask_of_node(cpu_to_node(cpu)); } +#ifdef CONFIG_NUMA +int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node); +extern const struct cpumask *sched_numa_hop_mask(unsigned int node, unsigned int hops); +#else +static __always_inline int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node) +{ + return cpumask_nth(cpu, cpus); +} + +static inline const struct cpumask * +sched_numa_hop_mask(unsigned int node, unsigned int hops) +{ + return ERR_PTR(-EOPNOTSUPP); +} +#endif /* CONFIG_NUMA */ + +/** + * for_each_numa_hop_mask - iterate over cpumasks of increasing NUMA distance + * from a given node. + * @mask: the iteration variable. + * @node: the NUMA node to start the search from. + * + * Requires rcu_lock to be held. + * + * Yields cpu_online_mask for @node == NUMA_NO_NODE. + */ +#define for_each_numa_hop_mask(mask, node) \ + for (unsigned int __hops = 0; \ + mask = (node != NUMA_NO_NODE || __hops) ? \ + sched_numa_hop_mask(node, __hops) : \ + cpu_online_mask, \ + !IS_ERR_OR_NULL(mask); \ + __hops++) #endif /* _LINUX_TOPOLOGY_H */ diff --git a/include/linux/util_macros.h b/include/linux/util_macros.h index 72299f261b25..43db6e47503c 100644 --- a/include/linux/util_macros.h +++ b/include/linux/util_macros.h @@ -38,4 +38,16 @@ */ #define find_closest_descending(x, a, as) __find_closest(x, a, as, >=) +/** + * is_insidevar - check if the @ptr points inside the @var memory range. + * @ptr: the pointer to a memory address. + * @var: the variable which address and size identify the memory range. + * + * Evaluates to true if the address in @ptr lies within the memory + * range allocated to @var. + */ +#define is_insidevar(ptr, var) \ + ((uintptr_t)(ptr) >= (uintptr_t)(var) && \ + (uintptr_t)(ptr) < (uintptr_t)(var) + sizeof(var)) + #endif diff --git a/include/net/devlink.h b/include/net/devlink.h index ab654cf552b8..2e85a5970a32 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1645,7 +1645,7 @@ static inline struct devlink *devlink_alloc(const struct devlink_ops *ops, { return devlink_alloc_ns(ops, priv_size, &init_net, dev); } -void devlink_set_features(struct devlink *devlink, u64 features); + int devl_register(struct devlink *devlink); void devl_unregister(struct devlink *devlink); void devlink_register(struct devlink *devlink); diff --git a/include/net/dropreason.h b/include/net/dropreason.h index 70539288f995..94bc3d5d8803 100644 --- a/include/net/dropreason.h +++ b/include/net/dropreason.h @@ -71,6 +71,7 @@ FN(DUP_FRAG) \ FN(FRAG_REASM_TIMEOUT) \ FN(FRAG_TOO_FAR) \ + FN(TCP_MINTTL) \ FNe(MAX) /** @@ -313,6 +314,11 @@ enum skb_drop_reason { */ SKB_DROP_REASON_FRAG_TOO_FAR, /** + * @SKB_DROP_REASON_TCP_MINTTL: ipv4 ttl or ipv6 hoplimit below + * the threshold (IP_MINTTL or IPV6_MINHOPCOUNT). + */ + SKB_DROP_REASON_TCP_MINTTL, + /** * @SKB_DROP_REASON_MAX: the maximum of drop reason, which shouldn't be * used as a real 'reason' */ diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 6a2019aaa464..7bbab8f2b73d 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -362,6 +362,10 @@ static inline struct nf_conntrack_net *nf_ct_pernet(const struct net *net) return net_generic(net, nf_conntrack_net_id); } +int nf_ct_skb_network_trim(struct sk_buff *skb, int family); +int nf_ct_handle_fragments(struct net *net, struct sk_buff *skb, + u16 zone, u8 family, u8 *proto, u16 *mru); + #define NF_CT_STAT_INC(net, count) __this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_ADD_ATOMIC(net, count, v) this_cpu_add((net)->ct.stat->count, (v)) diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index cd982f4a0f50..ebb28ec5b6fa 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -57,7 +57,7 @@ struct nf_flowtable_type { struct net_device *dev, enum flow_block_command cmd); int (*action)(struct net *net, - const struct flow_offload *flow, + struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule); void (*free)(struct nf_flowtable *ft); @@ -164,6 +164,8 @@ enum nf_flow_flags { NF_FLOW_HW_DYING, NF_FLOW_HW_DEAD, NF_FLOW_HW_PENDING, + NF_FLOW_HW_BIDIRECTIONAL, + NF_FLOW_HW_ESTABLISHED, }; enum flow_offload_type { @@ -312,10 +314,10 @@ void nf_flow_table_offload_flush_cleanup(struct nf_flowtable *flowtable); int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, struct net_device *dev, enum flow_block_command cmd); -int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow, +int nf_flow_rule_route_ipv4(struct net *net, struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule); -int nf_flow_rule_route_ipv6(struct net *net, const struct flow_offload *flow, +int nf_flow_rule_route_ipv6(struct net *net, struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule); diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index 112708f7a6b4..947973623dc7 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -29,7 +29,7 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) if (iph->ihl < 5 || iph->version != 4) return -1; - len = ntohs(iph->tot_len); + len = iph_totlen(pkt->skb, iph); thoff = iph->ihl * 4; if (pkt->skb->len < len) return -1; @@ -64,7 +64,7 @@ static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt) if (iph->ihl < 5 || iph->version != 4) goto inhdr_error; - len = ntohs(iph->tot_len); + len = iph_totlen(pkt->skb, iph); thoff = iph->ihl * 4; if (pkt->skb->len < len) { __IP_INC_STATS(nft_net(pkt), IPSTATS_MIB_INTRUNCATEDPKTS); diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 813c93499f20..34bf531ffc8d 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -386,7 +386,7 @@ static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid) static inline void page_pool_ring_lock(struct page_pool *pool) __acquires(&pool->ring.producer_lock) { - if (in_serving_softirq()) + if (in_softirq()) spin_lock(&pool->ring.producer_lock); else spin_lock_bh(&pool->ring.producer_lock); @@ -395,7 +395,7 @@ static inline void page_pool_ring_lock(struct page_pool *pool) static inline void page_pool_ring_unlock(struct page_pool *pool) __releases(&pool->ring.producer_lock) { - if (in_serving_softirq()) + if (in_softirq()) spin_unlock(&pool->ring.producer_lock); else spin_unlock_bh(&pool->ring.producer_lock); diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 4cabb32a2ad9..cd410a87517b 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -788,16 +788,6 @@ struct tc_cls_bpf_offload { bool exts_integrated; }; -struct tc_mqprio_qopt_offload { - /* struct tc_mqprio_qopt must always be the first element */ - struct tc_mqprio_qopt qopt; - u16 mode; - u16 shaper; - u32 flags; - u64 min_rate[TC_QOPT_MAX_QUEUE]; - u64 max_rate[TC_QOPT_MAX_QUEUE]; -}; - /* This structure holds cookie structure that is passed from user * to the kernel for actions and classifiers */ diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 38207873eda6..2016839991a4 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -160,8 +160,28 @@ struct tc_etf_qopt_offload { s32 queue; }; +struct tc_mqprio_caps { + bool validate_queue_counts:1; +}; + +struct tc_mqprio_qopt_offload { + /* struct tc_mqprio_qopt must always be the first element */ + struct tc_mqprio_qopt qopt; + u16 mode; + u16 shaper; + u32 flags; + u64 min_rate[TC_QOPT_MAX_QUEUE]; + u64 max_rate[TC_QOPT_MAX_QUEUE]; +}; + struct tc_taprio_caps { bool supports_queue_max_sdu:1; + bool gate_mask_per_txq:1; + /* Device expects lower TXQ numbers to have higher priority over higher + * TXQs, regardless of their TC mapping. DO NOT USE FOR NEW DRIVERS, + * INSTEAD ENFORCE A PROPER TC:TXQ MAPPING COMING FROM USER SPACE. + */ + bool broken_mqprio:1; }; struct tc_taprio_sched_entry { @@ -173,6 +193,7 @@ struct tc_taprio_sched_entry { }; struct tc_taprio_qopt_offload { + struct tc_mqprio_qopt_offload mqprio; u8 enable; ktime_t base_time; u64 cycle_time; diff --git a/include/net/raw.h b/include/net/raw.h index 5e665934ebc7..2c004c20ed99 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -15,6 +15,8 @@ #include <net/inet_sock.h> #include <net/protocol.h> +#include <net/netns/hash.h> +#include <linux/hash.h> #include <linux/icmp.h> extern struct proto raw_prot; @@ -29,13 +31,20 @@ int raw_local_deliver(struct sk_buff *, int); int raw_rcv(struct sock *, struct sk_buff *); -#define RAW_HTABLE_SIZE MAX_INET_PROTOS +#define RAW_HTABLE_LOG 8 +#define RAW_HTABLE_SIZE (1U << RAW_HTABLE_LOG) struct raw_hashinfo { spinlock_t lock; - struct hlist_nulls_head ht[RAW_HTABLE_SIZE]; + + struct hlist_nulls_head ht[RAW_HTABLE_SIZE] ____cacheline_aligned; }; +static inline u32 raw_hashfunc(const struct net *net, u32 proto) +{ + return hash_32(net_hash_mix(net) ^ proto, RAW_HTABLE_LOG); +} + static inline void raw_hashinfo_init(struct raw_hashinfo *hashinfo) { int i; diff --git a/include/net/route.h b/include/net/route.h index 6e92dd5bcd61..fe00b0a2e475 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -35,9 +35,6 @@ #include <linux/cache.h> #include <linux/security.h> -/* IPv4 datagram length is stored into 16bit field (tot_len) */ -#define IP_MAX_MTU 0xFFFFU - #define RTO_ONLINK 0x01 #define RT_CONN_FLAGS(sk) (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE)) diff --git a/include/net/sock.h b/include/net/sock.h index dcd72e6285b2..937e842dc930 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1956,7 +1956,12 @@ void sk_common_release(struct sock *sk); * Default socket callbacks and setup code */ -/* Initialise core socket variables */ +/* Initialise core socket variables using an explicit uid. */ +void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid); + +/* Initialise core socket variables. + * Assumes struct socket *sock is embedded in a struct socket_alloc. + */ void sock_init_data(struct socket *sock, struct sock *sk); /* diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h index 3e02709a1df6..83fe39931781 100644 --- a/include/net/tc_act/tc_pedit.h +++ b/include/net/tc_act/tc_pedit.h @@ -4,22 +4,29 @@ #include <net/act_api.h> #include <linux/tc_act/tc_pedit.h> +#include <linux/types.h> struct tcf_pedit_key_ex { enum pedit_header_type htype; enum pedit_cmd cmd; }; -struct tcf_pedit { - struct tc_action common; - unsigned char tcfp_nkeys; - unsigned char tcfp_flags; - u32 tcfp_off_max_hint; +struct tcf_pedit_parms { struct tc_pedit_key *tcfp_keys; struct tcf_pedit_key_ex *tcfp_keys_ex; + u32 tcfp_off_max_hint; + unsigned char tcfp_nkeys; + unsigned char tcfp_flags; + struct rcu_head rcu; +}; + +struct tcf_pedit { + struct tc_action common; + struct tcf_pedit_parms __rcu *parms; }; #define to_pedit(a) ((struct tcf_pedit *)a) +#define to_pedit_parms(a) (rcu_dereference(to_pedit(a)->parms)) static inline bool is_tcf_pedit(const struct tc_action *a) { @@ -32,37 +39,81 @@ static inline bool is_tcf_pedit(const struct tc_action *a) static inline int tcf_pedit_nkeys(const struct tc_action *a) { - return to_pedit(a)->tcfp_nkeys; + struct tcf_pedit_parms *parms; + int nkeys; + + rcu_read_lock(); + parms = to_pedit_parms(a); + nkeys = parms->tcfp_nkeys; + rcu_read_unlock(); + + return nkeys; } static inline u32 tcf_pedit_htype(const struct tc_action *a, int index) { - if (to_pedit(a)->tcfp_keys_ex) - return to_pedit(a)->tcfp_keys_ex[index].htype; + u32 htype = TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK; + struct tcf_pedit_parms *parms; + + rcu_read_lock(); + parms = to_pedit_parms(a); + if (parms->tcfp_keys_ex) + htype = parms->tcfp_keys_ex[index].htype; + rcu_read_unlock(); - return TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK; + return htype; } static inline u32 tcf_pedit_cmd(const struct tc_action *a, int index) { - if (to_pedit(a)->tcfp_keys_ex) - return to_pedit(a)->tcfp_keys_ex[index].cmd; + struct tcf_pedit_parms *parms; + u32 cmd = __PEDIT_CMD_MAX; - return __PEDIT_CMD_MAX; + rcu_read_lock(); + parms = to_pedit_parms(a); + if (parms->tcfp_keys_ex) + cmd = parms->tcfp_keys_ex[index].cmd; + rcu_read_unlock(); + + return cmd; } static inline u32 tcf_pedit_mask(const struct tc_action *a, int index) { - return to_pedit(a)->tcfp_keys[index].mask; + struct tcf_pedit_parms *parms; + u32 mask; + + rcu_read_lock(); + parms = to_pedit_parms(a); + mask = parms->tcfp_keys[index].mask; + rcu_read_unlock(); + + return mask; } static inline u32 tcf_pedit_val(const struct tc_action *a, int index) { - return to_pedit(a)->tcfp_keys[index].val; + struct tcf_pedit_parms *parms; + u32 val; + + rcu_read_lock(); + parms = to_pedit_parms(a); + val = parms->tcfp_keys[index].val; + rcu_read_unlock(); + + return val; } static inline u32 tcf_pedit_offset(const struct tc_action *a, int index) { - return to_pedit(a)->tcfp_keys[index].off; + struct tcf_pedit_parms *parms; + u32 off; + + rcu_read_lock(); + parms = to_pedit_parms(a); + off = parms->tcfp_keys[index].off; + rcu_read_unlock(); + + return off; } #endif /* __NET_TC_PED_H */ diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index afb11680a793..2080879e4134 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -967,6 +967,7 @@ void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb, int ocelot_regfields_init(struct ocelot *ocelot, const struct reg_field *const regfields); struct regmap *ocelot_regmap_init(struct ocelot *ocelot, struct resource *res); +int ocelot_reset(struct ocelot *ocelot); int ocelot_init(struct ocelot *ocelot); void ocelot_deinit(struct ocelot *ocelot); void ocelot_init_port(struct ocelot *ocelot, int port); @@ -978,6 +979,11 @@ void ocelot_port_assign_dsa_8021q_cpu(struct ocelot *ocelot, int port, int cpu); void ocelot_port_unassign_dsa_8021q_cpu(struct ocelot *ocelot, int port); u32 ocelot_port_assigned_dsa_8021q_cpu_mask(struct ocelot *ocelot, int port); +/* Watermark interface */ +u16 ocelot_wm_enc(u16 value); +u16 ocelot_wm_dec(u16 wm); +void ocelot_wm_stat(u32 val, u32 *inuse, u32 *maxuse); + /* DSA callbacks */ void ocelot_get_strings(struct ocelot *ocelot, int port, u32 sset, u8 *data); void ocelot_get_ethtool_stats(struct ocelot *ocelot, int port, u64 *data); diff --git a/include/soc/mscc/vsc7514_regs.h b/include/soc/mscc/vsc7514_regs.h index ceee26c96959..ffe343a9c04b 100644 --- a/include/soc/mscc/vsc7514_regs.h +++ b/include/soc/mscc/vsc7514_regs.h @@ -10,20 +10,10 @@ #include <soc/mscc/ocelot_vcap.h> -extern const u32 vsc7514_ana_regmap[]; -extern const u32 vsc7514_qs_regmap[]; -extern const u32 vsc7514_qsys_regmap[]; -extern const u32 vsc7514_rew_regmap[]; -extern const u32 vsc7514_sys_regmap[]; -extern const u32 vsc7514_vcap_regmap[]; -extern const u32 vsc7514_ptp_regmap[]; -extern const u32 vsc7514_dev_gmii_regmap[]; +extern struct vcap_props vsc7514_vcap_props[]; -extern const struct vcap_field vsc7514_vcap_es0_keys[]; -extern const struct vcap_field vsc7514_vcap_es0_actions[]; -extern const struct vcap_field vsc7514_vcap_is1_keys[]; -extern const struct vcap_field vsc7514_vcap_is1_actions[]; -extern const struct vcap_field vsc7514_vcap_is2_keys[]; -extern const struct vcap_field vsc7514_vcap_is2_actions[]; +extern const struct reg_field vsc7514_regfields[REGFIELD_MAX]; + +extern const u32 *vsc7514_regmap[TARGET_MAX]; #endif diff --git a/include/trace/events/bridge.h b/include/trace/events/bridge.h index 6b200059c2c5..a6b3a4e409f0 100644 --- a/include/trace/events/bridge.h +++ b/include/trace/events/bridge.h @@ -122,6 +122,64 @@ TRACE_EVENT(br_fdb_update, __entry->flags) ); +TRACE_EVENT(br_mdb_full, + + TP_PROTO(const struct net_device *dev, + const struct br_ip *group), + + TP_ARGS(dev, group), + + TP_STRUCT__entry( + __string(dev, dev->name) + __field(int, af) + __field(u16, vid) + __array(__u8, src, 16) + __array(__u8, grp, 16) + __array(__u8, grpmac, ETH_ALEN) /* For af == 0. */ + ), + + TP_fast_assign( + struct in6_addr *in6; + + __assign_str(dev, dev->name); + __entry->vid = group->vid; + + if (!group->proto) { + __entry->af = 0; + + memset(__entry->src, 0, sizeof(__entry->src)); + memset(__entry->grp, 0, sizeof(__entry->grp)); + memcpy(__entry->grpmac, group->dst.mac_addr, ETH_ALEN); + } else if (group->proto == htons(ETH_P_IP)) { + __entry->af = AF_INET; + + in6 = (struct in6_addr *)__entry->src; + ipv6_addr_set_v4mapped(group->src.ip4, in6); + + in6 = (struct in6_addr *)__entry->grp; + ipv6_addr_set_v4mapped(group->dst.ip4, in6); + + memset(__entry->grpmac, 0, ETH_ALEN); + +#if IS_ENABLED(CONFIG_IPV6) + } else { + __entry->af = AF_INET6; + + in6 = (struct in6_addr *)__entry->src; + *in6 = group->src.ip6; + + in6 = (struct in6_addr *)__entry->grp; + *in6 = group->dst.ip6; + + memset(__entry->grpmac, 0, ETH_ALEN); +#endif + } + ), + + TP_printk("dev %s af %u src %pI6c grp %pI6c/%pM vid %u", + __get_str(dev), __entry->af, __entry->src, __entry->grp, + __entry->grpmac, __entry->vid) +); #endif /* _TRACE_BRIDGE_H */ diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 283db0ea3db4..c3c0b0aa8381 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -163,7 +163,7 @@ EM(rxrpc_local_put_for_use, "PUT for-use ") \ EM(rxrpc_local_put_kill_conn, "PUT conn-kil") \ EM(rxrpc_local_put_peer, "PUT peer ") \ - EM(rxrpc_local_put_prealloc_conn, "PUT conn-pre") \ + EM(rxrpc_local_put_prealloc_peer, "PUT peer-pre") \ EM(rxrpc_local_put_release_sock, "PUT rel-sock") \ EM(rxrpc_local_stop, "STOP ") \ EM(rxrpc_local_stopped, "STOPPED ") \ @@ -360,11 +360,12 @@ EM(rxrpc_propose_ack_client_tx_end, "ClTxEnd") \ EM(rxrpc_propose_ack_input_data, "DataIn ") \ EM(rxrpc_propose_ack_input_data_hole, "DataInH") \ - EM(rxrpc_propose_ack_ping_for_check_life, "ChkLife") \ EM(rxrpc_propose_ack_ping_for_keepalive, "KeepAlv") \ EM(rxrpc_propose_ack_ping_for_lost_ack, "LostAck") \ EM(rxrpc_propose_ack_ping_for_lost_reply, "LostRpl") \ + EM(rxrpc_propose_ack_ping_for_old_rtt, "OldRtt ") \ EM(rxrpc_propose_ack_ping_for_params, "Params ") \ + EM(rxrpc_propose_ack_ping_for_rtt, "Rtt ") \ EM(rxrpc_propose_ack_processing_op, "ProcOp ") \ EM(rxrpc_propose_ack_respond_to_ack, "Rsp2Ack") \ EM(rxrpc_propose_ack_respond_to_ping, "Rsp2Png") \ @@ -421,6 +422,13 @@ EM(RXRPC_ACK_IDLE, "IDL") \ E_(RXRPC_ACK__INVALID, "-?-") +#define rxrpc_sack_traces \ + EM(rxrpc_sack_advance, "ADV") \ + EM(rxrpc_sack_fill, "FIL") \ + EM(rxrpc_sack_nack, "NAK") \ + EM(rxrpc_sack_none, "---") \ + E_(rxrpc_sack_oos, "OOS") + #define rxrpc_completions \ EM(RXRPC_CALL_SUCCEEDED, "Succeeded") \ EM(RXRPC_CALL_REMOTELY_ABORTED, "RemoteAbort") \ @@ -496,6 +504,7 @@ enum rxrpc_recvmsg_trace { rxrpc_recvmsg_traces } __mode(byte); enum rxrpc_req_ack_trace { rxrpc_req_ack_traces } __mode(byte); enum rxrpc_rtt_rx_trace { rxrpc_rtt_rx_traces } __mode(byte); enum rxrpc_rtt_tx_trace { rxrpc_rtt_tx_traces } __mode(byte); +enum rxrpc_sack_trace { rxrpc_sack_traces } __mode(byte); enum rxrpc_skb_trace { rxrpc_skb_traces } __mode(byte); enum rxrpc_timer_trace { rxrpc_timer_traces } __mode(byte); enum rxrpc_tx_point { rxrpc_tx_points } __mode(byte); @@ -530,6 +539,7 @@ rxrpc_recvmsg_traces; rxrpc_req_ack_traces; rxrpc_rtt_rx_traces; rxrpc_rtt_tx_traces; +rxrpc_sack_traces; rxrpc_skb_traces; rxrpc_timer_traces; rxrpc_tx_points; @@ -552,10 +562,10 @@ TRACE_EVENT(rxrpc_local, TP_ARGS(local_debug_id, op, ref, usage), TP_STRUCT__entry( - __field(unsigned int, local ) - __field(int, op ) - __field(int, ref ) - __field(int, usage ) + __field(unsigned int, local) + __field(int, op) + __field(int, ref) + __field(int, usage) ), TP_fast_assign( @@ -578,9 +588,9 @@ TRACE_EVENT(rxrpc_peer, TP_ARGS(peer_debug_id, ref, why), TP_STRUCT__entry( - __field(unsigned int, peer ) - __field(int, ref ) - __field(enum rxrpc_peer_trace, why ) + __field(unsigned int, peer) + __field(int, ref) + __field(enum rxrpc_peer_trace, why) ), TP_fast_assign( @@ -601,9 +611,9 @@ TRACE_EVENT(rxrpc_bundle, TP_ARGS(bundle_debug_id, ref, why), TP_STRUCT__entry( - __field(unsigned int, bundle ) - __field(int, ref ) - __field(int, why ) + __field(unsigned int, bundle) + __field(int, ref) + __field(int, why) ), TP_fast_assign( @@ -624,9 +634,9 @@ TRACE_EVENT(rxrpc_conn, TP_ARGS(conn_debug_id, ref, why), TP_STRUCT__entry( - __field(unsigned int, conn ) - __field(int, ref ) - __field(int, why ) + __field(unsigned int, conn) + __field(int, ref) + __field(int, why) ), TP_fast_assign( @@ -648,11 +658,11 @@ TRACE_EVENT(rxrpc_client, TP_ARGS(conn, channel, op), TP_STRUCT__entry( - __field(unsigned int, conn ) - __field(u32, cid ) - __field(int, channel ) - __field(int, usage ) - __field(enum rxrpc_client_trace, op ) + __field(unsigned int, conn) + __field(u32, cid) + __field(int, channel) + __field(int, usage) + __field(enum rxrpc_client_trace, op) ), TP_fast_assign( @@ -678,10 +688,10 @@ TRACE_EVENT(rxrpc_call, TP_ARGS(call_debug_id, ref, aux, why), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(int, ref ) - __field(int, why ) - __field(unsigned long, aux ) + __field(unsigned int, call) + __field(int, ref) + __field(int, why) + __field(unsigned long, aux) ), TP_fast_assign( @@ -705,10 +715,10 @@ TRACE_EVENT(rxrpc_skb, TP_ARGS(skb, usage, mod_count, why), TP_STRUCT__entry( - __field(struct sk_buff *, skb ) - __field(int, usage ) - __field(int, mod_count ) - __field(enum rxrpc_skb_trace, why ) + __field(struct sk_buff *, skb) + __field(int, usage) + __field(int, mod_count) + __field(enum rxrpc_skb_trace, why) ), TP_fast_assign( @@ -731,7 +741,7 @@ TRACE_EVENT(rxrpc_rx_packet, TP_ARGS(sp), TP_STRUCT__entry( - __field_struct(struct rxrpc_host_header, hdr ) + __field_struct(struct rxrpc_host_header, hdr) ), TP_fast_assign( @@ -742,9 +752,8 @@ TRACE_EVENT(rxrpc_rx_packet, __entry->hdr.epoch, __entry->hdr.cid, __entry->hdr.callNumber, __entry->hdr.serviceId, __entry->hdr.serial, __entry->hdr.seq, - __entry->hdr.type, __entry->hdr.flags, - __entry->hdr.type <= 15 ? - __print_symbolic(__entry->hdr.type, rxrpc_pkts) : "?UNK") + __entry->hdr.securityIndex, __entry->hdr.flags, + __print_symbolic(__entry->hdr.type, rxrpc_pkts)) ); TRACE_EVENT(rxrpc_rx_done, @@ -753,8 +762,8 @@ TRACE_EVENT(rxrpc_rx_done, TP_ARGS(result, abort_code), TP_STRUCT__entry( - __field(int, result ) - __field(int, abort_code ) + __field(int, result) + __field(int, abort_code) ), TP_fast_assign( @@ -772,13 +781,13 @@ TRACE_EVENT(rxrpc_abort, TP_ARGS(call_nr, why, cid, call_id, seq, abort_code, error), TP_STRUCT__entry( - __field(unsigned int, call_nr ) - __field(enum rxrpc_abort_reason, why ) - __field(u32, cid ) - __field(u32, call_id ) - __field(rxrpc_seq_t, seq ) - __field(int, abort_code ) - __field(int, error ) + __field(unsigned int, call_nr) + __field(enum rxrpc_abort_reason, why) + __field(u32, cid) + __field(u32, call_id) + __field(rxrpc_seq_t, seq) + __field(int, abort_code) + __field(int, error) ), TP_fast_assign( @@ -804,10 +813,10 @@ TRACE_EVENT(rxrpc_call_complete, TP_ARGS(call), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(enum rxrpc_call_completion, compl ) - __field(int, error ) - __field(u32, abort_code ) + __field(unsigned int, call) + __field(enum rxrpc_call_completion, compl) + __field(int, error) + __field(u32, abort_code) ), TP_fast_assign( @@ -830,13 +839,13 @@ TRACE_EVENT(rxrpc_txqueue, TP_ARGS(call, why), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(enum rxrpc_txqueue_trace, why ) - __field(rxrpc_seq_t, acks_hard_ack ) - __field(rxrpc_seq_t, tx_bottom ) - __field(rxrpc_seq_t, tx_top ) - __field(rxrpc_seq_t, tx_prepared ) - __field(int, tx_winsize ) + __field(unsigned int, call) + __field(enum rxrpc_txqueue_trace, why) + __field(rxrpc_seq_t, acks_hard_ack) + __field(rxrpc_seq_t, tx_bottom) + __field(rxrpc_seq_t, tx_top) + __field(rxrpc_seq_t, tx_prepared) + __field(int, tx_winsize) ), TP_fast_assign( @@ -867,10 +876,10 @@ TRACE_EVENT(rxrpc_rx_data, TP_ARGS(call, seq, serial, flags), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(rxrpc_seq_t, seq ) - __field(rxrpc_serial_t, serial ) - __field(u8, flags ) + __field(unsigned int, call) + __field(rxrpc_seq_t, seq) + __field(rxrpc_serial_t, serial) + __field(u8, flags) ), TP_fast_assign( @@ -895,13 +904,13 @@ TRACE_EVENT(rxrpc_rx_ack, TP_ARGS(call, serial, ack_serial, first, prev, reason, n_acks), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(rxrpc_serial_t, serial ) - __field(rxrpc_serial_t, ack_serial ) - __field(rxrpc_seq_t, first ) - __field(rxrpc_seq_t, prev ) - __field(u8, reason ) - __field(u8, n_acks ) + __field(unsigned int, call) + __field(rxrpc_serial_t, serial) + __field(rxrpc_serial_t, ack_serial) + __field(rxrpc_seq_t, first) + __field(rxrpc_seq_t, prev) + __field(u8, reason) + __field(u8, n_acks) ), TP_fast_assign( @@ -931,9 +940,9 @@ TRACE_EVENT(rxrpc_rx_abort, TP_ARGS(call, serial, abort_code), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(rxrpc_serial_t, serial ) - __field(u32, abort_code ) + __field(unsigned int, call) + __field(rxrpc_serial_t, serial) + __field(u32, abort_code) ), TP_fast_assign( @@ -955,11 +964,11 @@ TRACE_EVENT(rxrpc_rx_challenge, TP_ARGS(conn, serial, version, nonce, min_level), TP_STRUCT__entry( - __field(unsigned int, conn ) - __field(rxrpc_serial_t, serial ) - __field(u32, version ) - __field(u32, nonce ) - __field(u32, min_level ) + __field(unsigned int, conn) + __field(rxrpc_serial_t, serial) + __field(u32, version) + __field(u32, nonce) + __field(u32, min_level) ), TP_fast_assign( @@ -985,11 +994,11 @@ TRACE_EVENT(rxrpc_rx_response, TP_ARGS(conn, serial, version, kvno, ticket_len), TP_STRUCT__entry( - __field(unsigned int, conn ) - __field(rxrpc_serial_t, serial ) - __field(u32, version ) - __field(u32, kvno ) - __field(u32, ticket_len ) + __field(unsigned int, conn) + __field(rxrpc_serial_t, serial) + __field(u32, version) + __field(u32, kvno) + __field(u32, ticket_len) ), TP_fast_assign( @@ -1015,10 +1024,10 @@ TRACE_EVENT(rxrpc_rx_rwind_change, TP_ARGS(call, serial, rwind, wake), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(rxrpc_serial_t, serial ) - __field(u32, rwind ) - __field(bool, wake ) + __field(unsigned int, call) + __field(rxrpc_serial_t, serial) + __field(u32, rwind) + __field(bool, wake) ), TP_fast_assign( @@ -1042,9 +1051,9 @@ TRACE_EVENT(rxrpc_tx_packet, TP_ARGS(call_id, whdr, where), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(enum rxrpc_tx_point, where ) - __field_struct(struct rxrpc_wire_header, whdr ) + __field(unsigned int, call) + __field(enum rxrpc_tx_point, where) + __field_struct(struct rxrpc_wire_header, whdr) ), TP_fast_assign( @@ -1074,14 +1083,14 @@ TRACE_EVENT(rxrpc_tx_data, TP_ARGS(call, seq, serial, flags, retrans, lose), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(rxrpc_seq_t, seq ) - __field(rxrpc_serial_t, serial ) - __field(u32, cid ) - __field(u32, call_id ) - __field(u8, flags ) - __field(bool, retrans ) - __field(bool, lose ) + __field(unsigned int, call) + __field(rxrpc_seq_t, seq) + __field(rxrpc_serial_t, serial) + __field(u32, cid) + __field(u32, call_id) + __field(u8, flags) + __field(bool, retrans) + __field(bool, lose) ), TP_fast_assign( @@ -1109,17 +1118,18 @@ TRACE_EVENT(rxrpc_tx_data, TRACE_EVENT(rxrpc_tx_ack, TP_PROTO(unsigned int call, rxrpc_serial_t serial, rxrpc_seq_t ack_first, rxrpc_serial_t ack_serial, - u8 reason, u8 n_acks), + u8 reason, u8 n_acks, u16 rwind), - TP_ARGS(call, serial, ack_first, ack_serial, reason, n_acks), + TP_ARGS(call, serial, ack_first, ack_serial, reason, n_acks, rwind), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(rxrpc_serial_t, serial ) - __field(rxrpc_seq_t, ack_first ) - __field(rxrpc_serial_t, ack_serial ) - __field(u8, reason ) - __field(u8, n_acks ) + __field(unsigned int, call) + __field(rxrpc_serial_t, serial) + __field(rxrpc_seq_t, ack_first) + __field(rxrpc_serial_t, ack_serial) + __field(u8, reason) + __field(u8, n_acks) + __field(u16, rwind) ), TP_fast_assign( @@ -1129,15 +1139,17 @@ TRACE_EVENT(rxrpc_tx_ack, __entry->ack_serial = ack_serial; __entry->reason = reason; __entry->n_acks = n_acks; + __entry->rwind = rwind; ), - TP_printk(" c=%08x ACK %08x %s f=%08x r=%08x n=%u", + TP_printk(" c=%08x ACK %08x %s f=%08x r=%08x n=%u rw=%u", __entry->call, __entry->serial, __print_symbolic(__entry->reason, rxrpc_ack_names), __entry->ack_first, __entry->ack_serial, - __entry->n_acks) + __entry->n_acks, + __entry->rwind) ); TRACE_EVENT(rxrpc_receive, @@ -1147,11 +1159,12 @@ TRACE_EVENT(rxrpc_receive, TP_ARGS(call, why, serial, seq), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(enum rxrpc_receive_trace, why ) - __field(rxrpc_serial_t, serial ) - __field(rxrpc_seq_t, seq ) - __field(u64, window ) + __field(unsigned int, call) + __field(enum rxrpc_receive_trace, why) + __field(rxrpc_serial_t, serial) + __field(rxrpc_seq_t, seq) + __field(rxrpc_seq_t, window) + __field(rxrpc_seq_t, wtop) ), TP_fast_assign( @@ -1159,7 +1172,8 @@ TRACE_EVENT(rxrpc_receive, __entry->why = why; __entry->serial = serial; __entry->seq = seq; - __entry->window = atomic64_read(&call->ackr_window); + __entry->window = call->ackr_window; + __entry->wtop = call->ackr_wtop; ), TP_printk("c=%08x %s r=%08x q=%08x w=%08x-%08x", @@ -1167,8 +1181,8 @@ TRACE_EVENT(rxrpc_receive, __print_symbolic(__entry->why, rxrpc_receive_traces), __entry->serial, __entry->seq, - lower_32_bits(__entry->window), - upper_32_bits(__entry->window)) + __entry->window, + __entry->wtop) ); TRACE_EVENT(rxrpc_recvmsg, @@ -1178,9 +1192,9 @@ TRACE_EVENT(rxrpc_recvmsg, TP_ARGS(call_debug_id, why, ret), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(enum rxrpc_recvmsg_trace, why ) - __field(int, ret ) + __field(unsigned int, call) + __field(enum rxrpc_recvmsg_trace, why) + __field(int, ret) ), TP_fast_assign( @@ -1203,12 +1217,12 @@ TRACE_EVENT(rxrpc_recvdata, TP_ARGS(call, why, seq, offset, len, ret), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(enum rxrpc_recvmsg_trace, why ) - __field(rxrpc_seq_t, seq ) - __field(unsigned int, offset ) - __field(unsigned int, len ) - __field(int, ret ) + __field(unsigned int, call) + __field(enum rxrpc_recvmsg_trace, why) + __field(rxrpc_seq_t, seq) + __field(unsigned int, offset) + __field(unsigned int, len) + __field(int, ret) ), TP_fast_assign( @@ -1236,10 +1250,10 @@ TRACE_EVENT(rxrpc_rtt_tx, TP_ARGS(call, why, slot, send_serial), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(enum rxrpc_rtt_tx_trace, why ) - __field(int, slot ) - __field(rxrpc_serial_t, send_serial ) + __field(unsigned int, call) + __field(enum rxrpc_rtt_tx_trace, why) + __field(int, slot) + __field(rxrpc_serial_t, send_serial) ), TP_fast_assign( @@ -1265,13 +1279,13 @@ TRACE_EVENT(rxrpc_rtt_rx, TP_ARGS(call, why, slot, send_serial, resp_serial, rtt, rto), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(enum rxrpc_rtt_rx_trace, why ) - __field(int, slot ) - __field(rxrpc_serial_t, send_serial ) - __field(rxrpc_serial_t, resp_serial ) - __field(u32, rtt ) - __field(u32, rto ) + __field(unsigned int, call) + __field(enum rxrpc_rtt_rx_trace, why) + __field(int, slot) + __field(rxrpc_serial_t, send_serial) + __field(rxrpc_serial_t, resp_serial) + __field(u32, rtt) + __field(u32, rto) ), TP_fast_assign( @@ -1301,17 +1315,17 @@ TRACE_EVENT(rxrpc_timer, TP_ARGS(call, why, now), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(enum rxrpc_timer_trace, why ) - __field(long, now ) - __field(long, ack_at ) - __field(long, ack_lost_at ) - __field(long, resend_at ) - __field(long, ping_at ) - __field(long, expect_rx_by ) - __field(long, expect_req_by ) - __field(long, expect_term_by ) - __field(long, timer ) + __field(unsigned int, call) + __field(enum rxrpc_timer_trace, why) + __field(long, now) + __field(long, ack_at) + __field(long, ack_lost_at) + __field(long, resend_at) + __field(long, ping_at) + __field(long, expect_rx_by) + __field(long, expect_req_by) + __field(long, expect_term_by) + __field(long, timer) ), TP_fast_assign( @@ -1345,16 +1359,16 @@ TRACE_EVENT(rxrpc_timer_expired, TP_ARGS(call, now), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(long, now ) - __field(long, ack_at ) - __field(long, ack_lost_at ) - __field(long, resend_at ) - __field(long, ping_at ) - __field(long, expect_rx_by ) - __field(long, expect_req_by ) - __field(long, expect_term_by ) - __field(long, timer ) + __field(unsigned int, call) + __field(long, now) + __field(long, ack_at) + __field(long, ack_lost_at) + __field(long, resend_at) + __field(long, ping_at) + __field(long, expect_rx_by) + __field(long, expect_req_by) + __field(long, expect_term_by) + __field(long, timer) ), TP_fast_assign( @@ -1386,7 +1400,7 @@ TRACE_EVENT(rxrpc_rx_lose, TP_ARGS(sp), TP_STRUCT__entry( - __field_struct(struct rxrpc_host_header, hdr ) + __field_struct(struct rxrpc_host_header, hdr) ), TP_fast_assign( @@ -1409,10 +1423,10 @@ TRACE_EVENT(rxrpc_propose_ack, TP_ARGS(call, why, ack_reason, serial), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(enum rxrpc_propose_ack_trace, why ) - __field(rxrpc_serial_t, serial ) - __field(u8, ack_reason ) + __field(unsigned int, call) + __field(enum rxrpc_propose_ack_trace, why) + __field(rxrpc_serial_t, serial) + __field(u8, ack_reason) ), TP_fast_assign( @@ -1436,10 +1450,10 @@ TRACE_EVENT(rxrpc_send_ack, TP_ARGS(call, why, ack_reason, serial), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(enum rxrpc_propose_ack_trace, why ) - __field(rxrpc_serial_t, serial ) - __field(u8, ack_reason ) + __field(unsigned int, call) + __field(enum rxrpc_propose_ack_trace, why) + __field(rxrpc_serial_t, serial) + __field(u8, ack_reason) ), TP_fast_assign( @@ -1463,11 +1477,11 @@ TRACE_EVENT(rxrpc_drop_ack, TP_ARGS(call, why, ack_reason, serial, nobuf), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(enum rxrpc_propose_ack_trace, why ) - __field(rxrpc_serial_t, serial ) - __field(u8, ack_reason ) - __field(bool, nobuf ) + __field(unsigned int, call) + __field(enum rxrpc_propose_ack_trace, why) + __field(rxrpc_serial_t, serial) + __field(u8, ack_reason) + __field(bool, nobuf) ), TP_fast_assign( @@ -1491,9 +1505,9 @@ TRACE_EVENT(rxrpc_retransmit, TP_ARGS(call, seq, expiry), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(rxrpc_seq_t, seq ) - __field(s64, expiry ) + __field(unsigned int, call) + __field(rxrpc_seq_t, seq) + __field(s64, expiry) ), TP_fast_assign( @@ -1515,13 +1529,13 @@ TRACE_EVENT(rxrpc_congest, TP_ARGS(call, summary, ack_serial, change), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(enum rxrpc_congest_change, change ) - __field(rxrpc_seq_t, hard_ack ) - __field(rxrpc_seq_t, top ) - __field(rxrpc_seq_t, lowest_nak ) - __field(rxrpc_serial_t, ack_serial ) - __field_struct(struct rxrpc_ack_summary, sum ) + __field(unsigned int, call) + __field(enum rxrpc_congest_change, change) + __field(rxrpc_seq_t, hard_ack) + __field(rxrpc_seq_t, top) + __field(rxrpc_seq_t, lowest_nak) + __field(rxrpc_serial_t, ack_serial) + __field_struct(struct rxrpc_ack_summary, sum) ), TP_fast_assign( @@ -1559,14 +1573,14 @@ TRACE_EVENT(rxrpc_reset_cwnd, TP_ARGS(call, now), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(enum rxrpc_congest_mode, mode ) - __field(unsigned short, cwnd ) - __field(unsigned short, extra ) - __field(rxrpc_seq_t, hard_ack ) - __field(rxrpc_seq_t, prepared ) - __field(ktime_t, since_last_tx ) - __field(bool, has_data ) + __field(unsigned int, call) + __field(enum rxrpc_congest_mode, mode) + __field(unsigned short, cwnd) + __field(unsigned short, extra) + __field(rxrpc_seq_t, hard_ack) + __field(rxrpc_seq_t, prepared) + __field(ktime_t, since_last_tx) + __field(bool, has_data) ), TP_fast_assign( @@ -1597,8 +1611,8 @@ TRACE_EVENT(rxrpc_disconnect_call, TP_ARGS(call), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(u32, abort_code ) + __field(unsigned int, call) + __field(u32, abort_code) ), TP_fast_assign( @@ -1617,8 +1631,8 @@ TRACE_EVENT(rxrpc_improper_term, TP_ARGS(call), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(u32, abort_code ) + __field(unsigned int, call) + __field(u32, abort_code) ), TP_fast_assign( @@ -1637,11 +1651,11 @@ TRACE_EVENT(rxrpc_connect_call, TP_ARGS(call), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(unsigned long, user_call_ID ) - __field(u32, cid ) - __field(u32, call_id ) - __field_struct(struct sockaddr_rxrpc, srx ) + __field(unsigned int, call) + __field(unsigned long, user_call_ID) + __field(u32, cid) + __field(u32, call_id) + __field_struct(struct sockaddr_rxrpc, srx) ), TP_fast_assign( @@ -1666,10 +1680,10 @@ TRACE_EVENT(rxrpc_resend, TP_ARGS(call, ack), TP_STRUCT__entry( - __field(unsigned int, call ) - __field(rxrpc_seq_t, seq ) - __field(rxrpc_seq_t, transmitted ) - __field(rxrpc_serial_t, ack_serial ) + __field(unsigned int, call) + __field(rxrpc_seq_t, seq) + __field(rxrpc_seq_t, transmitted) + __field(rxrpc_serial_t, ack_serial) ), TP_fast_assign( @@ -1694,9 +1708,9 @@ TRACE_EVENT(rxrpc_rx_icmp, TP_ARGS(peer, ee, srx), TP_STRUCT__entry( - __field(unsigned int, peer ) - __field_struct(struct sock_extended_err, ee ) - __field_struct(struct sockaddr_rxrpc, srx ) + __field(unsigned int, peer) + __field_struct(struct sock_extended_err, ee) + __field_struct(struct sockaddr_rxrpc, srx) ), TP_fast_assign( @@ -1723,10 +1737,10 @@ TRACE_EVENT(rxrpc_tx_fail, TP_ARGS(debug_id, serial, ret, where), TP_STRUCT__entry( - __field(unsigned int, debug_id ) - __field(rxrpc_serial_t, serial ) - __field(int, ret ) - __field(enum rxrpc_tx_point, where ) + __field(unsigned int, debug_id) + __field(rxrpc_serial_t, serial) + __field(int, ret) + __field(enum rxrpc_tx_point, where) ), TP_fast_assign( @@ -1749,13 +1763,13 @@ TRACE_EVENT(rxrpc_call_reset, TP_ARGS(call), TP_STRUCT__entry( - __field(unsigned int, debug_id ) - __field(u32, cid ) - __field(u32, call_id ) - __field(rxrpc_serial_t, call_serial ) - __field(rxrpc_serial_t, conn_serial ) - __field(rxrpc_seq_t, tx_seq ) - __field(rxrpc_seq_t, rx_seq ) + __field(unsigned int, debug_id) + __field(u32, cid) + __field(u32, call_id) + __field(rxrpc_serial_t, call_serial) + __field(rxrpc_serial_t, conn_serial) + __field(rxrpc_seq_t, tx_seq) + __field(rxrpc_seq_t, rx_seq) ), TP_fast_assign( @@ -1781,8 +1795,8 @@ TRACE_EVENT(rxrpc_notify_socket, TP_ARGS(debug_id, serial), TP_STRUCT__entry( - __field(unsigned int, debug_id ) - __field(rxrpc_serial_t, serial ) + __field(unsigned int, debug_id) + __field(rxrpc_serial_t, serial) ), TP_fast_assign( @@ -1804,8 +1818,8 @@ TRACE_EVENT(rxrpc_rx_discard_ack, prev_pkt, call_ackr_prev), TP_STRUCT__entry( - __field(unsigned int, debug_id ) - __field(rxrpc_serial_t, serial ) + __field(unsigned int, debug_id) + __field(rxrpc_serial_t, serial) __field(rxrpc_seq_t, first_soft_ack) __field(rxrpc_seq_t, call_ackr_first) __field(rxrpc_seq_t, prev_pkt) @@ -1837,9 +1851,9 @@ TRACE_EVENT(rxrpc_req_ack, TP_ARGS(call_debug_id, seq, why), TP_STRUCT__entry( - __field(unsigned int, call_debug_id ) - __field(rxrpc_seq_t, seq ) - __field(enum rxrpc_req_ack_trace, why ) + __field(unsigned int, call_debug_id) + __field(rxrpc_seq_t, seq) + __field(enum rxrpc_req_ack_trace, why) ), TP_fast_assign( @@ -1862,11 +1876,11 @@ TRACE_EVENT(rxrpc_txbuf, TP_ARGS(debug_id, call_debug_id, seq, ref, what), TP_STRUCT__entry( - __field(unsigned int, debug_id ) - __field(unsigned int, call_debug_id ) - __field(rxrpc_seq_t, seq ) - __field(int, ref ) - __field(enum rxrpc_txbuf_trace, what ) + __field(unsigned int, debug_id) + __field(unsigned int, call_debug_id) + __field(rxrpc_seq_t, seq) + __field(int, ref) + __field(enum rxrpc_txbuf_trace, what) ), TP_fast_assign( @@ -1892,9 +1906,9 @@ TRACE_EVENT(rxrpc_poke_call, TP_ARGS(call, busy, what), TP_STRUCT__entry( - __field(unsigned int, call_debug_id ) - __field(bool, busy ) - __field(enum rxrpc_call_poke_trace, what ) + __field(unsigned int, call_debug_id) + __field(bool, busy) + __field(enum rxrpc_call_poke_trace, what) ), TP_fast_assign( @@ -1915,7 +1929,7 @@ TRACE_EVENT(rxrpc_call_poked, TP_ARGS(call), TP_STRUCT__entry( - __field(unsigned int, call_debug_id ) + __field(unsigned int, call_debug_id) ), TP_fast_assign( @@ -1926,6 +1940,33 @@ TRACE_EVENT(rxrpc_call_poked, __entry->call_debug_id) ); +TRACE_EVENT(rxrpc_sack, + TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, + unsigned int sack, enum rxrpc_sack_trace what), + + TP_ARGS(call, seq, sack, what), + + TP_STRUCT__entry( + __field(unsigned int, call_debug_id) + __field(rxrpc_seq_t, seq) + __field(unsigned int, sack) + __field(enum rxrpc_sack_trace, what) + ), + + TP_fast_assign( + __entry->call_debug_id = call->debug_id; + __entry->seq = seq; + __entry->sack = sack; + __entry->what = what; + ), + + TP_printk("c=%08x q=%08x %s k=%x", + __entry->call_debug_id, + __entry->seq, + __print_symbolic(__entry->what, rxrpc_sack_traces), + __entry->sack) + ); + #undef EM #undef E_ diff --git a/include/uapi/linux/batadv_packet.h b/include/uapi/linux/batadv_packet.h index ea4692c339ce..9204e4494b25 100644 --- a/include/uapi/linux/batadv_packet.h +++ b/include/uapi/linux/batadv_packet.h @@ -26,6 +26,7 @@ * @BATADV_CODED: network coded packets * @BATADV_ELP: echo location packets for B.A.T.M.A.N. V * @BATADV_OGM2: originator messages for B.A.T.M.A.N. V + * @BATADV_MCAST: multicast packet with multiple destination addresses * * @BATADV_UNICAST: unicast packets carrying unicast payload traffic * @BATADV_UNICAST_FRAG: unicast packets carrying a fragment of the original @@ -42,6 +43,7 @@ enum batadv_packettype { BATADV_CODED = 0x02, BATADV_ELP = 0x03, BATADV_OGM2 = 0x04, + BATADV_MCAST = 0x05, /* 0x40 - 0x7f: unicast */ #define BATADV_UNICAST_MIN 0x40 BATADV_UNICAST = 0x40, diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index d9de241d90f9..d60c456710b3 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -523,6 +523,8 @@ enum { BRIDGE_VLANDB_ENTRY_TUNNEL_INFO, BRIDGE_VLANDB_ENTRY_STATS, BRIDGE_VLANDB_ENTRY_MCAST_ROUTER, + BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS, + BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS, __BRIDGE_VLANDB_ENTRY_MAX, }; #define BRIDGE_VLANDB_ENTRY_MAX (__BRIDGE_VLANDB_ENTRY_MAX - 1) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 1021a7e47a86..57ceb788250f 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -374,6 +374,9 @@ enum { IFLA_DEVLINK_PORT, + IFLA_GSO_IPV4_MAX_SIZE, + IFLA_GRO_IPV4_MAX_SIZE, + __IFLA_MAX }; @@ -564,6 +567,8 @@ enum { IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, IFLA_BRPORT_LOCKED, IFLA_BRPORT_MAB, + IFLA_BRPORT_MCAST_N_GROUPS, + IFLA_BRPORT_MCAST_MAX_GROUPS, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index a8516b3594a4..78c981d6a9d4 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -115,6 +115,7 @@ struct tpacket_auxdata { #define TP_STATUS_BLK_TMO (1 << 5) #define TP_STATUS_VLAN_TPID_VALID (1 << 6) /* auxdata has valid tp_vlan_tpid */ #define TP_STATUS_CSUM_VALID (1 << 7) +#define TP_STATUS_GSO_TCP (1 << 8) /* Tx ring - header status */ #define TP_STATUS_AVAILABLE 0 diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h index 874a92349bf5..283dec7e3645 100644 --- a/include/uapi/linux/ip.h +++ b/include/uapi/linux/ip.h @@ -18,6 +18,7 @@ #ifndef _UAPI_LINUX_IP_H #define _UAPI_LINUX_IP_H #include <linux/types.h> +#include <linux/stddef.h> #include <asm/byteorder.h> #define IPTOS_TOS_MASK 0x1E diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 81f4243bebb1..53326dfc59ec 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -4,6 +4,7 @@ #include <linux/libc-compat.h> #include <linux/types.h> +#include <linux/stddef.h> #include <linux/in6.h> #include <asm/byteorder.h> diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 0a4efada9b3c..db623b3185c8 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1765,17 +1765,12 @@ queue: } spin_unlock(&ctx->completion_lock); - ret = io_req_prep_async(req); - if (ret) { -fail: - io_req_defer_failed(req, ret); - return; - } io_prep_async_link(req); de = kmalloc(sizeof(*de), GFP_KERNEL); if (!de) { ret = -ENOMEM; - goto fail; + io_req_defer_failed(req, ret); + return; } spin_lock(&ctx->completion_lock); @@ -2048,13 +2043,16 @@ static void io_queue_sqe_fallback(struct io_kiocb *req) req->flags &= ~REQ_F_HARDLINK; req->flags |= REQ_F_LINK; io_req_defer_failed(req, req->cqe.res); - } else if (unlikely(req->ctx->drain_active)) { - io_drain_req(req); } else { int ret = io_req_prep_async(req); - if (unlikely(ret)) + if (unlikely(ret)) { io_req_defer_failed(req, ret); + return; + } + + if (unlikely(req->ctx->drain_active)) + io_drain_req(req); else io_queue_iowq(req, NULL); } diff --git a/io_uring/net.c b/io_uring/net.c index fbc34a7c2743..90326b279965 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -62,6 +62,7 @@ struct io_sr_msg { u16 flags; /* initialised and used only by !msg send variants */ u16 addr_len; + u16 buf_group; void __user *addr; /* used only for send zerocopy */ struct io_kiocb *notif; @@ -580,6 +581,15 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (req->opcode == IORING_OP_RECV && sr->len) return -EINVAL; req->flags |= REQ_F_APOLL_MULTISHOT; + /* + * Store the buffer group for this multishot receive separately, + * as if we end up doing an io-wq based issue that selects a + * buffer, it has to be committed immediately and that will + * clear ->buf_list. This means we lose the link to the buffer + * list, and the eventual buffer put on completion then cannot + * restore it. + */ + sr->buf_group = req->buf_index; } #ifdef CONFIG_COMPAT @@ -596,6 +606,7 @@ static inline void io_recv_prep_retry(struct io_kiocb *req) sr->done_io = 0; sr->len = 0; /* get from the provided buffer */ + req->buf_index = sr->buf_group; } /* diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index a4a41ee3e80b..e14c822f8911 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -51,7 +51,6 @@ BTF_SET_END(bpf_lsm_current_hooks) */ BTF_SET_START(bpf_lsm_locked_sockopt_hooks) #ifdef CONFIG_SECURITY_NETWORK -BTF_ID(func, bpf_lsm_socket_sock_rcv_skb) BTF_ID(func, bpf_lsm_sock_graft) BTF_ID(func, bpf_lsm_inet_csk_clone) BTF_ID(func, bpf_lsm_inet_conn_established) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 1622a3b15d6f..740bdb045b14 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -7819,9 +7819,9 @@ int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_c sort(tab->dtors, tab->cnt, sizeof(tab->dtors[0]), btf_id_cmp_func, NULL); - return 0; end: - btf_free_dtor_kfunc_tab(btf); + if (ret) + btf_free_dtor_kfunc_tab(btf); btf_put(btf); return ret; } diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index e0b2d016f0bf..d2110c1f6fa6 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -361,7 +361,7 @@ static int cpu_map_kthread_run(void *data) /* Support running another XDP prog on this CPU */ nframes = cpu_map_bpf_prog_run(rcpu, frames, xdp_n, &stats, &list); if (nframes) { - m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, nframes, skbs); + m = kmem_cache_alloc_bulk(skbuff_cache, gfp, nframes, skbs); if (unlikely(m == 0)) { for (i = 0; i < nframes; i++) skbs[i] = NULL; /* effect: xdp_return_frame */ diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index ebcc3dd0fa19..1db156405b68 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -71,7 +71,7 @@ static int bpf_mem_cache_idx(size_t size) if (size <= 192) return size_index[(size - 1) / 8] - 1; - return fls(size - 1) - 1; + return fls(size - 1) - 2; } #define NUM_CACHES 11 diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4cc0e70ee71e..388245e8826e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3423,13 +3423,24 @@ static bool __is_pointer_value(bool allow_ptr_leaks, return reg->type != SCALAR_VALUE; } +/* Copy src state preserving dst->parent and dst->live fields */ +static void copy_register_state(struct bpf_reg_state *dst, const struct bpf_reg_state *src) +{ + struct bpf_reg_state *parent = dst->parent; + enum bpf_reg_liveness live = dst->live; + + *dst = *src; + dst->parent = parent; + dst->live = live; +} + static void save_register_state(struct bpf_func_state *state, int spi, struct bpf_reg_state *reg, int size) { int i; - state->stack[spi].spilled_ptr = *reg; + copy_register_state(&state->stack[spi].spilled_ptr, reg); if (size == BPF_REG_SIZE) state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; @@ -3769,7 +3780,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, */ s32 subreg_def = state->regs[dst_regno].subreg_def; - state->regs[dst_regno] = *reg; + copy_register_state(&state->regs[dst_regno], reg); state->regs[dst_regno].subreg_def = subreg_def; } else { for (i = 0; i < size; i++) { @@ -3790,7 +3801,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, if (dst_regno >= 0) { /* restore register state from stack */ - state->regs[dst_regno] = *reg; + copy_register_state(&state->regs[dst_regno], reg); /* mark reg as written since spilled pointer state likely * has its liveness marks cleared by is_state_visited() * which resets stack/reg liveness for state transitions @@ -9915,7 +9926,7 @@ do_sim: */ if (!ptr_is_dst_reg) { tmp = *dst_reg; - *dst_reg = *ptr_reg; + copy_register_state(dst_reg, ptr_reg); } ret = sanitize_speculative_path(env, NULL, env->insn_idx + 1, env->insn_idx); @@ -11168,7 +11179,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) * to propagate min/max range. */ src_reg->id = ++env->id_gen; - *dst_reg = *src_reg; + copy_register_state(dst_reg, src_reg); dst_reg->live |= REG_LIVE_WRITTEN; dst_reg->subreg_def = DEF_NOT_SUBREG; } else { @@ -11179,7 +11190,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) insn->src_reg); return -EACCES; } else if (src_reg->type == SCALAR_VALUE) { - *dst_reg = *src_reg; + copy_register_state(dst_reg, src_reg); /* Make sure ID is cleared otherwise * dst_reg min/max could be incorrectly * propagated into src_reg by find_equal_scalars() @@ -11978,7 +11989,7 @@ static void find_equal_scalars(struct bpf_verifier_state *vstate, bpf_for_each_reg_in_vstate(vstate, state, reg, ({ if (reg->type == SCALAR_VALUE && reg->id == known_reg->id) - *reg = *known_reg; + copy_register_state(reg, known_reg); })); } diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index a29c0b13706b..ca826bd1eba3 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1205,12 +1205,13 @@ void rebuild_sched_domains(void) /** * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset. * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed + * @new_cpus: the temp variable for the new effective_cpus mask * * Iterate through each task of @cs updating its cpus_allowed to the * effective cpuset's. As this function is called with cpuset_rwsem held, * cpuset membership stays stable. */ -static void update_tasks_cpumask(struct cpuset *cs) +static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus) { struct css_task_iter it; struct task_struct *task; @@ -1224,7 +1225,10 @@ static void update_tasks_cpumask(struct cpuset *cs) if (top_cs && (task->flags & PF_KTHREAD) && kthread_is_per_cpu(task)) continue; - set_cpus_allowed_ptr(task, cs->effective_cpus); + + cpumask_and(new_cpus, cs->effective_cpus, + task_cpu_possible_mask(task)); + set_cpus_allowed_ptr(task, new_cpus); } css_task_iter_end(&it); } @@ -1346,7 +1350,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, * A parent can be left with no CPU as long as there is no * task directly associated with the parent partition. */ - if (!cpumask_intersects(cs->cpus_allowed, parent->effective_cpus) && + if (cpumask_subset(parent->effective_cpus, cs->cpus_allowed) && partition_is_populated(parent, cs)) return PERR_NOCPUS; @@ -1509,7 +1513,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, spin_unlock_irq(&callback_lock); if (adding || deleting) - update_tasks_cpumask(parent); + update_tasks_cpumask(parent, tmp->new_cpus); /* * Set or clear CS_SCHED_LOAD_BALANCE when partcmd_update, if necessary. @@ -1661,7 +1665,7 @@ update_parent_subparts: WARN_ON(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); - update_tasks_cpumask(cp); + update_tasks_cpumask(cp, tmp->new_cpus); /* * On legacy hierarchy, if the effective cpumask of any non- @@ -2309,7 +2313,7 @@ static int update_prstate(struct cpuset *cs, int new_prs) } } - update_tasks_cpumask(parent); + update_tasks_cpumask(parent, tmpmask.new_cpus); if (parent->child_ecpus_count) update_sibling_cpumasks(parent, cs, &tmpmask); @@ -2324,6 +2328,7 @@ out: new_prs = -new_prs; spin_lock_irq(&callback_lock); cs->partition_root_state = new_prs; + WRITE_ONCE(cs->prs_err, err); spin_unlock_irq(&callback_lock); /* * Update child cpusets, if present. @@ -3347,7 +3352,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs, * as the tasks will be migrated to an ancestor. */ if (cpus_updated && !cpumask_empty(cs->cpus_allowed)) - update_tasks_cpumask(cs); + update_tasks_cpumask(cs, new_cpus); if (mems_updated && !nodes_empty(cs->mems_allowed)) update_tasks_nodemask(cs); @@ -3384,7 +3389,7 @@ hotplug_update_tasks(struct cpuset *cs, spin_unlock_irq(&callback_lock); if (cpus_updated) - update_tasks_cpumask(cs); + update_tasks_cpumask(cs, new_cpus); if (mems_updated) update_tasks_nodemask(cs); } @@ -3691,15 +3696,38 @@ void __init cpuset_init_smp(void) * Description: Returns the cpumask_var_t cpus_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty * subset of cpu_online_mask, even if this means going outside the - * tasks cpuset. + * tasks cpuset, except when the task is in the top cpuset. **/ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) { unsigned long flags; + struct cpuset *cs; spin_lock_irqsave(&callback_lock, flags); - guarantee_online_cpus(tsk, pmask); + rcu_read_lock(); + + cs = task_cs(tsk); + if (cs != &top_cpuset) + guarantee_online_cpus(tsk, pmask); + /* + * Tasks in the top cpuset won't get update to their cpumasks + * when a hotplug online/offline event happens. So we include all + * offline cpus in the allowed cpu list. + */ + if ((cs == &top_cpuset) || cpumask_empty(pmask)) { + const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); + + /* + * We first exclude cpus allocated to partitions. If there is no + * allowable online cpu left, we fall back to all possible cpus. + */ + cpumask_andnot(pmask, possible_mask, top_cpuset.subparts_cpus); + if (!cpumask_intersects(pmask, cpu_online_mask)) + cpumask_copy(pmask, possible_mask); + } + + rcu_read_unlock(); spin_unlock_irqrestore(&callback_lock, flags); } diff --git a/kernel/events/core.c b/kernel/events/core.c index d56328e5080e..c4be13e50547 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4813,19 +4813,17 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx, cpc = per_cpu_ptr(pmu->cpu_pmu_context, event->cpu); epc = &cpc->epc; - + raw_spin_lock_irq(&ctx->lock); if (!epc->ctx) { atomic_set(&epc->refcount, 1); epc->embedded = 1; - raw_spin_lock_irq(&ctx->lock); list_add(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list); epc->ctx = ctx; - raw_spin_unlock_irq(&ctx->lock); } else { WARN_ON_ONCE(epc->ctx != ctx); atomic_inc(&epc->refcount); } - + raw_spin_unlock_irq(&ctx->lock); return epc; } @@ -4896,33 +4894,30 @@ static void free_epc_rcu(struct rcu_head *head) static void put_pmu_ctx(struct perf_event_pmu_context *epc) { + struct perf_event_context *ctx = epc->ctx; unsigned long flags; - if (!atomic_dec_and_test(&epc->refcount)) + /* + * XXX + * + * lockdep_assert_held(&ctx->mutex); + * + * can't because of the call-site in _free_event()/put_event() + * which isn't always called under ctx->mutex. + */ + if (!atomic_dec_and_raw_lock_irqsave(&epc->refcount, &ctx->lock, flags)) return; - if (epc->ctx) { - struct perf_event_context *ctx = epc->ctx; + WARN_ON_ONCE(list_empty(&epc->pmu_ctx_entry)); - /* - * XXX - * - * lockdep_assert_held(&ctx->mutex); - * - * can't because of the call-site in _free_event()/put_event() - * which isn't always called under ctx->mutex. - */ - - WARN_ON_ONCE(list_empty(&epc->pmu_ctx_entry)); - raw_spin_lock_irqsave(&ctx->lock, flags); - list_del_init(&epc->pmu_ctx_entry); - epc->ctx = NULL; - raw_spin_unlock_irqrestore(&ctx->lock, flags); - } + list_del_init(&epc->pmu_ctx_entry); + epc->ctx = NULL; WARN_ON_ONCE(!list_empty(&epc->pinned_active)); WARN_ON_ONCE(!list_empty(&epc->flexible_active)); + raw_spin_unlock_irqrestore(&ctx->lock, flags); + if (epc->embedded) return; diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 8fe1da9614ee..798a9042421f 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -114,7 +114,7 @@ void irq_domain_free_fwnode(struct fwnode_handle *fwnode) { struct irqchip_fwid *fwid; - if (WARN_ON(!is_fwnode_irqchip(fwnode))) + if (!fwnode || WARN_ON(!is_fwnode_irqchip(fwnode))) return; fwid = container_of(fwnode, struct irqchip_fwid, fwnode); @@ -1915,7 +1915,7 @@ static void debugfs_add_domain_dir(struct irq_domain *d) static void debugfs_remove_domain_dir(struct irq_domain *d) { - debugfs_remove(debugfs_lookup(d->name, domain_dir)); + debugfs_lookup_and_remove(d->name, domain_dir); } void __init irq_domain_debugfs_init(struct dentry *root) diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 955267bbc2be..783a3e6a0b10 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -1000,7 +1000,7 @@ bool msi_create_device_irq_domain(struct device *dev, unsigned int domid, fail: msi_unlock_descs(dev); free_fwnode: - kfree(fwnode); + irq_domain_free_fwnode(fwnode); free_bundle: kfree(bundle); return false; @@ -1013,6 +1013,7 @@ free_bundle: */ void msi_remove_device_irq_domain(struct device *dev, unsigned int domid) { + struct fwnode_handle *fwnode = NULL; struct msi_domain_info *info; struct irq_domain *domain; @@ -1025,7 +1026,10 @@ void msi_remove_device_irq_domain(struct device *dev, unsigned int domid) dev->msi.data->__domains[domid].domain = NULL; info = domain->host_data; + if (irq_domain_is_msi_device(domain)) + fwnode = domain->fwnode; irq_domain_remove(domain); + irq_domain_free_fwnode(fwnode); kfree(container_of(info, struct msi_domain_template, info)); unlock: diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 8739c2a5a54e..1233affc106c 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -3,6 +3,8 @@ * Scheduler topology setup/handling methods */ +#include <linux/bsearch.h> + DEFINE_MUTEX(sched_domains_mutex); /* Protected by sched_domains_mutex: */ @@ -2067,6 +2069,94 @@ unlock: return found; } +struct __cmp_key { + const struct cpumask *cpus; + struct cpumask ***masks; + int node; + int cpu; + int w; +}; + +static int hop_cmp(const void *a, const void *b) +{ + struct cpumask **prev_hop = *((struct cpumask ***)b - 1); + struct cpumask **cur_hop = *(struct cpumask ***)b; + struct __cmp_key *k = (struct __cmp_key *)a; + + if (cpumask_weight_and(k->cpus, cur_hop[k->node]) <= k->cpu) + return 1; + + k->w = (b == k->masks) ? 0 : cpumask_weight_and(k->cpus, prev_hop[k->node]); + if (k->w <= k->cpu) + return 0; + + return -1; +} + +/* + * sched_numa_find_nth_cpu() - given the NUMA topology, find the Nth next cpu + * closest to @cpu from @cpumask. + * cpumask: cpumask to find a cpu from + * cpu: Nth cpu to find + * + * returns: cpu, or nr_cpu_ids when nothing found. + */ +int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node) +{ + struct __cmp_key k = { .cpus = cpus, .node = node, .cpu = cpu }; + struct cpumask ***hop_masks; + int hop, ret = nr_cpu_ids; + + rcu_read_lock(); + + k.masks = rcu_dereference(sched_domains_numa_masks); + if (!k.masks) + goto unlock; + + hop_masks = bsearch(&k, k.masks, sched_domains_numa_levels, sizeof(k.masks[0]), hop_cmp); + hop = hop_masks - k.masks; + + ret = hop ? + cpumask_nth_and_andnot(cpu - k.w, cpus, k.masks[hop][node], k.masks[hop-1][node]) : + cpumask_nth_and(cpu, cpus, k.masks[0][node]); +unlock: + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL_GPL(sched_numa_find_nth_cpu); + +/** + * sched_numa_hop_mask() - Get the cpumask of CPUs at most @hops hops away from + * @node + * @node: The node to count hops from. + * @hops: Include CPUs up to that many hops away. 0 means local node. + * + * Return: On success, a pointer to a cpumask of CPUs at most @hops away from + * @node, an error value otherwise. + * + * Requires rcu_lock to be held. Returned cpumask is only valid within that + * read-side section, copy it if required beyond that. + * + * Note that not all hops are equal in distance; see sched_init_numa() for how + * distances and masks are handled. + * Also note that this is a reflection of sched_domains_numa_masks, which may change + * during the lifetime of the system (offline nodes are taken out of the masks). + */ +const struct cpumask *sched_numa_hop_mask(unsigned int node, unsigned int hops) +{ + struct cpumask ***masks; + + if (node >= nr_node_ids || hops >= sched_domains_numa_levels) + return ERR_PTR(-EINVAL); + + masks = rcu_dereference(sched_domains_numa_masks); + if (!masks) + return ERR_PTR(-EBUSY); + + return masks[hops][node]; +} +EXPORT_SYMBOL_GPL(sched_numa_hop_mask); + #endif /* CONFIG_NUMA */ static int __sdt_alloc(const struct cpumask *cpu_map) diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 197545241ab8..d7043043f59c 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -933,8 +933,8 @@ config RING_BUFFER_RECORD_RECURSION default y help The ring buffer has its own internal recursion. Although when - recursion happens it wont cause harm because of the protection, - but it does cause an unwanted overhead. Enabling this option will + recursion happens it won't cause harm because of the protection, + but it does cause unwanted overhead. Enabling this option will place where recursion was detected into the ftrace "recursed_functions" file. @@ -1017,8 +1017,8 @@ config RING_BUFFER_STARTUP_TEST The test runs for 10 seconds. This will slow your boot time by at least 10 more seconds. - At the end of the test, statics and more checks are done. - It will output the stats of each per cpu buffer. What + At the end of the test, statistics and more checks are done. + It will output the stats of each per cpu buffer: What was written, the sizes, what was read, what was lost, and other similar details. diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index ff1458e541a8..c58baf9983cc 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -831,6 +831,7 @@ static void do_bpf_send_signal(struct irq_work *entry) work = container_of(entry, struct send_signal_irq_work, irq_work); group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, work->type); + put_task_struct(work->task); } static int bpf_send_signal_common(u32 sig, enum pid_type type) @@ -865,7 +866,7 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type) * to the irq_work. The current task may change when queued * irq works get executed. */ - work->task = current; + work->task = get_task_struct(current); work->sig = sig; work->type = type; irq_work_queue(&work->irq_work); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index d249a55d9005..49762ef50b72 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1248,12 +1248,17 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash) call_rcu(&hash->rcu, __free_ftrace_hash_rcu); } +/** + * ftrace_free_filter - remove all filters for an ftrace_ops + * @ops - the ops to remove the filters from + */ void ftrace_free_filter(struct ftrace_ops *ops) { ftrace_ops_init(ops); free_ftrace_hash(ops->func_hash->filter_hash); free_ftrace_hash(ops->func_hash->notrace_hash); } +EXPORT_SYMBOL_GPL(ftrace_free_filter); static struct ftrace_hash *alloc_ftrace_hash(int size_bits) { @@ -5839,6 +5844,10 @@ EXPORT_SYMBOL_GPL(modify_ftrace_direct_multi); * * Filters denote which functions should be enabled when tracing is enabled * If @ip is NULL, it fails to update filter. + * + * This can allocate memory which must be freed before @ops can be freed, + * either by removing each filtered addr or by using + * ftrace_free_filter(@ops). */ int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip, int remove, int reset) @@ -5858,7 +5867,11 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter_ip); * * Filters denote which functions should be enabled when tracing is enabled * If @ips array or any ip specified within is NULL , it fails to update filter. - */ + * + * This can allocate memory which must be freed before @ops can be freed, + * either by removing each filtered addr or by using + * ftrace_free_filter(@ops). +*/ int ftrace_set_filter_ips(struct ftrace_ops *ops, unsigned long *ips, unsigned int cnt, int remove, int reset) { @@ -5900,6 +5913,10 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, * * Filters denote which functions should be enabled when tracing is enabled. * If @buf is NULL and reset is set, all functions will be enabled for tracing. + * + * This can allocate memory which must be freed before @ops can be freed, + * either by removing each filtered addr or by using + * ftrace_free_filter(@ops). */ int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, int len, int reset) @@ -5919,6 +5936,10 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter); * Notrace Filters denote which functions should not be enabled when tracing * is enabled. If @buf is NULL and reset is set, all functions will be enabled * for tracing. + * + * This can allocate memory which must be freed before @ops can be freed, + * either by removing each filtered addr or by using + * ftrace_free_filter(@ops). */ int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, int len, int reset) diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c index 6c97cc2d754a..7e9061828c24 100644 --- a/kernel/trace/rv/rv.c +++ b/kernel/trace/rv/rv.c @@ -516,7 +516,7 @@ static ssize_t enabled_monitors_write(struct file *filp, const char __user *user struct rv_monitor_def *mdef; int retval = -EINVAL; bool enable = true; - char *ptr = buff; + char *ptr; int len; if (count < 1 || count > MAX_RV_MONITOR_NAME_SIZE + 1) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a555a861b978..c9e40f692650 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -9148,9 +9148,6 @@ buffer_percent_write(struct file *filp, const char __user *ubuf, if (val > 100) return -EINVAL; - if (!val) - val = 1; - tr->buffer_percent = val; (*ppos)++; @@ -10295,6 +10292,8 @@ void __init early_trace_init(void) static_key_enable(&tracepoint_printk_key.key); } tracer_alloc_buffers(); + + init_events(); } void __init trace_init(void) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index e46a49269be2..4eb6d6b97a9f 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1490,6 +1490,7 @@ extern void trace_event_enable_cmd_record(bool enable); extern void trace_event_enable_tgid_record(bool enable); extern int event_trace_init(void); +extern int init_events(void); extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr); extern int event_trace_del_tracer(struct trace_array *tr); extern void __trace_early_add_events(struct trace_array *tr); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 96acc2b71ac7..e095c3b3a50d 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -128,7 +128,7 @@ static bool is_not(const char *str) } /** - * prog_entry - a singe entry in the filter program + * struct prog_entry - a singe entry in the filter program * @target: Index to jump to on a branch (actually one minus the index) * @when_to_branch: The value of the result of the predicate to do a branch * @pred: The predicate to execute. @@ -140,16 +140,16 @@ struct prog_entry { }; /** - * update_preds- assign a program entry a label target + * update_preds - assign a program entry a label target * @prog: The program array * @N: The index of the current entry in @prog - * @when_to_branch: What to assign a program entry for its branch condition + * @invert: What to assign a program entry for its branch condition * * The program entry at @N has a target that points to the index of a program * entry that can have its target and when_to_branch fields updated. * Update the current program entry denoted by index @N target field to be * that of the updated entry. This will denote the entry to update if - * we are processing an "||" after an "&&" + * we are processing an "||" after an "&&". */ static void update_preds(struct prog_entry *prog, int N, int invert) { diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index fcaf226b7744..5edbf6b1da3f 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1988,6 +1988,8 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, hist_field->fn_num = flags & HIST_FIELD_FL_LOG2 ? HIST_FIELD_FN_LOG2 : HIST_FIELD_FN_BUCKET; hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL); + if (!hist_field->operands[0]) + goto free; hist_field->size = hist_field->operands[0]->size; hist_field->type = kstrdup_const(hist_field->operands[0]->type, GFP_KERNEL); if (!hist_field->type) diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 94c1b5eb1dc0..210e1f168392 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -147,9 +147,8 @@ static void osnoise_unregister_instance(struct trace_array *tr) * register/unregister serialization is provided by trace's * trace_types_lock. */ - lockdep_assert_held(&trace_types_lock); - - list_for_each_entry_rcu(inst, &osnoise_instances, list) { + list_for_each_entry_rcu(inst, &osnoise_instances, list, + lockdep_is_held(&trace_types_lock)) { if (inst->tr == tr) { list_del_rcu(&inst->list); found = 1; diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 57a13b61f186..bd475a00f96d 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -1535,7 +1535,7 @@ static struct trace_event *events[] __initdata = { NULL }; -__init static int init_events(void) +__init int init_events(void) { struct trace_event *event; int i, ret; @@ -1548,4 +1548,3 @@ __init static int init_events(void) return 0; } -early_initcall(init_events); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 335411ebaa1e..3509115a0e85 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -763,6 +763,7 @@ config DEBUG_KMEMLEAK select KALLSYMS select CRC32 select STACKDEPOT + select STACKDEPOT_ALWAYS_INIT if !DEBUG_KMEMLEAK_DEFAULT_OFF help Say Y here if you want to enable the memory leak detector. The memory allocation/freeing is traced in a way @@ -1216,7 +1217,7 @@ config SCHED_DEBUG depends on DEBUG_KERNEL && PROC_FS default y help - If you say Y here, the /proc/sched_debug file will be provided + If you say Y here, the /sys/kernel/debug/sched file will be provided that can help debug the scheduler. The runtime overhead of this option is minimal. @@ -1926,7 +1927,7 @@ config FUNCTION_ERROR_INJECTION help Add fault injections into various functions that are annotated with ALLOW_ERROR_INJECTION() in the kernel. BPF may also modify the return - value of theses functions. This is useful to test error paths of code. + value of these functions. This is useful to test error paths of code. If unsure, say N @@ -2575,6 +2576,15 @@ config MEMCPY_KUNIT_TEST If unsure, say N. +config MEMCPY_SLOW_KUNIT_TEST + bool "Include exhaustive memcpy tests" + depends on MEMCPY_KUNIT_TEST + default y + help + Some memcpy tests are quite exhaustive in checking for overlaps + and bit ranges. These can be very slow, so they are split out + as a separate config, in case they need to be disabled. + config IS_SIGNED_TYPE_KUNIT_TEST tristate "Test is_signed_type() macro" if !KUNIT_ALL_TESTS depends on KUNIT diff --git a/lib/Kconfig.kcsan b/lib/Kconfig.kcsan index 375575a5a0e3..4dedd61e5192 100644 --- a/lib/Kconfig.kcsan +++ b/lib/Kconfig.kcsan @@ -194,7 +194,7 @@ config KCSAN_WEAK_MEMORY Enable support for modeling a subset of weak memory, which allows detecting a subset of data races due to missing memory barriers. - Depends on KCSAN_STRICT, because the options strenghtening certain + Depends on KCSAN_STRICT, because the options strengthening certain plain accesses by default (depending on !KCSAN_STRICT) reduce the ability to detect any data races invoving reordered accesses, in particular reordered writes. diff --git a/lib/cpumask.c b/lib/cpumask.c index c7c392514fd3..e7258836b60b 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -110,15 +110,33 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask) #endif /** - * cpumask_local_spread - select the i'th cpu with local numa cpu's first + * cpumask_local_spread - select the i'th cpu based on NUMA distances * @i: index number * @node: local numa_node * - * This function selects an online CPU according to a numa aware policy; - * local cpus are returned first, followed by non-local ones, then it - * wraps around. + * Returns online CPU according to a numa aware policy; local cpus are returned + * first, followed by non-local ones, then it wraps around. * - * It's not very efficient, but useful for setup. + * For those who wants to enumerate all CPUs based on their NUMA distances, + * i.e. call this function in a loop, like: + * + * for (i = 0; i < num_online_cpus(); i++) { + * cpu = cpumask_local_spread(i, node); + * do_something(cpu); + * } + * + * There's a better alternative based on for_each()-like iterators: + * + * for_each_numa_hop_mask(mask, node) { + * for_each_cpu_andnot(cpu, mask, prev) + * do_something(cpu); + * prev = mask; + * } + * + * It's simpler and more verbose than above. Complexity of iterator-based + * enumeration is O(sched_domains_numa_levels * nr_cpu_ids), while + * cpumask_local_spread() when called for each cpu is + * O(sched_domains_numa_levels * nr_cpu_ids * log(nr_cpu_ids)). */ unsigned int cpumask_local_spread(unsigned int i, int node) { @@ -127,24 +145,12 @@ unsigned int cpumask_local_spread(unsigned int i, int node) /* Wrap: we always want a cpu. */ i %= num_online_cpus(); - if (node == NUMA_NO_NODE) { - cpu = cpumask_nth(i, cpu_online_mask); - if (cpu < nr_cpu_ids) - return cpu; - } else { - /* NUMA first. */ - cpu = cpumask_nth_and(i, cpu_online_mask, cpumask_of_node(node)); - if (cpu < nr_cpu_ids) - return cpu; - - i -= cpumask_weight_and(cpu_online_mask, cpumask_of_node(node)); - - /* Skip NUMA nodes, done above. */ - cpu = cpumask_nth_andnot(i, cpu_online_mask, cpumask_of_node(node)); - if (cpu < nr_cpu_ids) - return cpu; - } - BUG(); + cpu = (node == NUMA_NO_NODE) ? + cpumask_nth(i, cpu_online_mask) : + sched_numa_find_nth_cpu(cpu_online_mask, i, node); + + WARN_ON(cpu >= nr_cpu_ids); + return cpu; } EXPORT_SYMBOL(cpumask_local_spread); diff --git a/lib/dec_and_lock.c b/lib/dec_and_lock.c index 9555b68bb774..1dcca8f2e194 100644 --- a/lib/dec_and_lock.c +++ b/lib/dec_and_lock.c @@ -49,3 +49,34 @@ int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, return 0; } EXPORT_SYMBOL(_atomic_dec_and_lock_irqsave); + +int _atomic_dec_and_raw_lock(atomic_t *atomic, raw_spinlock_t *lock) +{ + /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ + if (atomic_add_unless(atomic, -1, 1)) + return 0; + + /* Otherwise do it the slow way */ + raw_spin_lock(lock); + if (atomic_dec_and_test(atomic)) + return 1; + raw_spin_unlock(lock); + return 0; +} +EXPORT_SYMBOL(_atomic_dec_and_raw_lock); + +int _atomic_dec_and_raw_lock_irqsave(atomic_t *atomic, raw_spinlock_t *lock, + unsigned long *flags) +{ + /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ + if (atomic_add_unless(atomic, -1, 1)) + return 0; + + /* Otherwise do it the slow way */ + raw_spin_lock_irqsave(lock, *flags); + if (atomic_dec_and_test(atomic)) + return 1; + raw_spin_unlock_irqrestore(lock, *flags); + return 0; +} +EXPORT_SYMBOL(_atomic_dec_and_raw_lock_irqsave); diff --git a/lib/find_bit.c b/lib/find_bit.c index 18bc0a7ac8ee..c10920e66788 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -155,6 +155,15 @@ unsigned long __find_nth_andnot_bit(const unsigned long *addr1, const unsigned l } EXPORT_SYMBOL(__find_nth_andnot_bit); +unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, + const unsigned long *addr2, + const unsigned long *addr3, + unsigned long size, unsigned long n) +{ + return FIND_NTH_BIT(addr1[idx] & addr2[idx] & ~addr3[idx], size, n); +} +EXPORT_SYMBOL(__find_nth_and_andnot_bit); + #ifndef find_next_and_bit unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start) diff --git a/lib/kunit/assert.c b/lib/kunit/assert.c index f5b50babe38d..05a09652f5a1 100644 --- a/lib/kunit/assert.c +++ b/lib/kunit/assert.c @@ -241,24 +241,34 @@ void kunit_mem_assert_format(const struct kunit_assert *assert, mem_assert = container_of(assert, struct kunit_mem_assert, assert); - string_stream_add(stream, - KUNIT_SUBTEST_INDENT "Expected %s %s %s, but\n", - mem_assert->text->left_text, - mem_assert->text->operation, - mem_assert->text->right_text); + if (!mem_assert->left_value) { + string_stream_add(stream, + KUNIT_SUBTEST_INDENT "Expected %s is not null, but is\n", + mem_assert->text->left_text); + } else if (!mem_assert->right_value) { + string_stream_add(stream, + KUNIT_SUBTEST_INDENT "Expected %s is not null, but is\n", + mem_assert->text->right_text); + } else { + string_stream_add(stream, + KUNIT_SUBTEST_INDENT "Expected %s %s %s, but\n", + mem_assert->text->left_text, + mem_assert->text->operation, + mem_assert->text->right_text); - string_stream_add(stream, KUNIT_SUBSUBTEST_INDENT "%s ==\n", - mem_assert->text->left_text); - kunit_assert_hexdump(stream, mem_assert->left_value, - mem_assert->right_value, mem_assert->size); + string_stream_add(stream, KUNIT_SUBSUBTEST_INDENT "%s ==\n", + mem_assert->text->left_text); + kunit_assert_hexdump(stream, mem_assert->left_value, + mem_assert->right_value, mem_assert->size); - string_stream_add(stream, "\n"); + string_stream_add(stream, "\n"); - string_stream_add(stream, KUNIT_SUBSUBTEST_INDENT "%s ==\n", - mem_assert->text->right_text); - kunit_assert_hexdump(stream, mem_assert->right_value, - mem_assert->left_value, mem_assert->size); + string_stream_add(stream, KUNIT_SUBSUBTEST_INDENT "%s ==\n", + mem_assert->text->right_text); + kunit_assert_hexdump(stream, mem_assert->right_value, + mem_assert->left_value, mem_assert->size); - kunit_assert_print_msg(message, stream); + kunit_assert_print_msg(message, stream); + } } EXPORT_SYMBOL_GPL(kunit_mem_assert_format); diff --git a/lib/kunit/test.c b/lib/kunit/test.c index c9ebf975e56b..890ba5b3a981 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -21,6 +21,7 @@ #include "try-catch-impl.h" DEFINE_STATIC_KEY_FALSE(kunit_running); +EXPORT_SYMBOL_GPL(kunit_running); #if IS_BUILTIN(CONFIG_KUNIT) /* diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 26e2045d3cda..5a976393c9ae 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -670,12 +670,13 @@ static inline unsigned long mte_pivot(const struct maple_enode *mn, unsigned char piv) { struct maple_node *node = mte_to_node(mn); + enum maple_type type = mte_node_type(mn); - if (piv >= mt_pivots[piv]) { + if (piv >= mt_pivots[type]) { WARN_ON(1); return 0; } - switch (mte_node_type(mn)) { + switch (type) { case maple_arange_64: return node->ma64.pivot[piv]; case maple_range_64: @@ -4887,7 +4888,7 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size) unsigned long *pivots, *gaps; void __rcu **slots; unsigned long gap = 0; - unsigned long max, min, index; + unsigned long max, min; unsigned char offset; if (unlikely(mas_is_err(mas))) @@ -4909,8 +4910,7 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size) min = mas_safe_min(mas, pivots, --offset); max = mas_safe_pivot(mas, pivots, offset, type); - index = mas->index; - while (index <= max) { + while (mas->index <= max) { gap = 0; if (gaps) gap = gaps[offset]; @@ -4941,10 +4941,8 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size) min = mas_safe_min(mas, pivots, offset); } - if (unlikely(index > max)) { - mas_set_err(mas, -EBUSY); - return false; - } + if (unlikely((mas->index > max) || (size - 1 > max - mas->index))) + goto no_space; if (unlikely(ma_is_leaf(type))) { mas->offset = offset; @@ -4961,9 +4959,11 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size) return false; ascend: - if (mte_is_root(mas->node)) - mas_set_err(mas, -EBUSY); + if (!mte_is_root(mas->node)) + return false; +no_space: + mas_set_err(mas, -EBUSY); return false; } diff --git a/lib/memcpy_kunit.c b/lib/memcpy_kunit.c index 89128551448d..887926f04731 100644 --- a/lib/memcpy_kunit.c +++ b/lib/memcpy_kunit.c @@ -309,6 +309,8 @@ static void set_random_nonzero(struct kunit *test, u8 *byte) static void init_large(struct kunit *test) { + if (!IS_ENABLED(CONFIG_MEMCPY_SLOW_KUNIT_TEST)) + kunit_skip(test, "Slow test skipped. Enable with CONFIG_MEMCPY_SLOW_KUNIT_TEST=y"); /* Get many bit patterns. */ get_random_bytes(large_src, ARRAY_SIZE(large_src)); diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c index 497fc93ccf9e..ec847bf4dcb4 100644 --- a/lib/test_maple_tree.c +++ b/lib/test_maple_tree.c @@ -2517,6 +2517,91 @@ static noinline void check_bnode_min_spanning(struct maple_tree *mt) mt_set_non_kernel(0); } +static noinline void check_empty_area_window(struct maple_tree *mt) +{ + unsigned long i, nr_entries = 20; + MA_STATE(mas, mt, 0, 0); + + for (i = 1; i <= nr_entries; i++) + mtree_store_range(mt, i*10, i*10 + 9, + xa_mk_value(i), GFP_KERNEL); + + /* Create another hole besides the one at 0 */ + mtree_store_range(mt, 160, 169, NULL, GFP_KERNEL); + + /* Check lower bounds that don't fit */ + rcu_read_lock(); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 5, 90, 10) != -EBUSY); + + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 6, 90, 5) != -EBUSY); + + /* Check lower bound that does fit */ + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 5, 90, 5) != 0); + MT_BUG_ON(mt, mas.index != 5); + MT_BUG_ON(mt, mas.last != 9); + rcu_read_unlock(); + + /* Check one gap that doesn't fit and one that does */ + rcu_read_lock(); + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 5, 217, 9) != 0); + MT_BUG_ON(mt, mas.index != 161); + MT_BUG_ON(mt, mas.last != 169); + + /* Check one gap that does fit above the min */ + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 100, 218, 3) != 0); + MT_BUG_ON(mt, mas.index != 216); + MT_BUG_ON(mt, mas.last != 218); + + /* Check size that doesn't fit any gap */ + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 100, 218, 16) != -EBUSY); + + /* + * Check size that doesn't fit the lower end of the window but + * does fit the gap + */ + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 167, 200, 4) != -EBUSY); + + /* + * Check size that doesn't fit the upper end of the window but + * does fit the gap + */ + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 100, 162, 4) != -EBUSY); + + /* Check mas_empty_area forward */ + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area(&mas, 0, 100, 9) != 0); + MT_BUG_ON(mt, mas.index != 0); + MT_BUG_ON(mt, mas.last != 8); + + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area(&mas, 0, 100, 4) != 0); + MT_BUG_ON(mt, mas.index != 0); + MT_BUG_ON(mt, mas.last != 3); + + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area(&mas, 0, 100, 11) != -EBUSY); + + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area(&mas, 5, 100, 6) != -EBUSY); + + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area(&mas, 0, 8, 10) != -EBUSY); + + mas_reset(&mas); + mas_empty_area(&mas, 100, 165, 3); + + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area(&mas, 100, 163, 6) != -EBUSY); + rcu_read_unlock(); +} + static DEFINE_MTREE(tree); static int maple_tree_seed(void) { @@ -2765,6 +2850,10 @@ static int maple_tree_seed(void) check_bnode_min_spanning(&tree); mtree_destroy(&tree); + mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); + check_empty_area_window(&tree); + mtree_destroy(&tree); + #if defined(BENCH) skip: #endif diff --git a/mm/compaction.c b/mm/compaction.c index ca1603524bbe..8238e83385a7 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1839,6 +1839,7 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc) pfn = cc->zone->zone_start_pfn; cc->fast_search_fail = 0; found_block = true; + set_pageblock_skip(freepage); break; } } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 7fcdb98c9e68..bdbfeb6fb393 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5051,6 +5051,9 @@ again: entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry); } else if (unlikely(is_pte_marker(entry))) { + /* No swap on hugetlb */ + WARN_ON_ONCE( + is_swapin_error_entry(pte_to_swp_entry(entry))); /* * We copy the pte marker only if the dst vma has * uffd-wp enabled. diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 79be13133322..90acfea40c13 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -847,6 +847,10 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, return SCAN_SUCCEED; } +/* + * See pmd_trans_unstable() for how the result may change out from + * underneath us, even if we hold mmap_lock in read. + */ static int find_pmd_or_thp_or_none(struct mm_struct *mm, unsigned long address, pmd_t **pmd) @@ -865,8 +869,12 @@ static int find_pmd_or_thp_or_none(struct mm_struct *mm, #endif if (pmd_none(pmde)) return SCAN_PMD_NONE; + if (!pmd_present(pmde)) + return SCAN_PMD_NULL; if (pmd_trans_huge(pmde)) return SCAN_PMD_MAPPED; + if (pmd_devmap(pmde)) + return SCAN_PMD_NULL; if (pmd_bad(pmde)) return SCAN_PMD_NULL; return SCAN_SUCCEED; @@ -1642,7 +1650,7 @@ static int retract_page_tables(struct address_space *mapping, pgoff_t pgoff, * has higher cost too. It would also probably require locking * the anon_vma. */ - if (vma->anon_vma) { + if (READ_ONCE(vma->anon_vma)) { result = SCAN_PAGE_ANON; goto next; } @@ -1671,6 +1679,18 @@ static int retract_page_tables(struct address_space *mapping, pgoff_t pgoff, if ((cc->is_khugepaged || is_target) && mmap_write_trylock(mm)) { /* + * Re-check whether we have an ->anon_vma, because + * collapse_and_free_pmd() requires that either no + * ->anon_vma exists or the anon_vma is locked. + * We already checked ->anon_vma above, but that check + * is racy because ->anon_vma can be populated under the + * mmap lock in read mode. + */ + if (vma->anon_vma) { + result = SCAN_PAGE_ANON; + goto unlock_next; + } + /* * When a vma is registered with uffd-wp, we can't * recycle the pmd pgtable because there can be pte * markers installed. Skip it only, so the rest mm/vma diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 92f670edbf51..55dc8b8b0616 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -2070,8 +2070,10 @@ static int __init kmemleak_boot_config(char *str) return -EINVAL; if (strcmp(str, "off") == 0) kmemleak_disable(); - else if (strcmp(str, "on") == 0) + else if (strcmp(str, "on") == 0) { kmemleak_skip_disable = 1; + stack_depot_want_early_init(); + } else return -EINVAL; return 0; @@ -2093,7 +2095,6 @@ void __init kmemleak_init(void) if (kmemleak_error) return; - stack_depot_init(); jiffies_min_age = msecs_to_jiffies(MSECS_MIN_AGE); jiffies_scan_wait = msecs_to_jiffies(SECS_SCAN_WAIT * 1000); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ab457f0394ab..73afff8062f9 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -63,7 +63,6 @@ #include <linux/resume_user_mode.h> #include <linux/psi.h> #include <linux/seq_buf.h> -#include <linux/parser.h> #include "internal.h" #include <net/sock.h> #include <net/ip.h> @@ -2393,8 +2392,7 @@ static unsigned long reclaim_high(struct mem_cgroup *memcg, psi_memstall_enter(&pflags); nr_reclaimed += try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, - MEMCG_RECLAIM_MAY_SWAP, - NULL); + MEMCG_RECLAIM_MAY_SWAP); psi_memstall_leave(&pflags); } while ((memcg = parent_mem_cgroup(memcg)) && !mem_cgroup_is_root(memcg)); @@ -2685,8 +2683,7 @@ retry: psi_memstall_enter(&pflags); nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages, - gfp_mask, reclaim_options, - NULL); + gfp_mask, reclaim_options); psi_memstall_leave(&pflags); if (mem_cgroup_margin(mem_over_limit) >= nr_pages) @@ -3506,8 +3503,7 @@ static int mem_cgroup_resize_max(struct mem_cgroup *memcg, } if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, - memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP, - NULL)) { + memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP)) { ret = -EBUSY; break; } @@ -3618,8 +3614,7 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg) return -EINTR; if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, - MEMCG_RECLAIM_MAY_SWAP, - NULL)) + MEMCG_RECLAIM_MAY_SWAP)) nr_retries--; } @@ -6429,8 +6424,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, } reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_pages - high, - GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP, - NULL); + GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP); if (!reclaimed && !nr_retries--) break; @@ -6479,8 +6473,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, if (nr_reclaims) { if (!try_to_free_mem_cgroup_pages(memcg, nr_pages - max, - GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP, - NULL)) + GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP)) nr_reclaims--; continue; } @@ -6603,54 +6596,21 @@ static ssize_t memory_oom_group_write(struct kernfs_open_file *of, return nbytes; } -enum { - MEMORY_RECLAIM_NODES = 0, - MEMORY_RECLAIM_NULL, -}; - -static const match_table_t if_tokens = { - { MEMORY_RECLAIM_NODES, "nodes=%s" }, - { MEMORY_RECLAIM_NULL, NULL }, -}; - static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); unsigned int nr_retries = MAX_RECLAIM_RETRIES; unsigned long nr_to_reclaim, nr_reclaimed = 0; - unsigned int reclaim_options = MEMCG_RECLAIM_MAY_SWAP | - MEMCG_RECLAIM_PROACTIVE; - char *old_buf, *start; - substring_t args[MAX_OPT_ARGS]; - int token; - char value[256]; - nodemask_t nodemask = NODE_MASK_ALL; - - buf = strstrip(buf); - - old_buf = buf; - nr_to_reclaim = memparse(buf, &buf) / PAGE_SIZE; - if (buf == old_buf) - return -EINVAL; + unsigned int reclaim_options; + int err; buf = strstrip(buf); + err = page_counter_memparse(buf, "", &nr_to_reclaim); + if (err) + return err; - while ((start = strsep(&buf, " ")) != NULL) { - if (!strlen(start)) - continue; - token = match_token(start, if_tokens, args); - match_strlcpy(value, args, sizeof(value)); - switch (token) { - case MEMORY_RECLAIM_NODES: - if (nodelist_parse(value, nodemask) < 0) - return -EINVAL; - break; - default: - return -EINVAL; - } - } - + reclaim_options = MEMCG_RECLAIM_MAY_SWAP | MEMCG_RECLAIM_PROACTIVE; while (nr_reclaimed < nr_to_reclaim) { unsigned long reclaimed; @@ -6667,8 +6627,7 @@ static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf, reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_to_reclaim - nr_reclaimed, - GFP_KERNEL, reclaim_options, - &nodemask); + GFP_KERNEL, reclaim_options); if (!reclaimed && !nr_retries--) return -EAGAIN; diff --git a/mm/memory.c b/mm/memory.c index aad226daf41b..3e836fecd035 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -828,12 +828,8 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, return -EBUSY; return -ENOENT; } else if (is_pte_marker_entry(entry)) { - /* - * We're copying the pgtable should only because dst_vma has - * uffd-wp enabled, do sanity check. - */ - WARN_ON_ONCE(!userfaultfd_wp(dst_vma)); - set_pte_at(dst_mm, addr, dst_pte, pte); + if (is_swapin_error_entry(entry) || userfaultfd_wp(dst_vma)) + set_pte_at(dst_mm, addr, dst_pte, pte); return 0; } if (!userfaultfd_wp(dst_vma)) @@ -3629,8 +3625,12 @@ static vm_fault_t pte_marker_clear(struct vm_fault *vmf) /* * Be careful so that we will only recover a special uffd-wp pte into a * none pte. Otherwise it means the pte could have changed, so retry. + * + * This should also cover the case where e.g. the pte changed + * quickly from a PTE_MARKER_UFFD_WP into PTE_MARKER_SWAPIN_ERROR. + * So is_pte_marker() check is not enough to safely drop the pte. */ - if (is_pte_marker(*vmf->pte)) + if (pte_same(vmf->orig_pte, *vmf->pte)) pte_clear(vmf->vma->vm_mm, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 02c8a712282f..f940395667c8 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -600,7 +600,8 @@ static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, /* With MPOL_MF_MOVE, we migrate only unshared hugepage. */ if (flags & (MPOL_MF_MOVE_ALL) || - (flags & MPOL_MF_MOVE && page_mapcount(page) == 1)) { + (flags & MPOL_MF_MOVE && page_mapcount(page) == 1 && + !hugetlb_pmd_shared(pte))) { if (isolate_hugetlb(page, qp->pagelist) && (flags & MPOL_MF_STRICT)) /* diff --git a/mm/mprotect.c b/mm/mprotect.c index 908df12caa26..61cf60015a8b 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -245,7 +245,13 @@ static unsigned long change_pte_range(struct mmu_gather *tlb, newpte = pte_swp_mksoft_dirty(newpte); if (pte_swp_uffd_wp(oldpte)) newpte = pte_swp_mkuffd_wp(newpte); - } else if (pte_marker_entry_uffd_wp(entry)) { + } else if (is_pte_marker_entry(entry)) { + /* + * Ignore swapin errors unconditionally, + * because any access should sigbus anyway. + */ + if (is_swapin_error_entry(entry)) + continue; /* * If this is uffd-wp pte marker and we'd like * to unprotect it, drop it; the next page diff --git a/mm/mremap.c b/mm/mremap.c index fe587c5d6591..930f65c315c0 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -1027,16 +1027,29 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, } /* - * Function vma_merge() is called on the extension we are adding to - * the already existing vma, vma_merge() will merge this extension with - * the already existing vma (expand operation itself) and possibly also - * with the next vma if it becomes adjacent to the expanded vma and - * otherwise compatible. + * Function vma_merge() is called on the extension we + * are adding to the already existing vma, vma_merge() + * will merge this extension with the already existing + * vma (expand operation itself) and possibly also with + * the next vma if it becomes adjacent to the expanded + * vma and otherwise compatible. + * + * However, vma_merge() can currently fail due to + * is_mergeable_vma() check for vm_ops->close (see the + * comment there). Yet this should not prevent vma + * expanding, so perform a simple expand for such vma. + * Ideally the check for close op should be only done + * when a vma would be actually removed due to a merge. */ - vma = vma_merge(mm, vma, extension_start, extension_end, + if (!vma->vm_ops || !vma->vm_ops->close) { + vma = vma_merge(mm, vma, extension_start, extension_end, vma->vm_flags, vma->anon_vma, vma->vm_file, extension_pgoff, vma_policy(vma), vma->vm_userfaultfd_ctx, anon_vma_name(vma)); + } else if (vma_adjust(vma, vma->vm_start, addr + new_len, + vma->vm_pgoff, NULL)) { + vma = NULL; + } if (!vma) { vm_unacct_memory(pages); ret = -ENOMEM; diff --git a/mm/swapfile.c b/mm/swapfile.c index 908a529bca12..4fa440e87cd6 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1100,6 +1100,7 @@ start_over: goto check_out; pr_debug("scan_swap_map of si %d failed to find offset\n", si->type); + cond_resched(); spin_lock(&swap_avail_lock); nextsi: diff --git a/mm/vmscan.c b/mm/vmscan.c index bd6637fcd8f9..bf3eedf0209c 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3323,13 +3323,16 @@ void lru_gen_migrate_mm(struct mm_struct *mm) if (mem_cgroup_disabled()) return; + /* migration can happen before addition */ + if (!mm->lru_gen.memcg) + return; + rcu_read_lock(); memcg = mem_cgroup_from_task(task); rcu_read_unlock(); if (memcg == mm->lru_gen.memcg) return; - VM_WARN_ON_ONCE(!mm->lru_gen.memcg); VM_WARN_ON_ONCE(list_empty(&mm->lru_gen.list)); lru_gen_del_mm(mm); @@ -6754,8 +6757,7 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, - unsigned int reclaim_options, - nodemask_t *nodemask) + unsigned int reclaim_options) { unsigned long nr_reclaimed; unsigned int noreclaim_flag; @@ -6770,7 +6772,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, .may_unmap = 1, .may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP), .proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE), - .nodemask = nodemask, }; /* * Traverse the ZONELIST_FALLBACK zonelist of the current node to put diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 9445bee6b014..702bc3fd687a 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -113,7 +113,23 @@ * have room for two bit at least. */ #define OBJ_ALLOCATED_TAG 1 -#define OBJ_TAG_BITS 1 + +#ifdef CONFIG_ZPOOL +/* + * The second least-significant bit in the object's header identifies if the + * value stored at the header is a deferred handle from the last reclaim + * attempt. + * + * As noted above, this is valid because we have room for two bits. + */ +#define OBJ_DEFERRED_HANDLE_TAG 2 +#define OBJ_TAG_BITS 2 +#define OBJ_TAG_MASK (OBJ_ALLOCATED_TAG | OBJ_DEFERRED_HANDLE_TAG) +#else +#define OBJ_TAG_BITS 1 +#define OBJ_TAG_MASK OBJ_ALLOCATED_TAG +#endif /* CONFIG_ZPOOL */ + #define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS - OBJ_TAG_BITS) #define OBJ_INDEX_MASK ((_AC(1, UL) << OBJ_INDEX_BITS) - 1) @@ -222,6 +238,12 @@ struct link_free { * Handle of allocated object. */ unsigned long handle; +#ifdef CONFIG_ZPOOL + /* + * Deferred handle of a reclaimed object. + */ + unsigned long deferred_handle; +#endif }; }; @@ -272,8 +294,6 @@ struct zspage { /* links the zspage to the lru list in the pool */ struct list_head lru; bool under_reclaim; - /* list of unfreed handles whose objects have been reclaimed */ - unsigned long *deferred_handles; #endif struct zs_pool *pool; @@ -897,7 +917,8 @@ static unsigned long handle_to_obj(unsigned long handle) return *(unsigned long *)handle; } -static bool obj_allocated(struct page *page, void *obj, unsigned long *phandle) +static bool obj_tagged(struct page *page, void *obj, unsigned long *phandle, + int tag) { unsigned long handle; struct zspage *zspage = get_zspage(page); @@ -908,13 +929,27 @@ static bool obj_allocated(struct page *page, void *obj, unsigned long *phandle) } else handle = *(unsigned long *)obj; - if (!(handle & OBJ_ALLOCATED_TAG)) + if (!(handle & tag)) return false; - *phandle = handle & ~OBJ_ALLOCATED_TAG; + /* Clear all tags before returning the handle */ + *phandle = handle & ~OBJ_TAG_MASK; return true; } +static inline bool obj_allocated(struct page *page, void *obj, unsigned long *phandle) +{ + return obj_tagged(page, obj, phandle, OBJ_ALLOCATED_TAG); +} + +#ifdef CONFIG_ZPOOL +static bool obj_stores_deferred_handle(struct page *page, void *obj, + unsigned long *phandle) +{ + return obj_tagged(page, obj, phandle, OBJ_DEFERRED_HANDLE_TAG); +} +#endif + static void reset_page(struct page *page) { __ClearPageMovable(page); @@ -946,22 +981,36 @@ unlock: } #ifdef CONFIG_ZPOOL +static unsigned long find_deferred_handle_obj(struct size_class *class, + struct page *page, int *obj_idx); + /* * Free all the deferred handles whose objects are freed in zs_free. */ -static void free_handles(struct zs_pool *pool, struct zspage *zspage) +static void free_handles(struct zs_pool *pool, struct size_class *class, + struct zspage *zspage) { - unsigned long handle = (unsigned long)zspage->deferred_handles; + int obj_idx = 0; + struct page *page = get_first_page(zspage); + unsigned long handle; - while (handle) { - unsigned long nxt_handle = handle_to_obj(handle); + while (1) { + handle = find_deferred_handle_obj(class, page, &obj_idx); + if (!handle) { + page = get_next_page(page); + if (!page) + break; + obj_idx = 0; + continue; + } cache_free_handle(pool, handle); - handle = nxt_handle; + obj_idx++; } } #else -static inline void free_handles(struct zs_pool *pool, struct zspage *zspage) {} +static inline void free_handles(struct zs_pool *pool, struct size_class *class, + struct zspage *zspage) {} #endif static void __free_zspage(struct zs_pool *pool, struct size_class *class, @@ -979,7 +1028,7 @@ static void __free_zspage(struct zs_pool *pool, struct size_class *class, VM_BUG_ON(fg != ZS_EMPTY); /* Free all deferred handles from zs_free */ - free_handles(pool, zspage); + free_handles(pool, class, zspage); next = page = get_first_page(zspage); do { @@ -1067,7 +1116,6 @@ static void init_zspage(struct size_class *class, struct zspage *zspage) #ifdef CONFIG_ZPOOL INIT_LIST_HEAD(&zspage->lru); zspage->under_reclaim = false; - zspage->deferred_handles = NULL; #endif set_freeobj(zspage, 0); @@ -1568,7 +1616,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) } EXPORT_SYMBOL_GPL(zs_malloc); -static void obj_free(int class_size, unsigned long obj) +static void obj_free(int class_size, unsigned long obj, unsigned long *handle) { struct link_free *link; struct zspage *zspage; @@ -1582,15 +1630,29 @@ static void obj_free(int class_size, unsigned long obj) zspage = get_zspage(f_page); vaddr = kmap_atomic(f_page); - - /* Insert this object in containing zspage's freelist */ link = (struct link_free *)(vaddr + f_offset); - if (likely(!ZsHugePage(zspage))) - link->next = get_freeobj(zspage) << OBJ_TAG_BITS; - else - f_page->index = 0; + + if (handle) { +#ifdef CONFIG_ZPOOL + /* Stores the (deferred) handle in the object's header */ + *handle |= OBJ_DEFERRED_HANDLE_TAG; + *handle &= ~OBJ_ALLOCATED_TAG; + + if (likely(!ZsHugePage(zspage))) + link->deferred_handle = *handle; + else + f_page->index = *handle; +#endif + } else { + /* Insert this object in containing zspage's freelist */ + if (likely(!ZsHugePage(zspage))) + link->next = get_freeobj(zspage) << OBJ_TAG_BITS; + else + f_page->index = 0; + set_freeobj(zspage, f_objidx); + } + kunmap_atomic(vaddr); - set_freeobj(zspage, f_objidx); mod_zspage_inuse(zspage, -1); } @@ -1615,7 +1677,6 @@ void zs_free(struct zs_pool *pool, unsigned long handle) zspage = get_zspage(f_page); class = zspage_class(pool, zspage); - obj_free(class->size, obj); class_stat_dec(class, OBJ_USED, 1); #ifdef CONFIG_ZPOOL @@ -1624,15 +1685,15 @@ void zs_free(struct zs_pool *pool, unsigned long handle) * Reclaim needs the handles during writeback. It'll free * them along with the zspage when it's done with them. * - * Record current deferred handle at the memory location - * whose address is given by handle. + * Record current deferred handle in the object's header. */ - record_obj(handle, (unsigned long)zspage->deferred_handles); - zspage->deferred_handles = (unsigned long *)handle; + obj_free(class->size, obj, &handle); spin_unlock(&pool->lock); return; } #endif + obj_free(class->size, obj, NULL); + fullness = fix_fullness_group(class, zspage); if (fullness == ZS_EMPTY) free_zspage(pool, class, zspage); @@ -1713,11 +1774,11 @@ static void zs_object_copy(struct size_class *class, unsigned long dst, } /* - * Find alloced object in zspage from index object and + * Find object with a certain tag in zspage from index object and * return handle. */ -static unsigned long find_alloced_obj(struct size_class *class, - struct page *page, int *obj_idx) +static unsigned long find_tagged_obj(struct size_class *class, + struct page *page, int *obj_idx, int tag) { unsigned int offset; int index = *obj_idx; @@ -1728,7 +1789,7 @@ static unsigned long find_alloced_obj(struct size_class *class, offset += class->size * index; while (offset < PAGE_SIZE) { - if (obj_allocated(page, addr + offset, &handle)) + if (obj_tagged(page, addr + offset, &handle, tag)) break; offset += class->size; @@ -1742,6 +1803,28 @@ static unsigned long find_alloced_obj(struct size_class *class, return handle; } +/* + * Find alloced object in zspage from index object and + * return handle. + */ +static unsigned long find_alloced_obj(struct size_class *class, + struct page *page, int *obj_idx) +{ + return find_tagged_obj(class, page, obj_idx, OBJ_ALLOCATED_TAG); +} + +#ifdef CONFIG_ZPOOL +/* + * Find object storing a deferred handle in header in zspage from index object + * and return handle. + */ +static unsigned long find_deferred_handle_obj(struct size_class *class, + struct page *page, int *obj_idx) +{ + return find_tagged_obj(class, page, obj_idx, OBJ_DEFERRED_HANDLE_TAG); +} +#endif + struct zs_compact_control { /* Source spage for migration which could be a subpage of zspage */ struct page *s_page; @@ -1784,7 +1867,7 @@ static int migrate_zspage(struct zs_pool *pool, struct size_class *class, zs_object_copy(class, free_obj, used_obj); obj_idx++; record_obj(handle, free_obj); - obj_free(class->size, used_obj); + obj_free(class->size, used_obj, NULL); } /* Remember last position in this iteration */ @@ -2478,6 +2561,90 @@ void zs_destroy_pool(struct zs_pool *pool) EXPORT_SYMBOL_GPL(zs_destroy_pool); #ifdef CONFIG_ZPOOL +static void restore_freelist(struct zs_pool *pool, struct size_class *class, + struct zspage *zspage) +{ + unsigned int obj_idx = 0; + unsigned long handle, off = 0; /* off is within-page offset */ + struct page *page = get_first_page(zspage); + struct link_free *prev_free = NULL; + void *prev_page_vaddr = NULL; + + /* in case no free object found */ + set_freeobj(zspage, (unsigned int)(-1UL)); + + while (page) { + void *vaddr = kmap_atomic(page); + struct page *next_page; + + while (off < PAGE_SIZE) { + void *obj_addr = vaddr + off; + + /* skip allocated object */ + if (obj_allocated(page, obj_addr, &handle)) { + obj_idx++; + off += class->size; + continue; + } + + /* free deferred handle from reclaim attempt */ + if (obj_stores_deferred_handle(page, obj_addr, &handle)) + cache_free_handle(pool, handle); + + if (prev_free) + prev_free->next = obj_idx << OBJ_TAG_BITS; + else /* first free object found */ + set_freeobj(zspage, obj_idx); + + prev_free = (struct link_free *)vaddr + off / sizeof(*prev_free); + /* if last free object in a previous page, need to unmap */ + if (prev_page_vaddr) { + kunmap_atomic(prev_page_vaddr); + prev_page_vaddr = NULL; + } + + obj_idx++; + off += class->size; + } + + /* + * Handle the last (full or partial) object on this page. + */ + next_page = get_next_page(page); + if (next_page) { + if (!prev_free || prev_page_vaddr) { + /* + * There is no free object in this page, so we can safely + * unmap it. + */ + kunmap_atomic(vaddr); + } else { + /* update prev_page_vaddr since prev_free is on this page */ + prev_page_vaddr = vaddr; + } + } else { /* this is the last page */ + if (prev_free) { + /* + * Reset OBJ_TAG_BITS bit to last link to tell + * whether it's allocated object or not. + */ + prev_free->next = -1UL << OBJ_TAG_BITS; + } + + /* unmap previous page (if not done yet) */ + if (prev_page_vaddr) { + kunmap_atomic(prev_page_vaddr); + prev_page_vaddr = NULL; + } + + kunmap_atomic(vaddr); + } + + page = next_page; + off %= PAGE_SIZE; + } +} + static int zs_reclaim_page(struct zs_pool *pool, unsigned int retries) { int i, obj_idx, ret = 0; @@ -2561,6 +2728,12 @@ next: return 0; } + /* + * Eviction fails on one of the handles, so we need to restore zspage. + * We need to rebuild its freelist (and free stored deferred handles), + * put it back to the correct size class, and add it to the LRU list. + */ + restore_freelist(pool, class, zspage); putback_zspage(class, zspage); list_add(&zspage->lru, &pool->lru); unlock_zspage(zspage); diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 114ee5da261f..828fb393ee94 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -27,7 +27,6 @@ #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/pkt_sched.h> -#include <linux/prandom.h> #include <linux/printk.h> #include <linux/random.h> #include <linux/rculist.h> diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index f9a58fb5442e..acff565849ae 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -21,7 +21,6 @@ #include <linux/minmax.h> #include <linux/netdevice.h> #include <linux/nl80211.h> -#include <linux/prandom.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/rcupdate.h> diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index addfd8c4fe95..e710e9afe78f 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -21,7 +21,6 @@ #include <linux/minmax.h> #include <linux/mutex.h> #include <linux/netdevice.h> -#include <linux/prandom.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/rcupdate.h> @@ -800,8 +799,8 @@ batadv_v_ogm_process_per_outif(struct batadv_priv *bat_priv, /* only unknown & newer OGMs contain TVLVs we are interested in */ if (seqno_age > 0 && if_outgoing == BATADV_IF_DEFAULT) - batadv_tvlv_containers_process(bat_priv, true, orig_node, - NULL, NULL, + batadv_tvlv_containers_process(bat_priv, BATADV_OGM2, orig_node, + NULL, (unsigned char *)(ogm2 + 1), ntohs(ogm2->tvlv_len)); diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index fefb51a5f606..6968e55eb971 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -822,7 +822,7 @@ int batadv_dat_init(struct batadv_priv *bat_priv) batadv_dat_start_timer(bat_priv); batadv_tvlv_handler_register(bat_priv, batadv_dat_tvlv_ogm_handler_v1, - NULL, BATADV_TVLV_DAT, 1, + NULL, NULL, BATADV_TVLV_DAT, 1, BATADV_TVLV_HANDLER_OGM_CIFNOTFND); batadv_dat_tvlv_container_update(bat_priv); return 0; diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index 9349c76f30c5..6a964a773f57 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -259,7 +259,7 @@ void batadv_gw_init(struct batadv_priv *bat_priv) atomic_set(&bat_priv->gw.sel_class, 1); batadv_tvlv_handler_register(bat_priv, batadv_gw_tvlv_ogm_handler_v1, - NULL, BATADV_TVLV_GW, 1, + NULL, NULL, BATADV_TVLV_GW, 1, BATADV_TVLV_HANDLER_OGM_CIFNOTFND); } diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index c48803b32bb0..156ed39eded1 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -13,7 +13,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2022.3" +#define BATADV_SOURCE_VERSION "2023.1" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index b238455913df..315394f12c55 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -26,7 +26,6 @@ #include <linux/ipv6.h> #include <linux/jiffies.h> #include <linux/kernel.h> -#include <linux/kref.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/netdevice.h> @@ -1137,222 +1136,19 @@ static int batadv_mcast_forw_rtr_count(struct batadv_priv *bat_priv, } /** - * batadv_mcast_forw_tt_node_get() - get a multicast tt node - * @bat_priv: the bat priv with all the soft interface information - * @ethhdr: the ether header containing the multicast destination - * - * Return: an orig_node matching the multicast address provided by ethhdr - * via a translation table lookup. This increases the returned nodes refcount. - */ -static struct batadv_orig_node * -batadv_mcast_forw_tt_node_get(struct batadv_priv *bat_priv, - struct ethhdr *ethhdr) -{ - return batadv_transtable_search(bat_priv, NULL, ethhdr->h_dest, - BATADV_NO_FLAGS); -} - -/** - * batadv_mcast_forw_ipv4_node_get() - get a node with an ipv4 flag - * @bat_priv: the bat priv with all the soft interface information - * - * Return: an orig_node which has the BATADV_MCAST_WANT_ALL_IPV4 flag set and - * increases its refcount. - */ -static struct batadv_orig_node * -batadv_mcast_forw_ipv4_node_get(struct batadv_priv *bat_priv) -{ - struct batadv_orig_node *tmp_orig_node, *orig_node = NULL; - - rcu_read_lock(); - hlist_for_each_entry_rcu(tmp_orig_node, - &bat_priv->mcast.want_all_ipv4_list, - mcast_want_all_ipv4_node) { - if (!kref_get_unless_zero(&tmp_orig_node->refcount)) - continue; - - orig_node = tmp_orig_node; - break; - } - rcu_read_unlock(); - - return orig_node; -} - -/** - * batadv_mcast_forw_ipv6_node_get() - get a node with an ipv6 flag - * @bat_priv: the bat priv with all the soft interface information - * - * Return: an orig_node which has the BATADV_MCAST_WANT_ALL_IPV6 flag set - * and increases its refcount. - */ -static struct batadv_orig_node * -batadv_mcast_forw_ipv6_node_get(struct batadv_priv *bat_priv) -{ - struct batadv_orig_node *tmp_orig_node, *orig_node = NULL; - - rcu_read_lock(); - hlist_for_each_entry_rcu(tmp_orig_node, - &bat_priv->mcast.want_all_ipv6_list, - mcast_want_all_ipv6_node) { - if (!kref_get_unless_zero(&tmp_orig_node->refcount)) - continue; - - orig_node = tmp_orig_node; - break; - } - rcu_read_unlock(); - - return orig_node; -} - -/** - * batadv_mcast_forw_ip_node_get() - get a node with an ipv4/ipv6 flag - * @bat_priv: the bat priv with all the soft interface information - * @ethhdr: an ethernet header to determine the protocol family from - * - * Return: an orig_node which has the BATADV_MCAST_WANT_ALL_IPV4 or - * BATADV_MCAST_WANT_ALL_IPV6 flag, depending on the provided ethhdr, sets and - * increases its refcount. - */ -static struct batadv_orig_node * -batadv_mcast_forw_ip_node_get(struct batadv_priv *bat_priv, - struct ethhdr *ethhdr) -{ - switch (ntohs(ethhdr->h_proto)) { - case ETH_P_IP: - return batadv_mcast_forw_ipv4_node_get(bat_priv); - case ETH_P_IPV6: - return batadv_mcast_forw_ipv6_node_get(bat_priv); - default: - /* we shouldn't be here... */ - return NULL; - } -} - -/** - * batadv_mcast_forw_unsnoop_node_get() - get a node with an unsnoopable flag - * @bat_priv: the bat priv with all the soft interface information - * - * Return: an orig_node which has the BATADV_MCAST_WANT_ALL_UNSNOOPABLES flag - * set and increases its refcount. - */ -static struct batadv_orig_node * -batadv_mcast_forw_unsnoop_node_get(struct batadv_priv *bat_priv) -{ - struct batadv_orig_node *tmp_orig_node, *orig_node = NULL; - - rcu_read_lock(); - hlist_for_each_entry_rcu(tmp_orig_node, - &bat_priv->mcast.want_all_unsnoopables_list, - mcast_want_all_unsnoopables_node) { - if (!kref_get_unless_zero(&tmp_orig_node->refcount)) - continue; - - orig_node = tmp_orig_node; - break; - } - rcu_read_unlock(); - - return orig_node; -} - -/** - * batadv_mcast_forw_rtr4_node_get() - get a node with an ipv4 mcast router flag - * @bat_priv: the bat priv with all the soft interface information - * - * Return: an orig_node which has the BATADV_MCAST_WANT_NO_RTR4 flag unset and - * increases its refcount. - */ -static struct batadv_orig_node * -batadv_mcast_forw_rtr4_node_get(struct batadv_priv *bat_priv) -{ - struct batadv_orig_node *tmp_orig_node, *orig_node = NULL; - - rcu_read_lock(); - hlist_for_each_entry_rcu(tmp_orig_node, - &bat_priv->mcast.want_all_rtr4_list, - mcast_want_all_rtr4_node) { - if (!kref_get_unless_zero(&tmp_orig_node->refcount)) - continue; - - orig_node = tmp_orig_node; - break; - } - rcu_read_unlock(); - - return orig_node; -} - -/** - * batadv_mcast_forw_rtr6_node_get() - get a node with an ipv6 mcast router flag - * @bat_priv: the bat priv with all the soft interface information - * - * Return: an orig_node which has the BATADV_MCAST_WANT_NO_RTR6 flag unset - * and increases its refcount. - */ -static struct batadv_orig_node * -batadv_mcast_forw_rtr6_node_get(struct batadv_priv *bat_priv) -{ - struct batadv_orig_node *tmp_orig_node, *orig_node = NULL; - - rcu_read_lock(); - hlist_for_each_entry_rcu(tmp_orig_node, - &bat_priv->mcast.want_all_rtr6_list, - mcast_want_all_rtr6_node) { - if (!kref_get_unless_zero(&tmp_orig_node->refcount)) - continue; - - orig_node = tmp_orig_node; - break; - } - rcu_read_unlock(); - - return orig_node; -} - -/** - * batadv_mcast_forw_rtr_node_get() - get a node with an ipv4/ipv6 router flag - * @bat_priv: the bat priv with all the soft interface information - * @ethhdr: an ethernet header to determine the protocol family from - * - * Return: an orig_node which has no BATADV_MCAST_WANT_NO_RTR4 or - * BATADV_MCAST_WANT_NO_RTR6 flag, depending on the provided ethhdr, set and - * increases its refcount. - */ -static struct batadv_orig_node * -batadv_mcast_forw_rtr_node_get(struct batadv_priv *bat_priv, - struct ethhdr *ethhdr) -{ - switch (ntohs(ethhdr->h_proto)) { - case ETH_P_IP: - return batadv_mcast_forw_rtr4_node_get(bat_priv); - case ETH_P_IPV6: - return batadv_mcast_forw_rtr6_node_get(bat_priv); - default: - /* we shouldn't be here... */ - return NULL; - } -} - -/** * batadv_mcast_forw_mode() - check on how to forward a multicast packet * @bat_priv: the bat priv with all the soft interface information - * @skb: The multicast packet to check - * @orig: an originator to be set to forward the skb to + * @skb: the multicast packet to check * @is_routable: stores whether the destination is routable * - * Return: the forwarding mode as enum batadv_forw_mode and in case of - * BATADV_FORW_SINGLE set the orig to the single originator the skb - * should be forwarded to. + * Return: The forwarding mode as enum batadv_forw_mode. */ enum batadv_forw_mode batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, - struct batadv_orig_node **orig, int *is_routable) + int *is_routable) { int ret, tt_count, ip_count, unsnoop_count, total_count; bool is_unsnoopable = false; - unsigned int mcast_fanout; struct ethhdr *ethhdr; int rtr_count = 0; @@ -1361,7 +1157,7 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, if (ret == -ENOMEM) return BATADV_FORW_NONE; else if (ret < 0) - return BATADV_FORW_ALL; + return BATADV_FORW_BCAST; ethhdr = eth_hdr(skb); @@ -1374,32 +1170,15 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, total_count = tt_count + ip_count + unsnoop_count + rtr_count; - switch (total_count) { - case 1: - if (tt_count) - *orig = batadv_mcast_forw_tt_node_get(bat_priv, ethhdr); - else if (ip_count) - *orig = batadv_mcast_forw_ip_node_get(bat_priv, ethhdr); - else if (unsnoop_count) - *orig = batadv_mcast_forw_unsnoop_node_get(bat_priv); - else if (rtr_count) - *orig = batadv_mcast_forw_rtr_node_get(bat_priv, - ethhdr); - - if (*orig) - return BATADV_FORW_SINGLE; - - fallthrough; - case 0: + if (!total_count) return BATADV_FORW_NONE; - default: - mcast_fanout = atomic_read(&bat_priv->multicast_fanout); + else if (unsnoop_count) + return BATADV_FORW_BCAST; - if (!unsnoop_count && total_count <= mcast_fanout) - return BATADV_FORW_SOME; - } + if (total_count <= atomic_read(&bat_priv->multicast_fanout)) + return BATADV_FORW_UCASTS; - return BATADV_FORW_ALL; + return BATADV_FORW_BCAST; } /** @@ -1411,10 +1190,10 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, * * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ -int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, - struct sk_buff *skb, - unsigned short vid, - struct batadv_orig_node *orig_node) +static int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned short vid, + struct batadv_orig_node *orig_node) { /* Avoid sending multicast-in-unicast packets to other BLA * gateways - they already got the frame from the LAN side @@ -2039,7 +1818,7 @@ static void batadv_mcast_tvlv_ogm_handler(struct batadv_priv *bat_priv, void batadv_mcast_init(struct batadv_priv *bat_priv) { batadv_tvlv_handler_register(bat_priv, batadv_mcast_tvlv_ogm_handler, - NULL, BATADV_TVLV_MCAST, 2, + NULL, NULL, BATADV_TVLV_MCAST, 2, BATADV_TVLV_HANDLER_OGM_CIFNOTFND); INIT_DELAYED_WORK(&bat_priv->mcast.work, batadv_mcast_mla_update); diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index 8aec818d0bf6..a9770d8d6d36 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -17,23 +17,16 @@ */ enum batadv_forw_mode { /** - * @BATADV_FORW_ALL: forward the packet to all nodes (currently via - * classic flooding) + * @BATADV_FORW_BCAST: forward the packet to all nodes via a batman-adv + * broadcast packet */ - BATADV_FORW_ALL, + BATADV_FORW_BCAST, /** - * @BATADV_FORW_SOME: forward the packet to some nodes (currently via - * a multicast-to-unicast conversion and the BATMAN unicast routing - * protocol) + * @BATADV_FORW_UCASTS: forward the packet to some nodes via one + * or more batman-adv unicast packets */ - BATADV_FORW_SOME, - - /** - * @BATADV_FORW_SINGLE: forward the packet to a single node (currently - * via the BATMAN unicast routing protocol) - */ - BATADV_FORW_SINGLE, + BATADV_FORW_UCASTS, /** @BATADV_FORW_NONE: don't forward, drop it */ BATADV_FORW_NONE, @@ -43,14 +36,8 @@ enum batadv_forw_mode { enum batadv_forw_mode batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, - struct batadv_orig_node **mcast_single_orig, int *is_routable); -int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, - struct sk_buff *skb, - unsigned short vid, - struct batadv_orig_node *orig_node); - int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid, int is_routable); @@ -69,20 +56,9 @@ void batadv_mcast_purge_orig(struct batadv_orig_node *orig_node); static inline enum batadv_forw_mode batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, - struct batadv_orig_node **mcast_single_orig, int *is_routable) { - return BATADV_FORW_ALL; -} - -static inline int -batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, - struct sk_buff *skb, - unsigned short vid, - struct batadv_orig_node *orig_node) -{ - kfree_skb(skb); - return NET_XMIT_DROP; + return BATADV_FORW_BCAST; } static inline int diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index bf29fba4dde5..71ebd0284f95 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -25,8 +25,8 @@ #include <linux/lockdep.h> #include <linux/net.h> #include <linux/netdevice.h> -#include <linux/prandom.h> #include <linux/printk.h> +#include <linux/random.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> @@ -160,7 +160,7 @@ int batadv_nc_mesh_init(struct batadv_priv *bat_priv) batadv_nc_start_timer(bat_priv); batadv_tvlv_handler_register(bat_priv, batadv_nc_tvlv_ogm_handler_v1, - NULL, BATADV_TVLV_NC, 1, + NULL, NULL, BATADV_TVLV_NC, 1, BATADV_TVLV_HANDLER_OGM_CIFNOTFND); batadv_nc_tvlv_container_update(bat_priv); return 0; diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 83f31494ea4d..163cd43c4821 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1073,10 +1073,9 @@ int batadv_recv_unicast_tvlv(struct sk_buff *skb, if (tvlv_buff_len > skb->len - hdr_size) goto free_skb; - ret = batadv_tvlv_containers_process(bat_priv, false, NULL, - unicast_tvlv_packet->src, - unicast_tvlv_packet->dst, - tvlv_buff, tvlv_buff_len); + ret = batadv_tvlv_containers_process(bat_priv, BATADV_UNICAST_TVLV, + NULL, skb, tvlv_buff, + tvlv_buff_len); if (ret != NET_RX_SUCCESS) { ret = batadv_route_unicast_packet(skb, recv_if); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 0f5c0679b55a..125f4628687c 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -48,7 +48,6 @@ #include "hard-interface.h" #include "multicast.h" #include "network-coding.h" -#include "originator.h" #include "send.h" #include "translation-table.h" @@ -196,8 +195,7 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, unsigned short vid; u32 seqno; int gw_mode; - enum batadv_forw_mode forw_mode = BATADV_FORW_SINGLE; - struct batadv_orig_node *mcast_single_orig = NULL; + enum batadv_forw_mode forw_mode = BATADV_FORW_BCAST; int mcast_is_routable = 0; int network_offset = ETH_HLEN; __be16 proto; @@ -301,14 +299,18 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, send: if (do_bcast && !is_broadcast_ether_addr(ethhdr->h_dest)) { forw_mode = batadv_mcast_forw_mode(bat_priv, skb, - &mcast_single_orig, &mcast_is_routable); - if (forw_mode == BATADV_FORW_NONE) - goto dropped; - - if (forw_mode == BATADV_FORW_SINGLE || - forw_mode == BATADV_FORW_SOME) + switch (forw_mode) { + case BATADV_FORW_BCAST: + break; + case BATADV_FORW_UCASTS: do_bcast = false; + break; + case BATADV_FORW_NONE: + fallthrough; + default: + goto dropped; + } } } @@ -357,10 +359,7 @@ send: if (ret) goto dropped; ret = batadv_send_skb_via_gw(bat_priv, skb, vid); - } else if (mcast_single_orig) { - ret = batadv_mcast_forw_send_orig(bat_priv, skb, vid, - mcast_single_orig); - } else if (forw_mode == BATADV_FORW_SOME) { + } else if (forw_mode == BATADV_FORW_UCASTS) { ret = batadv_mcast_forw_send(bat_priv, skb, vid, mcast_is_routable); } else { @@ -386,7 +385,6 @@ dropped: dropped_freed: batadv_inc_counter(bat_priv, BATADV_CNT_TX_DROPPED); end: - batadv_orig_node_put(mcast_single_orig); batadv_hardif_put(primary_if); return NETDEV_TX_OK; } diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 01d30c1e412c..36ca31252a73 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -4168,11 +4168,11 @@ int batadv_tt_init(struct batadv_priv *bat_priv) } batadv_tvlv_handler_register(bat_priv, batadv_tt_tvlv_ogm_handler_v1, - batadv_tt_tvlv_unicast_handler_v1, + batadv_tt_tvlv_unicast_handler_v1, NULL, BATADV_TVLV_TT, 1, BATADV_NO_FLAGS); batadv_tvlv_handler_register(bat_priv, NULL, - batadv_roam_tvlv_unicast_handler_v1, + batadv_roam_tvlv_unicast_handler_v1, NULL, BATADV_TVLV_ROAM, 1, BATADV_NO_FLAGS); INIT_DELAYED_WORK(&bat_priv->tt.work, batadv_tt_purge); diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index 7ec2e2343884..2a583215d439 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -352,10 +352,9 @@ end: * appropriate handlers * @bat_priv: the bat priv with all the soft interface information * @tvlv_handler: tvlv callback function handling the tvlv content - * @ogm_source: flag indicating whether the tvlv is an ogm or a unicast packet + * @packet_type: indicates for which packet type the TVLV handler is called * @orig_node: orig node emitting the ogm packet - * @src: source mac address of the unicast packet - * @dst: destination mac address of the unicast packet + * @skb: the skb the TVLV handler is called for * @tvlv_value: tvlv content * @tvlv_value_len: tvlv content length * @@ -364,15 +363,20 @@ end: */ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv, struct batadv_tvlv_handler *tvlv_handler, - bool ogm_source, + u8 packet_type, struct batadv_orig_node *orig_node, - u8 *src, u8 *dst, - void *tvlv_value, u16 tvlv_value_len) + struct sk_buff *skb, void *tvlv_value, + u16 tvlv_value_len) { + unsigned int tvlv_offset; + u8 *src, *dst; + if (!tvlv_handler) return NET_RX_SUCCESS; - if (ogm_source) { + switch (packet_type) { + case BATADV_IV_OGM: + case BATADV_OGM2: if (!tvlv_handler->ogm_handler) return NET_RX_SUCCESS; @@ -383,19 +387,32 @@ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv, BATADV_NO_FLAGS, tvlv_value, tvlv_value_len); tvlv_handler->flags |= BATADV_TVLV_HANDLER_OGM_CALLED; - } else { - if (!src) - return NET_RX_SUCCESS; - - if (!dst) + break; + case BATADV_UNICAST_TVLV: + if (!skb) return NET_RX_SUCCESS; if (!tvlv_handler->unicast_handler) return NET_RX_SUCCESS; + src = ((struct batadv_unicast_tvlv_packet *)skb->data)->src; + dst = ((struct batadv_unicast_tvlv_packet *)skb->data)->dst; + return tvlv_handler->unicast_handler(bat_priv, src, dst, tvlv_value, tvlv_value_len); + case BATADV_MCAST: + if (!skb) + return NET_RX_SUCCESS; + + if (!tvlv_handler->mcast_handler) + return NET_RX_SUCCESS; + + tvlv_offset = (unsigned char *)tvlv_value - skb->data; + skb_set_network_header(skb, tvlv_offset); + skb_set_transport_header(skb, tvlv_offset + tvlv_value_len); + + return tvlv_handler->mcast_handler(bat_priv, skb); } return NET_RX_SUCCESS; @@ -405,10 +422,9 @@ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv, * batadv_tvlv_containers_process() - parse the given tvlv buffer to call the * appropriate handlers * @bat_priv: the bat priv with all the soft interface information - * @ogm_source: flag indicating whether the tvlv is an ogm or a unicast packet + * @packet_type: indicates for which packet type the TVLV handler is called * @orig_node: orig node emitting the ogm packet - * @src: source mac address of the unicast packet - * @dst: destination mac address of the unicast packet + * @skb: the skb the TVLV handler is called for * @tvlv_value: tvlv content * @tvlv_value_len: tvlv content length * @@ -416,10 +432,10 @@ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv, * handler callbacks. */ int batadv_tvlv_containers_process(struct batadv_priv *bat_priv, - bool ogm_source, + u8 packet_type, struct batadv_orig_node *orig_node, - u8 *src, u8 *dst, - void *tvlv_value, u16 tvlv_value_len) + struct sk_buff *skb, void *tvlv_value, + u16 tvlv_value_len) { struct batadv_tvlv_handler *tvlv_handler; struct batadv_tvlv_hdr *tvlv_hdr; @@ -441,20 +457,24 @@ int batadv_tvlv_containers_process(struct batadv_priv *bat_priv, tvlv_hdr->version); ret |= batadv_tvlv_call_handler(bat_priv, tvlv_handler, - ogm_source, orig_node, - src, dst, tvlv_value, + packet_type, orig_node, skb, + tvlv_value, tvlv_value_cont_len); batadv_tvlv_handler_put(tvlv_handler); tvlv_value = (u8 *)tvlv_value + tvlv_value_cont_len; tvlv_value_len -= tvlv_value_cont_len; } - if (!ogm_source) + if (packet_type != BATADV_IV_OGM && + packet_type != BATADV_OGM2) return ret; rcu_read_lock(); hlist_for_each_entry_rcu(tvlv_handler, &bat_priv->tvlv.handler_list, list) { + if (!tvlv_handler->ogm_handler) + continue; + if ((tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND) && !(tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CALLED)) tvlv_handler->ogm_handler(bat_priv, orig_node, @@ -490,7 +510,7 @@ void batadv_tvlv_ogm_receive(struct batadv_priv *bat_priv, tvlv_value = batadv_ogm_packet + 1; - batadv_tvlv_containers_process(bat_priv, true, orig_node, NULL, NULL, + batadv_tvlv_containers_process(bat_priv, BATADV_IV_OGM, orig_node, NULL, tvlv_value, tvlv_value_len); } @@ -504,6 +524,10 @@ void batadv_tvlv_ogm_receive(struct batadv_priv *bat_priv, * @uptr: unicast tvlv handler callback function. This function receives the * source & destination of the unicast packet as well as the tvlv content * to process. + * @mptr: multicast packet tvlv handler callback function. This function + * receives the full skb to process, with the skb network header pointing + * to the current tvlv and the skb transport header pointing to the first + * byte after the current tvlv. * @type: tvlv handler type to be registered * @version: tvlv handler version to be registered * @flags: flags to enable or disable TVLV API behavior @@ -518,6 +542,8 @@ void batadv_tvlv_handler_register(struct batadv_priv *bat_priv, u8 *src, u8 *dst, void *tvlv_value, u16 tvlv_value_len), + int (*mptr)(struct batadv_priv *bat_priv, + struct sk_buff *skb), u8 type, u8 version, u8 flags) { struct batadv_tvlv_handler *tvlv_handler; @@ -539,6 +565,7 @@ void batadv_tvlv_handler_register(struct batadv_priv *bat_priv, tvlv_handler->ogm_handler = optr; tvlv_handler->unicast_handler = uptr; + tvlv_handler->mcast_handler = mptr; tvlv_handler->type = type; tvlv_handler->version = version; tvlv_handler->flags = flags; diff --git a/net/batman-adv/tvlv.h b/net/batman-adv/tvlv.h index 4cf8af00fc11..e5697230d991 100644 --- a/net/batman-adv/tvlv.h +++ b/net/batman-adv/tvlv.h @@ -9,6 +9,7 @@ #include "main.h" +#include <linux/skbuff.h> #include <linux/types.h> #include <uapi/linux/batadv_packet.h> @@ -34,14 +35,16 @@ void batadv_tvlv_handler_register(struct batadv_priv *bat_priv, u8 *src, u8 *dst, void *tvlv_value, u16 tvlv_value_len), + int (*mptr)(struct batadv_priv *bat_priv, + struct sk_buff *skb), u8 type, u8 version, u8 flags); void batadv_tvlv_handler_unregister(struct batadv_priv *bat_priv, u8 type, u8 version); int batadv_tvlv_containers_process(struct batadv_priv *bat_priv, - bool ogm_source, + u8 packet_type, struct batadv_orig_node *orig_node, - u8 *src, u8 *dst, - void *tvlv_buff, u16 tvlv_buff_len); + struct sk_buff *skb, void *tvlv_buff, + u16 tvlv_buff_len); void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, const u8 *src, const u8 *dst, u8 type, u8 version, void *tvlv_value, u16 tvlv_value_len); diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 758cd797a063..ca9449ec9836 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -2335,6 +2335,12 @@ struct batadv_tvlv_handler { u8 *src, u8 *dst, void *tvlv_value, u16 tvlv_value_len); + /** + * @mcast_handler: handler callback which is given the tvlv payload to + * process on incoming mcast packet + */ + int (*mcast_handler)(struct batadv_priv *bat_priv, struct sk_buff *skb); + /** @type: tvlv type this handler feels responsible for */ u8 type; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index e6f773d12045..b766a84c8536 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -234,7 +234,7 @@ static int xdp_recv_frames(struct xdp_frame **frames, int nframes, int i, n; LIST_HEAD(list); - n = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, nframes, (void **)skbs); + n = kmem_cache_alloc_bulk(skbuff_cache, gfp, nframes, (void **)skbs); if (unlikely(n == 0)) { for (i = 0; i < nframes; i++) xdp_return_frame(frames[i]); diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 00e5743647b0..9f22ebfdc518 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -849,11 +849,10 @@ static int br_mdb_add_group_sg(const struct br_mdb_config *cfg, } p = br_multicast_new_port_group(cfg->p, &cfg->group, *pp, flags, NULL, - MCAST_INCLUDE, cfg->rt_protocol); - if (unlikely(!p)) { - NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new (S, G) port group"); + MCAST_INCLUDE, cfg->rt_protocol, extack); + if (unlikely(!p)) return -ENOMEM; - } + rcu_assign_pointer(*pp, p); if (!(flags & MDB_PG_FLAGS_PERMANENT) && !cfg->src_entry) mod_timer(&p->timer, @@ -1075,11 +1074,10 @@ static int br_mdb_add_group_star_g(const struct br_mdb_config *cfg, } p = br_multicast_new_port_group(cfg->p, &cfg->group, *pp, flags, NULL, - cfg->filter_mode, cfg->rt_protocol); - if (unlikely(!p)) { - NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new (*, G) port group"); + cfg->filter_mode, cfg->rt_protocol, + extack); + if (unlikely(!p)) return -ENOMEM; - } err = br_mdb_add_group_srcs(cfg, p, brmctx, extack); if (err) @@ -1101,8 +1099,7 @@ static int br_mdb_add_group_star_g(const struct br_mdb_config *cfg, return 0; err_del_port_group: - hlist_del_init(&p->mglist); - kfree(p); + br_multicast_del_port_group(p); return err; } diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index dea1ee1bd095..96d1fc78dd39 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -31,6 +31,7 @@ #include <net/ip6_checksum.h> #include <net/addrconf.h> #endif +#include <trace/events/bridge.h> #include "br_private.h" #include "br_private_mcast_eht.h" @@ -234,6 +235,29 @@ out: return pmctx; } +static struct net_bridge_mcast_port * +br_multicast_port_vid_to_port_ctx(struct net_bridge_port *port, u16 vid) +{ + struct net_bridge_mcast_port *pmctx = NULL; + struct net_bridge_vlan *vlan; + + lockdep_assert_held_once(&port->br->multicast_lock); + + if (!br_opt_get(port->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) + return NULL; + + /* Take RCU to access the vlan. */ + rcu_read_lock(); + + vlan = br_vlan_find(nbp_vlan_group_rcu(port), vid); + if (vlan && !br_multicast_port_ctx_vlan_disabled(&vlan->port_mcast_ctx)) + pmctx = &vlan->port_mcast_ctx; + + rcu_read_unlock(); + + return pmctx; +} + /* when snooping we need to check if the contexts should be used * in the following order: * - if pmctx is non-NULL (port), check if it should be used @@ -668,6 +692,101 @@ void br_multicast_del_group_src(struct net_bridge_group_src *src, __br_multicast_del_group_src(src); } +static int +br_multicast_port_ngroups_inc_one(struct net_bridge_mcast_port *pmctx, + struct netlink_ext_ack *extack, + const char *what) +{ + u32 max = READ_ONCE(pmctx->mdb_max_entries); + u32 n = READ_ONCE(pmctx->mdb_n_entries); + + if (max && n >= max) { + NL_SET_ERR_MSG_FMT_MOD(extack, "%s is already in %u groups, and mcast_max_groups=%u", + what, n, max); + return -E2BIG; + } + + WRITE_ONCE(pmctx->mdb_n_entries, n + 1); + return 0; +} + +static void br_multicast_port_ngroups_dec_one(struct net_bridge_mcast_port *pmctx) +{ + u32 n = READ_ONCE(pmctx->mdb_n_entries); + + WARN_ON_ONCE(n == 0); + WRITE_ONCE(pmctx->mdb_n_entries, n - 1); +} + +static int br_multicast_port_ngroups_inc(struct net_bridge_port *port, + const struct br_ip *group, + struct netlink_ext_ack *extack) +{ + struct net_bridge_mcast_port *pmctx; + int err; + + lockdep_assert_held_once(&port->br->multicast_lock); + + /* Always count on the port context. */ + err = br_multicast_port_ngroups_inc_one(&port->multicast_ctx, extack, + "Port"); + if (err) { + trace_br_mdb_full(port->dev, group); + return err; + } + + /* Only count on the VLAN context if VID is given, and if snooping on + * that VLAN is enabled. + */ + if (!group->vid) + return 0; + + pmctx = br_multicast_port_vid_to_port_ctx(port, group->vid); + if (!pmctx) + return 0; + + err = br_multicast_port_ngroups_inc_one(pmctx, extack, "Port-VLAN"); + if (err) { + trace_br_mdb_full(port->dev, group); + goto dec_one_out; + } + + return 0; + +dec_one_out: + br_multicast_port_ngroups_dec_one(&port->multicast_ctx); + return err; +} + +static void br_multicast_port_ngroups_dec(struct net_bridge_port *port, u16 vid) +{ + struct net_bridge_mcast_port *pmctx; + + lockdep_assert_held_once(&port->br->multicast_lock); + + if (vid) { + pmctx = br_multicast_port_vid_to_port_ctx(port, vid); + if (pmctx) + br_multicast_port_ngroups_dec_one(pmctx); + } + br_multicast_port_ngroups_dec_one(&port->multicast_ctx); +} + +u32 br_multicast_ngroups_get(const struct net_bridge_mcast_port *pmctx) +{ + return READ_ONCE(pmctx->mdb_n_entries); +} + +void br_multicast_ngroups_set_max(struct net_bridge_mcast_port *pmctx, u32 max) +{ + WRITE_ONCE(pmctx->mdb_max_entries, max); +} + +u32 br_multicast_ngroups_get_max(const struct net_bridge_mcast_port *pmctx) +{ + return READ_ONCE(pmctx->mdb_max_entries); +} + static void br_multicast_destroy_port_group(struct net_bridge_mcast_gc *gc) { struct net_bridge_port_group *pg; @@ -702,6 +821,7 @@ void br_multicast_del_pg(struct net_bridge_mdb_entry *mp, } else { br_multicast_star_g_handle_mode(pg, MCAST_INCLUDE); } + br_multicast_port_ngroups_dec(pg->key.port, pg->key.addr.vid); hlist_add_head(&pg->mcast_gc.gc_node, &br->mcast_gc_list); queue_work(system_long_wq, &br->mcast_gc_work); @@ -1165,6 +1285,7 @@ struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br, return mp; if (atomic_read(&br->mdb_hash_tbl.nelems) >= br->hash_max) { + trace_br_mdb_full(br->dev, group); br_mc_disabled_update(br->dev, false, NULL); br_opt_toggle(br, BROPT_MULTICAST_ENABLED, false); return ERR_PTR(-E2BIG); @@ -1284,14 +1405,22 @@ struct net_bridge_port_group *br_multicast_new_port_group( unsigned char flags, const unsigned char *src, u8 filter_mode, - u8 rt_protocol) + u8 rt_protocol, + struct netlink_ext_ack *extack) { struct net_bridge_port_group *p; + int err; - p = kzalloc(sizeof(*p), GFP_ATOMIC); - if (unlikely(!p)) + err = br_multicast_port_ngroups_inc(port, group, extack); + if (err) return NULL; + p = kzalloc(sizeof(*p), GFP_ATOMIC); + if (unlikely(!p)) { + NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new port group"); + goto dec_out; + } + p->key.addr = *group; p->key.port = port; p->flags = flags; @@ -1305,8 +1434,8 @@ struct net_bridge_port_group *br_multicast_new_port_group( if (!br_multicast_is_star_g(group) && rhashtable_lookup_insert_fast(&port->br->sg_port_tbl, &p->rhnode, br_sg_port_rht_params)) { - kfree(p); - return NULL; + NL_SET_ERR_MSG_MOD(extack, "Couldn't insert new port group"); + goto free_out; } rcu_assign_pointer(p->next, next); @@ -1320,6 +1449,25 @@ struct net_bridge_port_group *br_multicast_new_port_group( eth_broadcast_addr(p->eth_addr); return p; + +free_out: + kfree(p); +dec_out: + br_multicast_port_ngroups_dec(port, group->vid); + return NULL; +} + +void br_multicast_del_port_group(struct net_bridge_port_group *p) +{ + struct net_bridge_port *port = p->key.port; + __u16 vid = p->key.addr.vid; + + hlist_del_init(&p->mglist); + if (!br_multicast_is_star_g(&p->key.addr)) + rhashtable_remove_fast(&port->br->sg_port_tbl, &p->rhnode, + br_sg_port_rht_params); + kfree(p); + br_multicast_port_ngroups_dec(port, vid); } void br_multicast_host_join(const struct net_bridge_mcast *brmctx, @@ -1387,7 +1535,7 @@ __br_multicast_add_group(struct net_bridge_mcast *brmctx, } p = br_multicast_new_port_group(pmctx->port, group, *pp, 0, src, - filter_mode, RTPROT_KERNEL); + filter_mode, RTPROT_KERNEL, NULL); if (unlikely(!p)) { p = ERR_PTR(-ENOMEM); goto out; @@ -1933,6 +2081,25 @@ static void __br_multicast_enable_port_ctx(struct net_bridge_mcast_port *pmctx) br_ip4_multicast_add_router(brmctx, pmctx); br_ip6_multicast_add_router(brmctx, pmctx); } + + if (br_multicast_port_ctx_is_vlan(pmctx)) { + struct net_bridge_port_group *pg; + u32 n = 0; + + /* The mcast_n_groups counter might be wrong. First, + * BR_VLFLAG_MCAST_ENABLED is toggled before temporary entries + * are flushed, thus mcast_n_groups after the toggle does not + * reflect the true values. And second, permanent entries added + * while BR_VLFLAG_MCAST_ENABLED was disabled, are not reflected + * either. Thus we have to refresh the counter. + */ + + hlist_for_each_entry(pg, &pmctx->port->mglist, mglist) { + if (pg->key.addr.vid == pmctx->vlan->vid) + n++; + } + WRITE_ONCE(pmctx->mdb_n_entries, n); + } } void br_multicast_enable_port(struct net_bridge_port *port) diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index f20f4373ff40..638a4d5359db 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -214,7 +214,7 @@ static int br_validate_ipv4(struct net *net, struct sk_buff *skb) if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) goto csum_error; - len = ntohs(iph->tot_len); + len = skb_ip_totlen(skb); if (skb->len < len) { __IP_INC_STATS(net, IPSTATS_MIB_INTRUNCATEDPKTS); goto drop; @@ -871,6 +871,7 @@ static unsigned int ip_sabotage_in(void *priv, if (nf_bridge && !nf_bridge->in_prerouting && !netif_is_l3_master(skb->dev) && !netif_is_l3_slave(skb->dev)) { + nf_bridge_info_free(skb); state->okfn(state->net, state->sk, skb); return NF_STOLEN; } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 4316cc82ae17..9173e52b89e2 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -202,6 +202,8 @@ static inline size_t br_port_info_size(void) + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_HOLD_TIMER */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */ + + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_N_GROUPS */ + + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_MAX_GROUPS */ #endif + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_GROUP_FWD_MASK */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_RING_OPEN */ @@ -298,7 +300,11 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, p->multicast_eht_hosts_limit) || nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, - p->multicast_eht_hosts_cnt)) + p->multicast_eht_hosts_cnt) || + nla_put_u32(skb, IFLA_BRPORT_MCAST_N_GROUPS, + br_multicast_ngroups_get(&p->multicast_ctx)) || + nla_put_u32(skb, IFLA_BRPORT_MCAST_MAX_GROUPS, + br_multicast_ngroups_get_max(&p->multicast_ctx))) return -EMSGSIZE; #endif @@ -858,6 +864,8 @@ static int br_afspec(struct net_bridge *br, } static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { + [IFLA_BRPORT_UNSPEC] = { .strict_start_type = + IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT + 1 }, [IFLA_BRPORT_STATE] = { .type = NLA_U8 }, [IFLA_BRPORT_COST] = { .type = NLA_U32 }, [IFLA_BRPORT_PRIORITY] = { .type = NLA_U16 }, @@ -881,6 +889,8 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_MAB] = { .type = NLA_U8 }, [IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 }, [IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT] = { .type = NLA_U32 }, + [IFLA_BRPORT_MCAST_N_GROUPS] = { .type = NLA_REJECT }, + [IFLA_BRPORT_MCAST_MAX_GROUPS] = { .type = NLA_U32 }, }; /* Change the state of the port and notify spanning tree */ @@ -1015,6 +1025,13 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[], if (err) return err; } + + if (tb[IFLA_BRPORT_MCAST_MAX_GROUPS]) { + u32 max_groups; + + max_groups = nla_get_u32(tb[IFLA_BRPORT_MCAST_MAX_GROUPS]); + br_multicast_ngroups_set_max(&p->multicast_ctx, max_groups); + } #endif if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) { diff --git a/net/bridge/br_netlink_tunnel.c b/net/bridge/br_netlink_tunnel.c index 8914290c75d4..17abf092f7ca 100644 --- a/net/bridge/br_netlink_tunnel.c +++ b/net/bridge/br_netlink_tunnel.c @@ -188,6 +188,9 @@ initvars: } static const struct nla_policy vlan_tunnel_policy[IFLA_BRIDGE_VLAN_TUNNEL_MAX + 1] = { + [IFLA_BRIDGE_VLAN_TUNNEL_UNSPEC] = { + .strict_start_type = IFLA_BRIDGE_VLAN_TUNNEL_FLAGS + 1 + }, [IFLA_BRIDGE_VLAN_TUNNEL_ID] = { .type = NLA_U32 }, [IFLA_BRIDGE_VLAN_TUNNEL_VID] = { .type = NLA_U16 }, [IFLA_BRIDGE_VLAN_TUNNEL_FLAGS] = { .type = NLA_U16 }, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 15ef7fd508ee..cef5f6ea850c 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -126,6 +126,8 @@ struct net_bridge_mcast_port { struct hlist_node ip6_rlist; #endif /* IS_ENABLED(CONFIG_IPV6) */ unsigned char multicast_router; + u32 mdb_n_entries; + u32 mdb_max_entries; #endif /* CONFIG_BRIDGE_IGMP_SNOOPING */ }; @@ -956,7 +958,9 @@ br_multicast_new_port_group(struct net_bridge_port *port, const struct br_ip *group, struct net_bridge_port_group __rcu *next, unsigned char flags, const unsigned char *src, - u8 filter_mode, u8 rt_protocol); + u8 filter_mode, u8 rt_protocol, + struct netlink_ext_ack *extack); +void br_multicast_del_port_group(struct net_bridge_port_group *p); int br_mdb_hash_init(struct net_bridge *br); void br_mdb_hash_fini(struct net_bridge *br); void br_mdb_notify(struct net_device *dev, struct net_bridge_mdb_entry *mp, @@ -974,6 +978,9 @@ void br_multicast_uninit_stats(struct net_bridge *br); void br_multicast_get_stats(const struct net_bridge *br, const struct net_bridge_port *p, struct br_mcast_stats *dest); +u32 br_multicast_ngroups_get(const struct net_bridge_mcast_port *pmctx); +void br_multicast_ngroups_set_max(struct net_bridge_mcast_port *pmctx, u32 max); +u32 br_multicast_ngroups_get_max(const struct net_bridge_mcast_port *pmctx); void br_mdb_init(void); void br_mdb_uninit(void); void br_multicast_host_join(const struct net_bridge_mcast *brmctx, @@ -1757,7 +1764,8 @@ static inline u16 br_vlan_flags(const struct net_bridge_vlan *v, u16 pvid) #ifdef CONFIG_BRIDGE_VLAN_FILTERING bool br_vlan_opts_eq_range(const struct net_bridge_vlan *v_curr, const struct net_bridge_vlan *range_end); -bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v); +bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v, + const struct net_bridge_port *p); size_t br_vlan_opts_nl_size(void); int br_vlan_process_options(const struct net_bridge *br, const struct net_bridge_port *p, diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 7eb6fd5bb917..de18e9c1d7a7 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -104,9 +104,8 @@ int br_switchdev_set_port_flag(struct net_bridge_port *p, return 0; if (err) { - if (extack && !extack->_msg) - NL_SET_ERR_MSG_MOD(extack, - "bridge flag offload is not supported"); + NL_SET_ERR_MSG_WEAK_MOD(extack, + "bridge flag offload is not supported"); return -EOPNOTSUPP; } @@ -115,9 +114,8 @@ int br_switchdev_set_port_flag(struct net_bridge_port *p, err = switchdev_port_attr_set(p->dev, &attr, extack); if (err) { - if (extack && !extack->_msg) - NL_SET_ERR_MSG_MOD(extack, - "error setting offload flag on port"); + NL_SET_ERR_MSG_WEAK_MOD(extack, + "error setting offload flag on port"); return err; } diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index bc75fa1e4666..8a3dbc09ba38 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1816,6 +1816,7 @@ out_err: /* v_opts is used to dump the options which must be equal in the whole range */ static bool br_vlan_fill_vids(struct sk_buff *skb, u16 vid, u16 vid_range, const struct net_bridge_vlan *v_opts, + const struct net_bridge_port *p, u16 flags, bool dump_stats) { @@ -1842,7 +1843,7 @@ static bool br_vlan_fill_vids(struct sk_buff *skb, u16 vid, u16 vid_range, goto out_err; if (v_opts) { - if (!br_vlan_opts_fill(skb, v_opts)) + if (!br_vlan_opts_fill(skb, v_opts, p)) goto out_err; if (dump_stats && !br_vlan_stats_fill(skb, v_opts)) @@ -1925,7 +1926,7 @@ void br_vlan_notify(const struct net_bridge *br, goto out_kfree; } - if (!br_vlan_fill_vids(skb, vid, vid_range, v, flags, false)) + if (!br_vlan_fill_vids(skb, vid, vid_range, v, p, flags, false)) goto out_err; nlmsg_end(skb, nlh); @@ -2030,7 +2031,7 @@ static int br_vlan_dump_dev(const struct net_device *dev, if (!br_vlan_fill_vids(skb, range_start->vid, range_end->vid, range_start, - vlan_flags, dump_stats)) { + p, vlan_flags, dump_stats)) { err = -EMSGSIZE; break; } @@ -2056,7 +2057,7 @@ update_end: else if (!dump_global && !br_vlan_fill_vids(skb, range_start->vid, range_end->vid, range_start, - br_vlan_flags(range_start, pvid), + p, br_vlan_flags(range_start, pvid), dump_stats)) err = -EMSGSIZE; } @@ -2131,6 +2132,8 @@ static const struct nla_policy br_vlan_db_policy[BRIDGE_VLANDB_ENTRY_MAX + 1] = [BRIDGE_VLANDB_ENTRY_STATE] = { .type = NLA_U8 }, [BRIDGE_VLANDB_ENTRY_TUNNEL_INFO] = { .type = NLA_NESTED }, [BRIDGE_VLANDB_ENTRY_MCAST_ROUTER] = { .type = NLA_U8 }, + [BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS] = { .type = NLA_REJECT }, + [BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS] = { .type = NLA_U32 }, }; static int br_vlan_rtm_process_one(struct net_device *dev, diff --git a/net/bridge/br_vlan_options.c b/net/bridge/br_vlan_options.c index a2724d03278c..e378c2f3a9e2 100644 --- a/net/bridge/br_vlan_options.c +++ b/net/bridge/br_vlan_options.c @@ -48,7 +48,8 @@ bool br_vlan_opts_eq_range(const struct net_bridge_vlan *v_curr, curr_mc_rtr == range_mc_rtr; } -bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v) +bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v, + const struct net_bridge_port *p) { if (nla_put_u8(skb, BRIDGE_VLANDB_ENTRY_STATE, br_vlan_get_state(v)) || !__vlan_tun_put(skb, v)) @@ -58,6 +59,12 @@ bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v) if (nla_put_u8(skb, BRIDGE_VLANDB_ENTRY_MCAST_ROUTER, br_vlan_multicast_router(v))) return false; + if (p && !br_multicast_port_ctx_vlan_disabled(&v->port_mcast_ctx) && + (nla_put_u32(skb, BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS, + br_multicast_ngroups_get(&v->port_mcast_ctx)) || + nla_put_u32(skb, BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS, + br_multicast_ngroups_get_max(&v->port_mcast_ctx)))) + return false; #endif return true; @@ -70,6 +77,8 @@ size_t br_vlan_opts_nl_size(void) + nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_TINFO_ID */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) /* BRIDGE_VLANDB_ENTRY_MCAST_ROUTER */ + + nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS */ + + nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS */ #endif + 0; } @@ -212,6 +221,22 @@ static int br_vlan_process_one_opts(const struct net_bridge *br, return err; *changed = true; } + if (tb[BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS]) { + u32 val; + + if (!p) { + NL_SET_ERR_MSG_MOD(extack, "Can't set mcast_max_groups for non-port vlans"); + return -EINVAL; + } + if (br_multicast_port_ctx_vlan_disabled(&v->port_mcast_ctx)) { + NL_SET_ERR_MSG_MOD(extack, "Multicast snooping disabled on this VLAN"); + return -EINVAL; + } + + val = nla_get_u32(tb[BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS]); + br_multicast_ngroups_set_max(&v->port_mcast_ctx, val); + *changed = true; + } #endif return 0; diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 5c5dd437f1c2..71056ee84773 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -212,7 +212,7 @@ static int nf_ct_br_ip_check(const struct sk_buff *skb) iph->version != 4) return -1; - len = ntohs(iph->tot_len); + len = skb_ip_totlen(skb); if (skb->len < nhoff + len || len < (iph->ihl * 4)) return -1; @@ -256,7 +256,7 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct iphdr))) return NF_ACCEPT; - len = ntohs(ip_hdr(skb)->tot_len); + len = skb_ip_totlen(skb); if (pskb_trim_rcsum(skb, len)) return NF_ACCEPT; diff --git a/net/can/gw.c b/net/can/gw.c index 23a3d89cad81..37528826935e 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -1139,6 +1139,13 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, if (gwj->dst.dev->type != ARPHRD_CAN) goto out; + /* is sending the skb back to the incoming interface intended? */ + if (gwj->src.dev == gwj->dst.dev && + !(gwj->flags & CGW_FLAGS_CAN_IIF_TX_OK)) { + err = -EINVAL; + goto out; + } + ASSERT_RTNL(); err = cgw_register_filter(net, gwj); diff --git a/net/can/isotp.c b/net/can/isotp.c index 608f8c24ae46..9bc344851704 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -140,7 +140,7 @@ struct isotp_sock { canid_t rxid; ktime_t tx_gap; ktime_t lastrxcf_tstamp; - struct hrtimer rxtimer, txtimer; + struct hrtimer rxtimer, txtimer, txfrtimer; struct can_isotp_options opt; struct can_isotp_fc_options rxfc, txfc; struct can_isotp_ll_options ll; @@ -871,7 +871,7 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data) } /* start timer to send next consecutive frame with correct delay */ - hrtimer_start(&so->txtimer, so->tx_gap, HRTIMER_MODE_REL_SOFT); + hrtimer_start(&so->txfrtimer, so->tx_gap, HRTIMER_MODE_REL_SOFT); } static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) @@ -879,49 +879,39 @@ static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, txtimer); struct sock *sk = &so->sk; - enum hrtimer_restart restart = HRTIMER_NORESTART; - switch (so->tx.state) { - case ISOTP_SENDING: + /* don't handle timeouts in IDLE state */ + if (so->tx.state == ISOTP_IDLE) + return HRTIMER_NORESTART; - /* cfecho should be consumed by isotp_rcv_echo() here */ - if (!so->cfecho) { - /* start timeout for unlikely lost echo skb */ - hrtimer_set_expires(&so->txtimer, - ktime_add(ktime_get(), - ktime_set(ISOTP_ECHO_TIMEOUT, 0))); - restart = HRTIMER_RESTART; + /* we did not get any flow control or echo frame in time */ - /* push out the next consecutive frame */ - isotp_send_cframe(so); - break; - } + /* report 'communication error on send' */ + sk->sk_err = ECOMM; + if (!sock_flag(sk, SOCK_DEAD)) + sk_error_report(sk); - /* cfecho has not been cleared in isotp_rcv_echo() */ - pr_notice_once("can-isotp: cfecho %08X timeout\n", so->cfecho); - fallthrough; - - case ISOTP_WAIT_FC: - case ISOTP_WAIT_FIRST_FC: + /* reset tx state */ + so->tx.state = ISOTP_IDLE; + wake_up_interruptible(&so->wait); - /* we did not get any flow control frame in time */ + return HRTIMER_NORESTART; +} - /* report 'communication error on send' */ - sk->sk_err = ECOMM; - if (!sock_flag(sk, SOCK_DEAD)) - sk_error_report(sk); +static enum hrtimer_restart isotp_txfr_timer_handler(struct hrtimer *hrtimer) +{ + struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, + txfrtimer); - /* reset tx state */ - so->tx.state = ISOTP_IDLE; - wake_up_interruptible(&so->wait); - break; + /* start echo timeout handling and cover below protocol error */ + hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), + HRTIMER_MODE_REL_SOFT); - default: - WARN_ONCE(1, "can-isotp: tx timer state %08X cfecho %08X\n", - so->tx.state, so->cfecho); - } + /* cfecho should be consumed by isotp_rcv_echo() here */ + if (so->tx.state == ISOTP_SENDING && !so->cfecho) + isotp_send_cframe(so); - return restart; + return HRTIMER_NORESTART; } static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) @@ -1162,6 +1152,10 @@ static int isotp_release(struct socket *sock) /* wait for complete transmission of current pdu */ wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + /* force state machines to be idle also when a signal occurred */ + so->tx.state = ISOTP_IDLE; + so->rx.state = ISOTP_IDLE; + spin_lock(&isotp_notifier_lock); while (isotp_busy_notifier == so) { spin_unlock(&isotp_notifier_lock); @@ -1194,6 +1188,7 @@ static int isotp_release(struct socket *sock) } } + hrtimer_cancel(&so->txfrtimer); hrtimer_cancel(&so->txtimer); hrtimer_cancel(&so->rxtimer); @@ -1225,6 +1220,9 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (len < ISOTP_MIN_NAMELEN) return -EINVAL; + if (addr->can_family != AF_CAN) + return -EINVAL; + /* sanitize tx CAN identifier */ if (tx_id & CAN_EFF_FLAG) tx_id &= (CAN_EFF_FLAG | CAN_EFF_MASK); @@ -1597,6 +1595,8 @@ static int isotp_init(struct sock *sk) so->rxtimer.function = isotp_rx_timer_handler; hrtimer_init(&so->txtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); so->txtimer.function = isotp_tx_timer_handler; + hrtimer_init(&so->txfrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); + so->txfrtimer.function = isotp_txfr_timer_handler; init_waitqueue_head(&so->wait); spin_lock_init(&so->rx_lock); diff --git a/net/can/j1939/address-claim.c b/net/can/j1939/address-claim.c index f33c47327927..ca4ad6cdd5cb 100644 --- a/net/can/j1939/address-claim.c +++ b/net/can/j1939/address-claim.c @@ -165,6 +165,46 @@ static void j1939_ac_process(struct j1939_priv *priv, struct sk_buff *skb) * leaving this function. */ ecu = j1939_ecu_get_by_name_locked(priv, name); + + if (ecu && ecu->addr == skcb->addr.sa) { + /* The ISO 11783-5 standard, in "4.5.2 - Address claim + * requirements", states: + * d) No CF shall begin, or resume, transmission on the + * network until 250 ms after it has successfully claimed + * an address except when responding to a request for + * address-claimed. + * + * But "Figure 6" and "Figure 7" in "4.5.4.2 - Address-claim + * prioritization" show that the CF begins the transmission + * after 250 ms from the first AC (address-claimed) message + * even if it sends another AC message during that time window + * to resolve the address contention with another CF. + * + * As stated in "4.4.2.3 - Address-claimed message": + * In order to successfully claim an address, the CF sending + * an address claimed message shall not receive a contending + * claim from another CF for at least 250 ms. + * + * As stated in "4.4.3.2 - NAME management (NM) message": + * 1) A commanding CF can + * d) request that a CF with a specified NAME transmit + * the address-claimed message with its current NAME. + * 2) A target CF shall + * d) send an address-claimed message in response to a + * request for a matching NAME + * + * Taking the above arguments into account, the 250 ms wait is + * requested only during network initialization. + * + * Do not restart the timer on AC message if both the NAME and + * the address match and so if the address has already been + * claimed (timer has expired) or the AC message has been sent + * to resolve the contention with another CF (timer is still + * running). + */ + goto out_ecu_put; + } + if (!ecu && j1939_address_is_unicast(skcb->addr.sa)) ecu = j1939_ecu_create_locked(priv, name); diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index 5c722b55fe23..fce9b9ebf13f 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -1092,10 +1092,6 @@ static bool j1939_session_deactivate(struct j1939_session *session) bool active; j1939_session_list_lock(priv); - /* This function should be called with a session ref-count of at - * least 2. - */ - WARN_ON_ONCE(kref_read(&session->kref) < 2); active = j1939_session_deactivate_locked(session); j1939_session_list_unlock(priv); diff --git a/net/can/raw.c b/net/can/raw.c index 81071cdb0301..f64469b98260 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -132,8 +132,8 @@ static void raw_rcv(struct sk_buff *oskb, void *data) return; /* make sure to not pass oversized frames to the socket */ - if ((can_is_canfd_skb(oskb) && !ro->fd_frames && !ro->xl_frames) || - (can_is_canxl_skb(oskb) && !ro->xl_frames)) + if ((!ro->fd_frames && can_is_canfd_skb(oskb)) || + (!ro->xl_frames && can_is_canxl_skb(oskb))) return; /* eliminate multiple filter matches for the same skb */ @@ -523,6 +523,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, struct can_filter sfilter; /* single filter */ struct net_device *dev = NULL; can_err_mask_t err_mask = 0; + int fd_frames; int count = 0; int err = 0; @@ -664,12 +665,17 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, break; case CAN_RAW_FD_FRAMES: - if (optlen != sizeof(ro->fd_frames)) + if (optlen != sizeof(fd_frames)) return -EINVAL; - if (copy_from_sockptr(&ro->fd_frames, optval, optlen)) + if (copy_from_sockptr(&fd_frames, optval, optlen)) return -EFAULT; + /* Enabling CAN XL includes CAN FD */ + if (ro->xl_frames && !fd_frames) + return -EINVAL; + + ro->fd_frames = fd_frames; break; case CAN_RAW_XL_FRAMES: @@ -679,6 +685,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, if (copy_from_sockptr(&ro->xl_frames, optval, optlen)) return -EFAULT; + /* Enabling CAN XL includes CAN FD */ + if (ro->xl_frames) + ro->fd_frames = ro->xl_frames; break; case CAN_RAW_JOIN_FILTERS: @@ -786,6 +795,25 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, return 0; } +static bool raw_bad_txframe(struct raw_sock *ro, struct sk_buff *skb, int mtu) +{ + /* Classical CAN -> no checks for flags and device capabilities */ + if (can_is_can_skb(skb)) + return false; + + /* CAN FD -> needs to be enabled and a CAN FD or CAN XL device */ + if (ro->fd_frames && can_is_canfd_skb(skb) && + (mtu == CANFD_MTU || can_is_canxl_dev_mtu(mtu))) + return false; + + /* CAN XL -> needs to be enabled and a CAN XL device */ + if (ro->xl_frames && can_is_canxl_skb(skb) && + can_is_canxl_dev_mtu(mtu)) + return false; + + return true; +} + static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; @@ -833,20 +861,8 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) goto free_skb; err = -EINVAL; - if (ro->xl_frames && can_is_canxl_dev_mtu(dev->mtu)) { - /* CAN XL, CAN FD and Classical CAN */ - if (!can_is_canxl_skb(skb) && !can_is_canfd_skb(skb) && - !can_is_can_skb(skb)) - goto free_skb; - } else if (ro->fd_frames && dev->mtu == CANFD_MTU) { - /* CAN FD and Classical CAN */ - if (!can_is_canfd_skb(skb) && !can_is_can_skb(skb)) - goto free_skb; - } else { - /* Classical CAN */ - if (!can_is_can_skb(skb)) - goto free_skb; - } + if (raw_bad_txframe(ro, skb, dev->mtu)) + goto free_skb; sockcm_init(&sockc, sk); if (msg->msg_controllen) { diff --git a/net/core/dev.c b/net/core/dev.c index 9ac0eeb2c8cd..7307a0c15c9f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3002,6 +3002,8 @@ void netif_set_tso_max_size(struct net_device *dev, unsigned int size) dev->tso_max_size = min(GSO_MAX_SIZE, size); if (size < READ_ONCE(dev->gso_max_size)) netif_set_gso_max_size(dev, size); + if (size < READ_ONCE(dev->gso_ipv4_max_size)) + netif_set_gso_ipv4_max_size(dev, size); } EXPORT_SYMBOL(netif_set_tso_max_size); @@ -10615,6 +10617,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->gso_max_size = GSO_LEGACY_MAX_SIZE; dev->gso_max_segs = GSO_MAX_SEGS; dev->gro_max_size = GRO_LEGACY_MAX_SIZE; + dev->gso_ipv4_max_size = GSO_LEGACY_MAX_SIZE; + dev->gro_ipv4_max_size = GRO_LEGACY_MAX_SIZE; dev->tso_max_size = TSO_LEGACY_MAX_SIZE; dev->tso_max_segs = TSO_MAX_SEGS; dev->upper_level = 1; diff --git a/net/core/dev.h b/net/core/dev.h index 814ed5b7b960..e075e198092c 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -9,6 +9,7 @@ struct net_device; struct netdev_bpf; struct netdev_phys_item_id; struct netlink_ext_ack; +struct cpumask; /* Random bits of netdevice that don't need to be exposed */ #define FLOW_LIMIT_HISTORY (1 << 7) /* must be ^2 and !overflow buckets */ @@ -100,6 +101,8 @@ static inline void netif_set_gso_max_size(struct net_device *dev, { /* dev->gso_max_size is read locklessly from sk_setup_caps() */ WRITE_ONCE(dev->gso_max_size, size); + if (size <= GSO_LEGACY_MAX_SIZE) + WRITE_ONCE(dev->gso_ipv4_max_size, size); } static inline void netif_set_gso_max_segs(struct net_device *dev, @@ -114,6 +117,23 @@ static inline void netif_set_gro_max_size(struct net_device *dev, { /* This pairs with the READ_ONCE() in skb_gro_receive() */ WRITE_ONCE(dev->gro_max_size, size); + if (size <= GRO_LEGACY_MAX_SIZE) + WRITE_ONCE(dev->gro_ipv4_max_size, size); } +static inline void netif_set_gso_ipv4_max_size(struct net_device *dev, + unsigned int size) +{ + /* dev->gso_ipv4_max_size is read locklessly from sk_setup_caps() */ + WRITE_ONCE(dev->gso_ipv4_max_size, size); +} + +static inline void netif_set_gro_ipv4_max_size(struct net_device *dev, + unsigned int size) +{ + /* This pairs with the READ_ONCE() in skb_gro_receive() */ + WRITE_ONCE(dev->gro_ipv4_max_size, size); +} + +int rps_cpumask_housekeeping(struct cpumask *mask); #endif diff --git a/net/core/gro.c b/net/core/gro.c index 506f83d715f8..a606705a0859 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -162,16 +162,27 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) struct sk_buff *lp; int segs; - /* pairs with WRITE_ONCE() in netif_set_gro_max_size() */ - gro_max_size = READ_ONCE(p->dev->gro_max_size); + /* Do not splice page pool based packets w/ non-page pool + * packets. This can result in reference count issues as page + * pool pages will not decrement the reference count and will + * instead be immediately returned to the pool or have frag + * count decremented. + */ + if (p->pp_recycle != skb->pp_recycle) + return -ETOOMANYREFS; + + /* pairs with WRITE_ONCE() in netif_set_gro(_ipv4)_max_size() */ + gro_max_size = p->protocol == htons(ETH_P_IPV6) ? + READ_ONCE(p->dev->gro_max_size) : + READ_ONCE(p->dev->gro_ipv4_max_size); if (unlikely(p->len + len >= gro_max_size || NAPI_GRO_CB(skb)->flush)) return -E2BIG; if (unlikely(p->len + len >= GRO_LEGACY_MAX_SIZE)) { - if (p->protocol != htons(ETH_P_IPV6) || - skb_headroom(p) < sizeof(struct hop_jumbo_hdr) || - ipv6_hdr(p)->nexthdr != IPPROTO_TCP || + if (NAPI_GRO_CB(skb)->proto != IPPROTO_TCP || + (p->protocol == htons(ETH_P_IPV6) && + skb_headroom(p) < sizeof(struct hop_jumbo_hdr)) || p->encapsulation) return -E2BIG; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index f00a79fc301b..6798f6d2423b 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -269,7 +269,7 @@ static int neigh_forced_gc(struct neigh_table *tbl) (n->nud_state == NUD_NOARP) || (tbl->is_multicast && tbl->is_multicast(n->primary_key)) || - time_after(tref, n->updated)) + !time_in_range(n->updated, tref, jiffies)) remove = true; write_unlock(&n->lock); @@ -289,7 +289,17 @@ static int neigh_forced_gc(struct neigh_table *tbl) static void neigh_add_timer(struct neighbour *n, unsigned long when) { + /* Use safe distance from the jiffies - LONG_MAX point while timer + * is running in DELAY/PROBE state but still show to user space + * large times in the past. + */ + unsigned long mint = jiffies - (LONG_MAX - 86400 * HZ); + neigh_hold(n); + if (!time_in_range(n->confirmed, mint, jiffies)) + n->confirmed = mint; + if (time_before(n->used, n->confirmed)) + n->used = n->confirmed; if (unlikely(mod_timer(&n->timer, when))) { printk("NEIGH: BUG, double timer add, state is %x\n", n->nud_state); @@ -1001,12 +1011,14 @@ static void neigh_periodic_work(struct work_struct *work) goto next_elt; } - if (time_before(n->used, n->confirmed)) + if (time_before(n->used, n->confirmed) && + time_is_before_eq_jiffies(n->confirmed)) n->used = n->confirmed; if (refcount_read(&n->refcnt) == 1 && (state == NUD_FAILED || - time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { + !time_in_range_open(jiffies, n->used, + n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { *np = n->next; neigh_mark_dead(n); write_unlock(&n->lock); @@ -1662,11 +1674,21 @@ static void neigh_proxy_process(struct timer_list *t) spin_unlock(&tbl->proxy_queue.lock); } +static unsigned long neigh_proxy_delay(struct neigh_parms *p) +{ + /* If proxy_delay is zero, do not call get_random_u32_below() + * as it is undefined behavior. + */ + unsigned long proxy_delay = NEIGH_VAR(p, PROXY_DELAY); + + return proxy_delay ? + jiffies + get_random_u32_below(proxy_delay) : jiffies; +} + void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, struct sk_buff *skb) { - unsigned long sched_next = jiffies + - get_random_u32_below(NEIGH_VAR(p, PROXY_DELAY)); + unsigned long sched_next = neigh_proxy_delay(p); if (p->qlen > NEIGH_VAR(p, PROXY_QLEN)) { kfree_skb(skb); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index ca55dd747d6c..4b361ac6a252 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -831,42 +831,18 @@ static ssize_t show_rps_map(struct netdev_rx_queue *queue, char *buf) return len < PAGE_SIZE ? len : -EINVAL; } -static ssize_t store_rps_map(struct netdev_rx_queue *queue, - const char *buf, size_t len) +static int netdev_rx_queue_set_rps_mask(struct netdev_rx_queue *queue, + cpumask_var_t mask) { - struct rps_map *old_map, *map; - cpumask_var_t mask; - int err, cpu, i; static DEFINE_MUTEX(rps_map_mutex); - - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - - if (!alloc_cpumask_var(&mask, GFP_KERNEL)) - return -ENOMEM; - - err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); - if (err) { - free_cpumask_var(mask); - return err; - } - - if (!cpumask_empty(mask)) { - cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); - cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_WQ)); - if (cpumask_empty(mask)) { - free_cpumask_var(mask); - return -EINVAL; - } - } + struct rps_map *old_map, *map; + int cpu, i; map = kzalloc(max_t(unsigned int, RPS_MAP_SIZE(cpumask_weight(mask)), L1_CACHE_BYTES), GFP_KERNEL); - if (!map) { - free_cpumask_var(mask); + if (!map) return -ENOMEM; - } i = 0; for_each_cpu_and(cpu, mask, cpu_online_mask) @@ -893,9 +869,45 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, if (old_map) kfree_rcu(old_map, rcu); + return 0; +} +int rps_cpumask_housekeeping(struct cpumask *mask) +{ + if (!cpumask_empty(mask)) { + cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); + cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_WQ)); + if (cpumask_empty(mask)) + return -EINVAL; + } + return 0; +} + +static ssize_t store_rps_map(struct netdev_rx_queue *queue, + const char *buf, size_t len) +{ + cpumask_var_t mask; + int err; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); + if (err) + goto out; + + err = rps_cpumask_housekeeping(mask); + if (err) + goto out; + + err = netdev_rx_queue_set_rps_mask(queue, mask); + +out: free_cpumask_var(mask); - return len; + return err ? : len; } static ssize_t show_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, @@ -1071,6 +1083,13 @@ static int rx_queue_add_kobject(struct net_device *dev, int index) goto err; } +#if IS_ENABLED(CONFIG_RPS) && IS_ENABLED(CONFIG_SYSCTL) + if (!cpumask_empty(&rps_default_mask)) { + error = netdev_rx_queue_set_rps_mask(queue, &rps_default_mask); + if (error) + goto err; + } +#endif kobject_uevent(kobj, KOBJ_ADD); return error; diff --git a/net/core/net-traces.c b/net/core/net-traces.c index ee7006bbe49b..805b7385dd8d 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -41,6 +41,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_add); EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_external_learn_add); EXPORT_TRACEPOINT_SYMBOL_GPL(fdb_delete); EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_update); +EXPORT_TRACEPOINT_SYMBOL_GPL(br_mdb_full); #endif #if IS_ENABLED(CONFIG_PAGE_POOL) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 9b203d8660e4..193c18799865 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -511,8 +511,8 @@ static void page_pool_return_page(struct page_pool *pool, struct page *page) static bool page_pool_recycle_in_ring(struct page_pool *pool, struct page *page) { int ret; - /* BH protection not needed if current is serving softirq */ - if (in_serving_softirq()) + /* BH protection not needed if current is softirq */ + if (in_softirq()) ret = ptr_ring_produce(&pool->ring, page); else ret = ptr_ring_produce_bh(&pool->ring, page); @@ -570,7 +570,7 @@ __page_pool_put_page(struct page_pool *pool, struct page *page, page_pool_dma_sync_for_device(pool, page, dma_sync_size); - if (allow_direct && in_serving_softirq() && + if (allow_direct && in_softirq() && page_pool_recycle_in_cache(page, pool)) return NULL; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 64289bc98887..5d8eb57867a9 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -58,7 +58,7 @@ #include "dev.h" #define RTNL_MAX_TYPE 50 -#define RTNL_SLAVE_MAX_TYPE 40 +#define RTNL_SLAVE_MAX_TYPE 42 struct rtnl_link { rtnl_doit_func doit; @@ -1074,6 +1074,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_GSO_MAX_SEGS */ + nla_total_size(4) /* IFLA_GSO_MAX_SIZE */ + nla_total_size(4) /* IFLA_GRO_MAX_SIZE */ + + nla_total_size(4) /* IFLA_GSO_IPV4_MAX_SIZE */ + + nla_total_size(4) /* IFLA_GRO_IPV4_MAX_SIZE */ + nla_total_size(4) /* IFLA_TSO_MAX_SIZE */ + nla_total_size(4) /* IFLA_TSO_MAX_SEGS */ + nla_total_size(1) /* IFLA_OPERSTATE */ @@ -1807,6 +1809,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, nla_put_u32(skb, IFLA_GSO_MAX_SEGS, dev->gso_max_segs) || nla_put_u32(skb, IFLA_GSO_MAX_SIZE, dev->gso_max_size) || nla_put_u32(skb, IFLA_GRO_MAX_SIZE, dev->gro_max_size) || + nla_put_u32(skb, IFLA_GSO_IPV4_MAX_SIZE, dev->gso_ipv4_max_size) || + nla_put_u32(skb, IFLA_GRO_IPV4_MAX_SIZE, dev->gro_ipv4_max_size) || nla_put_u32(skb, IFLA_TSO_MAX_SIZE, dev->tso_max_size) || nla_put_u32(skb, IFLA_TSO_MAX_SEGS, dev->tso_max_segs) || #ifdef CONFIG_RPS @@ -1968,6 +1972,8 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_TSO_MAX_SIZE] = { .type = NLA_REJECT }, [IFLA_TSO_MAX_SEGS] = { .type = NLA_REJECT }, [IFLA_ALLMULTI] = { .type = NLA_REJECT }, + [IFLA_GSO_IPV4_MAX_SIZE] = { .type = NLA_U32 }, + [IFLA_GRO_IPV4_MAX_SIZE] = { .type = NLA_U32 }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -2883,6 +2889,29 @@ static int do_setlink(const struct sk_buff *skb, } } + if (tb[IFLA_GSO_IPV4_MAX_SIZE]) { + u32 max_size = nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]); + + if (max_size > dev->tso_max_size) { + err = -EINVAL; + goto errout; + } + + if (dev->gso_ipv4_max_size ^ max_size) { + netif_set_gso_ipv4_max_size(dev, max_size); + status |= DO_SETLINK_MODIFIED; + } + } + + if (tb[IFLA_GRO_IPV4_MAX_SIZE]) { + u32 gro_max_size = nla_get_u32(tb[IFLA_GRO_IPV4_MAX_SIZE]); + + if (dev->gro_ipv4_max_size ^ gro_max_size) { + netif_set_gro_ipv4_max_size(dev, gro_max_size); + status |= DO_SETLINK_MODIFIED; + } + } + if (tb[IFLA_OPERSTATE]) set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE])); @@ -3325,6 +3354,10 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, netif_set_gso_max_segs(dev, nla_get_u32(tb[IFLA_GSO_MAX_SEGS])); if (tb[IFLA_GRO_MAX_SIZE]) netif_set_gro_max_size(dev, nla_get_u32(tb[IFLA_GRO_MAX_SIZE])); + if (tb[IFLA_GSO_IPV4_MAX_SIZE]) + netif_set_gso_ipv4_max_size(dev, nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE])); + if (tb[IFLA_GRO_IPV4_MAX_SIZE]) + netif_set_gro_ipv4_max_size(dev, nla_get_u32(tb[IFLA_GRO_IPV4_MAX_SIZE])); return dev; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index bb79b4cb89db..13ea10cf8544 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -84,11 +84,39 @@ #include "dev.h" #include "sock_destructor.h" -struct kmem_cache *skbuff_head_cache __ro_after_init; +struct kmem_cache *skbuff_cache __ro_after_init; static struct kmem_cache *skbuff_fclone_cache __ro_after_init; #ifdef CONFIG_SKB_EXTENSIONS static struct kmem_cache *skbuff_ext_cache __ro_after_init; #endif + +/* skb_small_head_cache and related code is only supported + * for CONFIG_SLAB and CONFIG_SLUB. + * As soon as SLOB is removed from the kernel, we can clean up this. + */ +#if !defined(CONFIG_SLOB) +# define HAVE_SKB_SMALL_HEAD_CACHE 1 +#endif + +#ifdef HAVE_SKB_SMALL_HEAD_CACHE +static struct kmem_cache *skb_small_head_cache __ro_after_init; + +#define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(MAX_TCP_HEADER) + +/* We want SKB_SMALL_HEAD_CACHE_SIZE to not be a power of two. + * This should ensure that SKB_SMALL_HEAD_HEADROOM is a unique + * size, and we can differentiate heads from skb_small_head_cache + * vs system slabs by looking at their size (skb_end_offset()). + */ +#define SKB_SMALL_HEAD_CACHE_SIZE \ + (is_power_of_2(SKB_SMALL_HEAD_SIZE) ? \ + (SKB_SMALL_HEAD_SIZE + L1_CACHE_BYTES) : \ + SKB_SMALL_HEAD_SIZE) + +#define SKB_SMALL_HEAD_HEADROOM \ + SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) +#endif /* HAVE_SKB_SMALL_HEAD_CACHE */ + int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS; EXPORT_SYMBOL(sysctl_max_skb_frags); @@ -257,7 +285,7 @@ static struct sk_buff *napi_skb_cache_get(void) struct sk_buff *skb; if (unlikely(!nc->skb_count)) { - nc->skb_count = kmem_cache_alloc_bulk(skbuff_head_cache, + nc->skb_count = kmem_cache_alloc_bulk(skbuff_cache, GFP_ATOMIC, NAPI_SKB_CACHE_BULK, nc->skb_cache); @@ -266,7 +294,7 @@ static struct sk_buff *napi_skb_cache_get(void) } skb = nc->skb_cache[--nc->skb_count]; - kasan_unpoison_object_data(skbuff_head_cache, skb); + kasan_unpoison_object_data(skbuff_cache, skb); return skb; } @@ -324,7 +352,7 @@ struct sk_buff *slab_build_skb(void *data) struct sk_buff *skb; unsigned int size; - skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; @@ -375,7 +403,7 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; - skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; @@ -478,17 +506,37 @@ EXPORT_SYMBOL(napi_build_skb); * may be used. Otherwise, the packet data may be discarded until enough * memory is free */ -static void *kmalloc_reserve(size_t size, gfp_t flags, int node, +static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node, bool *pfmemalloc) { - void *obj; bool ret_pfmemalloc = false; + unsigned int obj_size; + void *obj; + obj_size = SKB_HEAD_ALIGN(*size); +#ifdef HAVE_SKB_SMALL_HEAD_CACHE + if (obj_size <= SKB_SMALL_HEAD_CACHE_SIZE && + !(flags & KMALLOC_NOT_NORMAL_BITS)) { + + /* skb_small_head_cache has non power of two size, + * likely forcing SLUB to use order-3 pages. + * We deliberately attempt a NOMEMALLOC allocation only. + */ + obj = kmem_cache_alloc_node(skb_small_head_cache, + flags | __GFP_NOMEMALLOC | __GFP_NOWARN, + node); + if (obj) { + *size = SKB_SMALL_HEAD_CACHE_SIZE; + goto out; + } + } +#endif + *size = obj_size = kmalloc_size_roundup(obj_size); /* * Try a regular allocation, when that fails and we're not entitled * to the reserves, fail. */ - obj = kmalloc_node_track_caller(size, + obj = kmalloc_node_track_caller(obj_size, flags | __GFP_NOMEMALLOC | __GFP_NOWARN, node); if (obj || !(gfp_pfmemalloc_allowed(flags))) @@ -496,7 +544,7 @@ static void *kmalloc_reserve(size_t size, gfp_t flags, int node, /* Try again but now we are using pfmemalloc reserves */ ret_pfmemalloc = true; - obj = kmalloc_node_track_caller(size, flags, node); + obj = kmalloc_node_track_caller(obj_size, flags, node); out: if (pfmemalloc) @@ -533,12 +581,11 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, { struct kmem_cache *cache; struct sk_buff *skb; - unsigned int osize; bool pfmemalloc; u8 *data; cache = (flags & SKB_ALLOC_FCLONE) - ? skbuff_fclone_cache : skbuff_head_cache; + ? skbuff_fclone_cache : skbuff_cache; if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) gfp_mask |= __GFP_MEMALLOC; @@ -558,18 +605,14 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, * aligned memory blocks, unless SLUB/SLAB debug is enabled. * Both skb->head and skb_shared_info are cache line aligned. */ - size = SKB_DATA_ALIGN(size); - size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - osize = kmalloc_size_roundup(size); - data = kmalloc_reserve(osize, gfp_mask, node, &pfmemalloc); + data = kmalloc_reserve(&size, gfp_mask, node, &pfmemalloc); if (unlikely(!data)) goto nodata; /* kmalloc_size_roundup() might give us more room than requested. * Put skb_shared_info exactly at the end of allocated zone, * to allow max possible filling before reallocation. */ - size = SKB_WITH_OVERHEAD(osize); - prefetchw(data + size); + prefetchw(data + SKB_WITH_OVERHEAD(size)); /* * Only clear those fields we need to clear, not those that we will @@ -577,7 +620,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, * the tail pointer in struct sk_buff! */ memset(skb, 0, offsetof(struct sk_buff, tail)); - __build_skb_around(skb, data, osize); + __build_skb_around(skb, data, size); skb->pfmemalloc = pfmemalloc; if (flags & SKB_ALLOC_FCLONE) { @@ -632,8 +675,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, goto skb_success; } - len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - len = SKB_DATA_ALIGN(len); + len = SKB_HEAD_ALIGN(len); if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; @@ -732,8 +774,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, data = page_frag_alloc_1k(&nc->page_small, gfp_mask); pfmemalloc = NAPI_SMALL_PAGE_PFMEMALLOC(nc->page_small); } else { - len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - len = SKB_DATA_ALIGN(len); + len = SKB_HEAD_ALIGN(len); data = page_frag_alloc(&nc->page, len, gfp_mask); pfmemalloc = nc->page.pfmemalloc; @@ -809,6 +850,16 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data) return page_pool_return_skb_page(virt_to_page(data)); } +static void skb_kfree_head(void *head, unsigned int end_offset) +{ +#ifdef HAVE_SKB_SMALL_HEAD_CACHE + if (end_offset == SKB_SMALL_HEAD_HEADROOM) + kmem_cache_free(skb_small_head_cache, head); + else +#endif + kfree(head); +} + static void skb_free_head(struct sk_buff *skb) { unsigned char *head = skb->head; @@ -818,7 +869,7 @@ static void skb_free_head(struct sk_buff *skb) return; skb_free_frag(head); } else { - kfree(head); + skb_kfree_head(head, skb_end_offset(skb)); } } @@ -870,7 +921,7 @@ static void kfree_skbmem(struct sk_buff *skb) switch (skb->fclone) { case SKB_FCLONE_UNAVAILABLE: - kmem_cache_free(skbuff_head_cache, skb); + kmem_cache_free(skbuff_cache, skb); return; case SKB_FCLONE_ORIG: @@ -984,7 +1035,7 @@ static void kfree_skb_add_bulk(struct sk_buff *skb, sa->skb_array[sa->skb_count++] = skb; if (unlikely(sa->skb_count == KFREE_SKB_BULK_SIZE)) { - kmem_cache_free_bulk(skbuff_head_cache, KFREE_SKB_BULK_SIZE, + kmem_cache_free_bulk(skbuff_cache, KFREE_SKB_BULK_SIZE, sa->skb_array); sa->skb_count = 0; } @@ -1000,15 +1051,16 @@ kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason) while (segs) { struct sk_buff *next = segs->next; - if (__kfree_skb_reason(segs, reason)) + if (__kfree_skb_reason(segs, reason)) { + skb_poison_list(segs); kfree_skb_add_bulk(segs, &sa, reason); + } segs = next; } if (sa.skb_count) - kmem_cache_free_bulk(skbuff_head_cache, sa.skb_count, - sa.skb_array); + kmem_cache_free_bulk(skbuff_cache, sa.skb_count, sa.skb_array); } EXPORT_SYMBOL(kfree_skb_list_reason); @@ -1162,15 +1214,15 @@ static void napi_skb_cache_put(struct sk_buff *skb) struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); u32 i; - kasan_poison_object_data(skbuff_head_cache, skb); + kasan_poison_object_data(skbuff_cache, skb); nc->skb_cache[nc->skb_count++] = skb; if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++) - kasan_unpoison_object_data(skbuff_head_cache, + kasan_unpoison_object_data(skbuff_cache, nc->skb_cache[i]); - kmem_cache_free_bulk(skbuff_head_cache, NAPI_SKB_CACHE_HALF, + kmem_cache_free_bulk(skbuff_cache, NAPI_SKB_CACHE_HALF, nc->skb_cache + NAPI_SKB_CACHE_HALF); nc->skb_count = NAPI_SKB_CACHE_HALF; } @@ -1754,7 +1806,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - n = kmem_cache_alloc(skbuff_head_cache, gfp_mask); + n = kmem_cache_alloc(skbuff_cache, gfp_mask); if (!n) return NULL; @@ -1936,10 +1988,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - size = SKB_DATA_ALIGN(size); - size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - size = kmalloc_size_roundup(size); - data = kmalloc_reserve(size, gfp_mask, NUMA_NO_NODE, NULL); + data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) goto nodata; size = SKB_WITH_OVERHEAD(size); @@ -2002,7 +2051,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, return 0; nofrags: - kfree(data); + skb_kfree_head(data, size); nodata: return -ENOMEM; } @@ -4143,7 +4192,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, skb_shinfo(skb)->frag_list = NULL; - do { + while (list_skb) { nskb = list_skb; list_skb = list_skb->next; @@ -4189,8 +4238,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, if (skb_needs_linearize(nskb, features) && __skb_linearize(nskb)) goto err_linearize; - - } while (list_skb); + } skb->truesize = skb->truesize - delta_truesize; skb->data_len = skb->data_len - delta_len; @@ -4628,7 +4676,7 @@ static void skb_extensions_init(void) {} void __init skb_init(void) { - skbuff_head_cache = kmem_cache_create_usercopy("skbuff_head_cache", + skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache", sizeof(struct sk_buff), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, @@ -4640,6 +4688,19 @@ void __init skb_init(void) 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); +#ifdef HAVE_SKB_SMALL_HEAD_CACHE + /* usercopy should only access first SKB_SMALL_HEAD_HEADROOM bytes. + * struct skb_shared_info is located at the end of skb->head, + * and should not be copied to/from user. + */ + skb_small_head_cache = kmem_cache_create_usercopy("skbuff_small_head", + SKB_SMALL_HEAD_CACHE_SIZE, + 0, + SLAB_HWCACHE_ALIGN | SLAB_PANIC, + 0, + SKB_SMALL_HEAD_HEADROOM, + NULL); +#endif skb_extensions_init(); } @@ -5494,7 +5555,7 @@ void kfree_skb_partial(struct sk_buff *skb, bool head_stolen) { if (head_stolen) { skb_release_head_state(skb); - kmem_cache_free(skbuff_head_cache, skb); + kmem_cache_free(skbuff_cache, skb); } else { __kfree_skb(skb); } @@ -6288,10 +6349,7 @@ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off, if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - size = SKB_DATA_ALIGN(size); - size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - size = kmalloc_size_roundup(size); - data = kmalloc_reserve(size, gfp_mask, NUMA_NO_NODE, NULL); + data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM; size = SKB_WITH_OVERHEAD(size); @@ -6307,7 +6365,7 @@ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off, if (skb_cloned(skb)) { /* drop the old head gracefully */ if (skb_orphan_frags(skb, gfp_mask)) { - kfree(data); + skb_kfree_head(data, size); return -ENOMEM; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) @@ -6407,10 +6465,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - size = SKB_DATA_ALIGN(size); - size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - size = kmalloc_size_roundup(size); - data = kmalloc_reserve(size, gfp_mask, NUMA_NO_NODE, NULL); + data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM; size = SKB_WITH_OVERHEAD(size); @@ -6418,7 +6473,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, frags[0])); if (skb_orphan_frags(skb, gfp_mask)) { - kfree(data); + skb_kfree_head(data, size); return -ENOMEM; } shinfo = (struct skb_shared_info *)(data + size); @@ -6454,7 +6509,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, /* skb_frag_unref() is not needed here as shinfo->nr_frags = 0. */ if (skb_has_frag_list(skb)) kfree_skb_list(skb_shinfo(skb)->frag_list); - kfree(data); + skb_kfree_head(data, size); return -ENOMEM; } skb_release_data(skb, SKB_CONSUMED); diff --git a/net/core/sock.c b/net/core/sock.c index 7ba4891460ad..afbb02984d5f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1531,6 +1531,8 @@ set_sndbuf: ret = -EINVAL; break; } + if ((u8)val == SOCK_TXREHASH_DEFAULT) + val = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); /* Paired with READ_ONCE() in tcp_rtx_synack() */ WRITE_ONCE(sk->sk_txrehash, (u8)val); break; @@ -2373,17 +2375,22 @@ void sk_free_unlock_clone(struct sock *sk) } EXPORT_SYMBOL_GPL(sk_free_unlock_clone); -static void sk_trim_gso_size(struct sock *sk) +static u32 sk_dst_gso_max_size(struct sock *sk, struct dst_entry *dst) { - if (sk->sk_gso_max_size <= GSO_LEGACY_MAX_SIZE) - return; + bool is_ipv6 = false; + u32 max_size; + #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6 && - sk_is_tcp(sk) && - !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) - return; + is_ipv6 = (sk->sk_family == AF_INET6 && + !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)); #endif - sk->sk_gso_max_size = GSO_LEGACY_MAX_SIZE; + /* pairs with the WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */ + max_size = is_ipv6 ? READ_ONCE(dst->dev->gso_max_size) : + READ_ONCE(dst->dev->gso_ipv4_max_size); + if (max_size > GSO_LEGACY_MAX_SIZE && !sk_is_tcp(sk)) + max_size = GSO_LEGACY_MAX_SIZE; + + return max_size - (MAX_TCP_HEADER + 1); } void sk_setup_caps(struct sock *sk, struct dst_entry *dst) @@ -2403,10 +2410,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) sk->sk_route_caps &= ~NETIF_F_GSO_MASK; } else { sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; - /* pairs with the WRITE_ONCE() in netif_set_gso_max_size() */ - sk->sk_gso_max_size = READ_ONCE(dst->dev->gso_max_size); - sk_trim_gso_size(sk); - sk->sk_gso_max_size -= (MAX_TCP_HEADER + 1); + sk->sk_gso_max_size = sk_dst_gso_max_size(sk, dst); /* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */ max_segs = max_t(u32, READ_ONCE(dst->dev->gso_max_segs), 1); } @@ -3381,7 +3385,7 @@ void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer) } EXPORT_SYMBOL(sk_stop_timer_sync); -void sock_init_data(struct socket *sock, struct sock *sk) +void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid) { sk_init_common(sk); sk->sk_send_head = NULL; @@ -3401,11 +3405,10 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_type = sock->type; RCU_INIT_POINTER(sk->sk_wq, &sock->wq); sock->sk = sk; - sk->sk_uid = SOCK_INODE(sock)->i_uid; } else { RCU_INIT_POINTER(sk->sk_wq, NULL); - sk->sk_uid = make_kuid(sock_net(sk)->user_ns, 0); } + sk->sk_uid = uid; rwlock_init(&sk->sk_callback_lock); if (sk->sk_kern_sock) @@ -3453,7 +3456,6 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_pacing_rate = ~0UL; WRITE_ONCE(sk->sk_pacing_shift, 10); sk->sk_incoming_cpu = -1; - sk->sk_txrehash = SOCK_TXREHASH_DEFAULT; sk_rx_queue_clear(sk); /* @@ -3464,6 +3466,16 @@ void sock_init_data(struct socket *sock, struct sock *sk) refcount_set(&sk->sk_refcnt, 1); atomic_set(&sk->sk_drops, 0); } +EXPORT_SYMBOL(sock_init_data_uid); + +void sock_init_data(struct socket *sock, struct sock *sk) +{ + kuid_t uid = sock ? + SOCK_INODE(sock)->i_uid : + make_kuid(sock_net(sk)->user_ns, 0); + + sock_init_data_uid(sock, sk, uid); +} EXPORT_SYMBOL(sock_init_data); void lock_sock_nested(struct sock *sk, int subclass) diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 22fa2c5bc6ec..a68a7290a3b2 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1569,15 +1569,16 @@ void sock_map_unhash(struct sock *sk) psock = sk_psock(sk); if (unlikely(!psock)) { rcu_read_unlock(); - if (sk->sk_prot->unhash) - sk->sk_prot->unhash(sk); - return; + saved_unhash = READ_ONCE(sk->sk_prot)->unhash; + } else { + saved_unhash = psock->saved_unhash; + sock_map_remove_links(sk, psock); + rcu_read_unlock(); } - - saved_unhash = psock->saved_unhash; - sock_map_remove_links(sk, psock); - rcu_read_unlock(); - saved_unhash(sk); + if (WARN_ON_ONCE(saved_unhash == sock_map_unhash)) + return; + if (saved_unhash) + saved_unhash(sk); } EXPORT_SYMBOL_GPL(sock_map_unhash); @@ -1590,17 +1591,18 @@ void sock_map_destroy(struct sock *sk) psock = sk_psock_get(sk); if (unlikely(!psock)) { rcu_read_unlock(); - if (sk->sk_prot->destroy) - sk->sk_prot->destroy(sk); - return; + saved_destroy = READ_ONCE(sk->sk_prot)->destroy; + } else { + saved_destroy = psock->saved_destroy; + sock_map_remove_links(sk, psock); + rcu_read_unlock(); + sk_psock_stop(psock); + sk_psock_put(sk, psock); } - - saved_destroy = psock->saved_destroy; - sock_map_remove_links(sk, psock); - rcu_read_unlock(); - sk_psock_stop(psock); - sk_psock_put(sk, psock); - saved_destroy(sk); + if (WARN_ON_ONCE(saved_destroy == sock_map_destroy)) + return; + if (saved_destroy) + saved_destroy(sk); } EXPORT_SYMBOL_GPL(sock_map_destroy); @@ -1615,16 +1617,21 @@ void sock_map_close(struct sock *sk, long timeout) if (unlikely(!psock)) { rcu_read_unlock(); release_sock(sk); - return sk->sk_prot->close(sk, timeout); + saved_close = READ_ONCE(sk->sk_prot)->close; + } else { + saved_close = psock->saved_close; + sock_map_remove_links(sk, psock); + rcu_read_unlock(); + sk_psock_stop(psock); + release_sock(sk); + cancel_work_sync(&psock->work); + sk_psock_put(sk, psock); } - - saved_close = psock->saved_close; - sock_map_remove_links(sk, psock); - rcu_read_unlock(); - sk_psock_stop(psock); - release_sock(sk); - cancel_work_sync(&psock->work); - sk_psock_put(sk, psock); + /* Make sure we do not recurse. This is a bug. + * Leak the socket instead of crashing on a stack overflow. + */ + if (WARN_ON_ONCE(saved_close == sock_map_close)) + return; saved_close(sk, timeout); } EXPORT_SYMBOL_GPL(sock_map_close); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index e7b98162c632..7130e6d9e263 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -16,6 +16,7 @@ #include <linux/vmalloc.h> #include <linux/init.h> #include <linux/slab.h> +#include <linux/sched/isolation.h> #include <net/ip.h> #include <net/sock.h> @@ -45,7 +46,59 @@ EXPORT_SYMBOL(sysctl_fb_tunnels_only_for_init_net); int sysctl_devconf_inherit_init_net __read_mostly; EXPORT_SYMBOL(sysctl_devconf_inherit_init_net); +#if IS_ENABLED(CONFIG_NET_FLOW_LIMIT) || IS_ENABLED(CONFIG_RPS) +static void dump_cpumask(void *buffer, size_t *lenp, loff_t *ppos, + struct cpumask *mask) +{ + char kbuf[128]; + int len; + + if (*ppos || !*lenp) { + *lenp = 0; + return; + } + + len = min(sizeof(kbuf) - 1, *lenp); + len = scnprintf(kbuf, len, "%*pb", cpumask_pr_args(mask)); + if (!len) { + *lenp = 0; + return; + } + + if (len < *lenp) + kbuf[len++] = '\n'; + memcpy(buffer, kbuf, len); + *lenp = len; + *ppos += len; +} +#endif + #ifdef CONFIG_RPS +struct cpumask rps_default_mask; + +static int rps_default_mask_sysctl(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int err = 0; + + rtnl_lock(); + if (write) { + err = cpumask_parse(buffer, &rps_default_mask); + if (err) + goto done; + + err = rps_cpumask_housekeeping(&rps_default_mask); + if (err) + goto done; + } else { + dump_cpumask(buffer, lenp, ppos, &rps_default_mask); + } + +done: + rtnl_unlock(); + return err; +} + static int rps_sock_flow_sysctl(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -155,13 +208,6 @@ static int flow_limit_cpu_sysctl(struct ctl_table *table, int write, write_unlock: mutex_unlock(&flow_limit_update_mutex); } else { - char kbuf[128]; - - if (*ppos || !*lenp) { - *lenp = 0; - goto done; - } - cpumask_clear(mask); rcu_read_lock(); for_each_possible_cpu(i) { @@ -171,17 +217,7 @@ write_unlock: } rcu_read_unlock(); - len = min(sizeof(kbuf) - 1, *lenp); - len = scnprintf(kbuf, len, "%*pb", cpumask_pr_args(mask)); - if (!len) { - *lenp = 0; - goto done; - } - if (len < *lenp) - kbuf[len++] = '\n'; - memcpy(buffer, kbuf, len); - *lenp = len; - *ppos += len; + dump_cpumask(buffer, lenp, ppos, mask); } done: @@ -472,6 +508,11 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = rps_sock_flow_sysctl }, + { + .procname = "rps_default_mask", + .mode = 0644, + .proc_handler = rps_default_mask_sysctl + }, #endif #ifdef CONFIG_NET_FLOW_LIMIT { @@ -675,6 +716,10 @@ static __net_initdata struct pernet_operations sysctl_core_ops = { static __init int sysctl_core_init(void) { +#if IS_ENABLED(CONFIG_RPS) + cpumask_copy(&rps_default_mask, cpu_none_mask); +#endif + register_net_sysctl(&init_net, "net/core", net_core_table); return register_pernet_subsys(&sysctl_core_ops); } diff --git a/net/core/xdp.c b/net/core/xdp.c index 26483935b7a4..8c92fc553317 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -604,8 +604,7 @@ EXPORT_SYMBOL_GPL(xdp_warn); int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp) { - n_skb = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, - n_skb, skbs); + n_skb = kmem_cache_alloc_bulk(skbuff_cache, gfp, n_skb, skbs); if (unlikely(!n_skb)) return -ENOMEM; @@ -674,7 +673,7 @@ struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, { struct sk_buff *skb; - skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; diff --git a/net/devlink/Makefile b/net/devlink/Makefile index 1b1eeac59cb3..daad4521c61e 100644 --- a/net/devlink/Makefile +++ b/net/devlink/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 -obj-y := leftover.o core.o netlink.o +obj-y := leftover.o core.o netlink.o dev.o diff --git a/net/devlink/core.c b/net/devlink/core.c index 6c0e2fc57e45..a4f47dafb864 100644 --- a/net/devlink/core.c +++ b/net/devlink/core.c @@ -126,23 +126,6 @@ next: } /** - * devlink_set_features - Set devlink supported features - * - * @devlink: devlink - * @features: devlink support features - * - * This interface allows us to set reload ops separatelly from - * the devlink_alloc. - */ -void devlink_set_features(struct devlink *devlink, u64 features) -{ - WARN_ON(features & DEVLINK_F_RELOAD && - !devlink_reload_supported(devlink->ops)); - devlink->features = features; -} -EXPORT_SYMBOL_GPL(devlink_set_features); - -/** * devl_register - Register devlink instance * @devlink: devlink */ @@ -222,7 +205,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, goto err_xa_alloc; devlink->netdevice_nb.notifier_call = devlink_port_netdevice_event; - ret = register_netdevice_notifier_net(net, &devlink->netdevice_nb); + ret = register_netdevice_notifier(&devlink->netdevice_nb); if (ret) goto err_register_netdevice_notifier; @@ -283,8 +266,7 @@ void devlink_free(struct devlink *devlink) xa_destroy(&devlink->snapshot_ids); xa_destroy(&devlink->ports); - WARN_ON_ONCE(unregister_netdevice_notifier_net(devlink_net(devlink), - &devlink->netdevice_nb)); + WARN_ON_ONCE(unregister_netdevice_notifier(&devlink->netdevice_nb)); xa_erase(&devlinks, devlink->index); @@ -303,7 +285,6 @@ static void __net_exit devlink_pernet_pre_exit(struct net *net) * all devlink instances from this namespace into init_net. */ devlinks_xa_for_each_registered_get(net, index, devlink) { - WARN_ON(!(devlink->features & DEVLINK_F_RELOAD)); devl_lock(devlink); err = 0; if (devl_is_registered(devlink)) @@ -313,7 +294,6 @@ static void __net_exit devlink_pernet_pre_exit(struct net *net) &actions_performed, NULL); devl_unlock(devlink); devlink_put(devlink); - if (err && err != -EOPNOTSUPP) pr_warn("Failed to reload devlink instance into init_net\n"); } diff --git a/net/devlink/dev.c b/net/devlink/dev.c new file mode 100644 index 000000000000..78d824eda5ec --- /dev/null +++ b/net/devlink/dev.c @@ -0,0 +1,1343 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> + */ + +#include <net/genetlink.h> +#include <net/sock.h> +#include "devl_internal.h" + +struct devlink_info_req { + struct sk_buff *msg; + void (*version_cb)(const char *version_name, + enum devlink_info_version_type version_type, + void *version_cb_priv); + void *version_cb_priv; +}; + +struct devlink_reload_combination { + enum devlink_reload_action action; + enum devlink_reload_limit limit; +}; + +static const struct devlink_reload_combination devlink_reload_invalid_combinations[] = { + { + /* can't reinitialize driver with no down time */ + .action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT, + .limit = DEVLINK_RELOAD_LIMIT_NO_RESET, + }, +}; + +static bool +devlink_reload_combination_is_invalid(enum devlink_reload_action action, + enum devlink_reload_limit limit) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) + if (devlink_reload_invalid_combinations[i].action == action && + devlink_reload_invalid_combinations[i].limit == limit) + return true; + return false; +} + +static bool +devlink_reload_action_is_supported(struct devlink *devlink, enum devlink_reload_action action) +{ + return test_bit(action, &devlink->ops->reload_actions); +} + +static bool +devlink_reload_limit_is_supported(struct devlink *devlink, enum devlink_reload_limit limit) +{ + return test_bit(limit, &devlink->ops->reload_limits); +} + +static int devlink_reload_stat_put(struct sk_buff *msg, + enum devlink_reload_limit limit, u32 value) +{ + struct nlattr *reload_stats_entry; + + reload_stats_entry = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS_ENTRY); + if (!reload_stats_entry) + return -EMSGSIZE; + + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) || + nla_put_u32(msg, DEVLINK_ATTR_RELOAD_STATS_VALUE, value)) + goto nla_put_failure; + nla_nest_end(msg, reload_stats_entry); + return 0; + +nla_put_failure: + nla_nest_cancel(msg, reload_stats_entry); + return -EMSGSIZE; +} + +static int +devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink, bool is_remote) +{ + struct nlattr *reload_stats_attr, *act_info, *act_stats; + int i, j, stat_idx; + u32 value; + + if (!is_remote) + reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS); + else + reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_REMOTE_RELOAD_STATS); + + if (!reload_stats_attr) + return -EMSGSIZE; + + for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) { + if ((!is_remote && + !devlink_reload_action_is_supported(devlink, i)) || + i == DEVLINK_RELOAD_ACTION_UNSPEC) + continue; + act_info = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_INFO); + if (!act_info) + goto nla_put_failure; + + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, i)) + goto action_info_nest_cancel; + act_stats = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_STATS); + if (!act_stats) + goto action_info_nest_cancel; + + for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) { + /* Remote stats are shown even if not locally supported. + * Stats of actions with unspecified limit are shown + * though drivers don't need to register unspecified + * limit. + */ + if ((!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC && + !devlink_reload_limit_is_supported(devlink, j)) || + devlink_reload_combination_is_invalid(i, j)) + continue; + + stat_idx = j * __DEVLINK_RELOAD_ACTION_MAX + i; + if (!is_remote) + value = devlink->stats.reload_stats[stat_idx]; + else + value = devlink->stats.remote_reload_stats[stat_idx]; + if (devlink_reload_stat_put(msg, j, value)) + goto action_stats_nest_cancel; + } + nla_nest_end(msg, act_stats); + nla_nest_end(msg, act_info); + } + nla_nest_end(msg, reload_stats_attr); + return 0; + +action_stats_nest_cancel: + nla_nest_cancel(msg, act_stats); +action_info_nest_cancel: + nla_nest_cancel(msg, act_info); +nla_put_failure: + nla_nest_cancel(msg, reload_stats_attr); + return -EMSGSIZE; +} + +static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink, + enum devlink_command cmd, u32 portid, + u32 seq, int flags) +{ + struct nlattr *dev_stats; + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_FAILED, devlink->reload_failed)) + goto nla_put_failure; + + dev_stats = nla_nest_start(msg, DEVLINK_ATTR_DEV_STATS); + if (!dev_stats) + goto nla_put_failure; + + if (devlink_reload_stats_put(msg, devlink, false)) + goto dev_stats_nest_cancel; + if (devlink_reload_stats_put(msg, devlink, true)) + goto dev_stats_nest_cancel; + + nla_nest_end(msg, dev_stats); + genlmsg_end(msg, hdr); + return 0; + +dev_stats_nest_cancel: + nla_nest_cancel(msg, dev_stats); +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +void devlink_notify(struct devlink *devlink, enum devlink_command cmd) +{ + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_NEW && cmd != DEVLINK_CMD_DEL); + WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_fill(msg, devlink, cmd, 0, 0, 0); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, + info->snd_portid, info->snd_seq, 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int +devlink_nl_cmd_get_dump_one(struct sk_buff *msg, struct devlink *devlink, + struct netlink_callback *cb) +{ + return devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI); +} + +const struct devlink_cmd devl_cmd_get = { + .dump_one = devlink_nl_cmd_get_dump_one, +}; + +static void devlink_reload_failed_set(struct devlink *devlink, + bool reload_failed) +{ + if (devlink->reload_failed == reload_failed) + return; + devlink->reload_failed = reload_failed; + devlink_notify(devlink, DEVLINK_CMD_NEW); +} + +bool devlink_is_reload_failed(const struct devlink *devlink) +{ + return devlink->reload_failed; +} +EXPORT_SYMBOL_GPL(devlink_is_reload_failed); + +static void +__devlink_reload_stats_update(struct devlink *devlink, u32 *reload_stats, + enum devlink_reload_limit limit, u32 actions_performed) +{ + unsigned long actions = actions_performed; + int stat_idx; + int action; + + for_each_set_bit(action, &actions, __DEVLINK_RELOAD_ACTION_MAX) { + stat_idx = limit * __DEVLINK_RELOAD_ACTION_MAX + action; + reload_stats[stat_idx]++; + } + devlink_notify(devlink, DEVLINK_CMD_NEW); +} + +static void +devlink_reload_stats_update(struct devlink *devlink, enum devlink_reload_limit limit, + u32 actions_performed) +{ + __devlink_reload_stats_update(devlink, devlink->stats.reload_stats, limit, + actions_performed); +} + +/** + * devlink_remote_reload_actions_performed - Update devlink on reload actions + * performed which are not a direct result of devlink reload call. + * + * This should be called by a driver after performing reload actions in case it was not + * a result of devlink reload call. For example fw_activate was performed as a result + * of devlink reload triggered fw_activate on another host. + * The motivation for this function is to keep data on reload actions performed on this + * function whether it was done due to direct devlink reload call or not. + * + * @devlink: devlink + * @limit: reload limit + * @actions_performed: bitmask of actions performed + */ +void devlink_remote_reload_actions_performed(struct devlink *devlink, + enum devlink_reload_limit limit, + u32 actions_performed) +{ + if (WARN_ON(!actions_performed || + actions_performed & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || + actions_performed >= BIT(__DEVLINK_RELOAD_ACTION_MAX) || + limit > DEVLINK_RELOAD_LIMIT_MAX)) + return; + + __devlink_reload_stats_update(devlink, devlink->stats.remote_reload_stats, limit, + actions_performed); +} +EXPORT_SYMBOL_GPL(devlink_remote_reload_actions_performed); + +static struct net *devlink_netns_get(struct sk_buff *skb, + struct genl_info *info) +{ + struct nlattr *netns_pid_attr = info->attrs[DEVLINK_ATTR_NETNS_PID]; + struct nlattr *netns_fd_attr = info->attrs[DEVLINK_ATTR_NETNS_FD]; + struct nlattr *netns_id_attr = info->attrs[DEVLINK_ATTR_NETNS_ID]; + struct net *net; + + if (!!netns_pid_attr + !!netns_fd_attr + !!netns_id_attr > 1) { + NL_SET_ERR_MSG_MOD(info->extack, "multiple netns identifying attributes specified"); + return ERR_PTR(-EINVAL); + } + + if (netns_pid_attr) { + net = get_net_ns_by_pid(nla_get_u32(netns_pid_attr)); + } else if (netns_fd_attr) { + net = get_net_ns_by_fd(nla_get_u32(netns_fd_attr)); + } else if (netns_id_attr) { + net = get_net_ns_by_id(sock_net(skb->sk), + nla_get_u32(netns_id_attr)); + if (!net) + net = ERR_PTR(-EINVAL); + } else { + WARN_ON(1); + net = ERR_PTR(-EINVAL); + } + if (IS_ERR(net)) { + NL_SET_ERR_MSG_MOD(info->extack, "Unknown network namespace"); + return ERR_PTR(-EINVAL); + } + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { + put_net(net); + return ERR_PTR(-EPERM); + } + return net; +} + +static void devlink_reload_netns_change(struct devlink *devlink, + struct net *curr_net, + struct net *dest_net) +{ + /* Userspace needs to be notified about devlink objects + * removed from original and entering new network namespace. + * The rest of the devlink objects are re-created during + * reload process so the notifications are generated separatelly. + */ + devlink_notify_unregister(devlink); + move_netdevice_notifier_net(curr_net, dest_net, + &devlink->netdevice_nb); + write_pnet(&devlink->_net, dest_net); + devlink_notify_register(devlink); +} + +int devlink_reload(struct devlink *devlink, struct net *dest_net, + enum devlink_reload_action action, + enum devlink_reload_limit limit, + u32 *actions_performed, struct netlink_ext_ack *extack) +{ + u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; + struct net *curr_net; + int err; + + memcpy(remote_reload_stats, devlink->stats.remote_reload_stats, + sizeof(remote_reload_stats)); + + err = devlink->ops->reload_down(devlink, !!dest_net, action, limit, extack); + if (err) + return err; + + curr_net = devlink_net(devlink); + if (dest_net && !net_eq(dest_net, curr_net)) + devlink_reload_netns_change(devlink, curr_net, dest_net); + + err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack); + devlink_reload_failed_set(devlink, !!err); + if (err) + return err; + + WARN_ON(!(*actions_performed & BIT(action))); + /* Catch driver on updating the remote action within devlink reload */ + WARN_ON(memcmp(remote_reload_stats, devlink->stats.remote_reload_stats, + sizeof(remote_reload_stats))); + devlink_reload_stats_update(devlink, limit, *actions_performed); + return 0; +} + +static int +devlink_nl_reload_actions_performed_snd(struct devlink *devlink, u32 actions_performed, + enum devlink_command cmd, struct genl_info *info) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &devlink_nl_family, 0, cmd); + if (!hdr) + goto free_msg; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (nla_put_bitfield32(msg, DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED, actions_performed, + actions_performed)) + goto nla_put_failure; + genlmsg_end(msg, hdr); + + return genlmsg_reply(msg, info); + +nla_put_failure: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return -EMSGSIZE; +} + +int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + enum devlink_reload_action action; + enum devlink_reload_limit limit; + struct net *dest_net = NULL; + u32 actions_performed; + int err; + + err = devlink_resources_validate(devlink, NULL, info); + if (err) { + NL_SET_ERR_MSG_MOD(info->extack, "resources size validation failed"); + return err; + } + + if (info->attrs[DEVLINK_ATTR_RELOAD_ACTION]) + action = nla_get_u8(info->attrs[DEVLINK_ATTR_RELOAD_ACTION]); + else + action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT; + + if (!devlink_reload_action_is_supported(devlink, action)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Requested reload action is not supported by the driver"); + return -EOPNOTSUPP; + } + + limit = DEVLINK_RELOAD_LIMIT_UNSPEC; + if (info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) { + struct nla_bitfield32 limits; + u32 limits_selected; + + limits = nla_get_bitfield32(info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]); + limits_selected = limits.value & limits.selector; + if (!limits_selected) { + NL_SET_ERR_MSG_MOD(info->extack, "Invalid limit selected"); + return -EINVAL; + } + for (limit = 0 ; limit <= DEVLINK_RELOAD_LIMIT_MAX ; limit++) + if (limits_selected & BIT(limit)) + break; + /* UAPI enables multiselection, but currently it is not used */ + if (limits_selected != BIT(limit)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Multiselection of limit is not supported"); + return -EOPNOTSUPP; + } + if (!devlink_reload_limit_is_supported(devlink, limit)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Requested limit is not supported by the driver"); + return -EOPNOTSUPP; + } + if (devlink_reload_combination_is_invalid(action, limit)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Requested limit is invalid for this action"); + return -EINVAL; + } + } + if (info->attrs[DEVLINK_ATTR_NETNS_PID] || + info->attrs[DEVLINK_ATTR_NETNS_FD] || + info->attrs[DEVLINK_ATTR_NETNS_ID]) { + dest_net = devlink_netns_get(skb, info); + if (IS_ERR(dest_net)) + return PTR_ERR(dest_net); + } + + err = devlink_reload(devlink, dest_net, action, limit, &actions_performed, info->extack); + + if (dest_net) + put_net(dest_net); + + if (err) + return err; + /* For backward compatibility generate reply only if attributes used by user */ + if (!info->attrs[DEVLINK_ATTR_RELOAD_ACTION] && !info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) + return 0; + + return devlink_nl_reload_actions_performed_snd(devlink, actions_performed, + DEVLINK_CMD_RELOAD, info); +} + +bool devlink_reload_actions_valid(const struct devlink_ops *ops) +{ + const struct devlink_reload_combination *comb; + int i; + + if (!devlink_reload_supported(ops)) { + if (WARN_ON(ops->reload_actions)) + return false; + return true; + } + + if (WARN_ON(!ops->reload_actions || + ops->reload_actions & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || + ops->reload_actions >= BIT(__DEVLINK_RELOAD_ACTION_MAX))) + return false; + + if (WARN_ON(ops->reload_limits & BIT(DEVLINK_RELOAD_LIMIT_UNSPEC) || + ops->reload_limits >= BIT(__DEVLINK_RELOAD_LIMIT_MAX))) + return false; + + for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) { + comb = &devlink_reload_invalid_combinations[i]; + if (ops->reload_actions == BIT(comb->action) && + ops->reload_limits == BIT(comb->limit)) + return false; + } + return true; +} + +static int devlink_nl_eswitch_fill(struct sk_buff *msg, struct devlink *devlink, + enum devlink_command cmd, u32 portid, + u32 seq, int flags) +{ + const struct devlink_ops *ops = devlink->ops; + enum devlink_eswitch_encap_mode encap_mode; + u8 inline_mode; + void *hdr; + int err = 0; + u16 mode; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + err = devlink_nl_put_handle(msg, devlink); + if (err) + goto nla_put_failure; + + if (ops->eswitch_mode_get) { + err = ops->eswitch_mode_get(devlink, &mode); + if (err) + goto nla_put_failure; + err = nla_put_u16(msg, DEVLINK_ATTR_ESWITCH_MODE, mode); + if (err) + goto nla_put_failure; + } + + if (ops->eswitch_inline_mode_get) { + err = ops->eswitch_inline_mode_get(devlink, &inline_mode); + if (err) + goto nla_put_failure; + err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_INLINE_MODE, + inline_mode); + if (err) + goto nla_put_failure; + } + + if (ops->eswitch_encap_mode_get) { + err = ops->eswitch_encap_mode_get(devlink, &encap_mode); + if (err) + goto nla_put_failure; + err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_ENCAP_MODE, encap_mode); + if (err) + goto nla_put_failure; + } + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return err; +} + +int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_GET, + info->snd_portid, info->snd_seq, 0); + + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + const struct devlink_ops *ops = devlink->ops; + enum devlink_eswitch_encap_mode encap_mode; + u8 inline_mode; + int err = 0; + u16 mode; + + if (info->attrs[DEVLINK_ATTR_ESWITCH_MODE]) { + if (!ops->eswitch_mode_set) + return -EOPNOTSUPP; + mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]); + err = devlink_rate_nodes_check(devlink, mode, info->extack); + if (err) + return err; + err = ops->eswitch_mode_set(devlink, mode, info->extack); + if (err) + return err; + } + + if (info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]) { + if (!ops->eswitch_inline_mode_set) + return -EOPNOTSUPP; + inline_mode = nla_get_u8(info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]); + err = ops->eswitch_inline_mode_set(devlink, inline_mode, + info->extack); + if (err) + return err; + } + + if (info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]) { + if (!ops->eswitch_encap_mode_set) + return -EOPNOTSUPP; + encap_mode = nla_get_u8(info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]); + err = ops->eswitch_encap_mode_set(devlink, encap_mode, + info->extack); + if (err) + return err; + } + + return 0; +} + +int devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn) +{ + if (!req->msg) + return 0; + return nla_put_string(req->msg, DEVLINK_ATTR_INFO_SERIAL_NUMBER, sn); +} +EXPORT_SYMBOL_GPL(devlink_info_serial_number_put); + +int devlink_info_board_serial_number_put(struct devlink_info_req *req, + const char *bsn) +{ + if (!req->msg) + return 0; + return nla_put_string(req->msg, DEVLINK_ATTR_INFO_BOARD_SERIAL_NUMBER, + bsn); +} +EXPORT_SYMBOL_GPL(devlink_info_board_serial_number_put); + +static int devlink_info_version_put(struct devlink_info_req *req, int attr, + const char *version_name, + const char *version_value, + enum devlink_info_version_type version_type) +{ + struct nlattr *nest; + int err; + + if (req->version_cb) + req->version_cb(version_name, version_type, + req->version_cb_priv); + + if (!req->msg) + return 0; + + nest = nla_nest_start_noflag(req->msg, attr); + if (!nest) + return -EMSGSIZE; + + err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_NAME, + version_name); + if (err) + goto nla_put_failure; + + err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_VALUE, + version_value); + if (err) + goto nla_put_failure; + + nla_nest_end(req->msg, nest); + + return 0; + +nla_put_failure: + nla_nest_cancel(req->msg, nest); + return err; +} + +int devlink_info_version_fixed_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_FIXED, + version_name, version_value, + DEVLINK_INFO_VERSION_TYPE_NONE); +} +EXPORT_SYMBOL_GPL(devlink_info_version_fixed_put); + +int devlink_info_version_stored_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, + version_name, version_value, + DEVLINK_INFO_VERSION_TYPE_NONE); +} +EXPORT_SYMBOL_GPL(devlink_info_version_stored_put); + +int devlink_info_version_stored_put_ext(struct devlink_info_req *req, + const char *version_name, + const char *version_value, + enum devlink_info_version_type version_type) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, + version_name, version_value, + version_type); +} +EXPORT_SYMBOL_GPL(devlink_info_version_stored_put_ext); + +int devlink_info_version_running_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, + version_name, version_value, + DEVLINK_INFO_VERSION_TYPE_NONE); +} +EXPORT_SYMBOL_GPL(devlink_info_version_running_put); + +int devlink_info_version_running_put_ext(struct devlink_info_req *req, + const char *version_name, + const char *version_value, + enum devlink_info_version_type version_type) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, + version_name, version_value, + version_type); +} +EXPORT_SYMBOL_GPL(devlink_info_version_running_put_ext); + +static int devlink_nl_driver_info_get(struct device_driver *drv, + struct devlink_info_req *req) +{ + if (!drv) + return 0; + + if (drv->name[0]) + return nla_put_string(req->msg, DEVLINK_ATTR_INFO_DRIVER_NAME, + drv->name); + + return 0; +} + +static int +devlink_nl_info_fill(struct sk_buff *msg, struct devlink *devlink, + enum devlink_command cmd, u32 portid, + u32 seq, int flags, struct netlink_ext_ack *extack) +{ + struct device *dev = devlink_to_dev(devlink); + struct devlink_info_req req = {}; + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + err = -EMSGSIZE; + if (devlink_nl_put_handle(msg, devlink)) + goto err_cancel_msg; + + req.msg = msg; + if (devlink->ops->info_get) { + err = devlink->ops->info_get(devlink, &req, extack); + if (err) + goto err_cancel_msg; + } + + err = devlink_nl_driver_info_get(dev->driver, &req); + if (err) + goto err_cancel_msg; + + genlmsg_end(msg, hdr); + return 0; + +err_cancel_msg: + genlmsg_cancel(msg, hdr); + return err; +} + +int devlink_nl_cmd_info_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, + info->snd_portid, info->snd_seq, 0, + info->extack); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int +devlink_nl_cmd_info_get_dump_one(struct sk_buff *msg, struct devlink *devlink, + struct netlink_callback *cb) +{ + int err; + + err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + cb->extack); + if (err == -EOPNOTSUPP) + err = 0; + return err; +} + +const struct devlink_cmd devl_cmd_info_get = { + .dump_one = devlink_nl_cmd_info_get_dump_one, +}; + +static int devlink_nl_flash_update_fill(struct sk_buff *msg, + struct devlink *devlink, + enum devlink_command cmd, + struct devlink_flash_notify *params) +{ + void *hdr; + + hdr = genlmsg_put(msg, 0, 0, &devlink_nl_family, 0, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS) + goto out; + + if (params->status_msg && + nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_MSG, + params->status_msg)) + goto nla_put_failure; + if (params->component && + nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, + params->component)) + goto nla_put_failure; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_DONE, + params->done, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL, + params->total, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT, + params->timeout, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + +out: + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static void __devlink_flash_update_notify(struct devlink *devlink, + enum devlink_command cmd, + struct devlink_flash_notify *params) +{ + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_FLASH_UPDATE && + cmd != DEVLINK_CMD_FLASH_UPDATE_END && + cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS); + + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_flash_update_fill(msg, devlink, cmd, params); + if (err) + goto out_free_msg; + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); + return; + +out_free_msg: + nlmsg_free(msg); +} + +static void devlink_flash_update_begin_notify(struct devlink *devlink) +{ + struct devlink_flash_notify params = {}; + + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE, + ¶ms); +} + +static void devlink_flash_update_end_notify(struct devlink *devlink) +{ + struct devlink_flash_notify params = {}; + + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE_END, + ¶ms); +} + +void devlink_flash_update_status_notify(struct devlink *devlink, + const char *status_msg, + const char *component, + unsigned long done, + unsigned long total) +{ + struct devlink_flash_notify params = { + .status_msg = status_msg, + .component = component, + .done = done, + .total = total, + }; + + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE_STATUS, + ¶ms); +} +EXPORT_SYMBOL_GPL(devlink_flash_update_status_notify); + +void devlink_flash_update_timeout_notify(struct devlink *devlink, + const char *status_msg, + const char *component, + unsigned long timeout) +{ + struct devlink_flash_notify params = { + .status_msg = status_msg, + .component = component, + .timeout = timeout, + }; + + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE_STATUS, + ¶ms); +} +EXPORT_SYMBOL_GPL(devlink_flash_update_timeout_notify); + +struct devlink_flash_component_lookup_ctx { + const char *lookup_name; + bool lookup_name_found; +}; + +static void +devlink_flash_component_lookup_cb(const char *version_name, + enum devlink_info_version_type version_type, + void *version_cb_priv) +{ + struct devlink_flash_component_lookup_ctx *lookup_ctx = version_cb_priv; + + if (version_type != DEVLINK_INFO_VERSION_TYPE_COMPONENT || + lookup_ctx->lookup_name_found) + return; + + lookup_ctx->lookup_name_found = + !strcmp(lookup_ctx->lookup_name, version_name); +} + +static int devlink_flash_component_get(struct devlink *devlink, + struct nlattr *nla_component, + const char **p_component, + struct netlink_ext_ack *extack) +{ + struct devlink_flash_component_lookup_ctx lookup_ctx = {}; + struct devlink_info_req req = {}; + const char *component; + int ret; + + if (!nla_component) + return 0; + + component = nla_data(nla_component); + + if (!devlink->ops->info_get) { + NL_SET_ERR_MSG_ATTR(extack, nla_component, + "component update is not supported by this device"); + return -EOPNOTSUPP; + } + + lookup_ctx.lookup_name = component; + req.version_cb = devlink_flash_component_lookup_cb; + req.version_cb_priv = &lookup_ctx; + + ret = devlink->ops->info_get(devlink, &req, NULL); + if (ret) + return ret; + + if (!lookup_ctx.lookup_name_found) { + NL_SET_ERR_MSG_ATTR(extack, nla_component, + "selected component is not supported by this device"); + return -EINVAL; + } + *p_component = component; + return 0; +} + +int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *nla_overwrite_mask, *nla_file_name; + struct devlink_flash_update_params params = {}; + struct devlink *devlink = info->user_ptr[0]; + const char *file_name; + u32 supported_params; + int ret; + + if (!devlink->ops->flash_update) + return -EOPNOTSUPP; + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME)) + return -EINVAL; + + ret = devlink_flash_component_get(devlink, + info->attrs[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT], + ¶ms.component, info->extack); + if (ret) + return ret; + + supported_params = devlink->ops->supported_flash_update_params; + + nla_overwrite_mask = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK]; + if (nla_overwrite_mask) { + struct nla_bitfield32 sections; + + if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK)) { + NL_SET_ERR_MSG_ATTR(info->extack, nla_overwrite_mask, + "overwrite settings are not supported by this device"); + return -EOPNOTSUPP; + } + sections = nla_get_bitfield32(nla_overwrite_mask); + params.overwrite_mask = sections.value & sections.selector; + } + + nla_file_name = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]; + file_name = nla_data(nla_file_name); + ret = request_firmware(¶ms.fw, file_name, devlink->dev); + if (ret) { + NL_SET_ERR_MSG_ATTR(info->extack, nla_file_name, + "failed to locate the requested firmware file"); + return ret; + } + + devlink_flash_update_begin_notify(devlink); + ret = devlink->ops->flash_update(devlink, ¶ms, info->extack); + devlink_flash_update_end_notify(devlink); + + release_firmware(params.fw); + + return ret; +} + +static void __devlink_compat_running_version(struct devlink *devlink, + char *buf, size_t len) +{ + struct devlink_info_req req = {}; + const struct nlattr *nlattr; + struct sk_buff *msg; + int rem, err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + req.msg = msg; + err = devlink->ops->info_get(devlink, &req, NULL); + if (err) + goto free_msg; + + nla_for_each_attr(nlattr, (void *)msg->data, msg->len, rem) { + const struct nlattr *kv; + int rem_kv; + + if (nla_type(nlattr) != DEVLINK_ATTR_INFO_VERSION_RUNNING) + continue; + + nla_for_each_nested(kv, nlattr, rem_kv) { + if (nla_type(kv) != DEVLINK_ATTR_INFO_VERSION_VALUE) + continue; + + strlcat(buf, nla_data(kv), len); + strlcat(buf, " ", len); + } + } +free_msg: + nlmsg_free(msg); +} + +void devlink_compat_running_version(struct devlink *devlink, + char *buf, size_t len) +{ + if (!devlink->ops->info_get) + return; + + devl_lock(devlink); + if (devl_is_registered(devlink)) + __devlink_compat_running_version(devlink, buf, len); + devl_unlock(devlink); +} + +int devlink_compat_flash_update(struct devlink *devlink, const char *file_name) +{ + struct devlink_flash_update_params params = {}; + int ret; + + devl_lock(devlink); + if (!devl_is_registered(devlink)) { + ret = -ENODEV; + goto out_unlock; + } + + if (!devlink->ops->flash_update) { + ret = -EOPNOTSUPP; + goto out_unlock; + } + + ret = request_firmware(¶ms.fw, file_name, devlink->dev); + if (ret) + goto out_unlock; + + devlink_flash_update_begin_notify(devlink); + ret = devlink->ops->flash_update(devlink, ¶ms, NULL); + devlink_flash_update_end_notify(devlink); + + release_firmware(params.fw); +out_unlock: + devl_unlock(devlink); + + return ret; +} + +static int +devlink_nl_selftests_fill(struct sk_buff *msg, struct devlink *devlink, + u32 portid, u32 seq, int flags, + struct netlink_ext_ack *extack) +{ + struct nlattr *selftests; + void *hdr; + int err; + int i; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, + DEVLINK_CMD_SELFTESTS_GET); + if (!hdr) + return -EMSGSIZE; + + err = -EMSGSIZE; + if (devlink_nl_put_handle(msg, devlink)) + goto err_cancel_msg; + + selftests = nla_nest_start(msg, DEVLINK_ATTR_SELFTESTS); + if (!selftests) + goto err_cancel_msg; + + for (i = DEVLINK_ATTR_SELFTEST_ID_UNSPEC + 1; + i <= DEVLINK_ATTR_SELFTEST_ID_MAX; i++) { + if (devlink->ops->selftest_check(devlink, i, extack)) { + err = nla_put_flag(msg, i); + if (err) + goto err_cancel_msg; + } + } + + nla_nest_end(msg, selftests); + genlmsg_end(msg, hdr); + return 0; + +err_cancel_msg: + genlmsg_cancel(msg, hdr); + return err; +} + +int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + if (!devlink->ops->selftest_check) + return -EOPNOTSUPP; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_selftests_fill(msg, devlink, info->snd_portid, + info->snd_seq, 0, info->extack); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int +devlink_nl_cmd_selftests_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb) +{ + if (!devlink->ops->selftest_check) + return 0; + + return devlink_nl_selftests_fill(msg, devlink, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + cb->extack); +} + +const struct devlink_cmd devl_cmd_selftests_get = { + .dump_one = devlink_nl_cmd_selftests_get_dump_one, +}; + +static int devlink_selftest_result_put(struct sk_buff *skb, unsigned int id, + enum devlink_selftest_status test_status) +{ + struct nlattr *result_attr; + + result_attr = nla_nest_start(skb, DEVLINK_ATTR_SELFTEST_RESULT); + if (!result_attr) + return -EMSGSIZE; + + if (nla_put_u32(skb, DEVLINK_ATTR_SELFTEST_RESULT_ID, id) || + nla_put_u8(skb, DEVLINK_ATTR_SELFTEST_RESULT_STATUS, + test_status)) + goto nla_put_failure; + + nla_nest_end(skb, result_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, result_attr); + return -EMSGSIZE; +} + +static const struct nla_policy devlink_selftest_nl_policy[DEVLINK_ATTR_SELFTEST_ID_MAX + 1] = { + [DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .type = NLA_FLAG }, +}; + +int devlink_nl_cmd_selftests_run(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *tb[DEVLINK_ATTR_SELFTEST_ID_MAX + 1]; + struct devlink *devlink = info->user_ptr[0]; + struct nlattr *attrs, *selftests; + struct sk_buff *msg; + void *hdr; + int err; + int i; + + if (!devlink->ops->selftest_run || !devlink->ops->selftest_check) + return -EOPNOTSUPP; + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SELFTESTS)) + return -EINVAL; + + attrs = info->attrs[DEVLINK_ATTR_SELFTESTS]; + + err = nla_parse_nested(tb, DEVLINK_ATTR_SELFTEST_ID_MAX, attrs, + devlink_selftest_nl_policy, info->extack); + if (err < 0) + return err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = -EMSGSIZE; + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, + &devlink_nl_family, 0, DEVLINK_CMD_SELFTESTS_RUN); + if (!hdr) + goto free_msg; + + if (devlink_nl_put_handle(msg, devlink)) + goto genlmsg_cancel; + + selftests = nla_nest_start(msg, DEVLINK_ATTR_SELFTESTS); + if (!selftests) + goto genlmsg_cancel; + + for (i = DEVLINK_ATTR_SELFTEST_ID_UNSPEC + 1; + i <= DEVLINK_ATTR_SELFTEST_ID_MAX; i++) { + enum devlink_selftest_status test_status; + + if (nla_get_flag(tb[i])) { + if (!devlink->ops->selftest_check(devlink, i, + info->extack)) { + if (devlink_selftest_result_put(msg, i, + DEVLINK_SELFTEST_STATUS_SKIP)) + goto selftests_nest_cancel; + continue; + } + + test_status = devlink->ops->selftest_run(devlink, i, + info->extack); + if (devlink_selftest_result_put(msg, i, test_status)) + goto selftests_nest_cancel; + } + } + + nla_nest_end(msg, selftests); + genlmsg_end(msg, hdr); + return genlmsg_reply(msg, info); + +selftests_nest_cancel: + nla_nest_cancel(msg, selftests); +genlmsg_cancel: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return err; +} diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h index d0d889038138..941174e157d4 100644 --- a/net/devlink/devl_internal.h +++ b/net/devlink/devl_internal.h @@ -38,7 +38,6 @@ struct devlink { struct list_head trap_policer_list; struct list_head linecard_list; const struct devlink_ops *ops; - u64 features; struct xarray snapshot_ids; struct devlink_dev_stats stats; struct device *dev; @@ -116,7 +115,7 @@ struct devlink_nl_dump_state { }; }; -struct devlink_gen_cmd { +struct devlink_cmd { int (*dump_one)(struct sk_buff *msg, struct devlink *devlink, struct netlink_callback *cb); }; @@ -129,8 +128,8 @@ devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs); void devlink_notify_unregister(struct devlink *devlink); void devlink_notify_register(struct devlink *devlink); -int devlink_nl_instance_iter_dump(struct sk_buff *msg, - struct netlink_callback *cb); +int devlink_nl_instance_iter_dumpit(struct sk_buff *msg, + struct netlink_callback *cb); static inline struct devlink_nl_dump_state * devlink_dump_state(struct netlink_callback *cb) @@ -140,22 +139,36 @@ devlink_dump_state(struct netlink_callback *cb) return (struct devlink_nl_dump_state *)cb->ctx; } -/* gen cmds */ -extern const struct devlink_gen_cmd devl_gen_inst; -extern const struct devlink_gen_cmd devl_gen_port; -extern const struct devlink_gen_cmd devl_gen_sb; -extern const struct devlink_gen_cmd devl_gen_sb_pool; -extern const struct devlink_gen_cmd devl_gen_sb_port_pool; -extern const struct devlink_gen_cmd devl_gen_sb_tc_pool_bind; -extern const struct devlink_gen_cmd devl_gen_selftests; -extern const struct devlink_gen_cmd devl_gen_param; -extern const struct devlink_gen_cmd devl_gen_region; -extern const struct devlink_gen_cmd devl_gen_info; -extern const struct devlink_gen_cmd devl_gen_health_reporter; -extern const struct devlink_gen_cmd devl_gen_trap; -extern const struct devlink_gen_cmd devl_gen_trap_group; -extern const struct devlink_gen_cmd devl_gen_trap_policer; -extern const struct devlink_gen_cmd devl_gen_linecard; +static inline int +devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink) +{ + if (nla_put_string(msg, DEVLINK_ATTR_BUS_NAME, devlink->dev->bus->name)) + return -EMSGSIZE; + if (nla_put_string(msg, DEVLINK_ATTR_DEV_NAME, dev_name(devlink->dev))) + return -EMSGSIZE; + return 0; +} + +/* Commands */ +extern const struct devlink_cmd devl_cmd_get; +extern const struct devlink_cmd devl_cmd_port_get; +extern const struct devlink_cmd devl_cmd_sb_get; +extern const struct devlink_cmd devl_cmd_sb_pool_get; +extern const struct devlink_cmd devl_cmd_sb_port_pool_get; +extern const struct devlink_cmd devl_cmd_sb_tc_pool_bind_get; +extern const struct devlink_cmd devl_cmd_param_get; +extern const struct devlink_cmd devl_cmd_region_get; +extern const struct devlink_cmd devl_cmd_info_get; +extern const struct devlink_cmd devl_cmd_health_reporter_get; +extern const struct devlink_cmd devl_cmd_trap_get; +extern const struct devlink_cmd devl_cmd_trap_group_get; +extern const struct devlink_cmd devl_cmd_trap_policer_get; +extern const struct devlink_cmd devl_cmd_rate_get; +extern const struct devlink_cmd devl_cmd_linecard_get; +extern const struct devlink_cmd devl_cmd_selftests_get; + +/* Notify */ +void devlink_notify(struct devlink *devlink, enum devlink_command cmd); /* Ports */ int devlink_port_netdevice_event(struct notifier_block *nb, @@ -176,6 +189,12 @@ static inline bool devlink_reload_supported(const struct devlink_ops *ops) return ops->reload_down && ops->reload_up; } +/* Resources */ +struct devlink_resource; +int devlink_resources_validate(struct devlink *devlink, + struct devlink_resource *resource, + struct genl_info *info); + /* Line cards */ struct devlink_linecard; @@ -183,10 +202,19 @@ struct devlink_linecard * devlink_linecard_get_from_info(struct devlink *devlink, struct genl_info *info); /* Rates */ -extern const struct devlink_gen_cmd devl_gen_rate_get; - +int devlink_rate_nodes_check(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack); struct devlink_rate * devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info); struct devlink_rate * devlink_rate_node_get_from_info(struct devlink *devlink, struct genl_info *info); +/* Devlink nl cmds */ +int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_info_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_selftests_run(struct sk_buff *skb, struct genl_info *info); diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c index bd4c5d2dd612..f05ab093d231 100644 --- a/net/devlink/leftover.c +++ b/net/devlink/leftover.c @@ -143,10 +143,6 @@ static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ NLA_POLICY_BITFIELD32(DEVLINK_PORT_FN_CAPS_VALID_MASK), }; -static const struct nla_policy devlink_selftest_nl_policy[DEVLINK_ATTR_SELFTEST_ID_MAX + 1] = { - [DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .type = NLA_FLAG }, -}; - #define ASSERT_DEVLINK_PORT_REGISTERED(devlink_port) \ WARN_ON_ONCE(!(devlink_port)->registered) #define ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port) \ @@ -596,15 +592,6 @@ devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) return NULL; } -static int devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink) -{ - if (nla_put_string(msg, DEVLINK_ATTR_BUS_NAME, devlink->dev->bus->name)) - return -EMSGSIZE; - if (nla_put_string(msg, DEVLINK_ATTR_DEV_NAME, dev_name(devlink->dev))) - return -EMSGSIZE; - return 0; -} - static int devlink_nl_put_nested_handle(struct sk_buff *msg, struct devlink *devlink) { struct nlattr *nested_attr; @@ -641,185 +628,6 @@ size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port) + nla_total_size(4); /* DEVLINK_ATTR_PORT_INDEX */ } -struct devlink_reload_combination { - enum devlink_reload_action action; - enum devlink_reload_limit limit; -}; - -static const struct devlink_reload_combination devlink_reload_invalid_combinations[] = { - { - /* can't reinitialize driver with no down time */ - .action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT, - .limit = DEVLINK_RELOAD_LIMIT_NO_RESET, - }, -}; - -static bool -devlink_reload_combination_is_invalid(enum devlink_reload_action action, - enum devlink_reload_limit limit) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) - if (devlink_reload_invalid_combinations[i].action == action && - devlink_reload_invalid_combinations[i].limit == limit) - return true; - return false; -} - -static bool -devlink_reload_action_is_supported(struct devlink *devlink, enum devlink_reload_action action) -{ - return test_bit(action, &devlink->ops->reload_actions); -} - -static bool -devlink_reload_limit_is_supported(struct devlink *devlink, enum devlink_reload_limit limit) -{ - return test_bit(limit, &devlink->ops->reload_limits); -} - -static int devlink_reload_stat_put(struct sk_buff *msg, - enum devlink_reload_limit limit, u32 value) -{ - struct nlattr *reload_stats_entry; - - reload_stats_entry = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS_ENTRY); - if (!reload_stats_entry) - return -EMSGSIZE; - - if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) || - nla_put_u32(msg, DEVLINK_ATTR_RELOAD_STATS_VALUE, value)) - goto nla_put_failure; - nla_nest_end(msg, reload_stats_entry); - return 0; - -nla_put_failure: - nla_nest_cancel(msg, reload_stats_entry); - return -EMSGSIZE; -} - -static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink, bool is_remote) -{ - struct nlattr *reload_stats_attr, *act_info, *act_stats; - int i, j, stat_idx; - u32 value; - - if (!is_remote) - reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS); - else - reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_REMOTE_RELOAD_STATS); - - if (!reload_stats_attr) - return -EMSGSIZE; - - for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) { - if ((!is_remote && - !devlink_reload_action_is_supported(devlink, i)) || - i == DEVLINK_RELOAD_ACTION_UNSPEC) - continue; - act_info = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_INFO); - if (!act_info) - goto nla_put_failure; - - if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, i)) - goto action_info_nest_cancel; - act_stats = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_STATS); - if (!act_stats) - goto action_info_nest_cancel; - - for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) { - /* Remote stats are shown even if not locally supported. - * Stats of actions with unspecified limit are shown - * though drivers don't need to register unspecified - * limit. - */ - if ((!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC && - !devlink_reload_limit_is_supported(devlink, j)) || - devlink_reload_combination_is_invalid(i, j)) - continue; - - stat_idx = j * __DEVLINK_RELOAD_ACTION_MAX + i; - if (!is_remote) - value = devlink->stats.reload_stats[stat_idx]; - else - value = devlink->stats.remote_reload_stats[stat_idx]; - if (devlink_reload_stat_put(msg, j, value)) - goto action_stats_nest_cancel; - } - nla_nest_end(msg, act_stats); - nla_nest_end(msg, act_info); - } - nla_nest_end(msg, reload_stats_attr); - return 0; - -action_stats_nest_cancel: - nla_nest_cancel(msg, act_stats); -action_info_nest_cancel: - nla_nest_cancel(msg, act_info); -nla_put_failure: - nla_nest_cancel(msg, reload_stats_attr); - return -EMSGSIZE; -} - -static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink, - enum devlink_command cmd, u32 portid, - u32 seq, int flags) -{ - struct nlattr *dev_stats; - void *hdr; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_FAILED, devlink->reload_failed)) - goto nla_put_failure; - - dev_stats = nla_nest_start(msg, DEVLINK_ATTR_DEV_STATS); - if (!dev_stats) - goto nla_put_failure; - - if (devlink_reload_stats_put(msg, devlink, false)) - goto dev_stats_nest_cancel; - if (devlink_reload_stats_put(msg, devlink, true)) - goto dev_stats_nest_cancel; - - nla_nest_end(msg, dev_stats); - genlmsg_end(msg, hdr); - return 0; - -dev_stats_nest_cancel: - nla_nest_cancel(msg, dev_stats); -nla_put_failure: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; -} - -static void devlink_notify(struct devlink *devlink, enum devlink_command cmd) -{ - struct sk_buff *msg; - int err; - - WARN_ON(cmd != DEVLINK_CMD_NEW && cmd != DEVLINK_CMD_DEL); - WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)); - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - - err = devlink_nl_fill(msg, devlink, cmd, 0, 0, 0); - if (err) { - nlmsg_free(msg); - return; - } - - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), - msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); -} - static int devlink_nl_port_attrs_put(struct sk_buff *msg, struct devlink_port *devlink_port) { @@ -1236,7 +1044,7 @@ devlink_nl_cmd_rate_get_dump_one(struct sk_buff *msg, struct devlink *devlink, return err; } -const struct devlink_gen_cmd devl_gen_rate_get = { +const struct devlink_cmd devl_cmd_rate_get = { .dump_one = devlink_nl_cmd_rate_get_dump_one, }; @@ -1274,39 +1082,6 @@ devlink_rate_is_parent_node(struct devlink_rate *devlink_rate, return false; } -static int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct sk_buff *msg; - int err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, - info->snd_portid, info->snd_seq, 0); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int -devlink_nl_cmd_get_dump_one(struct sk_buff *msg, struct devlink *devlink, - struct netlink_callback *cb) -{ - return devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI); -} - -const struct devlink_gen_cmd devl_gen_inst = { - .dump_one = devlink_nl_cmd_get_dump_one, -}; - static int devlink_nl_cmd_port_get_doit(struct sk_buff *skb, struct genl_info *info) { @@ -1359,7 +1134,7 @@ devlink_nl_cmd_port_get_dump_one(struct sk_buff *msg, struct devlink *devlink, return err; } -const struct devlink_gen_cmd devl_gen_port = { +const struct devlink_cmd devl_cmd_port_get = { .dump_one = devlink_nl_cmd_port_get_dump_one, }; @@ -2137,7 +1912,7 @@ static int devlink_nl_cmd_linecard_get_dump_one(struct sk_buff *msg, return err; } -const struct devlink_gen_cmd devl_gen_linecard = { +const struct devlink_cmd devl_cmd_linecard_get = { .dump_one = devlink_nl_cmd_linecard_get_dump_one, }; @@ -2392,7 +2167,7 @@ devlink_nl_cmd_sb_get_dump_one(struct sk_buff *msg, struct devlink *devlink, return err; } -const struct devlink_gen_cmd devl_gen_sb = { +const struct devlink_cmd devl_cmd_sb_get = { .dump_one = devlink_nl_cmd_sb_get_dump_one, }; @@ -2530,7 +2305,7 @@ devlink_nl_cmd_sb_pool_get_dump_one(struct sk_buff *msg, return err; } -const struct devlink_gen_cmd devl_gen_sb_pool = { +const struct devlink_cmd devl_cmd_sb_pool_get = { .dump_one = devlink_nl_cmd_sb_pool_get_dump_one, }; @@ -2738,7 +2513,7 @@ devlink_nl_cmd_sb_port_pool_get_dump_one(struct sk_buff *msg, return err; } -const struct devlink_gen_cmd devl_gen_sb_port_pool = { +const struct devlink_cmd devl_cmd_sb_port_pool_get = { .dump_one = devlink_nl_cmd_sb_port_pool_get_dump_one, }; @@ -2973,7 +2748,7 @@ devlink_nl_cmd_sb_tc_pool_bind_get_dump_one(struct sk_buff *msg, return err; } -const struct devlink_gen_cmd devl_gen_sb_tc_pool_bind = { +const struct devlink_cmd devl_cmd_sb_tc_pool_bind_get = { .dump_one = devlink_nl_cmd_sb_tc_pool_bind_get_dump_one, }; @@ -3064,85 +2839,8 @@ static int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb, return -EOPNOTSUPP; } -static int devlink_nl_eswitch_fill(struct sk_buff *msg, struct devlink *devlink, - enum devlink_command cmd, u32 portid, - u32 seq, int flags) -{ - const struct devlink_ops *ops = devlink->ops; - enum devlink_eswitch_encap_mode encap_mode; - u8 inline_mode; - void *hdr; - int err = 0; - u16 mode; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - err = devlink_nl_put_handle(msg, devlink); - if (err) - goto nla_put_failure; - - if (ops->eswitch_mode_get) { - err = ops->eswitch_mode_get(devlink, &mode); - if (err) - goto nla_put_failure; - err = nla_put_u16(msg, DEVLINK_ATTR_ESWITCH_MODE, mode); - if (err) - goto nla_put_failure; - } - - if (ops->eswitch_inline_mode_get) { - err = ops->eswitch_inline_mode_get(devlink, &inline_mode); - if (err) - goto nla_put_failure; - err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_INLINE_MODE, - inline_mode); - if (err) - goto nla_put_failure; - } - - if (ops->eswitch_encap_mode_get) { - err = ops->eswitch_encap_mode_get(devlink, &encap_mode); - if (err) - goto nla_put_failure; - err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_ENCAP_MODE, encap_mode); - if (err) - goto nla_put_failure; - } - - genlmsg_end(msg, hdr); - return 0; - -nla_put_failure: - genlmsg_cancel(msg, hdr); - return err; -} - -static int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct sk_buff *msg; - int err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_GET, - info->snd_portid, info->snd_seq, 0); - - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int devlink_rate_nodes_check(struct devlink *devlink, u16 mode, - struct netlink_ext_ack *extack) +int devlink_rate_nodes_check(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack) { struct devlink_rate *devlink_rate; @@ -3154,52 +2852,6 @@ static int devlink_rate_nodes_check(struct devlink *devlink, u16 mode, return 0; } -static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - const struct devlink_ops *ops = devlink->ops; - enum devlink_eswitch_encap_mode encap_mode; - u8 inline_mode; - int err = 0; - u16 mode; - - if (info->attrs[DEVLINK_ATTR_ESWITCH_MODE]) { - if (!ops->eswitch_mode_set) - return -EOPNOTSUPP; - mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]); - err = devlink_rate_nodes_check(devlink, mode, info->extack); - if (err) - return err; - err = ops->eswitch_mode_set(devlink, mode, info->extack); - if (err) - return err; - } - - if (info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]) { - if (!ops->eswitch_inline_mode_set) - return -EOPNOTSUPP; - inline_mode = nla_get_u8( - info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]); - err = ops->eswitch_inline_mode_set(devlink, inline_mode, - info->extack); - if (err) - return err; - } - - if (info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]) { - if (!ops->eswitch_encap_mode_set) - return -EOPNOTSUPP; - encap_mode = nla_get_u8(info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]); - err = ops->eswitch_encap_mode_set(devlink, encap_mode, - info->extack); - if (err) - return err; - } - - return 0; -} - int devlink_dpipe_match_put(struct sk_buff *skb, struct devlink_dpipe_match *match) { @@ -4170,10 +3822,9 @@ static int devlink_nl_cmd_resource_dump(struct sk_buff *skb, return devlink_resource_fill(info, DEVLINK_CMD_RESOURCE_DUMP, 0); } -static int -devlink_resources_validate(struct devlink *devlink, - struct devlink_resource *resource, - struct genl_info *info) +int devlink_resources_validate(struct devlink *devlink, + struct devlink_resource *resource, + struct genl_info *info) { struct list_head *resource_list; int err = 0; @@ -4193,722 +3844,6 @@ devlink_resources_validate(struct devlink *devlink, return err; } -static struct net *devlink_netns_get(struct sk_buff *skb, - struct genl_info *info) -{ - struct nlattr *netns_pid_attr = info->attrs[DEVLINK_ATTR_NETNS_PID]; - struct nlattr *netns_fd_attr = info->attrs[DEVLINK_ATTR_NETNS_FD]; - struct nlattr *netns_id_attr = info->attrs[DEVLINK_ATTR_NETNS_ID]; - struct net *net; - - if (!!netns_pid_attr + !!netns_fd_attr + !!netns_id_attr > 1) { - NL_SET_ERR_MSG_MOD(info->extack, "multiple netns identifying attributes specified"); - return ERR_PTR(-EINVAL); - } - - if (netns_pid_attr) { - net = get_net_ns_by_pid(nla_get_u32(netns_pid_attr)); - } else if (netns_fd_attr) { - net = get_net_ns_by_fd(nla_get_u32(netns_fd_attr)); - } else if (netns_id_attr) { - net = get_net_ns_by_id(sock_net(skb->sk), - nla_get_u32(netns_id_attr)); - if (!net) - net = ERR_PTR(-EINVAL); - } else { - WARN_ON(1); - net = ERR_PTR(-EINVAL); - } - if (IS_ERR(net)) { - NL_SET_ERR_MSG_MOD(info->extack, "Unknown network namespace"); - return ERR_PTR(-EINVAL); - } - if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { - put_net(net); - return ERR_PTR(-EPERM); - } - return net; -} - -static void devlink_param_notify(struct devlink *devlink, - unsigned int port_index, - struct devlink_param_item *param_item, - enum devlink_command cmd); - -static void devlink_ns_change_notify(struct devlink *devlink, - struct net *dest_net, struct net *curr_net, - bool new) -{ - struct devlink_param_item *param_item; - enum devlink_command cmd; - - /* Userspace needs to be notified about devlink objects - * removed from original and entering new network namespace. - * The rest of the devlink objects are re-created during - * reload process so the notifications are generated separatelly. - */ - - if (!dest_net || net_eq(dest_net, curr_net)) - return; - - if (new) - devlink_notify(devlink, DEVLINK_CMD_NEW); - - cmd = new ? DEVLINK_CMD_PARAM_NEW : DEVLINK_CMD_PARAM_DEL; - list_for_each_entry(param_item, &devlink->param_list, list) - devlink_param_notify(devlink, 0, param_item, cmd); - - if (!new) - devlink_notify(devlink, DEVLINK_CMD_DEL); -} - -static void devlink_reload_failed_set(struct devlink *devlink, - bool reload_failed) -{ - if (devlink->reload_failed == reload_failed) - return; - devlink->reload_failed = reload_failed; - devlink_notify(devlink, DEVLINK_CMD_NEW); -} - -bool devlink_is_reload_failed(const struct devlink *devlink) -{ - return devlink->reload_failed; -} -EXPORT_SYMBOL_GPL(devlink_is_reload_failed); - -static void -__devlink_reload_stats_update(struct devlink *devlink, u32 *reload_stats, - enum devlink_reload_limit limit, u32 actions_performed) -{ - unsigned long actions = actions_performed; - int stat_idx; - int action; - - for_each_set_bit(action, &actions, __DEVLINK_RELOAD_ACTION_MAX) { - stat_idx = limit * __DEVLINK_RELOAD_ACTION_MAX + action; - reload_stats[stat_idx]++; - } - devlink_notify(devlink, DEVLINK_CMD_NEW); -} - -static void -devlink_reload_stats_update(struct devlink *devlink, enum devlink_reload_limit limit, - u32 actions_performed) -{ - __devlink_reload_stats_update(devlink, devlink->stats.reload_stats, limit, - actions_performed); -} - -/** - * devlink_remote_reload_actions_performed - Update devlink on reload actions - * performed which are not a direct result of devlink reload call. - * - * This should be called by a driver after performing reload actions in case it was not - * a result of devlink reload call. For example fw_activate was performed as a result - * of devlink reload triggered fw_activate on another host. - * The motivation for this function is to keep data on reload actions performed on this - * function whether it was done due to direct devlink reload call or not. - * - * @devlink: devlink - * @limit: reload limit - * @actions_performed: bitmask of actions performed - */ -void devlink_remote_reload_actions_performed(struct devlink *devlink, - enum devlink_reload_limit limit, - u32 actions_performed) -{ - if (WARN_ON(!actions_performed || - actions_performed & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || - actions_performed >= BIT(__DEVLINK_RELOAD_ACTION_MAX) || - limit > DEVLINK_RELOAD_LIMIT_MAX)) - return; - - __devlink_reload_stats_update(devlink, devlink->stats.remote_reload_stats, limit, - actions_performed); -} -EXPORT_SYMBOL_GPL(devlink_remote_reload_actions_performed); - -int devlink_reload(struct devlink *devlink, struct net *dest_net, - enum devlink_reload_action action, - enum devlink_reload_limit limit, - u32 *actions_performed, struct netlink_ext_ack *extack) -{ - u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; - struct net *curr_net; - int err; - - memcpy(remote_reload_stats, devlink->stats.remote_reload_stats, - sizeof(remote_reload_stats)); - - curr_net = devlink_net(devlink); - devlink_ns_change_notify(devlink, dest_net, curr_net, false); - err = devlink->ops->reload_down(devlink, !!dest_net, action, limit, extack); - if (err) - return err; - - if (dest_net && !net_eq(dest_net, curr_net)) { - move_netdevice_notifier_net(curr_net, dest_net, - &devlink->netdevice_nb); - write_pnet(&devlink->_net, dest_net); - } - - err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack); - devlink_reload_failed_set(devlink, !!err); - if (err) - return err; - - devlink_ns_change_notify(devlink, dest_net, curr_net, true); - WARN_ON(!(*actions_performed & BIT(action))); - /* Catch driver on updating the remote action within devlink reload */ - WARN_ON(memcmp(remote_reload_stats, devlink->stats.remote_reload_stats, - sizeof(remote_reload_stats))); - devlink_reload_stats_update(devlink, limit, *actions_performed); - return 0; -} - -static int -devlink_nl_reload_actions_performed_snd(struct devlink *devlink, u32 actions_performed, - enum devlink_command cmd, struct genl_info *info) -{ - struct sk_buff *msg; - void *hdr; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &devlink_nl_family, 0, cmd); - if (!hdr) - goto free_msg; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - - if (nla_put_bitfield32(msg, DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED, actions_performed, - actions_performed)) - goto nla_put_failure; - genlmsg_end(msg, hdr); - - return genlmsg_reply(msg, info); - -nla_put_failure: - genlmsg_cancel(msg, hdr); -free_msg: - nlmsg_free(msg); - return -EMSGSIZE; -} - -static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - enum devlink_reload_action action; - enum devlink_reload_limit limit; - struct net *dest_net = NULL; - u32 actions_performed; - int err; - - if (!(devlink->features & DEVLINK_F_RELOAD)) - return -EOPNOTSUPP; - - err = devlink_resources_validate(devlink, NULL, info); - if (err) { - NL_SET_ERR_MSG_MOD(info->extack, "resources size validation failed"); - return err; - } - - if (info->attrs[DEVLINK_ATTR_RELOAD_ACTION]) - action = nla_get_u8(info->attrs[DEVLINK_ATTR_RELOAD_ACTION]); - else - action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT; - - if (!devlink_reload_action_is_supported(devlink, action)) { - NL_SET_ERR_MSG_MOD(info->extack, - "Requested reload action is not supported by the driver"); - return -EOPNOTSUPP; - } - - limit = DEVLINK_RELOAD_LIMIT_UNSPEC; - if (info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) { - struct nla_bitfield32 limits; - u32 limits_selected; - - limits = nla_get_bitfield32(info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]); - limits_selected = limits.value & limits.selector; - if (!limits_selected) { - NL_SET_ERR_MSG_MOD(info->extack, "Invalid limit selected"); - return -EINVAL; - } - for (limit = 0 ; limit <= DEVLINK_RELOAD_LIMIT_MAX ; limit++) - if (limits_selected & BIT(limit)) - break; - /* UAPI enables multiselection, but currently it is not used */ - if (limits_selected != BIT(limit)) { - NL_SET_ERR_MSG_MOD(info->extack, - "Multiselection of limit is not supported"); - return -EOPNOTSUPP; - } - if (!devlink_reload_limit_is_supported(devlink, limit)) { - NL_SET_ERR_MSG_MOD(info->extack, - "Requested limit is not supported by the driver"); - return -EOPNOTSUPP; - } - if (devlink_reload_combination_is_invalid(action, limit)) { - NL_SET_ERR_MSG_MOD(info->extack, - "Requested limit is invalid for this action"); - return -EINVAL; - } - } - if (info->attrs[DEVLINK_ATTR_NETNS_PID] || - info->attrs[DEVLINK_ATTR_NETNS_FD] || - info->attrs[DEVLINK_ATTR_NETNS_ID]) { - dest_net = devlink_netns_get(skb, info); - if (IS_ERR(dest_net)) - return PTR_ERR(dest_net); - } - - err = devlink_reload(devlink, dest_net, action, limit, &actions_performed, info->extack); - - if (dest_net) - put_net(dest_net); - - if (err) - return err; - /* For backward compatibility generate reply only if attributes used by user */ - if (!info->attrs[DEVLINK_ATTR_RELOAD_ACTION] && !info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) - return 0; - - return devlink_nl_reload_actions_performed_snd(devlink, actions_performed, - DEVLINK_CMD_RELOAD, info); -} - -static int devlink_nl_flash_update_fill(struct sk_buff *msg, - struct devlink *devlink, - enum devlink_command cmd, - struct devlink_flash_notify *params) -{ - void *hdr; - - hdr = genlmsg_put(msg, 0, 0, &devlink_nl_family, 0, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - - if (cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS) - goto out; - - if (params->status_msg && - nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_MSG, - params->status_msg)) - goto nla_put_failure; - if (params->component && - nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, - params->component)) - goto nla_put_failure; - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_DONE, - params->done, DEVLINK_ATTR_PAD)) - goto nla_put_failure; - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL, - params->total, DEVLINK_ATTR_PAD)) - goto nla_put_failure; - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT, - params->timeout, DEVLINK_ATTR_PAD)) - goto nla_put_failure; - -out: - genlmsg_end(msg, hdr); - return 0; - -nla_put_failure: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; -} - -static void __devlink_flash_update_notify(struct devlink *devlink, - enum devlink_command cmd, - struct devlink_flash_notify *params) -{ - struct sk_buff *msg; - int err; - - WARN_ON(cmd != DEVLINK_CMD_FLASH_UPDATE && - cmd != DEVLINK_CMD_FLASH_UPDATE_END && - cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS); - - if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) - return; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - - err = devlink_nl_flash_update_fill(msg, devlink, cmd, params); - if (err) - goto out_free_msg; - - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), - msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); - return; - -out_free_msg: - nlmsg_free(msg); -} - -static void devlink_flash_update_begin_notify(struct devlink *devlink) -{ - struct devlink_flash_notify params = {}; - - __devlink_flash_update_notify(devlink, - DEVLINK_CMD_FLASH_UPDATE, - ¶ms); -} - -static void devlink_flash_update_end_notify(struct devlink *devlink) -{ - struct devlink_flash_notify params = {}; - - __devlink_flash_update_notify(devlink, - DEVLINK_CMD_FLASH_UPDATE_END, - ¶ms); -} - -void devlink_flash_update_status_notify(struct devlink *devlink, - const char *status_msg, - const char *component, - unsigned long done, - unsigned long total) -{ - struct devlink_flash_notify params = { - .status_msg = status_msg, - .component = component, - .done = done, - .total = total, - }; - - __devlink_flash_update_notify(devlink, - DEVLINK_CMD_FLASH_UPDATE_STATUS, - ¶ms); -} -EXPORT_SYMBOL_GPL(devlink_flash_update_status_notify); - -void devlink_flash_update_timeout_notify(struct devlink *devlink, - const char *status_msg, - const char *component, - unsigned long timeout) -{ - struct devlink_flash_notify params = { - .status_msg = status_msg, - .component = component, - .timeout = timeout, - }; - - __devlink_flash_update_notify(devlink, - DEVLINK_CMD_FLASH_UPDATE_STATUS, - ¶ms); -} -EXPORT_SYMBOL_GPL(devlink_flash_update_timeout_notify); - -struct devlink_info_req { - struct sk_buff *msg; - void (*version_cb)(const char *version_name, - enum devlink_info_version_type version_type, - void *version_cb_priv); - void *version_cb_priv; -}; - -struct devlink_flash_component_lookup_ctx { - const char *lookup_name; - bool lookup_name_found; -}; - -static void -devlink_flash_component_lookup_cb(const char *version_name, - enum devlink_info_version_type version_type, - void *version_cb_priv) -{ - struct devlink_flash_component_lookup_ctx *lookup_ctx = version_cb_priv; - - if (version_type != DEVLINK_INFO_VERSION_TYPE_COMPONENT || - lookup_ctx->lookup_name_found) - return; - - lookup_ctx->lookup_name_found = - !strcmp(lookup_ctx->lookup_name, version_name); -} - -static int devlink_flash_component_get(struct devlink *devlink, - struct nlattr *nla_component, - const char **p_component, - struct netlink_ext_ack *extack) -{ - struct devlink_flash_component_lookup_ctx lookup_ctx = {}; - struct devlink_info_req req = {}; - const char *component; - int ret; - - if (!nla_component) - return 0; - - component = nla_data(nla_component); - - if (!devlink->ops->info_get) { - NL_SET_ERR_MSG_ATTR(extack, nla_component, - "component update is not supported by this device"); - return -EOPNOTSUPP; - } - - lookup_ctx.lookup_name = component; - req.version_cb = devlink_flash_component_lookup_cb; - req.version_cb_priv = &lookup_ctx; - - ret = devlink->ops->info_get(devlink, &req, NULL); - if (ret) - return ret; - - if (!lookup_ctx.lookup_name_found) { - NL_SET_ERR_MSG_ATTR(extack, nla_component, - "selected component is not supported by this device"); - return -EINVAL; - } - *p_component = component; - return 0; -} - -static int devlink_nl_cmd_flash_update(struct sk_buff *skb, - struct genl_info *info) -{ - struct nlattr *nla_overwrite_mask, *nla_file_name; - struct devlink_flash_update_params params = {}; - struct devlink *devlink = info->user_ptr[0]; - const char *file_name; - u32 supported_params; - int ret; - - if (!devlink->ops->flash_update) - return -EOPNOTSUPP; - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME)) - return -EINVAL; - - ret = devlink_flash_component_get(devlink, - info->attrs[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT], - ¶ms.component, info->extack); - if (ret) - return ret; - - supported_params = devlink->ops->supported_flash_update_params; - - nla_overwrite_mask = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK]; - if (nla_overwrite_mask) { - struct nla_bitfield32 sections; - - if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK)) { - NL_SET_ERR_MSG_ATTR(info->extack, nla_overwrite_mask, - "overwrite settings are not supported by this device"); - return -EOPNOTSUPP; - } - sections = nla_get_bitfield32(nla_overwrite_mask); - params.overwrite_mask = sections.value & sections.selector; - } - - nla_file_name = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]; - file_name = nla_data(nla_file_name); - ret = request_firmware(¶ms.fw, file_name, devlink->dev); - if (ret) { - NL_SET_ERR_MSG_ATTR(info->extack, nla_file_name, "failed to locate the requested firmware file"); - return ret; - } - - devlink_flash_update_begin_notify(devlink); - ret = devlink->ops->flash_update(devlink, ¶ms, info->extack); - devlink_flash_update_end_notify(devlink); - - release_firmware(params.fw); - - return ret; -} - -static int -devlink_nl_selftests_fill(struct sk_buff *msg, struct devlink *devlink, - u32 portid, u32 seq, int flags, - struct netlink_ext_ack *extack) -{ - struct nlattr *selftests; - void *hdr; - int err; - int i; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, - DEVLINK_CMD_SELFTESTS_GET); - if (!hdr) - return -EMSGSIZE; - - err = -EMSGSIZE; - if (devlink_nl_put_handle(msg, devlink)) - goto err_cancel_msg; - - selftests = nla_nest_start(msg, DEVLINK_ATTR_SELFTESTS); - if (!selftests) - goto err_cancel_msg; - - for (i = DEVLINK_ATTR_SELFTEST_ID_UNSPEC + 1; - i <= DEVLINK_ATTR_SELFTEST_ID_MAX; i++) { - if (devlink->ops->selftest_check(devlink, i, extack)) { - err = nla_put_flag(msg, i); - if (err) - goto err_cancel_msg; - } - } - - nla_nest_end(msg, selftests); - genlmsg_end(msg, hdr); - return 0; - -err_cancel_msg: - genlmsg_cancel(msg, hdr); - return err; -} - -static int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct sk_buff *msg; - int err; - - if (!devlink->ops->selftest_check) - return -EOPNOTSUPP; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_selftests_fill(msg, devlink, info->snd_portid, - info->snd_seq, 0, info->extack); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int -devlink_nl_cmd_selftests_get_dump_one(struct sk_buff *msg, - struct devlink *devlink, - struct netlink_callback *cb) -{ - if (!devlink->ops->selftest_check) - return 0; - - return devlink_nl_selftests_fill(msg, devlink, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, - cb->extack); -} - -const struct devlink_gen_cmd devl_gen_selftests = { - .dump_one = devlink_nl_cmd_selftests_get_dump_one, -}; - -static int devlink_selftest_result_put(struct sk_buff *skb, unsigned int id, - enum devlink_selftest_status test_status) -{ - struct nlattr *result_attr; - - result_attr = nla_nest_start(skb, DEVLINK_ATTR_SELFTEST_RESULT); - if (!result_attr) - return -EMSGSIZE; - - if (nla_put_u32(skb, DEVLINK_ATTR_SELFTEST_RESULT_ID, id) || - nla_put_u8(skb, DEVLINK_ATTR_SELFTEST_RESULT_STATUS, - test_status)) - goto nla_put_failure; - - nla_nest_end(skb, result_attr); - return 0; - -nla_put_failure: - nla_nest_cancel(skb, result_attr); - return -EMSGSIZE; -} - -static int devlink_nl_cmd_selftests_run(struct sk_buff *skb, - struct genl_info *info) -{ - struct nlattr *tb[DEVLINK_ATTR_SELFTEST_ID_MAX + 1]; - struct devlink *devlink = info->user_ptr[0]; - struct nlattr *attrs, *selftests; - struct sk_buff *msg; - void *hdr; - int err; - int i; - - if (!devlink->ops->selftest_run || !devlink->ops->selftest_check) - return -EOPNOTSUPP; - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SELFTESTS)) - return -EINVAL; - - attrs = info->attrs[DEVLINK_ATTR_SELFTESTS]; - - err = nla_parse_nested(tb, DEVLINK_ATTR_SELFTEST_ID_MAX, attrs, - devlink_selftest_nl_policy, info->extack); - if (err < 0) - return err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = -EMSGSIZE; - hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, - &devlink_nl_family, 0, DEVLINK_CMD_SELFTESTS_RUN); - if (!hdr) - goto free_msg; - - if (devlink_nl_put_handle(msg, devlink)) - goto genlmsg_cancel; - - selftests = nla_nest_start(msg, DEVLINK_ATTR_SELFTESTS); - if (!selftests) - goto genlmsg_cancel; - - for (i = DEVLINK_ATTR_SELFTEST_ID_UNSPEC + 1; - i <= DEVLINK_ATTR_SELFTEST_ID_MAX; i++) { - enum devlink_selftest_status test_status; - - if (nla_get_flag(tb[i])) { - if (!devlink->ops->selftest_check(devlink, i, - info->extack)) { - if (devlink_selftest_result_put(msg, i, - DEVLINK_SELFTEST_STATUS_SKIP)) - goto selftests_nest_cancel; - continue; - } - - test_status = devlink->ops->selftest_run(devlink, i, - info->extack); - if (devlink_selftest_result_put(msg, i, test_status)) - goto selftests_nest_cancel; - } - } - - nla_nest_end(msg, selftests); - genlmsg_end(msg, hdr); - return genlmsg_reply(msg, info); - -selftests_nest_cancel: - nla_nest_cancel(msg, selftests); -genlmsg_cancel: - genlmsg_cancel(msg, hdr); -free_msg: - nlmsg_free(msg); - return err; -} - static const struct devlink_param devlink_param_generic[] = { { .id = DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET, @@ -5295,7 +4230,7 @@ devlink_nl_cmd_param_get_dump_one(struct sk_buff *msg, struct devlink *devlink, return err; } -const struct devlink_gen_cmd devl_gen_param = { +const struct devlink_cmd devl_cmd_param_get = { .dump_one = devlink_nl_cmd_param_get_dump_one, }; @@ -6002,7 +4937,7 @@ devlink_nl_cmd_region_get_dump_one(struct sk_buff *msg, struct devlink *devlink, return 0; } -const struct devlink_gen_cmd devl_gen_region = { +const struct devlink_cmd devl_cmd_region_get = { .dump_one = devlink_nl_cmd_region_get_dump_one, }; @@ -6454,205 +5389,6 @@ out_unlock: return err; } -int devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn) -{ - if (!req->msg) - return 0; - return nla_put_string(req->msg, DEVLINK_ATTR_INFO_SERIAL_NUMBER, sn); -} -EXPORT_SYMBOL_GPL(devlink_info_serial_number_put); - -int devlink_info_board_serial_number_put(struct devlink_info_req *req, - const char *bsn) -{ - if (!req->msg) - return 0; - return nla_put_string(req->msg, DEVLINK_ATTR_INFO_BOARD_SERIAL_NUMBER, - bsn); -} -EXPORT_SYMBOL_GPL(devlink_info_board_serial_number_put); - -static int devlink_info_version_put(struct devlink_info_req *req, int attr, - const char *version_name, - const char *version_value, - enum devlink_info_version_type version_type) -{ - struct nlattr *nest; - int err; - - if (req->version_cb) - req->version_cb(version_name, version_type, - req->version_cb_priv); - - if (!req->msg) - return 0; - - nest = nla_nest_start_noflag(req->msg, attr); - if (!nest) - return -EMSGSIZE; - - err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_NAME, - version_name); - if (err) - goto nla_put_failure; - - err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_VALUE, - version_value); - if (err) - goto nla_put_failure; - - nla_nest_end(req->msg, nest); - - return 0; - -nla_put_failure: - nla_nest_cancel(req->msg, nest); - return err; -} - -int devlink_info_version_fixed_put(struct devlink_info_req *req, - const char *version_name, - const char *version_value) -{ - return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_FIXED, - version_name, version_value, - DEVLINK_INFO_VERSION_TYPE_NONE); -} -EXPORT_SYMBOL_GPL(devlink_info_version_fixed_put); - -int devlink_info_version_stored_put(struct devlink_info_req *req, - const char *version_name, - const char *version_value) -{ - return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, - version_name, version_value, - DEVLINK_INFO_VERSION_TYPE_NONE); -} -EXPORT_SYMBOL_GPL(devlink_info_version_stored_put); - -int devlink_info_version_stored_put_ext(struct devlink_info_req *req, - const char *version_name, - const char *version_value, - enum devlink_info_version_type version_type) -{ - return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, - version_name, version_value, - version_type); -} -EXPORT_SYMBOL_GPL(devlink_info_version_stored_put_ext); - -int devlink_info_version_running_put(struct devlink_info_req *req, - const char *version_name, - const char *version_value) -{ - return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, - version_name, version_value, - DEVLINK_INFO_VERSION_TYPE_NONE); -} -EXPORT_SYMBOL_GPL(devlink_info_version_running_put); - -int devlink_info_version_running_put_ext(struct devlink_info_req *req, - const char *version_name, - const char *version_value, - enum devlink_info_version_type version_type) -{ - return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, - version_name, version_value, - version_type); -} -EXPORT_SYMBOL_GPL(devlink_info_version_running_put_ext); - -static int devlink_nl_driver_info_get(struct device_driver *drv, - struct devlink_info_req *req) -{ - if (!drv) - return 0; - - if (drv->name[0]) - return nla_put_string(req->msg, DEVLINK_ATTR_INFO_DRIVER_NAME, - drv->name); - - return 0; -} - -static int -devlink_nl_info_fill(struct sk_buff *msg, struct devlink *devlink, - enum devlink_command cmd, u32 portid, - u32 seq, int flags, struct netlink_ext_ack *extack) -{ - struct device *dev = devlink_to_dev(devlink); - struct devlink_info_req req = {}; - void *hdr; - int err; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - err = -EMSGSIZE; - if (devlink_nl_put_handle(msg, devlink)) - goto err_cancel_msg; - - req.msg = msg; - if (devlink->ops->info_get) { - err = devlink->ops->info_get(devlink, &req, extack); - if (err) - goto err_cancel_msg; - } - - err = devlink_nl_driver_info_get(dev->driver, &req); - if (err) - goto err_cancel_msg; - - genlmsg_end(msg, hdr); - return 0; - -err_cancel_msg: - genlmsg_cancel(msg, hdr); - return err; -} - -static int devlink_nl_cmd_info_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct sk_buff *msg; - int err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, - info->snd_portid, info->snd_seq, 0, - info->extack); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int -devlink_nl_cmd_info_get_dump_one(struct sk_buff *msg, struct devlink *devlink, - struct netlink_callback *cb) -{ - int err; - - err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, - cb->extack); - if (err == -EOPNOTSUPP) - err = 0; - return err; -} - -const struct devlink_gen_cmd devl_gen_info = { - .dump_one = devlink_nl_cmd_info_get_dump_one, -}; - struct devlink_fmsg_item { struct list_head list; int attrtype; @@ -7817,7 +6553,7 @@ devlink_nl_cmd_health_reporter_get_dump_one(struct sk_buff *msg, return 0; } -const struct devlink_gen_cmd devl_gen_health_reporter = { +const struct devlink_cmd devl_cmd_health_reporter_get = { .dump_one = devlink_nl_cmd_health_reporter_get_dump_one, }; @@ -7890,18 +6626,22 @@ static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, err = devlink_fmsg_obj_nest_start(fmsg); if (err) - return err; + goto out; err = reporter->ops->diagnose(reporter, fmsg, info->extack); if (err) - return err; + goto out; err = devlink_fmsg_obj_nest_end(fmsg); if (err) - return err; + goto out; + + err = devlink_fmsg_snd(fmsg, info, + DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, 0); - return devlink_fmsg_snd(fmsg, info, - DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, 0); +out: + devlink_fmsg_free(fmsg); + return err; } static int @@ -8335,7 +7075,7 @@ devlink_nl_cmd_trap_get_dump_one(struct sk_buff *msg, struct devlink *devlink, return err; } -const struct devlink_gen_cmd devl_gen_trap = { +const struct devlink_cmd devl_cmd_trap_get = { .dump_one = devlink_nl_cmd_trap_get_dump_one, }; @@ -8548,7 +7288,7 @@ devlink_nl_cmd_trap_group_get_dump_one(struct sk_buff *msg, return err; } -const struct devlink_gen_cmd devl_gen_trap_group = { +const struct devlink_cmd devl_cmd_trap_group_get = { .dump_one = devlink_nl_cmd_trap_group_get_dump_one, }; @@ -8841,7 +7581,7 @@ devlink_nl_cmd_trap_policer_get_dump_one(struct sk_buff *msg, return err; } -const struct devlink_gen_cmd devl_gen_trap_policer = { +const struct devlink_cmd devl_cmd_trap_policer_get = { .dump_one = devlink_nl_cmd_trap_policer_get_dump_one, }; @@ -8922,14 +7662,14 @@ const struct genl_small_ops devlink_nl_ops[56] = { .cmd = DEVLINK_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_get_doit, - .dumpit = devlink_nl_instance_iter_dump, + .dumpit = devlink_nl_instance_iter_dumpit, /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_PORT_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_port_get_doit, - .dumpit = devlink_nl_instance_iter_dump, + .dumpit = devlink_nl_instance_iter_dumpit, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, /* can be retrieved by unprivileged users */ }, @@ -8943,7 +7683,7 @@ const struct genl_small_ops devlink_nl_ops[56] = { { .cmd = DEVLINK_CMD_RATE_GET, .doit = devlink_nl_cmd_rate_get_doit, - .dumpit = devlink_nl_instance_iter_dump, + .dumpit = devlink_nl_instance_iter_dumpit, .internal_flags = DEVLINK_NL_FLAG_NEED_RATE, /* can be retrieved by unprivileged users */ }, @@ -8991,7 +7731,7 @@ const struct genl_small_ops devlink_nl_ops[56] = { { .cmd = DEVLINK_CMD_LINECARD_GET, .doit = devlink_nl_cmd_linecard_get_doit, - .dumpit = devlink_nl_instance_iter_dump, + .dumpit = devlink_nl_instance_iter_dumpit, .internal_flags = DEVLINK_NL_FLAG_NEED_LINECARD, /* can be retrieved by unprivileged users */ }, @@ -9005,14 +7745,14 @@ const struct genl_small_ops devlink_nl_ops[56] = { .cmd = DEVLINK_CMD_SB_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_sb_get_doit, - .dumpit = devlink_nl_instance_iter_dump, + .dumpit = devlink_nl_instance_iter_dumpit, /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_SB_POOL_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_sb_pool_get_doit, - .dumpit = devlink_nl_instance_iter_dump, + .dumpit = devlink_nl_instance_iter_dumpit, /* can be retrieved by unprivileged users */ }, { @@ -9025,7 +7765,7 @@ const struct genl_small_ops devlink_nl_ops[56] = { .cmd = DEVLINK_CMD_SB_PORT_POOL_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_sb_port_pool_get_doit, - .dumpit = devlink_nl_instance_iter_dump, + .dumpit = devlink_nl_instance_iter_dumpit, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, /* can be retrieved by unprivileged users */ }, @@ -9040,7 +7780,7 @@ const struct genl_small_ops devlink_nl_ops[56] = { .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_sb_tc_pool_bind_get_doit, - .dumpit = devlink_nl_instance_iter_dump, + .dumpit = devlink_nl_instance_iter_dumpit, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, /* can be retrieved by unprivileged users */ }, @@ -9121,7 +7861,7 @@ const struct genl_small_ops devlink_nl_ops[56] = { .cmd = DEVLINK_CMD_PARAM_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_param_get_doit, - .dumpit = devlink_nl_instance_iter_dump, + .dumpit = devlink_nl_instance_iter_dumpit, /* can be retrieved by unprivileged users */ }, { @@ -9149,7 +7889,7 @@ const struct genl_small_ops devlink_nl_ops[56] = { .cmd = DEVLINK_CMD_REGION_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_region_get_doit, - .dumpit = devlink_nl_instance_iter_dump, + .dumpit = devlink_nl_instance_iter_dumpit, .flags = GENL_ADMIN_PERM, }, { @@ -9175,14 +7915,14 @@ const struct genl_small_ops devlink_nl_ops[56] = { .cmd = DEVLINK_CMD_INFO_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_info_get_doit, - .dumpit = devlink_nl_instance_iter_dump, + .dumpit = devlink_nl_instance_iter_dumpit, /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_HEALTH_REPORTER_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_health_reporter_get_doit, - .dumpit = devlink_nl_instance_iter_dump, + .dumpit = devlink_nl_instance_iter_dumpit, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, /* can be retrieved by unprivileged users */ }, @@ -9237,7 +7977,7 @@ const struct genl_small_ops devlink_nl_ops[56] = { { .cmd = DEVLINK_CMD_TRAP_GET, .doit = devlink_nl_cmd_trap_get_doit, - .dumpit = devlink_nl_instance_iter_dump, + .dumpit = devlink_nl_instance_iter_dumpit, /* can be retrieved by unprivileged users */ }, { @@ -9248,7 +7988,7 @@ const struct genl_small_ops devlink_nl_ops[56] = { { .cmd = DEVLINK_CMD_TRAP_GROUP_GET, .doit = devlink_nl_cmd_trap_group_get_doit, - .dumpit = devlink_nl_instance_iter_dump, + .dumpit = devlink_nl_instance_iter_dumpit, /* can be retrieved by unprivileged users */ }, { @@ -9259,7 +7999,7 @@ const struct genl_small_ops devlink_nl_ops[56] = { { .cmd = DEVLINK_CMD_TRAP_POLICER_GET, .doit = devlink_nl_cmd_trap_policer_get_doit, - .dumpit = devlink_nl_instance_iter_dump, + .dumpit = devlink_nl_instance_iter_dumpit, /* can be retrieved by unprivileged users */ }, { @@ -9270,7 +8010,7 @@ const struct genl_small_ops devlink_nl_ops[56] = { { .cmd = DEVLINK_CMD_SELFTESTS_GET, .doit = devlink_nl_cmd_selftests_get_doit, - .dumpit = devlink_nl_instance_iter_dump, + .dumpit = devlink_nl_instance_iter_dumpit, /* can be retrieved by unprivileged users */ }, { @@ -9281,35 +8021,6 @@ const struct genl_small_ops devlink_nl_ops[56] = { /* -- No new ops here! Use split ops going forward! -- */ }; -bool devlink_reload_actions_valid(const struct devlink_ops *ops) -{ - const struct devlink_reload_combination *comb; - int i; - - if (!devlink_reload_supported(ops)) { - if (WARN_ON(ops->reload_actions)) - return false; - return true; - } - - if (WARN_ON(!ops->reload_actions || - ops->reload_actions & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || - ops->reload_actions >= BIT(__DEVLINK_RELOAD_ACTION_MAX))) - return false; - - if (WARN_ON(ops->reload_limits & BIT(DEVLINK_RELOAD_LIMIT_UNSPEC) || - ops->reload_limits >= BIT(__DEVLINK_RELOAD_LIMIT_MAX))) - return false; - - for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) { - comb = &devlink_reload_invalid_combinations[i]; - if (ops->reload_actions == BIT(comb->action) && - ops->reload_limits == BIT(comb->limit)) - return false; - } - return true; -} - static void devlink_trap_policer_notify(struct devlink *devlink, const struct devlink_trap_policer_item *policer_item, @@ -9719,6 +8430,8 @@ int devlink_port_netdevice_event(struct notifier_block *nb, break; case NETDEV_REGISTER: case NETDEV_CHANGENAME: + if (devlink_net(devlink) != dev_net(netdev)) + return NOTIFY_OK; /* Set the netdev on top of previously set type. Note this * event happens also during net namespace change so here * we take into account netdev pointer appearing in this @@ -9728,6 +8441,8 @@ int devlink_port_netdevice_event(struct notifier_block *nb, netdev); break; case NETDEV_UNREGISTER: + if (devlink_net(devlink) != dev_net(netdev)) + return NOTIFY_OK; /* Clear netdev pointer, but not the type. This event happens * also during net namespace change so we need to clear * pointer to netdev that is going to another net namespace. @@ -12092,85 +10807,6 @@ devl_trap_policers_unregister(struct devlink *devlink, } EXPORT_SYMBOL_GPL(devl_trap_policers_unregister); -static void __devlink_compat_running_version(struct devlink *devlink, - char *buf, size_t len) -{ - struct devlink_info_req req = {}; - const struct nlattr *nlattr; - struct sk_buff *msg; - int rem, err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - - req.msg = msg; - err = devlink->ops->info_get(devlink, &req, NULL); - if (err) - goto free_msg; - - nla_for_each_attr(nlattr, (void *)msg->data, msg->len, rem) { - const struct nlattr *kv; - int rem_kv; - - if (nla_type(nlattr) != DEVLINK_ATTR_INFO_VERSION_RUNNING) - continue; - - nla_for_each_nested(kv, nlattr, rem_kv) { - if (nla_type(kv) != DEVLINK_ATTR_INFO_VERSION_VALUE) - continue; - - strlcat(buf, nla_data(kv), len); - strlcat(buf, " ", len); - } - } -free_msg: - nlmsg_free(msg); -} - -void devlink_compat_running_version(struct devlink *devlink, - char *buf, size_t len) -{ - if (!devlink->ops->info_get) - return; - - devl_lock(devlink); - if (devl_is_registered(devlink)) - __devlink_compat_running_version(devlink, buf, len); - devl_unlock(devlink); -} - -int devlink_compat_flash_update(struct devlink *devlink, const char *file_name) -{ - struct devlink_flash_update_params params = {}; - int ret; - - devl_lock(devlink); - if (!devl_is_registered(devlink)) { - ret = -ENODEV; - goto out_unlock; - } - - if (!devlink->ops->flash_update) { - ret = -EOPNOTSUPP; - goto out_unlock; - } - - ret = request_firmware(¶ms.fw, file_name, devlink->dev); - if (ret) - goto out_unlock; - - devlink_flash_update_begin_notify(devlink); - ret = devlink->ops->flash_update(devlink, ¶ms, NULL); - devlink_flash_update_end_notify(devlink); - - release_firmware(params.fw); -out_unlock: - devl_unlock(devlink); - - return ret; -} - int devlink_compat_phys_port_name_get(struct net_device *dev, char *name, size_t len) { diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c index 3f44633af01c..7a332eb70f70 100644 --- a/net/devlink/netlink.c +++ b/net/devlink/netlink.c @@ -177,35 +177,35 @@ static void devlink_nl_post_doit(const struct genl_split_ops *ops, devlink_put(devlink); } -static const struct devlink_gen_cmd *devl_gen_cmds[] = { - [DEVLINK_CMD_GET] = &devl_gen_inst, - [DEVLINK_CMD_PORT_GET] = &devl_gen_port, - [DEVLINK_CMD_SB_GET] = &devl_gen_sb, - [DEVLINK_CMD_SB_POOL_GET] = &devl_gen_sb_pool, - [DEVLINK_CMD_SB_PORT_POOL_GET] = &devl_gen_sb_port_pool, - [DEVLINK_CMD_SB_TC_POOL_BIND_GET] = &devl_gen_sb_tc_pool_bind, - [DEVLINK_CMD_PARAM_GET] = &devl_gen_param, - [DEVLINK_CMD_REGION_GET] = &devl_gen_region, - [DEVLINK_CMD_INFO_GET] = &devl_gen_info, - [DEVLINK_CMD_HEALTH_REPORTER_GET] = &devl_gen_health_reporter, - [DEVLINK_CMD_RATE_GET] = &devl_gen_rate_get, - [DEVLINK_CMD_TRAP_GET] = &devl_gen_trap, - [DEVLINK_CMD_TRAP_GROUP_GET] = &devl_gen_trap_group, - [DEVLINK_CMD_TRAP_POLICER_GET] = &devl_gen_trap_policer, - [DEVLINK_CMD_LINECARD_GET] = &devl_gen_linecard, - [DEVLINK_CMD_SELFTESTS_GET] = &devl_gen_selftests, +static const struct devlink_cmd *devl_cmds[] = { + [DEVLINK_CMD_GET] = &devl_cmd_get, + [DEVLINK_CMD_PORT_GET] = &devl_cmd_port_get, + [DEVLINK_CMD_SB_GET] = &devl_cmd_sb_get, + [DEVLINK_CMD_SB_POOL_GET] = &devl_cmd_sb_pool_get, + [DEVLINK_CMD_SB_PORT_POOL_GET] = &devl_cmd_sb_port_pool_get, + [DEVLINK_CMD_SB_TC_POOL_BIND_GET] = &devl_cmd_sb_tc_pool_bind_get, + [DEVLINK_CMD_PARAM_GET] = &devl_cmd_param_get, + [DEVLINK_CMD_REGION_GET] = &devl_cmd_region_get, + [DEVLINK_CMD_INFO_GET] = &devl_cmd_info_get, + [DEVLINK_CMD_HEALTH_REPORTER_GET] = &devl_cmd_health_reporter_get, + [DEVLINK_CMD_TRAP_GET] = &devl_cmd_trap_get, + [DEVLINK_CMD_TRAP_GROUP_GET] = &devl_cmd_trap_group_get, + [DEVLINK_CMD_TRAP_POLICER_GET] = &devl_cmd_trap_policer_get, + [DEVLINK_CMD_RATE_GET] = &devl_cmd_rate_get, + [DEVLINK_CMD_LINECARD_GET] = &devl_cmd_linecard_get, + [DEVLINK_CMD_SELFTESTS_GET] = &devl_cmd_selftests_get, }; -int devlink_nl_instance_iter_dump(struct sk_buff *msg, - struct netlink_callback *cb) +int devlink_nl_instance_iter_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct devlink_nl_dump_state *state = devlink_dump_state(cb); - const struct devlink_gen_cmd *cmd; + const struct devlink_cmd *cmd; struct devlink *devlink; int err = 0; - cmd = devl_gen_cmds[info->op.cmd]; + cmd = devl_cmds[info->op.cmd]; while ((devlink = devlinks_xa_find_get(sock_net(msg->sk), &state->instance))) { diff --git a/net/dsa/master.c b/net/dsa/master.c index 26d90140d271..22d3f16b0e6d 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -299,7 +299,7 @@ static ssize_t tagging_show(struct device *d, struct device_attribute *attr, struct net_device *dev = to_net_dev(d); struct dsa_port *cpu_dp = dev->dsa_ptr; - return sprintf(buf, "%s\n", + return sysfs_emit(buf, "%s\n", dsa_tag_protocol_to_str(cpu_dp->tag_ops)); } @@ -464,9 +464,7 @@ int dsa_master_lag_setup(struct net_device *lag_dev, struct dsa_port *cpu_dp, err = dsa_port_lag_join(cpu_dp, lag_dev, uinfo, extack); if (err) { - if (extack && !extack->_msg) - NL_SET_ERR_MSG_MOD(extack, - "CPU port failed to join LAG"); + NL_SET_ERR_MSG_WEAK_MOD(extack, "CPU port failed to join LAG"); goto out_master_teardown; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 6014ac3aad34..6957971c2db2 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -2692,9 +2692,8 @@ static int dsa_slave_changeupper(struct net_device *dev, if (!err) dsa_bridge_mtu_normalization(dp); if (err == -EOPNOTSUPP) { - if (extack && !extack->_msg) - NL_SET_ERR_MSG_MOD(extack, - "Offloading not supported"); + NL_SET_ERR_MSG_WEAK_MOD(extack, + "Offloading not supported"); err = 0; } err = notifier_from_errno(err); @@ -2707,8 +2706,8 @@ static int dsa_slave_changeupper(struct net_device *dev, err = dsa_port_lag_join(dp, info->upper_dev, info->upper_info, extack); if (err == -EOPNOTSUPP) { - NL_SET_ERR_MSG_MOD(info->info.extack, - "Offloading not supported"); + NL_SET_ERR_MSG_WEAK_MOD(extack, + "Offloading not supported"); err = 0; } err = notifier_from_errno(err); @@ -2720,8 +2719,8 @@ static int dsa_slave_changeupper(struct net_device *dev, if (info->linking) { err = dsa_port_hsr_join(dp, info->upper_dev); if (err == -EOPNOTSUPP) { - NL_SET_ERR_MSG_MOD(info->info.extack, - "Offloading not supported"); + NL_SET_ERR_MSG_WEAK_MOD(extack, + "Offloading not supported"); err = 0; } err = notifier_from_errno(err); diff --git a/net/ethtool/mm.c b/net/ethtool/mm.c index 7e51f7633001..e612856eed8c 100644 --- a/net/ethtool/mm.c +++ b/net/ethtool/mm.c @@ -56,7 +56,7 @@ static int mm_prepare_data(const struct ethnl_req_info *req_base, out_complete: ethnl_ops_complete(dev); - return 0; + return ret; } static int mm_reply_size(const struct ethnl_req_info *req_base, diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 6c0ec2789943..2c778b013cb0 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -347,6 +347,7 @@ lookup_protocol: sk->sk_destruct = inet_sock_destruct; sk->sk_protocol = protocol; sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv; + sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash); inet->uc_ttl = -1; inet->mc_loop = 1; @@ -1485,6 +1486,7 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) if (unlikely(ip_fast_csum((u8 *)iph, 5))) goto out; + NAPI_GRO_CB(skb)->proto = proto; id = ntohl(*(__be32 *)&iph->id); flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id & ~IP_DF)); id >>= 16; @@ -1618,9 +1620,9 @@ int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) int inet_gro_complete(struct sk_buff *skb, int nhoff) { - __be16 newlen = htons(skb->len - nhoff); struct iphdr *iph = (struct iphdr *)(skb->data + nhoff); const struct net_offload *ops; + __be16 totlen = iph->tot_len; int proto = iph->protocol; int err = -ENOSYS; @@ -1629,8 +1631,8 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff) skb_set_inner_network_header(skb, nhoff); } - csum_replace2(&iph->check, iph->tot_len, newlen); - iph->tot_len = newlen; + iph_set_totlen(iph, skb->len - nhoff); + csum_replace2(&iph->check, totlen, iph->tot_len); ops = rcu_dereference(inet_offloads[proto]); if (WARN_ON(!ops || !ops->callbacks.gro_complete)) diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 6cd3b6c559f0..79ae7204e8ed 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -2222,7 +2222,7 @@ int cipso_v4_skbuff_setattr(struct sk_buff *skb, memset((char *)(iph + 1) + buf_len, 0, opt_len - buf_len); if (len_delta != 0) { iph->ihl = 5 + (opt_len >> 2); - iph->tot_len = htons(skb->len); + iph_set_totlen(iph, skb->len); } ip_send_check(iph); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 6ed7e65de494..7d206a10ad14 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1246,9 +1246,6 @@ int inet_csk_listen_start(struct sock *sk) sk->sk_ack_backlog = 0; inet_csk_delack_init(sk); - if (sk->sk_txrehash == SOCK_TXREHASH_DEFAULT) - sk->sk_txrehash = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); - /* There is race window here: we announce ourselves listening, * but this transition is still not validated by get_port(). * It is OK, because this socket enters to hash table only diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index e880ce77322a..fe9ead9ee863 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -511,7 +511,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) goto csum_error; - len = ntohs(iph->tot_len); + len = iph_totlen(skb, iph); if (skb->len < len) { drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL; __IP_INC_STATS(net, IPSTATS_MIB_INTRUNCATEDPKTS); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 922c87ef1ab5..4e4e308c3230 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -100,7 +100,7 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { struct iphdr *iph = ip_hdr(skb); - iph->tot_len = htons(skb->len); + iph_set_totlen(iph, skb->len); ip_send_check(iph); /* if egress device is enslaved to an L3 master device pass the diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 006c1f0ed8b4..94df935ee0c5 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -93,7 +93,7 @@ int raw_hash_sk(struct sock *sk) struct raw_hashinfo *h = sk->sk_prot->h.raw_hash; struct hlist_nulls_head *hlist; - hlist = &h->ht[inet_sk(sk)->inet_num & (RAW_HTABLE_SIZE - 1)]; + hlist = &h->ht[raw_hashfunc(sock_net(sk), inet_sk(sk)->inet_num)]; spin_lock(&h->lock); __sk_nulls_add_node_rcu(sk, hlist); @@ -160,9 +160,9 @@ static int icmp_filter(const struct sock *sk, const struct sk_buff *skb) * RFC 1122: SHOULD pass TOS value up to the transport layer. * -> It does. And not only TOS, but all IP header. */ -static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash) +static int raw_v4_input(struct net *net, struct sk_buff *skb, + const struct iphdr *iph, int hash) { - struct net *net = dev_net(skb->dev); struct hlist_nulls_head *hlist; struct hlist_nulls_node *hnode; int sdif = inet_sdif(skb); @@ -193,9 +193,10 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash) int raw_local_deliver(struct sk_buff *skb, int protocol) { - int hash = protocol & (RAW_HTABLE_SIZE - 1); + struct net *net = dev_net(skb->dev); - return raw_v4_input(skb, ip_hdr(skb), hash); + return raw_v4_input(net, skb, ip_hdr(skb), + raw_hashfunc(net, protocol)); } static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) @@ -271,7 +272,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) struct sock *sk; int hash; - hash = protocol & (RAW_HTABLE_SIZE - 1); + hash = raw_hashfunc(net, protocol); hlist = &raw_v4_hashinfo.ht[hash]; rcu_read_lock(); @@ -287,11 +288,13 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb) { + enum skb_drop_reason reason; + /* Charge it to the socket. */ ipv4_pktinfo_prepare(sk, skb); - if (sock_queue_rcv_skb(sk, skb) < 0) { - kfree_skb(skb); + if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) { + kfree_skb_reason(skb, reason); return NET_RX_DROP; } @@ -302,7 +305,7 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb) { if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) { atomic_inc(&sk->sk_drops); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_XFRM_POLICY); return NET_RX_DROP; } nf_reset_ct(skb); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 94aad3870c5f..cf26d65ca389 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -6,6 +6,7 @@ #include <linux/bpf.h> #include <linux/init.h> #include <linux/wait.h> +#include <linux/util_macros.h> #include <net/inet_common.h> #include <net/tls.h> @@ -639,10 +640,9 @@ EXPORT_SYMBOL_GPL(tcp_bpf_update_proto); */ void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) { - int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4; struct proto *prot = newsk->sk_prot; - if (prot == &tcp_bpf_prots[family][TCP_BPF_BASE]) + if (is_insidevar(prot, tcp_bpf_prots)) newsk->sk_prot = sk->sk_prot_creator; } #endif /* CONFIG_BPF_SYSCALL */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 8320d0ecb13a..ea370afa70ed 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2102,6 +2102,7 @@ process: /* min_ttl can be changed concurrently from do_ip_setsockopt() */ if (unlikely(iph->ttl < READ_ONCE(inet_sk(sk)->min_ttl))) { __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); + drop_reason = SKB_DROP_REASON_TCP_MINTTL; goto discard_and_relse; } } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f7a84a4acffc..faa47f9ea73a 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3127,17 +3127,17 @@ static void add_v4_addrs(struct inet6_dev *idev) offset = sizeof(struct in6_addr) - 4; memcpy(&addr.s6_addr32[3], idev->dev->dev_addr + offset, 4); - if (idev->dev->flags&IFF_POINTOPOINT) { + if (!(idev->dev->flags & IFF_POINTOPOINT) && idev->dev->type == ARPHRD_SIT) { + scope = IPV6_ADDR_COMPATv4; + plen = 96; + pflags |= RTF_NONEXTHOP; + } else { if (idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_NONE) return; addr.s6_addr32[0] = htonl(0xfe800000); scope = IFA_LINK; plen = 64; - } else { - scope = IPV6_ADDR_COMPATv4; - plen = 96; - pflags |= RTF_NONEXTHOP; } if (addr.s6_addr32[3]) { @@ -3447,6 +3447,30 @@ static void addrconf_gre_config(struct net_device *dev) } #endif +static void addrconf_init_auto_addrs(struct net_device *dev) +{ + switch (dev->type) { +#if IS_ENABLED(CONFIG_IPV6_SIT) + case ARPHRD_SIT: + addrconf_sit_config(dev); + break; +#endif +#if IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE) + case ARPHRD_IP6GRE: + case ARPHRD_IPGRE: + addrconf_gre_config(dev); + break; +#endif + case ARPHRD_LOOPBACK: + init_loopback(dev); + break; + + default: + addrconf_dev_config(dev); + break; + } +} + static int fixup_permanent_addr(struct net *net, struct inet6_dev *idev, struct inet6_ifaddr *ifp) @@ -3615,26 +3639,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, run_pending = 1; } - switch (dev->type) { -#if IS_ENABLED(CONFIG_IPV6_SIT) - case ARPHRD_SIT: - addrconf_sit_config(dev); - break; -#endif -#if IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE) - case ARPHRD_IP6GRE: - case ARPHRD_IPGRE: - addrconf_gre_config(dev); - break; -#endif - case ARPHRD_LOOPBACK: - init_loopback(dev); - break; - - default: - addrconf_dev_config(dev); - break; - } + addrconf_init_auto_addrs(dev); if (!IS_ERR_OR_NULL(idev)) { if (run_pending) @@ -6397,7 +6402,7 @@ static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write, if (idev->cnf.addr_gen_mode != new_val) { idev->cnf.addr_gen_mode = new_val; - addrconf_dev_config(idev->dev); + addrconf_init_auto_addrs(idev->dev); } } else if (&net->ipv6.devconf_all->addr_gen_mode == ctl->data) { struct net_device *dev; @@ -6408,7 +6413,7 @@ static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write, if (idev && idev->cnf.addr_gen_mode != new_val) { idev->cnf.addr_gen_mode = new_val; - addrconf_dev_config(idev->dev); + addrconf_init_auto_addrs(idev->dev); } } } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index fee9163382c2..847934763868 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -222,6 +222,7 @@ lookup_protocol: np->pmtudisc = IPV6_PMTUDISC_WANT; np->repflow = net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_ESTABLISHED; sk->sk_ipv6only = net->ipv6.sysctl.bindv6only; + sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash); /* Init the ipv4 part of the socket since we can have sockets * using v6 API for ipv4. diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 79c769c0d113..c9346515e24d 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -332,7 +332,6 @@ static void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt { struct ipv6hdr *iph = ipv6_hdr(skb); struct ipv6_destopt_hao *hao; - struct in6_addr tmp; int off; if (opt->dsthao) { @@ -340,9 +339,7 @@ static void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt if (likely(off >= 0)) { hao = (struct ipv6_destopt_hao *) (skb_network_header(skb) + off); - tmp = iph->saddr; - iph->saddr = hao->addr; - hao->addr = tmp; + swap(iph->saddr, hao->addr); } } } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ada087b50541..bac9ba747bde 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -152,7 +152,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) saddr = &ipv6_hdr(skb)->saddr; daddr = saddr + 1; - hash = nexthdr & (RAW_HTABLE_SIZE - 1); + hash = raw_hashfunc(net, nexthdr); hlist = &raw_v6_hashinfo.ht[hash]; rcu_read_lock(); sk_nulls_for_each(sk, hnode, hlist) { @@ -338,7 +338,7 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, struct sock *sk; int hash; - hash = nexthdr & (RAW_HTABLE_SIZE - 1); + hash = raw_hashfunc(net, nexthdr); hlist = &raw_v6_hashinfo.ht[hash]; rcu_read_lock(); sk_nulls_for_each(sk, hnode, hlist) { @@ -355,17 +355,19 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb) { + enum skb_drop_reason reason; + if ((raw6_sk(sk)->checksum || rcu_access_pointer(sk->sk_filter)) && skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_SKB_CSUM); return NET_RX_DROP; } /* Charge it to the socket. */ skb_dst_drop(skb); - if (sock_queue_rcv_skb(sk, skb) < 0) { - kfree_skb(skb); + if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) { + kfree_skb_reason(skb, reason); return NET_RX_DROP; } @@ -386,7 +388,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { atomic_inc(&sk->sk_drops); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_XFRM_POLICY); return NET_RX_DROP; } @@ -410,7 +412,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) if (inet->hdrincl) { if (skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_SKB_CSUM); return NET_RX_DROP; } } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 11b736a76bd7..543ee2167720 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1708,8 +1708,9 @@ process: if (static_branch_unlikely(&ip6_min_hopcount)) { /* min_hopcount can be changed concurrently from do_ipv6_setsockopt() */ - if (hdr->hop_limit < READ_ONCE(tcp_inet6_sk(sk)->min_hopcount)) { + if (unlikely(hdr->hop_limit < READ_ONCE(tcp_inet6_sk(sk)->min_hopcount))) { __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); + drop_reason = SKB_DROP_REASON_TCP_MINTTL; goto discard_and_relse; } } diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index c2aae2a6d6a6..97bb4401dd3e 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -213,7 +213,6 @@ __ieee802154_rx_handle_packet(struct ieee802154_local *local, ret = ieee802154_parse_frame_start(skb, &hdr); if (ret) { pr_debug("got invalid frame\n"); - kfree_skb(skb); return; } diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index 45bbe3e54cc2..3150f3f0c872 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -587,6 +587,11 @@ static void mctp_sk_unhash(struct sock *sk) del_timer_sync(&msk->key_expiry); } +static void mctp_sk_destruct(struct sock *sk) +{ + skb_queue_purge(&sk->sk_receive_queue); +} + static struct proto mctp_proto = { .name = "MCTP", .owner = THIS_MODULE, @@ -623,6 +628,7 @@ static int mctp_pf_create(struct net *net, struct socket *sock, return -ENOMEM; sock_init_data(sock, sk); + sk->sk_destruct = mctp_sk_destruct; rc = 0; if (sk->sk_prot->init) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index db07cc5b4fcb..56628b52d100 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1002,8 +1002,8 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, { int addrlen = sizeof(struct sockaddr_in); struct sockaddr_storage addr; - struct mptcp_sock *msk; struct socket *ssock; + struct sock *newsk; int backlog = 1024; int err; @@ -1012,11 +1012,13 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, if (err) return err; - msk = mptcp_sk(entry->lsk->sk); - if (!msk) + newsk = entry->lsk->sk; + if (!newsk) return -EINVAL; - ssock = __mptcp_nmpc_socket(msk); + lock_sock(newsk); + ssock = __mptcp_nmpc_socket(mptcp_sk(newsk)); + release_sock(newsk); if (!ssock) return -EINVAL; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 1ff2efbab29e..c9817aa0f413 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2902,6 +2902,7 @@ bool __mptcp_close(struct sock *sk, long timeout) struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); bool do_cancel_work = false; + int subflows_alive = 0; sk->sk_shutdown = SHUTDOWN_MASK; @@ -2928,6 +2929,8 @@ cleanup: struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast_nested(ssk); + subflows_alive += ssk->sk_state != TCP_CLOSE; + /* since the close timeout takes precedence on the fail one, * cancel the latter */ @@ -2943,6 +2946,12 @@ cleanup: } sock_orphan(sk); + /* all the subflows are closed, only timeout can change the msk + * state, let's not keep resources busy for no reasons + */ + if (subflows_alive == 0) + inet_sk_state_store(sk, TCP_CLOSE); + sock_hold(sk); pr_debug("msk=%p state=%d", sk, sk->sk_state); if (msk->token) diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 9986681aaf40..8a9656248b0f 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -760,14 +760,21 @@ static int mptcp_setsockopt_v4(struct mptcp_sock *msk, int optname, static int mptcp_setsockopt_first_sf_only(struct mptcp_sock *msk, int level, int optname, sockptr_t optval, unsigned int optlen) { + struct sock *sk = (struct sock *)msk; struct socket *sock; + int ret = -EINVAL; /* Limit to first subflow, before the connection establishment */ + lock_sock(sk); sock = __mptcp_nmpc_socket(msk); if (!sock) - return -EINVAL; + goto unlock; - return tcp_setsockopt(sock->sk, level, optname, optval, optlen); + ret = tcp_setsockopt(sock->sk, level, optname, optval, optlen); + +unlock: + release_sock(sk); + return ret; } static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index beaec843f5ca..4ae1a7304cf0 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1400,6 +1400,7 @@ void __mptcp_error_report(struct sock *sk) mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); int err = sock_error(ssk); + int ssk_state; if (!err) continue; @@ -1410,7 +1411,14 @@ void __mptcp_error_report(struct sock *sk) if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk)) continue; - inet_sk_state_store(sk, inet_sk_state_load(ssk)); + /* We need to propagate only transition to CLOSE state. + * Orphaned socket will see such state change via + * subflow_sched_work_if_closed() and that path will properly + * destroy the msk as needed. + */ + ssk_state = inet_sk_state_load(ssk); + if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) + inet_sk_state_store(sk, ssk_state); sk->sk_err = -err; /* This barrier is coupled with smp_rmb() in mptcp_poll() */ @@ -1682,7 +1690,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, if (err) return err; - lock_sock(sf->sk); + lock_sock_nested(sf->sk, SINGLE_DEPTH_NESTING); /* the newly created socket has to be in the same cgroup as its parent */ mptcp_attach_cgroup(sk, sf->sk); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index f71b41c7ce2f..4d6737160857 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -189,6 +189,9 @@ config NF_CONNTRACK_LABELS to connection tracking entries. It can be used with xtables connlabel match and the nftables ct expression. +config NF_CONNTRACK_OVS + bool + config NF_CT_PROTO_DCCP bool 'DCCP protocol connection tracking support' depends on NETFILTER_ADVANCED diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index ba2a6b5e93d9..5ffef1cd6143 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -11,6 +11,7 @@ nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMEOUT) += nf_conntrack_timeout.o nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o nf_conntrack-$(CONFIG_NF_CONNTRACK_LABELS) += nf_conntrack_labels.o +nf_conntrack-$(CONFIG_NF_CONNTRACK_OVS) += nf_conntrack_ovs.o nf_conntrack-$(CONFIG_NF_CT_PROTO_DCCP) += nf_conntrack_proto_dccp.o nf_conntrack-$(CONFIG_NF_CT_PROTO_SCTP) += nf_conntrack_proto_sctp.o nf_conntrack-$(CONFIG_NF_CT_PROTO_GRE) += nf_conntrack_proto_gre.o diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 029171379884..80448885c3d7 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -994,7 +994,7 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af, old_dsfield = ipv4_get_dsfield(old_iph); *ttl = old_iph->ttl; if (payload_len) - *payload_len = ntohs(old_iph->tot_len); + *payload_len = skb_ip_totlen(skb); } /* Implement full-functionality option for ECN encapsulation */ diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index c00858344f02..9a830573480e 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1371,9 +1371,6 @@ static unsigned int early_drop_list(struct net *net, hlist_nulls_for_each_entry_rcu(h, n, head, hnnode) { tmp = nf_ct_tuplehash_to_ctrack(h); - if (test_bit(IPS_OFFLOAD_BIT, &tmp->status)) - continue; - if (nf_ct_is_expired(tmp)) { nf_ct_gc_expired(tmp); continue; @@ -1443,11 +1440,14 @@ static bool gc_worker_skip_ct(const struct nf_conn *ct) static bool gc_worker_can_early_drop(const struct nf_conn *ct) { const struct nf_conntrack_l4proto *l4proto; + u8 protonum = nf_ct_protonum(ct); + if (test_bit(IPS_OFFLOAD_BIT, &ct->status) && protonum != IPPROTO_UDP) + return false; if (!test_bit(IPS_ASSURED_BIT, &ct->status)) return true; - l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); + l4proto = nf_ct_l4proto_find(protonum); if (l4proto->can_early_drop && l4proto->can_early_drop(ct)) return true; @@ -1504,7 +1504,8 @@ static void gc_worker(struct work_struct *work) if (test_bit(IPS_OFFLOAD_BIT, &tmp->status)) { nf_ct_offload_timeout(tmp); - continue; + if (!nf_conntrack_max95) + continue; } if (expired_count > GC_SCAN_EXPIRED_MAX) { diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 48ea6d0264b5..0c4db2f2ac43 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -242,104 +242,6 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, } EXPORT_SYMBOL_GPL(__nf_ct_try_assign_helper); -/* 'skb' should already be pulled to nh_ofs. */ -int nf_ct_helper(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo, u16 proto) -{ - const struct nf_conntrack_helper *helper; - const struct nf_conn_help *help; - unsigned int protoff; - int err; - - if (ctinfo == IP_CT_RELATED_REPLY) - return NF_ACCEPT; - - help = nfct_help(ct); - if (!help) - return NF_ACCEPT; - - helper = rcu_dereference(help->helper); - if (!helper) - return NF_ACCEPT; - - if (helper->tuple.src.l3num != NFPROTO_UNSPEC && - helper->tuple.src.l3num != proto) - return NF_ACCEPT; - - switch (proto) { - case NFPROTO_IPV4: - protoff = ip_hdrlen(skb); - proto = ip_hdr(skb)->protocol; - break; - case NFPROTO_IPV6: { - u8 nexthdr = ipv6_hdr(skb)->nexthdr; - __be16 frag_off; - int ofs; - - ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, - &frag_off); - if (ofs < 0 || (frag_off & htons(~0x7)) != 0) { - pr_debug("proto header not found\n"); - return NF_ACCEPT; - } - protoff = ofs; - proto = nexthdr; - break; - } - default: - WARN_ONCE(1, "helper invoked on non-IP family!"); - return NF_DROP; - } - - if (helper->tuple.dst.protonum != proto) - return NF_ACCEPT; - - err = helper->help(skb, protoff, ct, ctinfo); - if (err != NF_ACCEPT) - return err; - - /* Adjust seqs after helper. This is needed due to some helpers (e.g., - * FTP with NAT) adusting the TCP payload size when mangling IP - * addresses and/or port numbers in the text-based control connection. - */ - if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && - !nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) - return NF_DROP; - return NF_ACCEPT; -} -EXPORT_SYMBOL_GPL(nf_ct_helper); - -int nf_ct_add_helper(struct nf_conn *ct, const char *name, u8 family, - u8 proto, bool nat, struct nf_conntrack_helper **hp) -{ - struct nf_conntrack_helper *helper; - struct nf_conn_help *help; - int ret = 0; - - helper = nf_conntrack_helper_try_module_get(name, family, proto); - if (!helper) - return -EINVAL; - - help = nf_ct_helper_ext_add(ct, GFP_KERNEL); - if (!help) { - nf_conntrack_helper_put(helper); - return -ENOMEM; - } -#if IS_ENABLED(CONFIG_NF_NAT) - if (nat) { - ret = nf_nat_helper_try_module_get(name, family, proto); - if (ret) { - nf_conntrack_helper_put(helper); - return ret; - } - } -#endif - rcu_assign_pointer(help->helper, helper); - *hp = helper; - return ret; -} -EXPORT_SYMBOL_GPL(nf_ct_add_helper); - /* appropriate ct lock protecting must be taken by caller */ static int unhelp(struct nf_conn *ct, void *me) { diff --git a/net/netfilter/nf_conntrack_ovs.c b/net/netfilter/nf_conntrack_ovs.c new file mode 100644 index 000000000000..52b776bdf526 --- /dev/null +++ b/net/netfilter/nf_conntrack_ovs.c @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Support ct functions for openvswitch and used by OVS and TC conntrack. */ + +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_seqadj.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> +#include <net/ipv6_frag.h> +#include <net/ip.h> + +/* 'skb' should already be pulled to nh_ofs. */ +int nf_ct_helper(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, u16 proto) +{ + const struct nf_conntrack_helper *helper; + const struct nf_conn_help *help; + unsigned int protoff; + int err; + + if (ctinfo == IP_CT_RELATED_REPLY) + return NF_ACCEPT; + + help = nfct_help(ct); + if (!help) + return NF_ACCEPT; + + helper = rcu_dereference(help->helper); + if (!helper) + return NF_ACCEPT; + + if (helper->tuple.src.l3num != NFPROTO_UNSPEC && + helper->tuple.src.l3num != proto) + return NF_ACCEPT; + + switch (proto) { + case NFPROTO_IPV4: + protoff = ip_hdrlen(skb); + proto = ip_hdr(skb)->protocol; + break; + case NFPROTO_IPV6: { + u8 nexthdr = ipv6_hdr(skb)->nexthdr; + __be16 frag_off; + int ofs; + + ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, + &frag_off); + if (ofs < 0 || (frag_off & htons(~0x7)) != 0) { + pr_debug("proto header not found\n"); + return NF_ACCEPT; + } + protoff = ofs; + proto = nexthdr; + break; + } + default: + WARN_ONCE(1, "helper invoked on non-IP family!"); + return NF_DROP; + } + + if (helper->tuple.dst.protonum != proto) + return NF_ACCEPT; + + err = helper->help(skb, protoff, ct, ctinfo); + if (err != NF_ACCEPT) + return err; + + /* Adjust seqs after helper. This is needed due to some helpers (e.g., + * FTP with NAT) adusting the TCP payload size when mangling IP + * addresses and/or port numbers in the text-based control connection. + */ + if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && + !nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) + return NF_DROP; + return NF_ACCEPT; +} +EXPORT_SYMBOL_GPL(nf_ct_helper); + +int nf_ct_add_helper(struct nf_conn *ct, const char *name, u8 family, + u8 proto, bool nat, struct nf_conntrack_helper **hp) +{ + struct nf_conntrack_helper *helper; + struct nf_conn_help *help; + int ret = 0; + + helper = nf_conntrack_helper_try_module_get(name, family, proto); + if (!helper) + return -EINVAL; + + help = nf_ct_helper_ext_add(ct, GFP_KERNEL); + if (!help) { + nf_conntrack_helper_put(helper); + return -ENOMEM; + } +#if IS_ENABLED(CONFIG_NF_NAT) + if (nat) { + ret = nf_nat_helper_try_module_get(name, family, proto); + if (ret) { + nf_conntrack_helper_put(helper); + return ret; + } + } +#endif + rcu_assign_pointer(help->helper, helper); + *hp = helper; + return ret; +} +EXPORT_SYMBOL_GPL(nf_ct_add_helper); + +/* Trim the skb to the length specified by the IP/IPv6 header, + * removing any trailing lower-layer padding. This prepares the skb + * for higher-layer processing that assumes skb->len excludes padding + * (such as nf_ip_checksum). The caller needs to pull the skb to the + * network header, and ensure ip_hdr/ipv6_hdr points to valid data. + */ +int nf_ct_skb_network_trim(struct sk_buff *skb, int family) +{ + unsigned int len; + + switch (family) { + case NFPROTO_IPV4: + len = skb_ip_totlen(skb); + break; + case NFPROTO_IPV6: + len = sizeof(struct ipv6hdr) + + ntohs(ipv6_hdr(skb)->payload_len); + break; + default: + len = skb->len; + } + + return pskb_trim_rcsum(skb, len); +} +EXPORT_SYMBOL_GPL(nf_ct_skb_network_trim); + +/* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero + * value if 'skb' is freed. + */ +int nf_ct_handle_fragments(struct net *net, struct sk_buff *skb, + u16 zone, u8 family, u8 *proto, u16 *mru) +{ + int err; + + if (family == NFPROTO_IPV4) { + enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone; + + memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + local_bh_disable(); + err = ip_defrag(net, skb, user); + local_bh_enable(); + if (err) + return err; + + *mru = IPCB(skb)->frag_max_size; +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) + } else if (family == NFPROTO_IPV6) { + enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone; + + memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); + err = nf_ct_frag6_gather(net, skb, user); + if (err) { + if (err != -EINPROGRESS) + kfree_skb(skb); + return err; + } + + *proto = ipv6_hdr(skb)->nexthdr; + *mru = IP6CB(skb)->frag_max_size; +#endif + } else { + kfree_skb(skb); + return -EPFNOSUPPORT; + } + + skb_clear_hash(skb); + skb->ignore_df = 1; + + return 0; +} +EXPORT_SYMBOL_GPL(nf_ct_handle_fragments); diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 3937cbee9418..91eacc9b0b98 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -142,10 +142,11 @@ static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct) } #endif +/* do_basic_checks ensures sch->length > 0, do not use before */ #define for_each_sctp_chunk(skb, sch, _sch, offset, dataoff, count) \ for ((offset) = (dataoff) + sizeof(struct sctphdr), (count) = 0; \ - ((sch) = skb_header_pointer((skb), (offset), sizeof(_sch), &(_sch))) && \ - (sch)->length; \ + (offset) < (skb)->len && \ + ((sch) = skb_header_pointer((skb), (offset), sizeof(_sch), &(_sch))); \ (offset) += (ntohs((sch)->length) + 3) & ~3, (count)++) /* Some validity checks to make sure the chunks are fine */ diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 81c26a96c30b..04bd0ed4d2ae 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -193,8 +193,11 @@ static void flow_offload_fixup_ct(struct nf_conn *ct) timeout -= tn->offload_timeout; } else if (l4num == IPPROTO_UDP) { struct nf_udp_net *tn = nf_udp_pernet(net); + enum udp_conntrack state = + test_bit(IPS_SEEN_REPLY_BIT, &ct->status) ? + UDP_CT_REPLIED : UDP_CT_UNREPLIED; - timeout = tn->timeouts[UDP_CT_REPLIED]; + timeout = tn->timeouts[state]; timeout -= tn->offload_timeout; } else { return; diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 0ccabf3fa6aa..9505f9d188ff 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -39,7 +39,7 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb, } static int nf_flow_rule_route_inet(struct net *net, - const struct flow_offload *flow, + struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 4d9b99abe37d..1c26f03fc661 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -679,7 +679,7 @@ nf_flow_rule_route_common(struct net *net, const struct flow_offload *flow, return 0; } -int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow, +int nf_flow_rule_route_ipv4(struct net *net, struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { @@ -704,7 +704,7 @@ int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow, } EXPORT_SYMBOL_GPL(nf_flow_rule_route_ipv4); -int nf_flow_rule_route_ipv6(struct net *net, const struct flow_offload *flow, +int nf_flow_rule_route_ipv6(struct net *net, struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { @@ -735,7 +735,7 @@ nf_flow_offload_rule_alloc(struct net *net, { const struct nf_flowtable *flowtable = offload->flowtable; const struct flow_offload_tuple *tuple, *other_tuple; - const struct flow_offload *flow = offload->flow; + struct flow_offload *flow = offload->flow; struct dst_entry *other_dst = NULL; struct nf_flow_rule *flow_rule; int err = -ENOMEM; @@ -895,8 +895,9 @@ static int flow_offload_rule_add(struct flow_offload_work *offload, ok_count += flow_offload_tuple_add(offload, flow_rule[0], FLOW_OFFLOAD_DIR_ORIGINAL); - ok_count += flow_offload_tuple_add(offload, flow_rule[1], - FLOW_OFFLOAD_DIR_REPLY); + if (test_bit(NF_FLOW_HW_BIDIRECTIONAL, &offload->flow->flags)) + ok_count += flow_offload_tuple_add(offload, flow_rule[1], + FLOW_OFFLOAD_DIR_REPLY); if (ok_count == 0) return -ENOENT; @@ -926,7 +927,8 @@ static void flow_offload_work_del(struct flow_offload_work *offload) { clear_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status); flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_ORIGINAL); - flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_REPLY); + if (test_bit(NF_FLOW_HW_BIDIRECTIONAL, &offload->flow->flags)) + flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_REPLY); set_bit(NF_FLOW_HW_DEAD, &offload->flow->flags); } @@ -946,7 +948,9 @@ static void flow_offload_work_stats(struct flow_offload_work *offload) u64 lastused; flow_offload_tuple_stats(offload, FLOW_OFFLOAD_DIR_ORIGINAL, &stats[0]); - flow_offload_tuple_stats(offload, FLOW_OFFLOAD_DIR_REPLY, &stats[1]); + if (test_bit(NF_FLOW_HW_BIDIRECTIONAL, &offload->flow->flags)) + flow_offload_tuple_stats(offload, FLOW_OFFLOAD_DIR_REPLY, + &stats[1]); lastused = max_t(u64, stats[0].lastused, stats[1].lastused); offload->flow->timeout = max_t(u64, offload->flow->timeout, diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c index cb894f0d63e9..c66689ad2b49 100644 --- a/net/netfilter/nf_log_syslog.c +++ b/net/netfilter/nf_log_syslog.c @@ -322,7 +322,7 @@ dump_ipv4_packet(struct net *net, struct nf_log_buf *m, /* Max length: 46 "LEN=65535 TOS=0xFF PREC=0xFF TTL=255 ID=65535 " */ nf_log_buf_add(m, "LEN=%u TOS=0x%02X PREC=0x%02X TTL=%u ID=%u ", - ntohs(ih->tot_len), ih->tos & IPTOS_TOS_MASK, + iph_totlen(skb, ih), ih->tos & IPTOS_TOS_MASK, ih->tos & IPTOS_PREC_MASK, ih->ttl, ntohs(ih->id)); /* Max length: 6 "CE DF MF " */ diff --git a/net/netfilter/xt_length.c b/net/netfilter/xt_length.c index 1873da3a945a..b3d623a52885 100644 --- a/net/netfilter/xt_length.c +++ b/net/netfilter/xt_length.c @@ -21,7 +21,7 @@ static bool length_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_length_info *info = par->matchinfo; - u_int16_t pktlen = ntohs(ip_hdr(skb)->tot_len); + u32 pktlen = skb_ip_totlen(skb); return (pktlen >= info->min && pktlen <= info->max) ^ info->invert; } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 600993c80050..04c4036bf406 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -13,7 +13,7 @@ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> -#include <linux/string.h> +#include <linux/string_helpers.h> #include <linux/skbuff.h> #include <linux/mutex.h> #include <linux/bitmap.h> @@ -457,7 +457,7 @@ static int genl_validate_assign_mc_groups(struct genl_family *family) if (WARN_ON(grp->name[0] == '\0')) return -EINVAL; - if (WARN_ON(memchr(grp->name, '\0', GENL_NAMSIZ) == NULL)) + if (WARN_ON(!string_is_terminated(grp->name, GENL_NAMSIZ))) return -EINVAL; } diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 6f7f4392cffb..5a4cb796150f 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -400,6 +400,11 @@ static int nr_listen(struct socket *sock, int backlog) struct sock *sk = sock->sk; lock_sock(sk); + if (sock->state != SS_UNCONNECTED) { + release_sock(sk); + return -EINVAL; + } + if (sk->sk_state != TCP_LISTEN) { memset(&nr_sk(sk)->user_addr, 0, AX25_ADDR_LEN); sk->sk_max_ack_backlog = backlog; diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index 747d537a3f06..29a7081858cd 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -15,6 +15,7 @@ config OPENVSWITCH select NET_MPLS_GSO select DST_CACHE select NET_NSH + select NF_CONNTRACK_OVS if NF_CONNTRACK select NF_NAT_OVS if NF_NAT help Open vSwitch is a multilayer Ethernet switch targeted at virtualized diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index c8b137649ca4..331730fd3580 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -9,6 +9,7 @@ #include <linux/udp.h> #include <linux/sctp.h> #include <linux/static_key.h> +#include <linux/string_helpers.h> #include <net/ip.h> #include <net/genetlink.h> #include <net/netfilter/nf_conntrack_core.h> @@ -434,52 +435,21 @@ static int ovs_ct_set_labels(struct nf_conn *ct, struct sw_flow_key *key, return 0; } -/* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero - * value if 'skb' is freed. - */ -static int handle_fragments(struct net *net, struct sw_flow_key *key, - u16 zone, struct sk_buff *skb) +static int ovs_ct_handle_fragments(struct net *net, struct sw_flow_key *key, + u16 zone, int family, struct sk_buff *skb) { struct ovs_skb_cb ovs_cb = *OVS_CB(skb); int err; - if (key->eth.type == htons(ETH_P_IP)) { - enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone; - - memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); - err = ip_defrag(net, skb, user); - if (err) - return err; - - ovs_cb.mru = IPCB(skb)->frag_max_size; -#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) - } else if (key->eth.type == htons(ETH_P_IPV6)) { - enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone; - - memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); - err = nf_ct_frag6_gather(net, skb, user); - if (err) { - if (err != -EINPROGRESS) - kfree_skb(skb); - return err; - } - - key->ip.proto = ipv6_hdr(skb)->nexthdr; - ovs_cb.mru = IP6CB(skb)->frag_max_size; -#endif - } else { - kfree_skb(skb); - return -EPFNOSUPPORT; - } + err = nf_ct_handle_fragments(net, skb, zone, family, &key->ip.proto, &ovs_cb.mru); + if (err) + return err; /* The key extracted from the fragment that completed this datagram * likely didn't have an L4 header, so regenerate it. */ ovs_flow_key_update_l3l4(skb, key); - key->ip.frag = OVS_FRAG_TYPE_NONE; - skb_clear_hash(skb); - skb->ignore_df = 1; *OVS_CB(skb) = ovs_cb; return 0; @@ -1090,36 +1060,6 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, return 0; } -/* Trim the skb to the length specified by the IP/IPv6 header, - * removing any trailing lower-layer padding. This prepares the skb - * for higher-layer processing that assumes skb->len excludes padding - * (such as nf_ip_checksum). The caller needs to pull the skb to the - * network header, and ensure ip_hdr/ipv6_hdr points to valid data. - */ -static int ovs_skb_network_trim(struct sk_buff *skb) -{ - unsigned int len; - int err; - - switch (skb->protocol) { - case htons(ETH_P_IP): - len = ntohs(ip_hdr(skb)->tot_len); - break; - case htons(ETH_P_IPV6): - len = sizeof(struct ipv6hdr) - + ntohs(ipv6_hdr(skb)->payload_len); - break; - default: - len = skb->len; - } - - err = pskb_trim_rcsum(skb, len); - if (err) - kfree_skb(skb); - - return err; -} - /* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero * value if 'skb' is freed. */ @@ -1134,12 +1074,15 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, nh_ofs = skb_network_offset(skb); skb_pull_rcsum(skb, nh_ofs); - err = ovs_skb_network_trim(skb); - if (err) + err = nf_ct_skb_network_trim(skb, info->family); + if (err) { + kfree_skb(skb); return err; + } if (key->ip.frag != OVS_FRAG_TYPE_NONE) { - err = handle_fragments(net, key, info->zone.id, skb); + err = ovs_ct_handle_fragments(net, key, info->zone.id, + info->family, skb); if (err) return err; } @@ -1383,7 +1326,7 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, #endif case OVS_CT_ATTR_HELPER: *helper = nla_data(a); - if (!memchr(*helper, '\0', nla_len(a))) { + if (!string_is_terminated(*helper, nla_len(a))) { OVS_NLERR(log, "Invalid conntrack helper"); return -EINVAL; } @@ -1404,7 +1347,7 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, #ifdef CONFIG_NF_CONNTRACK_TIMEOUT case OVS_CT_ATTR_TIMEOUT: memcpy(info->timeout, nla_data(a), nla_len(a)); - if (!memchr(info->timeout, '\0', nla_len(a))) { + if (!string_is_terminated(info->timeout, nla_len(a))) { OVS_NLERR(log, "Invalid conntrack timeout"); return -EINVAL; } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index a71795355aec..fcee6012293b 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1004,14 +1004,14 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) key = kzalloc(sizeof(*key), GFP_KERNEL); if (!key) { error = -ENOMEM; - goto err_kfree_key; + goto err_kfree_flow; } ovs_match_init(&match, key, false, &mask); error = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK], log); if (error) - goto err_kfree_flow; + goto err_kfree_key; ovs_flow_mask_key(&new_flow->key, key, true, &mask); @@ -1019,14 +1019,14 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID], key, log); if (error) - goto err_kfree_flow; + goto err_kfree_key; /* Validate actions. */ error = ovs_nla_copy_actions(net, a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key, &acts, log); if (error) { OVS_NLERR(log, "Flow actions may not be safe on all matching packets."); - goto err_kfree_flow; + goto err_kfree_key; } reply = ovs_flow_cmd_alloc_info(acts, &new_flow->id, info, false, @@ -1126,10 +1126,10 @@ err_unlock_ovs: kfree_skb(reply); err_kfree_acts: ovs_nla_free_flow_actions(acts); -err_kfree_flow: - ovs_flow_free(new_flow, false); err_kfree_key: kfree(key); +err_kfree_flow: + ovs_flow_free(new_flow, false); error: return error; } diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index e20d1a973417..416976f70322 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -107,7 +107,8 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags, rcu_assign_pointer(flow->stats[cpu], new_stats); - cpumask_set_cpu(cpu, &flow->cpu_used_mask); + cpumask_set_cpu(cpu, + flow->cpu_used_mask); goto unlock; } } @@ -135,7 +136,8 @@ void ovs_flow_stats_get(const struct sw_flow *flow, memset(ovs_stats, 0, sizeof(*ovs_stats)); /* We open code this to make sure cpu 0 is always considered */ - for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) { + for (cpu = 0; cpu < nr_cpu_ids; + cpu = cpumask_next(cpu, flow->cpu_used_mask)) { struct sw_flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]); if (stats) { @@ -159,7 +161,8 @@ void ovs_flow_stats_clear(struct sw_flow *flow) int cpu; /* We open code this to make sure cpu 0 is always considered */ - for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) { + for (cpu = 0; cpu < nr_cpu_ids; + cpu = cpumask_next(cpu, flow->cpu_used_mask)) { struct sw_flow_stats *stats = ovsl_dereference(flow->stats[cpu]); if (stats) { diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 073ab73ffeaa..b5711aff6e76 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -229,7 +229,7 @@ struct sw_flow { */ struct sw_flow_key key; struct sw_flow_id id; - struct cpumask cpu_used_mask; + struct cpumask *cpu_used_mask; struct sw_flow_mask *mask; struct sw_flow_actions __rcu *sf_acts; struct sw_flow_stats __rcu *stats[]; /* One for each CPU. First one diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 0a0e4c283f02..791504b7f42b 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -79,6 +79,7 @@ struct sw_flow *ovs_flow_alloc(void) return ERR_PTR(-ENOMEM); flow->stats_last_writer = -1; + flow->cpu_used_mask = (struct cpumask *)&flow->stats[nr_cpu_ids]; /* Initialize the default stat node. */ stats = kmem_cache_alloc_node(flow_stats_cache, @@ -91,7 +92,7 @@ struct sw_flow *ovs_flow_alloc(void) RCU_INIT_POINTER(flow->stats[0], stats); - cpumask_set_cpu(0, &flow->cpu_used_mask); + cpumask_set_cpu(0, flow->cpu_used_mask); return flow; err: @@ -115,7 +116,7 @@ static void flow_free(struct sw_flow *flow) flow->sf_acts); /* We open code this to make sure cpu 0 is always considered */ for (cpu = 0; cpu < nr_cpu_ids; - cpu = cpumask_next(cpu, &flow->cpu_used_mask)) { + cpu = cpumask_next(cpu, flow->cpu_used_mask)) { if (flow->stats[cpu]) kmem_cache_free(flow_stats_cache, (struct sw_flow_stats __force *)flow->stats[cpu]); @@ -1196,7 +1197,8 @@ int ovs_flow_init(void) flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow) + (nr_cpu_ids - * sizeof(struct sw_flow_stats *)), + * sizeof(struct sw_flow_stats *)) + + cpumask_size(), 0, 0, NULL); if (flow_cache == NULL) return -ENOMEM; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index b5ab98ca2511..8ffb19c643ab 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2296,6 +2296,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, else if (skb->pkt_type != PACKET_OUTGOING && skb_csum_unnecessary(skb)) status |= TP_STATUS_CSUM_VALID; + if (skb_is_gso(skb) && skb_is_gso_tcp(skb)) + status |= TP_STATUS_GSO_TCP; if (snaplen > res) snaplen = res; @@ -3522,6 +3524,8 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, else if (skb->pkt_type != PACKET_OUTGOING && skb_csum_unnecessary(skb)) aux.tp_status |= TP_STATUS_CSUM_VALID; + if (skb_is_gso(skb) && skb_is_gso_tcp(skb)) + aux.tp_status |= TP_STATUS_GSO_TCP; aux.tp_len = origlen; aux.tp_snaplen = skb->len; diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index 97bfdf9fd028..722936f7dd98 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -84,7 +84,10 @@ static struct qrtr_node *node_get(unsigned int node_id) node->id = node_id; - radix_tree_insert(&nodes, node_id, node); + if (radix_tree_insert(&nodes, node_id, node)) { + kfree(node); + return NULL; + } return node; } diff --git a/net/rds/message.c b/net/rds/message.c index b47e4f0a1639..c19c93561227 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -104,9 +104,9 @@ static void rds_rm_zerocopy_callback(struct rds_sock *rs, spin_lock_irqsave(&q->lock, flags); head = &q->zcookie_head; if (!list_empty(head)) { - info = list_entry(head, struct rds_msg_zcopy_info, - rs_zcookie_next); - if (info && rds_zcookie_add(info, cookie)) { + info = list_first_entry(head, struct rds_msg_zcopy_info, + rs_zcookie_next); + if (rds_zcookie_add(info, cookie)) { spin_unlock_irqrestore(&q->lock, flags); kfree(rds_info_from_znotifier(znotif)); /* caller invokes rds_wake_sk_sleep() */ diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 36fefc3957d7..ca2b17f32670 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -488,6 +488,12 @@ static int rose_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; + lock_sock(sk); + if (sock->state != SS_UNCONNECTED) { + release_sock(sk); + return -EINVAL; + } + if (sk->sk_state != TCP_LISTEN) { struct rose_sock *rose = rose_sk(sk); @@ -497,8 +503,10 @@ static int rose_listen(struct socket *sock, int backlog) memset(rose->dest_digis, 0, AX25_ADDR_LEN * ROSE_MAX_DIGIS); sk->sk_max_ack_backlog = backlog; sk->sk_state = TCP_LISTEN; + release_sock(sk); return 0; } + release_sock(sk); return -EOPNOTSUPP; } diff --git a/net/rxrpc/Kconfig b/net/rxrpc/Kconfig index 7ae023b37a83..a20986806fea 100644 --- a/net/rxrpc/Kconfig +++ b/net/rxrpc/Kconfig @@ -36,6 +36,15 @@ config AF_RXRPC_INJECT_LOSS Say Y here to inject packet loss by discarding some received and some transmitted packets. +config AF_RXRPC_INJECT_RX_DELAY + bool "Inject delay into packet reception" + depends on SYSCTL + help + Say Y here to inject a delay into packet reception, allowing an + extended RTT time to be modelled. The delay can be configured using + /proc/sys/net/rxrpc/rxrpc_inject_rx_delay, setting a number of + milliseconds up to 0.5s (note that the granularity is actually in + jiffies). config AF_RXRPC_DEBUG bool "RxRPC dynamic debugging" diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index ebbd4a1c3f86..102f5cbff91a 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -786,7 +786,7 @@ static int rxrpc_create(struct net *net, struct socket *sock, int protocol, INIT_LIST_HEAD(&rx->sock_calls); INIT_LIST_HEAD(&rx->to_be_accepted); INIT_LIST_HEAD(&rx->recvmsg_q); - rwlock_init(&rx->recvmsg_lock); + spin_lock_init(&rx->recvmsg_lock); rwlock_init(&rx->call_lock); memset(&rx->srx, 0, sizeof(rx->srx)); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 433060cade03..9e19688b0e06 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -149,7 +149,7 @@ struct rxrpc_sock { struct list_head sock_calls; /* List of calls owned by this socket */ struct list_head to_be_accepted; /* calls awaiting acceptance */ struct list_head recvmsg_q; /* Calls awaiting recvmsg's attention */ - rwlock_t recvmsg_lock; /* Lock for recvmsg_q */ + spinlock_t recvmsg_lock; /* Lock for recvmsg_q */ struct key *key; /* security for this socket */ struct key *securities; /* list of server security descriptors */ struct rb_root calls; /* User ID -> call mapping */ @@ -284,7 +284,9 @@ struct rxrpc_local { struct task_struct *io_thread; struct completion io_thread_ready; /* Indication that the I/O thread started */ struct rxrpc_sock *service; /* Service(s) listening on this endpoint */ - struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */ +#ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY + struct sk_buff_head rx_delay_queue; /* Delay injection queue */ +#endif struct sk_buff_head rx_queue; /* Received packets */ struct list_head conn_attend_q; /* Conns requiring immediate attention */ struct list_head call_attend_q; /* Calls requiring immediate attention */ @@ -688,9 +690,11 @@ struct rxrpc_call { /* Receive-phase ACK management (ACKs we send). */ u8 ackr_reason; /* reason to ACK */ + u16 ackr_sack_base; /* Starting slot in SACK table ring */ rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */ - atomic64_t ackr_window; /* Base (in LSW) and top (in MSW) of SACK window */ - atomic_t ackr_nr_unacked; /* Number of unacked packets */ + rxrpc_seq_t ackr_window; /* Base of SACK window */ + rxrpc_seq_t ackr_wtop; /* Base of SACK window */ + unsigned int ackr_nr_unacked; /* Number of unacked packets */ atomic_t ackr_nr_consumed; /* Number of packets needing hard ACK */ struct { #define RXRPC_SACK_SIZE 256 @@ -1109,6 +1113,9 @@ extern unsigned long rxrpc_idle_ack_delay; extern unsigned int rxrpc_rx_window_size; extern unsigned int rxrpc_rx_mtu; extern unsigned int rxrpc_rx_jumbo_max; +#ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY +extern unsigned long rxrpc_inject_rx_delay; +#endif /* * net_ns.c diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 3e8689fdc437..0f5a1d77b890 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -195,7 +195,7 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) tail = b->peer_backlog_tail; while (CIRC_CNT(head, tail, size) > 0) { struct rxrpc_peer *peer = b->peer_backlog[tail]; - rxrpc_put_local(peer->local, rxrpc_local_put_prealloc_conn); + rxrpc_put_local(peer->local, rxrpc_local_put_prealloc_peer); kfree(peer); tail = (tail + 1) & (size - 1); } diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 1abdef15debc..e363f21a2014 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -498,9 +498,18 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_send_ACK(call, RXRPC_ACK_IDLE, 0, rxrpc_propose_ack_rx_idle); - if (atomic_read(&call->ackr_nr_unacked) > 2) - rxrpc_send_ACK(call, RXRPC_ACK_IDLE, 0, - rxrpc_propose_ack_input_data); + if (call->ackr_nr_unacked > 2) { + if (call->peer->rtt_count < 3) + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_rtt); + else if (ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), + ktime_get_real())) + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_old_rtt); + else + rxrpc_send_ACK(call, RXRPC_ACK_IDLE, 0, + rxrpc_propose_ack_input_data); + } /* Make sure the timer is restarted */ if (!__rxrpc_call_is_complete(call)) { diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index f3c9f0201c15..e9f1f49d18c2 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -54,12 +54,14 @@ void rxrpc_poke_call(struct rxrpc_call *call, enum rxrpc_call_poke_trace what) spin_lock_bh(&local->lock); busy = !list_empty(&call->attend_link); trace_rxrpc_poke_call(call, busy, what); + if (!busy && !rxrpc_try_get_call(call, rxrpc_call_get_poke)) + busy = true; if (!busy) { - rxrpc_get_call(call, rxrpc_call_get_poke); list_add_tail(&call->attend_link, &local->call_attend_q); } spin_unlock_bh(&local->lock); - rxrpc_wake_up_io_thread(local); + if (!busy) + rxrpc_wake_up_io_thread(local); } } @@ -167,7 +169,8 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, call->tx_total_len = -1; call->next_rx_timo = 20 * HZ; call->next_req_timo = 1 * HZ; - atomic64_set(&call->ackr_window, 0x100000001ULL); + call->ackr_window = 1; + call->ackr_wtop = 1; memset(&call->sock_node, 0xed, sizeof(call->sock_node)); @@ -560,7 +563,7 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) rxrpc_put_call_slot(call); /* Make sure we don't get any more notifications */ - write_lock(&rx->recvmsg_lock); + spin_lock(&rx->recvmsg_lock); if (!list_empty(&call->recvmsg_link)) { _debug("unlinking once-pending call %p { e=%lx f=%lx }", @@ -573,7 +576,7 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) call->recvmsg_link.next = NULL; call->recvmsg_link.prev = NULL; - write_unlock(&rx->recvmsg_lock); + spin_unlock(&rx->recvmsg_lock); if (put) rxrpc_put_call(call, rxrpc_call_put_unnotify); diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 44414e724415..95f4bc206b3d 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -163,7 +163,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, trace_rxrpc_tx_ack(chan->call_debug_id, serial, ntohl(pkt.ack.firstPacket), ntohl(pkt.ack.serial), - pkt.ack.reason, 0); + pkt.ack.reason, 0, rxrpc_rx_window_size); break; default: diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index f30323de82bd..89ac05a711a4 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -8,11 +8,6 @@ #include <linux/slab.h> #include "ar-internal.h" -static struct rxrpc_bundle rxrpc_service_dummy_bundle = { - .ref = REFCOUNT_INIT(1), - .debug_id = UINT_MAX, -}; - /* * Find a service connection under RCU conditions. * @@ -132,8 +127,6 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn */ conn->state = RXRPC_CONN_SERVICE_PREALLOC; refcount_set(&conn->ref, 2); - conn->bundle = rxrpc_get_bundle(&rxrpc_service_dummy_bundle, - rxrpc_bundle_get_service_conn); atomic_inc(&rxnet->nr_conns); write_lock(&rxnet->conn_lock); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 367927a99881..d68848fce51f 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -338,7 +338,8 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) static void rxrpc_input_update_ack_window(struct rxrpc_call *call, rxrpc_seq_t window, rxrpc_seq_t wtop) { - atomic64_set_release(&call->ackr_window, ((u64)wtop) << 32 | window); + call->ackr_window = window; + call->ackr_wtop = wtop; } /* @@ -367,9 +368,9 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb, struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct sk_buff *oos; rxrpc_serial_t serial = sp->hdr.serial; - u64 win = atomic64_read(&call->ackr_window); - rxrpc_seq_t window = lower_32_bits(win); - rxrpc_seq_t wtop = upper_32_bits(win); + unsigned int sack = call->ackr_sack_base; + rxrpc_seq_t window = call->ackr_window; + rxrpc_seq_t wtop = call->ackr_wtop; rxrpc_seq_t wlimit = window + call->rx_winsize - 1; rxrpc_seq_t seq = sp->hdr.seq; bool last = sp->hdr.flags & RXRPC_LAST_PACKET; @@ -410,20 +411,23 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb, /* Queue the packet. */ if (seq == window) { - rxrpc_seq_t reset_from; - bool reset_sack = false; - if (sp->hdr.flags & RXRPC_REQUEST_ACK) ack_reason = RXRPC_ACK_REQUESTED; /* Send an immediate ACK if we fill in a hole */ else if (!skb_queue_empty(&call->rx_oos_queue)) ack_reason = RXRPC_ACK_DELAY; else - atomic_inc_return(&call->ackr_nr_unacked); + call->ackr_nr_unacked++; window++; - if (after(window, wtop)) + if (after(window, wtop)) { + trace_rxrpc_sack(call, seq, sack, rxrpc_sack_none); wtop = window; + } else { + trace_rxrpc_sack(call, seq, sack, rxrpc_sack_advance); + sack = (sack + 1) % RXRPC_SACK_SIZE; + } + rxrpc_get_skb(skb, rxrpc_skb_get_to_recvmsg); @@ -440,43 +444,39 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb, __skb_unlink(oos, &call->rx_oos_queue); last = osp->hdr.flags & RXRPC_LAST_PACKET; seq = osp->hdr.seq; - if (!reset_sack) { - reset_from = seq; - reset_sack = true; - } + call->ackr_sack_table[sack] = 0; + trace_rxrpc_sack(call, seq, sack, rxrpc_sack_fill); + sack = (sack + 1) % RXRPC_SACK_SIZE; window++; rxrpc_input_queue_data(call, oos, window, wtop, - rxrpc_receive_queue_oos); + rxrpc_receive_queue_oos); } spin_unlock(&call->recvmsg_queue.lock); - if (reset_sack) { - do { - call->ackr_sack_table[reset_from % RXRPC_SACK_SIZE] = 0; - } while (reset_from++, before(reset_from, window)); - } + call->ackr_sack_base = sack; } else { - bool keep = false; + unsigned int slot; ack_reason = RXRPC_ACK_OUT_OF_SEQUENCE; - if (!call->ackr_sack_table[seq % RXRPC_SACK_SIZE]) { - call->ackr_sack_table[seq % RXRPC_SACK_SIZE] = 1; - keep = 1; + slot = seq - window; + sack = (sack + slot) % RXRPC_SACK_SIZE; + + if (call->ackr_sack_table[sack % RXRPC_SACK_SIZE]) { + ack_reason = RXRPC_ACK_DUPLICATE; + goto send_ack; } + call->ackr_sack_table[sack % RXRPC_SACK_SIZE] |= 1; + trace_rxrpc_sack(call, seq, sack, rxrpc_sack_oos); + if (after(seq + 1, wtop)) { wtop = seq + 1; rxrpc_input_update_ack_window(call, window, wtop); } - if (!keep) { - ack_reason = RXRPC_ACK_DUPLICATE; - goto send_ack; - } - skb_queue_walk(&call->rx_oos_queue, oos) { struct rxrpc_skb_priv *osp = rxrpc_skb(oos); @@ -567,8 +567,8 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_serial_t serial = sp->hdr.serial; rxrpc_seq_t seq0 = sp->hdr.seq; - _enter("{%llx,%x},{%u,%x}", - atomic64_read(&call->ackr_window), call->rx_highest_seq, + _enter("{%x,%x,%x},{%u,%x}", + call->ackr_window, call->ackr_wtop, call->rx_highest_seq, skb->len, seq0); if (__rxrpc_call_is_complete(call)) diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 9e9dfb2fc559..4a3a08a0e2cd 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -25,6 +25,7 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn, */ int rxrpc_encap_rcv(struct sock *udp_sk, struct sk_buff *skb) { + struct sk_buff_head *rx_queue; struct rxrpc_local *local = rcu_dereference_sk_user_data(udp_sk); if (unlikely(!local)) { @@ -36,7 +37,16 @@ int rxrpc_encap_rcv(struct sock *udp_sk, struct sk_buff *skb) skb->mark = RXRPC_SKB_MARK_PACKET; rxrpc_new_skb(skb, rxrpc_skb_new_encap_rcv); - skb_queue_tail(&local->rx_queue, skb); + rx_queue = &local->rx_queue; +#ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY + if (rxrpc_inject_rx_delay || + !skb_queue_empty(&local->rx_delay_queue)) { + skb->tstamp = ktime_add_ms(skb->tstamp, rxrpc_inject_rx_delay); + rx_queue = &local->rx_delay_queue; + } +#endif + + skb_queue_tail(rx_queue, skb); rxrpc_wake_up_io_thread(local); return 0; } @@ -407,6 +417,9 @@ int rxrpc_io_thread(void *data) struct rxrpc_local *local = data; struct rxrpc_call *call; struct sk_buff *skb; +#ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY + ktime_t now; +#endif bool should_stop; complete(&local->io_thread_ready); @@ -481,6 +494,17 @@ int rxrpc_io_thread(void *data) continue; } + /* Inject a delay into packets if requested. */ +#ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY + now = ktime_get_real(); + while ((skb = skb_peek(&local->rx_delay_queue))) { + if (ktime_before(now, skb->tstamp)) + break; + skb = skb_dequeue(&local->rx_delay_queue); + skb_queue_tail(&local->rx_queue, skb); + } +#endif + if (!skb_queue_empty(&local->rx_queue)) { spin_lock_irq(&local->rx_queue.lock); skb_queue_splice_tail_init(&local->rx_queue, &rx_queue); @@ -502,6 +526,28 @@ int rxrpc_io_thread(void *data) if (should_stop) break; + +#ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY + skb = skb_peek(&local->rx_delay_queue); + if (skb) { + unsigned long timeout; + ktime_t tstamp = skb->tstamp; + ktime_t now = ktime_get_real(); + s64 delay_ns = ktime_to_ns(ktime_sub(tstamp, now)); + + if (delay_ns <= 0) { + __set_current_state(TASK_RUNNING); + continue; + } + + timeout = nsecs_to_jiffies(delay_ns); + timeout = max(timeout, 1UL); + schedule_timeout(timeout); + __set_current_state(TASK_RUNNING); + continue; + } +#endif + schedule(); } diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index b8eaca5d9f22..7d910aee4f8c 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -108,8 +108,10 @@ static struct rxrpc_local *rxrpc_alloc_local(struct net *net, local->net = net; local->rxnet = rxrpc_net(net); INIT_HLIST_NODE(&local->link); - init_rwsem(&local->defrag_sem); init_completion(&local->io_thread_ready); +#ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY + skb_queue_head_init(&local->rx_delay_queue); +#endif skb_queue_head_init(&local->rx_queue); INIT_LIST_HEAD(&local->conn_attend_q); INIT_LIST_HEAD(&local->call_attend_q); @@ -434,6 +436,9 @@ void rxrpc_destroy_local(struct rxrpc_local *local) /* At this point, there should be no more packets coming in to the * local endpoint. */ +#ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY + rxrpc_purge_queue(&local->rx_delay_queue); +#endif rxrpc_purge_queue(&local->rx_queue); rxrpc_purge_client_connections(local); } diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c index 056c428d8bf3..825b81183046 100644 --- a/net/rxrpc/misc.c +++ b/net/rxrpc/misc.c @@ -53,3 +53,10 @@ unsigned int rxrpc_rx_mtu = 5692; * sender that we're willing to handle. */ unsigned int rxrpc_rx_jumbo_max = 4; + +#ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY +/* + * The delay to inject into packet reception. + */ +unsigned long rxrpc_inject_rx_delay; +#endif diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index a9746be29634..5e53429c6922 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -80,62 +80,40 @@ static void rxrpc_set_keepalive(struct rxrpc_call *call) */ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, struct rxrpc_call *call, - struct rxrpc_txbuf *txb) + struct rxrpc_txbuf *txb, + u16 *_rwind) { struct rxrpc_ackinfo ackinfo; - unsigned int qsize; - rxrpc_seq_t window, wtop, wrap_point, ix, first; + unsigned int qsize, sack, wrap, to; + rxrpc_seq_t window, wtop; int rsize; - u64 wtmp; u32 mtu, jmax; u8 *ackp = txb->acks; - u8 sack_buffer[sizeof(call->ackr_sack_table)] __aligned(8); - atomic_set(&call->ackr_nr_unacked, 0); + call->ackr_nr_unacked = 0; atomic_set(&call->ackr_nr_consumed, 0); rxrpc_inc_stat(call->rxnet, stat_tx_ack_fill); + clear_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags); - /* Barrier against rxrpc_input_data(). */ -retry: - wtmp = atomic64_read_acquire(&call->ackr_window); - window = lower_32_bits(wtmp); - wtop = upper_32_bits(wtmp); + window = call->ackr_window; + wtop = call->ackr_wtop; + sack = call->ackr_sack_base % RXRPC_SACK_SIZE; txb->ack.firstPacket = htonl(window); - txb->ack.nAcks = 0; + txb->ack.nAcks = wtop - window; if (after(wtop, window)) { - /* Try to copy the SACK ring locklessly. We can use the copy, - * only if the now-current top of the window didn't go past the - * previously read base - otherwise we can't know whether we - * have old data or new data. - */ - memcpy(sack_buffer, call->ackr_sack_table, sizeof(sack_buffer)); - wrap_point = window + RXRPC_SACK_SIZE - 1; - wtmp = atomic64_read_acquire(&call->ackr_window); - window = lower_32_bits(wtmp); - wtop = upper_32_bits(wtmp); - if (after(wtop, wrap_point)) { - cond_resched(); - goto retry; - } - - /* The buffer is maintained as a ring with an invariant mapping - * between bit position and sequence number, so we'll probably - * need to rotate it. - */ - txb->ack.nAcks = wtop - window; - ix = window % RXRPC_SACK_SIZE; - first = sizeof(sack_buffer) - ix; + wrap = RXRPC_SACK_SIZE - sack; + to = min_t(unsigned int, txb->ack.nAcks, RXRPC_SACK_SIZE); - if (ix + txb->ack.nAcks <= RXRPC_SACK_SIZE) { - memcpy(txb->acks, sack_buffer + ix, txb->ack.nAcks); + if (sack + txb->ack.nAcks <= RXRPC_SACK_SIZE) { + memcpy(txb->acks, call->ackr_sack_table + sack, txb->ack.nAcks); } else { - memcpy(txb->acks, sack_buffer + ix, first); - memcpy(txb->acks + first, sack_buffer, - txb->ack.nAcks - first); + memcpy(txb->acks, call->ackr_sack_table + sack, wrap); + memcpy(txb->acks + wrap, call->ackr_sack_table, + to - wrap); } - ackp += txb->ack.nAcks; + ackp += to; } else if (before(wtop, window)) { pr_warn("ack window backward %x %x", window, wtop); } else if (txb->ack.reason == RXRPC_ACK_DELAY) { @@ -147,6 +125,7 @@ retry: jmax = rxrpc_rx_jumbo_max; qsize = (window - 1) - call->rx_consumed; rsize = max_t(int, call->rx_winsize - qsize, 0); + *_rwind = rsize; ackinfo.rxMTU = htonl(rxrpc_rx_mtu); ackinfo.maxMTU = htonl(mtu); ackinfo.rwind = htonl(rsize); @@ -213,6 +192,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) rxrpc_serial_t serial; size_t len, n; int ret, rtt_slot = -1; + u16 rwind; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) return -ECONNRESET; @@ -228,7 +208,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) if (txb->ack.reason == RXRPC_ACK_PING) txb->wire.flags |= RXRPC_REQUEST_ACK; - n = rxrpc_fill_out_ack(conn, call, txb); + n = rxrpc_fill_out_ack(conn, call, txb, &rwind); if (n == 0) return 0; @@ -240,7 +220,8 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) txb->wire.serial = htonl(serial); trace_rxrpc_tx_ack(call->debug_id, serial, ntohl(txb->ack.firstPacket), - ntohl(txb->ack.serial), txb->ack.reason, txb->ack.nAcks); + ntohl(txb->ack.serial), txb->ack.reason, txb->ack.nAcks, + rwind); if (txb->ack.reason == RXRPC_ACK_PING) rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_ping); @@ -253,12 +234,15 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); ret = do_udp_sendmsg(conn->local->socket, &msg, len); call->peer->last_tx_at = ktime_get_seconds(); - if (ret < 0) + if (ret < 0) { trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_ack); - else + } else { trace_rxrpc_tx_packet(call->debug_id, &txb->wire, rxrpc_tx_point_call_ack); + if (txb->wire.flags & RXRPC_REQUEST_ACK) + call->peer->rtt_last_req = ktime_get_real(); + } rxrpc_tx_backoff(call, ret); if (!__rxrpc_call_is_complete(call)) { @@ -429,8 +413,6 @@ dont_set_request_ack: if (txb->len >= call->peer->maxdata) goto send_fragmentable; - down_read(&conn->local->defrag_sem); - txb->last_sent = ktime_get_real(); if (txb->wire.flags & RXRPC_REQUEST_ACK) rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); @@ -445,7 +427,6 @@ dont_set_request_ack: ret = do_udp_sendmsg(conn->local->socket, &msg, len); conn->peer->last_tx_at = ktime_get_seconds(); - up_read(&conn->local->defrag_sem); if (ret < 0) { rxrpc_inc_stat(call->rxnet, stat_tx_data_send_fail); rxrpc_cancel_rtt_probe(call, serial, rtt_slot); @@ -506,8 +487,6 @@ send_fragmentable: /* attempt to send this message with fragmentation enabled */ _debug("send fragment"); - down_write(&conn->local->defrag_sem); - txb->last_sent = ktime_get_real(); if (txb->wire.flags & RXRPC_REQUEST_ACK) rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); @@ -539,8 +518,6 @@ send_fragmentable: rxrpc_tx_point_call_data_frag); } rxrpc_tx_backoff(call, ret); - - up_write(&conn->local->defrag_sem); goto done; } diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 750158a085cd..682636d3b060 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -55,7 +55,6 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) unsigned long timeout = 0; rxrpc_seq_t acks_hard_ack; char lbuff[50], rbuff[50]; - u64 wtmp; if (v == &rxnet->calls) { seq_puts(seq, @@ -83,7 +82,6 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) } acks_hard_ack = READ_ONCE(call->acks_hard_ack); - wtmp = atomic64_read_acquire(&call->ackr_window); seq_printf(seq, "UDP %-47.47s %-47.47s %4x %08x %08x %s %3u" " %-8.8s %08x %08x %08x %02x %08x %02x %08x %02x %06lx\n", @@ -98,7 +96,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) call->abort_code, call->debug_id, acks_hard_ack, READ_ONCE(call->tx_top) - acks_hard_ack, - lower_32_bits(wtmp), upper_32_bits(wtmp) - lower_32_bits(wtmp), + call->ackr_window, call->ackr_wtop - call->ackr_window, call->rx_serial, call->cong_cwnd, timeout); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index dd54ceee7bcc..76eb2b9cd936 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -40,12 +40,12 @@ void rxrpc_notify_socket(struct rxrpc_call *call) call->notify_rx(sk, call, call->user_call_ID); spin_unlock(&call->notify_lock); } else { - write_lock(&rx->recvmsg_lock); + spin_lock(&rx->recvmsg_lock); if (list_empty(&call->recvmsg_link)) { rxrpc_get_call(call, rxrpc_call_get_notify_socket); list_add_tail(&call->recvmsg_link, &rx->recvmsg_q); } - write_unlock(&rx->recvmsg_lock); + spin_unlock(&rx->recvmsg_lock); if (!sock_flag(sk, SOCK_DEAD)) { _debug("call %ps", sk->sk_data_ready); @@ -95,7 +95,7 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg) } trace_rxrpc_recvdata(call, rxrpc_recvmsg_terminal, - lower_32_bits(atomic64_read(&call->ackr_window)) - 1, + call->ackr_window - 1, call->rx_pkt_offset, call->rx_pkt_len, ret); return ret; } @@ -137,7 +137,7 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) /* Check to see if there's an ACK that needs sending. */ acked = atomic_add_return(call->rx_consumed - old_consumed, &call->ackr_nr_consumed); - if (acked > 2 && + if (acked > 8 && !test_and_set_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags)) rxrpc_poke_call(call, rxrpc_call_poke_idle); } @@ -175,13 +175,13 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, rx_pkt_len = call->rx_pkt_len; if (rxrpc_call_has_failed(call)) { - seq = lower_32_bits(atomic64_read(&call->ackr_window)) - 1; + seq = call->ackr_window - 1; ret = -EIO; goto done; } if (test_bit(RXRPC_CALL_RECVMSG_READ_ALL, &call->flags)) { - seq = lower_32_bits(atomic64_read(&call->ackr_window)) - 1; + seq = call->ackr_window - 1; ret = 1; goto done; } @@ -335,14 +335,14 @@ try_again: /* Find the next call and dequeue it if we're not just peeking. If we * do dequeue it, that comes with a ref that we will need to release. */ - write_lock(&rx->recvmsg_lock); + spin_lock(&rx->recvmsg_lock); l = rx->recvmsg_q.next; call = list_entry(l, struct rxrpc_call, recvmsg_link); if (!(flags & MSG_PEEK)) list_del_init(&call->recvmsg_link); else rxrpc_get_call(call, rxrpc_call_get_recvmsg); - write_unlock(&rx->recvmsg_lock); + spin_unlock(&rx->recvmsg_lock); call_debug_id = call->debug_id; trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_dequeue, 0); @@ -431,9 +431,9 @@ error_unlock_call: error_requeue_call: if (!(flags & MSG_PEEK)) { - write_lock(&rx->recvmsg_lock); + spin_lock(&rx->recvmsg_lock); list_add(&call->recvmsg_link, &rx->recvmsg_q); - write_unlock(&rx->recvmsg_lock); + spin_unlock(&rx->recvmsg_lock); trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_requeue, 0); } else { rxrpc_put_call(call, rxrpc_call_put_recvmsg); diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c index ebe0c75e7b07..3bcd6ee80396 100644 --- a/net/rxrpc/skbuff.c +++ b/net/rxrpc/skbuff.c @@ -63,7 +63,7 @@ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) if (skb) { int n = atomic_dec_return(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); - kfree_skb(skb); + consume_skb(skb); } } @@ -78,6 +78,6 @@ void rxrpc_purge_queue(struct sk_buff_head *list) int n = atomic_dec_return(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, rxrpc_skb_put_purge); - kfree_skb(skb); + consume_skb(skb); } } diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c index cde3224a5cd2..ecaeb4ecfb58 100644 --- a/net/rxrpc/sysctl.c +++ b/net/rxrpc/sysctl.c @@ -17,6 +17,9 @@ static const unsigned int n_65535 = 65535; static const unsigned int n_max_acks = 255; static const unsigned long one_jiffy = 1; static const unsigned long max_jiffies = MAX_JIFFY_OFFSET; +#ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY +static const unsigned long max_500 = 500; +#endif /* * RxRPC operating parameters. @@ -63,6 +66,19 @@ static struct ctl_table rxrpc_sysctl_table[] = { .extra2 = (void *)&max_jiffies, }, + /* Values used in milliseconds */ +#ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY + { + .procname = "inject_rx_delay", + .data = &rxrpc_inject_rx_delay, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + .extra1 = (void *)SYSCTL_LONG_ZERO, + .extra2 = (void *)&max_500, + }, +#endif + /* Non-time values */ { .procname = "reap_client_conns", @@ -109,7 +125,6 @@ static struct ctl_table rxrpc_sysctl_table[] = { .extra1 = (void *)SYSCTL_ONE, .extra2 = (void *)&four, }, - { } }; diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index d2cf2aac3adb..d43be8512386 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -110,12 +110,8 @@ void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *call) _enter("%x/%x/%x", call->tx_bottom, call->acks_hard_ack, call->tx_top); - for (;;) { - spin_lock(&call->tx_lock); - txb = list_first_entry_or_null(&call->tx_buffer, - struct rxrpc_txbuf, call_link); - if (!txb) - break; + while ((txb = list_first_entry_or_null(&call->tx_buffer, + struct rxrpc_txbuf, call_link))) { hard_ack = smp_load_acquire(&call->acks_hard_ack); if (before(hard_ack, txb->seq)) break; @@ -128,15 +124,11 @@ void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *call) trace_rxrpc_txqueue(call, rxrpc_txqueue_dequeue); - spin_unlock(&call->tx_lock); - rxrpc_put_txbuf(txb, rxrpc_txbuf_put_rotated); if (after(call->acks_hard_ack, call->tx_bottom + 128)) wake = true; } - spin_unlock(&call->tx_lock); - if (wake) wake_up(&call->waitq); } diff --git a/net/sched/Kconfig b/net/sched/Kconfig index de18a0dda6df..4f7b52f5a11c 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -195,8 +195,14 @@ config NET_SCH_ETF To compile this code as a module, choose M here: the module will be called sch_etf. +config NET_SCH_MQPRIO_LIB + tristate + help + Common library for manipulating mqprio queue configurations. + config NET_SCH_TAPRIO tristate "Time Aware Priority (taprio) Scheduler" + select NET_SCH_MQPRIO_LIB help Say Y here if you want to use the Time Aware Priority (taprio) packet scheduling algorithm. @@ -253,6 +259,7 @@ config NET_SCH_DRR config NET_SCH_MQPRIO tristate "Multi-queue priority scheduler (MQPRIO)" + select NET_SCH_MQPRIO_LIB help Say Y here if you want to use the Multi-queue Priority scheduler. This scheduler allows QOS to be offloaded on NICs that have support @@ -977,6 +984,7 @@ config NET_ACT_TUNNEL_KEY config NET_ACT_CT tristate "connection tracking tc action" depends on NET_CLS_ACT && NF_CONNTRACK && (!NF_NAT || NF_NAT) && NF_FLOW_TABLE + select NF_CONNTRACK_OVS select NF_NAT_OVS if NF_NAT help Say Y here to allow sending the packets to conntrack module. diff --git a/net/sched/Makefile b/net/sched/Makefile index dd14ef413fda..7911eec09837 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -52,6 +52,7 @@ obj-$(CONFIG_NET_SCH_DRR) += sch_drr.o obj-$(CONFIG_NET_SCH_PLUG) += sch_plug.o obj-$(CONFIG_NET_SCH_ETS) += sch_ets.o obj-$(CONFIG_NET_SCH_MQPRIO) += sch_mqprio.o +obj-$(CONFIG_NET_SCH_MQPRIO_LIB) += sch_mqprio_lib.o obj-$(CONFIG_NET_SCH_SKBPRIO) += sch_skbprio.o obj-$(CONFIG_NET_SCH_CHOKE) += sch_choke.o obj-$(CONFIG_NET_SCH_QFQ) += sch_qfq.o diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 0ca2bb8ed026..9cc0bc7c71ed 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -170,11 +170,11 @@ tcf_ct_flow_table_add_action_nat_udp(const struct nf_conntrack_tuple *tuple, static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct, enum ip_conntrack_dir dir, + enum ip_conntrack_info ctinfo, struct flow_action *action) { struct nf_conn_labels *ct_labels; struct flow_action_entry *entry; - enum ip_conntrack_info ctinfo; u32 *act_ct_labels; entry = tcf_ct_flow_table_flow_action_get_next(action); @@ -182,8 +182,6 @@ static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct, #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) entry->ct_metadata.mark = READ_ONCE(ct->mark); #endif - ctinfo = dir == IP_CT_DIR_ORIGINAL ? IP_CT_ESTABLISHED : - IP_CT_ESTABLISHED_REPLY; /* aligns with the CT reference on the SKB nf_ct_set */ entry->ct_metadata.cookie = (unsigned long)ct | ctinfo; entry->ct_metadata.orig_dir = dir == IP_CT_DIR_ORIGINAL; @@ -237,22 +235,28 @@ static int tcf_ct_flow_table_add_action_nat(struct net *net, } static int tcf_ct_flow_table_fill_actions(struct net *net, - const struct flow_offload *flow, + struct flow_offload *flow, enum flow_offload_tuple_dir tdir, struct nf_flow_rule *flow_rule) { struct flow_action *action = &flow_rule->rule->action; int num_entries = action->num_entries; struct nf_conn *ct = flow->ct; + enum ip_conntrack_info ctinfo; enum ip_conntrack_dir dir; int i, err; switch (tdir) { case FLOW_OFFLOAD_DIR_ORIGINAL: dir = IP_CT_DIR_ORIGINAL; + ctinfo = test_bit(IPS_SEEN_REPLY_BIT, &ct->status) ? + IP_CT_ESTABLISHED : IP_CT_NEW; + if (ctinfo == IP_CT_ESTABLISHED) + set_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); break; case FLOW_OFFLOAD_DIR_REPLY: dir = IP_CT_DIR_REPLY; + ctinfo = IP_CT_ESTABLISHED_REPLY; break; default: return -EOPNOTSUPP; @@ -262,7 +266,7 @@ static int tcf_ct_flow_table_fill_actions(struct net *net, if (err) goto err_nat; - tcf_ct_flow_table_add_action_meta(ct, dir, action); + tcf_ct_flow_table_add_action_meta(ct, dir, ctinfo, action); return 0; err_nat: @@ -365,7 +369,7 @@ static void tcf_ct_flow_tc_ifidx(struct flow_offload *entry, static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft, struct nf_conn *ct, - bool tcp) + bool tcp, bool bidirectional) { struct nf_conn_act_ct_ext *act_ct_ext; struct flow_offload *entry; @@ -384,6 +388,8 @@ static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft, ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; } + if (bidirectional) + __set_bit(NF_FLOW_HW_BIDIRECTIONAL, &entry->flags); act_ct_ext = nf_conn_act_ct_ext_find(ct); if (act_ct_ext) { @@ -407,26 +413,34 @@ static void tcf_ct_flow_table_process_conn(struct tcf_ct_flow_table *ct_ft, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { - bool tcp = false; - - if ((ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) || - !test_bit(IPS_ASSURED_BIT, &ct->status)) - return; + bool tcp = false, bidirectional = true; switch (nf_ct_protonum(ct)) { case IPPROTO_TCP: - tcp = true; - if (ct->proto.tcp.state != TCP_CONNTRACK_ESTABLISHED) + if ((ctinfo != IP_CT_ESTABLISHED && + ctinfo != IP_CT_ESTABLISHED_REPLY) || + !test_bit(IPS_ASSURED_BIT, &ct->status) || + ct->proto.tcp.state != TCP_CONNTRACK_ESTABLISHED) return; + + tcp = true; break; case IPPROTO_UDP: + if (!nf_ct_is_confirmed(ct)) + return; + if (!test_bit(IPS_ASSURED_BIT, &ct->status)) + bidirectional = false; break; #ifdef CONFIG_NF_CT_PROTO_GRE case IPPROTO_GRE: { struct nf_conntrack_tuple *tuple; - if (ct->status & IPS_NAT_MASK) + if ((ctinfo != IP_CT_ESTABLISHED && + ctinfo != IP_CT_ESTABLISHED_REPLY) || + !test_bit(IPS_ASSURED_BIT, &ct->status) || + ct->status & IPS_NAT_MASK) return; + tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; /* No support for GRE v1 */ if (tuple->src.u.gre.key || tuple->dst.u.gre.key) @@ -442,7 +456,7 @@ static void tcf_ct_flow_table_process_conn(struct tcf_ct_flow_table *ct_ft, ct->status & IPS_SEQ_ADJUST) return; - tcf_ct_flow_table_add(ct_ft, ct, tcp); + tcf_ct_flow_table_add(ct_ft, ct, tcp, bidirectional); } static bool @@ -621,13 +635,30 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p, flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); ct = flow->ct; + if (dir == FLOW_OFFLOAD_DIR_REPLY && + !test_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags)) { + /* Only offload reply direction after connection became + * assured. + */ + if (test_bit(IPS_ASSURED_BIT, &ct->status)) + set_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags); + else if (test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags)) + /* If flow_table flow has already been updated to the + * established state, then don't refresh. + */ + return false; + } + if (tcph && (unlikely(tcph->fin || tcph->rst))) { flow_offload_teardown(flow); return false; } - ctinfo = dir == FLOW_OFFLOAD_DIR_ORIGINAL ? IP_CT_ESTABLISHED : - IP_CT_ESTABLISHED_REPLY; + if (dir == FLOW_OFFLOAD_DIR_ORIGINAL) + ctinfo = test_bit(IPS_SEEN_REPLY_BIT, &ct->status) ? + IP_CT_ESTABLISHED : IP_CT_NEW; + else + ctinfo = IP_CT_ESTABLISHED_REPLY; flow_offload_refresh(nf_ft, flow); nf_conntrack_get(&ct->ct_general); @@ -695,31 +726,6 @@ drop_ct: return false; } -/* Trim the skb to the length specified by the IP/IPv6 header, - * removing any trailing lower-layer padding. This prepares the skb - * for higher-layer processing that assumes skb->len excludes padding - * (such as nf_ip_checksum). The caller needs to pull the skb to the - * network header, and ensure ip_hdr/ipv6_hdr points to valid data. - */ -static int tcf_ct_skb_network_trim(struct sk_buff *skb, int family) -{ - unsigned int len; - - switch (family) { - case NFPROTO_IPV4: - len = ntohs(ip_hdr(skb)->tot_len); - break; - case NFPROTO_IPV6: - len = sizeof(struct ipv6hdr) - + ntohs(ipv6_hdr(skb)->payload_len); - break; - default: - len = skb->len; - } - - return pskb_trim_rcsum(skb, len); -} - static u8 tcf_ct_skb_nf_family(struct sk_buff *skb) { u8 family = NFPROTO_UNSPEC; @@ -779,6 +785,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, struct nf_conn *ct; int err = 0; bool frag; + u8 proto; u16 mru; /* Previously seen (loopback)? Ignore. */ @@ -794,50 +801,14 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, return err; skb_get(skb); - mru = tc_skb_cb(skb)->mru; - - if (family == NFPROTO_IPV4) { - enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone; - - memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); - local_bh_disable(); - err = ip_defrag(net, skb, user); - local_bh_enable(); - if (err && err != -EINPROGRESS) - return err; - - if (!err) { - *defrag = true; - mru = IPCB(skb)->frag_max_size; - } - } else { /* NFPROTO_IPV6 */ -#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) - enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone; - - memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); - err = nf_ct_frag6_gather(net, skb, user); - if (err && err != -EINPROGRESS) - goto out_free; - - if (!err) { - *defrag = true; - mru = IP6CB(skb)->frag_max_size; - } -#else - err = -EOPNOTSUPP; - goto out_free; -#endif - } + err = nf_ct_handle_fragments(net, skb, zone, family, &proto, &mru); + if (err) + return err; - if (err != -EINPROGRESS) - tc_skb_cb(skb)->mru = mru; - skb_clear_hash(skb); - skb->ignore_df = 1; - return err; + *defrag = true; + tc_skb_cb(skb)->mru = mru; -out_free: - kfree_skb(skb); - return err; + return 0; } static void tcf_ct_params_free(struct tcf_ct_params *params) @@ -980,7 +951,7 @@ TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, if (err) goto drop; - err = tcf_ct_skb_network_trim(skb, family); + err = nf_ct_skb_network_trim(skb, family); if (err) goto drop; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index a0378e9f0121..c42fcc47dd6d 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -134,6 +134,17 @@ nla_failure: return -EINVAL; } +static void tcf_pedit_cleanup_rcu(struct rcu_head *head) +{ + struct tcf_pedit_parms *parms = + container_of(head, struct tcf_pedit_parms, rcu); + + kfree(parms->tcfp_keys_ex); + kfree(parms->tcfp_keys); + + kfree(parms); +} + static int tcf_pedit_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 flags, @@ -141,10 +152,9 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, { struct tc_action_net *tn = net_generic(net, act_pedit_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; - struct nlattr *tb[TCA_PEDIT_MAX + 1]; struct tcf_chain *goto_ch = NULL; - struct tc_pedit_key *keys = NULL; - struct tcf_pedit_key_ex *keys_ex; + struct tcf_pedit_parms *oparms, *nparms; + struct nlattr *tb[TCA_PEDIT_MAX + 1]; struct tc_pedit *parm; struct nlattr *pattr; struct tcf_pedit *p; @@ -181,18 +191,25 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, return -EINVAL; } - keys_ex = tcf_pedit_keys_ex_parse(tb[TCA_PEDIT_KEYS_EX], parm->nkeys); - if (IS_ERR(keys_ex)) - return PTR_ERR(keys_ex); + nparms = kzalloc(sizeof(*nparms), GFP_KERNEL); + if (!nparms) + return -ENOMEM; + + nparms->tcfp_keys_ex = + tcf_pedit_keys_ex_parse(tb[TCA_PEDIT_KEYS_EX], parm->nkeys); + if (IS_ERR(nparms->tcfp_keys_ex)) { + ret = PTR_ERR(nparms->tcfp_keys_ex); + goto out_free; + } index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, index, est, a, - &act_pedit_ops, bind, false, flags); + ret = tcf_idr_create_from_flags(tn, index, est, a, + &act_pedit_ops, bind, flags); if (ret) { tcf_idr_cleanup(tn, index); - goto out_free; + goto out_free_ex; } ret = ACT_P_CREATED; } else if (err > 0) { @@ -204,7 +221,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, } } else { ret = err; - goto out_free; + goto out_free_ex; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); @@ -212,48 +229,50 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, ret = err; goto out_release; } - p = to_pedit(*a); - spin_lock_bh(&p->tcf_lock); - if (ret == ACT_P_CREATED || - (p->tcfp_nkeys && p->tcfp_nkeys != parm->nkeys)) { - keys = kmalloc(ksize, GFP_ATOMIC); - if (!keys) { - spin_unlock_bh(&p->tcf_lock); - ret = -ENOMEM; - goto put_chain; - } - kfree(p->tcfp_keys); - p->tcfp_keys = keys; - p->tcfp_nkeys = parm->nkeys; + nparms->tcfp_off_max_hint = 0; + nparms->tcfp_flags = parm->flags; + nparms->tcfp_nkeys = parm->nkeys; + + nparms->tcfp_keys = kmalloc(ksize, GFP_KERNEL); + if (!nparms->tcfp_keys) { + ret = -ENOMEM; + goto put_chain; } - memcpy(p->tcfp_keys, parm->keys, ksize); - p->tcfp_off_max_hint = 0; - for (i = 0; i < p->tcfp_nkeys; ++i) { - u32 cur = p->tcfp_keys[i].off; + + memcpy(nparms->tcfp_keys, parm->keys, ksize); + + for (i = 0; i < nparms->tcfp_nkeys; ++i) { + u32 cur = nparms->tcfp_keys[i].off; /* sanitize the shift value for any later use */ - p->tcfp_keys[i].shift = min_t(size_t, BITS_PER_TYPE(int) - 1, - p->tcfp_keys[i].shift); + nparms->tcfp_keys[i].shift = min_t(size_t, + BITS_PER_TYPE(int) - 1, + nparms->tcfp_keys[i].shift); /* The AT option can read a single byte, we can bound the actual * value with uchar max. */ - cur += (0xff & p->tcfp_keys[i].offmask) >> p->tcfp_keys[i].shift; + cur += (0xff & nparms->tcfp_keys[i].offmask) >> nparms->tcfp_keys[i].shift; /* Each key touches 4 bytes starting from the computed offset */ - p->tcfp_off_max_hint = max(p->tcfp_off_max_hint, cur + 4); + nparms->tcfp_off_max_hint = + max(nparms->tcfp_off_max_hint, cur + 4); } - p->tcfp_flags = parm->flags; + p = to_pedit(*a); + + spin_lock_bh(&p->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); + oparms = rcu_replace_pointer(p->parms, nparms, 1); + spin_unlock_bh(&p->tcf_lock); - kfree(p->tcfp_keys_ex); - p->tcfp_keys_ex = keys_ex; + if (oparms) + call_rcu(&oparms->rcu, tcf_pedit_cleanup_rcu); - spin_unlock_bh(&p->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); + return ret; put_chain: @@ -261,19 +280,22 @@ put_chain: tcf_chain_put_by_act(goto_ch); out_release: tcf_idr_release(*a, bind); +out_free_ex: + kfree(nparms->tcfp_keys_ex); out_free: - kfree(keys_ex); + kfree(nparms); return ret; - } static void tcf_pedit_cleanup(struct tc_action *a) { struct tcf_pedit *p = to_pedit(a); - struct tc_pedit_key *keys = p->tcfp_keys; + struct tcf_pedit_parms *parms; + + parms = rcu_dereference_protected(p->parms, 1); - kfree(keys); - kfree(p->tcfp_keys_ex); + if (parms) + call_rcu(&parms->rcu, tcf_pedit_cleanup_rcu); } static bool offset_valid(struct sk_buff *skb, int offset) @@ -324,109 +346,107 @@ TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { + enum pedit_header_type htype = TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK; + enum pedit_cmd cmd = TCA_PEDIT_KEY_EX_CMD_SET; struct tcf_pedit *p = to_pedit(a); + struct tcf_pedit_key_ex *tkey_ex; + struct tcf_pedit_parms *parms; + struct tc_pedit_key *tkey; u32 max_offset; int i; - spin_lock(&p->tcf_lock); + parms = rcu_dereference_bh(p->parms); max_offset = (skb_transport_header_was_set(skb) ? skb_transport_offset(skb) : skb_network_offset(skb)) + - p->tcfp_off_max_hint; + parms->tcfp_off_max_hint; if (skb_ensure_writable(skb, min(skb->len, max_offset))) - goto unlock; + goto done; tcf_lastuse_update(&p->tcf_tm); + tcf_action_update_bstats(&p->common, skb); - if (p->tcfp_nkeys > 0) { - struct tc_pedit_key *tkey = p->tcfp_keys; - struct tcf_pedit_key_ex *tkey_ex = p->tcfp_keys_ex; - enum pedit_header_type htype = - TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK; - enum pedit_cmd cmd = TCA_PEDIT_KEY_EX_CMD_SET; - - for (i = p->tcfp_nkeys; i > 0; i--, tkey++) { - u32 *ptr, hdata; - int offset = tkey->off; - int hoffset; - u32 val; - int rc; - - if (tkey_ex) { - htype = tkey_ex->htype; - cmd = tkey_ex->cmd; - - tkey_ex++; - } + tkey = parms->tcfp_keys; + tkey_ex = parms->tcfp_keys_ex; - rc = pedit_skb_hdr_offset(skb, htype, &hoffset); - if (rc) { - pr_info("tc action pedit bad header type specified (0x%x)\n", - htype); - goto bad; - } + for (i = parms->tcfp_nkeys; i > 0; i--, tkey++) { + int offset = tkey->off; + u32 *ptr, hdata; + int hoffset; + u32 val; + int rc; - if (tkey->offmask) { - u8 *d, _d; - - if (!offset_valid(skb, hoffset + tkey->at)) { - pr_info("tc action pedit 'at' offset %d out of bounds\n", - hoffset + tkey->at); - goto bad; - } - d = skb_header_pointer(skb, hoffset + tkey->at, - sizeof(_d), &_d); - if (!d) - goto bad; - offset += (*d & tkey->offmask) >> tkey->shift; - } + if (tkey_ex) { + htype = tkey_ex->htype; + cmd = tkey_ex->cmd; - if (offset % 4) { - pr_info("tc action pedit offset must be on 32 bit boundaries\n"); - goto bad; - } + tkey_ex++; + } - if (!offset_valid(skb, hoffset + offset)) { - pr_info("tc action pedit offset %d out of bounds\n", - hoffset + offset); - goto bad; - } + rc = pedit_skb_hdr_offset(skb, htype, &hoffset); + if (rc) { + pr_info("tc action pedit bad header type specified (0x%x)\n", + htype); + goto bad; + } - ptr = skb_header_pointer(skb, hoffset + offset, - sizeof(hdata), &hdata); - if (!ptr) - goto bad; - /* just do it, baby */ - switch (cmd) { - case TCA_PEDIT_KEY_EX_CMD_SET: - val = tkey->val; - break; - case TCA_PEDIT_KEY_EX_CMD_ADD: - val = (*ptr + tkey->val) & ~tkey->mask; - break; - default: - pr_info("tc action pedit bad command (%d)\n", - cmd); + if (tkey->offmask) { + u8 *d, _d; + + if (!offset_valid(skb, hoffset + tkey->at)) { + pr_info("tc action pedit 'at' offset %d out of bounds\n", + hoffset + tkey->at); goto bad; } + d = skb_header_pointer(skb, hoffset + tkey->at, + sizeof(_d), &_d); + if (!d) + goto bad; + offset += (*d & tkey->offmask) >> tkey->shift; + } - *ptr = ((*ptr & tkey->mask) ^ val); - if (ptr == &hdata) - skb_store_bits(skb, hoffset + offset, ptr, 4); + if (offset % 4) { + pr_info("tc action pedit offset must be on 32 bit boundaries\n"); + goto bad; } - goto done; - } else { - WARN(1, "pedit BUG: index %d\n", p->tcf_index); + if (!offset_valid(skb, hoffset + offset)) { + pr_info("tc action pedit offset %d out of bounds\n", + hoffset + offset); + goto bad; + } + + ptr = skb_header_pointer(skb, hoffset + offset, + sizeof(hdata), &hdata); + if (!ptr) + goto bad; + /* just do it, baby */ + switch (cmd) { + case TCA_PEDIT_KEY_EX_CMD_SET: + val = tkey->val; + break; + case TCA_PEDIT_KEY_EX_CMD_ADD: + val = (*ptr + tkey->val) & ~tkey->mask; + break; + default: + pr_info("tc action pedit bad command (%d)\n", + cmd); + goto bad; + } + + *ptr = ((*ptr & tkey->mask) ^ val); + if (ptr == &hdata) + skb_store_bits(skb, hoffset + offset, ptr, 4); } + goto done; + bad: + spin_lock(&p->tcf_lock); p->tcf_qstats.overlimits++; -done: - bstats_update(&p->tcf_bstats, skb); -unlock: spin_unlock(&p->tcf_lock); +done: return p->tcf_action; } @@ -445,30 +465,33 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a, { unsigned char *b = skb_tail_pointer(skb); struct tcf_pedit *p = to_pedit(a); + struct tcf_pedit_parms *parms; struct tc_pedit *opt; struct tcf_t t; int s; - s = struct_size(opt, keys, p->tcfp_nkeys); + spin_lock_bh(&p->tcf_lock); + parms = rcu_dereference_protected(p->parms, 1); + s = struct_size(opt, keys, parms->tcfp_nkeys); - /* netlink spinlocks held above us - must use ATOMIC */ opt = kzalloc(s, GFP_ATOMIC); - if (unlikely(!opt)) + if (unlikely(!opt)) { + spin_unlock_bh(&p->tcf_lock); return -ENOBUFS; + } - spin_lock_bh(&p->tcf_lock); - memcpy(opt->keys, p->tcfp_keys, flex_array_size(opt, keys, p->tcfp_nkeys)); + memcpy(opt->keys, parms->tcfp_keys, + flex_array_size(opt, keys, parms->tcfp_nkeys)); opt->index = p->tcf_index; - opt->nkeys = p->tcfp_nkeys; - opt->flags = p->tcfp_flags; + opt->nkeys = parms->tcfp_nkeys; + opt->flags = parms->tcfp_flags; opt->action = p->tcf_action; opt->refcnt = refcount_read(&p->tcf_refcnt) - ref; opt->bindcnt = atomic_read(&p->tcf_bindcnt) - bind; - if (p->tcfp_keys_ex) { - if (tcf_pedit_key_ex_dump(skb, - p->tcfp_keys_ex, - p->tcfp_nkeys)) + if (parms->tcfp_keys_ex) { + if (tcf_pedit_key_ex_dump(skb, parms->tcfp_keys_ex, + parms->tcfp_nkeys)) goto nla_put_failure; if (nla_put(skb, TCA_PEDIT_PARMS_EX, s, opt)) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index c14018a8052c..e9780631b5b5 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1282,12 +1282,6 @@ static struct Qdisc *qdisc_create(struct net_device *dev, if (err) goto err_out3; - if (ops->init) { - err = ops->init(sch, tca[TCA_OPTIONS], extack); - if (err != 0) - goto err_out5; - } - if (tca[TCA_STAB]) { stab = qdisc_get_stab(tca[TCA_STAB], extack); if (IS_ERR(stab)) { @@ -1296,11 +1290,18 @@ static struct Qdisc *qdisc_create(struct net_device *dev, } rcu_assign_pointer(sch->stab, stab); } + + if (ops->init) { + err = ops->init(sch, tca[TCA_OPTIONS], extack); + if (err != 0) + goto err_out5; + } + if (tca[TCA_RATE]) { err = -EOPNOTSUPP; if (sch->flags & TCQ_F_MQROOT) { NL_SET_ERR_MSG(extack, "Cannot attach rate estimator to a multi-queue root qdisc"); - goto err_out4; + goto err_out5; } err = gen_new_estimator(&sch->bstats, @@ -1311,7 +1312,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to generate new estimator"); - goto err_out4; + goto err_out5; } } @@ -1321,6 +1322,8 @@ static struct Qdisc *qdisc_create(struct net_device *dev, return sch; err_out5: + qdisc_put_stab(rtnl_dereference(sch->stab)); +err_out4: /* ops->init() failed, we call ->destroy() like qdisc_create_dflt() */ if (ops->destroy) ops->destroy(sch); @@ -1332,16 +1335,6 @@ err_out2: err_out: *errp = err; return NULL; - -err_out4: - /* - * Any broken qdiscs that would require a ops->reset() here? - * The qdisc was never in action so it shouldn't be necessary. - */ - qdisc_put_stab(rtnl_dereference(sch->stab)); - if (ops->destroy) - ops->destroy(sch); - goto err_out3; } static int qdisc_change(struct Qdisc *sch, struct nlattr **tca, diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 3ed0c3342189..7970217b565a 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1209,7 +1209,7 @@ static struct sk_buff *cake_ack_filter(struct cake_sched_data *q, iph_check->daddr != iph->daddr) continue; - seglen = ntohs(iph_check->tot_len) - + seglen = iph_totlen(skb, iph_check) - (4 * iph_check->ihl); } else if (iph_check->version == 6) { ipv6h = (struct ipv6hdr *)iph; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index f46643850df8..92f2975b6a82 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -431,7 +431,10 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) while (cl->cmode == HTB_MAY_BORROW && p && mask) { m = mask; while (m) { - int prio = ffz(~m); + unsigned int prio = ffz(~m); + + if (WARN_ON_ONCE(prio >= ARRAY_SIZE(p->inner.clprio))) + break; m &= ~(1 << prio); if (p->inner.clprio[prio].feed.rb_node) diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 4c68abaa289b..48ed87b91086 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -17,6 +17,8 @@ #include <net/sch_generic.h> #include <net/pkt_cls.h> +#include "sch_mqprio_lib.h" + struct mqprio_sched { struct Qdisc **qdiscs; u16 mode; @@ -27,6 +29,62 @@ struct mqprio_sched { u64 max_rate[TC_QOPT_MAX_QUEUE]; }; +static int mqprio_enable_offload(struct Qdisc *sch, + const struct tc_mqprio_qopt *qopt, + struct netlink_ext_ack *extack) +{ + struct tc_mqprio_qopt_offload mqprio = {.qopt = *qopt}; + struct mqprio_sched *priv = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + int err, i; + + switch (priv->mode) { + case TC_MQPRIO_MODE_DCB: + if (priv->shaper != TC_MQPRIO_SHAPER_DCB) + return -EINVAL; + break; + case TC_MQPRIO_MODE_CHANNEL: + mqprio.flags = priv->flags; + if (priv->flags & TC_MQPRIO_F_MODE) + mqprio.mode = priv->mode; + if (priv->flags & TC_MQPRIO_F_SHAPER) + mqprio.shaper = priv->shaper; + if (priv->flags & TC_MQPRIO_F_MIN_RATE) + for (i = 0; i < mqprio.qopt.num_tc; i++) + mqprio.min_rate[i] = priv->min_rate[i]; + if (priv->flags & TC_MQPRIO_F_MAX_RATE) + for (i = 0; i < mqprio.qopt.num_tc; i++) + mqprio.max_rate[i] = priv->max_rate[i]; + break; + default: + return -EINVAL; + } + + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQPRIO, + &mqprio); + if (err) + return err; + + priv->hw_offload = mqprio.qopt.hw; + + return 0; +} + +static void mqprio_disable_offload(struct Qdisc *sch) +{ + struct tc_mqprio_qopt_offload mqprio = { { 0 } }; + struct mqprio_sched *priv = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + + switch (priv->mode) { + case TC_MQPRIO_MODE_DCB: + case TC_MQPRIO_MODE_CHANNEL: + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQPRIO, + &mqprio); + break; + } +} + static void mqprio_destroy(struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); @@ -41,37 +99,17 @@ static void mqprio_destroy(struct Qdisc *sch) kfree(priv->qdiscs); } - if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) { - struct tc_mqprio_qopt_offload mqprio = { { 0 } }; - - switch (priv->mode) { - case TC_MQPRIO_MODE_DCB: - case TC_MQPRIO_MODE_CHANNEL: - dev->netdev_ops->ndo_setup_tc(dev, - TC_SETUP_QDISC_MQPRIO, - &mqprio); - break; - default: - return; - } - } else { + if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) + mqprio_disable_offload(sch); + else netdev_set_num_tc(dev, 0); - } } -static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) +static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt, + const struct tc_mqprio_caps *caps, + struct netlink_ext_ack *extack) { - int i, j; - - /* Verify num_tc is not out of max range */ - if (qopt->num_tc > TC_MAX_QUEUE) - return -EINVAL; - - /* Verify priority mapping uses valid tcs */ - for (i = 0; i < TC_BITMASK + 1; i++) { - if (qopt->prio_tc_map[i] >= qopt->num_tc) - return -EINVAL; - } + int err; /* Limit qopt->hw to maximum supported offload value. Drivers have * the option of overriding this later if they don't support the a @@ -80,31 +118,23 @@ static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) if (qopt->hw > TC_MQPRIO_HW_OFFLOAD_MAX) qopt->hw = TC_MQPRIO_HW_OFFLOAD_MAX; - /* If hardware offload is requested we will leave it to the device - * to either populate the queue counts itself or to validate the - * provided queue counts. If ndo_setup_tc is not present then - * hardware doesn't support offload and we should return an error. + /* If hardware offload is requested, we will leave 3 options to the + * device driver: + * - populate the queue counts itself (and ignore what was requested) + * - validate the provided queue counts by itself (and apply them) + * - request queue count validation here (and apply them) */ - if (qopt->hw) - return dev->netdev_ops->ndo_setup_tc ? 0 : -EINVAL; - - for (i = 0; i < qopt->num_tc; i++) { - unsigned int last = qopt->offset[i] + qopt->count[i]; - - /* Verify the queue count is in tx range being equal to the - * real_num_tx_queues indicates the last queue is in use. - */ - if (qopt->offset[i] >= dev->real_num_tx_queues || - !qopt->count[i] || - last > dev->real_num_tx_queues) - return -EINVAL; - - /* Verify that the offset and counts do not overlap */ - for (j = i + 1; j < qopt->num_tc; j++) { - if (last > qopt->offset[j]) - return -EINVAL; - } - } + err = mqprio_validate_qopt(dev, qopt, + !qopt->hw || caps->validate_queue_counts, + false, extack); + if (err) + return err; + + /* If ndo_setup_tc is not present then hardware doesn't support offload + * and we should return an error. + */ + if (qopt->hw && !dev->netdev_ops->ndo_setup_tc) + return -EINVAL; return 0; } @@ -130,6 +160,67 @@ static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, return 0; } +static int mqprio_parse_nlattr(struct Qdisc *sch, struct tc_mqprio_qopt *qopt, + struct nlattr *opt) +{ + struct mqprio_sched *priv = qdisc_priv(sch); + struct nlattr *tb[TCA_MQPRIO_MAX + 1]; + struct nlattr *attr; + int i, rem, err; + + err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy, + sizeof(*qopt)); + if (err < 0) + return err; + + if (!qopt->hw) + return -EINVAL; + + if (tb[TCA_MQPRIO_MODE]) { + priv->flags |= TC_MQPRIO_F_MODE; + priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]); + } + + if (tb[TCA_MQPRIO_SHAPER]) { + priv->flags |= TC_MQPRIO_F_SHAPER; + priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]); + } + + if (tb[TCA_MQPRIO_MIN_RATE64]) { + if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) + return -EINVAL; + i = 0; + nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64], + rem) { + if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64) + return -EINVAL; + if (i >= qopt->num_tc) + break; + priv->min_rate[i] = *(u64 *)nla_data(attr); + i++; + } + priv->flags |= TC_MQPRIO_F_MIN_RATE; + } + + if (tb[TCA_MQPRIO_MAX_RATE64]) { + if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) + return -EINVAL; + i = 0; + nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64], + rem) { + if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64) + return -EINVAL; + if (i >= qopt->num_tc) + break; + priv->max_rate[i] = *(u64 *)nla_data(attr); + i++; + } + priv->flags |= TC_MQPRIO_F_MAX_RATE; + } + + return 0; +} + static int mqprio_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { @@ -139,9 +230,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt, struct Qdisc *qdisc; int i, err = -EOPNOTSUPP; struct tc_mqprio_qopt *qopt = NULL; - struct nlattr *tb[TCA_MQPRIO_MAX + 1]; - struct nlattr *attr; - int rem; + struct tc_mqprio_caps caps; int len; BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE); @@ -160,61 +249,18 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt, if (!opt || nla_len(opt) < sizeof(*qopt)) return -EINVAL; + qdisc_offload_query_caps(dev, TC_SETUP_QDISC_MQPRIO, + &caps, sizeof(caps)); + qopt = nla_data(opt); - if (mqprio_parse_opt(dev, qopt)) + if (mqprio_parse_opt(dev, qopt, &caps, extack)) return -EINVAL; len = nla_len(opt) - NLA_ALIGN(sizeof(*qopt)); if (len > 0) { - err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy, - sizeof(*qopt)); - if (err < 0) + err = mqprio_parse_nlattr(sch, qopt, opt); + if (err) return err; - - if (!qopt->hw) - return -EINVAL; - - if (tb[TCA_MQPRIO_MODE]) { - priv->flags |= TC_MQPRIO_F_MODE; - priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]); - } - - if (tb[TCA_MQPRIO_SHAPER]) { - priv->flags |= TC_MQPRIO_F_SHAPER; - priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]); - } - - if (tb[TCA_MQPRIO_MIN_RATE64]) { - if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) - return -EINVAL; - i = 0; - nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64], - rem) { - if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64) - return -EINVAL; - if (i >= qopt->num_tc) - break; - priv->min_rate[i] = *(u64 *)nla_data(attr); - i++; - } - priv->flags |= TC_MQPRIO_F_MIN_RATE; - } - - if (tb[TCA_MQPRIO_MAX_RATE64]) { - if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) - return -EINVAL; - i = 0; - nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64], - rem) { - if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64) - return -EINVAL; - if (i >= qopt->num_tc) - break; - priv->max_rate[i] = *(u64 *)nla_data(attr); - i++; - } - priv->flags |= TC_MQPRIO_F_MAX_RATE; - } } /* pre-allocate qdisc, attachment can't fail */ @@ -241,36 +287,9 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt, * supplied and verified mapping */ if (qopt->hw) { - struct tc_mqprio_qopt_offload mqprio = {.qopt = *qopt}; - - switch (priv->mode) { - case TC_MQPRIO_MODE_DCB: - if (priv->shaper != TC_MQPRIO_SHAPER_DCB) - return -EINVAL; - break; - case TC_MQPRIO_MODE_CHANNEL: - mqprio.flags = priv->flags; - if (priv->flags & TC_MQPRIO_F_MODE) - mqprio.mode = priv->mode; - if (priv->flags & TC_MQPRIO_F_SHAPER) - mqprio.shaper = priv->shaper; - if (priv->flags & TC_MQPRIO_F_MIN_RATE) - for (i = 0; i < mqprio.qopt.num_tc; i++) - mqprio.min_rate[i] = priv->min_rate[i]; - if (priv->flags & TC_MQPRIO_F_MAX_RATE) - for (i = 0; i < mqprio.qopt.num_tc; i++) - mqprio.max_rate[i] = priv->max_rate[i]; - break; - default: - return -EINVAL; - } - err = dev->netdev_ops->ndo_setup_tc(dev, - TC_SETUP_QDISC_MQPRIO, - &mqprio); + err = mqprio_enable_offload(sch, qopt, extack); if (err) return err; - - priv->hw_offload = mqprio.qopt.hw; } else { netdev_set_num_tc(dev, qopt->num_tc); for (i = 0; i < qopt->num_tc; i++) @@ -387,7 +406,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) struct nlattr *nla = (struct nlattr *)skb_tail_pointer(skb); struct tc_mqprio_qopt opt = { 0 }; struct Qdisc *qdisc; - unsigned int ntx, tc; + unsigned int ntx; sch->q.qlen = 0; gnet_stats_basic_sync_init(&sch->bstats); @@ -411,15 +430,9 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) spin_unlock_bh(qdisc_lock(qdisc)); } - opt.num_tc = netdev_get_num_tc(dev); - memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map)); + mqprio_qopt_reconstruct(dev, &opt); opt.hw = priv->hw_offload; - for (tc = 0; tc < netdev_get_num_tc(dev); tc++) { - opt.count[tc] = dev->tc_to_txq[tc].count; - opt.offset[tc] = dev->tc_to_txq[tc].offset; - } - if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) goto nla_put_failure; diff --git a/net/sched/sch_mqprio_lib.c b/net/sched/sch_mqprio_lib.c new file mode 100644 index 000000000000..c58a533b8ec5 --- /dev/null +++ b/net/sched/sch_mqprio_lib.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/net.h> +#include <linux/netdevice.h> +#include <linux/netlink.h> +#include <linux/types.h> +#include <net/pkt_sched.h> + +#include "sch_mqprio_lib.h" + +/* Returns true if the intervals [a, b) and [c, d) overlap. */ +static bool intervals_overlap(int a, int b, int c, int d) +{ + int left = max(a, c), right = min(b, d); + + return left < right; +} + +static int mqprio_validate_queue_counts(struct net_device *dev, + const struct tc_mqprio_qopt *qopt, + bool allow_overlapping_txqs, + struct netlink_ext_ack *extack) +{ + int i, j; + + for (i = 0; i < qopt->num_tc; i++) { + unsigned int last = qopt->offset[i] + qopt->count[i]; + + if (!qopt->count[i]) { + NL_SET_ERR_MSG_FMT_MOD(extack, "No queues for TC %d", + i); + return -EINVAL; + } + + /* Verify the queue count is in tx range being equal to the + * real_num_tx_queues indicates the last queue is in use. + */ + if (qopt->offset[i] >= dev->real_num_tx_queues || + last > dev->real_num_tx_queues) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "Queues %d:%d for TC %d exceed the %d TX queues available", + qopt->count[i], qopt->offset[i], + i, dev->real_num_tx_queues); + return -EINVAL; + } + + if (allow_overlapping_txqs) + continue; + + /* Verify that the offset and counts do not overlap */ + for (j = i + 1; j < qopt->num_tc; j++) { + if (intervals_overlap(qopt->offset[i], last, + qopt->offset[j], + qopt->offset[j] + + qopt->count[j])) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "TC %d queues %d@%d overlap with TC %d queues %d@%d", + i, qopt->count[i], qopt->offset[i], + j, qopt->count[j], qopt->offset[j]); + return -EINVAL; + } + } + } + + return 0; +} + +int mqprio_validate_qopt(struct net_device *dev, struct tc_mqprio_qopt *qopt, + bool validate_queue_counts, + bool allow_overlapping_txqs, + struct netlink_ext_ack *extack) +{ + int i, err; + + /* Verify num_tc is not out of max range */ + if (qopt->num_tc > TC_MAX_QUEUE) { + NL_SET_ERR_MSG(extack, + "Number of traffic classes is outside valid range"); + return -EINVAL; + } + + /* Verify priority mapping uses valid tcs */ + for (i = 0; i <= TC_BITMASK; i++) { + if (qopt->prio_tc_map[i] >= qopt->num_tc) { + NL_SET_ERR_MSG(extack, + "Invalid traffic class in priority to traffic class mapping"); + return -EINVAL; + } + } + + if (validate_queue_counts) { + err = mqprio_validate_queue_counts(dev, qopt, + allow_overlapping_txqs, + extack); + if (err) + return err; + } + + return 0; +} +EXPORT_SYMBOL_GPL(mqprio_validate_qopt); + +void mqprio_qopt_reconstruct(struct net_device *dev, struct tc_mqprio_qopt *qopt) +{ + int tc, num_tc = netdev_get_num_tc(dev); + + qopt->num_tc = num_tc; + memcpy(qopt->prio_tc_map, dev->prio_tc_map, sizeof(qopt->prio_tc_map)); + + for (tc = 0; tc < num_tc; tc++) { + qopt->count[tc] = dev->tc_to_txq[tc].count; + qopt->offset[tc] = dev->tc_to_txq[tc].offset; + } +} +EXPORT_SYMBOL_GPL(mqprio_qopt_reconstruct); + +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_mqprio_lib.h b/net/sched/sch_mqprio_lib.h new file mode 100644 index 000000000000..63f725ab8761 --- /dev/null +++ b/net/sched/sch_mqprio_lib.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SCH_MQPRIO_LIB_H +#define __SCH_MQPRIO_LIB_H + +#include <linux/types.h> + +struct net_device; +struct netlink_ext_ack; +struct tc_mqprio_qopt; + +int mqprio_validate_qopt(struct net_device *dev, struct tc_mqprio_qopt *qopt, + bool validate_queue_counts, + bool allow_overlapping_txqs, + struct netlink_ext_ack *extack); +void mqprio_qopt_reconstruct(struct net_device *dev, + struct tc_mqprio_qopt *qopt); + +#endif diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index c322a61eaeea..9781b47962bb 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -26,7 +26,11 @@ #include <net/sock.h> #include <net/tcp.h> +#include "sch_mqprio_lib.h" + static LIST_HEAD(taprio_list); +static struct static_key_false taprio_have_broken_mqprio; +static struct static_key_false taprio_have_working_mqprio; #define TAPRIO_ALL_GATES_OPEN -1 @@ -35,15 +39,19 @@ static LIST_HEAD(taprio_list); #define TAPRIO_FLAGS_INVALID U32_MAX struct sched_entry { - struct list_head list; - - /* The instant that this entry "closes" and the next one - * should open, the qdisc will make some effort so that no - * packet leaves after this time. + /* Durations between this GCL entry and the GCL entry where the + * respective traffic class gate closes */ - ktime_t close_time; + u64 gate_duration[TC_MAX_QUEUE]; + atomic_t budget[TC_MAX_QUEUE]; + /* The qdisc makes some effort so that no packet leaves + * after this time + */ + ktime_t gate_close_time[TC_MAX_QUEUE]; + struct list_head list; + /* Used to calculate when to advance the schedule */ + ktime_t end_time; ktime_t next_txtime; - atomic_t budget; int index; u32 gate_mask; u32 interval; @@ -51,10 +59,16 @@ struct sched_entry { }; struct sched_gate_list { + /* Longest non-zero contiguous gate durations per traffic class, + * or 0 if a traffic class gate never opens during the schedule. + */ + u64 max_open_gate_duration[TC_MAX_QUEUE]; + u32 max_frm_len[TC_MAX_QUEUE]; /* for the fast path */ + u32 max_sdu[TC_MAX_QUEUE]; /* for dump */ struct rcu_head rcu; struct list_head entries; size_t num_entries; - ktime_t cycle_close_time; + ktime_t cycle_end_time; s64 cycle_time; s64 cycle_time_extension; s64 base_time; @@ -67,6 +81,8 @@ struct taprio_sched { enum tk_offsets tk_offset; int clockid; bool offloaded; + bool detected_mqprio; + bool broken_mqprio; atomic64_t picos_per_byte; /* Using picoseconds because for 10Gbps+ * speeds it's sub-nanoseconds per byte */ @@ -78,8 +94,8 @@ struct taprio_sched { struct sched_gate_list __rcu *admin_sched; struct hrtimer advance_timer; struct list_head taprio_list; - u32 max_frm_len[TC_MAX_QUEUE]; /* for the fast path */ - u32 max_sdu[TC_MAX_QUEUE]; /* for dump and offloading */ + int cur_txq[TC_MAX_QUEUE]; + u32 max_sdu[TC_MAX_QUEUE]; /* save info from the user */ u32 txtime_delay; }; @@ -88,6 +104,57 @@ struct __tc_taprio_qopt_offload { struct tc_taprio_qopt_offload offload; }; +static void taprio_calculate_gate_durations(struct taprio_sched *q, + struct sched_gate_list *sched) +{ + struct net_device *dev = qdisc_dev(q->root); + int num_tc = netdev_get_num_tc(dev); + struct sched_entry *entry, *cur; + int tc; + + list_for_each_entry(entry, &sched->entries, list) { + u32 gates_still_open = entry->gate_mask; + + /* For each traffic class, calculate each open gate duration, + * starting at this schedule entry and ending at the schedule + * entry containing a gate close event for that TC. + */ + cur = entry; + + do { + if (!gates_still_open) + break; + + for (tc = 0; tc < num_tc; tc++) { + if (!(gates_still_open & BIT(tc))) + continue; + + if (cur->gate_mask & BIT(tc)) + entry->gate_duration[tc] += cur->interval; + else + gates_still_open &= ~BIT(tc); + } + + cur = list_next_entry_circular(cur, &sched->entries, list); + } while (cur != entry); + + /* Keep track of the maximum gate duration for each traffic + * class, taking care to not confuse a traffic class which is + * temporarily closed with one that is always closed. + */ + for (tc = 0; tc < num_tc; tc++) + if (entry->gate_duration[tc] && + sched->max_open_gate_duration[tc] < entry->gate_duration[tc]) + sched->max_open_gate_duration[tc] = entry->gate_duration[tc]; + } +} + +static bool taprio_entry_allows_tx(ktime_t skb_end_time, + struct sched_entry *entry, int tc) +{ + return ktime_before(skb_end_time, entry->gate_close_time[tc]); +} + static ktime_t sched_base_time(const struct sched_gate_list *sched) { if (!sched) @@ -180,6 +247,55 @@ static int length_to_duration(struct taprio_sched *q, int len) return div_u64(len * atomic64_read(&q->picos_per_byte), PSEC_PER_NSEC); } +static int duration_to_length(struct taprio_sched *q, u64 duration) +{ + return div_u64(duration * PSEC_PER_NSEC, atomic64_read(&q->picos_per_byte)); +} + +/* Sets sched->max_sdu[] and sched->max_frm_len[] to the minimum between the + * q->max_sdu[] requested by the user and the max_sdu dynamically determined by + * the maximum open gate durations at the given link speed. + */ +static void taprio_update_queue_max_sdu(struct taprio_sched *q, + struct sched_gate_list *sched, + struct qdisc_size_table *stab) +{ + struct net_device *dev = qdisc_dev(q->root); + int num_tc = netdev_get_num_tc(dev); + u32 max_sdu_from_user; + u32 max_sdu_dynamic; + u32 max_sdu; + int tc; + + for (tc = 0; tc < num_tc; tc++) { + max_sdu_from_user = q->max_sdu[tc] ?: U32_MAX; + + /* TC gate never closes => keep the queueMaxSDU + * selected by the user + */ + if (sched->max_open_gate_duration[tc] == sched->cycle_time) { + max_sdu_dynamic = U32_MAX; + } else { + u32 max_frm_len; + + max_frm_len = duration_to_length(q, sched->max_open_gate_duration[tc]); + if (stab) + max_frm_len -= stab->szopts.overhead; + max_sdu_dynamic = max_frm_len - dev->hard_header_len; + } + + max_sdu = min(max_sdu_dynamic, max_sdu_from_user); + + if (max_sdu != U32_MAX) { + sched->max_frm_len[tc] = max_sdu + dev->hard_header_len; + sched->max_sdu[tc] = max_sdu; + } else { + sched->max_frm_len[tc] = U32_MAX; /* never oversized */ + sched->max_sdu[tc] = 0; + } + } +} + /* Returns the entry corresponding to next available interval. If * validate_interval is set, it only validates whether the timestamp occurs * when the gate corresponding to the skb's traffic class is open. @@ -413,14 +529,33 @@ done: return txtime; } -static int taprio_enqueue_one(struct sk_buff *skb, struct Qdisc *sch, - struct Qdisc *child, struct sk_buff **to_free) +/* Devices with full offload are expected to honor this in hardware */ +static bool taprio_skb_exceeds_queue_max_sdu(struct Qdisc *sch, + struct sk_buff *skb) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); + struct sched_gate_list *sched; int prio = skb->priority; + bool exceeds = false; u8 tc; + tc = netdev_get_prio_tc_map(dev, prio); + + rcu_read_lock(); + sched = rcu_dereference(q->oper_sched); + if (sched && skb->len > sched->max_frm_len[tc]) + exceeds = true; + rcu_read_unlock(); + + return exceeds; +} + +static int taprio_enqueue_one(struct sk_buff *skb, struct Qdisc *sch, + struct Qdisc *child, struct sk_buff **to_free) +{ + struct taprio_sched *q = qdisc_priv(sch); + /* sk_flags are only safe to use on full sockets. */ if (skb->sk && sk_fullsock(skb->sk) && sock_flag(skb->sk, SOCK_TXTIME)) { if (!is_valid_interval(skb, sch)) @@ -431,17 +566,53 @@ static int taprio_enqueue_one(struct sk_buff *skb, struct Qdisc *sch, return qdisc_drop(skb, sch, to_free); } - /* Devices with full offload are expected to honor this in hardware */ - tc = netdev_get_prio_tc_map(dev, prio); - if (skb->len > q->max_frm_len[tc]) - return qdisc_drop(skb, sch, to_free); - qdisc_qstats_backlog_inc(sch, skb); sch->q.qlen++; return qdisc_enqueue(skb, child, to_free); } +static int taprio_enqueue_segmented(struct sk_buff *skb, struct Qdisc *sch, + struct Qdisc *child, + struct sk_buff **to_free) +{ + unsigned int slen = 0, numsegs = 0, len = qdisc_pkt_len(skb); + netdev_features_t features = netif_skb_features(skb); + struct sk_buff *segs, *nskb; + int ret; + + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + if (IS_ERR_OR_NULL(segs)) + return qdisc_drop(skb, sch, to_free); + + skb_list_walk_safe(segs, segs, nskb) { + skb_mark_not_on_list(segs); + qdisc_skb_cb(segs)->pkt_len = segs->len; + slen += segs->len; + + /* FIXME: we should be segmenting to a smaller size + * rather than dropping these + */ + if (taprio_skb_exceeds_queue_max_sdu(sch, segs)) + ret = qdisc_drop(segs, sch, to_free); + else + ret = taprio_enqueue_one(segs, sch, child, to_free); + + if (ret != NET_XMIT_SUCCESS) { + if (net_xmit_drop_count(ret)) + qdisc_qstats_drop(sch); + } else { + numsegs++; + } + } + + if (numsegs > 1) + qdisc_tree_reduce_backlog(sch, 1 - numsegs, len - slen); + consume_skb(skb); + + return numsegs > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; +} + /* Will not be called in the full offload case, since the TX queues are * attached to the Qdisc created using qdisc_create_dflt() */ @@ -458,97 +629,190 @@ static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (unlikely(!child)) return qdisc_drop(skb, sch, to_free); - /* Large packets might not be transmitted when the transmission duration - * exceeds any configured interval. Therefore, segment the skb into - * smaller chunks. Drivers with full offload are expected to handle - * this in hardware. - */ - if (skb_is_gso(skb)) { - unsigned int slen = 0, numsegs = 0, len = qdisc_pkt_len(skb); - netdev_features_t features = netif_skb_features(skb); - struct sk_buff *segs, *nskb; - int ret; - - segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); - if (IS_ERR_OR_NULL(segs)) - return qdisc_drop(skb, sch, to_free); + if (taprio_skb_exceeds_queue_max_sdu(sch, skb)) { + /* Large packets might not be transmitted when the transmission + * duration exceeds any configured interval. Therefore, segment + * the skb into smaller chunks. Drivers with full offload are + * expected to handle this in hardware. + */ + if (skb_is_gso(skb)) + return taprio_enqueue_segmented(skb, sch, child, + to_free); - skb_list_walk_safe(segs, segs, nskb) { - skb_mark_not_on_list(segs); - qdisc_skb_cb(segs)->pkt_len = segs->len; - slen += segs->len; + return qdisc_drop(skb, sch, to_free); + } - ret = taprio_enqueue_one(segs, sch, child, to_free); - if (ret != NET_XMIT_SUCCESS) { - if (net_xmit_drop_count(ret)) - qdisc_qstats_drop(sch); - } else { - numsegs++; - } - } + return taprio_enqueue_one(skb, sch, child, to_free); +} + +static struct sk_buff *taprio_peek(struct Qdisc *sch) +{ + WARN_ONCE(1, "taprio only supports operating as root qdisc, peek() not implemented"); + return NULL; +} + +static void taprio_set_budgets(struct taprio_sched *q, + struct sched_gate_list *sched, + struct sched_entry *entry) +{ + struct net_device *dev = qdisc_dev(q->root); + int num_tc = netdev_get_num_tc(dev); + int tc, budget; - if (numsegs > 1) - qdisc_tree_reduce_backlog(sch, 1 - numsegs, len - slen); - consume_skb(skb); + for (tc = 0; tc < num_tc; tc++) { + /* Traffic classes which never close have infinite budget */ + if (entry->gate_duration[tc] == sched->cycle_time) + budget = INT_MAX; + else + budget = div64_u64((u64)entry->gate_duration[tc] * PSEC_PER_NSEC, + atomic64_read(&q->picos_per_byte)); - return numsegs > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; + atomic_set(&entry->budget[tc], budget); } +} - return taprio_enqueue_one(skb, sch, child, to_free); +/* When an skb is sent, it consumes from the budget of all traffic classes */ +static int taprio_update_budgets(struct sched_entry *entry, size_t len, + int tc_consumed, int num_tc) +{ + int tc, budget, new_budget = 0; + + for (tc = 0; tc < num_tc; tc++) { + budget = atomic_read(&entry->budget[tc]); + /* Don't consume from infinite budget */ + if (budget == INT_MAX) { + if (tc == tc_consumed) + new_budget = budget; + continue; + } + + if (tc == tc_consumed) + new_budget = atomic_sub_return(len, &entry->budget[tc]); + else + atomic_sub(len, &entry->budget[tc]); + } + + return new_budget; } -/* Will not be called in the full offload case, since the TX queues are - * attached to the Qdisc created using qdisc_create_dflt() - */ -static struct sk_buff *taprio_peek(struct Qdisc *sch) +static struct sk_buff *taprio_dequeue_from_txq(struct Qdisc *sch, int txq, + struct sched_entry *entry, + u32 gate_mask) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); - struct sched_entry *entry; + struct Qdisc *child = q->qdiscs[txq]; + int num_tc = netdev_get_num_tc(dev); struct sk_buff *skb; - u32 gate_mask; - int i; + ktime_t guard; + int prio; + int len; + u8 tc; - rcu_read_lock(); - entry = rcu_dereference(q->current_entry); - gate_mask = entry ? entry->gate_mask : TAPRIO_ALL_GATES_OPEN; - rcu_read_unlock(); + if (unlikely(!child)) + return NULL; - if (!gate_mask) + if (TXTIME_ASSIST_IS_ENABLED(q->flags)) + goto skip_peek_checks; + + skb = child->ops->peek(child); + if (!skb) return NULL; - for (i = 0; i < dev->num_tx_queues; i++) { - struct Qdisc *child = q->qdiscs[i]; - int prio; - u8 tc; + prio = skb->priority; + tc = netdev_get_prio_tc_map(dev, prio); - if (unlikely(!child)) - continue; + if (!(gate_mask & BIT(tc))) + return NULL; - skb = child->ops->peek(child); - if (!skb) - continue; + len = qdisc_pkt_len(skb); + guard = ktime_add_ns(taprio_get_time(q), length_to_duration(q, len)); - if (TXTIME_ASSIST_IS_ENABLED(q->flags)) - return skb; + /* In the case that there's no gate entry, there's no + * guard band ... + */ + if (gate_mask != TAPRIO_ALL_GATES_OPEN && + !taprio_entry_allows_tx(guard, entry, tc)) + return NULL; + + /* ... and no budget. */ + if (gate_mask != TAPRIO_ALL_GATES_OPEN && + taprio_update_budgets(entry, len, tc, num_tc) < 0) + return NULL; + +skip_peek_checks: + skb = child->ops->dequeue(child); + if (unlikely(!skb)) + return NULL; + + qdisc_bstats_update(sch, skb); + qdisc_qstats_backlog_dec(sch, skb); + sch->q.qlen--; + + return skb; +} + +static void taprio_next_tc_txq(struct net_device *dev, int tc, int *txq) +{ + int offset = dev->tc_to_txq[tc].offset; + int count = dev->tc_to_txq[tc].count; + + (*txq)++; + if (*txq == offset + count) + *txq = offset; +} - prio = skb->priority; - tc = netdev_get_prio_tc_map(dev, prio); +/* Prioritize higher traffic classes, and select among TXQs belonging to the + * same TC using round robin + */ +static struct sk_buff *taprio_dequeue_tc_priority(struct Qdisc *sch, + struct sched_entry *entry, + u32 gate_mask) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + int num_tc = netdev_get_num_tc(dev); + struct sk_buff *skb; + int tc; + + for (tc = num_tc - 1; tc >= 0; tc--) { + int first_txq = q->cur_txq[tc]; if (!(gate_mask & BIT(tc))) continue; - return skb; + do { + skb = taprio_dequeue_from_txq(sch, q->cur_txq[tc], + entry, gate_mask); + + taprio_next_tc_txq(dev, tc, &q->cur_txq[tc]); + + if (skb) + return skb; + } while (q->cur_txq[tc] != first_txq); } return NULL; } -static void taprio_set_budget(struct taprio_sched *q, struct sched_entry *entry) +/* Broken way of prioritizing smaller TXQ indices and ignoring the traffic + * class other than to determine whether the gate is open or not + */ +static struct sk_buff *taprio_dequeue_txq_priority(struct Qdisc *sch, + struct sched_entry *entry, + u32 gate_mask) { - atomic_set(&entry->budget, - div64_u64((u64)entry->interval * PSEC_PER_NSEC, - atomic64_read(&q->picos_per_byte))); + struct net_device *dev = qdisc_dev(sch); + struct sk_buff *skb; + int i; + + for (i = 0; i < dev->num_tx_queues; i++) { + skb = taprio_dequeue_from_txq(sch, i, entry, gate_mask); + if (skb) + return skb; + } + + return NULL; } /* Will not be called in the full offload case, since the TX queues are @@ -557,11 +821,9 @@ static void taprio_set_budget(struct taprio_sched *q, struct sched_entry *entry) static struct sk_buff *taprio_dequeue(struct Qdisc *sch) { struct taprio_sched *q = qdisc_priv(sch); - struct net_device *dev = qdisc_dev(sch); struct sk_buff *skb = NULL; struct sched_entry *entry; u32 gate_mask; - int i; rcu_read_lock(); entry = rcu_dereference(q->current_entry); @@ -571,69 +833,23 @@ static struct sk_buff *taprio_dequeue(struct Qdisc *sch) * "AdminGateStates" */ gate_mask = entry ? entry->gate_mask : TAPRIO_ALL_GATES_OPEN; - if (!gate_mask) goto done; - for (i = 0; i < dev->num_tx_queues; i++) { - struct Qdisc *child = q->qdiscs[i]; - ktime_t guard; - int prio; - int len; - u8 tc; - - if (unlikely(!child)) - continue; - - if (TXTIME_ASSIST_IS_ENABLED(q->flags)) { - skb = child->ops->dequeue(child); - if (!skb) - continue; - goto skb_found; - } - - skb = child->ops->peek(child); - if (!skb) - continue; - - prio = skb->priority; - tc = netdev_get_prio_tc_map(dev, prio); - - if (!(gate_mask & BIT(tc))) { - skb = NULL; - continue; - } - - len = qdisc_pkt_len(skb); - guard = ktime_add_ns(taprio_get_time(q), - length_to_duration(q, len)); - - /* In the case that there's no gate entry, there's no - * guard band ... - */ - if (gate_mask != TAPRIO_ALL_GATES_OPEN && - ktime_after(guard, entry->close_time)) { - skb = NULL; - continue; - } - - /* ... and no budget. */ - if (gate_mask != TAPRIO_ALL_GATES_OPEN && - atomic_sub_return(len, &entry->budget) < 0) { - skb = NULL; - continue; - } - - skb = child->ops->dequeue(child); - if (unlikely(!skb)) - goto done; - -skb_found: - qdisc_bstats_update(sch, skb); - qdisc_qstats_backlog_dec(sch, skb); - sch->q.qlen--; - - goto done; + if (static_branch_unlikely(&taprio_have_broken_mqprio) && + !static_branch_likely(&taprio_have_working_mqprio)) { + /* Single NIC kind which is broken */ + skb = taprio_dequeue_txq_priority(sch, entry, gate_mask); + } else if (static_branch_likely(&taprio_have_working_mqprio) && + !static_branch_unlikely(&taprio_have_broken_mqprio)) { + /* Single NIC kind which prioritizes properly */ + skb = taprio_dequeue_tc_priority(sch, entry, gate_mask); + } else { + /* Mixed NIC kinds present in system, need dynamic testing */ + if (q->broken_mqprio) + skb = taprio_dequeue_txq_priority(sch, entry, gate_mask); + else + skb = taprio_dequeue_tc_priority(sch, entry, gate_mask); } done: @@ -648,7 +864,7 @@ static bool should_restart_cycle(const struct sched_gate_list *oper, if (list_is_last(&entry->list, &oper->entries)) return true; - if (ktime_compare(entry->close_time, oper->cycle_close_time) == 0) + if (ktime_compare(entry->end_time, oper->cycle_end_time) == 0) return true; return false; @@ -656,7 +872,7 @@ static bool should_restart_cycle(const struct sched_gate_list *oper, static bool should_change_schedules(const struct sched_gate_list *admin, const struct sched_gate_list *oper, - ktime_t close_time) + ktime_t end_time) { ktime_t next_base_time, extension_time; @@ -665,18 +881,18 @@ static bool should_change_schedules(const struct sched_gate_list *admin, next_base_time = sched_base_time(admin); - /* This is the simple case, the close_time would fall after + /* This is the simple case, the end_time would fall after * the next schedule base_time. */ - if (ktime_compare(next_base_time, close_time) <= 0) + if (ktime_compare(next_base_time, end_time) <= 0) return true; - /* This is the cycle_time_extension case, if the close_time + /* This is the cycle_time_extension case, if the end_time * plus the amount that can be extended would fall after the * next schedule base_time, we can extend the current schedule * for that amount. */ - extension_time = ktime_add_ns(close_time, oper->cycle_time_extension); + extension_time = ktime_add_ns(end_time, oper->cycle_time_extension); /* FIXME: the IEEE 802.1Q-2018 Specification isn't clear about * how precisely the extension should be made. So after @@ -692,10 +908,13 @@ static enum hrtimer_restart advance_sched(struct hrtimer *timer) { struct taprio_sched *q = container_of(timer, struct taprio_sched, advance_timer); + struct net_device *dev = qdisc_dev(q->root); struct sched_gate_list *oper, *admin; + int num_tc = netdev_get_num_tc(dev); struct sched_entry *entry, *next; struct Qdisc *sch = q->root; - ktime_t close_time; + ktime_t end_time; + int tc; spin_lock(&q->current_entry_lock); entry = rcu_dereference_protected(q->current_entry, @@ -714,41 +933,49 @@ static enum hrtimer_restart advance_sched(struct hrtimer *timer) * entry of all schedules are pre-calculated during the * schedule initialization. */ - if (unlikely(!entry || entry->close_time == oper->base_time)) { + if (unlikely(!entry || entry->end_time == oper->base_time)) { next = list_first_entry(&oper->entries, struct sched_entry, list); - close_time = next->close_time; + end_time = next->end_time; goto first_run; } if (should_restart_cycle(oper, entry)) { next = list_first_entry(&oper->entries, struct sched_entry, list); - oper->cycle_close_time = ktime_add_ns(oper->cycle_close_time, - oper->cycle_time); + oper->cycle_end_time = ktime_add_ns(oper->cycle_end_time, + oper->cycle_time); } else { next = list_next_entry(entry, list); } - close_time = ktime_add_ns(entry->close_time, next->interval); - close_time = min_t(ktime_t, close_time, oper->cycle_close_time); + end_time = ktime_add_ns(entry->end_time, next->interval); + end_time = min_t(ktime_t, end_time, oper->cycle_end_time); + + for (tc = 0; tc < num_tc; tc++) { + if (next->gate_duration[tc] == oper->cycle_time) + next->gate_close_time[tc] = KTIME_MAX; + else + next->gate_close_time[tc] = ktime_add_ns(entry->end_time, + next->gate_duration[tc]); + } - if (should_change_schedules(admin, oper, close_time)) { + if (should_change_schedules(admin, oper, end_time)) { /* Set things so the next time this runs, the new * schedule runs. */ - close_time = sched_base_time(admin); + end_time = sched_base_time(admin); switch_schedules(q, &admin, &oper); } - next->close_time = close_time; - taprio_set_budget(q, next); + next->end_time = end_time; + taprio_set_budgets(q, oper, next); first_run: rcu_assign_pointer(q->current_entry, next); spin_unlock(&q->current_entry_lock); - hrtimer_set_expires(&q->advance_timer, close_time); + hrtimer_set_expires(&q->advance_timer, end_time); rcu_read_lock(); __netif_schedule(sch); @@ -916,6 +1143,8 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, new->cycle_time = cycle; } + taprio_calculate_gate_durations(q, new); + return 0; } @@ -924,7 +1153,7 @@ static int taprio_parse_mqprio_opt(struct net_device *dev, struct netlink_ext_ack *extack, u32 taprio_flags) { - int i, j; + bool allow_overlapping_txqs = TXTIME_ASSIST_IS_ENABLED(taprio_flags); if (!qopt && !dev->num_tc) { NL_SET_ERR_MSG(extack, "'mqprio' configuration is necessary"); @@ -937,52 +1166,17 @@ static int taprio_parse_mqprio_opt(struct net_device *dev, if (dev->num_tc) return 0; - /* Verify num_tc is not out of max range */ - if (qopt->num_tc > TC_MAX_QUEUE) { - NL_SET_ERR_MSG(extack, "Number of traffic classes is outside valid range"); - return -EINVAL; - } - /* taprio imposes that traffic classes map 1:n to tx queues */ if (qopt->num_tc > dev->num_tx_queues) { NL_SET_ERR_MSG(extack, "Number of traffic classes is greater than number of HW queues"); return -EINVAL; } - /* Verify priority mapping uses valid tcs */ - for (i = 0; i <= TC_BITMASK; i++) { - if (qopt->prio_tc_map[i] >= qopt->num_tc) { - NL_SET_ERR_MSG(extack, "Invalid traffic class in priority to traffic class mapping"); - return -EINVAL; - } - } - - for (i = 0; i < qopt->num_tc; i++) { - unsigned int last = qopt->offset[i] + qopt->count[i]; - - /* Verify the queue count is in tx range being equal to the - * real_num_tx_queues indicates the last queue is in use. - */ - if (qopt->offset[i] >= dev->num_tx_queues || - !qopt->count[i] || - last > dev->real_num_tx_queues) { - NL_SET_ERR_MSG(extack, "Invalid queue in traffic class to queue mapping"); - return -EINVAL; - } - - if (TXTIME_ASSIST_IS_ENABLED(taprio_flags)) - continue; - - /* Verify that the offset and counts do not overlap */ - for (j = i + 1; j < qopt->num_tc; j++) { - if (last > qopt->offset[j]) { - NL_SET_ERR_MSG(extack, "Detected overlap in the traffic class to queue mapping"); - return -EINVAL; - } - } - } - - return 0; + /* For some reason, in txtime-assist mode, we allow TXQ ranges for + * different TCs to overlap, and just validate the TXQ ranges. + */ + return mqprio_validate_qopt(dev, qopt, true, allow_overlapping_txqs, + extack); } static int taprio_get_start_time(struct Qdisc *sch, @@ -1019,11 +1213,14 @@ static int taprio_get_start_time(struct Qdisc *sch, return 0; } -static void setup_first_close_time(struct taprio_sched *q, - struct sched_gate_list *sched, ktime_t base) +static void setup_first_end_time(struct taprio_sched *q, + struct sched_gate_list *sched, ktime_t base) { + struct net_device *dev = qdisc_dev(q->root); + int num_tc = netdev_get_num_tc(dev); struct sched_entry *first; ktime_t cycle; + int tc; first = list_first_entry(&sched->entries, struct sched_entry, list); @@ -1031,10 +1228,18 @@ static void setup_first_close_time(struct taprio_sched *q, cycle = sched->cycle_time; /* FIXME: find a better place to do this */ - sched->cycle_close_time = ktime_add_ns(base, cycle); + sched->cycle_end_time = ktime_add_ns(base, cycle); + + first->end_time = ktime_add_ns(base, first->interval); + taprio_set_budgets(q, sched, first); + + for (tc = 0; tc < num_tc; tc++) { + if (first->gate_duration[tc] == sched->cycle_time) + first->gate_close_time[tc] = KTIME_MAX; + else + first->gate_close_time[tc] = ktime_add_ns(base, first->gate_duration[tc]); + } - first->close_time = ktime_add_ns(base, first->interval); - taprio_set_budget(q, first); rcu_assign_pointer(q->current_entry, NULL); } @@ -1088,6 +1293,8 @@ static int taprio_dev_notifier(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct sched_gate_list *oper, *admin; + struct qdisc_size_table *stab; struct taprio_sched *q; ASSERT_RTNL(); @@ -1100,6 +1307,17 @@ static int taprio_dev_notifier(struct notifier_block *nb, unsigned long event, continue; taprio_set_picos_per_byte(dev, q); + + stab = rtnl_dereference(q->root->stab); + + oper = rtnl_dereference(q->oper_sched); + if (oper) + taprio_update_queue_max_sdu(q, oper, stab); + + admin = rtnl_dereference(q->admin_sched); + if (admin) + taprio_update_queue_max_sdu(q, admin, stab); + break; } @@ -1203,7 +1421,8 @@ static u32 tc_map_to_queue_mask(struct net_device *dev, u32 tc_mask) static void taprio_sched_to_offload(struct net_device *dev, struct sched_gate_list *sched, - struct tc_taprio_qopt_offload *offload) + struct tc_taprio_qopt_offload *offload, + const struct tc_taprio_caps *caps) { struct sched_entry *entry; int i = 0; @@ -1217,7 +1436,11 @@ static void taprio_sched_to_offload(struct net_device *dev, e->command = entry->command; e->interval = entry->interval; - e->gate_mask = tc_map_to_queue_mask(dev, entry->gate_mask); + if (caps->gate_mask_per_txq) + e->gate_mask = tc_map_to_queue_mask(dev, + entry->gate_mask); + else + e->gate_mask = entry->gate_mask; i++; } @@ -1225,6 +1448,34 @@ static void taprio_sched_to_offload(struct net_device *dev, offload->num_entries = i; } +static void taprio_detect_broken_mqprio(struct taprio_sched *q) +{ + struct net_device *dev = qdisc_dev(q->root); + struct tc_taprio_caps caps; + + qdisc_offload_query_caps(dev, TC_SETUP_QDISC_TAPRIO, + &caps, sizeof(caps)); + + q->broken_mqprio = caps.broken_mqprio; + if (q->broken_mqprio) + static_branch_inc(&taprio_have_broken_mqprio); + else + static_branch_inc(&taprio_have_working_mqprio); + + q->detected_mqprio = true; +} + +static void taprio_cleanup_broken_mqprio(struct taprio_sched *q) +{ + if (!q->detected_mqprio) + return; + + if (q->broken_mqprio) + static_branch_dec(&taprio_have_broken_mqprio); + else + static_branch_dec(&taprio_have_working_mqprio); +} + static int taprio_enable_offload(struct net_device *dev, struct taprio_sched *q, struct sched_gate_list *sched, @@ -1261,7 +1512,8 @@ static int taprio_enable_offload(struct net_device *dev, return -ENOMEM; } offload->enable = 1; - taprio_sched_to_offload(dev, sched, offload); + mqprio_qopt_reconstruct(dev, &offload->mqprio.qopt); + taprio_sched_to_offload(dev, sched, offload, &caps); for (tc = 0; tc < TC_MAX_QUEUE; tc++) offload->max_sdu[tc] = q->max_sdu[tc]; @@ -1452,7 +1704,6 @@ static int taprio_parse_tc_entries(struct Qdisc *sch, struct netlink_ext_ack *extack) { struct taprio_sched *q = qdisc_priv(sch); - struct net_device *dev = qdisc_dev(sch); u32 max_sdu[TC_QOPT_MAX_QUEUE]; unsigned long seen_tcs = 0; struct nlattr *n; @@ -1466,18 +1717,14 @@ static int taprio_parse_tc_entries(struct Qdisc *sch, if (nla_type(n) != TCA_TAPRIO_ATTR_TC_ENTRY) continue; - err = taprio_parse_tc_entry(sch, n, max_sdu, &seen_tcs, extack); + err = taprio_parse_tc_entry(sch, n, max_sdu, &seen_tcs, + extack); if (err) goto out; } - for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) { + for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) q->max_sdu[tc] = max_sdu[tc]; - if (max_sdu[tc]) - q->max_frm_len[tc] = max_sdu[tc] + dev->hard_header_len; - else - q->max_frm_len[tc] = U32_MAX; /* never oversized */ - } out: return err; @@ -1533,6 +1780,7 @@ static int taprio_new_flags(const struct nlattr *attr, u32 old, static int taprio_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + struct qdisc_size_table *stab = rtnl_dereference(sch->stab); struct nlattr *tb[TCA_TAPRIO_ATTR_MAX + 1] = { }; struct sched_gate_list *oper, *admin, *new_admin; struct taprio_sched *q = qdisc_priv(sch); @@ -1600,15 +1848,18 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, goto free_sched; taprio_set_picos_per_byte(dev, q); + taprio_update_queue_max_sdu(q, new_admin, stab); if (mqprio) { err = netdev_set_num_tc(dev, mqprio->num_tc); if (err) goto free_sched; - for (i = 0; i < mqprio->num_tc; i++) + for (i = 0; i < mqprio->num_tc; i++) { netdev_set_tc_queue(dev, i, mqprio->count[i], mqprio->offset[i]); + q->cur_txq[i] = mqprio->offset[i]; + } /* Always use supplied priority mappings */ for (i = 0; i <= TC_BITMASK; i++) @@ -1663,7 +1914,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, if (admin) call_rcu(&admin->rcu, taprio_free_sched_cb); } else { - setup_first_close_time(q, new_admin, start); + setup_first_end_time(q, new_admin, start); /* Protects against advance_sched() */ spin_lock_irqsave(&q->current_entry_lock, flags); @@ -1683,6 +1934,10 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, new_admin = NULL; err = 0; + if (!stab) + NL_SET_ERR_MSG_MOD(extack, + "Size table not specified, frame length estimations may be inaccurate"); + unlock: spin_unlock_bh(qdisc_lock(sch)); @@ -1743,6 +1998,8 @@ static void taprio_destroy(struct Qdisc *sch) if (admin) call_rcu(&admin->rcu, taprio_free_sched_cb); + + taprio_cleanup_broken_mqprio(q); } static int taprio_init(struct Qdisc *sch, struct nlattr *opt, @@ -1807,6 +2064,8 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt, q->qdiscs[i] = qdisc; } + taprio_detect_broken_mqprio(q); + return taprio_change(sch, opt, extack); } @@ -1947,7 +2206,8 @@ error_nest: return -1; } -static int taprio_dump_tc_entries(struct taprio_sched *q, struct sk_buff *skb) +static int taprio_dump_tc_entries(struct sk_buff *skb, + struct sched_gate_list *sched) { struct nlattr *n; int tc; @@ -1961,7 +2221,7 @@ static int taprio_dump_tc_entries(struct taprio_sched *q, struct sk_buff *skb) goto nla_put_failure; if (nla_put_u32(skb, TCA_TAPRIO_TC_ENTRY_MAX_SDU, - q->max_sdu[tc])) + sched->max_sdu[tc])) goto nla_put_failure; nla_nest_end(skb, n); @@ -1981,18 +2241,11 @@ static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) struct sched_gate_list *oper, *admin; struct tc_mqprio_qopt opt = { 0 }; struct nlattr *nest, *sched_nest; - unsigned int i; oper = rtnl_dereference(q->oper_sched); admin = rtnl_dereference(q->admin_sched); - opt.num_tc = netdev_get_num_tc(dev); - memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map)); - - for (i = 0; i < netdev_get_num_tc(dev); i++) { - opt.count[i] = dev->tc_to_txq[i].count; - opt.offset[i] = dev->tc_to_txq[i].offset; - } + mqprio_qopt_reconstruct(dev, &opt); nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!nest) @@ -2012,7 +2265,7 @@ static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) nla_put_u32(skb, TCA_TAPRIO_ATTR_TXTIME_DELAY, q->txtime_delay)) goto options_error; - if (taprio_dump_tc_entries(q, skb)) + if (oper && taprio_dump_tc_entries(skb, oper)) goto options_error; if (oper && dump_schedule(skb, oper)) diff --git a/net/sctp/transport.c b/net/sctp/transport.c index ca1eba95c293..2f66a2006517 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -196,9 +196,7 @@ void sctp_transport_reset_hb_timer(struct sctp_transport *transport) /* When a data chunk is sent, reset the heartbeat interval. */ expires = jiffies + sctp_transport_timeout(transport); - if ((time_before(transport->hb_timer.expires, expires) || - !timer_pending(&transport->hb_timer)) && - !mod_timer(&transport->hb_timer, + if (!mod_timer(&transport->hb_timer, expires + get_random_u32_below(transport->rto))) sctp_transport_hold(transport); } diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 1c0fe9ba5358..b163266e581a 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -502,7 +502,7 @@ static int smcr_lgr_reg_sndbufs(struct smc_link *link, return -EINVAL; /* protect against parallel smcr_link_reg_buf() */ - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (!smc_link_active(&lgr->lnk[i])) continue; @@ -510,7 +510,7 @@ static int smcr_lgr_reg_sndbufs(struct smc_link *link, if (rc) break; } - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); return rc; } @@ -519,15 +519,30 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link, struct smc_buf_desc *rmb_desc) { struct smc_link_group *lgr = link->lgr; + bool do_slow = false; int i, rc = 0; rc = smc_llc_flow_initiate(lgr, SMC_LLC_FLOW_RKEY); if (rc) return rc; + + down_read(&lgr->llc_conf_mutex); + for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { + if (!smc_link_active(&lgr->lnk[i])) + continue; + if (!rmb_desc->is_reg_mr[link->link_idx]) { + up_read(&lgr->llc_conf_mutex); + goto slow_path; + } + } + /* mr register already */ + goto fast_path; +slow_path: + do_slow = true; /* protect against parallel smc_llc_cli_rkey_exchange() and * parallel smcr_link_reg_buf() */ - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (!smc_link_active(&lgr->lnk[i])) continue; @@ -535,7 +550,7 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link, if (rc) goto out; } - +fast_path: /* exchange confirm_rkey msg with peer */ rc = smc_llc_do_confirm_rkey(link, rmb_desc); if (rc) { @@ -544,7 +559,7 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link, } rmb_desc->is_conf_rkey = true; out: - mutex_unlock(&lgr->llc_conf_mutex); + do_slow ? up_write(&lgr->llc_conf_mutex) : up_read(&lgr->llc_conf_mutex); smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl); return rc; } diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 7642b16c41d1..b330a1fa453e 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -854,8 +854,8 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) lgr->freeing = 0; lgr->vlan_id = ini->vlan_id; refcount_set(&lgr->refcnt, 1); /* set lgr refcnt to 1 */ - mutex_init(&lgr->sndbufs_lock); - mutex_init(&lgr->rmbs_lock); + init_rwsem(&lgr->sndbufs_lock); + init_rwsem(&lgr->rmbs_lock); rwlock_init(&lgr->conns_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { INIT_LIST_HEAD(&lgr->sndbufs[i]); @@ -1098,7 +1098,7 @@ err_out: static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, struct smc_link_group *lgr) { - struct mutex *lock; /* lock buffer list */ + struct rw_semaphore *lock; /* lock buffer list */ int rc; if (is_rmb && buf_desc->is_conf_rkey && !list_empty(&lgr->list)) { @@ -1106,10 +1106,10 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, rc = smc_llc_flow_initiate(lgr, SMC_LLC_FLOW_RKEY); if (!rc) { /* protect against smc_llc_cli_rkey_exchange() */ - mutex_lock(&lgr->llc_conf_mutex); + down_read(&lgr->llc_conf_mutex); smc_llc_do_delete_rkey(lgr, buf_desc); buf_desc->is_conf_rkey = false; - mutex_unlock(&lgr->llc_conf_mutex); + up_read(&lgr->llc_conf_mutex); smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl); } } @@ -1118,9 +1118,9 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, /* buf registration failed, reuse not possible */ lock = is_rmb ? &lgr->rmbs_lock : &lgr->sndbufs_lock; - mutex_lock(lock); + down_write(lock); list_del(&buf_desc->list); - mutex_unlock(lock); + up_write(lock); smc_buf_free(lgr, is_rmb, buf_desc); } else { @@ -1224,15 +1224,16 @@ static void smcr_buf_unmap_lgr(struct smc_link *lnk) int i; for (i = 0; i < SMC_RMBE_SIZES; i++) { - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list) smcr_buf_unmap_link(buf_desc, true, lnk); - mutex_unlock(&lgr->rmbs_lock); - mutex_lock(&lgr->sndbufs_lock); + up_write(&lgr->rmbs_lock); + + down_write(&lgr->sndbufs_lock); list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i], list) smcr_buf_unmap_link(buf_desc, false, lnk); - mutex_unlock(&lgr->sndbufs_lock); + up_write(&lgr->sndbufs_lock); } } @@ -1377,12 +1378,12 @@ static void smc_lgr_free(struct smc_link_group *lgr) int i; if (!lgr->is_smcd) { - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (lgr->lnk[i].state != SMC_LNK_UNUSED) smcr_link_clear(&lgr->lnk[i], false); } - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); smc_llc_lgr_clear(lgr); } @@ -1696,12 +1697,12 @@ static void smcr_link_down(struct smc_link *lnk) } else { if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE) { /* another llc task is ongoing */ - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); wait_event_timeout(lgr->llc_flow_waiter, (list_empty(&lgr->list) || lgr->llc_flow_lcl.type == SMC_LLC_FLOW_NONE), SMC_LLC_WAIT_TIME); - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); } if (!list_empty(&lgr->list)) { smc_llc_send_delete_link(to_lnk, del_link_id, @@ -1761,9 +1762,9 @@ static void smc_link_down_work(struct work_struct *work) if (list_empty(&lgr->list)) return; wake_up_all(&lgr->llc_msg_waiter); - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); smcr_link_down(link); - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); } static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev, @@ -1990,19 +1991,19 @@ int smc_uncompress_bufsize(u8 compressed) * buffer size; if not available, return NULL */ static struct smc_buf_desc *smc_buf_get_slot(int compressed_bufsize, - struct mutex *lock, + struct rw_semaphore *lock, struct list_head *buf_list) { struct smc_buf_desc *buf_slot; - mutex_lock(lock); + down_read(lock); list_for_each_entry(buf_slot, buf_list, list) { if (cmpxchg(&buf_slot->used, 0, 1) == 0) { - mutex_unlock(lock); + up_read(lock); return buf_slot; } } - mutex_unlock(lock); + up_read(lock); return NULL; } @@ -2111,13 +2112,13 @@ int smcr_link_reg_buf(struct smc_link *link, struct smc_buf_desc *buf_desc) return 0; } -static int _smcr_buf_map_lgr(struct smc_link *lnk, struct mutex *lock, +static int _smcr_buf_map_lgr(struct smc_link *lnk, struct rw_semaphore *lock, struct list_head *lst, bool is_rmb) { struct smc_buf_desc *buf_desc, *bf; int rc = 0; - mutex_lock(lock); + down_write(lock); list_for_each_entry_safe(buf_desc, bf, lst, list) { if (!buf_desc->used) continue; @@ -2126,7 +2127,7 @@ static int _smcr_buf_map_lgr(struct smc_link *lnk, struct mutex *lock, goto out; } out: - mutex_unlock(lock); + up_write(lock); return rc; } @@ -2159,37 +2160,37 @@ int smcr_buf_reg_lgr(struct smc_link *lnk) int i, rc = 0; /* reg all RMBs for a new link */ - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list) { if (!buf_desc->used) continue; rc = smcr_link_reg_buf(lnk, buf_desc); if (rc) { - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return rc; } } } - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); if (lgr->buf_type == SMCR_PHYS_CONT_BUFS) return rc; /* reg all vzalloced sndbufs for a new link */ - mutex_lock(&lgr->sndbufs_lock); + down_write(&lgr->sndbufs_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i], list) { if (!buf_desc->used || !buf_desc->is_vm) continue; rc = smcr_link_reg_buf(lnk, buf_desc); if (rc) { - mutex_unlock(&lgr->sndbufs_lock); + up_write(&lgr->sndbufs_lock); return rc; } } } - mutex_unlock(&lgr->sndbufs_lock); + up_write(&lgr->sndbufs_lock); return rc; } @@ -2247,7 +2248,7 @@ static int smcr_buf_map_usable_links(struct smc_link_group *lgr, int i, rc = 0, cnt = 0; /* protect against parallel link reconfiguration */ - mutex_lock(&lgr->llc_conf_mutex); + down_read(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *lnk = &lgr->lnk[i]; @@ -2260,7 +2261,7 @@ static int smcr_buf_map_usable_links(struct smc_link_group *lgr, cnt++; } out: - mutex_unlock(&lgr->llc_conf_mutex); + up_read(&lgr->llc_conf_mutex); if (!rc && !cnt) rc = -EINVAL; return rc; @@ -2309,8 +2310,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) struct smc_link_group *lgr = conn->lgr; struct list_head *buf_list; int bufsize, bufsize_short; + struct rw_semaphore *lock; /* lock buffer list */ bool is_dgraded = false; - struct mutex *lock; /* lock buffer list */ int sk_buf_size; if (is_rmb) @@ -2358,9 +2359,9 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rmb); SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); buf_desc->used = 1; - mutex_lock(lock); + down_write(lock); list_add(&buf_desc->list, buf_list); - mutex_unlock(lock); + up_write(lock); break; /* found */ } @@ -2434,9 +2435,9 @@ int smc_buf_create(struct smc_sock *smc, bool is_smcd) /* create rmb */ rc = __smc_buf_create(smc, is_smcd, true); if (rc) { - mutex_lock(&smc->conn.lgr->sndbufs_lock); + down_write(&smc->conn.lgr->sndbufs_lock); list_del(&smc->conn.sndbuf_desc->list); - mutex_unlock(&smc->conn.lgr->sndbufs_lock); + up_write(&smc->conn.lgr->sndbufs_lock); smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc); smc->conn.sndbuf_desc = NULL; } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 285f9bd8e232..08b457c2d294 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -252,9 +252,9 @@ struct smc_link_group { unsigned short vlan_id; /* vlan id of link group */ struct list_head sndbufs[SMC_RMBE_SIZES];/* tx buffers */ - struct mutex sndbufs_lock; /* protects tx buffers */ + struct rw_semaphore sndbufs_lock; /* protects tx buffers */ struct list_head rmbs[SMC_RMBE_SIZES]; /* rx buffers */ - struct mutex rmbs_lock; /* protects rx buffers */ + struct rw_semaphore rmbs_lock; /* protects rx buffers */ u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */ struct delayed_work free_work; /* delayed freeing of an lgr */ @@ -298,7 +298,7 @@ struct smc_link_group { /* queue for llc events */ spinlock_t llc_event_q_lock; /* protects llc_event_q */ - struct mutex llc_conf_mutex; + struct rw_semaphore llc_conf_mutex; /* protects lgr reconfig. */ struct work_struct llc_add_link_work; struct work_struct llc_del_link_work; diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 524649d0ab65..a0840b8c935b 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -608,7 +608,7 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, prim_lnk_idx = link->link_idx; lnk_idx = link_new->link_idx; - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); ext->num_rkeys = lgr->conns_num; if (!ext->num_rkeys) goto out; @@ -628,7 +628,7 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, } len += i * sizeof(ext->rt[0]); out: - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return len; } @@ -889,7 +889,7 @@ static int smc_llc_cli_rkey_exchange(struct smc_link *link, int rc = 0; int i; - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); num_rkeys_send = lgr->conns_num; buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst); do { @@ -916,7 +916,7 @@ static int smc_llc_cli_rkey_exchange(struct smc_link *link, break; } while (num_rkeys_send || num_rkeys_recv); - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return rc; } @@ -999,14 +999,14 @@ static void smc_llc_save_add_link_rkeys(struct smc_link *link, ext = (struct smc_llc_msg_add_link_v2_ext *)((u8 *)lgr->wr_rx_buf_v2 + SMC_WR_TX_SIZE); max = min_t(u8, ext->num_rkeys, SMC_LLC_RKEYS_PER_MSG_V2); - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); for (i = 0; i < max; i++) { smc_rtoken_set(lgr, link->link_idx, link_new->link_idx, ext->rt[i].rmb_key, ext->rt[i].rmb_vaddr_new, ext->rt[i].rmb_key_new); } - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); } static void smc_llc_save_add_link_info(struct smc_link *link, @@ -1202,12 +1202,12 @@ static void smc_llc_process_cli_add_link(struct smc_link_group *lgr) qentry = smc_llc_flow_qentry_clr(&lgr->llc_flow_lcl); - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); if (smc_llc_is_local_add_link(&qentry->msg)) smc_llc_cli_add_link_invite(qentry->link, qentry); else smc_llc_cli_add_link(qentry->link, qentry); - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); } static int smc_llc_active_link_count(struct smc_link_group *lgr) @@ -1313,7 +1313,7 @@ static int smc_llc_srv_rkey_exchange(struct smc_link *link, int rc = 0; int i; - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); num_rkeys_send = lgr->conns_num; buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst); do { @@ -1338,7 +1338,7 @@ static int smc_llc_srv_rkey_exchange(struct smc_link *link, smc_llc_flow_qentry_del(&lgr->llc_flow_lcl); } while (num_rkeys_send || num_rkeys_recv); out: - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return rc; } @@ -1509,13 +1509,13 @@ static void smc_llc_process_srv_add_link(struct smc_link_group *lgr) qentry = smc_llc_flow_qentry_clr(&lgr->llc_flow_lcl); - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); rc = smc_llc_srv_add_link(link, qentry); if (!rc && lgr->type == SMC_LGR_SYMMETRIC) { /* delete any asymmetric link */ smc_llc_delete_asym_link(lgr); } - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); kfree(qentry); } @@ -1582,7 +1582,7 @@ static void smc_llc_process_cli_delete_link(struct smc_link_group *lgr) smc_lgr_terminate_sched(lgr); goto out; } - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); /* delete single link */ for (lnk_idx = 0; lnk_idx < SMC_LINKS_PER_LGR_MAX; lnk_idx++) { if (lgr->lnk[lnk_idx].link_id != del_llc->link_num) @@ -1616,7 +1616,7 @@ static void smc_llc_process_cli_delete_link(struct smc_link_group *lgr) smc_lgr_terminate_sched(lgr); } out_unlock: - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); out: kfree(qentry); } @@ -1652,7 +1652,7 @@ static void smc_llc_process_srv_delete_link(struct smc_link_group *lgr) int active_links; int i; - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); qentry = smc_llc_flow_qentry_clr(&lgr->llc_flow_lcl); lnk = qentry->link; del_llc = &qentry->msg.delete_link; @@ -1708,7 +1708,7 @@ static void smc_llc_process_srv_delete_link(struct smc_link_group *lgr) smc_llc_add_link_local(lnk); } out: - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); kfree(qentry); } @@ -2126,7 +2126,7 @@ void smc_llc_lgr_init(struct smc_link_group *lgr, struct smc_sock *smc) spin_lock_init(&lgr->llc_flow_lock); init_waitqueue_head(&lgr->llc_flow_waiter); init_waitqueue_head(&lgr->llc_msg_waiter); - mutex_init(&lgr->llc_conf_mutex); + init_rwsem(&lgr->llc_conf_mutex); lgr->llc_testlink_time = READ_ONCE(net->smc.sysctl_smcr_testlink_time); } diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index dfea27a906f2..9b47c8409231 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -39,6 +39,7 @@ #include "node.h" #include "net.h" #include <net/genetlink.h> +#include <linux/string_helpers.h> #include <linux/tipc_config.h> /* The legacy API had an artificial message length limit called @@ -173,11 +174,6 @@ static struct sk_buff *tipc_get_err_tlv(char *str) return buf; } -static inline bool string_is_valid(char *s, int len) -{ - return memchr(s, '\0', len) ? true : false; -} - static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, struct tipc_nl_compat_msg *msg, struct sk_buff *arg) @@ -445,7 +441,7 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd, return -EINVAL; len = min_t(int, len, TIPC_MAX_BEARER_NAME); - if (!string_is_valid(b->name, len)) + if (!string_is_terminated(b->name, len)) return -EINVAL; if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, b->name)) @@ -486,7 +482,7 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd, return -EINVAL; len = min_t(int, len, TIPC_MAX_BEARER_NAME); - if (!string_is_valid(name, len)) + if (!string_is_terminated(name, len)) return -EINVAL; if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, name)) @@ -584,7 +580,7 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg, return -EINVAL; len = min_t(int, len, TIPC_MAX_LINK_NAME); - if (!string_is_valid(name, len)) + if (!string_is_terminated(name, len)) return -EINVAL; if (strcmp(name, nla_data(link[TIPC_NLA_LINK_NAME])) != 0) @@ -819,7 +815,7 @@ static int tipc_nl_compat_link_set(struct tipc_nl_compat_cmd_doit *cmd, return -EINVAL; len = min_t(int, len, TIPC_MAX_LINK_NAME); - if (!string_is_valid(lc->name, len)) + if (!string_is_terminated(lc->name, len)) return -EINVAL; media = tipc_media_find(lc->name); @@ -856,7 +852,7 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd, return -EINVAL; len = min_t(int, len, TIPC_MAX_LINK_NAME); - if (!string_is_valid(name, len)) + if (!string_is_terminated(name, len)) return -EINVAL; if (nla_put_string(skb, TIPC_NLA_LINK_NAME, name)) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index fa137063aaa0..6d0a534b7baa 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2430,7 +2430,7 @@ static bool tls_is_tx_ready(struct tls_sw_context_tx *ctx) { struct tls_rec *rec; - rec = list_first_entry(&ctx->tx_list, struct tls_rec, list); + rec = list_first_entry_or_null(&ctx->tx_list, struct tls_rec, list); if (!rec) return false; diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index a0f62fa02e06..8cbf45a8bcdc 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -5,6 +5,7 @@ * Based on code and translator idea by: Florian Westphal <fw@strlen.de> */ #include <linux/compat.h> +#include <linux/nospec.h> #include <linux/xfrm.h> #include <net/xfrm.h> @@ -302,7 +303,7 @@ static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src) nla_for_each_attr(nla, attrs, len, remaining) { int err; - switch (type) { + switch (nlh_src->nlmsg_type) { case XFRM_MSG_NEWSPDINFO: err = xfrm_nla_cpy(dst, nla, nla_len(nla)); break; @@ -437,6 +438,7 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, NL_SET_ERR_MSG(extack, "Bad attribute"); return -EOPNOTSUPP; } + type = array_index_nospec(type, XFRMA_MAX + 1); if (nla_len(nla) < compat_policy[type].len) { NL_SET_ERR_MSG(extack, "Attribute bad length"); return -EOPNOTSUPP; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 562b9d951598..95f1436bf6a2 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -325,8 +325,10 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, * authors to do not return -EOPNOTSUPP in packet offload mode. */ WARN_ON(err == -EOPNOTSUPP && is_packet_offload); - if (err != -EOPNOTSUPP || is_packet_offload) + if (err != -EOPNOTSUPP || is_packet_offload) { + NL_SET_ERR_MSG_WEAK(extack, "Device failed to offload this state"); return err; + } } return 0; @@ -388,6 +390,7 @@ int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, xdo->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; xdo->dir = 0; netdev_put(dev, &xdo->dev_tracker); + NL_SET_ERR_MSG_WEAK(extack, "Device failed to offload this policy"); return err; } diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index c06e54a10540..436d29640ac2 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -279,8 +279,7 @@ static int xfrm6_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb) goto out; if (x->props.flags & XFRM_STATE_DECAP_DSCP) - ipv6_copy_dscp(ipv6_get_dsfield(ipv6_hdr(skb)), - ipipv6_hdr(skb)); + ipv6_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, ipipv6_hdr(skb)); if (!(x->props.flags & XFRM_STATE_NOECN)) ipip6_ecn_decapsulate(skb); diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 1f99dc469027..35279c220bd7 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -310,6 +310,52 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) skb->mark = 0; } +static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type, unsigned short family) +{ + struct sec_path *sp; + + sp = skb_sec_path(skb); + if (sp && (sp->len || sp->olen) && + !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + goto discard; + + XFRM_SPI_SKB_CB(skb)->family = family; + if (family == AF_INET) { + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + } else { + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; + } + + return xfrm_input(skb, nexthdr, spi, encap_type); +discard: + kfree_skb(skb); + return 0; +} + +static int xfrmi4_rcv(struct sk_buff *skb) +{ + return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET); +} + +static int xfrmi6_rcv(struct sk_buff *skb) +{ + return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], + 0, 0, AF_INET6); +} + +static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) +{ + return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET); +} + +static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) +{ + return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6); +} + static int xfrmi_rcv_cb(struct sk_buff *skb, int err) { const struct xfrm_mode *inner_mode; @@ -945,8 +991,8 @@ static struct pernet_operations xfrmi_net_ops = { }; static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { - .handler = xfrm6_rcv, - .input_handler = xfrm_input, + .handler = xfrmi6_rcv, + .input_handler = xfrmi6_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, @@ -996,8 +1042,8 @@ static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = { #endif static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { - .handler = xfrm4_rcv, - .input_handler = xfrm_input, + .handler = xfrmi4_rcv, + .input_handler = xfrmi4_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index e9eb82c5457d..5c61ec04b839 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -336,7 +336,7 @@ static void xfrm_policy_timer(struct timer_list *t) } if (xp->lft.hard_use_expires_seconds) { time64_t tmo = xp->lft.hard_use_expires_seconds + - (xp->curlft.use_time ? : xp->curlft.add_time) - now; + (READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now; if (tmo <= 0) goto expired; if (tmo < next) @@ -354,7 +354,7 @@ static void xfrm_policy_timer(struct timer_list *t) } if (xp->lft.soft_use_expires_seconds) { time64_t tmo = xp->lft.soft_use_expires_seconds + - (xp->curlft.use_time ? : xp->curlft.add_time) - now; + (READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now; if (tmo <= 0) { warn = 1; tmo = XFRM_KM_TIMEOUT; @@ -3661,7 +3661,8 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, return 1; } - pol->curlft.use_time = ktime_get_real_seconds(); + /* This lockless write can happen from different cpus. */ + WRITE_ONCE(pol->curlft.use_time, ktime_get_real_seconds()); pols[0] = pol; npols++; @@ -3676,7 +3677,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, xfrm_pol_put(pols[0]); return 0; } - pols[1]->curlft.use_time = ktime_get_real_seconds(); + /* This write can happen from different cpus. */ + WRITE_ONCE(pols[1]->curlft.use_time, + ktime_get_real_seconds()); npols++; } } @@ -3742,6 +3745,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, goto reject; } + if (if_id) + secpath_reset(skb); + xfrm_pols_put(pols, npols); return 1; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 59fffa02d1cc..2ab3e09e2227 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -577,7 +577,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) if (x->km.state == XFRM_STATE_EXPIRED) goto expired; if (x->lft.hard_add_expires_seconds) { - long tmo = x->lft.hard_add_expires_seconds + + time64_t tmo = x->lft.hard_add_expires_seconds + x->curlft.add_time - now; if (tmo <= 0) { if (x->xflags & XFRM_SOFT_EXPIRE) { @@ -594,8 +594,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) next = tmo; } if (x->lft.hard_use_expires_seconds) { - long tmo = x->lft.hard_use_expires_seconds + - (x->curlft.use_time ? : now) - now; + time64_t tmo = x->lft.hard_use_expires_seconds + + (READ_ONCE(x->curlft.use_time) ? : now) - now; if (tmo <= 0) goto expired; if (tmo < next) @@ -604,7 +604,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) if (x->km.dying) goto resched; if (x->lft.soft_add_expires_seconds) { - long tmo = x->lft.soft_add_expires_seconds + + time64_t tmo = x->lft.soft_add_expires_seconds + x->curlft.add_time - now; if (tmo <= 0) { warn = 1; @@ -616,8 +616,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) } } if (x->lft.soft_use_expires_seconds) { - long tmo = x->lft.soft_use_expires_seconds + - (x->curlft.use_time ? : now) - now; + time64_t tmo = x->lft.soft_use_expires_seconds + + (READ_ONCE(x->curlft.use_time) ? : now) - now; if (tmo <= 0) warn = 1; else if (tmo < next) @@ -1906,7 +1906,7 @@ out: hrtimer_start(&x1->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); - if (x1->curlft.use_time) + if (READ_ONCE(x1->curlft.use_time)) xfrm_state_check_expire(x1); if (x->props.smark.m || x->props.smark.v || x->if_id) { @@ -1940,8 +1940,8 @@ int xfrm_state_check_expire(struct xfrm_state *x) { xfrm_dev_state_update_curlft(x); - if (!x->curlft.use_time) - x->curlft.use_time = ktime_get_real_seconds(); + if (!READ_ONCE(x->curlft.use_time)) + WRITE_ONCE(x->curlft.use_time, ktime_get_real_seconds()); if (x->curlft.bytes >= x->lft.hard_byte_limit || x->curlft.packets >= x->lft.hard_packet_limit) { diff --git a/samples/ftrace/ftrace-direct-multi-modify.c b/samples/ftrace/ftrace-direct-multi-modify.c index d52370cad0b6..a825dbd2c9cf 100644 --- a/samples/ftrace/ftrace-direct-multi-modify.c +++ b/samples/ftrace/ftrace-direct-multi-modify.c @@ -152,6 +152,7 @@ static void __exit ftrace_direct_multi_exit(void) { kthread_stop(simple_tsk); unregister_ftrace_direct_multi(&direct, my_tramp); + ftrace_free_filter(&direct); } module_init(ftrace_direct_multi_init); diff --git a/samples/ftrace/ftrace-direct-multi.c b/samples/ftrace/ftrace-direct-multi.c index ec1088922517..d955a2650605 100644 --- a/samples/ftrace/ftrace-direct-multi.c +++ b/samples/ftrace/ftrace-direct-multi.c @@ -79,6 +79,7 @@ static int __init ftrace_direct_multi_init(void) static void __exit ftrace_direct_multi_exit(void) { unregister_ftrace_direct_multi(&direct, (unsigned long) my_tramp); + ftrace_free_filter(&direct); } module_init(ftrace_direct_multi_init); diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst index 836391e5d209..4815a8e32227 100644 --- a/scripts/Makefile.modinst +++ b/scripts/Makefile.modinst @@ -66,9 +66,13 @@ endif # Don't stop modules_install even if we can't sign external modules. # ifeq ($(CONFIG_MODULE_SIG_ALL),y) +ifeq ($(filter pkcs11:%, $(CONFIG_MODULE_SIG_KEY)),) sig-key := $(if $(wildcard $(CONFIG_MODULE_SIG_KEY)),,$(srctree)/)$(CONFIG_MODULE_SIG_KEY) +else +sig-key := $(CONFIG_MODULE_SIG_KEY) +endif quiet_cmd_sign = SIGN $@ - cmd_sign = scripts/sign-file $(CONFIG_MODULE_SIG_HASH) $(sig-key) certs/signing_key.x509 $@ \ + cmd_sign = scripts/sign-file $(CONFIG_MODULE_SIG_HASH) "$(sig-key)" certs/signing_key.x509 $@ \ $(if $(KBUILD_EXTMOD),|| true) else quiet_cmd_sign := diff --git a/scripts/atomic/atomics.tbl b/scripts/atomic/atomics.tbl index fbee2f6190d9..fbee2f6190d9 100755..100644 --- a/scripts/atomic/atomics.tbl +++ b/scripts/atomic/atomics.tbl diff --git a/scripts/gcc-plugins/gcc-common.h b/scripts/gcc-plugins/gcc-common.h index 9a1895747b15..84c730da36dd 100644 --- a/scripts/gcc-plugins/gcc-common.h +++ b/scripts/gcc-plugins/gcc-common.h @@ -71,7 +71,9 @@ #include "varasm.h" #include "stor-layout.h" #include "internal-fn.h" +#include "gimple.h" #include "gimple-expr.h" +#include "gimple-iterator.h" #include "gimple-fold.h" #include "context.h" #include "tree-ssa-alias.h" @@ -85,10 +87,8 @@ #include "tree-eh.h" #include "stmt.h" #include "gimplify.h" -#include "gimple.h" #include "tree-phinodes.h" #include "tree-cfg.h" -#include "gimple-iterator.h" #include "gimple-ssa.h" #include "ssa-iterators.h" diff --git a/scripts/tracing/ftrace-bisect.sh b/scripts/tracing/ftrace-bisect.sh index 926701162bc8..bb4f59262bbe 100755 --- a/scripts/tracing/ftrace-bisect.sh +++ b/scripts/tracing/ftrace-bisect.sh @@ -12,7 +12,7 @@ # (note, if this is a problem with function_graph tracing, then simply # replace "function" with "function_graph" in the following steps). # -# # cd /sys/kernel/debug/tracing +# # cd /sys/kernel/tracing # # echo schedule > set_ftrace_filter # # echo function > current_tracer # @@ -20,22 +20,40 @@ # # # echo nop > current_tracer # -# # cat available_filter_functions > ~/full-file +# Starting with v5.1 this can be done with numbers, making it much faster: +# +# The old (slow) way, for kernels before v5.1. +# +# [old-way] # cat available_filter_functions > ~/full-file +# +# [old-way] *** Note *** this process will take several minutes to update the +# [old-way] filters. Setting multiple functions is an O(n^2) operation, and we +# [old-way] are dealing with thousands of functions. So go have coffee, talk +# [old-way] with your coworkers, read facebook. And eventually, this operation +# [old-way] will end. +# +# The new way (using numbers) is an O(n) operation, and usually takes less than a second. +# +# seq `wc -l available_filter_functions | cut -d' ' -f1` > ~/full-file +# +# This will create a sequence of numbers that match the functions in +# available_filter_functions, and when echoing in a number into the +# set_ftrace_filter file, it will enable the corresponding function in +# O(1) time. Making enabling all functions O(n) where n is the number of +# functions to enable. +# +# For either the new or old way, the rest of the operations remain the same. +# # # ftrace-bisect ~/full-file ~/test-file ~/non-test-file # # cat ~/test-file > set_ftrace_filter # -# *** Note *** this will take several minutes. Setting multiple functions is -# an O(n^2) operation, and we are dealing with thousands of functions. So go -# have coffee, talk with your coworkers, read facebook. And eventually, this -# operation will end. -# # # echo function > current_tracer # # If it crashes, we know that ~/test-file has a bad function. # # Reboot back to test kernel. # -# # cd /sys/kernel/debug/tracing +# # cd /sys/kernel/tracing # # mv ~/test-file ~/full-file # # If it didn't crash. diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c index 81025f50a542..f901504b5afc 100644 --- a/sound/core/memalloc.c +++ b/sound/core/memalloc.c @@ -541,16 +541,15 @@ static void *snd_dma_noncontig_alloc(struct snd_dma_buffer *dmab, size_t size) struct sg_table *sgt; void *p; +#ifdef CONFIG_SND_DMA_SGBUF + if (cpu_feature_enabled(X86_FEATURE_XENPV)) + return snd_dma_sg_fallback_alloc(dmab, size); +#endif sgt = dma_alloc_noncontiguous(dmab->dev.dev, size, dmab->dev.dir, DEFAULT_GFP, 0); #ifdef CONFIG_SND_DMA_SGBUF - if (!sgt && !get_dma_ops(dmab->dev.dev)) { - if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG) - dmab->dev.type = SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK; - else - dmab->dev.type = SNDRV_DMA_TYPE_DEV_SG_FALLBACK; + if (!sgt && !get_dma_ops(dmab->dev.dev)) return snd_dma_sg_fallback_alloc(dmab, size); - } #endif if (!sgt) return NULL; @@ -717,19 +716,38 @@ static const struct snd_malloc_ops snd_dma_sg_wc_ops = { /* Fallback SG-buffer allocations for x86 */ struct snd_dma_sg_fallback { + bool use_dma_alloc_coherent; size_t count; struct page **pages; + /* DMA address array; the first page contains #pages in ~PAGE_MASK */ + dma_addr_t *addrs; }; static void __snd_dma_sg_fallback_free(struct snd_dma_buffer *dmab, struct snd_dma_sg_fallback *sgbuf) { - bool wc = dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK; - size_t i; - - for (i = 0; i < sgbuf->count && sgbuf->pages[i]; i++) - do_free_pages(page_address(sgbuf->pages[i]), PAGE_SIZE, wc); + size_t i, size; + + if (sgbuf->pages && sgbuf->addrs) { + i = 0; + while (i < sgbuf->count) { + if (!sgbuf->pages[i] || !sgbuf->addrs[i]) + break; + size = sgbuf->addrs[i] & ~PAGE_MASK; + if (WARN_ON(!size)) + break; + if (sgbuf->use_dma_alloc_coherent) + dma_free_coherent(dmab->dev.dev, size << PAGE_SHIFT, + page_address(sgbuf->pages[i]), + sgbuf->addrs[i] & PAGE_MASK); + else + do_free_pages(page_address(sgbuf->pages[i]), + size << PAGE_SHIFT, false); + i += size; + } + } kvfree(sgbuf->pages); + kvfree(sgbuf->addrs); kfree(sgbuf); } @@ -738,24 +756,36 @@ static void *snd_dma_sg_fallback_alloc(struct snd_dma_buffer *dmab, size_t size) struct snd_dma_sg_fallback *sgbuf; struct page **pagep, *curp; size_t chunk, npages; + dma_addr_t *addrp; dma_addr_t addr; void *p; - bool wc = dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK; + + /* correct the type */ + if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_SG) + dmab->dev.type = SNDRV_DMA_TYPE_DEV_SG_FALLBACK; + else if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG) + dmab->dev.type = SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK; sgbuf = kzalloc(sizeof(*sgbuf), GFP_KERNEL); if (!sgbuf) return NULL; + sgbuf->use_dma_alloc_coherent = cpu_feature_enabled(X86_FEATURE_XENPV); size = PAGE_ALIGN(size); sgbuf->count = size >> PAGE_SHIFT; sgbuf->pages = kvcalloc(sgbuf->count, sizeof(*sgbuf->pages), GFP_KERNEL); - if (!sgbuf->pages) + sgbuf->addrs = kvcalloc(sgbuf->count, sizeof(*sgbuf->addrs), GFP_KERNEL); + if (!sgbuf->pages || !sgbuf->addrs) goto error; pagep = sgbuf->pages; - chunk = size; + addrp = sgbuf->addrs; + chunk = (PAGE_SIZE - 1) << PAGE_SHIFT; /* to fit in low bits in addrs */ while (size > 0) { chunk = min(size, chunk); - p = do_alloc_pages(dmab->dev.dev, chunk, &addr, wc); + if (sgbuf->use_dma_alloc_coherent) + p = dma_alloc_coherent(dmab->dev.dev, chunk, &addr, DEFAULT_GFP); + else + p = do_alloc_pages(dmab->dev.dev, chunk, &addr, false); if (!p) { if (chunk <= PAGE_SIZE) goto error; @@ -767,17 +797,25 @@ static void *snd_dma_sg_fallback_alloc(struct snd_dma_buffer *dmab, size_t size) size -= chunk; /* fill pages */ npages = chunk >> PAGE_SHIFT; + *addrp = npages; /* store in lower bits */ curp = virt_to_page(p); - while (npages--) + while (npages--) { *pagep++ = curp++; + *addrp++ |= addr; + addr += PAGE_SIZE; + } } p = vmap(sgbuf->pages, sgbuf->count, VM_MAP, PAGE_KERNEL); if (!p) goto error; + + if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK) + set_pages_array_wc(sgbuf->pages, sgbuf->count); + dmab->private_data = sgbuf; /* store the first page address for convenience */ - dmab->addr = snd_sgbuf_get_addr(dmab, 0); + dmab->addr = sgbuf->addrs[0] & PAGE_MASK; return p; error: @@ -787,10 +825,23 @@ static void *snd_dma_sg_fallback_alloc(struct snd_dma_buffer *dmab, size_t size) static void snd_dma_sg_fallback_free(struct snd_dma_buffer *dmab) { + struct snd_dma_sg_fallback *sgbuf = dmab->private_data; + + if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK) + set_pages_array_wb(sgbuf->pages, sgbuf->count); vunmap(dmab->area); __snd_dma_sg_fallback_free(dmab, dmab->private_data); } +static dma_addr_t snd_dma_sg_fallback_get_addr(struct snd_dma_buffer *dmab, + size_t offset) +{ + struct snd_dma_sg_fallback *sgbuf = dmab->private_data; + size_t index = offset >> PAGE_SHIFT; + + return (sgbuf->addrs[index] & PAGE_MASK) | (offset & ~PAGE_MASK); +} + static int snd_dma_sg_fallback_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { @@ -805,8 +856,8 @@ static const struct snd_malloc_ops snd_dma_sg_fallback_ops = { .alloc = snd_dma_sg_fallback_alloc, .free = snd_dma_sg_fallback_free, .mmap = snd_dma_sg_fallback_mmap, + .get_addr = snd_dma_sg_fallback_get_addr, /* reuse vmalloc helpers */ - .get_addr = snd_dma_vmalloc_get_addr, .get_page = snd_dma_vmalloc_get_page, .get_chunk_size = snd_dma_vmalloc_get_chunk_size, }; diff --git a/sound/firewire/motu/motu-hwdep.c b/sound/firewire/motu/motu-hwdep.c index a900fc0e7644..88d1f4b56e4b 100644 --- a/sound/firewire/motu/motu-hwdep.c +++ b/sound/firewire/motu/motu-hwdep.c @@ -87,6 +87,10 @@ static long hwdep_read(struct snd_hwdep *hwdep, char __user *buf, long count, return -EFAULT; count = consumed; + } else { + spin_unlock_irq(&motu->lock); + + count = 0; } return count; diff --git a/sound/pci/hda/hda_bind.c b/sound/pci/hda/hda_bind.c index 1a868dd9dc4b..890c2f7c33fc 100644 --- a/sound/pci/hda/hda_bind.c +++ b/sound/pci/hda/hda_bind.c @@ -144,6 +144,7 @@ static int hda_codec_driver_probe(struct device *dev) error: snd_hda_codec_cleanup_for_unbind(codec); + codec->preset = NULL; return err; } @@ -166,6 +167,7 @@ static int hda_codec_driver_remove(struct device *dev) if (codec->patch_ops.free) codec->patch_ops.free(codec); snd_hda_codec_cleanup_for_unbind(codec); + codec->preset = NULL; module_put(dev->driver->owner); return 0; } diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index edd653ece70d..ac1cc7c5290e 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -795,7 +795,6 @@ void snd_hda_codec_cleanup_for_unbind(struct hda_codec *codec) snd_array_free(&codec->cvt_setups); snd_array_free(&codec->spdif_out); snd_array_free(&codec->verbs); - codec->preset = NULL; codec->follower_dig_outs = NULL; codec->spdif_status_reset = 0; snd_array_free(&codec->mixers); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 6fab7c8fc19a..db9518de9343 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9202,6 +9202,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x142b, "Acer Swift SF314-42", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1430, "Acer TravelMate B311R-31", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1466, "Acer Aspire A515-56", ALC255_FIXUP_ACER_HEADPHONE_AND_MIC), + SND_PCI_QUIRK(0x1025, 0x1534, "Acer Predator PH315-54", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z), SND_PCI_QUIRK(0x1028, 0x053c, "Dell Latitude E5430", ALC292_FIXUP_DELL_E7X), SND_PCI_QUIRK(0x1028, 0x054b, "Dell XPS one 2710", ALC275_FIXUP_DELL_XPS), @@ -9432,6 +9433,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b5d, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b5e, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8b92, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8bf0, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c index aea7fae2ca4b..2994f85bc1b9 100644 --- a/sound/pci/hda/patch_via.c +++ b/sound/pci/hda/patch_via.c @@ -819,6 +819,9 @@ static int add_secret_dac_path(struct hda_codec *codec) return 0; nums = snd_hda_get_connections(codec, spec->gen.mixer_nid, conn, ARRAY_SIZE(conn) - 1); + if (nums < 0) + return nums; + for (i = 0; i < nums; i++) { if (get_wcaps_type(get_wcaps(codec, conn[i])) == AC_WID_AUD_OUT) return 0; diff --git a/sound/soc/amd/acp-es8336.c b/sound/soc/amd/acp-es8336.c index 2fe8df86053a..89499542c803 100644 --- a/sound/soc/amd/acp-es8336.c +++ b/sound/soc/amd/acp-es8336.c @@ -198,9 +198,11 @@ static int st_es8336_late_probe(struct snd_soc_card *card) int ret; adev = acpi_dev_get_first_match_dev("ESSX8336", NULL, -1); - if (adev) - put_device(&adev->dev); + if (!adev) + return -ENODEV; + codec_dev = acpi_get_first_physical_node(adev); + acpi_dev_put(adev); if (!codec_dev) dev_err(card->dev, "can not find codec dev\n"); diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 0d283e41f66d..36314753923b 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -230,10 +230,31 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { { .driver_data = &acp6x_card, .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "TIMI"), + DMI_MATCH(DMI_PRODUCT_NAME, "Redmi Book Pro 15 2022"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Razer"), DMI_MATCH(DMI_PRODUCT_NAME, "Blade 14 (2022) - RZ09-0427"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "RB"), + DMI_MATCH(DMI_PRODUCT_NAME, "Swift SFA16-41"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "IRBIS"), + DMI_MATCH(DMI_PRODUCT_NAME, "15NBC1011"), + } + }, {} }; diff --git a/sound/soc/codecs/cs42l56.c b/sound/soc/codecs/cs42l56.c index 26066682c983..3b0e715549c9 100644 --- a/sound/soc/codecs/cs42l56.c +++ b/sound/soc/codecs/cs42l56.c @@ -1191,18 +1191,12 @@ static int cs42l56_i2c_probe(struct i2c_client *i2c_client) if (pdata) { cs42l56->pdata = *pdata; } else { - pdata = devm_kzalloc(&i2c_client->dev, sizeof(*pdata), - GFP_KERNEL); - if (!pdata) - return -ENOMEM; - if (i2c_client->dev.of_node) { ret = cs42l56_handle_of_data(i2c_client, &cs42l56->pdata); if (ret != 0) return ret; } - cs42l56->pdata = *pdata; } if (cs42l56->pdata.gpio_nreset) { diff --git a/sound/soc/codecs/wsa883x.c b/sound/soc/codecs/wsa883x.c index 966ba4909204..58fdb4e9fd97 100644 --- a/sound/soc/codecs/wsa883x.c +++ b/sound/soc/codecs/wsa883x.c @@ -1359,8 +1359,8 @@ static struct snd_soc_dai_driver wsa883x_dais[] = { .stream_name = "SPKR Playback", .rates = WSA883X_RATES | WSA883X_FRAC_RATES, .formats = WSA883X_FORMATS, - .rate_max = 8000, - .rate_min = 352800, + .rate_min = 8000, + .rate_max = 352800, .channels_min = 1, .channels_max = 1, }, diff --git a/sound/soc/intel/avs/core.c b/sound/soc/intel/avs/core.c index 2ca24273c491..637501850728 100644 --- a/sound/soc/intel/avs/core.c +++ b/sound/soc/intel/avs/core.c @@ -481,6 +481,29 @@ err_remap_bar0: return ret; } +static void avs_pci_shutdown(struct pci_dev *pci) +{ + struct hdac_bus *bus = pci_get_drvdata(pci); + struct avs_dev *adev = hdac_to_avs(bus); + + cancel_work_sync(&adev->probe_work); + avs_ipc_block(adev->ipc); + + snd_hdac_stop_streams(bus); + avs_dsp_op(adev, int_control, false); + snd_hdac_ext_bus_ppcap_int_enable(bus, false); + snd_hdac_ext_bus_link_power_down_all(bus); + + snd_hdac_bus_stop_chip(bus); + snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, false); + + if (avs_platattr_test(adev, CLDMA)) + pci_free_irq(pci, 0, &code_loader); + pci_free_irq(pci, 0, adev); + pci_free_irq(pci, 0, bus); + pci_free_irq_vectors(pci); +} + static void avs_pci_remove(struct pci_dev *pci) { struct hdac_device *hdev, *save; @@ -739,6 +762,7 @@ static struct pci_driver avs_pci_driver = { .id_table = avs_ids, .probe = avs_pci_probe, .remove = avs_pci_remove, + .shutdown = avs_pci_shutdown, .driver = { .pm = &avs_dev_pm, }, diff --git a/sound/soc/intel/boards/bytcht_es8316.c b/sound/soc/intel/boards/bytcht_es8316.c index 09d1f0f6d686..df157b01df8b 100644 --- a/sound/soc/intel/boards/bytcht_es8316.c +++ b/sound/soc/intel/boards/bytcht_es8316.c @@ -497,21 +497,28 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev) if (adev) { snprintf(codec_name, sizeof(codec_name), "i2c-%s", acpi_dev_name(adev)); - put_device(&adev->dev); byt_cht_es8316_dais[dai_index].codecs->name = codec_name; } else { dev_err(dev, "Error cannot find '%s' dev\n", mach->id); return -ENXIO; } + codec_dev = acpi_get_first_physical_node(adev); + acpi_dev_put(adev); + if (!codec_dev) + return -EPROBE_DEFER; + priv->codec_dev = get_device(codec_dev); + /* override platform name, if required */ byt_cht_es8316_card.dev = dev; platform_name = mach->mach_params.platform; ret = snd_soc_fixup_dai_links_platform_name(&byt_cht_es8316_card, platform_name); - if (ret) + if (ret) { + put_device(codec_dev); return ret; + } /* Check for BYTCR or other platform and setup quirks */ dmi_id = dmi_first_match(byt_cht_es8316_quirk_table); @@ -539,13 +546,10 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev) /* get the clock */ priv->mclk = devm_clk_get(dev, "pmc_plt_clk_3"); - if (IS_ERR(priv->mclk)) + if (IS_ERR(priv->mclk)) { + put_device(codec_dev); return dev_err_probe(dev, PTR_ERR(priv->mclk), "clk_get pmc_plt_clk_3 failed\n"); - - codec_dev = acpi_get_first_physical_node(adev); - if (!codec_dev) - return -EPROBE_DEFER; - priv->codec_dev = get_device(codec_dev); + } if (quirk & BYT_CHT_ES8316_JD_INVERTED) props[cnt++] = PROPERTY_ENTRY_BOOL("everest,jack-detect-inverted"); diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 4699ca79f3ea..79e0039c79a3 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -1636,13 +1636,18 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev) if (adev) { snprintf(byt_rt5640_codec_name, sizeof(byt_rt5640_codec_name), "i2c-%s", acpi_dev_name(adev)); - put_device(&adev->dev); byt_rt5640_dais[dai_index].codecs->name = byt_rt5640_codec_name; } else { dev_err(dev, "Error cannot find '%s' dev\n", mach->id); return -ENXIO; } + codec_dev = acpi_get_first_physical_node(adev); + acpi_dev_put(adev); + if (!codec_dev) + return -EPROBE_DEFER; + priv->codec_dev = get_device(codec_dev); + /* * swap SSP0 if bytcr is detected * (will be overridden if DMI quirk is detected) @@ -1717,11 +1722,6 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev) byt_rt5640_quirk = quirk_override; } - codec_dev = acpi_get_first_physical_node(adev); - if (!codec_dev) - return -EPROBE_DEFER; - priv->codec_dev = get_device(codec_dev); - if (byt_rt5640_quirk & BYT_RT5640_JD_HP_ELITEP_1000G2) { acpi_dev_add_driver_gpios(ACPI_COMPANION(priv->codec_dev), byt_rt5640_hp_elitepad_1000g2_gpios); diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c index 81ac6eeda2e6..8fca9b82d4d0 100644 --- a/sound/soc/intel/boards/bytcr_rt5651.c +++ b/sound/soc/intel/boards/bytcr_rt5651.c @@ -922,7 +922,6 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev) if (adev) { snprintf(byt_rt5651_codec_name, sizeof(byt_rt5651_codec_name), "i2c-%s", acpi_dev_name(adev)); - put_device(&adev->dev); byt_rt5651_dais[dai_index].codecs->name = byt_rt5651_codec_name; } else { dev_err(dev, "Error cannot find '%s' dev\n", mach->id); @@ -930,6 +929,7 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev) } codec_dev = acpi_get_first_physical_node(adev); + acpi_dev_put(adev); if (!codec_dev) return -EPROBE_DEFER; priv->codec_dev = get_device(codec_dev); diff --git a/sound/soc/intel/boards/bytcr_wm5102.c b/sound/soc/intel/boards/bytcr_wm5102.c index 1669eb3bd80f..c0706537f673 100644 --- a/sound/soc/intel/boards/bytcr_wm5102.c +++ b/sound/soc/intel/boards/bytcr_wm5102.c @@ -411,9 +411,9 @@ static int snd_byt_wm5102_mc_probe(struct platform_device *pdev) return -ENOENT; } snprintf(codec_name, sizeof(codec_name), "spi-%s", acpi_dev_name(adev)); - put_device(&adev->dev); codec_dev = bus_find_device_by_name(&spi_bus_type, NULL, codec_name); + acpi_dev_put(adev); if (!codec_dev) return -EPROBE_DEFER; diff --git a/sound/soc/intel/boards/sof_cs42l42.c b/sound/soc/intel/boards/sof_cs42l42.c index e38bd2831e6a..e9d190cb13b0 100644 --- a/sound/soc/intel/boards/sof_cs42l42.c +++ b/sound/soc/intel/boards/sof_cs42l42.c @@ -336,6 +336,9 @@ static int create_spk_amp_dai_links(struct device *dev, links[*id].platforms = platform_component; links[*id].num_platforms = ARRAY_SIZE(platform_component); links[*id].dpcm_playback = 1; + /* firmware-generated echo reference */ + links[*id].dpcm_capture = 1; + links[*id].no_pcm = 1; links[*id].cpus = &cpus[*id]; links[*id].num_cpus = 1; diff --git a/sound/soc/intel/boards/sof_es8336.c b/sound/soc/intel/boards/sof_es8336.c index 773e5d1d87d4..894b6610b9e2 100644 --- a/sound/soc/intel/boards/sof_es8336.c +++ b/sound/soc/intel/boards/sof_es8336.c @@ -681,7 +681,6 @@ static int sof_es8336_probe(struct platform_device *pdev) if (adev) { snprintf(codec_name, sizeof(codec_name), "i2c-%s", acpi_dev_name(adev)); - put_device(&adev->dev); dai_links[0].codecs->name = codec_name; /* also fixup codec dai name if relevant */ @@ -692,16 +691,19 @@ static int sof_es8336_probe(struct platform_device *pdev) return -ENXIO; } - ret = snd_soc_fixup_dai_links_platform_name(&sof_es8336_card, - mach->mach_params.platform); - if (ret) - return ret; - codec_dev = acpi_get_first_physical_node(adev); + acpi_dev_put(adev); if (!codec_dev) return -EPROBE_DEFER; priv->codec_dev = get_device(codec_dev); + ret = snd_soc_fixup_dai_links_platform_name(&sof_es8336_card, + mach->mach_params.platform); + if (ret) { + put_device(codec_dev); + return ret; + } + if (quirk & SOF_ES8336_JD_INVERTED) props[cnt++] = PROPERTY_ENTRY_BOOL("everest,jack-detect-inverted"); diff --git a/sound/soc/intel/boards/sof_nau8825.c b/sound/soc/intel/boards/sof_nau8825.c index a800854c2831..6794a0249a9a 100644 --- a/sound/soc/intel/boards/sof_nau8825.c +++ b/sound/soc/intel/boards/sof_nau8825.c @@ -487,8 +487,6 @@ static struct snd_soc_dai_link *sof_card_dai_links_create(struct device *dev, links[id].num_codecs = ARRAY_SIZE(max_98373_components); links[id].init = max_98373_spk_codec_init; links[id].ops = &max_98373_ops; - /* feedback stream */ - links[id].dpcm_capture = 1; } else if (sof_nau8825_quirk & SOF_MAX98360A_SPEAKER_AMP_PRESENT) { max_98360a_dai_link(&links[id]); @@ -506,6 +504,9 @@ static struct snd_soc_dai_link *sof_card_dai_links_create(struct device *dev, links[id].platforms = platform_component; links[id].num_platforms = ARRAY_SIZE(platform_component); links[id].dpcm_playback = 1; + /* feedback stream or firmware-generated echo reference */ + links[id].dpcm_capture = 1; + links[id].no_pcm = 1; links[id].cpus = &cpus[id]; links[id].num_cpus = 1; diff --git a/sound/soc/intel/boards/sof_rt5682.c b/sound/soc/intel/boards/sof_rt5682.c index 2eabc4b0fafa..71a11d747622 100644 --- a/sound/soc/intel/boards/sof_rt5682.c +++ b/sound/soc/intel/boards/sof_rt5682.c @@ -761,8 +761,6 @@ static struct snd_soc_dai_link *sof_card_dai_links_create(struct device *dev, links[id].num_codecs = ARRAY_SIZE(max_98373_components); links[id].init = max_98373_spk_codec_init; links[id].ops = &max_98373_ops; - /* feedback stream */ - links[id].dpcm_capture = 1; } else if (sof_rt5682_quirk & SOF_MAX98360A_SPEAKER_AMP_PRESENT) { max_98360a_dai_link(&links[id]); @@ -789,6 +787,9 @@ static struct snd_soc_dai_link *sof_card_dai_links_create(struct device *dev, links[id].platforms = platform_component; links[id].num_platforms = ARRAY_SIZE(platform_component); links[id].dpcm_playback = 1; + /* feedback stream or firmware-generated echo reference */ + links[id].dpcm_capture = 1; + links[id].no_pcm = 1; links[id].cpus = &cpus[id]; links[id].num_cpus = 1; diff --git a/sound/soc/intel/boards/sof_ssp_amp.c b/sound/soc/intel/boards/sof_ssp_amp.c index 94d25aeb6e7c..7b74f122e340 100644 --- a/sound/soc/intel/boards/sof_ssp_amp.c +++ b/sound/soc/intel/boards/sof_ssp_amp.c @@ -258,13 +258,12 @@ static struct snd_soc_dai_link *sof_card_dai_links_create(struct device *dev, sof_rt1308_dai_link(&links[id]); } else if (sof_ssp_amp_quirk & SOF_CS35L41_SPEAKER_AMP_PRESENT) { cs35l41_set_dai_link(&links[id]); - - /* feedback from amplifier */ - links[id].dpcm_capture = 1; } links[id].platforms = platform_component; links[id].num_platforms = ARRAY_SIZE(platform_component); links[id].dpcm_playback = 1; + /* feedback from amplifier or firmware-generated echo reference */ + links[id].dpcm_capture = 1; links[id].no_pcm = 1; links[id].cpus = &cpus[id]; links[id].num_cpus = 1; diff --git a/sound/soc/sof/ipc4-mtrace.c b/sound/soc/sof/ipc4-mtrace.c index 70dea8ae706e..0ec6ef681012 100644 --- a/sound/soc/sof/ipc4-mtrace.c +++ b/sound/soc/sof/ipc4-mtrace.c @@ -344,9 +344,10 @@ static ssize_t sof_ipc4_priority_mask_dfs_write(struct file *file, size_t count, loff_t *ppos) { struct sof_mtrace_priv *priv = file->private_data; - int id, ret; + unsigned int id; char *buf; u32 mask; + int ret; /* * To update Nth mask entry, write: @@ -357,9 +358,9 @@ static ssize_t sof_ipc4_priority_mask_dfs_write(struct file *file, if (IS_ERR(buf)) return PTR_ERR(buf); - ret = sscanf(buf, "%d,0x%x", &id, &mask); + ret = sscanf(buf, "%u,0x%x", &id, &mask); if (ret != 2) { - ret = sscanf(buf, "%d,%x", &id, &mask); + ret = sscanf(buf, "%u,%x", &id, &mask); if (ret != 2) { ret = -EINVAL; goto out; diff --git a/sound/soc/sof/sof-audio.c b/sound/soc/sof/sof-audio.c index 7306a2649857..865c367eb2f2 100644 --- a/sound/soc/sof/sof-audio.c +++ b/sound/soc/sof/sof-audio.c @@ -271,9 +271,9 @@ sof_unprepare_widgets_in_path(struct snd_sof_dev *sdev, struct snd_soc_dapm_widg struct snd_sof_widget *swidget = widget->dobj.private; struct snd_soc_dapm_path *p; - /* return if the widget is in use or if it is already unprepared */ - if (!swidget->prepared || swidget->use_count > 1) - return; + /* skip if the widget is in use or if it is already unprepared */ + if (!swidget || !swidget->prepared || swidget->use_count > 0) + goto sink_unprepare; if (widget_ops[widget->id].ipc_unprepare) /* unprepare the source widget */ @@ -281,6 +281,7 @@ sof_unprepare_widgets_in_path(struct snd_sof_dev *sdev, struct snd_soc_dapm_widg swidget->prepared = false; +sink_unprepare: /* unprepare all widgets in the sink paths */ snd_soc_dapm_widget_for_each_sink_path(widget, p) { if (!p->walking && p->sink->dobj.private) { @@ -303,7 +304,7 @@ sof_prepare_widgets_in_path(struct snd_sof_dev *sdev, struct snd_soc_dapm_widget struct snd_soc_dapm_path *p; int ret; - if (!widget_ops[widget->id].ipc_prepare || swidget->prepared) + if (!swidget || !widget_ops[widget->id].ipc_prepare || swidget->prepared) goto sink_prepare; /* prepare the source widget */ @@ -326,7 +327,8 @@ sink_prepare: p->walking = false; if (ret < 0) { /* unprepare the source widget */ - if (widget_ops[widget->id].ipc_unprepare && swidget->prepared) { + if (widget_ops[widget->id].ipc_unprepare && + swidget && swidget->prepared) { widget_ops[widget->id].ipc_unprepare(swidget); swidget->prepared = false; } @@ -429,11 +431,11 @@ sof_walk_widgets_in_order(struct snd_sof_dev *sdev, struct snd_soc_dapm_widget_l for_each_dapm_widgets(list, i, widget) { /* starting widget for playback is AIF type */ - if (dir == SNDRV_PCM_STREAM_PLAYBACK && !WIDGET_IS_AIF(widget->id)) + if (dir == SNDRV_PCM_STREAM_PLAYBACK && widget->id != snd_soc_dapm_aif_in) continue; /* starting widget for capture is DAI type */ - if (dir == SNDRV_PCM_STREAM_CAPTURE && !WIDGET_IS_DAI(widget->id)) + if (dir == SNDRV_PCM_STREAM_CAPTURE && widget->id != snd_soc_dapm_dai_out) continue; switch (op) { diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 3d13fdf7590c..3ecd1ba7fd4b 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2152,6 +2152,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x0525, 0xa4ad, /* Hamedal C20 usb camero */ QUIRK_FLAG_IFACE_SKIP_CLOSE), + DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */ + QUIRK_FLAG_FIXED_RATE), DEVICE_FLG(0x0ecb, 0x2069, /* JBL Quantum810 Wireless */ QUIRK_FLAG_FIXED_RATE), diff --git a/tools/gpio/gpio-event-mon.c b/tools/gpio/gpio-event-mon.c index 6c122952c589..5dee2b98ab60 100644 --- a/tools/gpio/gpio-event-mon.c +++ b/tools/gpio/gpio-event-mon.c @@ -86,6 +86,7 @@ int monitor_device(const char *device_name, gpiotools_test_bit(values.bits, i)); } + i = 0; while (1) { struct gpio_v2_line_event event; diff --git a/tools/net/ynl/samples/cli.py b/tools/net/ynl/cli.py index b27159c70710..db410b74d539 100755 --- a/tools/net/ynl/samples/cli.py +++ b/tools/net/ynl/cli.py @@ -1,4 +1,4 @@ -#!/usr/bin/env python +#!/usr/bin/env python3 # SPDX-License-Identifier: BSD-3-Clause import argparse @@ -6,13 +6,14 @@ import json import pprint import time -from ynl import YnlFamily +from lib import YnlFamily def main(): parser = argparse.ArgumentParser(description='YNL CLI sample') parser.add_argument('--spec', dest='spec', type=str, required=True) parser.add_argument('--schema', dest='schema', type=str) + parser.add_argument('--no-schema', action='store_true') parser.add_argument('--json', dest='json_text', type=str) parser.add_argument('--do', dest='do', type=str) parser.add_argument('--dump', dest='dump', type=str) @@ -20,6 +21,9 @@ def main(): parser.add_argument('--subscribe', dest='ntf', type=str) args = parser.parse_args() + if args.no_schema: + args.schema = '' + attrs = {} if args.json_text: attrs = json.loads(args.json_text) @@ -32,10 +36,11 @@ def main(): if args.sleep: time.sleep(args.sleep) - if args.do or args.dump: - method = getattr(ynl, args.do if args.do else args.dump) - - reply = method(attrs, dump=bool(args.dump)) + if args.do: + reply = ynl.do(args.do, attrs) + pprint.PrettyPrinter().pprint(reply) + if args.dump: + reply = ynl.dump(args.dump, attrs) pprint.PrettyPrinter().pprint(reply) if args.ntf: diff --git a/tools/net/ynl/lib/__init__.py b/tools/net/ynl/lib/__init__.py new file mode 100644 index 000000000000..3c73f59eabab --- /dev/null +++ b/tools/net/ynl/lib/__init__.py @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: BSD-3-Clause + +from .nlspec import SpecAttr, SpecAttrSet, SpecFamily, SpecOperation +from .ynl import YnlFamily + +__all__ = ["SpecAttr", "SpecAttrSet", "SpecFamily", "SpecOperation", + "YnlFamily"] diff --git a/tools/net/ynl/lib/nlspec.py b/tools/net/ynl/lib/nlspec.py new file mode 100644 index 000000000000..e204679ad8b7 --- /dev/null +++ b/tools/net/ynl/lib/nlspec.py @@ -0,0 +1,310 @@ +# SPDX-License-Identifier: BSD-3-Clause + +import collections +import importlib +import os +import traceback +import yaml + + +# To be loaded dynamically as needed +jsonschema = None + + +class SpecElement: + """Netlink spec element. + + Abstract element of the Netlink spec. Implements the dictionary interface + for access to the raw spec. Supports iterative resolution of dependencies + across elements and class inheritance levels. The elements of the spec + may refer to each other, and although loops should be very rare, having + to maintain correct ordering of instantiation is painful, so the resolve() + method should be used to perform parts of init which require access to + other parts of the spec. + + Attributes: + yaml raw spec as loaded from the spec file + family back reference to the full family + + name name of the entity as listed in the spec (optional) + ident_name name which can be safely used as identifier in code (optional) + """ + def __init__(self, family, yaml): + self.yaml = yaml + self.family = family + + if 'name' in self.yaml: + self.name = self.yaml['name'] + self.ident_name = self.name.replace('-', '_') + + self._super_resolved = False + family.add_unresolved(self) + + def __getitem__(self, key): + return self.yaml[key] + + def __contains__(self, key): + return key in self.yaml + + def get(self, key, default=None): + return self.yaml.get(key, default) + + def resolve_up(self, up): + if not self._super_resolved: + up.resolve() + self._super_resolved = True + + def resolve(self): + pass + + +class SpecAttr(SpecElement): + """ Single Netlink atttribute type + + Represents a single attribute type within an attr space. + + Attributes: + value numerical ID when serialized + attr_set Attribute Set containing this attr + """ + def __init__(self, family, attr_set, yaml, value): + super().__init__(family, yaml) + + self.value = value + self.attr_set = attr_set + self.is_multi = yaml.get('multi-attr', False) + + +class SpecAttrSet(SpecElement): + """ Netlink Attribute Set class. + + Represents a ID space of attributes within Netlink. + + Note that unlike other elements, which expose contents of the raw spec + via the dictionary interface Attribute Set exposes attributes by name. + + Attributes: + attrs ordered dict of all attributes (indexed by name) + attrs_by_val ordered dict of all attributes (indexed by value) + subset_of parent set if this is a subset, otherwise None + """ + def __init__(self, family, yaml): + super().__init__(family, yaml) + + self.subset_of = self.yaml.get('subset-of', None) + + self.attrs = collections.OrderedDict() + self.attrs_by_val = collections.OrderedDict() + + val = 0 + for elem in self.yaml['attributes']: + if 'value' in elem: + val = elem['value'] + + attr = self.new_attr(elem, val) + self.attrs[attr.name] = attr + self.attrs_by_val[attr.value] = attr + val += 1 + + def new_attr(self, elem, value): + return SpecAttr(self.family, self, elem, value) + + def __getitem__(self, key): + return self.attrs[key] + + def __contains__(self, key): + return key in self.attrs + + def __iter__(self): + yield from self.attrs + + def items(self): + return self.attrs.items() + + +class SpecOperation(SpecElement): + """Netlink Operation + + Information about a single Netlink operation. + + Attributes: + value numerical ID when serialized, None if req/rsp values differ + + req_value numerical ID when serialized, user -> kernel + rsp_value numerical ID when serialized, user <- kernel + is_call bool, whether the operation is a call + is_async bool, whether the operation is a notification + is_resv bool, whether the operation does not exist (it's just a reserved ID) + attr_set attribute set name + + yaml raw spec as loaded from the spec file + """ + def __init__(self, family, yaml, req_value, rsp_value): + super().__init__(family, yaml) + + self.value = req_value if req_value == rsp_value else None + self.req_value = req_value + self.rsp_value = rsp_value + + self.is_call = 'do' in yaml or 'dump' in yaml + self.is_async = 'notify' in yaml or 'event' in yaml + self.is_resv = not self.is_async and not self.is_call + + # Added by resolve: + self.attr_set = None + delattr(self, "attr_set") + + def resolve(self): + self.resolve_up(super()) + + if 'attribute-set' in self.yaml: + attr_set_name = self.yaml['attribute-set'] + elif 'notify' in self.yaml: + msg = self.family.msgs[self.yaml['notify']] + attr_set_name = msg['attribute-set'] + elif self.is_resv: + attr_set_name = '' + else: + raise Exception(f"Can't resolve attribute set for op '{self.name}'") + if attr_set_name: + self.attr_set = self.family.attr_sets[attr_set_name] + + +class SpecFamily(SpecElement): + """ Netlink Family Spec class. + + Netlink family information loaded from a spec (e.g. in YAML). + Takes care of unfolding implicit information which can be skipped + in the spec itself for brevity. + + The class can be used like a dictionary to access the raw spec + elements but that's usually a bad idea. + + Attributes: + proto protocol type (e.g. genetlink) + + attr_sets dict of attribute sets + msgs dict of all messages (index by name) + msgs_by_value dict of all messages (indexed by name) + ops dict of all valid requests / responses + """ + def __init__(self, spec_path, schema_path=None): + with open(spec_path, "r") as stream: + spec = yaml.safe_load(stream) + + self._resolution_list = [] + + super().__init__(self, spec) + + self.proto = self.yaml.get('protocol', 'genetlink') + + if schema_path is None: + schema_path = os.path.dirname(os.path.dirname(spec_path)) + f'/{self.proto}.yaml' + if schema_path: + global jsonschema + + with open(schema_path, "r") as stream: + schema = yaml.safe_load(stream) + + if jsonschema is None: + jsonschema = importlib.import_module("jsonschema") + + jsonschema.validate(self.yaml, schema) + + self.attr_sets = collections.OrderedDict() + self.msgs = collections.OrderedDict() + self.req_by_value = collections.OrderedDict() + self.rsp_by_value = collections.OrderedDict() + self.ops = collections.OrderedDict() + + last_exception = None + while len(self._resolution_list) > 0: + resolved = [] + unresolved = self._resolution_list + self._resolution_list = [] + + for elem in unresolved: + try: + elem.resolve() + except (KeyError, AttributeError) as e: + self._resolution_list.append(elem) + last_exception = e + continue + + resolved.append(elem) + + if len(resolved) == 0: + traceback.print_exception(last_exception) + raise Exception("Could not resolve any spec element, infinite loop?") + + def new_attr_set(self, elem): + return SpecAttrSet(self, elem) + + def new_operation(self, elem, req_val, rsp_val): + return SpecOperation(self, elem, req_val, rsp_val) + + def add_unresolved(self, elem): + self._resolution_list.append(elem) + + def _dictify_ops_unified(self): + val = 0 + for elem in self.yaml['operations']['list']: + if 'value' in elem: + val = elem['value'] + + op = self.new_operation(elem, val, val) + val += 1 + + self.msgs[op.name] = op + + def _dictify_ops_directional(self): + req_val = rsp_val = 0 + for elem in self.yaml['operations']['list']: + if 'notify' in elem: + if 'value' in elem: + rsp_val = elem['value'] + req_val_next = req_val + rsp_val_next = rsp_val + 1 + req_val = None + elif 'do' in elem or 'dump' in elem: + mode = elem['do'] if 'do' in elem else elem['dump'] + + v = mode.get('request', {}).get('value', None) + if v: + req_val = v + v = mode.get('reply', {}).get('value', None) + if v: + rsp_val = v + + rsp_inc = 1 if 'reply' in mode else 0 + req_val_next = req_val + 1 + rsp_val_next = rsp_val + rsp_inc + else: + raise Exception("Can't parse directional ops") + + op = self.new_operation(elem, req_val, rsp_val) + req_val = req_val_next + rsp_val = rsp_val_next + + self.msgs[op.name] = op + + def resolve(self): + self.resolve_up(super()) + + for elem in self.yaml['attribute-sets']: + attr_set = self.new_attr_set(elem) + self.attr_sets[elem['name']] = attr_set + + msg_id_model = self.yaml['operations'].get('enum-model', 'unified') + if msg_id_model == 'unified': + self._dictify_ops_unified() + elif msg_id_model == 'directional': + self._dictify_ops_directional() + + for op in self.msgs.values(): + if op.req_value is not None: + self.req_by_value[op.req_value] = op + if op.rsp_value is not None: + self.rsp_by_value[op.rsp_value] = op + if not op.is_async and 'attribute-set' in op: + self.ops[op.name] = op diff --git a/tools/net/ynl/samples/ynl.py b/tools/net/ynl/lib/ynl.py index b71523d71d46..1c7411ee04dc 100644 --- a/tools/net/ynl/samples/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -1,13 +1,14 @@ # SPDX-License-Identifier: BSD-3-Clause import functools -import jsonschema import os import random import socket import struct import yaml +from .nlspec import SpecFamily + # # Generic Netlink code which should really be in some library, but I can't quickly find one. # @@ -74,6 +75,9 @@ class NlAttr: self.full_len = (self.payload_len + 3) & ~3 self.raw = raw[offset + 4:offset + self.payload_len] + def as_u8(self): + return struct.unpack("B", self.raw)[0] + def as_u16(self): return struct.unpack("H", self.raw)[0] @@ -158,8 +162,8 @@ class NlMsg: # We don't have the ability to parse nests yet, so only do global if 'miss-type' in self.extack and 'miss-nest' not in self.extack: miss_type = self.extack['miss-type'] - if len(attr_space.attr_list) > miss_type: - spec = attr_space.attr_list[miss_type] + if miss_type in attr_space.attrs_by_val: + spec = attr_space.attrs_by_val[miss_type] desc = spec['name'] if 'doc' in spec: desc += f" ({spec['doc']})" @@ -289,100 +293,31 @@ class GenlFamily: # -class YnlAttrSpace: - def __init__(self, family, yaml): - self.yaml = yaml - - self.attrs = dict() - self.name = self.yaml['name'] - self.subspace_of = self.yaml['subset-of'] if 'subspace-of' in self.yaml else None - - val = 0 - max_val = 0 - for elem in self.yaml['attributes']: - if 'value' in elem: - val = elem['value'] - else: - elem['value'] = val - if val > max_val: - max_val = val - val += 1 - - self.attrs[elem['name']] = elem - - self.attr_list = [None] * (max_val + 1) - for elem in self.yaml['attributes']: - self.attr_list[elem['value']] = elem - - def __getitem__(self, key): - return self.attrs[key] - - def __contains__(self, key): - return key in self.yaml - - def __iter__(self): - yield from self.attrs - - def items(self): - return self.attrs.items() - - -class YnlFamily: +class YnlFamily(SpecFamily): def __init__(self, def_path, schema=None): - self.include_raw = False + super().__init__(def_path, schema) - with open(def_path, "r") as stream: - self.yaml = yaml.safe_load(stream) - - if schema: - with open(schema, "r") as stream: - schema = yaml.safe_load(stream) - - jsonschema.validate(self.yaml, schema) + self.include_raw = False self.sock = socket.socket(socket.AF_NETLINK, socket.SOCK_RAW, Netlink.NETLINK_GENERIC) self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_CAP_ACK, 1) self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_EXT_ACK, 1) - self._ops = dict() - self._spaces = dict() self._types = dict() - for elem in self.yaml['attribute-sets']: - self._spaces[elem['name']] = YnlAttrSpace(self, elem) - - for elem in self.yaml['definitions']: + for elem in self.yaml.get('definitions', []): self._types[elem['name']] = elem - async_separation = 'async-prefix' in self.yaml['operations'] self.async_msg_ids = set() self.async_msg_queue = [] - val = 0 - max_val = 0 - for elem in self.yaml['operations']['list']: - if not (async_separation and ('notify' in elem or 'event' in elem)): - if 'value' in elem: - val = elem['value'] - else: - elem['value'] = val - val += 1 - max_val = max(val, max_val) - - if 'notify' in elem or 'event' in elem: - self.async_msg_ids.add(elem['value']) - - self._ops[elem['name']] = elem - - op_name = elem['name'].replace('-', '_') - bound_f = functools.partial(self._op, elem['name']) - setattr(self, op_name, bound_f) + for msg in self.msgs.values(): + if msg.is_async: + self.async_msg_ids.add(msg.rsp_value) - self._op_array = [None] * max_val - for _, op in self._ops.items(): - self._op_array[op['value']] = op - if 'notify' in op: - op['attribute-set'] = self._ops[op['notify']]['attribute-set'] + for op_name, op in self.ops.items(): + bound_f = functools.partial(self._op, op_name) + setattr(self, op.ident_name, bound_f) self.family = GenlFamily(self.yaml['name']) @@ -395,13 +330,15 @@ class YnlFamily: self.family.genl_family['mcast'][mcast_name]) def _add_attr(self, space, name, value): - attr = self._spaces[space][name] - nl_type = attr['value'] + attr = self.attr_sets[space][name] + nl_type = attr.value if attr["type"] == 'nest': nl_type |= Netlink.NLA_F_NESTED attr_payload = b'' for subname, subvalue in value.items(): attr_payload += self._add_attr(attr['nested-attributes'], subname, subvalue) + elif attr["type"] == 'flag': + attr_payload = b'' elif attr["type"] == 'u32': attr_payload = struct.pack("I", int(value)) elif attr["type"] == 'string': @@ -430,36 +367,81 @@ class YnlFamily: rsp[attr_spec['name']] = value def _decode(self, attrs, space): - attr_space = self._spaces[space] + attr_space = self.attr_sets[space] rsp = dict() for attr in attrs: - attr_spec = attr_space.attr_list[attr.type] + attr_spec = attr_space.attrs_by_val[attr.type] if attr_spec["type"] == 'nest': subdict = self._decode(NlAttrs(attr.raw), attr_spec['nested-attributes']) - rsp[attr_spec['name']] = subdict + decoded = subdict + elif attr_spec['type'] == 'u8': + decoded = attr.as_u8() elif attr_spec['type'] == 'u32': - rsp[attr_spec['name']] = attr.as_u32() + decoded = attr.as_u32() elif attr_spec['type'] == 'u64': - rsp[attr_spec['name']] = attr.as_u64() + decoded = attr.as_u64() elif attr_spec["type"] == 'string': - rsp[attr_spec['name']] = attr.as_strz() + decoded = attr.as_strz() elif attr_spec["type"] == 'binary': - rsp[attr_spec['name']] = attr.as_bin() + decoded = attr.as_bin() + elif attr_spec["type"] == 'flag': + decoded = True else: raise Exception(f'Unknown {attr.type} {attr_spec["name"]} {attr_spec["type"]}') + if not attr_spec.is_multi: + rsp[attr_spec['name']] = decoded + elif attr_spec.name in rsp: + rsp[attr_spec.name].append(decoded) + else: + rsp[attr_spec.name] = [decoded] + if 'enum' in attr_spec: self._decode_enum(rsp, attr_spec) return rsp + def _decode_extack_path(self, attrs, attr_set, offset, target): + for attr in attrs: + attr_spec = attr_set.attrs_by_val[attr.type] + if offset > target: + break + if offset == target: + return '.' + attr_spec.name + + if offset + attr.full_len <= target: + offset += attr.full_len + continue + if attr_spec['type'] != 'nest': + raise Exception(f"Can't dive into {attr.type} ({attr_spec['name']}) for extack") + offset += 4 + subpath = self._decode_extack_path(NlAttrs(attr.raw), + self.attr_sets[attr_spec['nested-attributes']], + offset, target) + if subpath is None: + return None + return '.' + attr_spec.name + subpath + + return None + + def _decode_extack(self, request, attr_space, extack): + if 'bad-attr-offs' not in extack: + return + + genl_req = GenlMsg(NlMsg(request, 0, attr_space=attr_space)) + path = self._decode_extack_path(genl_req.raw_attrs, attr_space, + 20, extack['bad-attr-offs']) + if path: + del extack['bad-attr-offs'] + extack['bad-attr'] = path + def handle_ntf(self, nl_msg, genl_msg): msg = dict() if self.include_raw: msg['nlmsg'] = nl_msg msg['genlmsg'] = genl_msg - op = self._op_array[genl_msg.genl_cmd] + op = self.rsp_by_value[genl_msg.genl_cmd] msg['name'] = op['name'] - msg['msg'] = self._decode(genl_msg.raw_attrs, op['attribute-set']) + msg['msg'] = self._decode(genl_msg.raw_attrs, op.attr_set.name) self.async_msg_queue.append(msg) def check_ntf(self): @@ -487,16 +469,16 @@ class YnlFamily: self.handle_ntf(nl_msg, gm) def _op(self, method, vals, dump=False): - op = self._ops[method] + op = self.ops[method] nl_flags = Netlink.NLM_F_REQUEST | Netlink.NLM_F_ACK if dump: nl_flags |= Netlink.NLM_F_DUMP req_seq = random.randint(1024, 65535) - msg = _genl_msg(self.family.family_id, nl_flags, op['value'], 1, req_seq) + msg = _genl_msg(self.family.family_id, nl_flags, op.req_value, 1, req_seq) for name, value in vals.items(): - msg += self._add_attr(op['attribute-set'], name, value) + msg += self._add_attr(op.attr_set.name, name, value) msg = _genl_msg_finalize(msg) self.sock.send(msg, 0) @@ -505,19 +487,25 @@ class YnlFamily: rsp = [] while not done: reply = self.sock.recv(128 * 1024) - nms = NlMsgs(reply, attr_space=self._spaces[op['attribute-set']]) + nms = NlMsgs(reply, attr_space=op.attr_set) for nl_msg in nms: + if nl_msg.extack: + self._decode_extack(msg, op.attr_set, nl_msg.extack) + if nl_msg.error: print("Netlink error:", os.strerror(-nl_msg.error)) print(nl_msg) return if nl_msg.done: + if nl_msg.extack: + print("Netlink warning:") + print(nl_msg) done = True break gm = GenlMsg(nl_msg) # Check if this is a reply to our request - if nl_msg.nl_seq != req_seq or gm.genl_cmd != op['value']: + if nl_msg.nl_seq != req_seq or gm.genl_cmd != op.rsp_value: if gm.genl_cmd in self.async_msg_ids: self.handle_ntf(nl_msg, gm) continue @@ -525,10 +513,16 @@ class YnlFamily: print('Unexpected message: ' + repr(gm)) continue - rsp.append(self._decode(gm.raw_attrs, op['attribute-set'])) + rsp.append(self._decode(gm.raw_attrs, op.attr_set.name)) if not rsp: return None if not dump and len(rsp) == 1: return rsp[0] return rsp + + def do(self, method, vals): + return self._op(method, vals) + + def dump(self, method, vals): + return self._op(method, vals, dump=True) diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index 1aa872e582ab..3942f24b9163 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -1,11 +1,12 @@ -#!/usr/bin/env python +#!/usr/bin/env python3 import argparse import collections -import jsonschema import os import yaml +from lib import SpecFamily, SpecAttrSet, SpecAttr, SpecOperation + def c_upper(name): return name.upper().replace('-', '_') @@ -28,12 +29,12 @@ class BaseNlLib: "ynl_cb_array, NLMSG_MIN_TYPE)" -class Type: - def __init__(self, family, attr_set, attr): - self.family = family +class Type(SpecAttr): + def __init__(self, family, attr_set, attr, value): + super().__init__(family, attr_set, attr, value) + self.attr = attr - self.value = attr['value'] - self.name = c_lower(attr['name']) + self.attr_set = attr_set self.type = attr['type'] self.checks = attr.get('checks', {}) @@ -46,17 +47,17 @@ class Type: else: self.nested_render_name = f"{family.name}_{c_lower(self.nested_attrs)}" - self.enum_name = f"{attr_set.name_prefix}{self.name}" - self.enum_name = c_upper(self.enum_name) self.c_name = c_lower(self.name) if self.c_name in _C_KW: self.c_name += '_' - def __getitem__(self, key): - return self.attr[key] + # Added by resolve(): + self.enum_name = None + delattr(self, "enum_name") - def __contains__(self, key): - return key in self.attr + def resolve(self): + self.enum_name = f"{self.attr_set.name_prefix}{self.name}" + self.enum_name = c_upper(self.enum_name) def is_multi_val(self): return None @@ -214,24 +215,34 @@ class TypePad(Type): class TypeScalar(Type): - def __init__(self, family, attr_set, attr): - super().__init__(family, attr_set, attr) + def __init__(self, family, attr_set, attr, value): + super().__init__(family, attr_set, attr, value) + + self.byte_order_comment = '' + if 'byte-order' in attr: + self.byte_order_comment = f" /* {attr['byte-order']} */" + + # Added by resolve(): + self.is_bitfield = None + delattr(self, "is_bitfield") + self.type_name = None + delattr(self, "type_name") + + def resolve(self): + self.resolve_up(super()) - self.is_bitfield = False - if 'enum' in self.attr: - self.is_bitfield = family.consts[self.attr['enum']]['type'] == 'flags' if 'enum-as-flags' in self.attr and self.attr['enum-as-flags']: self.is_bitfield = True + elif 'enum' in self.attr: + self.is_bitfield = self.family.consts[self.attr['enum']]['type'] == 'flags' + else: + self.is_bitfield = False if 'enum' in self.attr and not self.is_bitfield: - self.type_name = f"enum {family.name}_{c_lower(self.attr['enum'])}" + self.type_name = f"enum {self.family.name}_{c_lower(self.attr['enum'])}" else: self.type_name = '__' + self.type - self.byte_order_comment = '' - if 'byte-order' in attr: - self.byte_order_comment = f" /* {attr['byte-order']} */" - def _mnl_type(self): t = self.type # mnl does not have a helper for signed types @@ -648,14 +659,11 @@ class EnumSet: return mask -class AttrSet: +class AttrSet(SpecAttrSet): def __init__(self, family, yaml): - self.yaml = yaml + super().__init__(family, yaml) - self.attrs = dict() - self.name = self.yaml['name'] - if 'subset-of' not in yaml: - self.subset_of = None + if self.subset_of is None: if 'name-prefix' in yaml: pfx = yaml['name-prefix'] elif self.name == family.name: @@ -665,83 +673,68 @@ class AttrSet: self.name_prefix = c_upper(pfx) self.max_name = c_upper(self.yaml.get('attr-max-name', f"{self.name_prefix}max")) else: - self.subset_of = self.yaml['subset-of'] self.name_prefix = family.attr_sets[self.subset_of].name_prefix self.max_name = family.attr_sets[self.subset_of].max_name + # Added by resolve: + self.c_name = None + delattr(self, "c_name") + + def resolve(self): self.c_name = c_lower(self.name) if self.c_name in _C_KW: self.c_name += '_' - if self.c_name == family.c_name: + if self.c_name == self.family.c_name: self.c_name = '' - val = 0 - for elem in self.yaml['attributes']: - if 'value' in elem: - val = elem['value'] - else: - elem['value'] = val - val += 1 - - if 'multi-attr' in elem and elem['multi-attr']: - attr = TypeMultiAttr(family, self, elem) - elif elem['type'] in scalars: - attr = TypeScalar(family, self, elem) - elif elem['type'] == 'unused': - attr = TypeUnused(family, self, elem) - elif elem['type'] == 'pad': - attr = TypePad(family, self, elem) - elif elem['type'] == 'flag': - attr = TypeFlag(family, self, elem) - elif elem['type'] == 'string': - attr = TypeString(family, self, elem) - elif elem['type'] == 'binary': - attr = TypeBinary(family, self, elem) - elif elem['type'] == 'nest': - attr = TypeNest(family, self, elem) - elif elem['type'] == 'array-nest': - attr = TypeArrayNest(family, self, elem) - elif elem['type'] == 'nest-type-value': - attr = TypeNestTypeValue(family, self, elem) - else: - raise Exception(f"No typed class for type {elem['type']}") - - self.attrs[elem['name']] = attr - - def __getitem__(self, key): - return self.attrs[key] - - def __contains__(self, key): - return key in self.yaml - - def __iter__(self): - yield from self.attrs + def new_attr(self, elem, value): + if 'multi-attr' in elem and elem['multi-attr']: + return TypeMultiAttr(self.family, self, elem, value) + elif elem['type'] in scalars: + return TypeScalar(self.family, self, elem, value) + elif elem['type'] == 'unused': + return TypeUnused(self.family, self, elem, value) + elif elem['type'] == 'pad': + return TypePad(self.family, self, elem, value) + elif elem['type'] == 'flag': + return TypeFlag(self.family, self, elem, value) + elif elem['type'] == 'string': + return TypeString(self.family, self, elem, value) + elif elem['type'] == 'binary': + return TypeBinary(self.family, self, elem, value) + elif elem['type'] == 'nest': + return TypeNest(self.family, self, elem, value) + elif elem['type'] == 'array-nest': + return TypeArrayNest(self.family, self, elem, value) + elif elem['type'] == 'nest-type-value': + return TypeNestTypeValue(self.family, self, elem, value) + else: + raise Exception(f"No typed class for type {elem['type']}") - def items(self): - return self.attrs.items() +class Operation(SpecOperation): + def __init__(self, family, yaml, req_value, rsp_value): + super().__init__(family, yaml, req_value, rsp_value) -class Operation: - def __init__(self, family, yaml, value): - self.yaml = yaml - self.value = value + if req_value != rsp_value: + raise Exception("Directional messages not supported by codegen") - self.name = self.yaml['name'] self.render_name = family.name + '_' + c_lower(self.name) - self.is_async = 'notify' in yaml or 'event' in yaml - if not self.is_async: - self.enum_name = family.op_prefix + c_upper(self.name) - else: - self.enum_name = family.async_op_prefix + c_upper(self.name) self.dual_policy = ('do' in yaml and 'request' in yaml['do']) and \ ('dump' in yaml and 'request' in yaml['dump']) - def __getitem__(self, key): - return self.yaml[key] + # Added by resolve: + self.enum_name = None + delattr(self, "enum_name") - def __contains__(self, key): - return key in self.yaml + def resolve(self): + self.resolve_up(super()) + + if not self.is_async: + self.enum_name = self.family.op_prefix + c_upper(self.name) + else: + self.enum_name = self.family.async_op_prefix + c_upper(self.name) def add_notification(self, op): if 'notify' not in self.yaml: @@ -751,21 +744,23 @@ class Operation: self.yaml['notify']['cmds'].append(op) -class Family: +class Family(SpecFamily): def __init__(self, file_name): - with open(file_name, "r") as stream: - self.yaml = yaml.safe_load(stream) - - self.proto = self.yaml.get('protocol', 'genetlink') - - with open(os.path.dirname(os.path.dirname(file_name)) + - f'/{self.proto}.yaml', "r") as stream: - schema = yaml.safe_load(stream) - - jsonschema.validate(self.yaml, schema) - - if self.yaml.get('protocol', 'genetlink') not in {'genetlink', 'genetlink-c', 'genetlink-legacy'}: - raise Exception("Codegen only supported for genetlink") + # Added by resolve: + self.c_name = None + delattr(self, "c_name") + self.op_prefix = None + delattr(self, "op_prefix") + self.async_op_prefix = None + delattr(self, "async_op_prefix") + self.mcgrps = None + delattr(self, "mcgrps") + self.consts = None + delattr(self, "consts") + self.hooks = None + delattr(self, "hooks") + + super().__init__(file_name) self.fam_key = c_upper(self.yaml.get('c-family-name', self.yaml["name"] + '_FAMILY_NAME')) self.ver_key = c_upper(self.yaml.get('c-version-name', self.yaml["name"] + '_FAMILY_VERSION')) @@ -773,12 +768,18 @@ class Family: if 'definitions' not in self.yaml: self.yaml['definitions'] = [] - self.name = self.yaml['name'] - self.c_name = c_lower(self.name) if 'uapi-header' in self.yaml: self.uapi_header = self.yaml['uapi-header'] else: self.uapi_header = f"linux/{self.name}.h" + + def resolve(self): + self.resolve_up(super()) + + if self.yaml.get('protocol', 'genetlink') not in {'genetlink', 'genetlink-c', 'genetlink-legacy'}: + raise Exception("Codegen only supported for genetlink") + + self.c_name = c_lower(self.name) if 'name-prefix' in self.yaml['operations']: self.op_prefix = c_upper(self.yaml['operations']['name-prefix']) else: @@ -791,12 +792,6 @@ class Family: self.mcgrps = self.yaml.get('mcast-groups', {'list': []}) self.consts = dict() - # list of all operations - self.msg_list = [] - # dict of operations which have their own message type (have attributes) - self.ops = collections.OrderedDict() - self.attr_sets = dict() - self.attr_sets_list = [] self.hooks = dict() for when in ['pre', 'post']: @@ -824,11 +819,11 @@ class Family: if self.kernel_policy == 'global': self._load_global_policy() - def __getitem__(self, key): - return self.yaml[key] + def new_attr_set(self, elem): + return AttrSet(self, elem) - def get(self, key, default=None): - return self.yaml.get(key, default) + def new_operation(self, elem, req_value, rsp_value): + return Operation(self, elem, req_value, rsp_value) # Fake a 'do' equivalent of all events, so that we can render their response parsing def _mock_up_events(self): @@ -847,27 +842,10 @@ class Family: else: self.consts[elem['name']] = elem - for elem in self.yaml['attribute-sets']: - attr_set = AttrSet(self, elem) - self.attr_sets[elem['name']] = attr_set - self.attr_sets_list.append((elem['name'], attr_set), ) - ntf = [] - val = 0 - for elem in self.yaml['operations']['list']: - if 'value' in elem: - val = elem['value'] - - op = Operation(self, elem, val) - val += 1 - - self.msg_list.append(op) - if 'notify' in elem: - ntf.append(op) - continue - if 'attribute-set' not in elem: - continue - self.ops[elem['name']] = op + for msg in self.msgs.values(): + if 'notify' in msg: + ntf.append(msg) for n in ntf: self.ops[n['notify']].add_notification(n) @@ -933,7 +911,7 @@ class Family: if attr_set_name != op['attribute-set']: raise Exception('For a global policy all ops must use the same set') - for op_mode in {'do', 'dump'}: + for op_mode in ['do', 'dump']: if op_mode in op: global_set.update(op[op_mode].get('request', [])) @@ -2033,7 +2011,7 @@ def render_uapi(family, cw): max_by_define = family.get('max-by-define', False) - for _, attr_set in family.attr_sets_list: + for _, attr_set in family.attr_sets.items(): if attr_set.subset_of: continue @@ -2044,9 +2022,9 @@ def render_uapi(family, cw): uapi_enum_start(family, cw, attr_set.yaml, 'enum-name') for _, attr in attr_set.items(): suffix = ',' - if attr['value'] != val: - suffix = f" = {attr['value']}," - val = attr['value'] + if attr.value != val: + suffix = f" = {attr.value}," + val = attr.value val += 1 cw.p(attr.enum_name + suffix) cw.nl() @@ -2066,7 +2044,7 @@ def render_uapi(family, cw): max_value = f"({cnt_name} - 1)" uapi_enum_start(family, cw, family['operations'], 'enum-name') - for op in family.msg_list: + for op in family.msgs.values(): if separate_ntf and ('notify' in op or 'event' in op): continue @@ -2085,7 +2063,7 @@ def render_uapi(family, cw): if separate_ntf: uapi_enum_start(family, cw, family['operations'], enum_name='async-enum') - for op in family.msg_list: + for op in family.msgs.values(): if separate_ntf and not ('notify' in op or 'event' in op): continue @@ -2244,7 +2222,7 @@ def main(): for op_name, op in parsed.ops.items(): if parsed.kernel_policy in {'per-op', 'split'}: - for op_mode in {'do', 'dump'}: + for op_mode in ['do', 'dump']: if op_mode in op and 'request' in op[op_mode]: cw.p(f"/* {op.enum_name} - {op_mode} */") ri = RenderInfo(cw, parsed, args.mode, op, op_name, op_mode) diff --git a/tools/testing/selftests/amd-pstate/Makefile b/tools/testing/selftests/amd-pstate/Makefile index 5f195ee756d6..5fd1424db37d 100644 --- a/tools/testing/selftests/amd-pstate/Makefile +++ b/tools/testing/selftests/amd-pstate/Makefile @@ -7,11 +7,6 @@ all: uname_M := $(shell uname -m 2>/dev/null || echo not) ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) -ifeq (x86,$(ARCH)) -TEST_GEN_FILES += ../../../power/x86/amd_pstate_tracer/amd_pstate_trace.py -TEST_GEN_FILES += ../../../power/x86/intel_pstate_tracer/intel_pstate_tracer.py -endif - TEST_PROGS := run.sh TEST_FILES := basic.sh tbench.sh gitsource.sh diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 2cf0c7a3fe23..567e07c19ecc 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -30,6 +30,8 @@ #define MAX_STRERR_LEN 256 #define MAX_TEST_NAME 80 +#define __always_unused __attribute__((__unused__)) + #define _FAIL(errnum, fmt...) \ ({ \ error_at_line(0, (errnum), __func__, __LINE__, fmt); \ @@ -321,7 +323,8 @@ static int socket_loopback(int family, int sotype) return socket_loopback_reuseport(family, sotype, -1); } -static void test_insert_invalid(int family, int sotype, int mapfd) +static void test_insert_invalid(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { u32 key = 0; u64 value; @@ -338,7 +341,8 @@ static void test_insert_invalid(int family, int sotype, int mapfd) FAIL_ERRNO("map_update: expected EBADF"); } -static void test_insert_opened(int family, int sotype, int mapfd) +static void test_insert_opened(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { u32 key = 0; u64 value; @@ -359,7 +363,8 @@ static void test_insert_opened(int family, int sotype, int mapfd) xclose(s); } -static void test_insert_bound(int family, int sotype, int mapfd) +static void test_insert_bound(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { struct sockaddr_storage addr; socklen_t len; @@ -386,7 +391,8 @@ close: xclose(s); } -static void test_insert(int family, int sotype, int mapfd) +static void test_insert(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { u64 value; u32 key; @@ -402,7 +408,8 @@ static void test_insert(int family, int sotype, int mapfd) xclose(s); } -static void test_delete_after_insert(int family, int sotype, int mapfd) +static void test_delete_after_insert(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { u64 value; u32 key; @@ -419,7 +426,8 @@ static void test_delete_after_insert(int family, int sotype, int mapfd) xclose(s); } -static void test_delete_after_close(int family, int sotype, int mapfd) +static void test_delete_after_close(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { int err, s; u64 value; @@ -442,7 +450,8 @@ static void test_delete_after_close(int family, int sotype, int mapfd) FAIL_ERRNO("map_delete: expected EINVAL/EINVAL"); } -static void test_lookup_after_insert(int family, int sotype, int mapfd) +static void test_lookup_after_insert(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { u64 cookie, value; socklen_t len; @@ -470,7 +479,8 @@ static void test_lookup_after_insert(int family, int sotype, int mapfd) xclose(s); } -static void test_lookup_after_delete(int family, int sotype, int mapfd) +static void test_lookup_after_delete(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { int err, s; u64 value; @@ -493,7 +503,8 @@ static void test_lookup_after_delete(int family, int sotype, int mapfd) xclose(s); } -static void test_lookup_32_bit_value(int family, int sotype, int mapfd) +static void test_lookup_32_bit_value(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { u32 key, value32; int err, s; @@ -523,7 +534,8 @@ close: xclose(s); } -static void test_update_existing(int family, int sotype, int mapfd) +static void test_update_existing(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { int s1, s2; u64 value; @@ -551,7 +563,7 @@ close_s1: /* Exercise the code path where we destroy child sockets that never * got accept()'ed, aka orphans, when parent socket gets closed. */ -static void test_destroy_orphan_child(int family, int sotype, int mapfd) +static void do_destroy_orphan_child(int family, int sotype, int mapfd) { struct sockaddr_storage addr; socklen_t len; @@ -582,10 +594,38 @@ close_srv: xclose(s); } +static void test_destroy_orphan_child(struct test_sockmap_listen *skel, + int family, int sotype, int mapfd) +{ + int msg_verdict = bpf_program__fd(skel->progs.prog_msg_verdict); + int skb_verdict = bpf_program__fd(skel->progs.prog_skb_verdict); + const struct test { + int progfd; + enum bpf_attach_type atype; + } tests[] = { + { -1, -1 }, + { msg_verdict, BPF_SK_MSG_VERDICT }, + { skb_verdict, BPF_SK_SKB_VERDICT }, + }; + const struct test *t; + + for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { + if (t->progfd != -1 && + xbpf_prog_attach(t->progfd, mapfd, t->atype, 0) != 0) + return; + + do_destroy_orphan_child(family, sotype, mapfd); + + if (t->progfd != -1) + xbpf_prog_detach2(t->progfd, mapfd, t->atype); + } +} + /* Perform a passive open after removing listening socket from SOCKMAP * to ensure that callbacks get restored properly. */ -static void test_clone_after_delete(int family, int sotype, int mapfd) +static void test_clone_after_delete(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { struct sockaddr_storage addr; socklen_t len; @@ -621,7 +661,8 @@ close_srv: * SOCKMAP, but got accept()'ed only after the parent has been removed * from SOCKMAP, gets cloned without parent psock state or callbacks. */ -static void test_accept_after_delete(int family, int sotype, int mapfd) +static void test_accept_after_delete(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { struct sockaddr_storage addr; const u32 zero = 0; @@ -675,7 +716,8 @@ close_srv: /* Check that child socket that got created and accepted while parent * was in a SOCKMAP is cloned without parent psock state or callbacks. */ -static void test_accept_before_delete(int family, int sotype, int mapfd) +static void test_accept_before_delete(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { struct sockaddr_storage addr; const u32 zero = 0, one = 1; @@ -784,7 +826,8 @@ done: return NULL; } -static void test_syn_recv_insert_delete(int family, int sotype, int mapfd) +static void test_syn_recv_insert_delete(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { struct connect_accept_ctx ctx = { 0 }; struct sockaddr_storage addr; @@ -847,7 +890,8 @@ static void *listen_thread(void *arg) return NULL; } -static void test_race_insert_listen(int family, int socktype, int mapfd) +static void test_race_insert_listen(struct test_sockmap_listen *skel __always_unused, + int family, int socktype, int mapfd) { struct connect_accept_ctx ctx = { 0 }; const u32 zero = 0; @@ -1473,7 +1517,8 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map, int family, int sotype) { const struct op_test { - void (*fn)(int family, int sotype, int mapfd); + void (*fn)(struct test_sockmap_listen *skel, + int family, int sotype, int mapfd); const char *name; int sotype; } tests[] = { @@ -1520,7 +1565,7 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map, if (!test__start_subtest(s)) continue; - t->fn(family, sotype, map_fd); + t->fn(skel, family, sotype, map_fd); test_ops_cleanup(map); } } diff --git a/tools/testing/selftests/bpf/verifier/search_pruning.c b/tools/testing/selftests/bpf/verifier/search_pruning.c index 68b14fdfebdb..d63fd8991b03 100644 --- a/tools/testing/selftests/bpf/verifier/search_pruning.c +++ b/tools/testing/selftests/bpf/verifier/search_pruning.c @@ -225,3 +225,39 @@ .result_unpriv = ACCEPT, .insn_processed = 15, }, +/* The test performs a conditional 64-bit write to a stack location + * fp[-8], this is followed by an unconditional 8-bit write to fp[-8], + * then data is read from fp[-8]. This sequence is unsafe. + * + * The test would be mistakenly marked as safe w/o dst register parent + * preservation in verifier.c:copy_register_state() function. + * + * Note the usage of BPF_F_TEST_STATE_FREQ to force creation of the + * checkpoint state after conditional 64-bit assignment. + */ +{ + "write tracking and register parent chain bug", + .insns = { + /* r6 = ktime_get_ns() */ + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + /* r0 = ktime_get_ns() */ + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + /* if r0 > r6 goto +1 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_6, 1), + /* *(u64 *)(r10 - 8) = 0xdeadbeef */ + BPF_ST_MEM(BPF_DW, BPF_REG_FP, -8, 0xdeadbeef), + /* r1 = 42 */ + BPF_MOV64_IMM(BPF_REG_1, 42), + /* *(u8 *)(r10 - 8) = r1 */ + BPF_STX_MEM(BPF_B, BPF_REG_FP, BPF_REG_1, -8), + /* r2 = *(u64 *)(r10 - 8) */ + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_FP, -8), + /* exit(0) */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .flags = BPF_F_TEST_STATE_FREQ, + .errstr = "invalid read from stack off -8+1 size 8", + .result = REJECT, +}, diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index 186e1c26867e..75c100de90ff 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -268,6 +268,7 @@ TEST_MATRIX=( # Taking away all CPUs from parent or itself if there are tasks # will make the partition invalid. " S+ C2-3:P1:S+ C3:P1 . . T C2-3 . . 0 A1:2-3,A2:2-3 A1:P1,A2:P-1" + " S+ C3:P1:S+ C3 . . T P1 . . 0 A1:3,A2:3 A1:P1,A2:P-1" " S+ $SETUP_A123_PARTITIONS . T:C2-3 . . . 0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1" " S+ $SETUP_A123_PARTITIONS . T:C2-3:C1-3 . . . 0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1" diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh index 71066bc4b886..5492fa5550d7 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh @@ -5,18 +5,18 @@ # prioritized according to the default priority specified at the port. # rx_octets_prio_* counters are used to verify the prioritization. # -# +-----------------------+ -# | H1 | -# | + $h1 | -# | | 192.0.2.1/28 | -# +----|------------------+ +# +----------------------------------+ +# | H1 | +# | + $h1 | +# | | 192.0.2.1/28 | +# +----|-----------------------------+ # | -# +----|------------------+ -# | SW | | -# | + $swp1 | -# | 192.0.2.2/28 | -# | APP=<prio>,1,0 | -# +-----------------------+ +# +----|-----------------------------+ +# | SW | | +# | + $swp1 | +# | 192.0.2.2/28 | +# | dcb app default-prio <prio> | +# +----------------------------------+ ALL_TESTS=" ping_ipv4 @@ -29,42 +29,6 @@ NUM_NETIFS=2 : ${HIT_TIMEOUT:=1000} # ms source $lib_dir/lib.sh -declare -a APP - -defprio_install() -{ - local dev=$1; shift - local prio=$1; shift - local app="app=$prio,1,0" - - lldptool -T -i $dev -V APP $app >/dev/null - lldpad_app_wait_set $dev - APP[$prio]=$app -} - -defprio_uninstall() -{ - local dev=$1; shift - local prio=$1; shift - local app=${APP[$prio]} - - lldptool -T -i $dev -V APP -d $app >/dev/null - lldpad_app_wait_del - unset APP[$prio] -} - -defprio_flush() -{ - local dev=$1; shift - local prio - - if ((${#APP[@]})); then - lldptool -T -i $dev -V APP -d ${APP[@]} >/dev/null - fi - lldpad_app_wait_del - APP=() -} - h1_create() { simple_if_init $h1 192.0.2.1/28 @@ -83,7 +47,7 @@ switch_create() switch_destroy() { - defprio_flush $swp1 + dcb app flush dev $swp1 default-prio ip addr del dev $swp1 192.0.2.2/28 ip link set dev $swp1 down } @@ -124,7 +88,7 @@ __test_defprio() RET=0 - defprio_install $swp1 $prio_install + dcb app add dev $swp1 default-prio $prio_install local t0=$(ethtool_stats_get $swp1 rx_frames_prio_$prio_observe) mausezahn -q $h1 -d 100m -c 10 -t arp reply @@ -134,7 +98,7 @@ __test_defprio() check_err $? "Default priority $prio_install/$prio_observe: Expected to capture 10 packets, got $((t1 - t0))." log_test "Default priority $prio_install/$prio_observe" - defprio_uninstall $swp1 $prio_install + dcb app del dev $swp1 default-prio $prio_install } test_defprio() @@ -145,7 +109,7 @@ test_defprio() __test_defprio $prio $prio done - defprio_install $swp1 3 + dcb app add dev $swp1 default-prio 3 __test_defprio 0 3 __test_defprio 1 3 __test_defprio 2 3 @@ -153,7 +117,7 @@ test_defprio() __test_defprio 5 5 __test_defprio 6 6 __test_defprio 7 7 - defprio_uninstall $swp1 3 + dcb app del dev $swp1 default-prio 3 } trap cleanup EXIT diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh index 28a570006d4d..87c41f5727c9 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh @@ -20,7 +20,7 @@ # | SW | | | # | +-|----------------------------------------------------------------|-+ | # | | + $swp1 BR $swp2 + | | -# | | APP=0,5,10 .. 7,5,17 APP=0,5,20 .. 7,5,27 | | +# | | dcb dscp-prio 10:0...17:7 dcb dscp-prio 20:0...27:7 | | # | +--------------------------------------------------------------------+ | # +---------------------------------------------------------------------------+ @@ -62,16 +62,6 @@ h2_destroy() simple_if_fini $h2 192.0.2.2/28 } -dscp_map() -{ - local base=$1; shift - local prio - - for prio in {0..7}; do - echo app=$prio,5,$((base + prio)) - done -} - switch_create() { ip link add name br1 type bridge vlan_filtering 1 @@ -81,17 +71,14 @@ switch_create() ip link set dev $swp2 master br1 ip link set dev $swp2 up - lldptool -T -i $swp1 -V APP $(dscp_map 10) >/dev/null - lldptool -T -i $swp2 -V APP $(dscp_map 20) >/dev/null - lldpad_app_wait_set $swp1 - lldpad_app_wait_set $swp2 + dcb app add dev $swp1 dscp-prio 10:0 11:1 12:2 13:3 14:4 15:5 16:6 17:7 + dcb app add dev $swp2 dscp-prio 20:0 21:1 22:2 23:3 24:4 25:5 26:6 27:7 } switch_destroy() { - lldptool -T -i $swp2 -V APP -d $(dscp_map 20) >/dev/null - lldptool -T -i $swp1 -V APP -d $(dscp_map 10) >/dev/null - lldpad_app_wait_del + dcb app del dev $swp2 dscp-prio 20:0 21:1 22:2 23:3 24:4 25:5 26:6 27:7 + dcb app del dev $swp1 dscp-prio 10:0 11:1 12:2 13:3 14:4 15:5 16:6 17:7 ip link set dev $swp2 down ip link set dev $swp2 nomaster diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh index 4cb2aa65278a..f6c23f84423e 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh @@ -94,16 +94,6 @@ h2_destroy() simple_if_fini $h2 192.0.2.18/28 } -dscp_map() -{ - local base=$1; shift - local prio - - for prio in {0..7}; do - echo app=$prio,5,$((base + prio)) - done -} - switch_create() { simple_if_init $swp1 192.0.2.2/28 @@ -112,17 +102,14 @@ switch_create() tc qdisc add dev $swp1 clsact tc qdisc add dev $swp2 clsact - lldptool -T -i $swp1 -V APP $(dscp_map 0) >/dev/null - lldptool -T -i $swp2 -V APP $(dscp_map 0) >/dev/null - lldpad_app_wait_set $swp1 - lldpad_app_wait_set $swp2 + dcb app add dev $swp1 dscp-prio 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 + dcb app add dev $swp2 dscp-prio 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 } switch_destroy() { - lldptool -T -i $swp2 -V APP -d $(dscp_map 0) >/dev/null - lldptool -T -i $swp1 -V APP -d $(dscp_map 0) >/dev/null - lldpad_app_wait_del + dcb app del dev $swp2 dscp-prio 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 + dcb app del dev $swp1 dscp-prio 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 tc qdisc del dev $swp2 clsact tc qdisc del dev $swp1 clsact @@ -265,13 +252,11 @@ test_dscp_leftover() { echo "Test that last removed DSCP rule is deconfigured correctly" - lldptool -T -i $swp2 -V APP -d $(dscp_map 0) >/dev/null - lldpad_app_wait_del + dcb app del dev $swp2 dscp-prio 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 __test_update 0 zero - lldptool -T -i $swp2 -V APP $(dscp_map 0) >/dev/null - lldpad_app_wait_set $swp2 + dcb app add dev $swp2 dscp-prio 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 } trap cleanup EXIT diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh index 9c79bbcce5a8..aff0a59f92d9 100755 --- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh +++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh @@ -246,7 +246,7 @@ test_vlan_ingress_modify() bridge vlan add dev $swp2 vid 300 tc filter add dev $swp1 ingress chain $(IS1 2) pref 3 \ - protocol 802.1Q flower skip_sw vlan_id 200 \ + protocol 802.1Q flower skip_sw vlan_id 200 src_mac $h1_mac \ action vlan modify id 300 \ action goto chain $(IS2 0 0) diff --git a/tools/testing/selftests/filesystems/fat/run_fat_tests.sh b/tools/testing/selftests/filesystems/fat/run_fat_tests.sh index 7f35dc3d15df..7f35dc3d15df 100644..100755 --- a/tools/testing/selftests/filesystems/fat/run_fat_tests.sh +++ b/tools/testing/selftests/filesystems/fat/run_fat_tests.sh diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c index beb944fa6fd4..54680dc5887f 100644 --- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c +++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c @@ -237,6 +237,11 @@ static void guest_check_s1ptw_wr_in_dirty_log(void) GUEST_SYNC(CMD_CHECK_S1PTW_WR_IN_DIRTY_LOG); } +static void guest_check_no_s1ptw_wr_in_dirty_log(void) +{ + GUEST_SYNC(CMD_CHECK_NO_S1PTW_WR_IN_DIRTY_LOG); +} + static void guest_exec(void) { int (*code)(void) = (int (*)(void))TEST_EXEC_GVA; @@ -304,7 +309,7 @@ static struct uffd_args { /* Returns true to continue the test, and false if it should be skipped. */ static int uffd_generic_handler(int uffd_mode, int uffd, struct uffd_msg *msg, - struct uffd_args *args, bool expect_write) + struct uffd_args *args) { uint64_t addr = msg->arg.pagefault.address; uint64_t flags = msg->arg.pagefault.flags; @@ -313,7 +318,6 @@ static int uffd_generic_handler(int uffd_mode, int uffd, struct uffd_msg *msg, TEST_ASSERT(uffd_mode == UFFDIO_REGISTER_MODE_MISSING, "The only expected UFFD mode is MISSING"); - ASSERT_EQ(!!(flags & UFFD_PAGEFAULT_FLAG_WRITE), expect_write); ASSERT_EQ(addr, (uint64_t)args->hva); pr_debug("uffd fault: addr=%p write=%d\n", @@ -337,19 +341,14 @@ static int uffd_generic_handler(int uffd_mode, int uffd, struct uffd_msg *msg, return 0; } -static int uffd_pt_write_handler(int mode, int uffd, struct uffd_msg *msg) -{ - return uffd_generic_handler(mode, uffd, msg, &pt_args, true); -} - -static int uffd_data_write_handler(int mode, int uffd, struct uffd_msg *msg) +static int uffd_pt_handler(int mode, int uffd, struct uffd_msg *msg) { - return uffd_generic_handler(mode, uffd, msg, &data_args, true); + return uffd_generic_handler(mode, uffd, msg, &pt_args); } -static int uffd_data_read_handler(int mode, int uffd, struct uffd_msg *msg) +static int uffd_data_handler(int mode, int uffd, struct uffd_msg *msg) { - return uffd_generic_handler(mode, uffd, msg, &data_args, false); + return uffd_generic_handler(mode, uffd, msg, &data_args); } static void setup_uffd_args(struct userspace_mem_region *region, @@ -471,9 +470,12 @@ static bool handle_cmd(struct kvm_vm *vm, int cmd) { struct userspace_mem_region *data_region, *pt_region; bool continue_test = true; + uint64_t pte_gpa, pte_pg; data_region = vm_get_mem_region(vm, MEM_REGION_TEST_DATA); pt_region = vm_get_mem_region(vm, MEM_REGION_PT); + pte_gpa = addr_hva2gpa(vm, virt_get_pte_hva(vm, TEST_GVA)); + pte_pg = (pte_gpa - pt_region->region.guest_phys_addr) / getpagesize(); if (cmd == CMD_SKIP_TEST) continue_test = false; @@ -486,13 +488,13 @@ static bool handle_cmd(struct kvm_vm *vm, int cmd) TEST_ASSERT(check_write_in_dirty_log(vm, data_region, 0), "Missing write in dirty log"); if (cmd & CMD_CHECK_S1PTW_WR_IN_DIRTY_LOG) - TEST_ASSERT(check_write_in_dirty_log(vm, pt_region, 0), + TEST_ASSERT(check_write_in_dirty_log(vm, pt_region, pte_pg), "Missing s1ptw write in dirty log"); if (cmd & CMD_CHECK_NO_WRITE_IN_DIRTY_LOG) TEST_ASSERT(!check_write_in_dirty_log(vm, data_region, 0), "Unexpected write in dirty log"); if (cmd & CMD_CHECK_NO_S1PTW_WR_IN_DIRTY_LOG) - TEST_ASSERT(!check_write_in_dirty_log(vm, pt_region, 0), + TEST_ASSERT(!check_write_in_dirty_log(vm, pt_region, pte_pg), "Unexpected s1ptw write in dirty log"); return continue_test; @@ -797,7 +799,7 @@ static void help(char *name) .expected_events = { .uffd_faults = _uffd_faults, }, \ } -#define TEST_DIRTY_LOG(_access, _with_af, _test_check) \ +#define TEST_DIRTY_LOG(_access, _with_af, _test_check, _pt_check) \ { \ .name = SCAT3(dirty_log, _access, _with_af), \ .data_memslot_flags = KVM_MEM_LOG_DIRTY_PAGES, \ @@ -805,13 +807,12 @@ static void help(char *name) .guest_prepare = { _PREPARE(_with_af), \ _PREPARE(_access) }, \ .guest_test = _access, \ - .guest_test_check = { _CHECK(_with_af), _test_check, \ - guest_check_s1ptw_wr_in_dirty_log}, \ + .guest_test_check = { _CHECK(_with_af), _test_check, _pt_check }, \ .expected_events = { 0 }, \ } #define TEST_UFFD_AND_DIRTY_LOG(_access, _with_af, _uffd_data_handler, \ - _uffd_faults, _test_check) \ + _uffd_faults, _test_check, _pt_check) \ { \ .name = SCAT3(uffd_and_dirty_log, _access, _with_af), \ .data_memslot_flags = KVM_MEM_LOG_DIRTY_PAGES, \ @@ -820,16 +821,17 @@ static void help(char *name) _PREPARE(_access) }, \ .guest_test = _access, \ .mem_mark_cmd = CMD_HOLE_DATA | CMD_HOLE_PT, \ - .guest_test_check = { _CHECK(_with_af), _test_check }, \ + .guest_test_check = { _CHECK(_with_af), _test_check, _pt_check }, \ .uffd_data_handler = _uffd_data_handler, \ - .uffd_pt_handler = uffd_pt_write_handler, \ + .uffd_pt_handler = uffd_pt_handler, \ .expected_events = { .uffd_faults = _uffd_faults, }, \ } #define TEST_RO_MEMSLOT(_access, _mmio_handler, _mmio_exits) \ { \ - .name = SCAT3(ro_memslot, _access, _with_af), \ + .name = SCAT2(ro_memslot, _access), \ .data_memslot_flags = KVM_MEM_READONLY, \ + .pt_memslot_flags = KVM_MEM_READONLY, \ .guest_prepare = { _PREPARE(_access) }, \ .guest_test = _access, \ .mmio_handler = _mmio_handler, \ @@ -840,6 +842,7 @@ static void help(char *name) { \ .name = SCAT2(ro_memslot_no_syndrome, _access), \ .data_memslot_flags = KVM_MEM_READONLY, \ + .pt_memslot_flags = KVM_MEM_READONLY, \ .guest_test = _access, \ .fail_vcpu_run_handler = fail_vcpu_run_mmio_no_syndrome_handler, \ .expected_events = { .fail_vcpu_runs = 1 }, \ @@ -848,9 +851,9 @@ static void help(char *name) #define TEST_RO_MEMSLOT_AND_DIRTY_LOG(_access, _mmio_handler, _mmio_exits, \ _test_check) \ { \ - .name = SCAT3(ro_memslot, _access, _with_af), \ + .name = SCAT2(ro_memslot, _access), \ .data_memslot_flags = KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES, \ - .pt_memslot_flags = KVM_MEM_LOG_DIRTY_PAGES, \ + .pt_memslot_flags = KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES, \ .guest_prepare = { _PREPARE(_access) }, \ .guest_test = _access, \ .guest_test_check = { _test_check }, \ @@ -862,7 +865,7 @@ static void help(char *name) { \ .name = SCAT2(ro_memslot_no_syn_and_dlog, _access), \ .data_memslot_flags = KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES, \ - .pt_memslot_flags = KVM_MEM_LOG_DIRTY_PAGES, \ + .pt_memslot_flags = KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES, \ .guest_test = _access, \ .guest_test_check = { _test_check }, \ .fail_vcpu_run_handler = fail_vcpu_run_mmio_no_syndrome_handler, \ @@ -874,11 +877,12 @@ static void help(char *name) { \ .name = SCAT2(ro_memslot_uffd, _access), \ .data_memslot_flags = KVM_MEM_READONLY, \ + .pt_memslot_flags = KVM_MEM_READONLY, \ .mem_mark_cmd = CMD_HOLE_DATA | CMD_HOLE_PT, \ .guest_prepare = { _PREPARE(_access) }, \ .guest_test = _access, \ .uffd_data_handler = _uffd_data_handler, \ - .uffd_pt_handler = uffd_pt_write_handler, \ + .uffd_pt_handler = uffd_pt_handler, \ .mmio_handler = _mmio_handler, \ .expected_events = { .mmio_exits = _mmio_exits, \ .uffd_faults = _uffd_faults }, \ @@ -889,10 +893,11 @@ static void help(char *name) { \ .name = SCAT2(ro_memslot_no_syndrome, _access), \ .data_memslot_flags = KVM_MEM_READONLY, \ + .pt_memslot_flags = KVM_MEM_READONLY, \ .mem_mark_cmd = CMD_HOLE_DATA | CMD_HOLE_PT, \ .guest_test = _access, \ .uffd_data_handler = _uffd_data_handler, \ - .uffd_pt_handler = uffd_pt_write_handler, \ + .uffd_pt_handler = uffd_pt_handler, \ .fail_vcpu_run_handler = fail_vcpu_run_mmio_no_syndrome_handler, \ .expected_events = { .fail_vcpu_runs = 1, \ .uffd_faults = _uffd_faults }, \ @@ -933,44 +938,51 @@ static struct test_desc tests[] = { * (S1PTW). */ TEST_UFFD(guest_read64, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_read_handler, uffd_pt_write_handler, 2), - /* no_af should also lead to a PT write. */ + uffd_data_handler, uffd_pt_handler, 2), TEST_UFFD(guest_read64, no_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_read_handler, uffd_pt_write_handler, 2), - /* Note how that cas invokes the read handler. */ + uffd_data_handler, uffd_pt_handler, 2), TEST_UFFD(guest_cas, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_read_handler, uffd_pt_write_handler, 2), + uffd_data_handler, uffd_pt_handler, 2), /* * Can't test guest_at with_af as it's IMPDEF whether the AF is set. * The S1PTW fault should still be marked as a write. */ TEST_UFFD(guest_at, no_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_read_handler, uffd_pt_write_handler, 1), + uffd_no_handler, uffd_pt_handler, 1), TEST_UFFD(guest_ld_preidx, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_read_handler, uffd_pt_write_handler, 2), + uffd_data_handler, uffd_pt_handler, 2), TEST_UFFD(guest_write64, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_write_handler, uffd_pt_write_handler, 2), + uffd_data_handler, uffd_pt_handler, 2), TEST_UFFD(guest_dc_zva, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_write_handler, uffd_pt_write_handler, 2), + uffd_data_handler, uffd_pt_handler, 2), TEST_UFFD(guest_st_preidx, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_write_handler, uffd_pt_write_handler, 2), + uffd_data_handler, uffd_pt_handler, 2), TEST_UFFD(guest_exec, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_read_handler, uffd_pt_write_handler, 2), + uffd_data_handler, uffd_pt_handler, 2), /* * Try accesses when the data and PT memory regions are both * tracked for dirty logging. */ - TEST_DIRTY_LOG(guest_read64, with_af, guest_check_no_write_in_dirty_log), - /* no_af should also lead to a PT write. */ - TEST_DIRTY_LOG(guest_read64, no_af, guest_check_no_write_in_dirty_log), - TEST_DIRTY_LOG(guest_ld_preidx, with_af, guest_check_no_write_in_dirty_log), - TEST_DIRTY_LOG(guest_at, no_af, guest_check_no_write_in_dirty_log), - TEST_DIRTY_LOG(guest_exec, with_af, guest_check_no_write_in_dirty_log), - TEST_DIRTY_LOG(guest_write64, with_af, guest_check_write_in_dirty_log), - TEST_DIRTY_LOG(guest_cas, with_af, guest_check_write_in_dirty_log), - TEST_DIRTY_LOG(guest_dc_zva, with_af, guest_check_write_in_dirty_log), - TEST_DIRTY_LOG(guest_st_preidx, with_af, guest_check_write_in_dirty_log), + TEST_DIRTY_LOG(guest_read64, with_af, guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_read64, no_af, guest_check_no_write_in_dirty_log, + guest_check_no_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_ld_preidx, with_af, + guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_at, no_af, guest_check_no_write_in_dirty_log, + guest_check_no_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_exec, with_af, guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_write64, with_af, guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_cas, with_af, guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_dc_zva, with_af, guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_st_preidx, with_af, guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), /* * Access when the data and PT memory regions are both marked for @@ -980,29 +992,43 @@ static struct test_desc tests[] = { * fault, and nothing in the dirty log. Any S1PTW should result in * a write in the dirty log and a userfaultfd write. */ - TEST_UFFD_AND_DIRTY_LOG(guest_read64, with_af, uffd_data_read_handler, 2, - guest_check_no_write_in_dirty_log), - /* no_af should also lead to a PT write. */ - TEST_UFFD_AND_DIRTY_LOG(guest_read64, no_af, uffd_data_read_handler, 2, - guest_check_no_write_in_dirty_log), - TEST_UFFD_AND_DIRTY_LOG(guest_ld_preidx, with_af, uffd_data_read_handler, - 2, guest_check_no_write_in_dirty_log), - TEST_UFFD_AND_DIRTY_LOG(guest_at, with_af, 0, 1, - guest_check_no_write_in_dirty_log), - TEST_UFFD_AND_DIRTY_LOG(guest_exec, with_af, uffd_data_read_handler, 2, - guest_check_no_write_in_dirty_log), - TEST_UFFD_AND_DIRTY_LOG(guest_write64, with_af, uffd_data_write_handler, - 2, guest_check_write_in_dirty_log), - TEST_UFFD_AND_DIRTY_LOG(guest_cas, with_af, uffd_data_read_handler, 2, - guest_check_write_in_dirty_log), - TEST_UFFD_AND_DIRTY_LOG(guest_dc_zva, with_af, uffd_data_write_handler, - 2, guest_check_write_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_read64, with_af, + uffd_data_handler, 2, + guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_read64, no_af, + uffd_data_handler, 2, + guest_check_no_write_in_dirty_log, + guest_check_no_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_ld_preidx, with_af, + uffd_data_handler, + 2, guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_at, with_af, uffd_no_handler, 1, + guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_exec, with_af, + uffd_data_handler, 2, + guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_write64, with_af, + uffd_data_handler, + 2, guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_cas, with_af, + uffd_data_handler, 2, + guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_dc_zva, with_af, + uffd_data_handler, + 2, guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), TEST_UFFD_AND_DIRTY_LOG(guest_st_preidx, with_af, - uffd_data_write_handler, 2, - guest_check_write_in_dirty_log), - + uffd_data_handler, 2, + guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), /* - * Try accesses when the data memory region is marked read-only + * Access when both the PT and data regions are marked read-only * (with KVM_MEM_READONLY). Writes with a syndrome result in an * MMIO exit, writes with no syndrome (e.g., CAS) result in a * failed vcpu run, and reads/execs with and without syndroms do @@ -1018,7 +1044,7 @@ static struct test_desc tests[] = { TEST_RO_MEMSLOT_NO_SYNDROME(guest_st_preidx), /* - * Access when both the data region is both read-only and marked + * The PT and data regions are both read-only and marked * for dirty logging at the same time. The expected result is that * for writes there should be no write in the dirty log. The * readonly handling is the same as if the memslot was not marked @@ -1043,7 +1069,7 @@ static struct test_desc tests[] = { guest_check_no_write_in_dirty_log), /* - * Access when the data region is both read-only and punched with + * The PT and data regions are both read-only and punched with * holes tracked with userfaultfd. The expected result is the * union of both userfaultfd and read-only behaviors. For example, * write accesses result in a userfaultfd write fault and an MMIO @@ -1051,22 +1077,15 @@ static struct test_desc tests[] = { * no userfaultfd write fault. Reads result in userfaultfd getting * triggered. */ - TEST_RO_MEMSLOT_AND_UFFD(guest_read64, 0, 0, - uffd_data_read_handler, 2), - TEST_RO_MEMSLOT_AND_UFFD(guest_ld_preidx, 0, 0, - uffd_data_read_handler, 2), - TEST_RO_MEMSLOT_AND_UFFD(guest_at, 0, 0, - uffd_no_handler, 1), - TEST_RO_MEMSLOT_AND_UFFD(guest_exec, 0, 0, - uffd_data_read_handler, 2), + TEST_RO_MEMSLOT_AND_UFFD(guest_read64, 0, 0, uffd_data_handler, 2), + TEST_RO_MEMSLOT_AND_UFFD(guest_ld_preidx, 0, 0, uffd_data_handler, 2), + TEST_RO_MEMSLOT_AND_UFFD(guest_at, 0, 0, uffd_no_handler, 1), + TEST_RO_MEMSLOT_AND_UFFD(guest_exec, 0, 0, uffd_data_handler, 2), TEST_RO_MEMSLOT_AND_UFFD(guest_write64, mmio_on_test_gpa_handler, 1, - uffd_data_write_handler, 2), - TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_cas, - uffd_data_read_handler, 2), - TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_dc_zva, - uffd_no_handler, 1), - TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_st_preidx, - uffd_no_handler, 1), + uffd_data_handler, 2), + TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_cas, uffd_data_handler, 2), + TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_dc_zva, uffd_no_handler, 1), + TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_st_preidx, uffd_no_handler, 1), { 0 } }; diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 951bd5342bc6..3364c548a23b 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -46,6 +46,7 @@ TEST_PROGS += stress_reuseport_listen.sh TEST_PROGS += l2_tos_ttl_inherit.sh TEST_PROGS += bind_bhash.sh TEST_PROGS += ip_local_port_range.sh +TEST_PROGS += rps_default_mask.sh TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh TEST_GEN_FILES = socket nettest diff --git a/tools/testing/selftests/net/cmsg_ipv6.sh b/tools/testing/selftests/net/cmsg_ipv6.sh index 2d89cb0ad288..330d0b1ceced 100755 --- a/tools/testing/selftests/net/cmsg_ipv6.sh +++ b/tools/testing/selftests/net/cmsg_ipv6.sh @@ -6,7 +6,7 @@ ksft_skip=4 NS=ns IP6=2001:db8:1::1/64 TGT6=2001:db8:1::2 -TMPF=`mktemp` +TMPF=$(mktemp --suffix ".pcap") cleanup() { diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index bd89198cd817..cc9fd55ab869 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -3,6 +3,9 @@ CONFIG_NET_NS=y CONFIG_BPF_SYSCALL=y CONFIG_TEST_BPF=m CONFIG_NUMA=y +CONFIG_RPS=y +CONFIG_SYSFS=y +CONFIG_PROC_SYSCTL=y CONFIG_NET_VRF=y CONFIG_NET_L3_MASTER_DEV=y CONFIG_IPV6=y diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 453ae006fbcf..91201ab3c4fc 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -4,6 +4,7 @@ TEST_PROGS = bridge_igmp.sh \ bridge_locked_port.sh \ bridge_mdb.sh \ bridge_mdb_host.sh \ + bridge_mdb_max.sh \ bridge_mdb_port_down.sh \ bridge_mld.sh \ bridge_port_isolation.sh \ diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh index 2fa5973c0c28..b48867d8cadf 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh @@ -1018,26 +1018,6 @@ fwd_test() ip -6 address del fe80::1/64 dev br0 } -igmpv3_is_in_get() -{ - local igmpv3 - - igmpv3=$(: - )"22:"$( : Type - Membership Report - )"00:"$( : Reserved - )"2a:f8:"$( : Checksum - )"00:00:"$( : Reserved - )"00:01:"$( : Number of Group Records - )"01:"$( : Record Type - IS_IN - )"00:"$( : Aux Data Len - )"00:01:"$( : Number of Sources - )"ef:01:01:01:"$( : Multicast Address - 239.1.1.1 - )"c0:00:02:02"$( : Source Address - 192.0.2.2 - ) - - echo $igmpv3 -} - ctrl_igmpv3_is_in_test() { RET=0 @@ -1049,7 +1029,7 @@ ctrl_igmpv3_is_in_test() # IS_IN ( 192.0.2.2 ) $MZ $h1.10 -c 1 -A 192.0.2.1 -B 239.1.1.1 \ - -t ip proto=2,p=$(igmpv3_is_in_get) -q + -t ip proto=2,p=$(igmpv3_is_in_get 239.1.1.1 192.0.2.2) -q bridge -d mdb show dev br0 vid 10 | grep 239.1.1.1 | grep -q 192.0.2.2 check_fail $? "Permanent entry affected by IGMP packet" @@ -1062,7 +1042,7 @@ ctrl_igmpv3_is_in_test() # IS_IN ( 192.0.2.2 ) $MZ $h1.10 -c 1 -A 192.0.2.1 -B 239.1.1.1 \ - -t ip proto=2,p=$(igmpv3_is_in_get) -q + -t ip proto=2,p=$(igmpv3_is_in_get 239.1.1.1 192.0.2.2) -q bridge -d mdb show dev br0 vid 10 | grep 239.1.1.1 | grep -v "src" | \ grep -q 192.0.2.2 @@ -1074,36 +1054,7 @@ ctrl_igmpv3_is_in_test() bridge mdb del dev br0 port $swp1 grp 239.1.1.1 vid 10 - log_test "IGMPv3 MODE_IS_INCLUE tests" -} - -mldv2_is_in_get() -{ - local hbh - local icmpv6 - - hbh=$(: - )"3a:"$( : Next Header - ICMPv6 - )"00:"$( : Hdr Ext Len - )"00:00:00:00:00:00:"$( : Options and Padding - ) - - icmpv6=$(: - )"8f:"$( : Type - MLDv2 Report - )"00:"$( : Code - )"45:39:"$( : Checksum - )"00:00:"$( : Reserved - )"00:01:"$( : Number of Group Records - )"01:"$( : Record Type - IS_IN - )"00:"$( : Aux Data Len - )"00:01:"$( : Number of Sources - )"ff:0e:00:00:00:00:00:00:"$( : Multicast address - ff0e::1 - )"00:00:00:00:00:00:00:01:"$( : - )"20:01:0d:b8:00:01:00:00:"$( : Source Address - 2001:db8:1::2 - )"00:00:00:00:00:00:00:02:"$( : - ) - - echo ${hbh}${icmpv6} + log_test "IGMPv3 MODE_IS_INCLUDE tests" } ctrl_mldv2_is_in_test() @@ -1116,8 +1067,9 @@ ctrl_mldv2_is_in_test() filter_mode include source_list 2001:db8:1::1 # IS_IN ( 2001:db8:1::2 ) + local p=$(mldv2_is_in_get fe80::1 ff0e::1 2001:db8:1::2) $MZ -6 $h1.10 -c 1 -A fe80::1 -B ff0e::1 \ - -t ip hop=1,next=0,p=$(mldv2_is_in_get) -q + -t ip hop=1,next=0,p="$p" -q bridge -d mdb show dev br0 vid 10 | grep ff0e::1 | \ grep -q 2001:db8:1::2 @@ -1131,7 +1083,7 @@ ctrl_mldv2_is_in_test() # IS_IN ( 2001:db8:1::2 ) $MZ -6 $h1.10 -c 1 -A fe80::1 -B ff0e::1 \ - -t ip hop=1,next=0,p=$(mldv2_is_in_get) -q + -t ip hop=1,next=0,p="$p" -q bridge -d mdb show dev br0 vid 10 | grep ff0e::1 | grep -v "src" | \ grep -q 2001:db8:1::2 diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh b/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh new file mode 100755 index 000000000000..ae255b662ba3 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh @@ -0,0 +1,1336 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +-----------------------+ +------------------------+ +# | H1 (vrf) | | H2 (vrf) | +# | + $h1.10 | | + $h2.10 | +# | | 192.0.2.1/28 | | | 192.0.2.2/28 | +# | | 2001:db8:1::1/64 | | | 2001:db8:1::2/64 | +# | | | | | | +# | | + $h1.20 | | | + $h2.20 | +# | \ | 198.51.100.1/24 | | \ | 198.51.100.2/24 | +# | \ | 2001:db8:2::1/64 | | \ | 2001:db8:2::2/64 | +# | \| | | \| | +# | + $h1 | | + $h2 | +# +----|------------------+ +----|-------------------+ +# | | +# +----|--------------------------------------------------|-------------------+ +# | SW | | | +# | +--|--------------------------------------------------|-----------------+ | +# | | + $swp1 BR0 (802.1q) + $swp2 | | +# | | vid 10 vid 10 | | +# | | vid 20 vid 20 | | +# | | | | +# | +-----------------------------------------------------------------------+ | +# +---------------------------------------------------------------------------+ + +ALL_TESTS=" + test_8021d + test_8021q + test_8021qvs +" + +NUM_NETIFS=4 +source lib.sh +source tc_common.sh + +h1_create() +{ + simple_if_init $h1 + vlan_create $h1 10 v$h1 192.0.2.1/28 2001:db8:1::1/64 + vlan_create $h1 20 v$h1 198.51.100.1/24 2001:db8:2::1/64 +} + +h1_destroy() +{ + vlan_destroy $h1 20 + vlan_destroy $h1 10 + simple_if_fini $h1 +} + +h2_create() +{ + simple_if_init $h2 + vlan_create $h2 10 v$h2 192.0.2.2/28 + vlan_create $h2 20 v$h2 198.51.100.2/24 +} + +h2_destroy() +{ + vlan_destroy $h2 20 + vlan_destroy $h2 10 + simple_if_fini $h2 +} + +switch_create_8021d() +{ + log_info "802.1d tests" + + ip link add name br0 type bridge vlan_filtering 0 \ + mcast_snooping 1 \ + mcast_igmp_version 3 mcast_mld_version 2 + ip link set dev br0 up + + ip link set dev $swp1 master br0 + ip link set dev $swp1 up + bridge link set dev $swp1 fastleave on + + ip link set dev $swp2 master br0 + ip link set dev $swp2 up +} + +switch_create_8021q() +{ + local br_flags=$1; shift + + log_info "802.1q $br_flags${br_flags:+ }tests" + + ip link add name br0 type bridge vlan_filtering 1 vlan_default_pvid 0 \ + mcast_snooping 1 $br_flags \ + mcast_igmp_version 3 mcast_mld_version 2 + bridge vlan add vid 10 dev br0 self + bridge vlan add vid 20 dev br0 self + ip link set dev br0 up + + ip link set dev $swp1 master br0 + ip link set dev $swp1 up + bridge link set dev $swp1 fastleave on + bridge vlan add vid 10 dev $swp1 + bridge vlan add vid 20 dev $swp1 + + ip link set dev $swp2 master br0 + ip link set dev $swp2 up + bridge vlan add vid 10 dev $swp2 + bridge vlan add vid 20 dev $swp2 +} + +switch_create_8021qvs() +{ + switch_create_8021q "mcast_vlan_snooping 1" + bridge vlan global set dev br0 vid 10 mcast_igmp_version 3 + bridge vlan global set dev br0 vid 10 mcast_mld_version 2 + bridge vlan global set dev br0 vid 20 mcast_igmp_version 3 + bridge vlan global set dev br0 vid 20 mcast_mld_version 2 +} + +switch_destroy() +{ + ip link set dev $swp2 down + ip link set dev $swp2 nomaster + + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + + ip link set dev br0 down + ip link del dev br0 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + forwarding_enable + + h1_create + h2_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy 2>/dev/null + h2_destroy + h1_destroy + + forwarding_restore + vrf_cleanup +} + +cfg_src_list() +{ + local IPs=("$@") + local IPstr=$(echo ${IPs[@]} | tr '[:space:]' , | sed 's/,$//') + + echo ${IPstr:+source_list }${IPstr} +} + +cfg_group_op() +{ + local op=$1; shift + local locus=$1; shift + local GRP=$1; shift + local state=$1; shift + local IPs=("$@") + + local source_list=$(cfg_src_list ${IPs[@]}) + + # Everything besides `bridge mdb' uses the "dev X vid Y" syntax, + # so we use it here as well and convert. + local br_locus=$(echo "$locus" | sed 's/^dev /port /') + + bridge mdb $op dev br0 $br_locus grp $GRP $state \ + filter_mode include $source_list +} + +cfg4_entries_op() +{ + local op=$1; shift + local locus=$1; shift + local state=$1; shift + local n=$1; shift + local grp=${1:-1}; shift + + local GRP=239.1.1.${grp} + local IPs=$(seq -f 192.0.2.%g 1 $((n - 1))) + cfg_group_op "$op" "$locus" "$GRP" "$state" ${IPs[@]} +} + +cfg4_entries_add() +{ + cfg4_entries_op add "$@" +} + +cfg4_entries_del() +{ + cfg4_entries_op del "$@" +} + +cfg6_entries_op() +{ + local op=$1; shift + local locus=$1; shift + local state=$1; shift + local n=$1; shift + local grp=${1:-1}; shift + + local GRP=ff0e::${grp} + local IPs=$(printf "2001:db8:1::%x\n" $(seq 1 $((n - 1)))) + cfg_group_op "$op" "$locus" "$GRP" "$state" ${IPs[@]} +} + +cfg6_entries_add() +{ + cfg6_entries_op add "$@" +} + +cfg6_entries_del() +{ + cfg6_entries_op del "$@" +} + +locus_dev_peer() +{ + local dev_kw=$1; shift + local dev=$1; shift + local vid_kw=$1; shift + local vid=$1; shift + + echo "$h1.${vid:-10}" +} + +locus_dev() +{ + local dev_kw=$1; shift + local dev=$1; shift + + echo $dev +} + +ctl4_entries_add() +{ + local locus=$1; shift + local state=$1; shift + local n=$1; shift + local grp=${1:-1}; shift + + local IPs=$(seq -f 192.0.2.%g 1 $((n - 1))) + local peer=$(locus_dev_peer $locus) + local GRP=239.1.1.${grp} + $MZ $peer -c 1 -A 192.0.2.1 -B $GRP \ + -t ip proto=2,p=$(igmpv3_is_in_get $GRP $IPs) -q + sleep 1 + + local nn=$(bridge mdb show dev br0 | grep $GRP | wc -l) + if ((nn != n)); then + echo mcast_max_groups > /dev/stderr + false + fi +} + +ctl4_entries_del() +{ + local locus=$1; shift + local state=$1; shift + local n=$1; shift + local grp=${1:-1}; shift + + local peer=$(locus_dev_peer $locus) + local GRP=239.1.1.${grp} + $MZ $peer -c 1 -A 192.0.2.1 -B 224.0.0.2 \ + -t ip proto=2,p=$(igmpv2_leave_get $GRP) -q + sleep 1 + ! bridge mdb show dev br0 | grep -q $GRP +} + +ctl6_entries_add() +{ + local locus=$1; shift + local state=$1; shift + local n=$1; shift + local grp=${1:-1}; shift + + local IPs=$(printf "2001:db8:1::%x\n" $(seq 1 $((n - 1)))) + local peer=$(locus_dev_peer $locus) + local SIP=fe80::1 + local GRP=ff0e::${grp} + local p=$(mldv2_is_in_get $SIP $GRP $IPs) + $MZ -6 $peer -c 1 -A $SIP -B $GRP -t ip hop=1,next=0,p="$p" -q + sleep 1 + + local nn=$(bridge mdb show dev br0 | grep $GRP | wc -l) + if ((nn != n)); then + echo mcast_max_groups > /dev/stderr + false + fi +} + +ctl6_entries_del() +{ + local locus=$1; shift + local state=$1; shift + local n=$1; shift + local grp=${1:-1}; shift + + local peer=$(locus_dev_peer $locus) + local SIP=fe80::1 + local GRP=ff0e::${grp} + local p=$(mldv1_done_get $SIP $GRP) + $MZ -6 $peer -c 1 -A $SIP -B $GRP -t ip hop=1,next=0,p="$p" -q + sleep 1 + ! bridge mdb show dev br0 | grep -q $GRP +} + +bridge_maxgroups_errmsg_check_cfg() +{ + local msg=$1; shift + local needle=$1; shift + + echo "$msg" | grep -q mcast_max_groups + check_err $? "Adding MDB entries failed for the wrong reason: $msg" +} + +bridge_maxgroups_errmsg_check_cfg4() +{ + bridge_maxgroups_errmsg_check_cfg "$@" +} + +bridge_maxgroups_errmsg_check_cfg6() +{ + bridge_maxgroups_errmsg_check_cfg "$@" +} + +bridge_maxgroups_errmsg_check_ctl4() +{ + : +} + +bridge_maxgroups_errmsg_check_ctl6() +{ + : +} + +bridge_port_ngroups_get() +{ + local locus=$1; shift + + bridge -j -d link show $locus | + jq '.[].mcast_n_groups' +} + +bridge_port_maxgroups_get() +{ + local locus=$1; shift + + bridge -j -d link show $locus | + jq '.[].mcast_max_groups' +} + +bridge_port_maxgroups_set() +{ + local locus=$1; shift + local max=$1; shift + + bridge link set dev $(locus_dev $locus) mcast_max_groups $max +} + +bridge_port_vlan_ngroups_get() +{ + local locus=$1; shift + + bridge -j -d vlan show $locus | + jq '.[].vlans[].mcast_n_groups' +} + +bridge_port_vlan_maxgroups_get() +{ + local locus=$1; shift + + bridge -j -d vlan show $locus | + jq '.[].vlans[].mcast_max_groups' +} + +bridge_port_vlan_maxgroups_set() +{ + local locus=$1; shift + local max=$1; shift + + bridge vlan set $locus mcast_max_groups $max +} + +test_ngroups_reporting() +{ + local CFG=$1; shift + local context=$1; shift + local locus=$1; shift + + RET=0 + + local n0=$(bridge_${context}_ngroups_get "$locus") + ${CFG}_entries_add "$locus" temp 5 + check_err $? "Couldn't add MDB entries" + local n1=$(bridge_${context}_ngroups_get "$locus") + + ((n1 == n0 + 5)) + check_err $? "Number of groups was $n0, now is $n1, but $((n0 + 5)) expected" + + ${CFG}_entries_del "$locus" temp 5 + check_err $? "Couldn't delete MDB entries" + local n2=$(bridge_${context}_ngroups_get "$locus") + + ((n2 == n0)) + check_err $? "Number of groups was $n0, now is $n2, but should be back to $n0" + + log_test "$CFG: $context: ngroups reporting" +} + +test_8021d_ngroups_reporting_cfg4() +{ + test_ngroups_reporting cfg4 port "dev $swp1" +} + +test_8021d_ngroups_reporting_ctl4() +{ + test_ngroups_reporting ctl4 port "dev $swp1" +} + +test_8021d_ngroups_reporting_cfg6() +{ + test_ngroups_reporting cfg6 port "dev $swp1" +} + +test_8021d_ngroups_reporting_ctl6() +{ + test_ngroups_reporting ctl6 port "dev $swp1" +} + +test_8021q_ngroups_reporting_cfg4() +{ + test_ngroups_reporting cfg4 port "dev $swp1 vid 10" +} + +test_8021q_ngroups_reporting_ctl4() +{ + test_ngroups_reporting ctl4 port "dev $swp1 vid 10" +} + +test_8021q_ngroups_reporting_cfg6() +{ + test_ngroups_reporting cfg6 port "dev $swp1 vid 10" +} + +test_8021q_ngroups_reporting_ctl6() +{ + test_ngroups_reporting ctl6 port "dev $swp1 vid 10" +} + +test_8021qvs_ngroups_reporting_cfg4() +{ + test_ngroups_reporting cfg4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_ngroups_reporting_ctl4() +{ + test_ngroups_reporting ctl4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_ngroups_reporting_cfg6() +{ + test_ngroups_reporting cfg6 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_ngroups_reporting_ctl6() +{ + test_ngroups_reporting ctl6 port_vlan "dev $swp1 vid 10" +} + +test_ngroups_cross_vlan() +{ + local CFG=$1; shift + + local locus1="dev $swp1 vid 10" + local locus2="dev $swp1 vid 20" + + RET=0 + + local n10=$(bridge_port_vlan_ngroups_get "$locus1") + local n20=$(bridge_port_vlan_ngroups_get "$locus2") + ${CFG}_entries_add "$locus1" temp 5 111 + check_err $? "Couldn't add MDB entries to VLAN 10" + local n11=$(bridge_port_vlan_ngroups_get "$locus1") + local n21=$(bridge_port_vlan_ngroups_get "$locus2") + + ((n11 == n10 + 5)) + check_err $? "Number of groups at VLAN 10 was $n10, now is $n11, but 5 entries added on VLAN 10, $((n10 + 5)) expected" + + ((n21 == n20)) + check_err $? "Number of groups at VLAN 20 was $n20, now is $n21, but no change expected on VLAN 20" + + ${CFG}_entries_add "$locus2" temp 5 112 + check_err $? "Couldn't add MDB entries to VLAN 20" + local n12=$(bridge_port_vlan_ngroups_get "$locus1") + local n22=$(bridge_port_vlan_ngroups_get "$locus2") + + ((n12 == n11)) + check_err $? "Number of groups at VLAN 10 was $n11, now is $n12, but no change expected on VLAN 10" + + ((n22 == n21 + 5)) + check_err $? "Number of groups at VLAN 20 was $n21, now is $n22, but 5 entries added on VLAN 20, $((n21 + 5)) expected" + + ${CFG}_entries_del "$locus1" temp 5 111 + check_err $? "Couldn't delete MDB entries from VLAN 10" + ${CFG}_entries_del "$locus2" temp 5 112 + check_err $? "Couldn't delete MDB entries from VLAN 20" + local n13=$(bridge_port_vlan_ngroups_get "$locus1") + local n23=$(bridge_port_vlan_ngroups_get "$locus2") + + ((n13 == n10)) + check_err $? "Number of groups at VLAN 10 was $n10, now is $n13, but should be back to $n10" + + ((n23 == n20)) + check_err $? "Number of groups at VLAN 20 was $n20, now is $n23, but should be back to $n20" + + log_test "$CFG: port_vlan: isolation of port and per-VLAN ngroups" +} + +test_8021qvs_ngroups_cross_vlan_cfg4() +{ + test_ngroups_cross_vlan cfg4 +} + +test_8021qvs_ngroups_cross_vlan_ctl4() +{ + test_ngroups_cross_vlan ctl4 +} + +test_8021qvs_ngroups_cross_vlan_cfg6() +{ + test_ngroups_cross_vlan cfg6 +} + +test_8021qvs_ngroups_cross_vlan_ctl6() +{ + test_ngroups_cross_vlan ctl6 +} + +test_maxgroups_zero() +{ + local CFG=$1; shift + local context=$1; shift + local locus=$1; shift + + RET=0 + local max + + max=$(bridge_${context}_maxgroups_get "$locus") + ((max == 0)) + check_err $? "Max groups on $locus should be 0, but $max reported" + + bridge_${context}_maxgroups_set "$locus" 100 + check_err $? "Failed to set max to 100" + max=$(bridge_${context}_maxgroups_get "$locus") + ((max == 100)) + check_err $? "Max groups expected to be 100, but $max reported" + + bridge_${context}_maxgroups_set "$locus" 0 + check_err $? "Couldn't set maximum to 0" + + # Test that setting 0 explicitly still serves as infinity. + ${CFG}_entries_add "$locus" temp 5 + check_err $? "Adding 5 MDB entries failed but should have passed" + ${CFG}_entries_del "$locus" temp 5 + check_err $? "Couldn't delete MDB entries" + + log_test "$CFG: $context maxgroups: reporting and treatment of 0" +} + +test_8021d_maxgroups_zero_cfg4() +{ + test_maxgroups_zero cfg4 port "dev $swp1" +} + +test_8021d_maxgroups_zero_ctl4() +{ + test_maxgroups_zero ctl4 port "dev $swp1" +} + +test_8021d_maxgroups_zero_cfg6() +{ + test_maxgroups_zero cfg6 port "dev $swp1" +} + +test_8021d_maxgroups_zero_ctl6() +{ + test_maxgroups_zero ctl6 port "dev $swp1" +} + +test_8021q_maxgroups_zero_cfg4() +{ + test_maxgroups_zero cfg4 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_zero_ctl4() +{ + test_maxgroups_zero ctl4 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_zero_cfg6() +{ + test_maxgroups_zero cfg6 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_zero_ctl6() +{ + test_maxgroups_zero ctl6 port "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_zero_cfg4() +{ + test_maxgroups_zero cfg4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_zero_ctl4() +{ + test_maxgroups_zero ctl4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_zero_cfg6() +{ + test_maxgroups_zero cfg6 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_zero_ctl6() +{ + test_maxgroups_zero ctl6 port_vlan "dev $swp1 vid 10" +} + +test_maxgroups_zero_cross_vlan() +{ + local CFG=$1; shift + + local locus0="dev $swp1" + local locus1="dev $swp1 vid 10" + local locus2="dev $swp1 vid 20" + local max + + RET=0 + + bridge_port_vlan_maxgroups_set "$locus1" 100 + check_err $? "$locus1: Failed to set max to 100" + + max=$(bridge_port_maxgroups_get "$locus0") + ((max == 0)) + check_err $? "$locus0: Max groups expected to be 0, but $max reported" + + max=$(bridge_port_vlan_maxgroups_get "$locus2") + ((max == 0)) + check_err $? "$locus2: Max groups expected to be 0, but $max reported" + + bridge_port_vlan_maxgroups_set "$locus2" 100 + check_err $? "$locus2: Failed to set max to 100" + + max=$(bridge_port_maxgroups_get "$locus0") + ((max == 0)) + check_err $? "$locus0: Max groups expected to be 0, but $max reported" + + max=$(bridge_port_vlan_maxgroups_get "$locus2") + ((max == 100)) + check_err $? "$locus2: Max groups expected to be 100, but $max reported" + + bridge_port_maxgroups_set "$locus0" 100 + check_err $? "$locus0: Failed to set max to 100" + + max=$(bridge_port_maxgroups_get "$locus0") + ((max == 100)) + check_err $? "$locus0: Max groups expected to be 100, but $max reported" + + max=$(bridge_port_vlan_maxgroups_get "$locus2") + ((max == 100)) + check_err $? "$locus2: Max groups expected to be 100, but $max reported" + + bridge_port_vlan_maxgroups_set "$locus1" 0 + check_err $? "$locus1: Failed to set max to 0" + + max=$(bridge_port_maxgroups_get "$locus0") + ((max == 100)) + check_err $? "$locus0: Max groups expected to be 100, but $max reported" + + max=$(bridge_port_vlan_maxgroups_get "$locus2") + ((max == 100)) + check_err $? "$locus2: Max groups expected to be 100, but $max reported" + + bridge_port_vlan_maxgroups_set "$locus2" 0 + check_err $? "$locus2: Failed to set max to 0" + + max=$(bridge_port_maxgroups_get "$locus0") + ((max == 100)) + check_err $? "$locus0: Max groups expected to be 100, but $max reported" + + max=$(bridge_port_vlan_maxgroups_get "$locus2") + ((max == 0)) + check_err $? "$locus2: Max groups expected to be 0 but $max reported" + + bridge_port_maxgroups_set "$locus0" 0 + check_err $? "$locus0: Failed to set max to 0" + + max=$(bridge_port_maxgroups_get "$locus0") + ((max == 0)) + check_err $? "$locus0: Max groups expected to be 0, but $max reported" + + max=$(bridge_port_vlan_maxgroups_get "$locus2") + ((max == 0)) + check_err $? "$locus2: Max groups expected to be 0, but $max reported" + + log_test "$CFG: port_vlan maxgroups: isolation of port and per-VLAN maximums" +} + +test_8021qvs_maxgroups_zero_cross_vlan_cfg4() +{ + test_maxgroups_zero_cross_vlan cfg4 +} + +test_8021qvs_maxgroups_zero_cross_vlan_ctl4() +{ + test_maxgroups_zero_cross_vlan ctl4 +} + +test_8021qvs_maxgroups_zero_cross_vlan_cfg6() +{ + test_maxgroups_zero_cross_vlan cfg6 +} + +test_8021qvs_maxgroups_zero_cross_vlan_ctl6() +{ + test_maxgroups_zero_cross_vlan ctl6 +} + +test_maxgroups_too_low() +{ + local CFG=$1; shift + local context=$1; shift + local locus=$1; shift + + RET=0 + + local n=$(bridge_${context}_ngroups_get "$locus") + local msg + + ${CFG}_entries_add "$locus" temp 5 111 + check_err $? "$locus: Couldn't add MDB entries" + + bridge_${context}_maxgroups_set "$locus" $((n+2)) + check_err $? "$locus: Setting maxgroups to $((n+2)) failed" + + msg=$(${CFG}_entries_add "$locus" temp 2 112 2>&1) + check_fail $? "$locus: Adding more entries passed when max<n" + bridge_maxgroups_errmsg_check_cfg "$msg" + + ${CFG}_entries_del "$locus" temp 5 111 + check_err $? "$locus: Couldn't delete MDB entries" + + ${CFG}_entries_add "$locus" temp 2 112 + check_err $? "$locus: Adding more entries failed" + + ${CFG}_entries_del "$locus" temp 2 112 + check_err $? "$locus: Deleting more entries failed" + + bridge_${context}_maxgroups_set "$locus" 0 + check_err $? "$locus: Couldn't set maximum to 0" + + log_test "$CFG: $context maxgroups: configure below ngroups" +} + +test_8021d_maxgroups_too_low_cfg4() +{ + test_maxgroups_too_low cfg4 port "dev $swp1" +} + +test_8021d_maxgroups_too_low_ctl4() +{ + test_maxgroups_too_low ctl4 port "dev $swp1" +} + +test_8021d_maxgroups_too_low_cfg6() +{ + test_maxgroups_too_low cfg6 port "dev $swp1" +} + +test_8021d_maxgroups_too_low_ctl6() +{ + test_maxgroups_too_low ctl6 port "dev $swp1" +} + +test_8021q_maxgroups_too_low_cfg4() +{ + test_maxgroups_too_low cfg4 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_too_low_ctl4() +{ + test_maxgroups_too_low ctl4 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_too_low_cfg6() +{ + test_maxgroups_too_low cfg6 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_too_low_ctl6() +{ + test_maxgroups_too_low ctl6 port "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_low_cfg4() +{ + test_maxgroups_too_low cfg4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_low_ctl4() +{ + test_maxgroups_too_low ctl4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_low_cfg6() +{ + test_maxgroups_too_low cfg6 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_low_ctl6() +{ + test_maxgroups_too_low ctl6 port_vlan "dev $swp1 vid 10" +} + +test_maxgroups_too_many_entries() +{ + local CFG=$1; shift + local context=$1; shift + local locus=$1; shift + + RET=0 + + local n=$(bridge_${context}_ngroups_get "$locus") + local msg + + # Configure a low maximum + bridge_${context}_maxgroups_set "$locus" $((n+1)) + check_err $? "$locus: Couldn't set maximum" + + # Try to add more entries than the configured maximum + msg=$(${CFG}_entries_add "$locus" temp 5 2>&1) + check_fail $? "Adding 5 MDB entries passed, but should have failed" + bridge_maxgroups_errmsg_check_${CFG} "$msg" + + # When adding entries through the control path, as many as possible + # get created. That's consistent with the mcast_hash_max behavior. + # So there, drop the entries explicitly. + if [[ ${CFG%[46]} == ctl ]]; then + ${CFG}_entries_del "$locus" temp 17 2>&1 + fi + + local n2=$(bridge_${context}_ngroups_get "$locus") + ((n2 == n)) + check_err $? "Number of groups was $n, but after a failed attempt to add MDB entries it changed to $n2" + + bridge_${context}_maxgroups_set "$locus" 0 + check_err $? "$locus: Couldn't set maximum to 0" + + log_test "$CFG: $context maxgroups: add too many MDB entries" +} + +test_8021d_maxgroups_too_many_entries_cfg4() +{ + test_maxgroups_too_many_entries cfg4 port "dev $swp1" +} + +test_8021d_maxgroups_too_many_entries_ctl4() +{ + test_maxgroups_too_many_entries ctl4 port "dev $swp1" +} + +test_8021d_maxgroups_too_many_entries_cfg6() +{ + test_maxgroups_too_many_entries cfg6 port "dev $swp1" +} + +test_8021d_maxgroups_too_many_entries_ctl6() +{ + test_maxgroups_too_many_entries ctl6 port "dev $swp1" +} + +test_8021q_maxgroups_too_many_entries_cfg4() +{ + test_maxgroups_too_many_entries cfg4 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_too_many_entries_ctl4() +{ + test_maxgroups_too_many_entries ctl4 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_too_many_entries_cfg6() +{ + test_maxgroups_too_many_entries cfg6 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_too_many_entries_ctl6() +{ + test_maxgroups_too_many_entries ctl6 port "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_many_entries_cfg4() +{ + test_maxgroups_too_many_entries cfg4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_many_entries_ctl4() +{ + test_maxgroups_too_many_entries ctl4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_many_entries_cfg6() +{ + test_maxgroups_too_many_entries cfg6 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_many_entries_ctl6() +{ + test_maxgroups_too_many_entries ctl6 port_vlan "dev $swp1 vid 10" +} + +test_maxgroups_too_many_cross_vlan() +{ + local CFG=$1; shift + + RET=0 + + local locus0="dev $swp1" + local locus1="dev $swp1 vid 10" + local locus2="dev $swp1 vid 20" + local n1=$(bridge_port_vlan_ngroups_get "$locus1") + local n2=$(bridge_port_vlan_ngroups_get "$locus2") + local msg + + if ((n1 > n2)); then + local tmp=$n1 + n1=$n2 + n2=$tmp + + tmp="$locus1" + locus1="$locus2" + locus2="$tmp" + fi + + # Now 0 <= n1 <= n2. + ${CFG}_entries_add "$locus2" temp 5 112 + check_err $? "Couldn't add 5 entries" + + n2=$(bridge_port_vlan_ngroups_get "$locus2") + # Now 0 <= n1 < n2-1. + + # Setting locus1'maxgroups to n2-1 should pass. The number is + # smaller than both the absolute number of MDB entries, and in + # particular than number of locus2's number of entries, but it is + # large enough to cover locus1's entries. Thus we check that + # individual VLAN's ngroups are independent. + bridge_port_vlan_maxgroups_set "$locus1" $((n2-1)) + check_err $? "Setting ${locus1}'s maxgroups to $((n2-1)) failed" + + msg=$(${CFG}_entries_add "$locus1" temp $n2 111 2>&1) + check_fail $? "$locus1: Adding $n2 MDB entries passed, but should have failed" + bridge_maxgroups_errmsg_check_${CFG} "$msg" + + bridge_port_maxgroups_set "$locus0" $((n1 + n2 + 2)) + check_err $? "$locus0: Couldn't set maximum" + + msg=$(${CFG}_entries_add "$locus1" temp 5 111 2>&1) + check_fail $? "$locus1: Adding 5 MDB entries passed, but should have failed" + bridge_maxgroups_errmsg_check_${CFG} "$msg" + + # IGMP/MLD packets can cause several entries to be added, before + # the maximum is hit and the rest is then bounced. Remove what was + # committed, if anything. + ${CFG}_entries_del "$locus1" temp 5 111 2>/dev/null + + ${CFG}_entries_add "$locus1" temp 2 111 + check_err $? "$locus1: Adding 2 MDB entries failed, but should have passed" + + ${CFG}_entries_del "$locus1" temp 2 111 + check_err $? "Couldn't delete MDB entries" + + ${CFG}_entries_del "$locus2" temp 5 112 + check_err $? "Couldn't delete MDB entries" + + bridge_port_vlan_maxgroups_set "$locus1" 0 + check_err $? "$locus1: Couldn't set maximum to 0" + + bridge_port_maxgroups_set "$locus0" 0 + check_err $? "$locus0: Couldn't set maximum to 0" + + log_test "$CFG: port_vlan maxgroups: isolation of port and per-VLAN ngroups" +} + +test_8021qvs_maxgroups_too_many_cross_vlan_cfg4() +{ + test_maxgroups_too_many_cross_vlan cfg4 +} + +test_8021qvs_maxgroups_too_many_cross_vlan_ctl4() +{ + test_maxgroups_too_many_cross_vlan ctl4 +} + +test_8021qvs_maxgroups_too_many_cross_vlan_cfg6() +{ + test_maxgroups_too_many_cross_vlan cfg6 +} + +test_8021qvs_maxgroups_too_many_cross_vlan_ctl6() +{ + test_maxgroups_too_many_cross_vlan ctl6 +} + +test_vlan_attributes() +{ + local locus=$1; shift + local expect=$1; shift + + RET=0 + + local max=$(bridge_port_vlan_maxgroups_get "$locus") + local n=$(bridge_port_vlan_ngroups_get "$locus") + + eval "[[ $max $expect ]]" + check_err $? "$locus: maxgroups attribute expected to be $expect, but was $max" + + eval "[[ $n $expect ]]" + check_err $? "$locus: ngroups attribute expected to be $expect, but was $n" + + log_test "port_vlan: presence of ngroups and maxgroups attributes" +} + +test_8021q_vlan_attributes() +{ + test_vlan_attributes "dev $swp1 vid 10" "== null" +} + +test_8021qvs_vlan_attributes() +{ + test_vlan_attributes "dev $swp1 vid 10" "-ge 0" +} + +test_toggle_vlan_snooping() +{ + local mode=$1; shift + + RET=0 + + local CFG=cfg4 + local context=port_vlan + local locus="dev $swp1 vid 10" + + ${CFG}_entries_add "$locus" $mode 5 + check_err $? "Couldn't add MDB entries" + + bridge_${context}_maxgroups_set "$locus" 100 + check_err $? "Failed to set max to 100" + + ip link set dev br0 type bridge mcast_vlan_snooping 0 + sleep 1 + ip link set dev br0 type bridge mcast_vlan_snooping 1 + + local n=$(bridge_${context}_ngroups_get "$locus") + local nn=$(bridge mdb show dev br0 | grep $swp1 | wc -l) + ((nn == n)) + check_err $? "mcast_n_groups expected to be $nn, but $n reported" + + local max=$(bridge_${context}_maxgroups_get "$locus") + ((max == 100)) + check_err $? "Max groups expected to be 100 but $max reported" + + bridge_${context}_maxgroups_set "$locus" 0 + check_err $? "Failed to set max to 0" + + log_test "$CFG: $context: $mode: mcast_vlan_snooping toggle" +} + +test_toggle_vlan_snooping_temp() +{ + test_toggle_vlan_snooping temp +} + +test_toggle_vlan_snooping_permanent() +{ + test_toggle_vlan_snooping permanent +} + +# ngroup test suites + +test_8021d_ngroups_cfg4() +{ + test_8021d_ngroups_reporting_cfg4 +} + +test_8021d_ngroups_ctl4() +{ + test_8021d_ngroups_reporting_ctl4 +} + +test_8021d_ngroups_cfg6() +{ + test_8021d_ngroups_reporting_cfg6 +} + +test_8021d_ngroups_ctl6() +{ + test_8021d_ngroups_reporting_ctl6 +} + +test_8021q_ngroups_cfg4() +{ + test_8021q_ngroups_reporting_cfg4 +} + +test_8021q_ngroups_ctl4() +{ + test_8021q_ngroups_reporting_ctl4 +} + +test_8021q_ngroups_cfg6() +{ + test_8021q_ngroups_reporting_cfg6 +} + +test_8021q_ngroups_ctl6() +{ + test_8021q_ngroups_reporting_ctl6 +} + +test_8021qvs_ngroups_cfg4() +{ + test_8021qvs_ngroups_reporting_cfg4 + test_8021qvs_ngroups_cross_vlan_cfg4 +} + +test_8021qvs_ngroups_ctl4() +{ + test_8021qvs_ngroups_reporting_ctl4 + test_8021qvs_ngroups_cross_vlan_ctl4 +} + +test_8021qvs_ngroups_cfg6() +{ + test_8021qvs_ngroups_reporting_cfg6 + test_8021qvs_ngroups_cross_vlan_cfg6 +} + +test_8021qvs_ngroups_ctl6() +{ + test_8021qvs_ngroups_reporting_ctl6 + test_8021qvs_ngroups_cross_vlan_ctl6 +} + +# maxgroups test suites + +test_8021d_maxgroups_cfg4() +{ + test_8021d_maxgroups_zero_cfg4 + test_8021d_maxgroups_too_low_cfg4 + test_8021d_maxgroups_too_many_entries_cfg4 +} + +test_8021d_maxgroups_ctl4() +{ + test_8021d_maxgroups_zero_ctl4 + test_8021d_maxgroups_too_low_ctl4 + test_8021d_maxgroups_too_many_entries_ctl4 +} + +test_8021d_maxgroups_cfg6() +{ + test_8021d_maxgroups_zero_cfg6 + test_8021d_maxgroups_too_low_cfg6 + test_8021d_maxgroups_too_many_entries_cfg6 +} + +test_8021d_maxgroups_ctl6() +{ + test_8021d_maxgroups_zero_ctl6 + test_8021d_maxgroups_too_low_ctl6 + test_8021d_maxgroups_too_many_entries_ctl6 +} + +test_8021q_maxgroups_cfg4() +{ + test_8021q_maxgroups_zero_cfg4 + test_8021q_maxgroups_too_low_cfg4 + test_8021q_maxgroups_too_many_entries_cfg4 +} + +test_8021q_maxgroups_ctl4() +{ + test_8021q_maxgroups_zero_ctl4 + test_8021q_maxgroups_too_low_ctl4 + test_8021q_maxgroups_too_many_entries_ctl4 +} + +test_8021q_maxgroups_cfg6() +{ + test_8021q_maxgroups_zero_cfg6 + test_8021q_maxgroups_too_low_cfg6 + test_8021q_maxgroups_too_many_entries_cfg6 +} + +test_8021q_maxgroups_ctl6() +{ + test_8021q_maxgroups_zero_ctl6 + test_8021q_maxgroups_too_low_ctl6 + test_8021q_maxgroups_too_many_entries_ctl6 +} + +test_8021qvs_maxgroups_cfg4() +{ + test_8021qvs_maxgroups_zero_cfg4 + test_8021qvs_maxgroups_zero_cross_vlan_cfg4 + test_8021qvs_maxgroups_too_low_cfg4 + test_8021qvs_maxgroups_too_many_entries_cfg4 + test_8021qvs_maxgroups_too_many_cross_vlan_cfg4 +} + +test_8021qvs_maxgroups_ctl4() +{ + test_8021qvs_maxgroups_zero_ctl4 + test_8021qvs_maxgroups_zero_cross_vlan_ctl4 + test_8021qvs_maxgroups_too_low_ctl4 + test_8021qvs_maxgroups_too_many_entries_ctl4 + test_8021qvs_maxgroups_too_many_cross_vlan_ctl4 +} + +test_8021qvs_maxgroups_cfg6() +{ + test_8021qvs_maxgroups_zero_cfg6 + test_8021qvs_maxgroups_zero_cross_vlan_cfg6 + test_8021qvs_maxgroups_too_low_cfg6 + test_8021qvs_maxgroups_too_many_entries_cfg6 + test_8021qvs_maxgroups_too_many_cross_vlan_cfg6 +} + +test_8021qvs_maxgroups_ctl6() +{ + test_8021qvs_maxgroups_zero_ctl6 + test_8021qvs_maxgroups_zero_cross_vlan_ctl6 + test_8021qvs_maxgroups_too_low_ctl6 + test_8021qvs_maxgroups_too_many_entries_ctl6 + test_8021qvs_maxgroups_too_many_cross_vlan_ctl6 +} + +# other test suites + +test_8021qvs_toggle_vlan_snooping() +{ + test_toggle_vlan_snooping_temp + test_toggle_vlan_snooping_permanent +} + +# test groups + +test_8021d() +{ + # Tests for vlan_filtering 0 mcast_vlan_snooping 0. + + switch_create_8021d + setup_wait + + test_8021d_ngroups_cfg4 + test_8021d_ngroups_ctl4 + test_8021d_ngroups_cfg6 + test_8021d_ngroups_ctl6 + test_8021d_maxgroups_cfg4 + test_8021d_maxgroups_ctl4 + test_8021d_maxgroups_cfg6 + test_8021d_maxgroups_ctl6 + + switch_destroy +} + +test_8021q() +{ + # Tests for vlan_filtering 1 mcast_vlan_snooping 0. + + switch_create_8021q + setup_wait + + test_8021q_vlan_attributes + test_8021q_ngroups_cfg4 + test_8021q_ngroups_ctl4 + test_8021q_ngroups_cfg6 + test_8021q_ngroups_ctl6 + test_8021q_maxgroups_cfg4 + test_8021q_maxgroups_ctl4 + test_8021q_maxgroups_cfg6 + test_8021q_maxgroups_ctl6 + + switch_destroy +} + +test_8021qvs() +{ + # Tests for vlan_filtering 1 mcast_vlan_snooping 1. + + switch_create_8021qvs + setup_wait + + test_8021qvs_vlan_attributes + test_8021qvs_ngroups_cfg4 + test_8021qvs_ngroups_ctl4 + test_8021qvs_ngroups_cfg6 + test_8021qvs_ngroups_ctl6 + test_8021qvs_maxgroups_cfg4 + test_8021qvs_maxgroups_ctl4 + test_8021qvs_maxgroups_cfg6 + test_8021qvs_maxgroups_ctl6 + test_8021qvs_toggle_vlan_snooping + + switch_destroy +} + +trap cleanup EXIT + +setup_prepare +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 1c4f866de7d7..d47499ba81c7 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -524,27 +524,6 @@ cmd_jq() [ ! -z "$output" ] } -lldpad_app_wait_set() -{ - local dev=$1; shift - - while lldptool -t -i $dev -V APP -c app | grep -Eq "pending|unknown"; do - echo "$dev: waiting for lldpad to push pending APP updates" - sleep 5 - done -} - -lldpad_app_wait_del() -{ - # Give lldpad a chance to push down the changes. If the device is downed - # too soon, the updates will be left pending. However, they will have - # been struck off the lldpad's DB already, so we won't be able to tell - # they are pending. Then on next test iteration this would cause - # weirdness as newly-added APP rules conflict with the old ones, - # sometimes getting stuck in an "unknown" state. - sleep 5 -} - pre_cleanup() { if [ "${PAUSE_ON_CLEANUP}" = "yes" ]; then @@ -914,14 +893,14 @@ sysctl_set() local value=$1; shift SYSCTL_ORIG[$key]=$(sysctl -n $key) - sysctl -qw $key=$value + sysctl -qw $key="$value" } sysctl_restore() { local key=$1; shift - sysctl -qw $key=${SYSCTL_ORIG["$key"]} + sysctl -qw $key="${SYSCTL_ORIG[$key]}" } forwarding_enable() @@ -1692,3 +1671,219 @@ hw_stats_monitor_test() log_test "${type}_stats notifications" } + +ipv4_to_bytes() +{ + local IP=$1; shift + + printf '%02x:' ${IP//./ } | + sed 's/:$//' +} + +# Convert a given IPv6 address, `IP' such that the :: token, if present, is +# expanded, and each 16-bit group is padded with zeroes to be 4 hexadecimal +# digits. An optional `BYTESEP' parameter can be given to further separate +# individual bytes of each 16-bit group. +expand_ipv6() +{ + local IP=$1; shift + local bytesep=$1; shift + + local cvt_ip=${IP/::/_} + local colons=${cvt_ip//[^:]/} + local allcol=::::::: + # IP where :: -> the appropriate number of colons: + local allcol_ip=${cvt_ip/_/${allcol:${#colons}}} + + echo $allcol_ip | tr : '\n' | + sed s/^/0000/ | + sed 's/.*\(..\)\(..\)/\1'"$bytesep"'\2/' | + tr '\n' : | + sed 's/:$//' +} + +ipv6_to_bytes() +{ + local IP=$1; shift + + expand_ipv6 "$IP" : +} + +u16_to_bytes() +{ + local u16=$1; shift + + printf "%04x" $u16 | sed 's/^/000/;s/^.*\(..\)\(..\)$/\1:\2/' +} + +# Given a mausezahn-formatted payload (colon-separated bytes given as %02x), +# possibly with a keyword CHECKSUM stashed where a 16-bit checksum should be, +# calculate checksum as per RFC 1071, assuming the CHECKSUM field (if any) +# stands for 00:00. +payload_template_calc_checksum() +{ + local payload=$1; shift + + ( + # Set input radix. + echo "16i" + # Push zero for the initial checksum. + echo 0 + + # Pad the payload with a terminating 00: in case we get an odd + # number of bytes. + echo "${payload%:}:00:" | + sed 's/CHECKSUM/00:00/g' | + tr '[:lower:]' '[:upper:]' | + # Add the word to the checksum. + sed 's/\(..\):\(..\):/\1\2+\n/g' | + # Strip the extra odd byte we pushed if left unconverted. + sed 's/\(..\):$//' + + echo "10000 ~ +" # Calculate and add carry. + echo "FFFF r - p" # Bit-flip and print. + ) | + dc | + tr '[:upper:]' '[:lower:]' +} + +payload_template_expand_checksum() +{ + local payload=$1; shift + local checksum=$1; shift + + local ckbytes=$(u16_to_bytes $checksum) + + echo "$payload" | sed "s/CHECKSUM/$ckbytes/g" +} + +payload_template_nbytes() +{ + local payload=$1; shift + + payload_template_expand_checksum "${payload%:}" 0 | + sed 's/:/\n/g' | wc -l +} + +igmpv3_is_in_get() +{ + local GRP=$1; shift + local sources=("$@") + + local igmpv3 + local nsources=$(u16_to_bytes ${#sources[@]}) + + # IS_IN ( $sources ) + igmpv3=$(: + )"22:"$( : Type - Membership Report + )"00:"$( : Reserved + )"CHECKSUM:"$( : Checksum + )"00:00:"$( : Reserved + )"00:01:"$( : Number of Group Records + )"01:"$( : Record Type - IS_IN + )"00:"$( : Aux Data Len + )"${nsources}:"$( : Number of Sources + )"$(ipv4_to_bytes $GRP):"$( : Multicast Address + )"$(for src in "${sources[@]}"; do + ipv4_to_bytes $src + echo -n : + done)"$( : Source Addresses + ) + local checksum=$(payload_template_calc_checksum "$igmpv3") + + payload_template_expand_checksum "$igmpv3" $checksum +} + +igmpv2_leave_get() +{ + local GRP=$1; shift + + local payload=$(: + )"17:"$( : Type - Leave Group + )"00:"$( : Max Resp Time - not meaningful + )"CHECKSUM:"$( : Checksum + )"$(ipv4_to_bytes $GRP)"$( : Group Address + ) + local checksum=$(payload_template_calc_checksum "$payload") + + payload_template_expand_checksum "$payload" $checksum +} + +mldv2_is_in_get() +{ + local SIP=$1; shift + local GRP=$1; shift + local sources=("$@") + + local hbh + local icmpv6 + local nsources=$(u16_to_bytes ${#sources[@]}) + + hbh=$(: + )"3a:"$( : Next Header - ICMPv6 + )"00:"$( : Hdr Ext Len + )"00:00:00:00:00:00:"$( : Options and Padding + ) + + icmpv6=$(: + )"8f:"$( : Type - MLDv2 Report + )"00:"$( : Code + )"CHECKSUM:"$( : Checksum + )"00:00:"$( : Reserved + )"00:01:"$( : Number of Group Records + )"01:"$( : Record Type - IS_IN + )"00:"$( : Aux Data Len + )"${nsources}:"$( : Number of Sources + )"$(ipv6_to_bytes $GRP):"$( : Multicast address + )"$(for src in "${sources[@]}"; do + ipv6_to_bytes $src + echo -n : + done)"$( : Source Addresses + ) + + local len=$(u16_to_bytes $(payload_template_nbytes $icmpv6)) + local sudohdr=$(: + )"$(ipv6_to_bytes $SIP):"$( : SIP + )"$(ipv6_to_bytes $GRP):"$( : DIP is multicast address + )"${len}:"$( : Upper-layer length + )"00:3a:"$( : Zero and next-header + ) + local checksum=$(payload_template_calc_checksum ${sudohdr}${icmpv6}) + + payload_template_expand_checksum "$hbh$icmpv6" $checksum +} + +mldv1_done_get() +{ + local SIP=$1; shift + local GRP=$1; shift + + local hbh + local icmpv6 + + hbh=$(: + )"3a:"$( : Next Header - ICMPv6 + )"00:"$( : Hdr Ext Len + )"00:00:00:00:00:00:"$( : Options and Padding + ) + + icmpv6=$(: + )"84:"$( : Type - MLDv1 Done + )"00:"$( : Code + )"CHECKSUM:"$( : Checksum + )"00:00:"$( : Max Resp Delay - not meaningful + )"00:00:"$( : Reserved + )"$(ipv6_to_bytes $GRP):"$( : Multicast address + ) + + local len=$(u16_to_bytes $(payload_template_nbytes $icmpv6)) + local sudohdr=$(: + )"$(ipv6_to_bytes $SIP):"$( : SIP + )"$(ipv6_to_bytes $GRP):"$( : DIP is multicast address + )"${len}:"$( : Upper-layer length + )"00:3a:"$( : Zero and next-header + ) + local checksum=$(payload_template_calc_checksum ${sudohdr}${icmpv6}) + + payload_template_expand_checksum "$hbh$icmpv6" $checksum +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 387abdcec011..42e3bd1a05f5 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -498,6 +498,12 @@ kill_events_pids() kill_wait $evts_ns2_pid } +kill_tests_wait() +{ + kill -SIGUSR1 $(ip netns pids $ns2) $(ip netns pids $ns1) + wait +} + pm_nl_set_limits() { local ns=$1 @@ -1687,6 +1693,7 @@ chk_subflow_nr() local subflow_nr=$3 local cnt1 local cnt2 + local dump_stats if [ -n "${need_title}" ]; then printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${msg}" @@ -1704,7 +1711,12 @@ chk_subflow_nr() echo "[ ok ]" fi - [ "${dump_stats}" = 1 ] && ( ss -N $ns1 -tOni ; ss -N $ns1 -tOni | grep token; ip -n $ns1 mptcp endpoint ) + if [ "${dump_stats}" = 1 ]; then + ss -N $ns1 -tOni + ss -N $ns1 -tOni | grep token + ip -n $ns1 mptcp endpoint + dump_stats + fi } chk_link_usage() @@ -3083,7 +3095,7 @@ endpoint_tests() pm_nl_set_limits $ns1 2 2 pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow 2>/dev/null & wait_mpj $ns1 pm_nl_check_endpoint 1 "creation" \ @@ -3096,14 +3108,14 @@ endpoint_tests() pm_nl_add_endpoint $ns2 10.0.2.2 flags signal pm_nl_check_endpoint 0 "modif is allowed" \ $ns2 10.0.2.2 id 1 flags signal - wait + kill_tests_wait fi if reset "delete and re-add"; then pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 4 0 0 slow & + run_tests $ns1 $ns2 10.0.1.1 4 0 0 speed_20 2>/dev/null & wait_mpj $ns2 pm_nl_del_endpoint $ns2 2 10.0.2.2 @@ -3113,7 +3125,7 @@ endpoint_tests() pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow wait_mpj $ns2 chk_subflow_nr "" "after re-add" 2 - wait + kill_tests_wait fi } diff --git a/tools/testing/selftests/net/rps_default_mask.sh b/tools/testing/selftests/net/rps_default_mask.sh new file mode 100755 index 000000000000..c81c0ac7ddfe --- /dev/null +++ b/tools/testing/selftests/net/rps_default_mask.sh @@ -0,0 +1,57 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +readonly ksft_skip=4 +readonly cpus=$(nproc) +ret=0 + +[ $cpus -gt 2 ] || exit $ksft_skip + +readonly INITIAL_RPS_DEFAULT_MASK=$(cat /proc/sys/net/core/rps_default_mask) +readonly NETNS="ns-$(mktemp -u XXXXXX)" + +setup() { + ip netns add "${NETNS}" + ip -netns "${NETNS}" link set lo up +} + +cleanup() { + echo $INITIAL_RPS_DEFAULT_MASK > /proc/sys/net/core/rps_default_mask + ip netns del $NETNS +} + +chk_rps() { + local rps_mask expected_rps_mask=$3 + local dev_name=$2 + local msg=$1 + + rps_mask=$(ip netns exec $NETNS cat /sys/class/net/$dev_name/queues/rx-0/rps_cpus) + printf "%-60s" "$msg" + if [ $rps_mask -eq $expected_rps_mask ]; then + echo "[ ok ]" + else + echo "[fail] expected $expected_rps_mask found $rps_mask" + ret=1 + fi +} + +trap cleanup EXIT + +echo 0 > /proc/sys/net/core/rps_default_mask +setup +chk_rps "empty rps_default_mask" lo 0 +cleanup + +echo 1 > /proc/sys/net/core/rps_default_mask +setup +chk_rps "non zero rps_default_mask" lo 1 + +echo 3 > /proc/sys/net/core/rps_default_mask +chk_rps "changing rps_default_mask dont affect existing netns" lo 1 + +ip -n $NETNS link add type veth +ip -n $NETNS link set dev veth0 up +ip -n $NETNS link set dev veth1 up +chk_rps "changing rps_default_mask affect newly created devices" veth0 3 +chk_rps "changing rps_default_mask affect newly created devices[II]" veth1 3 +exit $ret diff --git a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh index 704997ffc244..8c3ac0a72545 100755 --- a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh +++ b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh @@ -293,19 +293,11 @@ setup-vm() { elif [[ -n $vtype && $vtype == "vnifilterg" ]]; then # Add per vni group config with 'bridge vni' api if [ -n "$group" ]; then - if [ "$family" == "v4" ]; then - if [ $mcast -eq 1 ]; then - bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group $group - else - bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote $group - fi - else - if [ $mcast -eq 1 ]; then - bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group6 $group - else - bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote6 $group - fi - fi + if [ $mcast -eq 1 ]; then + bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group $group + else + bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote $group + fi fi fi done diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh index dc932fd65363..640bc43452fa 100755 --- a/tools/testing/selftests/net/udpgso_bench.sh +++ b/tools/testing/selftests/net/udpgso_bench.sh @@ -7,6 +7,7 @@ readonly GREEN='\033[0;92m' readonly YELLOW='\033[0;33m' readonly RED='\033[0;31m' readonly NC='\033[0m' # No Color +readonly TESTPORT=8000 readonly KSFT_PASS=0 readonly KSFT_FAIL=1 @@ -56,11 +57,26 @@ trap wake_children EXIT run_one() { local -r args=$@ + local nr_socks=0 + local i=0 + local -r timeout=10 + + ./udpgso_bench_rx -p "$TESTPORT" & + ./udpgso_bench_rx -p "$TESTPORT" -t & + + # Wait for the above test program to get ready to receive connections. + while [ "$i" -lt "$timeout" ]; do + nr_socks="$(ss -lnHi | grep -c "\*:${TESTPORT}")" + [ "$nr_socks" -eq 2 ] && break + i=$((i + 1)) + sleep 1 + done + if [ "$nr_socks" -ne 2 ]; then + echo "timed out while waiting for udpgso_bench_rx" + exit 1 + fi - ./udpgso_bench_rx & - ./udpgso_bench_rx -t & - - ./udpgso_bench_tx ${args} + ./udpgso_bench_tx -p "$TESTPORT" ${args} } run_in_netns() { diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index 6a193425c367..4058c7451e70 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -250,7 +250,7 @@ static int recv_msg(int fd, char *buf, int len, int *gso_size) static void do_flush_udp(int fd) { static char rbuf[ETH_MAX_MTU]; - int ret, len, gso_size, budget = 256; + int ret, len, gso_size = 0, budget = 256; len = cfg_read_all ? sizeof(rbuf) : 0; while (budget--) { @@ -336,6 +336,8 @@ static void parse_opts(int argc, char **argv) cfg_verify = true; cfg_read_all = true; break; + default: + exit(1); } } diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c index f1fdaa270291..477392715a9a 100644 --- a/tools/testing/selftests/net/udpgso_bench_tx.c +++ b/tools/testing/selftests/net/udpgso_bench_tx.c @@ -62,6 +62,7 @@ static int cfg_payload_len = (1472 * 42); static int cfg_port = 8000; static int cfg_runtime_ms = -1; static bool cfg_poll; +static int cfg_poll_loop_timeout_ms = 2000; static bool cfg_segment; static bool cfg_sendmmsg; static bool cfg_tcp; @@ -235,16 +236,17 @@ static void flush_errqueue_recv(int fd) } } -static void flush_errqueue(int fd, const bool do_poll) +static void flush_errqueue(int fd, const bool do_poll, + unsigned long poll_timeout, const bool poll_err) { if (do_poll) { struct pollfd fds = {0}; int ret; fds.fd = fd; - ret = poll(&fds, 1, 500); + ret = poll(&fds, 1, poll_timeout); if (ret == 0) { - if (cfg_verbose) + if ((cfg_verbose) && (poll_err)) fprintf(stderr, "poll timeout\n"); } else if (ret < 0) { error(1, errno, "poll"); @@ -254,6 +256,20 @@ static void flush_errqueue(int fd, const bool do_poll) flush_errqueue_recv(fd); } +static void flush_errqueue_retry(int fd, unsigned long num_sends) +{ + unsigned long tnow, tstop; + bool first_try = true; + + tnow = gettimeofday_ms(); + tstop = tnow + cfg_poll_loop_timeout_ms; + do { + flush_errqueue(fd, true, tstop - tnow, first_try); + first_try = false; + tnow = gettimeofday_ms(); + } while ((stat_zcopies != num_sends) && (tnow < tstop)); +} + static int send_tcp(int fd, char *data) { int ret, done = 0, count = 0; @@ -413,7 +429,8 @@ static int send_udp_segment(int fd, char *data) static void usage(const char *filepath) { - error(1, 0, "Usage: %s [-46acmHPtTuvz] [-C cpu] [-D dst ip] [-l secs] [-M messagenr] [-p port] [-s sendsize] [-S gsosize]", + error(1, 0, "Usage: %s [-46acmHPtTuvz] [-C cpu] [-D dst ip] [-l secs] " + "[-L secs] [-M messagenr] [-p port] [-s sendsize] [-S gsosize]", filepath); } @@ -423,7 +440,7 @@ static void parse_opts(int argc, char **argv) int max_len, hdrlen; int c; - while ((c = getopt(argc, argv, "46acC:D:Hl:mM:p:s:PS:tTuvz")) != -1) { + while ((c = getopt(argc, argv, "46acC:D:Hl:L:mM:p:s:PS:tTuvz")) != -1) { switch (c) { case '4': if (cfg_family != PF_UNSPEC) @@ -452,6 +469,9 @@ static void parse_opts(int argc, char **argv) case 'l': cfg_runtime_ms = strtoul(optarg, NULL, 10) * 1000; break; + case 'L': + cfg_poll_loop_timeout_ms = strtoul(optarg, NULL, 10) * 1000; + break; case 'm': cfg_sendmmsg = true; break; @@ -490,6 +510,8 @@ static void parse_opts(int argc, char **argv) case 'z': cfg_zerocopy = true; break; + default: + exit(1); } } @@ -677,7 +699,7 @@ int main(int argc, char **argv) num_sends += send_udp(fd, buf[i]); num_msgs++; if ((cfg_zerocopy && ((num_msgs & 0xF) == 0)) || cfg_tx_tstamp) - flush_errqueue(fd, cfg_poll); + flush_errqueue(fd, cfg_poll, 500, true); if (cfg_msg_nr && num_msgs >= cfg_msg_nr) break; @@ -696,7 +718,7 @@ int main(int argc, char **argv) } while (!interrupted && (cfg_runtime_ms == -1 || tnow < tstop)); if (cfg_zerocopy || cfg_tx_tstamp) - flush_errqueue(fd, true); + flush_errqueue_retry(fd, num_sends); if (close(fd)) error(1, errno, "close"); diff --git a/tools/testing/selftests/vm/hugetlb-madvise.c b/tools/testing/selftests/vm/hugetlb-madvise.c index a634f47d1e56..9a127a8fe176 100644 --- a/tools/testing/selftests/vm/hugetlb-madvise.c +++ b/tools/testing/selftests/vm/hugetlb-madvise.c @@ -17,7 +17,6 @@ #include <stdio.h> #include <unistd.h> #include <sys/mman.h> -#define __USE_GNU #include <fcntl.h> #define MIN_FREE_PAGES 20 diff --git a/tools/virtio/linux/bug.h b/tools/virtio/linux/bug.h index 813baf13f62a..51a919083d9b 100644 --- a/tools/virtio/linux/bug.h +++ b/tools/virtio/linux/bug.h @@ -1,13 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef BUG_H -#define BUG_H +#ifndef _LINUX_BUG_H +#define _LINUX_BUG_H #include <asm/bug.h> #define BUG_ON(__BUG_ON_cond) assert(!(__BUG_ON_cond)) -#define BUILD_BUG_ON(x) - #define BUG() abort() -#endif /* BUG_H */ +#endif /* _LINUX_BUG_H */ diff --git a/tools/virtio/linux/build_bug.h b/tools/virtio/linux/build_bug.h new file mode 100644 index 000000000000..cdbb75e28a60 --- /dev/null +++ b/tools/virtio/linux/build_bug.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_BUILD_BUG_H +#define _LINUX_BUILD_BUG_H + +#define BUILD_BUG_ON(x) + +#endif /* _LINUX_BUILD_BUG_H */ diff --git a/tools/virtio/linux/cpumask.h b/tools/virtio/linux/cpumask.h new file mode 100644 index 000000000000..307da69d6b26 --- /dev/null +++ b/tools/virtio/linux/cpumask.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_CPUMASK_H +#define _LINUX_CPUMASK_H + +#include <linux/kernel.h> + +#endif /* _LINUX_CPUMASK_H */ diff --git a/tools/virtio/linux/gfp.h b/tools/virtio/linux/gfp.h new file mode 100644 index 000000000000..43d146f236f1 --- /dev/null +++ b/tools/virtio/linux/gfp.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_GFP_H +#define __LINUX_GFP_H + +#include <linux/topology.h> + +#endif diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index 21593bf97755..8b877167933d 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -10,6 +10,7 @@ #include <stdarg.h> #include <linux/compiler.h> +#include <linux/log2.h> #include <linux/types.h> #include <linux/overflow.h> #include <linux/list.h> diff --git a/tools/virtio/linux/kmsan.h b/tools/virtio/linux/kmsan.h new file mode 100644 index 000000000000..272b5aa285d5 --- /dev/null +++ b/tools/virtio/linux/kmsan.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_KMSAN_H +#define _LINUX_KMSAN_H + +#include <linux/gfp.h> + +inline void kmsan_handle_dma(struct page *page, size_t offset, size_t size, + enum dma_data_direction dir) +{ +} + +#endif /* _LINUX_KMSAN_H */ diff --git a/tools/virtio/linux/scatterlist.h b/tools/virtio/linux/scatterlist.h index 369ee308b668..74d9e1825748 100644 --- a/tools/virtio/linux/scatterlist.h +++ b/tools/virtio/linux/scatterlist.h @@ -2,6 +2,7 @@ #ifndef SCATTERLIST_H #define SCATTERLIST_H #include <linux/kernel.h> +#include <linux/bug.h> struct scatterlist { unsigned long page_link; diff --git a/tools/virtio/linux/topology.h b/tools/virtio/linux/topology.h new file mode 100644 index 000000000000..910794afb993 --- /dev/null +++ b/tools/virtio/linux/topology.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_TOPOLOGY_H +#define _LINUX_TOPOLOGY_H + +#include <linux/cpumask.h> + +#endif /* _LINUX_TOPOLOGY_H */ |
