diff options
1055 files changed, 24633 insertions, 7969 deletions
diff --git a/.editorconfig b/.editorconfig index 854773350cc5..29a30ccfc07b 100644 --- a/.editorconfig +++ b/.editorconfig @@ -5,7 +5,6 @@ root = true [{*.{awk,c,dts,dtsi,dtso,h,mk,s,S},Kconfig,Makefile,Makefile.*}] charset = utf-8 end_of_line = lf -trim_trailing_whitespace = true insert_final_newline = true indent_style = tab indent_size = 8 @@ -13,7 +12,6 @@ indent_size = 8 [*.{json,py,rs}] charset = utf-8 end_of_line = lf -trim_trailing_whitespace = true insert_final_newline = true indent_style = space indent_size = 4 @@ -26,7 +24,6 @@ indent_size = 8 [*.yaml] charset = utf-8 end_of_line = lf -trim_trailing_whitespace = unset insert_final_newline = true indent_style = space indent_size = 2 @@ -72,6 +72,8 @@ Andrey Ryabinin <[email protected]> <[email protected]> Andrzej Hajda <[email protected]> <[email protected]> André Almeida <[email protected]> <[email protected]> Andy Adamson <[email protected]> +Andy Shevchenko <[email protected]> <[email protected]> +Andy Shevchenko <[email protected]> <[email protected]> Anilkumar Kolli <[email protected]> <[email protected]> Anirudh Ghayal <[email protected]> <[email protected]> Antoine Tenart <[email protected]> <[email protected]> @@ -217,6 +219,7 @@ Geliang Tang <[email protected]> <[email protected]> Geliang Tang <[email protected]> <[email protected]> Geliang Tang <[email protected]> <[email protected]> Geliang Tang <[email protected]> <[email protected]> +Geliang Tang <[email protected]> <[email protected]> Georgi Djakov <[email protected]> <[email protected]> Gerald Schaefer <[email protected]> <[email protected]> Gerald Schaefer <[email protected]> <[email protected]> @@ -605,6 +608,7 @@ Simon Kelley <[email protected]> Sricharan Ramabadhran <[email protected]> <[email protected]> Srinivas Ramana <[email protected]> <[email protected]> Sriram R <[email protected]> <[email protected]> +Stanislav Fomichev <[email protected]> <[email protected]> Stefan Wahren <[email protected]> <[email protected]> Stéphane Witzmann <[email protected]> Stephen Hemminger <[email protected]> <[email protected]> @@ -1214,6 +1214,10 @@ D: UDF filesystem S: (ask for current address) S: USA +N: Larry Finger +D: Maintainer of wireless drivers, too many to list here + N: Jürgen Fischer D: Author of Adaptec AHA-152x SCSI driver diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index b600df82669d..11e57ba2985c 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2192,12 +2192,6 @@ Format: 0 | 1 Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON. - init_mlocked_on_free= [MM] Fill freed userspace memory with zeroes if - it was mlock'ed and not explicitly munlock'ed - afterwards. - Format: 0 | 1 - Default set by CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON - init_pkru= [X86] Specify the default memory protection keys rights register contents for all processes. 0x55555554 by default (disallow access to all but pkey 0). Can diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index 076443cc10a6..d414d3f5592a 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -467,11 +467,11 @@ anon_fault_fallback_charge instead falls back to using huge pages with lower orders or small pages even though the allocation was successful. -anon_swpout +swpout is incremented every time a huge page is swapped out in one piece without splitting. -anon_swpout_fallback +swpout_fallback is incremented if a huge page has to be split before swapout. Usually because failed to allocate some continuous swap space for the huge page. diff --git a/Documentation/cdrom/cdrom-standard.rst b/Documentation/cdrom/cdrom-standard.rst index 7964fe134277..6c1303cff159 100644 --- a/Documentation/cdrom/cdrom-standard.rst +++ b/Documentation/cdrom/cdrom-standard.rst @@ -217,7 +217,7 @@ current *struct* is:: int (*media_changed)(struct cdrom_device_info *, int); int (*tray_move)(struct cdrom_device_info *, int); int (*lock_door)(struct cdrom_device_info *, int); - int (*select_speed)(struct cdrom_device_info *, int); + int (*select_speed)(struct cdrom_device_info *, unsigned long); int (*get_last_session) (struct cdrom_device_info *, struct cdrom_multisession *); int (*get_mcn)(struct cdrom_device_info *, struct cdrom_mcn *); @@ -396,7 +396,7 @@ action need be taken, and the return value should be 0. :: - int select_speed(struct cdrom_device_info *cdi, int speed) + int select_speed(struct cdrom_device_info *cdi, unsigned long speed) Some CD-ROM drives are capable of changing their head-speed. There are several reasons for changing the speed of a CD-ROM drive. Badly diff --git a/Documentation/devicetree/bindings/dma/fsl,edma.yaml b/Documentation/devicetree/bindings/dma/fsl,edma.yaml index acfb4b2ee7a9..d54140f18d34 100644 --- a/Documentation/devicetree/bindings/dma/fsl,edma.yaml +++ b/Documentation/devicetree/bindings/dma/fsl,edma.yaml @@ -59,8 +59,8 @@ properties: - 3 dma-channels: - minItems: 1 - maxItems: 64 + minimum: 1 + maximum: 64 clocks: minItems: 1 diff --git a/Documentation/devicetree/bindings/i2c/atmel,at91sam-i2c.yaml b/Documentation/devicetree/bindings/i2c/atmel,at91sam-i2c.yaml index b1c13bab2472..b2d19cfb87ad 100644 --- a/Documentation/devicetree/bindings/i2c/atmel,at91sam-i2c.yaml +++ b/Documentation/devicetree/bindings/i2c/atmel,at91sam-i2c.yaml @@ -77,7 +77,7 @@ required: - clocks allOf: - - $ref: i2c-controller.yaml + - $ref: /schemas/i2c/i2c-controller.yaml# - if: properties: compatible: diff --git a/Documentation/devicetree/bindings/i2c/google,cros-ec-i2c-tunnel.yaml b/Documentation/devicetree/bindings/i2c/google,cros-ec-i2c-tunnel.yaml index ab151c9db219..580003cdfff5 100644 --- a/Documentation/devicetree/bindings/i2c/google,cros-ec-i2c-tunnel.yaml +++ b/Documentation/devicetree/bindings/i2c/google,cros-ec-i2c-tunnel.yaml @@ -21,7 +21,7 @@ description: | google,cros-ec-spi or google,cros-ec-i2c. allOf: - - $ref: i2c-controller.yaml# + - $ref: /schemas/i2c/i2c-controller.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad3552r.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad3552r.yaml index 96340a05754c..8265d709094d 100644 --- a/Documentation/devicetree/bindings/iio/dac/adi,ad3552r.yaml +++ b/Documentation/devicetree/bindings/iio/dac/adi,ad3552r.yaml @@ -139,7 +139,7 @@ allOf: Voltage output range of the channel as <minimum, maximum> Required connections: Rfb1x for: 0 to 2.5 V; 0 to 3V; 0 to 5 V; - Rfb2x for: 0 to 10 V; 2.5 to 7.5V; -5 to 5 V; + Rfb2x for: 0 to 10 V; -2.5 to 7.5V; -5 to 5 V; oneOf: - items: - const: 0 diff --git a/Documentation/devicetree/bindings/input/elan,ekth6915.yaml b/Documentation/devicetree/bindings/input/elan,ekth6915.yaml index dc4ac41f2441..a62916d07a08 100644 --- a/Documentation/devicetree/bindings/input/elan,ekth6915.yaml +++ b/Documentation/devicetree/bindings/input/elan,ekth6915.yaml @@ -18,9 +18,12 @@ allOf: properties: compatible: - enum: - - elan,ekth6915 - - ilitek,ili2901 + oneOf: + - items: + - enum: + - elan,ekth5015m + - const: elan,ekth6915 + - const: elan,ekth6915 reg: const: 0x10 @@ -33,6 +36,12 @@ properties: reset-gpios: description: Reset GPIO; not all touchscreens using eKTH6915 hook this up. + no-reset-on-power-off: + type: boolean + description: + Reset line is wired so that it can (and should) be left deasserted when + the power supply is off. + vcc33-supply: description: The 3.3V supply to the touchscreen. @@ -58,8 +67,8 @@ examples: #address-cells = <1>; #size-cells = <0>; - ap_ts: touchscreen@10 { - compatible = "elan,ekth6915"; + touchscreen@10 { + compatible = "elan,ekth5015m", "elan,ekth6915"; reg = <0x10>; interrupt-parent = <&tlmm>; diff --git a/Documentation/devicetree/bindings/input/ilitek,ili2901.yaml b/Documentation/devicetree/bindings/input/ilitek,ili2901.yaml new file mode 100644 index 000000000000..1abeec768d79 --- /dev/null +++ b/Documentation/devicetree/bindings/input/ilitek,ili2901.yaml @@ -0,0 +1,66 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/input/ilitek,ili2901.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Ilitek ILI2901 touchscreen controller + +maintainers: + - Jiri Kosina <[email protected]> + +description: + Supports the Ilitek ILI2901 touchscreen controller. + This touchscreen controller uses the i2c-hid protocol with a reset GPIO. + +allOf: + - $ref: /schemas/input/touchscreen/touchscreen.yaml# + +properties: + compatible: + enum: + - ilitek,ili2901 + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + panel: true + + reset-gpios: + maxItems: 1 + + vcc33-supply: true + + vccio-supply: true + +required: + - compatible + - reg + - interrupts + - vcc33-supply + +additionalProperties: false + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + #include <dt-bindings/interrupt-controller/irq.h> + + i2c { + #address-cells = <1>; + #size-cells = <0>; + + touchscreen@41 { + compatible = "ilitek,ili2901"; + reg = <0x41>; + + interrupt-parent = <&tlmm>; + interrupts = <9 IRQ_TYPE_LEVEL_LOW>; + + reset-gpios = <&tlmm 8 GPIO_ACTIVE_LOW>; + vcc33-supply = <&pp3300_ts>; + }; + }; diff --git a/Documentation/devicetree/bindings/net/arc_emac.txt b/Documentation/devicetree/bindings/net/arc_emac.txt deleted file mode 100644 index c73a0e9c625e..000000000000 --- a/Documentation/devicetree/bindings/net/arc_emac.txt +++ /dev/null @@ -1,46 +0,0 @@ -* Synopsys ARC EMAC 10/100 Ethernet driver (EMAC) - -Required properties: -- compatible: Should be "snps,arc-emac" -- reg: Address and length of the register set for the device -- interrupts: Should contain the EMAC interrupts -- max-speed: see ethernet.txt file in the same directory. -- phy: see ethernet.txt file in the same directory. - -Optional properties: -- phy-reset-gpios : Should specify the gpio for phy reset -- phy-reset-duration : Reset duration in milliseconds. Should present - only if property "phy-reset-gpios" is available. Missing the property - will have the duration be 1 millisecond. Numbers greater than 1000 are - invalid and 1 millisecond will be used instead. - -Clock handling: -The clock frequency is needed to calculate and set polling period of EMAC. -It must be provided by one of: -- clock-frequency: CPU frequency. -- clocks: reference to the clock supplying the EMAC. - -Child nodes of the driver are the individual PHY devices connected to the -MDIO bus. They must have a "reg" property given the PHY address on the MDIO bus. - -Examples: - - ethernet@c0fc2000 { - compatible = "snps,arc-emac"; - reg = <0xc0fc2000 0x3c>; - interrupts = <6>; - mac-address = [ 00 11 22 33 44 55 ]; - - clock-frequency = <80000000>; - /* or */ - clocks = <&emac_clock>; - - max-speed = <100>; - phy = <&phy0>; - - #address-cells = <1>; - #size-cells = <0>; - phy0: ethernet-phy@0 { - reg = <1>; - }; - }; diff --git a/Documentation/devicetree/bindings/net/can/xilinx,can.yaml b/Documentation/devicetree/bindings/net/can/xilinx,can.yaml index 8d4e5af6fd6c..40835497050a 100644 --- a/Documentation/devicetree/bindings/net/can/xilinx,can.yaml +++ b/Documentation/devicetree/bindings/net/can/xilinx,can.yaml @@ -5,7 +5,7 @@ $id: http://devicetree.org/schemas/net/can/xilinx,can.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: - Xilinx Axi CAN/Zynq CANPS controller + Xilinx CAN and CANFD controller maintainers: - Appana Durga Kedareswara rao <[email protected]> diff --git a/Documentation/devicetree/bindings/net/cdns,macb.yaml b/Documentation/devicetree/bindings/net/cdns,macb.yaml index 2c71e2cf3a2f..3c30dd23cd4e 100644 --- a/Documentation/devicetree/bindings/net/cdns,macb.yaml +++ b/Documentation/devicetree/bindings/net/cdns,macb.yaml @@ -146,6 +146,7 @@ patternProperties: magic-packet: type: boolean + deprecated: true description: Indicates that the hardware supports waking up via magic packet. diff --git a/Documentation/devicetree/bindings/net/dsa/lantiq,gswip.yaml b/Documentation/devicetree/bindings/net/dsa/lantiq,gswip.yaml new file mode 100644 index 000000000000..f3154b19af78 --- /dev/null +++ b/Documentation/devicetree/bindings/net/dsa/lantiq,gswip.yaml @@ -0,0 +1,202 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/dsa/lantiq,gswip.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Lantiq GSWIP Ethernet switches + +allOf: + - $ref: dsa.yaml#/$defs/ethernet-ports + +maintainers: + - Hauke Mehrtens <[email protected]> + +properties: + compatible: + enum: + - lantiq,xrx200-gswip + - lantiq,xrx300-gswip + - lantiq,xrx330-gswip + + reg: + minItems: 3 + maxItems: 3 + + reg-names: + items: + - const: switch + - const: mdio + - const: mii + + mdio: + $ref: /schemas/net/mdio.yaml# + unevaluatedProperties: false + + properties: + compatible: + const: lantiq,xrx200-mdio + + required: + - compatible + + gphy-fw: + type: object + properties: + '#address-cells': + const: 1 + + '#size-cells': + const: 0 + + compatible: + items: + - enum: + - lantiq,xrx200-gphy-fw + - lantiq,xrx300-gphy-fw + - lantiq,xrx330-gphy-fw + - const: lantiq,gphy-fw + + lantiq,rcu: + $ref: /schemas/types.yaml#/definitions/phandle + description: phandle to the RCU syscon + + patternProperties: + "^gphy@[0-9a-f]{1,2}$": + type: object + + additionalProperties: false + + properties: + reg: + minimum: 0 + maximum: 255 + description: + Offset of the GPHY firmware register in the RCU register range + + resets: + items: + - description: GPHY reset line + + reset-names: + items: + - const: gphy + + required: + - reg + + required: + - compatible + - lantiq,rcu + + additionalProperties: false + +required: + - compatible + - reg + +unevaluatedProperties: false + +examples: + - | + switch@e108000 { + compatible = "lantiq,xrx200-gswip"; + reg = <0xe108000 0x3100>, /* switch */ + <0xe10b100 0xd8>, /* mdio */ + <0xe10b1d8 0x130>; /* mii */ + dsa,member = <0 0>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + label = "lan3"; + phy-mode = "rgmii"; + phy-handle = <&phy0>; + }; + + port@1 { + reg = <1>; + label = "lan4"; + phy-mode = "rgmii"; + phy-handle = <&phy1>; + }; + + port@2 { + reg = <2>; + label = "lan2"; + phy-mode = "internal"; + phy-handle = <&phy11>; + }; + + port@4 { + reg = <4>; + label = "lan1"; + phy-mode = "internal"; + phy-handle = <&phy13>; + }; + + port@5 { + reg = <5>; + label = "wan"; + phy-mode = "rgmii"; + phy-handle = <&phy5>; + }; + + port@6 { + reg = <0x6>; + phy-mode = "internal"; + ethernet = <ð0>; + + fixed-link { + speed = <1000>; + full-duplex; + }; + }; + }; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + compatible = "lantiq,xrx200-mdio"; + + phy0: ethernet-phy@0 { + reg = <0x0>; + }; + phy1: ethernet-phy@1 { + reg = <0x1>; + }; + phy5: ethernet-phy@5 { + reg = <0x5>; + }; + phy11: ethernet-phy@11 { + reg = <0x11>; + }; + phy13: ethernet-phy@13 { + reg = <0x13>; + }; + }; + + gphy-fw { + #address-cells = <1>; + #size-cells = <0>; + compatible = "lantiq,xrx200-gphy-fw", "lantiq,gphy-fw"; + lantiq,rcu = <&rcu0>; + + gphy@20 { + reg = <0x20>; + + resets = <&reset0 31 30>; + reset-names = "gphy"; + }; + + gphy@68 { + reg = <0x68>; + + resets = <&reset0 29 28>; + reset-names = "gphy"; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/net/dsa/lantiq-gswip.txt b/Documentation/devicetree/bindings/net/dsa/lantiq-gswip.txt deleted file mode 100644 index 8bb1eff21cb1..000000000000 --- a/Documentation/devicetree/bindings/net/dsa/lantiq-gswip.txt +++ /dev/null @@ -1,146 +0,0 @@ -Lantiq GSWIP Ethernet switches -================================== - -Required properties for GSWIP core: - -- compatible : "lantiq,xrx200-gswip" for the embedded GSWIP in the - xRX200 SoC - "lantiq,xrx300-gswip" for the embedded GSWIP in the - xRX300 SoC - "lantiq,xrx330-gswip" for the embedded GSWIP in the - xRX330 SoC -- reg : memory range of the GSWIP core registers - : memory range of the GSWIP MDIO registers - : memory range of the GSWIP MII registers - -See Documentation/devicetree/bindings/net/dsa/dsa.txt for a list of -additional required and optional properties. - - -Required properties for MDIO bus: -- compatible : "lantiq,xrx200-mdio" for the MDIO bus inside the GSWIP - core of the xRX200 SoC and the PHYs connected to it. - -See Documentation/devicetree/bindings/net/mdio.txt for a list of additional -required and optional properties. - - -Required properties for GPHY firmware loading: -- compatible : "lantiq,xrx200-gphy-fw", "lantiq,gphy-fw" - "lantiq,xrx300-gphy-fw", "lantiq,gphy-fw" - "lantiq,xrx330-gphy-fw", "lantiq,gphy-fw" - for the loading of the firmware into the embedded - GPHY core of the SoC. -- lantiq,rcu : reference to the rcu syscon - -The GPHY firmware loader has a list of GPHY entries, one for each -embedded GPHY - -- reg : Offset of the GPHY firmware register in the RCU - register range -- resets : list of resets of the embedded GPHY -- reset-names : list of names of the resets - -Example: - -Ethernet switch on the VRX200 SoC: - -switch@e108000 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "lantiq,xrx200-gswip"; - reg = < 0xe108000 0x3100 /* switch */ - 0xe10b100 0xd8 /* mdio */ - 0xe10b1d8 0x130 /* mii */ - >; - dsa,member = <0 0>; - - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; - label = "lan3"; - phy-mode = "rgmii"; - phy-handle = <&phy0>; - }; - - port@1 { - reg = <1>; - label = "lan4"; - phy-mode = "rgmii"; - phy-handle = <&phy1>; - }; - - port@2 { - reg = <2>; - label = "lan2"; - phy-mode = "internal"; - phy-handle = <&phy11>; - }; - - port@4 { - reg = <4>; - label = "lan1"; - phy-mode = "internal"; - phy-handle = <&phy13>; - }; - - port@5 { - reg = <5>; - label = "wan"; - phy-mode = "rgmii"; - phy-handle = <&phy5>; - }; - - port@6 { - reg = <0x6>; - ethernet = <ð0>; - }; - }; - - mdio { - #address-cells = <1>; - #size-cells = <0>; - compatible = "lantiq,xrx200-mdio"; - reg = <0>; - - phy0: ethernet-phy@0 { - reg = <0x0>; - }; - phy1: ethernet-phy@1 { - reg = <0x1>; - }; - phy5: ethernet-phy@5 { - reg = <0x5>; - }; - phy11: ethernet-phy@11 { - reg = <0x11>; - }; - phy13: ethernet-phy@13 { - reg = <0x13>; - }; - }; - - gphy-fw { - compatible = "lantiq,xrx200-gphy-fw", "lantiq,gphy-fw"; - lantiq,rcu = <&rcu0>; - #address-cells = <1>; - #size-cells = <0>; - - gphy@20 { - reg = <0x20>; - - resets = <&reset0 31 30>; - reset-names = "gphy"; - }; - - gphy@68 { - reg = <0x68>; - - resets = <&reset0 29 28>; - reset-names = "gphy"; - }; - }; -}; diff --git a/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml b/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml index 1c2444121e60..7e405ad96eb2 100644 --- a/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml +++ b/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml @@ -22,16 +22,16 @@ description: | The MT7988 SoC comes with a built-in switch similar to MT7531 as well as four Gigabit Ethernet PHYs. The switch registers are directly mapped into the SoC's - memory map rather than using MDIO. The switch got an internally connected 10G + memory map rather than using MDIO. The switch has an internally connected 10G CPU port and 4 user ports connected to the built-in Gigabit Ethernet PHYs. - MT7530 in MT7620AN, MT7620DA, MT7620DAN and MT7620NN SoCs has got 10/100 PHYs + The MT7530 in MT7620AN, MT7620DA, MT7620DAN and MT7620NN SoCs has 10/100 PHYs and the switch registers are directly mapped into SoC's memory map rather than using MDIO. The DSA driver currently doesn't support MT7620 variants. There is only the standalone version of MT7531. - Port 5 on MT7530 has got various ways of configuration: + Port 5 on MT7530 supports various configurations: - Port 5 can be used as a CPU port. diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml index b2785b03139f..45819b235800 100644 --- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml @@ -103,6 +103,7 @@ properties: - usxgmii - 10gbase-r - 25gbase-r + - 10g-qxgmii phy-mode: $ref: "#/properties/phy-connection-type" diff --git a/Documentation/devicetree/bindings/net/fsl,fman-dtsec.yaml b/Documentation/devicetree/bindings/net/fsl,fman-dtsec.yaml index c80c880a9dab..60aaf30d68ed 100644 --- a/Documentation/devicetree/bindings/net/fsl,fman-dtsec.yaml +++ b/Documentation/devicetree/bindings/net/fsl,fman-dtsec.yaml @@ -128,7 +128,6 @@ required: - cell-index - reg - fsl,fman-ports - - ptp-timer dependencies: pcs-handle-names: diff --git a/Documentation/devicetree/bindings/net/fsl,fman-mdio.yaml b/Documentation/devicetree/bindings/net/fsl,fman-mdio.yaml new file mode 100644 index 000000000000..6b2c0aa407a2 --- /dev/null +++ b/Documentation/devicetree/bindings/net/fsl,fman-mdio.yaml @@ -0,0 +1,123 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/fsl,fman-mdio.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Freescale Frame Manager MDIO Device + +maintainers: + - Frank Li <[email protected]> + +description: FMan MDIO Node. + The MDIO is a bus to which the PHY devices are connected. + +properties: + compatible: + enum: + - fsl,fman-mdio + - fsl,fman-xmdio + - fsl,fman-memac-mdio + description: + Must include "fsl,fman-mdio" for 1 Gb/s MDIO from FMan v2. + Must include "fsl,fman-xmdio" for 10 Gb/s MDIO from FMan v2. + Must include "fsl,fman-memac-mdio" for 1/10 Gb/s MDIO from + FMan v3. + + reg: + maxItems: 1 + + clocks: + items: + - description: A reference to the input clock of the controller + from which the MDC frequency is derived. + + interrupts: + maxItems: 1 + + fsl,fman-internal-mdio: + $ref: /schemas/types.yaml#/definitions/flag + description: + Fman has internal MDIO for internal PCS(Physical + Coding Sublayer) PHYs and external MDIO for external PHYs. + The settings and programming routines for internal/external + MDIO are different. Must be included for internal MDIO. + + fsl,erratum-a009885: + $ref: /schemas/types.yaml#/definitions/flag + description: Indicates the presence of the A009885 + erratum describing that the contents of MDIO_DATA may + become corrupt unless it is read within 16 MDC cycles + of MDIO_CFG[BSY] being cleared, when performing an + MDIO read operation. + + fsl,erratum-a011043: + $ref: /schemas/types.yaml#/definitions/flag + description: + Indicates the presence of the A011043 erratum + describing that the MDIO_CFG[MDIO_RD_ER] bit may be falsely + set when reading internal PCS registers. MDIO reads to + internal PCS registers may result in having the + MDIO_CFG[MDIO_RD_ER] bit set, even when there is no error and + read data (MDIO_DATA[MDIO_DATA]) is correct. + Software may get false read error when reading internal + PCS registers through MDIO. As a workaround, all internal + MDIO accesses should ignore the MDIO_CFG[MDIO_RD_ER] bit. + + For internal PHY device on internal mdio bus, a PHY node should be created. + See the definition of the PHY node in booting-without-of.txt for an + example of how to define a PHY (Internal PHY has no interrupt line). + - For "fsl,fman-mdio" compatible internal mdio bus, the PHY is TBI PHY. + - For "fsl,fman-memac-mdio" compatible internal mdio bus, the PHY is PCS PHY. + The PCS PHY address should correspond to the value of the appropriate + MDEV_PORT. + + little-endian: + $ref: /schemas/types.yaml#/definitions/flag + description: + IP block is little-endian mode. The default endian mode is big-endian. + +required: + - compatible + - reg + +allOf: + - $ref: mdio.yaml# + +unevaluatedProperties: false + +examples: + - | + mdio@f1000 { + compatible = "fsl,fman-xmdio"; + reg = <0xf1000 0x1000>; + interrupts = <101 2 0 0>; + }; + + - | + mdio@e3120 { + compatible = "fsl,fman-mdio"; + reg = <0xe3120 0xee0>; + fsl,fman-internal-mdio; + #address-cells = <1>; + #size-cells = <0>; + + tbi-phy@8 { + reg = <0x8>; + device_type = "tbi-phy"; + }; + }; + + - | + mdio@f1000 { + compatible = "fsl,fman-memac-mdio"; + reg = <0xf1000 0x1000>; + fsl,fman-internal-mdio; + #address-cells = <1>; + #size-cells = <0>; + + pcsphy6: ethernet-phy@0 { + reg = <0x0>; + }; + }; + diff --git a/Documentation/devicetree/bindings/net/fsl,fman-muram.yaml b/Documentation/devicetree/bindings/net/fsl,fman-muram.yaml new file mode 100644 index 000000000000..aa71acc7fa5b --- /dev/null +++ b/Documentation/devicetree/bindings/net/fsl,fman-muram.yaml @@ -0,0 +1,40 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/fsl,fman-muram.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Freescale Frame Manager MURAM Device + +maintainers: + - Frank Li <[email protected]> + +description: | + FMan Internal memory - shared between all the FMan modules. + It contains data structures that are common and written to or read by + the modules. + + FMan internal memory is split into the following parts: + Packet buffering (Tx/Rx FIFOs) + Frames internal context + +properties: + compatible: + enum: + - fsl,fman-muram + + reg: + maxItems: 1 + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + muram@0 { + compatible = "fsl,fman-muram"; + reg = <0x0 0x28000>; + }; diff --git a/Documentation/devicetree/bindings/net/fsl,fman-port.yaml b/Documentation/devicetree/bindings/net/fsl,fman-port.yaml new file mode 100644 index 000000000000..9de445307830 --- /dev/null +++ b/Documentation/devicetree/bindings/net/fsl,fman-port.yaml @@ -0,0 +1,75 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/fsl,fman-port.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Freescale Frame Manager Port Device + +maintainers: + - Frank Li <[email protected]> + +description: | + The Frame Manager (FMan) supports several types of hardware ports: + Ethernet receiver (RX) + Ethernet transmitter (TX) + Offline/Host command (O/H) + +properties: + compatible: + enum: + - fsl,fman-v2-port-oh + - fsl,fman-v2-port-rx + - fsl,fman-v2-port-tx + - fsl,fman-v3-port-oh + - fsl,fman-v3-port-rx + - fsl,fman-v3-port-tx + + cell-index: + $ref: /schemas/types.yaml#/definitions/uint32 + description: + Specifies the hardware port id. + Each hardware port on the FMan has its own hardware PortID. + Super set of all hardware Port IDs available at FMan Reference + Manual under "FMan Hardware Ports in Freescale Devices" table. + + Each hardware port is assigned a 4KB, port-specific page in + the FMan hardware port memory region (which is part of the + FMan memory map). The first 4 KB in the FMan hardware ports + memory region is used for what are called common registers. + The subsequent 63 4KB pages are allocated to the hardware + ports. + The page of a specific port is determined by the cell-index. + + reg: + items: + - description: There is one reg region describing the port + configuration registers. + + fsl,fman-10g-port: + $ref: /schemas/types.yaml#/definitions/flag + description: The default port rate is 1G. + If this property exists, the port is s 10G port. + + fsl,fman-best-effort-port: + $ref: /schemas/types.yaml#/definitions/flag + description: The default port rate is 1G. + Can be defined only if 10G-support is set. + This property marks a best-effort 10G port (10G port that + may not be capable of line rate). + +required: + - compatible + - reg + - cell-index + +additionalProperties: false + +examples: + - | + port@a8000 { + compatible = "fsl,fman-v2-port-tx"; + reg = <0xa8000 0x1000>; + cell-index = <0x28>; + }; + diff --git a/Documentation/devicetree/bindings/net/fsl,fman.yaml b/Documentation/devicetree/bindings/net/fsl,fman.yaml new file mode 100644 index 000000000000..7908f67413de --- /dev/null +++ b/Documentation/devicetree/bindings/net/fsl,fman.yaml @@ -0,0 +1,204 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/fsl,fman.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Freescale Frame Manager Device + +maintainers: + - Frank Li <[email protected]> + +description: + Due to the fact that the FMan is an aggregation of sub-engines (ports, MACs, + etc.) the FMan node will have child nodes for each of them. + +properties: + compatible: + enum: + - fsl,fman + description: + FMan version can be determined via FM_IP_REV_1 register in the + FMan block. The offset is 0xc4 from the beginning of the + Frame Processing Manager memory map (0xc3000 from the + beginning of the FMan node). + + cell-index: + $ref: /schemas/types.yaml#/definitions/uint32 + description: | + Specifies the index of the FMan unit. + + The cell-index value may be used by the SoC, to identify the + FMan unit in the SoC memory map. In the table below, + there's a description of the cell-index use in each SoC: + + - P1023: + register[bit] FMan unit cell-index + ============================================================ + DEVDISR[1] 1 0 + + - P2041, P3041, P4080 P5020, P5040: + register[bit] FMan unit cell-index + ============================================================ + DCFG_DEVDISR2[6] 1 0 + DCFG_DEVDISR2[14] 2 1 + (Second FM available only in P4080 and P5040) + + - B4860, T1040, T2080, T4240: + register[bit] FMan unit cell-index + ============================================================ + DCFG_CCSR_DEVDISR2[24] 1 0 + DCFG_CCSR_DEVDISR2[25] 2 1 + (Second FM available only in T4240) + + DEVDISR, DCFG_DEVDISR2 and DCFG_CCSR_DEVDISR2 are located in + the specific SoC "Device Configuration/Pin Control" Memory + Map. + + reg: + items: + - description: BMI configuration registers. + - description: QMI configuration registers. + - description: DMA configuration registers. + - description: FPM configuration registers. + - description: FMan controller configuration registers. + minItems: 1 + + ranges: true + + clocks: + maxItems: 1 + + clock-names: + items: + - const: fmanclk + + interrupts: + items: + - description: The first element is associated with the event interrupts. + - description: the second element is associated with the error interrupts. + + fsl,qman-channel-range: + $ref: /schemas/types.yaml#/definitions/uint32-array + description: + Specifies the range of the available dedicated + channels in the FMan. The first cell specifies the beginning + of the range and the second cell specifies the number of + channels + items: + - description: The first cell specifies the beginning of the range. + - description: | + The second cell specifies the number of channels. + Further information available at: + "Work Queue (WQ) Channel Assignments in the QMan" section + in DPAA Reference Manual. + + fsl,qman: + $ref: /schemas/types.yaml#/definitions/phandle + description: See soc/fsl/qman.txt + + fsl,bman: + $ref: /schemas/types.yaml#/definitions/phandle + description: See soc/fsl/bman.txt + + fsl,erratum-a050385: + $ref: /schemas/types.yaml#/definitions/flag + description: A boolean property. Indicates the presence of the + erratum A050385 which indicates that DMA transactions that are + split can result in a FMan lock. + + '#address-cells': + const: 1 + + '#size-cells': + const: 1 + +patternProperties: + '^muram@[a-f0-9]+$': + $ref: fsl,fman-muram.yaml + + '^port@[a-f0-9]+$': + $ref: fsl,fman-port.yaml + + '^ethernet@[a-f0-9]+$': + $ref: fsl,fman-dtsec.yaml + + '^mdio@[a-f0-9]+$': + $ref: fsl,fman-mdio.yaml + + '^phc@[a-f0-9]+$': + $ref: /schemas/ptp/fsl,ptp.yaml + +required: + - compatible + - cell-index + - reg + - ranges + - clocks + - clock-names + - interrupts + - fsl,qman-channel-range + +additionalProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/irq.h> + + fman@400000 { + compatible = "fsl,fman"; + reg = <0x400000 0x100000>; + ranges = <0 0x400000 0x100000>; + #address-cells = <1>; + #size-cells = <1>; + cell-index = <1>; + clocks = <&fman_clk>; + clock-names = "fmanclk"; + interrupts = <96 IRQ_TYPE_EDGE_FALLING>, + <16 IRQ_TYPE_EDGE_FALLING>; + fsl,qman-channel-range = <0x40 0xc>; + + muram@0 { + compatible = "fsl,fman-muram"; + reg = <0x0 0x28000>; + }; + + port@81000 { + cell-index = <1>; + compatible = "fsl,fman-v2-port-oh"; + reg = <0x81000 0x1000>; + }; + + fman1_rx_0x8: port@88000 { + cell-index = <0x8>; + compatible = "fsl,fman-v2-port-rx"; + reg = <0x88000 0x1000>; + }; + + fman1_tx_0x28: port@a8000 { + cell-index = <0x28>; + compatible = "fsl,fman-v2-port-tx"; + reg = <0xa8000 0x1000>; + }; + + ethernet@e0000 { + compatible = "fsl,fman-dtsec"; + cell-index = <0>; + reg = <0xe0000 0x1000>; + ptp-timer = <&ptp_timer>; + fsl,fman-ports = <&fman1_rx_0x8 &fman1_tx_0x28>; + tbi-handle = <&tbi5>; + }; + + ptp_timer: phc@fe000 { + compatible = "fsl,fman-ptp-timer"; + reg = <0xfe000 0x1000>; + interrupts = <12 IRQ_TYPE_LEVEL_LOW>; + }; + + mdio@f1000 { + compatible = "fsl,fman-xmdio"; + reg = <0xf1000 0x1000>; + interrupts = <101 IRQ_TYPE_EDGE_FALLING>; + }; + }; diff --git a/Documentation/devicetree/bindings/net/fsl-fman.txt b/Documentation/devicetree/bindings/net/fsl-fman.txt deleted file mode 100644 index bda4b41af074..000000000000 --- a/Documentation/devicetree/bindings/net/fsl-fman.txt +++ /dev/null @@ -1,548 +0,0 @@ -============================================================================= -Freescale Frame Manager Device Bindings - -CONTENTS - - FMan Node - - FMan Port Node - - FMan MURAM Node - - FMan dTSEC/XGEC/mEMAC Node - - FMan IEEE 1588 Node - - FMan MDIO Node - - Example - -============================================================================= -FMan Node - -DESCRIPTION - -Due to the fact that the FMan is an aggregation of sub-engines (ports, MACs, -etc.) the FMan node will have child nodes for each of them. - -PROPERTIES - -- compatible - Usage: required - Value type: <stringlist> - Definition: Must include "fsl,fman" - FMan version can be determined via FM_IP_REV_1 register in the - FMan block. The offset is 0xc4 from the beginning of the - Frame Processing Manager memory map (0xc3000 from the - beginning of the FMan node). - -- cell-index - Usage: required - Value type: <u32> - Definition: Specifies the index of the FMan unit. - - The cell-index value may be used by the SoC, to identify the - FMan unit in the SoC memory map. In the table below, - there's a description of the cell-index use in each SoC: - - - P1023: - register[bit] FMan unit cell-index - ============================================================ - DEVDISR[1] 1 0 - - - P2041, P3041, P4080 P5020, P5040: - register[bit] FMan unit cell-index - ============================================================ - DCFG_DEVDISR2[6] 1 0 - DCFG_DEVDISR2[14] 2 1 - (Second FM available only in P4080 and P5040) - - - B4860, T1040, T2080, T4240: - register[bit] FMan unit cell-index - ============================================================ - DCFG_CCSR_DEVDISR2[24] 1 0 - DCFG_CCSR_DEVDISR2[25] 2 1 - (Second FM available only in T4240) - - DEVDISR, DCFG_DEVDISR2 and DCFG_CCSR_DEVDISR2 are located in - the specific SoC "Device Configuration/Pin Control" Memory - Map. - -- reg - Usage: required - Value type: <prop-encoded-array> - Definition: A standard property. Specifies the offset of the - following configuration registers: - - BMI configuration registers. - - QMI configuration registers. - - DMA configuration registers. - - FPM configuration registers. - - FMan controller configuration registers. - -- ranges - Usage: required - Value type: <prop-encoded-array> - Definition: A standard property. - -- clocks - Usage: required - Value type: <prop-encoded-array> - Definition: phandle for the fman input clock. - -- clock-names - usage: required - Value type: <stringlist> - Definition: "fmanclk" for the fman input clock. - -- interrupts - Usage: required - Value type: <prop-encoded-array> - Definition: A pair of IRQs are specified in this property. - The first element is associated with the event interrupts and - the second element is associated with the error interrupts. - -- fsl,qman-channel-range - Usage: required - Value type: <prop-encoded-array> - Definition: Specifies the range of the available dedicated - channels in the FMan. The first cell specifies the beginning - of the range and the second cell specifies the number of - channels. - Further information available at: - "Work Queue (WQ) Channel Assignments in the QMan" section - in DPAA Reference Manual. - -- fsl,qman -- fsl,bman - Usage: required - Definition: See soc/fsl/qman.txt and soc/fsl/bman.txt - -- fsl,erratum-a050385 - Usage: optional - Value type: boolean - Definition: A boolean property. Indicates the presence of the - erratum A050385 which indicates that DMA transactions that are - split can result in a FMan lock. - -============================================================================= -FMan MURAM Node - -DESCRIPTION - -FMan Internal memory - shared between all the FMan modules. -It contains data structures that are common and written to or read by -the modules. -FMan internal memory is split into the following parts: - Packet buffering (Tx/Rx FIFOs) - Frames internal context - -PROPERTIES - -- compatible - Usage: required - Value type: <stringlist> - Definition: Must include "fsl,fman-muram" - -- ranges - Usage: required - Value type: <prop-encoded-array> - Definition: A standard property. - Specifies the multi-user memory offset and the size within - the FMan. - -EXAMPLE - -muram@0 { - compatible = "fsl,fman-muram"; - ranges = <0 0x000000 0x28000>; -}; - -============================================================================= -FMan Port Node - -DESCRIPTION - -The Frame Manager (FMan) supports several types of hardware ports: - Ethernet receiver (RX) - Ethernet transmitter (TX) - Offline/Host command (O/H) - -PROPERTIES - -- compatible - Usage: required - Value type: <stringlist> - Definition: A standard property. - Must include one of the following: - - "fsl,fman-v2-port-oh" for FManV2 OH ports - - "fsl,fman-v2-port-rx" for FManV2 RX ports - - "fsl,fman-v2-port-tx" for FManV2 TX ports - - "fsl,fman-v3-port-oh" for FManV3 OH ports - - "fsl,fman-v3-port-rx" for FManV3 RX ports - - "fsl,fman-v3-port-tx" for FManV3 TX ports - -- cell-index - Usage: required - Value type: <u32> - Definition: Specifies the hardware port id. - Each hardware port on the FMan has its own hardware PortID. - Super set of all hardware Port IDs available at FMan Reference - Manual under "FMan Hardware Ports in Freescale Devices" table. - - Each hardware port is assigned a 4KB, port-specific page in - the FMan hardware port memory region (which is part of the - FMan memory map). The first 4 KB in the FMan hardware ports - memory region is used for what are called common registers. - The subsequent 63 4KB pages are allocated to the hardware - ports. - The page of a specific port is determined by the cell-index. - -- reg - Usage: required - Value type: <prop-encoded-array> - Definition: There is one reg region describing the port - configuration registers. - -- fsl,fman-10g-port - Usage: optional - Value type: boolean - Definition: The default port rate is 1G. - If this property exists, the port is s 10G port. - -- fsl,fman-best-effort-port - Usage: optional - Value type: boolean - Definition: Can be defined only if 10G-support is set. - This property marks a best-effort 10G port (10G port that - may not be capable of line rate). - -EXAMPLE - -port@a8000 { - cell-index = <0x28>; - compatible = "fsl,fman-v2-port-tx"; - reg = <0xa8000 0x1000>; -}; - -port@88000 { - cell-index = <0x8>; - compatible = "fsl,fman-v2-port-rx"; - reg = <0x88000 0x1000>; -}; - -port@81000 { - cell-index = <0x1>; - compatible = "fsl,fman-v2-port-oh"; - reg = <0x81000 0x1000>; -}; - -============================================================================= -FMan dTSEC/XGEC/mEMAC Node - -Refer to Documentation/devicetree/bindings/net/fsl,fman-dtsec.yaml - -============================================================================ -FMan IEEE 1588 Node - -Refer to Documentation/devicetree/bindings/ptp/ptp-qoriq.txt - -============================================================================= -FMan MDIO Node - -DESCRIPTION - -The MDIO is a bus to which the PHY devices are connected. - -PROPERTIES - -- compatible - Usage: required - Value type: <stringlist> - Definition: A standard property. - Must include "fsl,fman-mdio" for 1 Gb/s MDIO from FMan v2. - Must include "fsl,fman-xmdio" for 10 Gb/s MDIO from FMan v2. - Must include "fsl,fman-memac-mdio" for 1/10 Gb/s MDIO from - FMan v3. - -- reg - Usage: required - Value type: <prop-encoded-array> - Definition: A standard property. - -- clocks - Usage: optional - Value type: <phandle> - Definition: A reference to the input clock of the controller - from which the MDC frequency is derived. - -- clock-frequency - Usage: optional - Value type: <u32> - Definition: Specifies the external MDC frequency, in Hertz, to - be used. Requires that the input clock is specified in the - "clocks" property. See also: mdio.yaml. - -- suppress-preamble - Usage: optional - Value type: <boolean> - Definition: Disable generation of preamble bits. See also: - mdio.yaml. - -- interrupts - Usage: required for external MDIO - Value type: <prop-encoded-array> - Definition: Event interrupt of external MDIO controller. - -- fsl,fman-internal-mdio - Usage: required for internal MDIO - Value type: boolean - Definition: Fman has internal MDIO for internal PCS(Physical - Coding Sublayer) PHYs and external MDIO for external PHYs. - The settings and programming routines for internal/external - MDIO are different. Must be included for internal MDIO. - -- fsl,erratum-a009885 - Usage: optional - Value type: <boolean> - Definition: Indicates the presence of the A009885 - erratum describing that the contents of MDIO_DATA may - become corrupt unless it is read within 16 MDC cycles - of MDIO_CFG[BSY] being cleared, when performing an - MDIO read operation. - -- fsl,erratum-a011043 - Usage: optional - Value type: <boolean> - Definition: Indicates the presence of the A011043 erratum - describing that the MDIO_CFG[MDIO_RD_ER] bit may be falsely - set when reading internal PCS registers. MDIO reads to - internal PCS registers may result in having the - MDIO_CFG[MDIO_RD_ER] bit set, even when there is no error and - read data (MDIO_DATA[MDIO_DATA]) is correct. - Software may get false read error when reading internal - PCS registers through MDIO. As a workaround, all internal - MDIO accesses should ignore the MDIO_CFG[MDIO_RD_ER] bit. - -For internal PHY device on internal mdio bus, a PHY node should be created. -See the definition of the PHY node in booting-without-of.txt for an -example of how to define a PHY (Internal PHY has no interrupt line). -- For "fsl,fman-mdio" compatible internal mdio bus, the PHY is TBI PHY. -- For "fsl,fman-memac-mdio" compatible internal mdio bus, the PHY is PCS PHY. - The PCS PHY address should correspond to the value of the appropriate - MDEV_PORT. - -EXAMPLE - -Example for FMan v2 external MDIO: - -mdio@f1000 { - compatible = "fsl,fman-xmdio"; - reg = <0xf1000 0x1000>; - interrupts = <101 2 0 0>; -}; - -Example for FMan v2 internal MDIO: - -mdio@e3120 { - compatible = "fsl,fman-mdio"; - reg = <0xe3120 0xee0>; - fsl,fman-internal-mdio; - - tbi1: tbi-phy@8 { - reg = <0x8>; - device_type = "tbi-phy"; - }; -}; - -Example for FMan v3 internal MDIO: - -mdio@f1000 { - compatible = "fsl,fman-memac-mdio"; - reg = <0xf1000 0x1000>; - fsl,fman-internal-mdio; - - pcsphy6: ethernet-phy@0 { - reg = <0x0>; - }; -}; - -============================================================================= -Example - -fman@400000 { - #address-cells = <1>; - #size-cells = <1>; - cell-index = <1>; - compatible = "fsl,fman" - ranges = <0 0x400000 0x100000>; - reg = <0x400000 0x100000>; - clocks = <&fman_clk>; - clock-names = "fmanclk"; - interrupts = < - 96 2 0 0 - 16 2 1 1>; - fsl,qman-channel-range = <0x40 0xc>; - - muram@0 { - compatible = "fsl,fman-muram"; - reg = <0x0 0x28000>; - }; - - port@81000 { - cell-index = <1>; - compatible = "fsl,fman-v2-port-oh"; - reg = <0x81000 0x1000>; - }; - - port@82000 { - cell-index = <2>; - compatible = "fsl,fman-v2-port-oh"; - reg = <0x82000 0x1000>; - }; - - port@83000 { - cell-index = <3>; - compatible = "fsl,fman-v2-port-oh"; - reg = <0x83000 0x1000>; - }; - - port@84000 { - cell-index = <4>; - compatible = "fsl,fman-v2-port-oh"; - reg = <0x84000 0x1000>; - }; - - port@85000 { - cell-index = <5>; - compatible = "fsl,fman-v2-port-oh"; - reg = <0x85000 0x1000>; - }; - - port@86000 { - cell-index = <6>; - compatible = "fsl,fman-v2-port-oh"; - reg = <0x86000 0x1000>; - }; - - fman1_rx_0x8: port@88000 { - cell-index = <0x8>; - compatible = "fsl,fman-v2-port-rx"; - reg = <0x88000 0x1000>; - }; - - fman1_rx_0x9: port@89000 { - cell-index = <0x9>; - compatible = "fsl,fman-v2-port-rx"; - reg = <0x89000 0x1000>; - }; - - fman1_rx_0xa: port@8a000 { - cell-index = <0xa>; - compatible = "fsl,fman-v2-port-rx"; - reg = <0x8a000 0x1000>; - }; - - fman1_rx_0xb: port@8b000 { - cell-index = <0xb>; - compatible = "fsl,fman-v2-port-rx"; - reg = <0x8b000 0x1000>; - }; - - fman1_rx_0xc: port@8c000 { - cell-index = <0xc>; - compatible = "fsl,fman-v2-port-rx"; - reg = <0x8c000 0x1000>; - }; - - fman1_rx_0x10: port@90000 { - cell-index = <0x10>; - compatible = "fsl,fman-v2-port-rx"; - reg = <0x90000 0x1000>; - }; - - fman1_tx_0x28: port@a8000 { - cell-index = <0x28>; - compatible = "fsl,fman-v2-port-tx"; - reg = <0xa8000 0x1000>; - }; - - fman1_tx_0x29: port@a9000 { - cell-index = <0x29>; - compatible = "fsl,fman-v2-port-tx"; - reg = <0xa9000 0x1000>; - }; - - fman1_tx_0x2a: port@aa000 { - cell-index = <0x2a>; - compatible = "fsl,fman-v2-port-tx"; - reg = <0xaa000 0x1000>; - }; - - fman1_tx_0x2b: port@ab000 { - cell-index = <0x2b>; - compatible = "fsl,fman-v2-port-tx"; - reg = <0xab000 0x1000>; - }; - - fman1_tx_0x2c: port@ac0000 { - cell-index = <0x2c>; - compatible = "fsl,fman-v2-port-tx"; - reg = <0xac000 0x1000>; - }; - - fman1_tx_0x30: port@b0000 { - cell-index = <0x30>; - compatible = "fsl,fman-v2-port-tx"; - reg = <0xb0000 0x1000>; - }; - - ethernet@e0000 { - compatible = "fsl,fman-dtsec"; - cell-index = <0>; - reg = <0xe0000 0x1000>; - fsl,fman-ports = <&fman1_rx_0x8 &fman1_tx_0x28>; - tbi-handle = <&tbi5>; - }; - - ethernet@e2000 { - compatible = "fsl,fman-dtsec"; - cell-index = <1>; - reg = <0xe2000 0x1000>; - fsl,fman-ports = <&fman1_rx_0x9 &fman1_tx_0x29>; - tbi-handle = <&tbi6>; - }; - - ethernet@e4000 { - compatible = "fsl,fman-dtsec"; - cell-index = <2>; - reg = <0xe4000 0x1000>; - fsl,fman-ports = <&fman1_rx_0xa &fman1_tx_0x2a>; - tbi-handle = <&tbi7>; - }; - - ethernet@e6000 { - compatible = "fsl,fman-dtsec"; - cell-index = <3>; - reg = <0xe6000 0x1000>; - fsl,fman-ports = <&fman1_rx_0xb &fman1_tx_0x2b>; - tbi-handle = <&tbi8>; - }; - - ethernet@e8000 { - compatible = "fsl,fman-dtsec"; - cell-index = <4>; - reg = <0xf0000 0x1000>; - fsl,fman-ports = <&fman1_rx_0xc &fman1_tx_0x2c>; - tbi-handle = <&tbi9>; - - ethernet@f0000 { - cell-index = <8>; - compatible = "fsl,fman-xgec"; - reg = <0xf0000 0x1000>; - fsl,fman-ports = <&fman1_rx_0x10 &fman1_tx_0x30>; - }; - - ptp-timer@fe000 { - compatible = "fsl,fman-ptp-timer"; - reg = <0xfe000 0x1000>; - }; - - mdio@f1000 { - compatible = "fsl,fman-xmdio"; - reg = <0xf1000 0x1000>; - interrupts = <101 2 0 0>; - }; -}; diff --git a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt index 047bdf7bdd2f..9c9668c1b6a2 100644 --- a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt +++ b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt @@ -86,4 +86,4 @@ Example: * Gianfar PTP clock nodes -Refer to Documentation/devicetree/bindings/ptp/ptp-qoriq.txt +Refer to Documentation/devicetree/bindings/ptp/fsl,ptp.yaml diff --git a/Documentation/devicetree/bindings/net/mscc,miim.yaml b/Documentation/devicetree/bindings/net/mscc,miim.yaml index 5b292e7c9e46..792f26b06b06 100644 --- a/Documentation/devicetree/bindings/net/mscc,miim.yaml +++ b/Documentation/devicetree/bindings/net/mscc,miim.yaml @@ -38,6 +38,16 @@ properties: clock-frequency: true + resets: + items: + - description: + Reset shared with all blocks attached to the Switch Core Register + Bus (CSR) including VRAP slave. + + reset-names: + items: + - const: switch + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/net/stm32-dwmac.yaml b/Documentation/devicetree/bindings/net/stm32-dwmac.yaml index 7ccf75676b6d..bf23838fe6e8 100644 --- a/Documentation/devicetree/bindings/net/stm32-dwmac.yaml +++ b/Documentation/devicetree/bindings/net/stm32-dwmac.yaml @@ -22,18 +22,22 @@ select: enum: - st,stm32-dwmac - st,stm32mp1-dwmac + - st,stm32mp13-dwmac + - st,stm32mp25-dwmac required: - compatible -allOf: - - $ref: snps,dwmac.yaml# - properties: compatible: oneOf: - items: - enum: + - st,stm32mp25-dwmac + - const: snps,dwmac-5.20 + - items: + - enum: - st,stm32mp1-dwmac + - st,stm32mp13-dwmac - const: snps,dwmac-4.20a - items: - enum: @@ -75,12 +79,15 @@ properties: st,syscon: $ref: /schemas/types.yaml#/definitions/phandle-array items: - - items: + - minItems: 2 + items: - description: phandle to the syscon node which encompases the glue register - description: offset of the control register + - description: field to set mask in register description: Should be phandle/offset pair. The phandle to the syscon node which - encompases the glue register, and the offset of the control register + encompases the glue register, the offset of the control register and + the mask to set bitfield in control register st,ext-phyclk: description: @@ -112,12 +119,40 @@ required: unevaluatedProperties: false +allOf: + - $ref: snps,dwmac.yaml# + - if: + properties: + compatible: + contains: + enum: + - st,stm32-dwmac + - st,stm32mp1-dwmac + - st,stm32mp25-dwmac + then: + properties: + st,syscon: + items: + minItems: 2 + maxItems: 2 + + - if: + properties: + compatible: + contains: + enum: + - st,stm32mp13-dwmac + then: + properties: + st,syscon: + items: + minItems: 3 + maxItems: 3 + examples: - | #include <dt-bindings/interrupt-controller/arm-gic.h> #include <dt-bindings/clock/stm32mp1-clks.h> - #include <dt-bindings/reset/stm32mp1-resets.h> - #include <dt-bindings/mfd/stm32h7-rcc.h> //Example 1 ethernet0: ethernet@5800a000 { compatible = "st,stm32mp1-dwmac", "snps,dwmac-4.20a"; diff --git a/Documentation/devicetree/bindings/net/ti,icss-iep.yaml b/Documentation/devicetree/bindings/net/ti,icss-iep.yaml index f5c22d6dcaee..e36e3a622904 100644 --- a/Documentation/devicetree/bindings/net/ti,icss-iep.yaml +++ b/Documentation/devicetree/bindings/net/ti,icss-iep.yaml @@ -28,6 +28,15 @@ properties: maxItems: 1 description: phandle to the IEP source clock + interrupts: + maxItems: 1 + description: + Interrupt specifier for capture/compare IRQ. + + interrupt-names: + items: + - const: iep_cap_cmp + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml index 50846a2d09c8..0bf2d9f093b5 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml @@ -29,7 +29,6 @@ properties: - qcom,pm7325-gpio - qcom,pm7550ba-gpio - qcom,pm8005-gpio - - qcom,pm8008-gpio - qcom,pm8018-gpio - qcom,pm8019-gpio - qcom,pm8038-gpio @@ -126,7 +125,6 @@ allOf: compatible: contains: enum: - - qcom,pm8008-gpio - qcom,pmi8950-gpio - qcom,pmr735d-gpio then: @@ -448,7 +446,6 @@ $defs: - gpio1-gpio10 for pm7325 - gpio1-gpio8 for pm7550ba - gpio1-gpio4 for pm8005 - - gpio1-gpio2 for pm8008 - gpio1-gpio6 for pm8018 - gpio1-gpio12 for pm8038 - gpio1-gpio40 for pm8058 diff --git a/Documentation/devicetree/bindings/ptp/fsl,ptp.yaml b/Documentation/devicetree/bindings/ptp/fsl,ptp.yaml new file mode 100644 index 000000000000..3bb8615e3e91 --- /dev/null +++ b/Documentation/devicetree/bindings/ptp/fsl,ptp.yaml @@ -0,0 +1,144 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/ptp/fsl,ptp.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Freescale QorIQ 1588 timer based PTP clock + +maintainers: + - Frank Li <[email protected]> + +properties: + compatible: + enum: + - fsl,etsec-ptp + - fsl,fman-ptp-timer + - fsl,dpaa2-ptp + - fsl,enetc-ptp + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 1 + + fsl,cksel: + $ref: /schemas/types.yaml#/definitions/uint32 + description: | + Timer reference clock source. + + Reference clock source is determined by the value, which is holded + in CKSEL bits in TMR_CTRL register. "fsl,cksel" property keeps the + value, which will be directly written in those bits, that is why, + according to reference manual, the next clock sources can be used: + + For eTSEC, + <0> - external high precision timer reference clock (TSEC_TMR_CLK + input is used for this purpose); + <1> - eTSEC system clock; + <2> - eTSEC1 transmit clock; + <3> - RTC clock input. + + For DPAA FMan, + <0> - external high precision timer reference clock (TMR_1588_CLK) + <1> - MAC system clock (1/2 FMan clock) + <2> - reserved + <3> - RTC clock oscillator + + fsl,tclk-period: + $ref: /schemas/types.yaml#/definitions/uint32 + description: Timer reference clock period in nanoseconds. + + fsl,tmr-prsc: + $ref: /schemas/types.yaml#/definitions/uint32 + description: Prescaler, divides the output clock. + + fsl,tmr-add: + $ref: /schemas/types.yaml#/definitions/uint32 + description: Frequency compensation value. + + fsl,tmr-fiper1: + $ref: /schemas/types.yaml#/definitions/uint32 + description: Fixed interval period pulse generator. + + fsl,tmr-fiper2: + $ref: /schemas/types.yaml#/definitions/uint32 + description: Fixed interval period pulse generator. + + fsl,tmr-fiper3: + $ref: /schemas/types.yaml#/definitions/uint32 + description: + Fixed interval period pulse generator. + Supported only on DPAA2 and ENETC hardware. + + fsl,max-adj: + $ref: /schemas/types.yaml#/definitions/uint32 + description: | + Maximum frequency adjustment in parts per billion. + + These properties set the operational parameters for the PTP + clock. You must choose these carefully for the clock to work right. + Here is how to figure good values: + + TimerOsc = selected reference clock MHz + tclk_period = desired clock period nanoseconds + NominalFreq = 1000 / tclk_period MHz + FreqDivRatio = TimerOsc / NominalFreq (must be greater that 1.0) + tmr_add = ceil(2^32 / FreqDivRatio) + OutputClock = NominalFreq / tmr_prsc MHz + PulseWidth = 1 / OutputClock microseconds + FiperFreq1 = desired frequency in Hz + FiperDiv1 = 1000000 * OutputClock / FiperFreq1 + tmr_fiper1 = tmr_prsc * tclk_period * FiperDiv1 - tclk_period + max_adj = 1000000000 * (FreqDivRatio - 1.0) - 1 + + The calculation for tmr_fiper2 is the same as for tmr_fiper1. The + driver expects that tmr_fiper1 will be correctly set to produce a 1 + Pulse Per Second (PPS) signal, since this will be offered to the PPS + subsystem to synchronize the Linux clock. + + When this attribute is not used, the IEEE 1588 timer reference clock + will use the eTSEC system clock (for Gianfar) or the MAC system + clock (for DPAA). + + fsl,extts-fifo: + $ref: /schemas/types.yaml#/definitions/flag + description: + The presence of this property indicates hardware + support for the external trigger stamp FIFO + + little-endian: + $ref: /schemas/types.yaml#/definitions/flag + description: + The presence of this property indicates the 1588 timer + support for the external trigger stamp FIFO. + IP block is little-endian mode. The default endian mode + is big-endian. + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/irq.h> + + phc@24e00 { + compatible = "fsl,etsec-ptp"; + reg = <0x24e00 0xb0>; + interrupts = <12 IRQ_TYPE_LEVEL_LOW>; + interrupt-parent = <&ipic>; + fsl,cksel = <1>; + fsl,tclk-period = <10>; + fsl,tmr-prsc = <100>; + fsl,tmr-add = <0x999999a4>; + fsl,tmr-fiper1 = <0x3b9ac9f6>; + fsl,tmr-fiper2 = <0x00018696>; + fsl,max-adj = <659999998>; + }; diff --git a/Documentation/devicetree/bindings/ptp/ptp-qoriq.txt b/Documentation/devicetree/bindings/ptp/ptp-qoriq.txt deleted file mode 100644 index 743eda754e65..000000000000 --- a/Documentation/devicetree/bindings/ptp/ptp-qoriq.txt +++ /dev/null @@ -1,87 +0,0 @@ -* Freescale QorIQ 1588 timer based PTP clock - -General Properties: - - - compatible Should be "fsl,etsec-ptp" for eTSEC - Should be "fsl,fman-ptp-timer" for DPAA FMan - Should be "fsl,dpaa2-ptp" for DPAA2 - Should be "fsl,enetc-ptp" for ENETC - - reg Offset and length of the register set for the device - - interrupts There should be at least two interrupts. Some devices - have as many as four PTP related interrupts. - -Clock Properties: - - - fsl,cksel Timer reference clock source. - - fsl,tclk-period Timer reference clock period in nanoseconds. - - fsl,tmr-prsc Prescaler, divides the output clock. - - fsl,tmr-add Frequency compensation value. - - fsl,tmr-fiper1 Fixed interval period pulse generator. - - fsl,tmr-fiper2 Fixed interval period pulse generator. - - fsl,tmr-fiper3 Fixed interval period pulse generator. - Supported only on DPAA2 and ENETC hardware. - - fsl,max-adj Maximum frequency adjustment in parts per billion. - - fsl,extts-fifo The presence of this property indicates hardware - support for the external trigger stamp FIFO. - - little-endian The presence of this property indicates the 1588 timer - IP block is little-endian mode. The default endian mode - is big-endian. - - These properties set the operational parameters for the PTP - clock. You must choose these carefully for the clock to work right. - Here is how to figure good values: - - TimerOsc = selected reference clock MHz - tclk_period = desired clock period nanoseconds - NominalFreq = 1000 / tclk_period MHz - FreqDivRatio = TimerOsc / NominalFreq (must be greater that 1.0) - tmr_add = ceil(2^32 / FreqDivRatio) - OutputClock = NominalFreq / tmr_prsc MHz - PulseWidth = 1 / OutputClock microseconds - FiperFreq1 = desired frequency in Hz - FiperDiv1 = 1000000 * OutputClock / FiperFreq1 - tmr_fiper1 = tmr_prsc * tclk_period * FiperDiv1 - tclk_period - max_adj = 1000000000 * (FreqDivRatio - 1.0) - 1 - - The calculation for tmr_fiper2 is the same as for tmr_fiper1. The - driver expects that tmr_fiper1 will be correctly set to produce a 1 - Pulse Per Second (PPS) signal, since this will be offered to the PPS - subsystem to synchronize the Linux clock. - - Reference clock source is determined by the value, which is holded - in CKSEL bits in TMR_CTRL register. "fsl,cksel" property keeps the - value, which will be directly written in those bits, that is why, - according to reference manual, the next clock sources can be used: - - For eTSEC, - <0> - external high precision timer reference clock (TSEC_TMR_CLK - input is used for this purpose); - <1> - eTSEC system clock; - <2> - eTSEC1 transmit clock; - <3> - RTC clock input. - - For DPAA FMan, - <0> - external high precision timer reference clock (TMR_1588_CLK) - <1> - MAC system clock (1/2 FMan clock) - <2> - reserved - <3> - RTC clock oscillator - - When this attribute is not used, the IEEE 1588 timer reference clock - will use the eTSEC system clock (for Gianfar) or the MAC system - clock (for DPAA). - -Example: - - ptp_clock@24e00 { - compatible = "fsl,etsec-ptp"; - reg = <0x24E00 0xB0>; - interrupts = <12 0x8 13 0x8>; - interrupt-parent = < &ipic >; - fsl,cksel = <1>; - fsl,tclk-period = <10>; - fsl,tmr-prsc = <100>; - fsl,tmr-add = <0x999999A4>; - fsl,tmr-fiper1 = <0x3B9AC9F6>; - fsl,tmr-fiper2 = <0x00018696>; - fsl,max-adj = <659999998>; - }; diff --git a/Documentation/devicetree/bindings/usb/realtek,rts5411.yaml b/Documentation/devicetree/bindings/usb/realtek,rts5411.yaml index 0874fc21f66f..6577a61cc075 100644 --- a/Documentation/devicetree/bindings/usb/realtek,rts5411.yaml +++ b/Documentation/devicetree/bindings/usb/realtek,rts5411.yaml @@ -65,6 +65,7 @@ patternProperties: description: The hard wired USB devices type: object $ref: /schemas/usb/usb-device.yaml + additionalProperties: true required: - peer-hub diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 7c3a565ffbef..82d142de3461 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -571,6 +571,7 @@ encoded manner. The codes are the following: um userfaultfd missing tracking uw userfaultfd wr-protect tracking ss shadow stack page + sl sealed == ======================================= Note that there is no guarantee that every flag and associated mnemonic will diff --git a/Documentation/i2c/i2c_bus.svg b/Documentation/i2c/i2c_bus.svg index 3170de976373..45801de4af7d 100644 --- a/Documentation/i2c/i2c_bus.svg +++ b/Documentation/i2c/i2c_bus.svg @@ -1,5 +1,6 @@ <?xml version="1.0" encoding="UTF-8" standalone="no"?> <!-- Created with Inkscape (http://www.inkscape.org/) --> +<!-- Updated to inclusive terminology by Wolfram Sang --> <svg xmlns:dc="http://purl.org/dc/elements/1.1/" @@ -1120,7 +1121,7 @@ <rect style="opacity:1;fill:#ffb9b9;fill-opacity:1;stroke:#f00000;stroke-width:2.8125;stroke-linecap:round;stroke-linejoin:round;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1" id="rect4424-3-2-9-7" - width="112.5" + width="134.5" height="113.75008" x="112.5" y="471.11221" @@ -1133,15 +1134,15 @@ y="521.46259" id="text4349"><tspan sodipodi:role="line" - x="167.5354" + x="178.5354" y="521.46259" style="font-size:25px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle" id="tspan1273">I2C</tspan><tspan sodipodi:role="line" - x="167.5354" + x="178.5354" y="552.71259" style="font-size:25px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle" - id="tspan1285">Master</tspan></text> + id="tspan1285">Controller</tspan></text> <rect style="color:#000000;clip-rule:nonzero;display:inline;overflow:visible;visibility:visible;opacity:1;isolation:auto;mix-blend-mode:normal;color-interpolation:sRGB;color-interpolation-filters:linearRGB;solid-color:#000000;solid-opacity:1;fill:#b9ffb9;fill-opacity:1;fill-rule:nonzero;stroke:#006400;stroke-width:2.8125;stroke-linecap:round;stroke-linejoin:round;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;color-rendering:auto;image-rendering:auto;shape-rendering:auto;text-rendering:auto;enable-background:accumulate" id="rect4424-3-2-9-7-3-3-5-3" @@ -1171,7 +1172,7 @@ x="318.59131" y="552.08752" style="font-size:25.00000191px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:1px" - id="tspan1287">Slave</tspan></text> + id="tspan1287">Target</tspan></text> <path style="fill:none;fill-rule:evenodd;stroke:#000000;stroke-width:1.99968767;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1" d="m 112.49995,677.36223 c 712.50005,0 712.50005,0 712.50005,0" @@ -1233,7 +1234,7 @@ x="468.59131" y="552.08746" style="font-size:25.00000191px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:1px" - id="tspan1287-6">Slave</tspan></text> + id="tspan1287-6">Target</tspan></text> <rect style="color:#000000;clip-rule:nonzero;display:inline;overflow:visible;visibility:visible;opacity:1;isolation:auto;mix-blend-mode:normal;color-interpolation:sRGB;color-interpolation-filters:linearRGB;solid-color:#000000;solid-opacity:1;vector-effect:none;fill:#b9ffb9;fill-opacity:1;fill-rule:nonzero;stroke:#006400;stroke-width:2.8125;stroke-linecap:round;stroke-linejoin:round;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;color-rendering:auto;image-rendering:auto;shape-rendering:auto;text-rendering:auto;enable-background:accumulate" id="rect4424-3-2-9-7-3-3-5-3-1" @@ -1258,7 +1259,7 @@ x="618.59131" y="552.08746" style="font-size:25.00000191px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:1px" - id="tspan1287-9">Slave</tspan></text> + id="tspan1287-9">Target</tspan></text> <path style="fill:none;fill-rule:evenodd;stroke:#000000;stroke-width:1.99968743;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#DotM)" d="m 150,583.61221 v 93.75" diff --git a/Documentation/i2c/summary.rst b/Documentation/i2c/summary.rst index 786c618ba3be..579a1c7df200 100644 --- a/Documentation/i2c/summary.rst +++ b/Documentation/i2c/summary.rst @@ -3,29 +3,27 @@ Introduction to I2C and SMBus ============================= I²C (pronounce: I squared C and written I2C in the kernel documentation) is -a protocol developed by Philips. It is a slow two-wire protocol (variable -speed, up to 400 kHz), with a high speed extension (3.4 MHz). It provides +a protocol developed by Philips. It is a two-wire protocol with variable +speed (typically up to 400 kHz, high speed modes up to 5 MHz). It provides an inexpensive bus for connecting many types of devices with infrequent or -low bandwidth communications needs. I2C is widely used with embedded -systems. Some systems use variants that don't meet branding requirements, +low bandwidth communications needs. I2C is widely used with embedded +systems. Some systems use variants that don't meet branding requirements, and so are not advertised as being I2C but come under different names, e.g. TWI (Two Wire Interface), IIC. -The latest official I2C specification is the `"I2C-bus specification and user -manual" (UM10204) <https://www.nxp.com/webapp/Download?colCode=UM10204>`_ -published by NXP Semiconductors. However, you need to log-in to the site to -access the PDF. An older version of the specification (revision 6) is archived -`here <https://web.archive.org/web/20210813122132/https://www.nxp.com/docs/en/user-guide/UM10204.pdf>`_. +The latest official I2C specification is the `"I²C-bus specification and user +manual" (UM10204) <https://www.nxp.com/docs/en/user-guide/UM10204.pdf>`_ +published by NXP Semiconductors, version 7 as of this writing. SMBus (System Management Bus) is based on the I2C protocol, and is mostly -a subset of I2C protocols and signaling. Many I2C devices will work on an +a subset of I2C protocols and signaling. Many I2C devices will work on an SMBus, but some SMBus protocols add semantics beyond what is required to -achieve I2C branding. Modern PC mainboards rely on SMBus. The most common +achieve I2C branding. Modern PC mainboards rely on SMBus. The most common devices connected through SMBus are RAM modules configured using I2C EEPROMs, and hardware monitoring chips. Because the SMBus is mostly a subset of the generalized I2C bus, we can -use its protocols on many I2C systems. However, there are systems that don't +use its protocols on many I2C systems. However, there are systems that don't meet both SMBus and I2C electrical constraints; and others which can't implement all the common SMBus protocol semantics or messages. @@ -33,29 +31,52 @@ implement all the common SMBus protocol semantics or messages. Terminology =========== -Using the terminology from the official documentation, the I2C bus connects -one or more *master* chips and one or more *slave* chips. +The I2C bus connects one or more controller chips and one or more target chips. .. kernel-figure:: i2c_bus.svg - :alt: Simple I2C bus with one master and 3 slaves + :alt: Simple I2C bus with one controller and 3 targets Simple I2C bus -A **master** chip is a node that starts communications with slaves. In the -Linux kernel implementation it is called an **adapter** or bus. Adapter -drivers are in the ``drivers/i2c/busses/`` subdirectory. +A **controller** chip is a node that starts communications with targets. In the +Linux kernel implementation it is also called an "adapter" or "bus". Controller +drivers are usually in the ``drivers/i2c/busses/`` subdirectory. -An **algorithm** contains general code that can be used to implement a -whole class of I2C adapters. Each specific adapter driver either depends on -an algorithm driver in the ``drivers/i2c/algos/`` subdirectory, or includes -its own implementation. +An **algorithm** contains general code that can be used to implement a whole +class of I2C controllers. Each specific controller driver either depends on an +algorithm driver in the ``drivers/i2c/algos/`` subdirectory, or includes its +own implementation. -A **slave** chip is a node that responds to communications when addressed -by the master. In Linux it is called a **client**. Client drivers are kept -in a directory specific to the feature they provide, for example -``drivers/media/gpio/`` for GPIO expanders and ``drivers/media/i2c/`` for +A **target** chip is a node that responds to communications when addressed by a +controller. In the Linux kernel implementation it is also called a "client". +While targets are usually separate external chips, Linux can also act as a +target (needs hardware support) and respond to another controller on the bus. +This is then called a **local target**. In contrast, an external chip is called +a **remote target**. + +Target drivers are kept in a directory specific to the feature they provide, +for example ``drivers/gpio/`` for GPIO expanders and ``drivers/media/i2c/`` for video-related chips. -For the example configuration in figure, you will need a driver for your -I2C adapter, and drivers for your I2C devices (usually one driver for each -device). +For the example configuration in the figure above, you will need one driver for +the I2C controller, and drivers for your I2C targets. Usually one driver for +each target. + +Synonyms +-------- + +As mentioned above, the Linux I2C implementation historically uses the terms +"adapter" for controller and "client" for target. A number of data structures +have these synonyms in their name. So, when discussing implementation details, +you should be aware of these terms as well. The official wording is preferred, +though. + +Outdated terminology +-------------------- + +In earlier I2C specifications, controller was named "master" and target was +named "slave". These terms have been obsoleted with v7 of the specification and +their use is also discouraged by the Linux Kernel Code of Conduct. You may +still find them in references to documentation which has not been updated. The +general attitude, however, is to use the inclusive terms: controller and +target. Work to replace the old terminology in the Linux Kernel is on-going. diff --git a/Documentation/kbuild/kconfig-language.rst b/Documentation/kbuild/kconfig-language.rst index 555c2f839969..1fb3f5e6193c 100644 --- a/Documentation/kbuild/kconfig-language.rst +++ b/Documentation/kbuild/kconfig-language.rst @@ -150,6 +150,12 @@ applicable everywhere (see syntax). That will limit the usefulness but on the other hand avoid the illegal configurations all over. + If "select" <symbol> is followed by "if" <expr>, <symbol> will be + selected by the logical AND of the value of the current menu symbol + and <expr>. This means, the lower limit can be downgraded due to the + presence of "if" <expr>. This behavior may seem weird, but we rely on + it. (The future of this behavior is undecided.) + - weak reverse dependencies: "imply" <symbol> ["if" <expr>] This is similar to "select" as it enforces a lower limit on another @@ -184,7 +190,7 @@ applicable everywhere (see syntax). ability to hook into a secondary subsystem while allowing the user to configure that subsystem out without also having to unset these drivers. - Note: If the combination of FOO=y and BAR=m causes a link error, + Note: If the combination of FOO=y and BAZ=m causes a link error, you can guard the function call with IS_REACHABLE():: foo_init() @@ -202,6 +208,10 @@ applicable everywhere (see syntax). imply BAR imply BAZ + Note: If "imply" <symbol> is followed by "if" <expr>, the default of <symbol> + will be the logical AND of the value of the current menu symbol and <expr>. + (The future of this behavior is undecided.) + - limiting menu display: "visible if" <expr> This attribute is only applicable to menu blocks, if the condition is diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 00dc61358be8..683f5c3f30ad 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -415,6 +415,26 @@ attribute-sets: type: u32 - + name: irq-moderation + attributes: + - + name: usec + type: u32 + - + name: pkts + type: u32 + - + name: comps + type: u32 + - + name: profile + attributes: + - + name: irq-moderation + type: nest + multi-attr: true + nested-attributes: irq-moderation + - name: coalesce attributes: - @@ -502,6 +522,15 @@ attribute-sets: - name: tx-aggr-time-usecs type: u32 + - + name: rx-profile + type: nest + nested-attributes: profile + - + name: tx-profile + type: nest + nested-attributes: profile + - name: pause-stat attributes: @@ -1325,6 +1354,8 @@ operations: - tx-aggr-max-bytes - tx-aggr-max-frames - tx-aggr-time-usecs + - rx-profile + - tx-profile dump: *coalesce-get-op - name: coalesce-set @@ -1603,7 +1634,7 @@ operations: attributes: - header reply: - attributes: &pse + attributes: - header - podl-pse-admin-state - podl-pse-admin-control @@ -1620,7 +1651,10 @@ operations: do: request: - attributes: *pse + attributes: + - header + - podl-pse-admin-control + - c33-pse-admin-control - name: rss-get doc: Get RSS params. diff --git a/Documentation/netlink/specs/nfsd.yaml b/Documentation/netlink/specs/nfsd.yaml index d21234097167..6bda7a467301 100644 --- a/Documentation/netlink/specs/nfsd.yaml +++ b/Documentation/netlink/specs/nfsd.yaml @@ -123,8 +123,6 @@ operations: doc: dump pending nfsd rpc attribute-set: rpc-status dump: - pre: nfsd-nl-rpc-status-get-start - post: nfsd-nl-rpc-status-get-done reply: attributes: - xid diff --git a/Documentation/networking/devlink/octeontx2.rst b/Documentation/networking/devlink/octeontx2.rst index 610de99b728a..d33a90dd44bf 100644 --- a/Documentation/networking/devlink/octeontx2.rst +++ b/Documentation/networking/devlink/octeontx2.rst @@ -40,3 +40,19 @@ The ``octeontx2 AF`` driver implements the following driver-specific parameters. - runtime - Use to set the quantum which hardware uses for scheduling among transmit queues. Hardware uses weighted DWRR algorithm to schedule among all transmit queues. + +The ``octeontx2 PF`` driver implements the following driver-specific parameters. + +.. list-table:: Driver-specific parameters implemented + :widths: 5 5 5 85 + + * - Name + - Type + - Mode + - Description + * - ``unicast_filter_count`` + - u8 + - runtime + - Set the maximum number of unicast filters that can be programmed for + the device. This can be used to achieve better device resource + utilization, avoiding over consumption of unused MCAM table entries. diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 160bfb0ae8ba..7ec08e903bab 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1033,6 +1033,8 @@ Kernel response contents: ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES`` u32 max aggr size, Tx ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES`` u32 max aggr packets, Tx ``ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS`` u32 time (us), aggr, Tx + ``ETHTOOL_A_COALESCE_RX_PROFILE`` nested profile of DIM, Rx + ``ETHTOOL_A_COALESCE_TX_PROFILE`` nested profile of DIM, Tx =========================================== ====== ======================= Attributes are only included in reply if their value is not zero or the @@ -1062,6 +1064,10 @@ block should be sent. This feature is mainly of interest for specific USB devices which does not cope well with frequent small-sized URBs transmissions. +``ETHTOOL_A_COALESCE_RX_PROFILE`` and ``ETHTOOL_A_COALESCE_TX_PROFILE`` refer +to DIM parameters, see `Generic Network Dynamic Interrupt Moderation (Net DIM) +<https://www.kernel.org/doc/Documentation/networking/net_dim.rst>`_. + COALESCE_SET ============ @@ -1098,6 +1104,8 @@ Request contents: ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES`` u32 max aggr size, Tx ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES`` u32 max aggr packets, Tx ``ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS`` u32 time (us), aggr, Tx + ``ETHTOOL_A_COALESCE_RX_PROFILE`` nested profile of DIM, Rx + ``ETHTOOL_A_COALESCE_TX_PROFILE`` nested profile of DIM, Tx =========================================== ====== ======================= Request is rejected if it attributes declared as unsupported by driver (i.e. diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index a6443851a142..d1af04b952f8 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -19,6 +19,7 @@ Contents: caif/index ethtool-netlink ieee802154 + iso15765-2 j1939 kapi msg_zerocopy @@ -105,6 +106,7 @@ Contents: seg6-sysctl skbuff smc-sysctl + sriov statistics strparser switchdev diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 6e99eccdb837..3616389c8c2d 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -131,6 +131,20 @@ fib_multipath_hash_fields - UNSIGNED INTEGER Default: 0x0007 (source IP, destination IP and IP protocol) +fib_multipath_hash_seed - UNSIGNED INTEGER + The seed value used when calculating hash for multipath routes. Applies + to both IPv4 and IPv6 datapath. Only present for kernels built with + CONFIG_IP_ROUTE_MULTIPATH enabled. + + When set to 0, the seed value used for multipath routing defaults to an + internal random-generated one. + + The actual hashing algorithm is not specified -- there is no guarantee + that a next hop distribution effected by a given seed will keep stable + across kernel versions. + + Default: 0 (random) + fib_sync_mem - UNSIGNED INTEGER Amount of dirty memory from fib entries that can be backlogged before synchronize_rcu is forced. diff --git a/Documentation/networking/iso15765-2.rst b/Documentation/networking/iso15765-2.rst new file mode 100644 index 000000000000..0e9d96074178 --- /dev/null +++ b/Documentation/networking/iso15765-2.rst @@ -0,0 +1,386 @@ +.. SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) + +==================== +ISO 15765-2 (ISO-TP) +==================== + +Overview +======== + +ISO 15765-2, also known as ISO-TP, is a transport protocol specifically defined +for diagnostic communication on CAN. It is widely used in the automotive +industry, for example as the transport protocol for UDSonCAN (ISO 14229-3) or +emission-related diagnostic services (ISO 15031-5). + +ISO-TP can be used both on CAN CC (aka Classical CAN) and CAN FD (CAN with +Flexible Datarate) based networks. It is also designed to be compatible with a +CAN network using SAE J1939 as data link layer (however, this is not a +requirement). + +Specifications used +------------------- + +* ISO 15765-2:2024 : Road vehicles - Diagnostic communication over Controller + Area Network (DoCAN). Part 2: Transport protocol and network layer services. + +Addressing +---------- + +In its simplest form, ISO-TP is based on two kinds of addressing modes for the +nodes connected to the same network: + +* physical addressing is implemented by two node-specific addresses and is used + in 1-to-1 communication. + +* functional addressing is implemented by one node-specific address and is used + in 1-to-N communication. + +Three different addressing formats can be employed: + +* "normal" : each address is represented simply by a CAN ID. + +* "extended": each address is represented by a CAN ID plus the first byte of + the CAN payload; both the CAN ID and the byte inside the payload shall be + different between two addresses. + +* "mixed": each address is represented by a CAN ID plus the first byte of + the CAN payload; the CAN ID is different between two addresses, but the + additional byte is the same. + +Transport protocol and associated frame types +--------------------------------------------- + +When transmitting data using the ISO-TP protocol, the payload can either fit +inside one single CAN message or not, also considering the overhead the protocol +is generating and the optional extended addressing. In the first case, the data +is transmitted at once using a so-called Single Frame (SF). In the second case, +ISO-TP defines a multi-frame protocol, in which the sender provides (through a +First Frame - FF) the PDU length which is to be transmitted and also asks for a +Flow Control (FC) frame, which provides the maximum supported size of a macro +data block (``blocksize``) and the minimum time between the single CAN messages +composing such block (``stmin``). Once this information has been received, the +sender starts to send frames containing fragments of the data payload (called +Consecutive Frames - CF), stopping after every ``blocksize``-sized block to wait +confirmation from the receiver which should then send another Flow Control +frame to inform the sender about its availability to receive more data. + +How to Use ISO-TP +================= + +As with others CAN protocols, the ISO-TP stack support is built into the +Linux network subsystem for the CAN bus, aka. Linux-CAN or SocketCAN, and +thus follows the same socket API. + +Creation and basic usage of an ISO-TP socket +-------------------------------------------- + +To use the ISO-TP stack, ``#include <linux/can/isotp.h>`` shall be used. A +socket can then be created using the ``PF_CAN`` protocol family, the +``SOCK_DGRAM`` type (as the underlying protocol is datagram-based by design) +and the ``CAN_ISOTP`` protocol: + +.. code-block:: C + + s = socket(PF_CAN, SOCK_DGRAM, CAN_ISOTP); + +After the socket has been successfully created, ``bind(2)`` shall be called to +bind the socket to the desired CAN interface; to do so: + +* a TX CAN ID shall be specified as part of the sockaddr supplied to the call + itself. + +* a RX CAN ID shall also be specified, unless broadcast flags have been set + through socket option (explained below). + +Once bound to an interface, the socket can be read from and written to using +the usual ``read(2)`` and ``write(2)`` system calls, as well as ``send(2)``, +``sendmsg(2)``, ``recv(2)`` and ``recvmsg(2)``. +Unlike the CAN_RAW socket API, only the ISO-TP data field (the actual payload) +is sent and received by the userspace application using these calls. The address +information and the protocol information are automatically filled by the ISO-TP +stack using the configuration supplied during socket creation. In the same way, +the stack will use the transport mechanism when required (i.e., when the size +of the data payload exceeds the MTU of the underlying CAN bus). + +The sockaddr structure used for SocketCAN has extensions for use with ISO-TP, +as specified below: + +.. code-block:: C + + struct sockaddr_can { + sa_family_t can_family; + int can_ifindex; + union { + struct { canid_t rx_id, tx_id; } tp; + ... + } can_addr; + } + +* ``can_family`` and ``can_ifindex`` serve the same purpose as for other + SocketCAN sockets. + +* ``can_addr.tp.rx_id`` specifies the receive (RX) CAN ID and will be used as + a RX filter. + +* ``can_addr.tp.tx_id`` specifies the transmit (TX) CAN ID + +ISO-TP socket options +--------------------- + +When creating an ISO-TP socket, reasonable defaults are set. Some options can +be modified with ``setsockopt(2)`` and/or read back with ``getsockopt(2)``. + +General options +~~~~~~~~~~~~~~~ + +General socket options can be passed using the ``CAN_ISOTP_OPTS`` optname: + +.. code-block:: C + + struct can_isotp_options opts; + ret = setsockopt(s, SOL_CAN_ISOTP, CAN_ISOTP_OPTS, &opts, sizeof(opts)) + +where the ``can_isotp_options`` structure has the following contents: + +.. code-block:: C + + struct can_isotp_options { + u32 flags; + u32 frame_txtime; + u8 ext_address; + u8 txpad_content; + u8 rxpad_content; + u8 rx_ext_address; + }; + +* ``flags``: modifiers to be applied to the default behaviour of the ISO-TP + stack. Following flags are available: + + * ``CAN_ISOTP_LISTEN_MODE``: listen only (do not send FC frames); normally + used as a testing feature. + + * ``CAN_ISOTP_EXTEND_ADDR``: use the byte specified in ``ext_address`` as an + additional address component. This enables the "mixed" addressing format if + used alone, or the "extended" addressing format if used in conjunction with + ``CAN_ISOTP_RX_EXT_ADDR``. + + * ``CAN_ISOTP_TX_PADDING``: enable padding for transmitted frames, using + ``txpad_content`` as value for the padding bytes. + + * ``CAN_ISOTP_RX_PADDING``: enable padding for the received frames, using + ``rxpad_content`` as value for the padding bytes. + + * ``CAN_ISOTP_CHK_PAD_LEN``: check for correct padding length on the received + frames. + + * ``CAN_ISOTP_CHK_PAD_DATA``: check padding bytes on the received frames + against ``rxpad_content``; if ``CAN_ISOTP_RX_PADDING`` is not specified, + this flag is ignored. + + * ``CAN_ISOTP_HALF_DUPLEX``: force ISO-TP socket in half duplex mode + (that is, transport mechanism can only be incoming or outgoing at the same + time, not both). + + * ``CAN_ISOTP_FORCE_TXSTMIN``: ignore stmin from received FC; normally + used as a testing feature. + + * ``CAN_ISOTP_FORCE_RXSTMIN``: ignore CFs depending on rx stmin; normally + used as a testing feature. + + * ``CAN_ISOTP_RX_EXT_ADDR``: use ``rx_ext_address`` instead of ``ext_address`` + as extended addressing byte on the reception path. If used in conjunction + with ``CAN_ISOTP_EXTEND_ADDR``, this flag effectively enables the "extended" + addressing format. + + * ``CAN_ISOTP_WAIT_TX_DONE``: wait until the frame is sent before returning + from ``write(2)`` and ``send(2)`` calls (i.e., blocking write operations). + + * ``CAN_ISOTP_SF_BROADCAST``: use 1-to-N functional addressing (cannot be + specified alongside ``CAN_ISOTP_CF_BROADCAST``). + + * ``CAN_ISOTP_CF_BROADCAST``: use 1-to-N transmission without flow control + (cannot be specified alongside ``CAN_ISOTP_SF_BROADCAST``). + NOTE: this is not covered by the ISO 15765-2 standard. + + * ``CAN_ISOTP_DYN_FC_PARMS``: enable dynamic update of flow control + parameters. + +* ``frame_txtime``: frame transmission time (defined as N_As/N_Ar inside the + ISO standard); if ``0``, the default (or the last set value) is used. + To set the transmission time to ``0``, the ``CAN_ISOTP_FRAME_TXTIME_ZERO`` + macro (equal to 0xFFFFFFFF) shall be used. + +* ``ext_address``: extended addressing byte, used if the + ``CAN_ISOTP_EXTEND_ADDR`` flag is specified. + +* ``txpad_content``: byte used as padding value for transmitted frames. + +* ``rxpad_content``: byte used as padding value for received frames. + +* ``rx_ext_address``: extended addressing byte for the reception path, used if + the ``CAN_ISOTP_RX_EXT_ADDR`` flag is specified. + +Flow Control options +~~~~~~~~~~~~~~~~~~~~ + +Flow Control (FC) options can be passed using the ``CAN_ISOTP_RECV_FC`` optname +to provide the communication parameters for receiving ISO-TP PDUs. + +.. code-block:: C + + struct can_isotp_fc_options fc_opts; + ret = setsockopt(s, SOL_CAN_ISOTP, CAN_ISOTP_RECV_FC, &fc_opts, sizeof(fc_opts)); + +where the ``can_isotp_fc_options`` structure has the following contents: + +.. code-block:: C + + struct can_isotp_options { + u8 bs; + u8 stmin; + u8 wftmax; + }; + +* ``bs``: blocksize provided in flow control frames. + +* ``stmin``: minimum separation time provided in flow control frames; can + have the following values (others are reserved): + + * 0x00 - 0x7F : 0 - 127 ms + + * 0xF1 - 0xF9 : 100 us - 900 us + +* ``wftmax``: maximum number of wait frames provided in flow control frames. + +Link Layer options +~~~~~~~~~~~~~~~~~~ + +Link Layer (LL) options can be passed using the ``CAN_ISOTP_LL_OPTS`` optname: + +.. code-block:: C + + struct can_isotp_ll_options ll_opts; + ret = setsockopt(s, SOL_CAN_ISOTP, CAN_ISOTP_LL_OPTS, &ll_opts, sizeof(ll_opts)); + +where the ``can_isotp_ll_options`` structure has the following contents: + +.. code-block:: C + + struct can_isotp_ll_options { + u8 mtu; + u8 tx_dl; + u8 tx_flags; + }; + +* ``mtu``: generated and accepted CAN frame type, can be equal to ``CAN_MTU`` + for classical CAN frames or ``CANFD_MTU`` for CAN FD frames. + +* ``tx_dl``: maximum payload length for transmitted frames, can have one value + among: 8, 12, 16, 20, 24, 32, 48, 64. Values above 8 only apply to CAN FD + traffic (i.e.: ``mtu = CANFD_MTU``). + +* ``tx_flags``: flags set into ``struct canfd_frame.flags`` at frame creation. + Only applies to CAN FD traffic (i.e.: ``mtu = CANFD_MTU``). + +Transmission stmin +~~~~~~~~~~~~~~~~~~ + +The transmission minimum separation time (stmin) can be forced using the +``CAN_ISOTP_TX_STMIN`` optname and providing an stmin value in microseconds as +a 32bit unsigned integer; this will overwrite the value sent by the receiver in +flow control frames: + +.. code-block:: C + + uint32_t stmin; + ret = setsockopt(s, SOL_CAN_ISOTP, CAN_ISOTP_TX_STMIN, &stmin, sizeof(stmin)); + +Reception stmin +~~~~~~~~~~~~~~~ + +The reception minimum separation time (stmin) can be forced using the +``CAN_ISOTP_RX_STMIN`` optname and providing an stmin value in microseconds as +a 32bit unsigned integer; received Consecutive Frames (CF) which timestamps +differ less than this value will be ignored: + +.. code-block:: C + + uint32_t stmin; + ret = setsockopt(s, SOL_CAN_ISOTP, CAN_ISOTP_RX_STMIN, &stmin, sizeof(stmin)); + +Multi-frame transport support +----------------------------- + +The ISO-TP stack contained inside the Linux kernel supports the multi-frame +transport mechanism defined by the standard, with the following constraints: + +* the maximum size of a PDU is defined by a module parameter, with an hard + limit imposed at build time. + +* when a transmission is in progress, subsequent calls to ``write(2)`` will + block, while calls to ``send(2)`` will either block or fail depending on the + presence of the ``MSG_DONTWAIT`` flag. + +* no support is present for sending "wait frames": whether a PDU can be fully + received or not is decided when the First Frame is received. + +Errors +------ + +Following errors are reported to userspace: + +RX path errors +~~~~~~~~~~~~~~ + +============ =============================================================== +-ETIMEDOUT timeout of data reception +-EILSEQ sequence number mismatch during a multi-frame reception +-EBADMSG data reception with wrong padding +============ =============================================================== + +TX path errors +~~~~~~~~~~~~~~ + +========== ================================================================= +-ECOMM flow control reception timeout +-EMSGSIZE flow control reception overflow +-EBADMSG flow control reception with wrong layout/padding +========== ================================================================= + +Examples +======== + +Basic node example +------------------ + +Following example implements a node using "normal" physical addressing, with +RX ID equal to 0x18DAF142 and a TX ID equal to 0x18DA42F1. All options are left +to their default. + +.. code-block:: C + + int s; + struct sockaddr_can addr; + int ret; + + s = socket(PF_CAN, SOCK_DGRAM, CAN_ISOTP); + if (s < 0) + exit(1); + + addr.can_family = AF_CAN; + addr.can_ifindex = if_nametoindex("can0"); + addr.tp.tx_id = 0x18DA42F1 | CAN_EFF_FLAG; + addr.tp.rx_id = 0x18DAF142 | CAN_EFF_FLAG; + + ret = bind(s, (struct sockaddr *)&addr, sizeof(addr)); + if (ret < 0) + exit(1); + + /* Data can now be received using read(s, ...) and sent using write(s, ...) */ + +Additional examples +------------------- + +More complete (and complex) examples can be found inside the ``isotp*`` userland +tools, distributed as part of the ``can-utils`` utilities at: +https://github.com/linux-can/can-utils diff --git a/Documentation/networking/net_dim.rst b/Documentation/networking/net_dim.rst index 3bed9fd95336..8908fd7b0a8d 100644 --- a/Documentation/networking/net_dim.rst +++ b/Documentation/networking/net_dim.rst @@ -169,6 +169,48 @@ usage is not complete but it should make the outline of the usage clear. ... } + +Tuning DIM +========== + +Net DIM serves a range of network devices and delivers excellent acceleration +benefits. Yet, it has been observed that some preset configurations of DIM may +not align seamlessly with the varying specifications of network devices, and +this discrepancy has been identified as a factor to the suboptimal performance +outcomes of DIM-enabled network devices, related to a mismatch in profiles. + +To address this issue, Net DIM introduces a per-device control to modify and +access a device's ``rx-profile`` and ``tx-profile`` parameters: +Assume that the target network device is named ethx, and ethx only declares +support for RX profile setting and supports modification of ``usec`` field +and ``pkts`` field (See the data structure: +:c:type:`struct dim_cq_moder <dim_cq_moder>`). + +You can use ethtool to modify the current RX DIM profile where all +values are 64:: + + $ ethtool -C ethx rx-profile 1,1,n_2,2,n_3,n,n_n,4,n_n,n,n + +``n`` means do not modify this field, and ``_`` separates structure +elements of the profile array. + +Querying the current profiles using:: + + $ ethtool -c ethx + ... + rx-profile: + {.usec = 1, .pkts = 1, .comps = n/a,}, + {.usec = 2, .pkts = 2, .comps = n/a,}, + {.usec = 3, .pkts = 64, .comps = n/a,}, + {.usec = 64, .pkts = 4, .comps = n/a,}, + {.usec = 64, .pkts = 64, .comps = n/a,} + tx-profile: n/a + +If the network device does not support specific fields of DIM profiles, +the corresponding ``n/a`` will display. If the ``n/a`` field is being +modified, error messages will be reported. + + Dynamic Interrupt Moderation (DIM) library API ============================================== diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst index 1283240d7620..f64641417c54 100644 --- a/Documentation/networking/phy.rst +++ b/Documentation/networking/phy.rst @@ -327,6 +327,12 @@ Some of the interface modes are described below: This is the Penta SGMII mode, it is similar to QSGMII but it combines 5 SGMII lines into a single link compared to 4 on QSGMII. +``PHY_INTERFACE_MODE_10G_QXGMII`` + Represents the 10G-QXGMII PHY-MAC interface as defined by the Cisco USXGMII + Multiport Copper Interface document. It supports 4 ports over a 10.3125 GHz + SerDes lane, each port having speeds of 2.5G / 1G / 100M / 10M achieved + through symbol replication. The PCS expects the standard USXGMII code word. + Pause frames / flow control =========================== diff --git a/Documentation/networking/sriov.rst b/Documentation/networking/sriov.rst new file mode 100644 index 000000000000..5deb4ff3154f --- /dev/null +++ b/Documentation/networking/sriov.rst @@ -0,0 +1,25 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=============== +NIC SR-IOV APIs +=============== + +Modern NICs are strongly encouraged to focus on implementing the ``switchdev`` +model (see :ref:`switchdev`) to configure forwarding and security of SR-IOV +functionality. + +Legacy API +========== + +The old SR-IOV API is implemented in ``rtnetlink`` Netlink family as part of +the ``RTM_GETLINK`` and ``RTM_SETLINK`` commands. On the driver side +it consists of a number of ``ndo_set_vf_*`` and ``ndo_get_vf_*`` callbacks. + +Since the legacy APIs do not integrate well with the rest of the stack +the API is considered frozen; no new functionality or extensions +will be accepted. New drivers should not implement the uncommon callbacks; +namely the following callbacks are off limits: + + - ``ndo_get_vf_port`` + - ``ndo_set_vf_port`` + - ``ndo_set_vf_rss_query_en`` diff --git a/Documentation/networking/tcp_ao.rst b/Documentation/networking/tcp_ao.rst index 8a58321acce7..e96e62d1dab3 100644 --- a/Documentation/networking/tcp_ao.rst +++ b/Documentation/networking/tcp_ao.rst @@ -337,6 +337,15 @@ TCP-AO per-socket counters are also duplicated with per-netns counters, exposed with SNMP. Those are ``TCPAOGood``, ``TCPAOBad``, ``TCPAOKeyNotFound``, ``TCPAORequired`` and ``TCPAODroppedIcmps``. +For monitoring purposes, there are following TCP-AO trace events: +``tcp_hash_bad_header``, ``tcp_hash_ao_required``, ``tcp_ao_handshake_failure``, +``tcp_ao_wrong_maclen``, ``tcp_ao_wrong_maclen``, ``tcp_ao_key_not_found``, +``tcp_ao_rnext_request``, ``tcp_ao_synack_no_key``, ``tcp_ao_snd_sne_update``, +``tcp_ao_rcv_sne_update``. It's possible to separately enable any of them and +one can filter them by net-namespace, 4-tuple, family, L3 index, and TCP header +flags. If a segment has a TCP-AO header, the filters may also include +keyid, rnext, and maclen. SNE updates include the rolled-over numbers. + RFC 5925 very permissively specifies how TCP port matching can be done for MKTs:: diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst index 5926115ec0ed..8a251d71fa6e 100644 --- a/Documentation/userspace-api/index.rst +++ b/Documentation/userspace-api/index.rst @@ -32,6 +32,7 @@ Security-related interfaces seccomp_filter landlock lsm + mfd_noexec spec_ctrl tee diff --git a/Documentation/userspace-api/media/v4l/dev-subdev.rst b/Documentation/userspace-api/media/v4l/dev-subdev.rst index 0f9eda3187f3..161b43f1ce66 100644 --- a/Documentation/userspace-api/media/v4l/dev-subdev.rst +++ b/Documentation/userspace-api/media/v4l/dev-subdev.rst @@ -582,7 +582,7 @@ depending on the hardware. In all cases, however, only routes that have the Devices generating the streams may allow enabling and disabling some of the routes or have a fixed routing configuration. If the routes can be disabled, not declaring the routes (or declaring them without -``VIDIOC_SUBDEV_STREAM_FL_ACTIVE`` flag set) in ``VIDIOC_SUBDEV_S_ROUTING`` will +``V4L2_SUBDEV_STREAM_FL_ACTIVE`` flag set) in ``VIDIOC_SUBDEV_S_ROUTING`` will disable the routes. ``VIDIOC_SUBDEV_S_ROUTING`` will still return such routes back to the user in the routes array, with the ``V4L2_SUBDEV_STREAM_FL_ACTIVE`` flag unset. diff --git a/Documentation/userspace-api/mfd_noexec.rst b/Documentation/userspace-api/mfd_noexec.rst new file mode 100644 index 000000000000..7afcc480e38f --- /dev/null +++ b/Documentation/userspace-api/mfd_noexec.rst @@ -0,0 +1,86 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================== +Introduction of non-executable mfd +================================== +:Author: + Daniel Verkamp <[email protected]> + Jeff Xu <[email protected]> + +:Contributor: + Aleksa Sarai <[email protected]> + +Since Linux introduced the memfd feature, memfds have always had their +execute bit set, and the memfd_create() syscall doesn't allow setting +it differently. + +However, in a secure-by-default system, such as ChromeOS, (where all +executables should come from the rootfs, which is protected by verified +boot), this executable nature of memfd opens a door for NoExec bypass +and enables “confused deputy attack”. E.g, in VRP bug [1]: cros_vm +process created a memfd to share the content with an external process, +however the memfd is overwritten and used for executing arbitrary code +and root escalation. [2] lists more VRP of this kind. + +On the other hand, executable memfd has its legit use: runc uses memfd’s +seal and executable feature to copy the contents of the binary then +execute them. For such a system, we need a solution to differentiate runc's +use of executable memfds and an attacker's [3]. + +To address those above: + - Let memfd_create() set X bit at creation time. + - Let memfd be sealed for modifying X bit when NX is set. + - Add a new pid namespace sysctl: vm.memfd_noexec to help applications in + migrating and enforcing non-executable MFD. + +User API +======== +``int memfd_create(const char *name, unsigned int flags)`` + +``MFD_NOEXEC_SEAL`` + When MFD_NOEXEC_SEAL bit is set in the ``flags``, memfd is created + with NX. F_SEAL_EXEC is set and the memfd can't be modified to + add X later. MFD_ALLOW_SEALING is also implied. + This is the most common case for the application to use memfd. + +``MFD_EXEC`` + When MFD_EXEC bit is set in the ``flags``, memfd is created with X. + +Note: + ``MFD_NOEXEC_SEAL`` implies ``MFD_ALLOW_SEALING``. In case that + an app doesn't want sealing, it can add F_SEAL_SEAL after creation. + + +Sysctl: +======== +``pid namespaced sysctl vm.memfd_noexec`` + +The new pid namespaced sysctl vm.memfd_noexec has 3 values: + + - 0: MEMFD_NOEXEC_SCOPE_EXEC + memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL acts like + MFD_EXEC was set. + + - 1: MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL + memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL acts like + MFD_NOEXEC_SEAL was set. + + - 2: MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED + memfd_create() without MFD_NOEXEC_SEAL will be rejected. + +The sysctl allows finer control of memfd_create for old software that +doesn't set the executable bit; for example, a container with +vm.memfd_noexec=1 means the old software will create non-executable memfd +by default while new software can create executable memfd by setting +MFD_EXEC. + +The value of vm.memfd_noexec is passed to child namespace at creation +time. In addition, the setting is hierarchical, i.e. during memfd_create, +we will search from current ns to root ns and use the most restrictive +setting. + +[1] https://crbug.com/1305267 + +[2] https://bugs.chromium.org/p/chromium/issues/list?q=type%3Dbug-security%20memfd%20escalation&can=1 + +[3] https://lwn.net/Articles/781013/ diff --git a/Documentation/virt/hyperv/clocks.rst b/Documentation/virt/hyperv/clocks.rst index a56f4837d443..176043265803 100644 --- a/Documentation/virt/hyperv/clocks.rst +++ b/Documentation/virt/hyperv/clocks.rst @@ -62,12 +62,21 @@ shared page with scale and offset values into user space. User space code performs the same algorithm of reading the TSC and applying the scale and offset to get the constant 10 MHz clock. -Linux clockevents are based on Hyper-V synthetic timer 0. While -Hyper-V offers 4 synthetic timers for each CPU, Linux only uses -timer 0. Interrupts from stimer0 are recorded on the "HVS" line in -/proc/interrupts. Clockevents based on the virtualized PIT and -local APIC timer also work, but the Hyper-V synthetic timer is -preferred. +Linux clockevents are based on Hyper-V synthetic timer 0 (stimer0). +While Hyper-V offers 4 synthetic timers for each CPU, Linux only uses +timer 0. In older versions of Hyper-V, an interrupt from stimer0 +results in a VMBus control message that is demultiplexed by +vmbus_isr() as described in the Documentation/virt/hyperv/vmbus.rst +documentation. In newer versions of Hyper-V, stimer0 interrupts can +be mapped to an architectural interrupt, which is referred to as +"Direct Mode". Linux prefers to use Direct Mode when available. Since +x86/x64 doesn't support per-CPU interrupts, Direct Mode statically +allocates an x86 interrupt vector (HYPERV_STIMER0_VECTOR) across all CPUs +and explicitly codes it to call the stimer0 interrupt handler. Hence +interrupts from stimer0 are recorded on the "HVS" line in /proc/interrupts +rather than being associated with a Linux IRQ. Clockevents based on the +virtualized PIT and local APIC timer also work, but Hyper-V stimer0 +is preferred. The driver for the Hyper-V synthetic system clock and timers is drivers/clocksource/hyperv_timer.c. diff --git a/Documentation/virt/hyperv/overview.rst b/Documentation/virt/hyperv/overview.rst index cd493332c88a..77408a89d1a4 100644 --- a/Documentation/virt/hyperv/overview.rst +++ b/Documentation/virt/hyperv/overview.rst @@ -40,7 +40,7 @@ Linux guests communicate with Hyper-V in four different ways: arm64, these synthetic registers must be accessed using explicit hypercalls. -* VMbus: VMbus is a higher-level software construct that is built on +* VMBus: VMBus is a higher-level software construct that is built on the other 3 mechanisms. It is a message passing interface between the Hyper-V host and the Linux guest. It uses memory that is shared between Hyper-V and the guest, along with various signaling @@ -54,8 +54,8 @@ x86/x64 architecture only. .. _Hyper-V Top Level Functional Spec (TLFS): https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/tlfs/tlfs -VMbus is not documented. This documentation provides a high-level -overview of VMbus and how it works, but the details can be discerned +VMBus is not documented. This documentation provides a high-level +overview of VMBus and how it works, but the details can be discerned only from the code. Sharing Memory @@ -74,7 +74,7 @@ follows: physical address space. How Hyper-V is told about the GPA or list of GPAs varies. In some cases, a single GPA is written to a synthetic register. In other cases, a GPA or list of GPAs is sent - in a VMbus message. + in a VMBus message. * Hyper-V translates the GPAs into "real" physical memory addresses, and creates a virtual mapping that it can use to access the memory. @@ -133,9 +133,9 @@ only the CPUs actually present in the VM, so Linux does not report any hot-add CPUs. A Linux guest CPU may be taken offline using the normal Linux -mechanisms, provided no VMbus channel interrupts are assigned to -the CPU. See the section on VMbus Interrupts for more details -on how VMbus channel interrupts can be re-assigned to permit +mechanisms, provided no VMBus channel interrupts are assigned to +the CPU. See the section on VMBus Interrupts for more details +on how VMBus channel interrupts can be re-assigned to permit taking a CPU offline. 32-bit and 64-bit @@ -169,14 +169,14 @@ and functionality. Hyper-V indicates feature/function availability via flags in synthetic MSRs that Hyper-V provides to the guest, and the guest code tests these flags. -VMbus has its own protocol version that is negotiated during the -initial VMbus connection from the guest to Hyper-V. This version +VMBus has its own protocol version that is negotiated during the +initial VMBus connection from the guest to Hyper-V. This version number is also output to dmesg during boot. This version number is checked in a few places in the code to determine if specific functionality is present. -Furthermore, each synthetic device on VMbus also has a protocol -version that is separate from the VMbus protocol version. Device +Furthermore, each synthetic device on VMBus also has a protocol +version that is separate from the VMBus protocol version. Device drivers for these synthetic devices typically negotiate the device protocol version, and may test that protocol version to determine if specific device functionality is present. diff --git a/Documentation/virt/hyperv/vmbus.rst b/Documentation/virt/hyperv/vmbus.rst index d2012d9022c5..1dcef6a7fda3 100644 --- a/Documentation/virt/hyperv/vmbus.rst +++ b/Documentation/virt/hyperv/vmbus.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0 -VMbus +VMBus ===== -VMbus is a software construct provided by Hyper-V to guest VMs. It +VMBus is a software construct provided by Hyper-V to guest VMs. It consists of a control path and common facilities used by synthetic devices that Hyper-V presents to guest VMs. The control path is used to offer synthetic devices to the guest VM and, in some cases, @@ -12,9 +12,9 @@ and the synthetic device implementation that is part of Hyper-V, and signaling primitives to allow Hyper-V and the guest to interrupt each other. -VMbus is modeled in Linux as a bus, with the expected /sys/bus/vmbus -entry in a running Linux guest. The VMbus driver (drivers/hv/vmbus_drv.c) -establishes the VMbus control path with the Hyper-V host, then +VMBus is modeled in Linux as a bus, with the expected /sys/bus/vmbus +entry in a running Linux guest. The VMBus driver (drivers/hv/vmbus_drv.c) +establishes the VMBus control path with the Hyper-V host, then registers itself as a Linux bus driver. It implements the standard bus functions for adding and removing devices to/from the bus. @@ -49,9 +49,9 @@ synthetic NIC is referred to as "netvsc" and the Linux driver for the synthetic SCSI controller is "storvsc". These drivers contain functions with names like "storvsc_connect_to_vsp". -VMbus channels +VMBus channels -------------- -An instance of a synthetic device uses VMbus channels to communicate +An instance of a synthetic device uses VMBus channels to communicate between the VSP and the VSC. Channels are bi-directional and used for passing messages. Most synthetic devices use a single channel, but the synthetic SCSI controller and synthetic NIC may use multiple @@ -73,7 +73,7 @@ write indices and some control flags, followed by the memory for the actual ring. The size of the ring is determined by the VSC in the guest and is specific to each synthetic device. The list of GPAs making up the ring is communicated to the Hyper-V host over the -VMbus control path as a GPA Descriptor List (GPADL). See function +VMBus control path as a GPA Descriptor List (GPADL). See function vmbus_establish_gpadl(). Each ring buffer is mapped into contiguous Linux kernel virtual @@ -102,10 +102,10 @@ resources. For Windows Server 2019 and later, this limit is approximately 1280 Mbytes. For versions prior to Windows Server 2019, the limit is approximately 384 Mbytes. -VMbus messages --------------- -All VMbus messages have a standard header that includes the message -length, the offset of the message payload, some flags, and a +VMBus channel messages +---------------------- +All messages sent in a VMBus channel have a standard header that includes +the message length, the offset of the message payload, some flags, and a transactionID. The portion of the message after the header is unique to each VSP/VSC pair. @@ -137,7 +137,7 @@ control message contains a list of GPAs that describe the data buffer. For example, the storvsc driver uses this approach to specify the data buffers to/from which disk I/O is done. -Three functions exist to send VMbus messages: +Three functions exist to send VMBus channel messages: 1. vmbus_sendpacket(): Control-only messages and messages with embedded data -- no GPAs @@ -154,20 +154,51 @@ Historically, Linux guests have trusted Hyper-V to send well-formed and valid messages, and Linux drivers for synthetic devices did not fully validate messages. With the introduction of processor technologies that fully encrypt guest memory and that allow the -guest to not trust the hypervisor (AMD SNP-SEV, Intel TDX), trusting +guest to not trust the hypervisor (AMD SEV-SNP, Intel TDX), trusting the Hyper-V host is no longer a valid assumption. The drivers for -VMbus synthetic devices are being updated to fully validate any +VMBus synthetic devices are being updated to fully validate any values read from memory that is shared with Hyper-V, which includes -messages from VMbus devices. To facilitate such validation, +messages from VMBus devices. To facilitate such validation, messages read by the guest from the "in" ring buffer are copied to a temporary buffer that is not shared with Hyper-V. Validation is performed in this temporary buffer without the risk of Hyper-V maliciously modifying the message after it is validated but before it is used. -VMbus interrupts +Synthetic Interrupt Controller (synic) +-------------------------------------- +Hyper-V provides each guest CPU with a synthetic interrupt controller +that is used by VMBus for host-guest communication. While each synic +defines 16 synthetic interrupts (SINT), Linux uses only one of the 16 +(VMBUS_MESSAGE_SINT). All interrupts related to communication between +the Hyper-V host and a guest CPU use that SINT. + +The SINT is mapped to a single per-CPU architectural interrupt (i.e, +an 8-bit x86/x64 interrupt vector, or an arm64 PPI INTID). Because +each CPU in the guest has a synic and may receive VMBus interrupts, +they are best modeled in Linux as per-CPU interrupts. This model works +well on arm64 where a single per-CPU Linux IRQ is allocated for +VMBUS_MESSAGE_SINT. This IRQ appears in /proc/interrupts as an IRQ labelled +"Hyper-V VMbus". Since x86/x64 lacks support for per-CPU IRQs, an x86 +interrupt vector is statically allocated (HYPERVISOR_CALLBACK_VECTOR) +across all CPUs and explicitly coded to call vmbus_isr(). In this case, +there's no Linux IRQ, and the interrupts are visible in aggregate in +/proc/interrupts on the "HYP" line. + +The synic provides the means to demultiplex the architectural interrupt into +one or more logical interrupts and route the logical interrupt to the proper +VMBus handler in Linux. This demultiplexing is done by vmbus_isr() and +related functions that access synic data structures. + +The synic is not modeled in Linux as an irq chip or irq domain, +and the demultiplexed logical interrupts are not Linux IRQs. As such, +they don't appear in /proc/interrupts or /proc/irq. The CPU +affinity for one of these logical interrupts is controlled via an +entry under /sys/bus/vmbus as described below. + +VMBus interrupts ---------------- -VMbus provides a mechanism for the guest to interrupt the host when +VMBus provides a mechanism for the guest to interrupt the host when the guest has queued new messages in a ring buffer. The host expects that the guest will send an interrupt only when an "out" ring buffer transitions from empty to non-empty. If the guest sends @@ -176,63 +207,55 @@ unnecessary. If a guest sends an excessive number of unnecessary interrupts, the host may throttle that guest by suspending its execution for a few seconds to prevent a denial-of-service attack. -Similarly, the host will interrupt the guest when it sends a new -message on the VMbus control path, or when a VMbus channel "in" ring -buffer transitions from empty to non-empty. Each CPU in the guest -may receive VMbus interrupts, so they are best modeled as per-CPU -interrupts in Linux. This model works well on arm64 where a single -per-CPU IRQ is allocated for VMbus. Since x86/x64 lacks support for -per-CPU IRQs, an x86 interrupt vector is statically allocated (see -HYPERVISOR_CALLBACK_VECTOR) across all CPUs and explicitly coded to -call the VMbus interrupt service routine. These interrupts are -visible in /proc/interrupts on the "HYP" line. - -The guest CPU that a VMbus channel will interrupt is selected by the +Similarly, the host will interrupt the guest via the synic when +it sends a new message on the VMBus control path, or when a VMBus +channel "in" ring buffer transitions from empty to non-empty due to +the host inserting a new VMBus channel message. The control message stream +and each VMBus channel "in" ring buffer are separate logical interrupts +that are demultiplexed by vmbus_isr(). It demultiplexes by first checking +for channel interrupts by calling vmbus_chan_sched(), which looks at a synic +bitmap to determine which channels have pending interrupts on this CPU. +If multiple channels have pending interrupts for this CPU, they are +processed sequentially. When all channel interrupts have been processed, +vmbus_isr() checks for and processes any messages received on the VMBus +control path. + +The guest CPU that a VMBus channel will interrupt is selected by the guest when the channel is created, and the host is informed of that -selection. VMbus devices are broadly grouped into two categories: +selection. VMBus devices are broadly grouped into two categories: -1. "Slow" devices that need only one VMbus channel. The devices +1. "Slow" devices that need only one VMBus channel. The devices (such as keyboard, mouse, heartbeat, and timesync) generate - relatively few interrupts. Their VMbus channels are all + relatively few interrupts. Their VMBus channels are all assigned to interrupt the VMBUS_CONNECT_CPU, which is always CPU 0. -2. "High speed" devices that may use multiple VMbus channels for +2. "High speed" devices that may use multiple VMBus channels for higher parallelism and performance. These devices include the - synthetic SCSI controller and synthetic NIC. Their VMbus + synthetic SCSI controller and synthetic NIC. Their VMBus channels interrupts are assigned to CPUs that are spread out among the available CPUs in the VM so that interrupts on multiple channels can be processed in parallel. -The assignment of VMbus channel interrupts to CPUs is done in the +The assignment of VMBus channel interrupts to CPUs is done in the function init_vp_index(). This assignment is done outside of the normal Linux interrupt affinity mechanism, so the interrupts are neither "unmanaged" nor "managed" interrupts. -The CPU that a VMbus channel will interrupt can be seen in +The CPU that a VMBus channel will interrupt can be seen in /sys/bus/vmbus/devices/<deviceGUID>/ channels/<channelRelID>/cpu. When running on later versions of Hyper-V, the CPU can be changed -by writing a new value to this sysfs entry. Because the interrupt -assignment is done outside of the normal Linux affinity mechanism, -there are no entries in /proc/irq corresponding to individual -VMbus channel interrupts. +by writing a new value to this sysfs entry. Because VMBus channel +interrupts are not Linux IRQs, there are no entries in /proc/interrupts +or /proc/irq corresponding to individual VMBus channel interrupts. An online CPU in a Linux guest may not be taken offline if it has -VMbus channel interrupts assigned to it. Any such channel +VMBus channel interrupts assigned to it. Any such channel interrupts must first be manually reassigned to another CPU as described above. When no channel interrupts are assigned to the CPU, it can be taken offline. -When a guest CPU receives a VMbus interrupt from the host, the -function vmbus_isr() handles the interrupt. It first checks for -channel interrupts by calling vmbus_chan_sched(), which looks at a -bitmap setup by the host to determine which channels have pending -interrupts on this CPU. If multiple channels have pending -interrupts for this CPU, they are processed sequentially. When all -channel interrupts have been processed, vmbus_isr() checks for and -processes any message received on the VMbus control path. - -The VMbus channel interrupt handling code is designed to work +The VMBus channel interrupt handling code is designed to work correctly even if an interrupt is received on a CPU other than the CPU assigned to the channel. Specifically, the code does not use CPU-based exclusion for correctness. In normal operation, Hyper-V @@ -242,23 +265,23 @@ when Hyper-V will make the transition. The code must work correctly even if there is a time lag before Hyper-V starts interrupting the new CPU. See comments in target_cpu_store(). -VMbus device creation/deletion +VMBus device creation/deletion ------------------------------ Hyper-V and the Linux guest have a separate message-passing path that is used for synthetic device creation and deletion. This -path does not use a VMbus channel. See vmbus_post_msg() and +path does not use a VMBus channel. See vmbus_post_msg() and vmbus_on_msg_dpc(). The first step is for the guest to connect to the generic -Hyper-V VMbus mechanism. As part of establishing this connection, -the guest and Hyper-V agree on a VMbus protocol version they will +Hyper-V VMBus mechanism. As part of establishing this connection, +the guest and Hyper-V agree on a VMBus protocol version they will use. This negotiation allows newer Linux kernels to run on older Hyper-V versions, and vice versa. The guest then tells Hyper-V to "send offers". Hyper-V sends an offer message to the guest for each synthetic device that the VM -is configured to have. Each VMbus device type has a fixed GUID -known as the "class ID", and each VMbus device instance is also +is configured to have. Each VMBus device type has a fixed GUID +known as the "class ID", and each VMBus device instance is also identified by a GUID. The offer message from Hyper-V contains both GUIDs to uniquely (within the VM) identify the device. There is one offer message for each device instance, so a VM with @@ -275,7 +298,7 @@ type based on the class ID, and invokes the correct driver to set up the device. Driver/device matching is performed using the standard Linux mechanism. -The device driver probe function opens the primary VMbus channel to +The device driver probe function opens the primary VMBus channel to the corresponding VSP. It allocates guest memory for the channel ring buffers and shares the ring buffer with the Hyper-V host by giving the host a list of GPAs for the ring buffer memory. See @@ -285,7 +308,7 @@ Once the ring buffer is set up, the device driver and VSP exchange setup messages via the primary channel. These messages may include negotiating the device protocol version to be used between the Linux VSC and the VSP on the Hyper-V host. The setup messages may also -include creating additional VMbus channels, which are somewhat +include creating additional VMBus channels, which are somewhat mis-named as "sub-channels" since they are functionally equivalent to the primary channel once they are created. diff --git a/MAINTAINERS b/MAINTAINERS index cd3277a98cfe..22328600cfd0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3601,10 +3601,9 @@ W: https://wireless.wiki.kernel.org/en/users/Drivers/b43 F: drivers/net/wireless/broadcom/b43/ B43LEGACY WIRELESS DRIVER -M: Larry Finger <[email protected]> -S: Maintained +S: Orphan W: https://wireless.wiki.kernel.org/en/users/Drivers/b43 F: drivers/net/wireless/broadcom/b43legacy/ @@ -3980,7 +3979,7 @@ R: Song Liu <[email protected]> R: Yonghong Song <[email protected]> R: John Fastabend <[email protected]> R: KP Singh <[email protected]> -R: Stanislav Fomichev <[email protected]> +R: Stanislav Fomichev <[email protected]> R: Hao Luo <[email protected]> R: Jiri Olsa <[email protected]> @@ -4083,12 +4082,13 @@ F: kernel/bpf/ringbuf.c BPF [SECURITY & LSM] (Security Audit and Enforcement using BPF) M: KP Singh <[email protected]> -R: Matt Bobrowski <[email protected]> +M: Matt Bobrowski <[email protected]> S: Maintained F: Documentation/bpf/prog_lsm.rst F: include/linux/bpf_lsm.h F: kernel/bpf/bpf_lsm.c +F: kernel/trace/bpf_trace.c F: security/bpf/ BPF [SELFTESTS] (Test Runners & Infrastructure) @@ -4842,6 +4842,7 @@ W: https://github.com/linux-can T: git git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can-next.git F: Documentation/networking/can.rst +F: Documentation/networking/iso15765-2.rst F: include/linux/can/can-ml.h F: include/linux/can/core.h F: include/linux/can/skb.h @@ -5295,7 +5296,7 @@ F: drivers/infiniband/hw/usnic/ CLANG CONTROL FLOW INTEGRITY SUPPORT M: Sami Tolvanen <[email protected]> -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> R: Nathan Chancellor <[email protected]> S: Supported @@ -8211,7 +8212,7 @@ F: rust/kernel/net/phy.rs EXEC & BINFMT API, ELF R: Eric Biederman <[email protected]> -R: Kees Cook <[email protected]> +R: Kees Cook <[email protected]> S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/execve @@ -8612,7 +8613,7 @@ S: Maintained F: drivers/net/ethernet/nvidia/* FORTIFY_SOURCE -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening @@ -8809,14 +8810,14 @@ M: Madalin Bucur <[email protected]> R: Sean Anderson <[email protected]> S: Maintained -F: Documentation/devicetree/bindings/net/fsl-fman.txt +F: Documentation/devicetree/bindings/net/fsl,fman*.yaml F: drivers/net/ethernet/freescale/fman FREESCALE QORIQ PTP CLOCK DRIVER M: Yangbo Lu <[email protected]> S: Maintained -F: Documentation/devicetree/bindings/ptp/ptp-qoriq.txt +F: Documentation/devicetree/bindings/ptp/fsl,ptp.yaml F: drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp* F: drivers/net/ethernet/freescale/dpaa2/dprtc* F: drivers/net/ethernet/freescale/enetc/enetc_ptp.c @@ -9102,7 +9103,7 @@ F: include/linux/mfd/gsc.h F: include/linux/platform_data/gsc_hwmon.h GCC PLUGINS -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening @@ -9236,7 +9237,7 @@ S: Maintained F: drivers/input/touchscreen/resistive-adc-touch.c GENERIC STRING LIBRARY -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> R: Andy Shevchenko <[email protected]> S: Supported @@ -11034,8 +11035,8 @@ F: include/uapi/drm/i915_drm.h INTEL DRM XE DRIVER (Lunar Lake and newer) M: Lucas De Marchi <[email protected]> -M: Oded Gabbay <[email protected]> M: Thomas Hellström <[email protected]> +M: Rodrigo Vivi <[email protected]> S: Supported W: https://drm.pages.freedesktop.org/intel-docs/ @@ -11950,7 +11951,7 @@ F: scripts/package/ F: usr/ KERNEL HARDENING (not covered by other areas) -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> R: Gustavo A. R. Silva <[email protected]> S: Supported @@ -12382,7 +12383,6 @@ F: drivers/video/backlight/ktz8866.c KVM PARAVIRT (KVM/paravirt) M: Paolo Bonzini <[email protected]> -R: Wanpeng Li <[email protected]> R: Vitaly Kuznetsov <[email protected]> S: Supported @@ -12449,6 +12449,7 @@ LANTIQ / INTEL Ethernet drivers M: Hauke Mehrtens <[email protected]> S: Maintained +F: Documentation/devicetree/bindings/net/dsa/lantiq,gswip.yaml F: drivers/net/dsa/lantiq_gswip.c F: drivers/net/dsa/lantiq_pce.h F: drivers/net/ethernet/lantiq_xrx200.c @@ -12478,7 +12479,7 @@ F: drivers/scsi/53c700* LEAKING_ADDRESSES M: Tycho Andersen <[email protected]> -R: Kees Cook <[email protected]> +R: Kees Cook <[email protected]> S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening @@ -12774,7 +12775,7 @@ F: arch/powerpc/platforms/8xx/ F: arch/powerpc/platforms/83xx/ LINUX KERNEL DUMP TEST MODULE (LKDTM) -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> S: Maintained F: drivers/misc/lkdtm/* F: tools/testing/selftests/lkdtm/* @@ -12904,7 +12905,7 @@ Q: http://patchwork.linuxtv.org/project/linux-media/list/ F: drivers/media/usb/dvb-usb-v2/lmedm04* LOADPIN SECURITY MODULE -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening F: Documentation/admin-guide/LSM/LoadPin.rst @@ -15825,7 +15826,7 @@ F: drivers/nfc/virtual_ncidev.c F: tools/testing/selftests/nci/ NFS, SUNRPC, AND LOCKD CLIENTS -M: Trond Myklebust <[email protected]> +M: Trond Myklebust <[email protected]> M: Anna Schumaker <[email protected]> S: Maintained @@ -17532,7 +17533,6 @@ F: include/linux/peci.h PENSANDO ETHERNET DRIVERS M: Shannon Nelson <[email protected]> M: Brett Creeley <[email protected]> S: Supported F: Documentation/networking/device_drivers/ethernet/pensando/ionic.rst @@ -17996,7 +17996,7 @@ F: tools/testing/selftests/proc/ PROC SYSCTL M: Luis Chamberlain <[email protected]> -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> M: Joel Granados <[email protected]> @@ -18052,7 +18052,7 @@ F: Documentation/devicetree/bindings/net/pse-pd/ F: drivers/net/pse-pd/ PSTORE FILESYSTEM -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> R: Tony Luck <[email protected]> R: Guilherme G. Piccoli <[email protected]> @@ -18210,6 +18210,7 @@ QCOM AUDIO (ASoC) DRIVERS M: Srinivas Kandagatla <[email protected]> M: Banajit Goswami <[email protected]> L: [email protected] (moderated for non-subscribers) S: Supported F: Documentation/devicetree/bindings/soc/qcom/qcom,apr* F: Documentation/devicetree/bindings/sound/qcom,* @@ -18374,7 +18375,7 @@ M: Jeff Johnson <[email protected]> S: Supported W: https://wireless.wiki.kernel.org/en/users/Drivers/ath12k -T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/ath/ath.git F: drivers/net/wireless/ath/ath12k/ N: ath12k @@ -18384,7 +18385,7 @@ M: Jeff Johnson <[email protected]> S: Supported W: https://wireless.wiki.kernel.org/en/users/Drivers/ath10k -T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/ath/ath.git F: drivers/net/wireless/ath/ath10k/ N: ath10k @@ -18395,7 +18396,7 @@ L: [email protected] S: Supported W: https://wireless.wiki.kernel.org/en/users/Drivers/ath11k B: https://wireless.wiki.kernel.org/en/users/Drivers/ath11k/bugreport -T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/ath/ath.git F: drivers/net/wireless/ath/ath11k/ N: ath11k @@ -18404,7 +18405,7 @@ M: Toke Høiland-Jørgensen <[email protected]> S: Maintained W: https://wireless.wiki.kernel.org/en/users/Drivers/ath9k -T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/ath/ath.git F: Documentation/devicetree/bindings/net/wireless/qca,ath9k.yaml F: drivers/net/wireless/ath/ath9k/ @@ -19031,6 +19032,14 @@ F: drivers/net/ethernet/renesas/Makefile F: drivers/net/ethernet/renesas/rcar_gen4* F: drivers/net/ethernet/renesas/rswitch* +RENESAS ETHERNET TSN DRIVER +M: Niklas Söderlund <[email protected]> +S: Supported +F: Documentation/devicetree/bindings/net/renesas,ethertsn.yaml +F: drivers/net/ethernet/renesas/rtsn.* + RENESAS IDT821034 ASoC CODEC M: Herve Codina <[email protected]> L: [email protected] (moderated for non-subscribers) @@ -19509,7 +19518,6 @@ F: drivers/net/wireless/realtek/rtl818x/rtl8180/ RTL8187 WIRELESS DRIVER M: Hin-Tak Leung <[email protected]> -M: Larry Finger <[email protected]> S: Maintained T: git https://github.com/pkshih/rtw.git @@ -20058,7 +20066,7 @@ F: drivers/media/cec/platform/seco/seco-cec.c F: drivers/media/cec/platform/seco/seco-cec.h SECURE COMPUTING -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> R: Andy Lutomirski <[email protected]> R: Will Drewry <[email protected]> S: Supported @@ -21247,7 +21255,6 @@ W: http://wiki.laptop.org/go/DCON F: drivers/staging/olpc_dcon/ STAGING - REALTEK RTL8712U DRIVERS -M: Larry Finger <[email protected]> M: Florian Schilhabel <[email protected]>. S: Odd Fixes F: drivers/staging/rtl8712/ @@ -22138,7 +22145,13 @@ TEHUTI ETHERNET DRIVER M: Andy Gospodarek <[email protected]> S: Supported -F: drivers/net/ethernet/tehuti/* +F: drivers/net/ethernet/tehuti/tehuti.* + +TEHUTI TN40XX ETHERNET DRIVER +M: FUJITA Tomonori <[email protected]> +S: Maintained +F: drivers/net/ethernet/tehuti/tn40* TELECOM CLOCK DRIVER FOR MCPL0010 M: Mark Gross <[email protected]> @@ -22746,7 +22759,7 @@ M: Jarkko Sakkinen <[email protected]> R: Jason Gunthorpe <[email protected]> S: Maintained -W: https://gitlab.com/jarkkojs/linux-tpmdd-test +W: https://codeberg.org/jarkko/linux-tpmdd-test Q: https://patchwork.kernel.org/project/linux-integrity/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/jarkko/linux-tpmdd.git F: Documentation/devicetree/bindings/tpm/ @@ -22972,7 +22985,7 @@ F: drivers/block/ublk_drv.c F: include/uapi/linux/ublk_cmd.h UBSAN -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> R: Marco Elver <[email protected]> R: Andrey Konovalov <[email protected]> R: Andrey Ryabinin <[email protected]> @@ -23974,7 +23987,6 @@ VMALLOC M: Andrew Morton <[email protected]> R: Uladzislau Rezki <[email protected]> R: Christoph Hellwig <[email protected]> -R: Lorenzo Stoakes <[email protected]> S: Maintained W: http://www.linux-mm.org @@ -24810,7 +24822,7 @@ F: drivers/net/hamradio/yam* F: include/linux/yam.h YAMA SECURITY MODULE -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening F: Documentation/admin-guide/LSM/Yama.rst @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 10 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc5 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/nxp/imx/imx53-qsb-common.dtsi b/arch/arm/boot/dts/nxp/imx/imx53-qsb-common.dtsi index d80440446473..05d7a462ea25 100644 --- a/arch/arm/boot/dts/nxp/imx/imx53-qsb-common.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx53-qsb-common.dtsi @@ -85,7 +85,7 @@ }; }; - panel { + panel_dpi: panel { compatible = "sii,43wvf1g"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_display_power>; diff --git a/arch/arm/boot/dts/nxp/imx/imx53-qsb-hdmi.dtso b/arch/arm/boot/dts/nxp/imx/imx53-qsb-hdmi.dtso index c84e9b052527..151e9cee3c87 100644 --- a/arch/arm/boot/dts/nxp/imx/imx53-qsb-hdmi.dtso +++ b/arch/arm/boot/dts/nxp/imx/imx53-qsb-hdmi.dtso @@ -10,8 +10,6 @@ /plugin/; &{/} { - /delete-node/ panel; - hdmi: connector-hdmi { compatible = "hdmi-connector"; label = "hdmi"; @@ -82,6 +80,10 @@ }; }; +&panel_dpi { + status = "disabled"; +}; + &tve { status = "disabled"; }; diff --git a/arch/arm/boot/dts/rockchip/rk3066a.dtsi b/arch/arm/boot/dts/rockchip/rk3066a.dtsi index 30139f21de64..51ae0418a7db 100644 --- a/arch/arm/boot/dts/rockchip/rk3066a.dtsi +++ b/arch/arm/boot/dts/rockchip/rk3066a.dtsi @@ -879,7 +879,3 @@ &wdt { compatible = "rockchip,rk3066-wdt", "snps,dw-wdt"; }; - -&emac { - compatible = "rockchip,rk3066-emac"; -}; diff --git a/arch/arm/boot/dts/rockchip/rk3xxx.dtsi b/arch/arm/boot/dts/rockchip/rk3xxx.dtsi index f37137f298d5..e6a78bcf9163 100644 --- a/arch/arm/boot/dts/rockchip/rk3xxx.dtsi +++ b/arch/arm/boot/dts/rockchip/rk3xxx.dtsi @@ -194,17 +194,14 @@ }; emac: ethernet@10204000 { - compatible = "snps,arc-emac"; + compatible = "rockchip,rk3066-emac"; reg = <0x10204000 0x3c>; interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>; - - rockchip,grf = <&grf>; - clocks = <&cru HCLK_EMAC>, <&cru SCLK_MAC>; clock-names = "hclk", "macref"; max-speed = <100>; phy-mode = "rmii"; - + rockchip,grf = <&grf>; status = "disabled"; }; diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h index 78282ced5038..e408399d5f0e 100644 --- a/arch/arm/include/asm/efi.h +++ b/arch/arm/include/asm/efi.h @@ -14,6 +14,7 @@ #include <asm/mach/map.h> #include <asm/mmu_context.h> #include <asm/ptrace.h> +#include <asm/uaccess.h> #ifdef CONFIG_EFI void efi_init(void); @@ -25,6 +26,18 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md, boo #define arch_efi_call_virt_setup() efi_virtmap_load() #define arch_efi_call_virt_teardown() efi_virtmap_unload() +#ifdef CONFIG_CPU_TTBR0_PAN +#undef arch_efi_call_virt +#define arch_efi_call_virt(p, f, args...) ({ \ + unsigned int flags = uaccess_save_and_enable(); \ + efi_status_t res = _Generic((p)->f(args), \ + efi_status_t: (p)->f(args), \ + default: ((p)->f(args), EFI_ABORTED)); \ + uaccess_restore(flags); \ + res; \ +}) +#endif + #define ARCH_EFI_IRQ_FLAGS_MASK \ (PSR_J_BIT | PSR_E_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT | \ PSR_T_BIT | MODE_MASK) diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c index a0b6d1e3812f..e61591f33a6c 100644 --- a/arch/arm/kernel/ftrace.c +++ b/arch/arm/kernel/ftrace.c @@ -232,11 +232,24 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, unsigned long old; if (unlikely(atomic_read(¤t->tracing_graph_pause))) +err_out: return; if (IS_ENABLED(CONFIG_UNWINDER_FRAME_POINTER)) { - /* FP points one word below parent's top of stack */ - frame_pointer += 4; + /* + * Usually, the stack frames are contiguous in memory but cases + * have been observed where the next stack frame does not live + * at 'frame_pointer + 4' as this code used to assume. + * + * Instead, dereference the field in the stack frame that + * stores the SP of the calling frame: to avoid unbounded + * recursion, this cannot involve any ftrace instrumented + * functions, so use the __get_kernel_nofault() primitive + * directly. + */ + __get_kernel_nofault(&frame_pointer, + (unsigned long *)(frame_pointer - 8), + unsigned long, err_out); } else { struct stackframe frame = { .fp = frame_pointer, diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi index 4768b05fd765..98544741ce17 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi @@ -6,6 +6,7 @@ #include <dt-bindings/phy/phy-imx8-pcie.h> #include <dt-bindings/pwm/pwm.h> #include "imx8mm.dtsi" +#include "imx8mm-overdrive.dtsi" / { chosen { @@ -935,7 +936,7 @@ /* Verdin GPIO_9_DSI (pulled-up as active-low) */ pinctrl_gpio_9_dsi: gpio9dsigrp { fsl,pins = - <MX8MM_IOMUXC_NAND_RE_B_GPIO3_IO15 0x146>; /* SODIMM 17 */ + <MX8MM_IOMUXC_NAND_RE_B_GPIO3_IO15 0x1c6>; /* SODIMM 17 */ }; /* Verdin GPIO_10_DSI (pulled-up as active-low) */ diff --git a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi index 43f1d45ccc96..f5115f9e8c47 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi @@ -254,7 +254,7 @@ <&clk IMX8MP_CLK_CLKOUT2>, <&clk IMX8MP_AUDIO_PLL2_OUT>; assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL2_OUT>; - assigned-clock-rates = <13000000>, <13000000>, <156000000>; + assigned-clock-rates = <13000000>, <13000000>, <208000000>; reset-gpios = <&gpio4 1 GPIO_ACTIVE_HIGH>; status = "disabled"; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi index dec57fad6828..e2b5e7ac3e46 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi @@ -219,7 +219,7 @@ bluetooth { compatible = "brcm,bcm4330-bt"; - shutdown-gpios = <&gpio4 16 GPIO_ACTIVE_HIGH>; + shutdown-gpios = <&gpio1 3 GPIO_ACTIVE_HIGH>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8qm-mek.dts b/arch/arm64/boot/dts/freescale/imx8qm-mek.dts index 5c6b39c6933f..6e05361c1ffb 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm-mek.dts +++ b/arch/arm64/boot/dts/freescale/imx8qm-mek.dts @@ -36,7 +36,7 @@ regulator-name = "SD1_SPWR"; regulator-min-microvolt = <3000000>; regulator-max-microvolt = <3000000>; - gpio = <&lsio_gpio4 19 GPIO_ACTIVE_HIGH>; + gpio = <&lsio_gpio4 7 GPIO_ACTIVE_HIGH>; enable-active-high; }; diff --git a/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts b/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts index d400d85f42a9..bd98eff4d685 100644 --- a/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts @@ -296,7 +296,6 @@ vmmc-supply = <®_usdhc2_vmmc>; bus-width = <4>; status = "okay"; - no-sdio; no-mmc; }; diff --git a/arch/arm64/boot/dts/ti/k3-am65-iot2050-common-pg1.dtsi b/arch/arm64/boot/dts/ti/k3-am65-iot2050-common-pg1.dtsi index ef7897763ef8..0a29ed172215 100644 --- a/arch/arm64/boot/dts/ti/k3-am65-iot2050-common-pg1.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65-iot2050-common-pg1.dtsi @@ -73,3 +73,15 @@ "rx0", "rx1", "rxmgm0", "rxmgm1"; }; + +&icssg0_iep0 { + interrupt-parent = <&icssg0_intc>; + interrupts = <7 7 7>; + interrupt-names = "iep_cap_cmp"; +}; + +&icssg0_iep1 { + interrupt-parent = <&icssg0_intc>; + interrupts = <56 8 8>; + interrupt-names = "iep_cap_cmp"; +}; diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 4ff0ae3f6d66..41fd90895dfc 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -153,8 +153,9 @@ extern void __memset_io(volatile void __iomem *, int, size_t); * emit the large TLP from the CPU. */ -static inline void __const_memcpy_toio_aligned32(volatile u32 __iomem *to, - const u32 *from, size_t count) +static __always_inline void +__const_memcpy_toio_aligned32(volatile u32 __iomem *to, const u32 *from, + size_t count) { switch (count) { case 8: @@ -196,24 +197,22 @@ static inline void __const_memcpy_toio_aligned32(volatile u32 __iomem *to, void __iowrite32_copy_full(void __iomem *to, const void *from, size_t count); -static inline void __const_iowrite32_copy(void __iomem *to, const void *from, - size_t count) +static __always_inline void +__iowrite32_copy(void __iomem *to, const void *from, size_t count) { - if (count == 8 || count == 4 || count == 2 || count == 1) { + if (__builtin_constant_p(count) && + (count == 8 || count == 4 || count == 2 || count == 1)) { __const_memcpy_toio_aligned32(to, from, count); dgh(); } else { __iowrite32_copy_full(to, from, count); } } +#define __iowrite32_copy __iowrite32_copy -#define __iowrite32_copy(to, from, count) \ - (__builtin_constant_p(count) ? \ - __const_iowrite32_copy(to, from, count) : \ - __iowrite32_copy_full(to, from, count)) - -static inline void __const_memcpy_toio_aligned64(volatile u64 __iomem *to, - const u64 *from, size_t count) +static __always_inline void +__const_memcpy_toio_aligned64(volatile u64 __iomem *to, const u64 *from, + size_t count) { switch (count) { case 8: @@ -255,21 +254,18 @@ static inline void __const_memcpy_toio_aligned64(volatile u64 __iomem *to, void __iowrite64_copy_full(void __iomem *to, const void *from, size_t count); -static inline void __const_iowrite64_copy(void __iomem *to, const void *from, - size_t count) +static __always_inline void +__iowrite64_copy(void __iomem *to, const void *from, size_t count) { - if (count == 8 || count == 4 || count == 2 || count == 1) { + if (__builtin_constant_p(count) && + (count == 8 || count == 4 || count == 2 || count == 1)) { __const_memcpy_toio_aligned64(to, from, count); dgh(); } else { __iowrite64_copy_full(to, from, count); } } - -#define __iowrite64_copy(to, from, count) \ - (__builtin_constant_p(count) ? \ - __const_iowrite64_copy(to, from, count) : \ - __iowrite64_copy_full(to, from, count)) +#define __iowrite64_copy __iowrite64_copy /* * I/O memory mapping functions. diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index dd6ce86d4332..b776e7424fe9 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -462,6 +462,9 @@ static int run_all_insn_set_hw_mode(unsigned int cpu) for (int i = 0; i < ARRAY_SIZE(insn_emulations); i++) { struct insn_emulation *insn = insn_emulations[i]; bool enable = READ_ONCE(insn->current_mode) == INSN_HW; + if (insn->status == INSN_UNAVAILABLE) + continue; + if (insn->set_hw_mode && insn->set_hw_mode(enable)) { pr_warn("CPU[%u] cannot support the emulation of %s", cpu, insn->name); diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 4a92096db34e..712718aed5dd 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -9,6 +9,7 @@ #include <linux/efi.h> #include <linux/init.h> +#include <linux/kmemleak.h> #include <linux/screen_info.h> #include <linux/vmalloc.h> @@ -213,6 +214,7 @@ l: if (!p) { return -ENOMEM; } + kmemleak_not_leak(p); efi_rt_stack_top = p + THREAD_SIZE; return 0; } diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c index 02746f9d0980..efb053af331c 100644 --- a/arch/arm64/kvm/hyp/nvhe/ffa.c +++ b/arch/arm64/kvm/hyp/nvhe/ffa.c @@ -177,6 +177,14 @@ static void ffa_retrieve_req(struct arm_smccc_res *res, u32 len) res); } +static void ffa_rx_release(struct arm_smccc_res *res) +{ + arm_smccc_1_1_smc(FFA_RX_RELEASE, + 0, 0, + 0, 0, 0, 0, 0, + res); +} + static void do_ffa_rxtx_map(struct arm_smccc_res *res, struct kvm_cpu_context *ctxt) { @@ -543,16 +551,19 @@ static void do_ffa_mem_reclaim(struct arm_smccc_res *res, if (WARN_ON(offset > len || fraglen > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE)) { ret = FFA_RET_ABORTED; + ffa_rx_release(res); goto out_unlock; } if (len > ffa_desc_buf.len) { ret = FFA_RET_NO_MEMORY; + ffa_rx_release(res); goto out_unlock; } buf = ffa_desc_buf.buf; memcpy(buf, hyp_buffers.rx, fraglen); + ffa_rx_release(res); for (fragoff = fraglen; fragoff < len; fragoff += fraglen) { ffa_mem_frag_rx(res, handle_lo, handle_hi, fragoff); @@ -563,6 +574,7 @@ static void do_ffa_mem_reclaim(struct arm_smccc_res *res, fraglen = res->a3; memcpy((void *)buf + fragoff, hyp_buffers.rx, fraglen); + ffa_rx_release(res); } ffa_mem_reclaim(res, handle_lo, handle_hi, flags); diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 8f5b7a3e7009..7f68cf58b978 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -391,7 +391,7 @@ static void kvm_vgic_dist_destroy(struct kvm *kvm) if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { list_for_each_entry_safe(rdreg, next, &dist->rd_regions, list) - vgic_v3_free_redist_region(rdreg); + vgic_v3_free_redist_region(kvm, rdreg); INIT_LIST_HEAD(&dist->rd_regions); } else { dist->vgic_cpu_base = VGIC_ADDR_UNDEF; diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index a3983a631b5a..9e50928f5d7d 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -919,8 +919,19 @@ free: return ret; } -void vgic_v3_free_redist_region(struct vgic_redist_region *rdreg) +void vgic_v3_free_redist_region(struct kvm *kvm, struct vgic_redist_region *rdreg) { + struct kvm_vcpu *vcpu; + unsigned long c; + + lockdep_assert_held(&kvm->arch.config_lock); + + /* Garbage collect the region */ + kvm_for_each_vcpu(c, vcpu, kvm) { + if (vcpu->arch.vgic_cpu.rdreg == rdreg) + vcpu->arch.vgic_cpu.rdreg = NULL; + } + list_del(&rdreg->list); kfree(rdreg); } @@ -945,7 +956,7 @@ int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count) mutex_lock(&kvm->arch.config_lock); rdreg = vgic_v3_rdist_region_from_index(kvm, index); - vgic_v3_free_redist_region(rdreg); + vgic_v3_free_redist_region(kvm, rdreg); mutex_unlock(&kvm->arch.config_lock); return ret; } diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index 6106ebd5ba42..03d356a12377 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -316,7 +316,7 @@ vgic_v3_rd_region_size(struct kvm *kvm, struct vgic_redist_region *rdreg) struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm, u32 index); -void vgic_v3_free_redist_region(struct vgic_redist_region *rdreg); +void vgic_v3_free_redist_region(struct kvm *kvm, struct vgic_redist_region *rdreg); bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size); diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c index 9f9486de0004..a3edced29ac1 100644 --- a/arch/arm64/mm/contpte.c +++ b/arch/arm64/mm/contpte.c @@ -376,7 +376,7 @@ void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, * clearing access/dirty for the whole block. */ unsigned long start = addr; - unsigned long end = start + nr; + unsigned long end = start + nr * PAGE_SIZE; if (pte_cont(__ptep_get(ptep + nr - 1))) end = ALIGN(end, CONT_PTE_SIZE); @@ -386,7 +386,7 @@ void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, ptep = contpte_align_down(ptep); } - __clear_young_dirty_ptes(vma, start, ptep, end - start, flags); + __clear_young_dirty_ptes(vma, start, ptep, (end - start) / PAGE_SIZE, flags); } EXPORT_SYMBOL_GPL(contpte_clear_young_dirty_ptes); diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index e38139c576ee..ddc042895d01 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -143,7 +143,7 @@ config LOONGARCH select HAVE_LIVEPATCH select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI - select HAVE_OBJTOOL if AS_HAS_EXPLICIT_RELOCS + select HAVE_OBJTOOL if AS_HAS_EXPLICIT_RELOCS && AS_HAS_THIN_ADD_SUB && !CC_IS_CLANG select HAVE_PCI select HAVE_PERF_EVENTS select HAVE_PERF_REGS @@ -261,6 +261,9 @@ config AS_HAS_EXPLICIT_RELOCS config AS_HAS_FCSR_CLASS def_bool $(as-instr,movfcsr2gr \$t0$(comma)\$fcsr0) +config AS_HAS_THIN_ADD_SUB + def_bool $(cc-option,-Wa$(comma)-mthin-add-sub) + config AS_HAS_LSX_EXTENSION def_bool $(as-instr,vld \$vr0$(comma)\$a0$(comma)0) diff --git a/arch/loongarch/Kconfig.debug b/arch/loongarch/Kconfig.debug index 98d60630c3d4..8b2ce5b5d43e 100644 --- a/arch/loongarch/Kconfig.debug +++ b/arch/loongarch/Kconfig.debug @@ -28,6 +28,7 @@ config UNWINDER_PROLOGUE config UNWINDER_ORC bool "ORC unwinder" + depends on HAVE_OBJTOOL select OBJTOOL help This option enables the ORC (Oops Rewind Capability) unwinder for diff --git a/arch/loongarch/include/asm/hw_breakpoint.h b/arch/loongarch/include/asm/hw_breakpoint.h index 21447fb1efc7..d78330916bd1 100644 --- a/arch/loongarch/include/asm/hw_breakpoint.h +++ b/arch/loongarch/include/asm/hw_breakpoint.h @@ -75,6 +75,8 @@ do { \ #define CSR_MWPC_NUM 0x3f #define CTRL_PLV_ENABLE 0x1e +#define CTRL_PLV0_ENABLE 0x02 +#define CTRL_PLV3_ENABLE 0x10 #define MWPnCFG3_LoadEn 8 #define MWPnCFG3_StoreEn 9 @@ -101,7 +103,7 @@ struct perf_event; struct perf_event_attr; extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, - int *gen_len, int *gen_type, int *offset); + int *gen_len, int *gen_type); extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); extern int hw_breakpoint_arch_parse(struct perf_event *bp, const struct perf_event_attr *attr, diff --git a/arch/loongarch/kernel/hw_breakpoint.c b/arch/loongarch/kernel/hw_breakpoint.c index fc55c4de2a11..621ad7634df7 100644 --- a/arch/loongarch/kernel/hw_breakpoint.c +++ b/arch/loongarch/kernel/hw_breakpoint.c @@ -174,11 +174,21 @@ void flush_ptrace_hw_breakpoint(struct task_struct *tsk) static int hw_breakpoint_control(struct perf_event *bp, enum hw_breakpoint_ops ops) { - u32 ctrl; + u32 ctrl, privilege; int i, max_slots, enable; + struct pt_regs *regs; struct perf_event **slots; struct arch_hw_breakpoint *info = counter_arch_bp(bp); + if (arch_check_bp_in_kernelspace(info)) + privilege = CTRL_PLV0_ENABLE; + else + privilege = CTRL_PLV3_ENABLE; + + /* Whether bp belongs to a task. */ + if (bp->hw.target) + regs = task_pt_regs(bp->hw.target); + if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { /* Breakpoint */ slots = this_cpu_ptr(bp_on_reg); @@ -197,31 +207,38 @@ static int hw_breakpoint_control(struct perf_event *bp, switch (ops) { case HW_BREAKPOINT_INSTALL: /* Set the FWPnCFG/MWPnCFG 1~4 register. */ - write_wb_reg(CSR_CFG_ADDR, i, 0, info->address); - write_wb_reg(CSR_CFG_ADDR, i, 1, info->address); - write_wb_reg(CSR_CFG_MASK, i, 0, info->mask); - write_wb_reg(CSR_CFG_MASK, i, 1, info->mask); - write_wb_reg(CSR_CFG_ASID, i, 0, 0); - write_wb_reg(CSR_CFG_ASID, i, 1, 0); if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { - write_wb_reg(CSR_CFG_CTRL, i, 0, CTRL_PLV_ENABLE); + write_wb_reg(CSR_CFG_ADDR, i, 0, info->address); + write_wb_reg(CSR_CFG_MASK, i, 0, info->mask); + write_wb_reg(CSR_CFG_ASID, i, 0, 0); + write_wb_reg(CSR_CFG_CTRL, i, 0, privilege); } else { + write_wb_reg(CSR_CFG_ADDR, i, 1, info->address); + write_wb_reg(CSR_CFG_MASK, i, 1, info->mask); + write_wb_reg(CSR_CFG_ASID, i, 1, 0); ctrl = encode_ctrl_reg(info->ctrl); - write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl | CTRL_PLV_ENABLE); + write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl | privilege); } enable = csr_read64(LOONGARCH_CSR_CRMD); csr_write64(CSR_CRMD_WE | enable, LOONGARCH_CSR_CRMD); + if (bp->hw.target) + regs->csr_prmd |= CSR_PRMD_PWE; break; case HW_BREAKPOINT_UNINSTALL: /* Reset the FWPnCFG/MWPnCFG 1~4 register. */ - write_wb_reg(CSR_CFG_ADDR, i, 0, 0); - write_wb_reg(CSR_CFG_ADDR, i, 1, 0); - write_wb_reg(CSR_CFG_MASK, i, 0, 0); - write_wb_reg(CSR_CFG_MASK, i, 1, 0); - write_wb_reg(CSR_CFG_CTRL, i, 0, 0); - write_wb_reg(CSR_CFG_CTRL, i, 1, 0); - write_wb_reg(CSR_CFG_ASID, i, 0, 0); - write_wb_reg(CSR_CFG_ASID, i, 1, 0); + if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { + write_wb_reg(CSR_CFG_ADDR, i, 0, 0); + write_wb_reg(CSR_CFG_MASK, i, 0, 0); + write_wb_reg(CSR_CFG_CTRL, i, 0, 0); + write_wb_reg(CSR_CFG_ASID, i, 0, 0); + } else { + write_wb_reg(CSR_CFG_ADDR, i, 1, 0); + write_wb_reg(CSR_CFG_MASK, i, 1, 0); + write_wb_reg(CSR_CFG_CTRL, i, 1, 0); + write_wb_reg(CSR_CFG_ASID, i, 1, 0); + } + if (bp->hw.target) + regs->csr_prmd &= ~CSR_PRMD_PWE; break; } @@ -283,7 +300,7 @@ int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) * to generic breakpoint descriptions. */ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, - int *gen_len, int *gen_type, int *offset) + int *gen_len, int *gen_type) { /* Type */ switch (ctrl.type) { @@ -303,11 +320,6 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, return -EINVAL; } - if (!ctrl.len) - return -EINVAL; - - *offset = __ffs(ctrl.len); - /* Len */ switch (ctrl.len) { case LOONGARCH_BREAKPOINT_LEN_1: @@ -386,21 +398,17 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, struct arch_hw_breakpoint *hw) { int ret; - u64 alignment_mask, offset; + u64 alignment_mask; /* Build the arch_hw_breakpoint. */ ret = arch_build_bp_info(bp, attr, hw); if (ret) return ret; - if (hw->ctrl.type != LOONGARCH_BREAKPOINT_EXECUTE) - alignment_mask = 0x7; - else + if (hw->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { alignment_mask = 0x3; - offset = hw->address & alignment_mask; - - hw->address &= ~alignment_mask; - hw->ctrl.len <<= offset; + hw->address &= ~alignment_mask; + } return 0; } @@ -471,12 +479,15 @@ void breakpoint_handler(struct pt_regs *regs) slots = this_cpu_ptr(bp_on_reg); for (i = 0; i < boot_cpu_data.watch_ireg_count; ++i) { - bp = slots[i]; - if (bp == NULL) - continue; - perf_bp_event(bp, regs); + if ((csr_read32(LOONGARCH_CSR_FWPS) & (0x1 << i))) { + bp = slots[i]; + if (bp == NULL) + continue; + perf_bp_event(bp, regs); + csr_write32(0x1 << i, LOONGARCH_CSR_FWPS); + update_bp_registers(regs, 0, 0); + } } - update_bp_registers(regs, 0, 0); } NOKPROBE_SYMBOL(breakpoint_handler); @@ -488,12 +499,15 @@ void watchpoint_handler(struct pt_regs *regs) slots = this_cpu_ptr(wp_on_reg); for (i = 0; i < boot_cpu_data.watch_dreg_count; ++i) { - wp = slots[i]; - if (wp == NULL) - continue; - perf_bp_event(wp, regs); + if ((csr_read32(LOONGARCH_CSR_MWPS) & (0x1 << i))) { + wp = slots[i]; + if (wp == NULL) + continue; + perf_bp_event(wp, regs); + csr_write32(0x1 << i, LOONGARCH_CSR_MWPS); + update_bp_registers(regs, 0, 1); + } } - update_bp_registers(regs, 0, 1); } NOKPROBE_SYMBOL(watchpoint_handler); diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c index c114c5ef1332..200109de1971 100644 --- a/arch/loongarch/kernel/ptrace.c +++ b/arch/loongarch/kernel/ptrace.c @@ -494,28 +494,14 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type, struct arch_hw_breakpoint_ctrl ctrl, struct perf_event_attr *attr) { - int err, len, type, offset; + int err, len, type; - err = arch_bp_generic_fields(ctrl, &len, &type, &offset); + err = arch_bp_generic_fields(ctrl, &len, &type); if (err) return err; - switch (note_type) { - case NT_LOONGARCH_HW_BREAK: - if ((type & HW_BREAKPOINT_X) != type) - return -EINVAL; - break; - case NT_LOONGARCH_HW_WATCH: - if ((type & HW_BREAKPOINT_RW) != type) - return -EINVAL; - break; - default: - return -EINVAL; - } - attr->bp_len = len; attr->bp_type = type; - attr->bp_addr += offset; return 0; } @@ -609,10 +595,27 @@ static int ptrace_hbp_set_ctrl(unsigned int note_type, return PTR_ERR(bp); attr = bp->attr; - decode_ctrl_reg(uctrl, &ctrl); - err = ptrace_hbp_fill_attr_ctrl(note_type, ctrl, &attr); - if (err) - return err; + + switch (note_type) { + case NT_LOONGARCH_HW_BREAK: + ctrl.type = LOONGARCH_BREAKPOINT_EXECUTE; + ctrl.len = LOONGARCH_BREAKPOINT_LEN_4; + break; + case NT_LOONGARCH_HW_WATCH: + decode_ctrl_reg(uctrl, &ctrl); + break; + default: + return -EINVAL; + } + + if (uctrl & CTRL_PLV_ENABLE) { + err = ptrace_hbp_fill_attr_ctrl(note_type, ctrl, &attr); + if (err) + return err; + attr.disabled = 0; + } else { + attr.disabled = 1; + } return modify_user_hw_breakpoint(bp, &attr); } @@ -643,6 +646,10 @@ static int ptrace_hbp_set_addr(unsigned int note_type, struct perf_event *bp; struct perf_event_attr attr; + /* Kernel-space address cannot be monitored by user-space */ + if ((unsigned long)addr >= XKPRANGE) + return -EINVAL; + bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); if (IS_ERR(bp)) return PTR_ERR(bp); diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c index c86e099af5ca..a68573e091c0 100644 --- a/arch/loongarch/kvm/exit.c +++ b/arch/loongarch/kvm/exit.c @@ -761,7 +761,7 @@ static void kvm_handle_service(struct kvm_vcpu *vcpu) default: ret = KVM_HCALL_INVALID_CODE; break; - }; + } kvm_write_reg(vcpu, LOONGARCH_GPR_A0, ret); } diff --git a/arch/mips/bmips/setup.c b/arch/mips/bmips/setup.c index ec180ab92eaa..66a8ba19c287 100644 --- a/arch/mips/bmips/setup.c +++ b/arch/mips/bmips/setup.c @@ -110,7 +110,8 @@ static void bcm6358_quirks(void) * RAC flush causes kernel panics on BCM6358 when booting from TP1 * because the bootloader is not initializing it properly. */ - bmips_rac_flush_disable = !!(read_c0_brcm_cmt_local() & (1 << 31)); + bmips_rac_flush_disable = !!(read_c0_brcm_cmt_local() & (1 << 31)) || + !!BMIPS_GET_CBR(); } static void bcm6368_quirks(void) diff --git a/arch/mips/include/asm/mipsmtregs.h b/arch/mips/include/asm/mipsmtregs.h index 30e86861c206..b1ee3c48e84b 100644 --- a/arch/mips/include/asm/mipsmtregs.h +++ b/arch/mips/include/asm/mipsmtregs.h @@ -322,7 +322,7 @@ static inline void ehb(void) " .set push \n" \ " .set "MIPS_ISA_LEVEL" \n" \ _ASM_SET_MFTC0 \ - " mftc0 $1, " #rt ", " #sel " \n" \ + " mftc0 %0, " #rt ", " #sel " \n" \ _ASM_UNSET_MFTC0 \ " .set pop \n" \ : "=r" (__res)); \ diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 008ebe60263e..81428a2eb660 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -27,7 +27,7 @@ 17 o32 break sys_ni_syscall # 18 was sys_stat 18 o32 unused18 sys_ni_syscall -19 o32 lseek sys_lseek +19 o32 lseek sys_lseek compat_sys_lseek 20 o32 getpid sys_getpid 21 o32 mount sys_mount 22 o32 umount sys_oldumount diff --git a/arch/mips/pci/ops-rc32434.c b/arch/mips/pci/ops-rc32434.c index 874ed6df9768..34b9323bdabb 100644 --- a/arch/mips/pci/ops-rc32434.c +++ b/arch/mips/pci/ops-rc32434.c @@ -112,8 +112,8 @@ retry: * gives them time to settle */ if (where == PCI_VENDOR_ID) { - if (ret == 0xffffffff || ret == 0x00000000 || - ret == 0x0000ffff || ret == 0xffff0000) { + if (*val == 0xffffffff || *val == 0x00000000 || + *val == 0x0000ffff || *val == 0xffff0000) { if (delay > 4) return 0; delay *= 2; diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index ba4c05bc24d6..8394718870e1 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -31,18 +31,17 @@ void flush_cache_all_local(void); void flush_cache_all(void); void flush_cache_mm(struct mm_struct *mm); -void flush_kernel_dcache_page_addr(const void *addr); - #define flush_kernel_dcache_range(start,size) \ flush_kernel_dcache_range_asm((start), (start)+(size)); +/* The only way to flush a vmap range is to flush whole cache */ #define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 void flush_kernel_vmap_range(void *vaddr, int size); void invalidate_kernel_vmap_range(void *vaddr, int size); -#define flush_cache_vmap(start, end) flush_cache_all() +void flush_cache_vmap(unsigned long start, unsigned long end); #define flush_cache_vmap_early(start, end) do { } while (0) -#define flush_cache_vunmap(start, end) flush_cache_all() +void flush_cache_vunmap(unsigned long start, unsigned long end); void flush_dcache_folio(struct folio *folio); #define flush_dcache_folio flush_dcache_folio @@ -77,17 +76,11 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); -/* defined in pacache.S exported in cache.c used by flush_anon_page */ -void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); - #define ARCH_HAS_FLUSH_ANON_PAGE void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr); #define ARCH_HAS_FLUSH_ON_KUNMAP -static inline void kunmap_flush_on_unmap(const void *addr) -{ - flush_kernel_dcache_page_addr(addr); -} +void kunmap_flush_on_unmap(const void *addr); #endif /* _PARISC_CACHEFLUSH_H */ diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 974accac05cd..babf65751e81 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -448,14 +448,17 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) return pte; } +static inline pte_t ptep_get(pte_t *ptep) +{ + return READ_ONCE(*ptep); +} +#define ptep_get ptep_get + static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t pte; - if (!pte_young(*ptep)) - return 0; - - pte = *ptep; + pte = ptep_get(ptep); if (!pte_young(pte)) { return 0; } @@ -463,17 +466,10 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned return 1; } -struct mm_struct; -static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) -{ - pte_t old_pte; - - old_pte = *ptep; - set_pte(ptep, __pte(0)); - - return old_pte; -} +int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); +pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); +struct mm_struct; static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { set_pte(ptep, pte_wrprotect(*ptep)); @@ -511,7 +507,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -#define __HAVE_ARCH_PTEP_GET_AND_CLEAR +#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +#define __HAVE_ARCH_PTEP_CLEAR_FLUSH #define __HAVE_ARCH_PTEP_SET_WRPROTECT #define __HAVE_ARCH_PTE_SAME diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 422f3e1e6d9c..483bfafd930c 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -20,6 +20,7 @@ #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/syscalls.h> +#include <linux/vmalloc.h> #include <asm/pdc.h> #include <asm/cache.h> #include <asm/cacheflush.h> @@ -31,20 +32,31 @@ #include <asm/mmu_context.h> #include <asm/cachectl.h> +#define PTR_PAGE_ALIGN_DOWN(addr) PTR_ALIGN_DOWN(addr, PAGE_SIZE) + +/* + * When nonzero, use _PAGE_ACCESSED bit to try to reduce the number + * of page flushes done flush_cache_page_if_present. There are some + * pros and cons in using this option. It may increase the risk of + * random segmentation faults. + */ +#define CONFIG_FLUSH_PAGE_ACCESSED 0 + int split_tlb __ro_after_init; int dcache_stride __ro_after_init; int icache_stride __ro_after_init; EXPORT_SYMBOL(dcache_stride); +/* Internal implementation in arch/parisc/kernel/pacache.S */ void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); EXPORT_SYMBOL(flush_dcache_page_asm); void purge_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); void flush_icache_page_asm(unsigned long phys_addr, unsigned long vaddr); - -/* Internal implementation in arch/parisc/kernel/pacache.S */ void flush_data_cache_local(void *); /* flushes local data-cache only */ void flush_instruction_cache_local(void); /* flushes local code-cache only */ +static void flush_kernel_dcache_page_addr(const void *addr); + /* On some machines (i.e., ones with the Merced bus), there can be * only a single PxTLB broadcast at a time; this must be guaranteed * by software. We need a spinlock around all TLB flushes to ensure @@ -321,6 +333,18 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, { if (!static_branch_likely(&parisc_has_cache)) return; + + /* + * The TLB is the engine of coherence on parisc. The CPU is + * entitled to speculate any page with a TLB mapping, so here + * we kill the mapping then flush the page along a special flush + * only alias mapping. This guarantees that the page is no-longer + * in the cache for any process and nor may it be speculatively + * read in (until the user or kernel specifically accesses it, + * of course). + */ + flush_tlb_page(vma, vmaddr); + preempt_disable(); flush_dcache_page_asm(physaddr, vmaddr); if (vma->vm_flags & VM_EXEC) @@ -328,46 +352,44 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, preempt_enable(); } -static void flush_user_cache_page(struct vm_area_struct *vma, unsigned long vmaddr) +static void flush_kernel_dcache_page_addr(const void *addr) { - unsigned long flags, space, pgd, prot; -#ifdef CONFIG_TLB_PTLOCK - unsigned long pgd_lock; -#endif + unsigned long vaddr = (unsigned long)addr; + unsigned long flags; - vmaddr &= PAGE_MASK; + /* Purge TLB entry to remove translation on all CPUs */ + purge_tlb_start(flags); + pdtlb(SR_KERNEL, addr); + purge_tlb_end(flags); + /* Use tmpalias flush to prevent data cache move-in */ preempt_disable(); + flush_dcache_page_asm(__pa(vaddr), vaddr); + preempt_enable(); +} - /* Set context for flush */ - local_irq_save(flags); - prot = mfctl(8); - space = mfsp(SR_USER); - pgd = mfctl(25); -#ifdef CONFIG_TLB_PTLOCK - pgd_lock = mfctl(28); -#endif - switch_mm_irqs_off(NULL, vma->vm_mm, NULL); - local_irq_restore(flags); - - flush_user_dcache_range_asm(vmaddr, vmaddr + PAGE_SIZE); - if (vma->vm_flags & VM_EXEC) - flush_user_icache_range_asm(vmaddr, vmaddr + PAGE_SIZE); - flush_tlb_page(vma, vmaddr); +static void flush_kernel_icache_page_addr(const void *addr) +{ + unsigned long vaddr = (unsigned long)addr; + unsigned long flags; - /* Restore previous context */ - local_irq_save(flags); -#ifdef CONFIG_TLB_PTLOCK - mtctl(pgd_lock, 28); -#endif - mtctl(pgd, 25); - mtsp(space, SR_USER); - mtctl(prot, 8); - local_irq_restore(flags); + /* Purge TLB entry to remove translation on all CPUs */ + purge_tlb_start(flags); + pdtlb(SR_KERNEL, addr); + purge_tlb_end(flags); + /* Use tmpalias flush to prevent instruction cache move-in */ + preempt_disable(); + flush_icache_page_asm(__pa(vaddr), vaddr); preempt_enable(); } +void kunmap_flush_on_unmap(const void *addr) +{ + flush_kernel_dcache_page_addr(addr); +} +EXPORT_SYMBOL(kunmap_flush_on_unmap); + void flush_icache_pages(struct vm_area_struct *vma, struct page *page, unsigned int nr) { @@ -375,13 +397,16 @@ void flush_icache_pages(struct vm_area_struct *vma, struct page *page, for (;;) { flush_kernel_dcache_page_addr(kaddr); - flush_kernel_icache_page(kaddr); + flush_kernel_icache_page_addr(kaddr); if (--nr == 0) break; kaddr += PAGE_SIZE; } } +/* + * Walk page directory for MM to find PTEP pointer for address ADDR. + */ static inline pte_t *get_ptep(struct mm_struct *mm, unsigned long addr) { pte_t *ptep = NULL; @@ -410,6 +435,41 @@ static inline bool pte_needs_flush(pte_t pte) == (_PAGE_PRESENT | _PAGE_ACCESSED); } +/* + * Return user physical address. Returns 0 if page is not present. + */ +static inline unsigned long get_upa(struct mm_struct *mm, unsigned long addr) +{ + unsigned long flags, space, pgd, prot, pa; +#ifdef CONFIG_TLB_PTLOCK + unsigned long pgd_lock; +#endif + + /* Save context */ + local_irq_save(flags); + prot = mfctl(8); + space = mfsp(SR_USER); + pgd = mfctl(25); +#ifdef CONFIG_TLB_PTLOCK + pgd_lock = mfctl(28); +#endif + + /* Set context for lpa_user */ + switch_mm_irqs_off(NULL, mm, NULL); + pa = lpa_user(addr); + + /* Restore previous context */ +#ifdef CONFIG_TLB_PTLOCK + mtctl(pgd_lock, 28); +#endif + mtctl(pgd, 25); + mtsp(space, SR_USER); + mtctl(prot, 8); + local_irq_restore(flags); + + return pa; +} + void flush_dcache_folio(struct folio *folio) { struct address_space *mapping = folio_flush_mapping(folio); @@ -458,50 +518,23 @@ void flush_dcache_folio(struct folio *folio) if (addr + nr * PAGE_SIZE > vma->vm_end) nr = (vma->vm_end - addr) / PAGE_SIZE; - if (parisc_requires_coherency()) { - for (i = 0; i < nr; i++) { - pte_t *ptep = get_ptep(vma->vm_mm, - addr + i * PAGE_SIZE); - if (!ptep) - continue; - if (pte_needs_flush(*ptep)) - flush_user_cache_page(vma, - addr + i * PAGE_SIZE); - /* Optimise accesses to the same table? */ - pte_unmap(ptep); - } - } else { + if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1)) + != (addr & (SHM_COLOUR - 1))) { + for (i = 0; i < nr; i++) + __flush_cache_page(vma, + addr + i * PAGE_SIZE, + (pfn + i) * PAGE_SIZE); /* - * The TLB is the engine of coherence on parisc: - * The CPU is entitled to speculate any page - * with a TLB mapping, so here we kill the - * mapping then flush the page along a special - * flush only alias mapping. This guarantees that - * the page is no-longer in the cache for any - * process and nor may it be speculatively read - * in (until the user or kernel specifically - * accesses it, of course) + * Software is allowed to have any number + * of private mappings to a page. */ - for (i = 0; i < nr; i++) - flush_tlb_page(vma, addr + i * PAGE_SIZE); - if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1)) - != (addr & (SHM_COLOUR - 1))) { - for (i = 0; i < nr; i++) - __flush_cache_page(vma, - addr + i * PAGE_SIZE, - (pfn + i) * PAGE_SIZE); - /* - * Software is allowed to have any number - * of private mappings to a page. - */ - if (!(vma->vm_flags & VM_SHARED)) - continue; - if (old_addr) - pr_err("INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n", - old_addr, addr, vma->vm_file); - if (nr == folio_nr_pages(folio)) - old_addr = addr; - } + if (!(vma->vm_flags & VM_SHARED)) + continue; + if (old_addr) + pr_err("INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n", + old_addr, addr, vma->vm_file); + if (nr == folio_nr_pages(folio)) + old_addr = addr; } WARN_ON(++count == 4096); } @@ -591,35 +624,28 @@ extern void purge_kernel_dcache_page_asm(unsigned long); extern void clear_user_page_asm(void *, unsigned long); extern void copy_user_page_asm(void *, void *, unsigned long); -void flush_kernel_dcache_page_addr(const void *addr) -{ - unsigned long flags; - - flush_kernel_dcache_page_asm(addr); - purge_tlb_start(flags); - pdtlb(SR_KERNEL, addr); - purge_tlb_end(flags); -} -EXPORT_SYMBOL(flush_kernel_dcache_page_addr); - static void flush_cache_page_if_present(struct vm_area_struct *vma, - unsigned long vmaddr, unsigned long pfn) + unsigned long vmaddr) { +#if CONFIG_FLUSH_PAGE_ACCESSED bool needs_flush = false; - pte_t *ptep; + pte_t *ptep, pte; - /* - * The pte check is racy and sometimes the flush will trigger - * a non-access TLB miss. Hopefully, the page has already been - * flushed. - */ ptep = get_ptep(vma->vm_mm, vmaddr); if (ptep) { - needs_flush = pte_needs_flush(*ptep); + pte = ptep_get(ptep); + needs_flush = pte_needs_flush(pte); pte_unmap(ptep); } if (needs_flush) - flush_cache_page(vma, vmaddr, pfn); + __flush_cache_page(vma, vmaddr, PFN_PHYS(pte_pfn(pte))); +#else + struct mm_struct *mm = vma->vm_mm; + unsigned long physaddr = get_upa(mm, vmaddr); + + if (physaddr) + __flush_cache_page(vma, vmaddr, PAGE_ALIGN_DOWN(physaddr)); +#endif } void copy_user_highpage(struct page *to, struct page *from, @@ -629,7 +655,7 @@ void copy_user_highpage(struct page *to, struct page *from, kfrom = kmap_local_page(from); kto = kmap_local_page(to); - flush_cache_page_if_present(vma, vaddr, page_to_pfn(from)); + __flush_cache_page(vma, vaddr, PFN_PHYS(page_to_pfn(from))); copy_page_asm(kto, kfrom); kunmap_local(kto); kunmap_local(kfrom); @@ -638,16 +664,17 @@ void copy_user_highpage(struct page *to, struct page *from, void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long user_vaddr, void *dst, void *src, int len) { - flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page)); + __flush_cache_page(vma, user_vaddr, PFN_PHYS(page_to_pfn(page))); memcpy(dst, src, len); - flush_kernel_dcache_range_asm((unsigned long)dst, (unsigned long)dst + len); + flush_kernel_dcache_page_addr(PTR_PAGE_ALIGN_DOWN(dst)); } void copy_from_user_page(struct vm_area_struct *vma, struct page *page, unsigned long user_vaddr, void *dst, void *src, int len) { - flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page)); + __flush_cache_page(vma, user_vaddr, PFN_PHYS(page_to_pfn(page))); memcpy(dst, src, len); + flush_kernel_dcache_page_addr(PTR_PAGE_ALIGN_DOWN(src)); } /* __flush_tlb_range() @@ -681,32 +708,10 @@ int __flush_tlb_range(unsigned long sid, unsigned long start, static void flush_cache_pages(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - unsigned long addr, pfn; - pte_t *ptep; - - for (addr = start; addr < end; addr += PAGE_SIZE) { - bool needs_flush = false; - /* - * The vma can contain pages that aren't present. Although - * the pte search is expensive, we need the pte to find the - * page pfn and to check whether the page should be flushed. - */ - ptep = get_ptep(vma->vm_mm, addr); - if (ptep) { - needs_flush = pte_needs_flush(*ptep); - pfn = pte_pfn(*ptep); - pte_unmap(ptep); - } - if (needs_flush) { - if (parisc_requires_coherency()) { - flush_user_cache_page(vma, addr); - } else { - if (WARN_ON(!pfn_valid(pfn))) - return; - __flush_cache_page(vma, addr, PFN_PHYS(pfn)); - } - } - } + unsigned long addr; + + for (addr = start; addr < end; addr += PAGE_SIZE) + flush_cache_page_if_present(vma, addr); } static inline unsigned long mm_total_size(struct mm_struct *mm) @@ -757,21 +762,19 @@ void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) return; flush_tlb_range(vma, start, end); - flush_cache_all(); + if (vma->vm_flags & VM_EXEC) + flush_cache_all(); + else + flush_data_cache(); return; } - flush_cache_pages(vma, start, end); + flush_cache_pages(vma, start & PAGE_MASK, end); } void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn) { - if (WARN_ON(!pfn_valid(pfn))) - return; - if (parisc_requires_coherency()) - flush_user_cache_page(vma, vmaddr); - else - __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); + __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); } void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr) @@ -779,34 +782,133 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned lon if (!PageAnon(page)) return; - if (parisc_requires_coherency()) { - if (vma->vm_flags & VM_SHARED) - flush_data_cache(); - else - flush_user_cache_page(vma, vmaddr); + __flush_cache_page(vma, vmaddr, PFN_PHYS(page_to_pfn(page))); +} + +int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep) +{ + pte_t pte = ptep_get(ptep); + + if (!pte_young(pte)) + return 0; + set_pte(ptep, pte_mkold(pte)); +#if CONFIG_FLUSH_PAGE_ACCESSED + __flush_cache_page(vma, addr, PFN_PHYS(pte_pfn(pte))); +#endif + return 1; +} + +/* + * After a PTE is cleared, we have no way to flush the cache for + * the physical page. On PA8800 and PA8900 processors, these lines + * can cause random cache corruption. Thus, we must flush the cache + * as well as the TLB when clearing a PTE that's valid. + */ +pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep) +{ + struct mm_struct *mm = (vma)->vm_mm; + pte_t pte = ptep_get_and_clear(mm, addr, ptep); + unsigned long pfn = pte_pfn(pte); + + if (pfn_valid(pfn)) + __flush_cache_page(vma, addr, PFN_PHYS(pfn)); + else if (pte_accessible(mm, pte)) + flush_tlb_page(vma, addr); + + return pte; +} + +/* + * The physical address for pages in the ioremap case can be obtained + * from the vm_struct struct. I wasn't able to successfully handle the + * vmalloc and vmap cases. We have an array of struct page pointers in + * the uninitialized vmalloc case but the flush failed using page_to_pfn. + */ +void flush_cache_vmap(unsigned long start, unsigned long end) +{ + unsigned long addr, physaddr; + struct vm_struct *vm; + + /* Prevent cache move-in */ + flush_tlb_kernel_range(start, end); + + if (end - start >= parisc_cache_flush_threshold) { + flush_cache_all(); return; } - flush_tlb_page(vma, vmaddr); - preempt_disable(); - flush_dcache_page_asm(page_to_phys(page), vmaddr); - preempt_enable(); + if (WARN_ON_ONCE(!is_vmalloc_addr((void *)start))) { + flush_cache_all(); + return; + } + + vm = find_vm_area((void *)start); + if (WARN_ON_ONCE(!vm)) { + flush_cache_all(); + return; + } + + /* The physical addresses of IOREMAP regions are contiguous */ + if (vm->flags & VM_IOREMAP) { + physaddr = vm->phys_addr; + for (addr = start; addr < end; addr += PAGE_SIZE) { + preempt_disable(); + flush_dcache_page_asm(physaddr, start); + flush_icache_page_asm(physaddr, start); + preempt_enable(); + physaddr += PAGE_SIZE; + } + return; + } + + flush_cache_all(); } +EXPORT_SYMBOL(flush_cache_vmap); +/* + * The vm_struct has been retired and the page table is set up. The + * last page in the range is a guard page. Its physical address can't + * be determined using lpa, so there is no way to flush the range + * using flush_dcache_page_asm. + */ +void flush_cache_vunmap(unsigned long start, unsigned long end) +{ + /* Prevent cache move-in */ + flush_tlb_kernel_range(start, end); + flush_data_cache(); +} +EXPORT_SYMBOL(flush_cache_vunmap); + +/* + * On systems with PA8800/PA8900 processors, there is no way to flush + * a vmap range other than using the architected loop to flush the + * entire cache. The page directory is not set up, so we can't use + * fdc, etc. FDCE/FICE don't work to flush a portion of the cache. + * L2 is physically indexed but FDCE/FICE instructions in virtual + * mode output their virtual address on the core bus, not their + * real address. As a result, the L2 cache index formed from the + * virtual address will most likely not be the same as the L2 index + * formed from the real address. + */ void flush_kernel_vmap_range(void *vaddr, int size) { unsigned long start = (unsigned long)vaddr; unsigned long end = start + size; - if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && - (unsigned long)size >= parisc_cache_flush_threshold) { - flush_tlb_kernel_range(start, end); - flush_data_cache(); + flush_tlb_kernel_range(start, end); + + if (!static_branch_likely(&parisc_has_dcache)) + return; + + /* If interrupts are disabled, we can only do local flush */ + if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) { + flush_data_cache_local(NULL); return; } - flush_kernel_dcache_range_asm(start, end); - flush_tlb_kernel_range(start, end); + flush_data_cache(); } EXPORT_SYMBOL(flush_kernel_vmap_range); @@ -818,15 +920,18 @@ void invalidate_kernel_vmap_range(void *vaddr, int size) /* Ensure DMA is complete */ asm_syncdma(); - if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && - (unsigned long)size >= parisc_cache_flush_threshold) { - flush_tlb_kernel_range(start, end); - flush_data_cache(); + flush_tlb_kernel_range(start, end); + + if (!static_branch_likely(&parisc_has_dcache)) + return; + + /* If interrupts are disabled, we can only do local flush */ + if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) { + flush_data_cache_local(NULL); return; } - purge_kernel_dcache_range_asm(start, end); - flush_tlb_kernel_range(start, end); + flush_data_cache(); } EXPORT_SYMBOL(invalidate_kernel_vmap_range); diff --git a/arch/powerpc/crypto/.gitignore b/arch/powerpc/crypto/.gitignore index e1094f08f713..e9fe73aac8b6 100644 --- a/arch/powerpc/crypto/.gitignore +++ b/arch/powerpc/crypto/.gitignore @@ -1,3 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only aesp10-ppc.S +aesp8-ppc.S ghashp10-ppc.S +ghashp8-ppc.S diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index b569ebaa590e..3ff3de9a52ac 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -130,14 +130,16 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, } rcu_read_unlock(); - fdput(f); - - if (!found) + if (!found) { + fdput(f); return -EINVAL; + } table_group = iommu_group_get_iommudata(grp); - if (WARN_ON(!table_group)) + if (WARN_ON(!table_group)) { + fdput(f); return -EFAULT; + } for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { struct iommu_table *tbltmp = table_group->tables[i]; @@ -158,8 +160,10 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, break; } } - if (!tbl) + if (!tbl) { + fdput(f); return -EINVAL; + } rcu_read_lock(); list_for_each_entry_rcu(stit, &stt->iommu_tables, next) { @@ -170,6 +174,7 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, /* stit is being destroyed */ iommu_tce_table_put(tbl); rcu_read_unlock(); + fdput(f); return -ENOTTY; } /* @@ -177,6 +182,7 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, * its KVM reference counter and can return. */ rcu_read_unlock(); + fdput(f); return 0; } rcu_read_unlock(); @@ -184,6 +190,7 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, stit = kzalloc(sizeof(*stit), GFP_KERNEL); if (!stit) { iommu_tce_table_put(tbl); + fdput(f); return -ENOMEM; } @@ -192,6 +199,7 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, list_add_rcu(&stit->next, &stt->iommu_tables); + fdput(f); return 0; } diff --git a/arch/riscv/boot/dts/sophgo/cv1800b-milkv-duo.dts b/arch/riscv/boot/dts/sophgo/cv1800b-milkv-duo.dts index cd013588adc0..375ff2661b6e 100644 --- a/arch/riscv/boot/dts/sophgo/cv1800b-milkv-duo.dts +++ b/arch/riscv/boot/dts/sophgo/cv1800b-milkv-duo.dts @@ -45,6 +45,7 @@ no-1-8-v; no-mmc; no-sdio; + disable-wp; }; &uart0 { diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index b3fcf7d67efb..5224f3733802 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -293,8 +293,8 @@ void handle_page_fault(struct pt_regs *regs) if (unlikely(access_error(cause, vma))) { vma_end_read(vma); count_vm_vma_lock_event(VMA_LOCK_SUCCESS); - tsk->thread.bad_cause = SEGV_ACCERR; - bad_area_nosemaphore(regs, code, addr); + tsk->thread.bad_cause = cause; + bad_area_nosemaphore(regs, SEGV_ACCERR, addr); return; } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index e3218d65f21d..e3405e4b99af 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -250,18 +250,19 @@ static void __init setup_bootmem(void) kernel_map.va_pa_offset = PAGE_OFFSET - phys_ram_base; /* - * memblock allocator is not aware of the fact that last 4K bytes of - * the addressable memory can not be mapped because of IS_ERR_VALUE - * macro. Make sure that last 4k bytes are not usable by memblock - * if end of dram is equal to maximum addressable memory. For 64-bit - * kernel, this problem can't happen here as the end of the virtual - * address space is occupied by the kernel mapping then this check must - * be done as soon as the kernel mapping base address is determined. + * Reserve physical address space that would be mapped to virtual + * addresses greater than (void *)(-PAGE_SIZE) because: + * - This memory would overlap with ERR_PTR + * - This memory belongs to high memory, which is not supported + * + * This is not applicable to 64-bit kernel, because virtual addresses + * after (void *)(-PAGE_SIZE) are not linearly mapped: they are + * occupied by kernel mapping. Also it is unrealistic for high memory + * to exist on 64-bit platforms. */ if (!IS_ENABLED(CONFIG_64BIT)) { - max_mapped_addr = __pa(~(ulong)0); - if (max_mapped_addr == (phys_ram_end - 1)) - memblock_set_current_limit(max_mapped_addr - 4096); + max_mapped_addr = __va_to_pa_nodebug(-PAGE_SIZE); + memblock_reserve(max_mapped_addr, (phys_addr_t)-max_mapped_addr); } min_low_pfn = PFN_UP(phys_ram_base); diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 182aac6a0f77..48ef5fe5c08a 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -384,7 +384,7 @@ static void fixup_vmlinux_info(void) void startup_kernel(void) { unsigned long kernel_size = vmlinux.image_size + vmlinux.bss_size; - unsigned long nokaslr_offset_phys = mem_safe_offset(); + unsigned long nokaslr_offset_phys, kaslr_large_page_offset; unsigned long amode31_lma = 0; unsigned long max_physmem_end; unsigned long asce_limit; @@ -393,6 +393,12 @@ void startup_kernel(void) fixup_vmlinux_info(); setup_lpp(); + + /* + * Non-randomized kernel physical start address must be _SEGMENT_SIZE + * aligned (see blow). + */ + nokaslr_offset_phys = ALIGN(mem_safe_offset(), _SEGMENT_SIZE); safe_addr = PAGE_ALIGN(nokaslr_offset_phys + kernel_size); /* @@ -425,10 +431,25 @@ void startup_kernel(void) save_ipl_cert_comp_list(); rescue_initrd(safe_addr, ident_map_size); - if (kaslr_enabled()) - __kaslr_offset_phys = randomize_within_range(kernel_size, THREAD_SIZE, 0, ident_map_size); + /* + * __kaslr_offset_phys must be _SEGMENT_SIZE aligned, so the lower + * 20 bits (the offset within a large page) are zero. Copy the last + * 20 bits of __kaslr_offset, which is THREAD_SIZE aligned, to + * __kaslr_offset_phys. + * + * With this the last 20 bits of __kaslr_offset_phys and __kaslr_offset + * are identical, which is required to allow for large mappings of the + * kernel image. + */ + kaslr_large_page_offset = __kaslr_offset & ~_SEGMENT_MASK; + if (kaslr_enabled()) { + unsigned long end = ident_map_size - kaslr_large_page_offset; + + __kaslr_offset_phys = randomize_within_range(kernel_size, _SEGMENT_SIZE, 0, end); + } if (!__kaslr_offset_phys) __kaslr_offset_phys = nokaslr_offset_phys; + __kaslr_offset_phys |= kaslr_large_page_offset; kaslr_adjust_vmlinux_info(__kaslr_offset_phys); physmem_reserve(RR_VMLINUX, __kaslr_offset_phys, kernel_size); deploy_kernel((void *)__kaslr_offset_phys); diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index 96d48b7112d4..40cfce2687c4 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -261,21 +261,27 @@ static unsigned long _pa(unsigned long addr, unsigned long size, enum populate_m static bool large_allowed(enum populate_mode mode) { - return (mode == POPULATE_DIRECT) || (mode == POPULATE_IDENTITY); + return (mode == POPULATE_DIRECT) || (mode == POPULATE_IDENTITY) || (mode == POPULATE_KERNEL); } static bool can_large_pud(pud_t *pu_dir, unsigned long addr, unsigned long end, enum populate_mode mode) { + unsigned long size = end - addr; + return machine.has_edat2 && large_allowed(mode) && - IS_ALIGNED(addr, PUD_SIZE) && (end - addr) >= PUD_SIZE; + IS_ALIGNED(addr, PUD_SIZE) && (size >= PUD_SIZE) && + IS_ALIGNED(_pa(addr, size, mode), PUD_SIZE); } static bool can_large_pmd(pmd_t *pm_dir, unsigned long addr, unsigned long end, enum populate_mode mode) { + unsigned long size = end - addr; + return machine.has_edat1 && large_allowed(mode) && - IS_ALIGNED(addr, PMD_SIZE) && (end - addr) >= PMD_SIZE; + IS_ALIGNED(addr, PMD_SIZE) && (size >= PMD_SIZE) && + IS_ALIGNED(_pa(addr, size, mode), PMD_SIZE); } static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long end, diff --git a/arch/s390/boot/vmlinux.lds.S b/arch/s390/boot/vmlinux.lds.S index 1fe5a1d3ff60..a750711d44c8 100644 --- a/arch/s390/boot/vmlinux.lds.S +++ b/arch/s390/boot/vmlinux.lds.S @@ -109,6 +109,7 @@ SECTIONS #ifdef CONFIG_KERNEL_UNCOMPRESSED . = ALIGN(PAGE_SIZE); . += AMODE31_SIZE; /* .amode31 section */ + . = ALIGN(1 << 20); /* _SEGMENT_SIZE */ #else . = ALIGN(8); #endif diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 145342e46ea8..8c4adece8911 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -43,7 +43,6 @@ CONFIG_PROFILING=y CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y CONFIG_KEXEC_SIG=y -CONFIG_CRASH_DUMP=y CONFIG_LIVEPATCH=y CONFIG_MARCH_Z13=y CONFIG_NR_CPUS=512 @@ -51,6 +50,7 @@ CONFIG_NUMA=y CONFIG_HZ_100=y CONFIG_CERT_STORE=y CONFIG_EXPOLINE=y +# CONFIG_EXPOLINE_EXTERN is not set CONFIG_EXPOLINE_AUTO=y CONFIG_CHSC_SCH=y CONFIG_VFIO_CCW=m @@ -76,6 +76,7 @@ CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y +CONFIG_MODULE_SIG_SHA256=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y @@ -100,7 +101,6 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y -CONFIG_CMA_DEBUG=y CONFIG_CMA_DEBUGFS=y CONFIG_CMA_SYSFS=y CONFIG_CMA_AREAS=7 @@ -119,6 +119,7 @@ CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m CONFIG_SMC_DIAG=m +CONFIG_SMC_LO=y CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_IP_ADVANCED_ROUTER=y @@ -133,7 +134,6 @@ CONFIG_IP_MROUTE=y CONFIG_IP_MROUTE_MULTIPLE_TABLES=y CONFIG_IP_PIMSM_V1=y CONFIG_IP_PIMSM_V2=y -CONFIG_SYN_COOKIES=y CONFIG_NET_IPVTI=m CONFIG_INET_AH=m CONFIG_INET_ESP=m @@ -167,6 +167,7 @@ CONFIG_BRIDGE_NETFILTER=m CONFIG_NETFILTER_NETLINK_HOOK=m CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_ZONES=y CONFIG_NF_CONNTRACK_PROCFS=y CONFIG_NF_CONNTRACK_EVENTS=y CONFIG_NF_CONNTRACK_TIMEOUT=y @@ -183,17 +184,39 @@ CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_CT_NETLINK=m CONFIG_NF_CT_NETLINK_TIMEOUT=m +CONFIG_NF_CT_NETLINK_HELPER=m +CONFIG_NETFILTER_NETLINK_GLUE_CT=y CONFIG_NF_TABLES=m CONFIG_NF_TABLES_INET=y +CONFIG_NF_TABLES_NETDEV=y +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m +CONFIG_NFT_FLOW_OFFLOAD=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m +CONFIG_NFT_MASQ=m +CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m +CONFIG_NFT_TUNNEL=m +CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m -CONFIG_NETFILTER_XTABLES_COMPAT=y +CONFIG_NFT_XFRM=m +CONFIG_NFT_SOCKET=m +CONFIG_NFT_OSF=m +CONFIG_NFT_TPROXY=m +CONFIG_NFT_SYNPROXY=m +CONFIG_NFT_DUP_NETDEV=m +CONFIG_NFT_FWD_NETDEV=m +CONFIG_NFT_FIB_NETDEV=m +CONFIG_NFT_REJECT_NETDEV=m +CONFIG_NF_FLOW_TABLE_INET=m +CONFIG_NF_FLOW_TABLE=m +CONFIG_NF_FLOW_TABLE_PROCFS=y CONFIG_NETFILTER_XT_SET=m CONFIG_NETFILTER_XT_TARGET_AUDIT=m CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m @@ -206,8 +229,10 @@ CONFIG_NETFILTER_XT_TARGET_HMARK=m CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m CONFIG_NETFILTER_XT_TARGET_LOG=m CONFIG_NETFILTER_XT_TARGET_MARK=m +CONFIG_NETFILTER_XT_TARGET_NETMAP=m CONFIG_NETFILTER_XT_TARGET_NFLOG=m CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m +CONFIG_NETFILTER_XT_TARGET_REDIRECT=m CONFIG_NETFILTER_XT_TARGET_TEE=m CONFIG_NETFILTER_XT_TARGET_TPROXY=m CONFIG_NETFILTER_XT_TARGET_TRACE=m @@ -216,6 +241,7 @@ CONFIG_NETFILTER_XT_TARGET_TCPMSS=m CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m CONFIG_NETFILTER_XT_MATCH_BPF=m +CONFIG_NETFILTER_XT_MATCH_CGROUP=m CONFIG_NETFILTER_XT_MATCH_CLUSTER=m CONFIG_NETFILTER_XT_MATCH_COMMENT=m CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m @@ -230,6 +256,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m CONFIG_NETFILTER_XT_MATCH_ESP=m CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m CONFIG_NETFILTER_XT_MATCH_HELPER=m +CONFIG_NETFILTER_XT_MATCH_IPCOMP=m CONFIG_NETFILTER_XT_MATCH_IPRANGE=m CONFIG_NETFILTER_XT_MATCH_IPVS=m CONFIG_NETFILTER_XT_MATCH_LENGTH=m @@ -247,6 +274,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m CONFIG_NETFILTER_XT_MATCH_REALM=m CONFIG_NETFILTER_XT_MATCH_RECENT=m +CONFIG_NETFILTER_XT_MATCH_SOCKET=m CONFIG_NETFILTER_XT_MATCH_STATE=m CONFIG_NETFILTER_XT_MATCH_STATISTIC=m CONFIG_NETFILTER_XT_MATCH_STRING=m @@ -302,7 +330,6 @@ CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m CONFIG_IP_NF_RAW=m CONFIG_IP_NF_SECURITY=m -CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NFT_FIB_IPV6=m @@ -373,7 +400,6 @@ CONFIG_NET_ACT_POLICE=m CONFIG_NET_ACT_GACT=m CONFIG_GACT_PROB=y CONFIG_NET_ACT_MIRRED=m -CONFIG_NET_ACT_IPT=m CONFIG_NET_ACT_NAT=m CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m @@ -462,6 +488,7 @@ CONFIG_DM_VERITY=m CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y CONFIG_DM_SWITCH=m CONFIG_DM_INTEGRITY=m +CONFIG_DM_VDO=m CONFIG_NETDEVICES=y CONFIG_BONDING=m CONFIG_DUMMY=m @@ -574,7 +601,6 @@ CONFIG_WATCHDOG=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m -# CONFIG_DRM_DEBUG_MODESET_LOCK is not set CONFIG_FB=y # CONFIG_FB_DEVICE is not set CONFIG_FRAMEBUFFER_CONSOLE=y @@ -645,7 +671,6 @@ CONFIG_MSDOS_FS=m CONFIG_VFAT_FS=m CONFIG_EXFAT_FS=m CONFIG_NTFS_FS=m -CONFIG_NTFS_RW=y CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y @@ -663,6 +688,7 @@ CONFIG_SQUASHFS_XZ=y CONFIG_SQUASHFS_ZSTD=y CONFIG_ROMFS_FS=m CONFIG_NFS_FS=m +CONFIG_NFS_V2=m CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=m CONFIG_NFS_SWAP=y @@ -879,6 +905,5 @@ CONFIG_RBTREE_TEST=y CONFIG_INTERVAL_TREE_TEST=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y -CONFIG_STRING_SELFTEST=y CONFIG_TEST_BITOPS=m CONFIG_TEST_BPF=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index dc237896f99d..6dd11d3b6aaa 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -41,7 +41,6 @@ CONFIG_PROFILING=y CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y CONFIG_KEXEC_SIG=y -CONFIG_CRASH_DUMP=y CONFIG_LIVEPATCH=y CONFIG_MARCH_Z13=y CONFIG_NR_CPUS=512 @@ -49,6 +48,7 @@ CONFIG_NUMA=y CONFIG_HZ_100=y CONFIG_CERT_STORE=y CONFIG_EXPOLINE=y +# CONFIG_EXPOLINE_EXTERN is not set CONFIG_EXPOLINE_AUTO=y CONFIG_CHSC_SCH=y CONFIG_VFIO_CCW=m @@ -71,6 +71,7 @@ CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y +CONFIG_MODULE_SIG_SHA256=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y @@ -110,6 +111,7 @@ CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m CONFIG_SMC_DIAG=m +CONFIG_SMC_LO=y CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_IP_ADVANCED_ROUTER=y @@ -124,7 +126,6 @@ CONFIG_IP_MROUTE=y CONFIG_IP_MROUTE_MULTIPLE_TABLES=y CONFIG_IP_PIMSM_V1=y CONFIG_IP_PIMSM_V2=y -CONFIG_SYN_COOKIES=y CONFIG_NET_IPVTI=m CONFIG_INET_AH=m CONFIG_INET_ESP=m @@ -158,6 +159,7 @@ CONFIG_BRIDGE_NETFILTER=m CONFIG_NETFILTER_NETLINK_HOOK=m CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_ZONES=y CONFIG_NF_CONNTRACK_PROCFS=y CONFIG_NF_CONNTRACK_EVENTS=y CONFIG_NF_CONNTRACK_TIMEOUT=y @@ -174,17 +176,39 @@ CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_CT_NETLINK=m CONFIG_NF_CT_NETLINK_TIMEOUT=m +CONFIG_NF_CT_NETLINK_HELPER=m +CONFIG_NETFILTER_NETLINK_GLUE_CT=y CONFIG_NF_TABLES=m CONFIG_NF_TABLES_INET=y +CONFIG_NF_TABLES_NETDEV=y +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m +CONFIG_NFT_FLOW_OFFLOAD=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m +CONFIG_NFT_MASQ=m +CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m +CONFIG_NFT_TUNNEL=m +CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m -CONFIG_NETFILTER_XTABLES_COMPAT=y +CONFIG_NFT_XFRM=m +CONFIG_NFT_SOCKET=m +CONFIG_NFT_OSF=m +CONFIG_NFT_TPROXY=m +CONFIG_NFT_SYNPROXY=m +CONFIG_NFT_DUP_NETDEV=m +CONFIG_NFT_FWD_NETDEV=m +CONFIG_NFT_FIB_NETDEV=m +CONFIG_NFT_REJECT_NETDEV=m +CONFIG_NF_FLOW_TABLE_INET=m +CONFIG_NF_FLOW_TABLE=m +CONFIG_NF_FLOW_TABLE_PROCFS=y CONFIG_NETFILTER_XT_SET=m CONFIG_NETFILTER_XT_TARGET_AUDIT=m CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m @@ -197,8 +221,10 @@ CONFIG_NETFILTER_XT_TARGET_HMARK=m CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m CONFIG_NETFILTER_XT_TARGET_LOG=m CONFIG_NETFILTER_XT_TARGET_MARK=m +CONFIG_NETFILTER_XT_TARGET_NETMAP=m CONFIG_NETFILTER_XT_TARGET_NFLOG=m CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m +CONFIG_NETFILTER_XT_TARGET_REDIRECT=m CONFIG_NETFILTER_XT_TARGET_TEE=m CONFIG_NETFILTER_XT_TARGET_TPROXY=m CONFIG_NETFILTER_XT_TARGET_TRACE=m @@ -207,6 +233,7 @@ CONFIG_NETFILTER_XT_TARGET_TCPMSS=m CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m CONFIG_NETFILTER_XT_MATCH_BPF=m +CONFIG_NETFILTER_XT_MATCH_CGROUP=m CONFIG_NETFILTER_XT_MATCH_CLUSTER=m CONFIG_NETFILTER_XT_MATCH_COMMENT=m CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m @@ -221,6 +248,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m CONFIG_NETFILTER_XT_MATCH_ESP=m CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m CONFIG_NETFILTER_XT_MATCH_HELPER=m +CONFIG_NETFILTER_XT_MATCH_IPCOMP=m CONFIG_NETFILTER_XT_MATCH_IPRANGE=m CONFIG_NETFILTER_XT_MATCH_IPVS=m CONFIG_NETFILTER_XT_MATCH_LENGTH=m @@ -238,6 +266,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m CONFIG_NETFILTER_XT_MATCH_REALM=m CONFIG_NETFILTER_XT_MATCH_RECENT=m +CONFIG_NETFILTER_XT_MATCH_SOCKET=m CONFIG_NETFILTER_XT_MATCH_STATE=m CONFIG_NETFILTER_XT_MATCH_STATISTIC=m CONFIG_NETFILTER_XT_MATCH_STRING=m @@ -293,7 +322,6 @@ CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m CONFIG_IP_NF_RAW=m CONFIG_IP_NF_SECURITY=m -CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NFT_FIB_IPV6=m @@ -363,7 +391,6 @@ CONFIG_NET_ACT_POLICE=m CONFIG_NET_ACT_GACT=m CONFIG_GACT_PROB=y CONFIG_NET_ACT_MIRRED=m -CONFIG_NET_ACT_IPT=m CONFIG_NET_ACT_NAT=m CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m @@ -452,6 +479,7 @@ CONFIG_DM_VERITY=m CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y CONFIG_DM_SWITCH=m CONFIG_DM_INTEGRITY=m +CONFIG_DM_VDO=m CONFIG_NETDEVICES=y CONFIG_BONDING=m CONFIG_DUMMY=m @@ -630,7 +658,6 @@ CONFIG_MSDOS_FS=m CONFIG_VFAT_FS=m CONFIG_EXFAT_FS=m CONFIG_NTFS_FS=m -CONFIG_NTFS_RW=y CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y @@ -649,6 +676,7 @@ CONFIG_SQUASHFS_XZ=y CONFIG_SQUASHFS_ZSTD=y CONFIG_ROMFS_FS=m CONFIG_NFS_FS=m +CONFIG_NFS_V2=m CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=m CONFIG_NFS_SWAP=y diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index c51f3ec4eb28..8c2b61363bab 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -9,25 +9,22 @@ CONFIG_BPF_SYSCALL=y CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_KEXEC=y -CONFIG_CRASH_DUMP=y CONFIG_MARCH_Z13=y CONFIG_NR_CPUS=2 CONFIG_HZ_100=y # CONFIG_CHSC_SCH is not set # CONFIG_SCM_BUS is not set +# CONFIG_AP is not set # CONFIG_PFAULT is not set # CONFIG_S390_HYPFS is not set # CONFIG_VIRTUALIZATION is not set # CONFIG_S390_GUEST is not set # CONFIG_SECCOMP is not set -# CONFIG_GCC_PLUGINS is not set # CONFIG_BLOCK_LEGACY_AUTOLOAD is not set CONFIG_PARTITION_ADVANCED=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set # CONFIG_SWAP is not set # CONFIG_COMPAT_BRK is not set -# CONFIG_COMPACTION is not set -# CONFIG_MIGRATION is not set CONFIG_NET=y # CONFIG_IUCV is not set # CONFIG_PCPU_DEV_REFCNT is not set diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index 9863ebe75019..edae13416196 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -451,7 +451,7 @@ static void *nt_final(void *ptr) /* * Initialize ELF header (new kernel) */ -static void *ehdr_init(Elf64_Ehdr *ehdr, int mem_chunk_cnt) +static void *ehdr_init(Elf64_Ehdr *ehdr, int phdr_count) { memset(ehdr, 0, sizeof(*ehdr)); memcpy(ehdr->e_ident, ELFMAG, SELFMAG); @@ -465,11 +465,8 @@ static void *ehdr_init(Elf64_Ehdr *ehdr, int mem_chunk_cnt) ehdr->e_phoff = sizeof(Elf64_Ehdr); ehdr->e_ehsize = sizeof(Elf64_Ehdr); ehdr->e_phentsize = sizeof(Elf64_Phdr); - /* - * Number of memory chunk PT_LOAD program headers plus one kernel - * image PT_LOAD program header plus one PT_NOTE program header. - */ - ehdr->e_phnum = mem_chunk_cnt + 1 + 1; + /* Number of PT_LOAD program headers plus PT_NOTE program header */ + ehdr->e_phnum = phdr_count + 1; return ehdr + 1; } @@ -503,12 +500,14 @@ static int get_mem_chunk_cnt(void) /* * Initialize ELF loads (new kernel) */ -static void loads_init(Elf64_Phdr *phdr) +static void loads_init(Elf64_Phdr *phdr, bool os_info_has_vm) { - unsigned long old_identity_base = os_info_old_value(OS_INFO_IDENTITY_BASE); + unsigned long old_identity_base = 0; phys_addr_t start, end; u64 idx; + if (os_info_has_vm) + old_identity_base = os_info_old_value(OS_INFO_IDENTITY_BASE); for_each_physmem_range(idx, &oldmem_type, &start, &end) { phdr->p_type = PT_LOAD; phdr->p_vaddr = old_identity_base + start; @@ -522,6 +521,11 @@ static void loads_init(Elf64_Phdr *phdr) } } +static bool os_info_has_vm(void) +{ + return os_info_old_value(OS_INFO_KASLR_OFFSET); +} + /* * Prepare PT_LOAD type program header for kernel image region */ @@ -566,7 +570,7 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset) return ptr; } -static size_t get_elfcorehdr_size(int mem_chunk_cnt) +static size_t get_elfcorehdr_size(int phdr_count) { size_t size; @@ -581,10 +585,8 @@ static size_t get_elfcorehdr_size(int mem_chunk_cnt) size += nt_vmcoreinfo_size(); /* nt_final */ size += sizeof(Elf64_Nhdr); - /* PT_LOAD type program header for kernel text region */ - size += sizeof(Elf64_Phdr); /* PT_LOADS */ - size += mem_chunk_cnt * sizeof(Elf64_Phdr); + size += phdr_count * sizeof(Elf64_Phdr); return size; } @@ -595,8 +597,8 @@ static size_t get_elfcorehdr_size(int mem_chunk_cnt) int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) { Elf64_Phdr *phdr_notes, *phdr_loads, *phdr_text; + int mem_chunk_cnt, phdr_text_cnt; size_t alloc_size; - int mem_chunk_cnt; void *ptr, *hdr; u64 hdr_off; @@ -615,12 +617,14 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) } mem_chunk_cnt = get_mem_chunk_cnt(); + phdr_text_cnt = os_info_has_vm() ? 1 : 0; - alloc_size = get_elfcorehdr_size(mem_chunk_cnt); + alloc_size = get_elfcorehdr_size(mem_chunk_cnt + phdr_text_cnt); hdr = kzalloc(alloc_size, GFP_KERNEL); - /* Without elfcorehdr /proc/vmcore cannot be created. Thus creating + /* + * Without elfcorehdr /proc/vmcore cannot be created. Thus creating * a dump with this crash kernel will fail. Panic now to allow other * dump mechanisms to take over. */ @@ -628,21 +632,23 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) panic("s390 kdump allocating elfcorehdr failed"); /* Init elf header */ - ptr = ehdr_init(hdr, mem_chunk_cnt); + phdr_notes = ehdr_init(hdr, mem_chunk_cnt + phdr_text_cnt); /* Init program headers */ - phdr_notes = ptr; - ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr)); - phdr_text = ptr; - ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr)); - phdr_loads = ptr; - ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr) * mem_chunk_cnt); + if (phdr_text_cnt) { + phdr_text = phdr_notes + 1; + phdr_loads = phdr_text + 1; + } else { + phdr_loads = phdr_notes + 1; + } + ptr = PTR_ADD(phdr_loads, sizeof(Elf64_Phdr) * mem_chunk_cnt); /* Init notes */ hdr_off = PTR_DIFF(ptr, hdr); ptr = notes_init(phdr_notes, ptr, ((unsigned long) hdr) + hdr_off); /* Init kernel text program header */ - text_init(phdr_text); + if (phdr_text_cnt) + text_init(phdr_text); /* Init loads */ - loads_init(phdr_loads); + loads_init(phdr_loads, phdr_text_cnt); /* Finalize program headers */ hdr_off = PTR_DIFF(ptr, hdr); *addr = (unsigned long long) hdr; diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 243ee86cb1b1..f2051644de94 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -105,9 +105,9 @@ vmlinux-objs-$(CONFIG_UNACCEPTED_MEMORY) += $(obj)/mem.o vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_mixed.o -vmlinux-objs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a +vmlinux-libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a -$(obj)/vmlinux: $(vmlinux-objs-y) FORCE +$(obj)/vmlinux: $(vmlinux-objs-y) $(vmlinux-libs-y) FORCE $(call if_changed,ld) OBJCOPYFLAGS_vmlinux.bin := -R .comment -S diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 1dc600fa3ba5..481096177500 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -401,7 +401,6 @@ extern int __init efi_memmap_alloc(unsigned int num_entries, struct efi_memory_map_data *data); extern void __efi_memmap_free(u64 phys, unsigned long size, unsigned long flags); -#define __efi_memmap_free __efi_memmap_free extern int __init efi_memmap_install(struct efi_memory_map_data *data); extern int __init efi_memmap_split_count(efi_memory_desc_t *md, diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 0f9bab92a43d..3a7755c1a441 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -78,10 +78,10 @@ extern int __get_user_bad(void); int __ret_gu; \ register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \ __chk_user_ptr(ptr); \ - asm volatile("call __" #fn "_%c4" \ + asm volatile("call __" #fn "_%c[size]" \ : "=a" (__ret_gu), "=r" (__val_gu), \ ASM_CALL_CONSTRAINT \ - : "0" (ptr), "i" (sizeof(*(ptr)))); \ + : "0" (ptr), [size] "i" (sizeof(*(ptr)))); \ instrument_get_user(__val_gu); \ (x) = (__force __typeof__(*(ptr))) __val_gu; \ __builtin_expect(__ret_gu, 0); \ diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 3cf156f70859..027a8c7a2c9e 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -215,7 +215,14 @@ out: int amd_smn_read(u16 node, u32 address, u32 *value) { - return __amd_smn_rw(node, address, value, false); + int err = __amd_smn_rw(node, address, value, false); + + if (PCI_POSSIBLE_ERROR(*value)) { + err = -ENODEV; + *value = 0; + } + + return err; } EXPORT_SYMBOL_GPL(amd_smn_read); diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 2345e6836593..366f496ca3ce 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -519,7 +519,8 @@ void free_rmid(u32 closid, u32 rmid) * allows architectures that ignore the closid parameter to avoid an * unnecessary check. */ - if (idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID, + if (!resctrl_arch_mon_capable() || + idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID, RESCTRL_RESERVED_RMID)) return; diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index b180d8e497c3..cc0f7f70b17b 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -295,8 +295,15 @@ void machine_kexec_cleanup(struct kimage *image) void machine_kexec(struct kimage *image) { unsigned long page_list[PAGES_NR]; - void *control_page; + unsigned int host_mem_enc_active; int save_ftrace_enabled; + void *control_page; + + /* + * This must be done before load_segments() since if call depth tracking + * is used then GS must be valid to make any function calls. + */ + host_mem_enc_active = cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT); #ifdef CONFIG_KEXEC_JUMP if (image->preserve_context) @@ -358,7 +365,7 @@ void machine_kexec(struct kimage *image) (unsigned long)page_list, image->start, image->preserve_context, - cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)); + host_mem_enc_active); #ifdef CONFIG_KEXEC_JUMP if (image->preserve_context) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 296c524988f9..c95d3900fe56 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2843,7 +2843,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (sev_es_prevent_msr_access(vcpu, msr_info)) { msr_info->data = 0; - return -EINVAL; + return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; } switch (msr_info->index) { @@ -2998,7 +2998,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) u64 data = msr->data; if (sev_es_prevent_msr_access(vcpu, msr)) - return -EINVAL; + return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; switch (ecx) { case MSR_AMD64_TSC_RATIO: diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8c9e4281d978..0763a0f72a06 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10718,13 +10718,12 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256); + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); + if (irqchip_split(vcpu->kvm)) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); - else { - static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); - if (ioapic_in_kernel(vcpu->kvm)) - kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); - } + else if (ioapic_in_kernel(vcpu->kvm)) + kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); if (is_guest_mode(vcpu)) vcpu->arch.load_eoi_exitmap_pending = true; diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index 10d5ed8b5990..a1cb3a4e6742 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -44,7 +44,11 @@ or %rdx, %rax .else cmp $TASK_SIZE_MAX-\size+1, %eax +.if \size != 8 jae .Lbad_get_user +.else + jae .Lbad_get_user_8 +.endif sbb %edx, %edx /* array_index_mask_nospec() */ and %edx, %eax .endif @@ -154,7 +158,7 @@ SYM_CODE_END(__get_user_handle_exception) #ifdef CONFIG_X86_32 SYM_CODE_START_LOCAL(__get_user_8_handle_exception) ASM_CLAC -bad_get_user_8: +.Lbad_get_user_8: xor %edx,%edx xor %ecx,%ecx mov $(-EFAULT),%_ASM_AX diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index ce84ba86e69e..6ce10e3c6228 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -493,7 +493,7 @@ static void __init numa_clear_kernel_node_hotplug(void) for_each_reserved_mem_region(mb_region) { int nid = memblock_get_region_node(mb_region); - if (nid != MAX_NUMNODES) + if (nid != NUMA_NO_NODE) node_set(nid, reserved_nodemask); } @@ -614,9 +614,9 @@ static int __init numa_init(int (*init_func)(void)) nodes_clear(node_online_map); memset(&numa_meminfo, 0, sizeof(numa_meminfo)); WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory, - MAX_NUMNODES)); + NUMA_NO_NODE)); WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.reserved, - MAX_NUMNODES)); + NUMA_NO_NODE)); /* In case that parsing SRAT failed. */ WARN_ON(memblock_clear_hotplug(0, ULLONG_MAX)); numa_reset_distance(); diff --git a/arch/x86/platform/efi/memmap.c b/arch/x86/platform/efi/memmap.c index 4ef20b49eb5e..6ed1935504b9 100644 --- a/arch/x86/platform/efi/memmap.c +++ b/arch/x86/platform/efi/memmap.c @@ -92,12 +92,22 @@ int __init efi_memmap_alloc(unsigned int num_entries, */ int __init efi_memmap_install(struct efi_memory_map_data *data) { + unsigned long size = efi.memmap.desc_size * efi.memmap.nr_map; + unsigned long flags = efi.memmap.flags; + u64 phys = efi.memmap.phys_map; + int ret; + efi_memmap_unmap(); if (efi_enabled(EFI_PARAVIRT)) return 0; - return __efi_memmap_init(data); + ret = __efi_memmap_init(data); + if (ret) + return ret; + + __efi_memmap_free(phys, size, flags); + return 0; } /** diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 2e3e8e04961e..8b528e12136f 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -144,10 +144,10 @@ void bio_integrity_free(struct bio *bio) struct bio_integrity_payload *bip = bio_integrity(bio); struct bio_set *bs = bio->bi_pool; + if (bip->bip_flags & BIP_INTEGRITY_USER) + return; if (bip->bip_flags & BIP_BLOCK_INTEGRITY) kfree(bvec_virt(bip->bip_vec)); - else if (bip->bip_flags & BIP_INTEGRITY_USER) - bio_integrity_unmap_user(bip); __bio_integrity_free(bs, bip); bio->bi_integrity = NULL; @@ -155,6 +155,28 @@ void bio_integrity_free(struct bio *bio) } /** + * bio_integrity_unmap_free_user - Unmap and free bio user integrity payload + * @bio: bio containing bip to be unmapped and freed + * + * Description: Used to unmap and free the user mapped integrity portion of a + * bio. Submitter attaching the user integrity buffer is responsible for + * unmapping and freeing it during completion. + */ +void bio_integrity_unmap_free_user(struct bio *bio) +{ + struct bio_integrity_payload *bip = bio_integrity(bio); + struct bio_set *bs = bio->bi_pool; + + if (WARN_ON_ONCE(!(bip->bip_flags & BIP_INTEGRITY_USER))) + return; + bio_integrity_unmap_user(bip); + __bio_integrity_free(bs, bip); + bio->bi_integrity = NULL; + bio->bi_opf &= ~REQ_INTEGRITY; +} +EXPORT_SYMBOL(bio_integrity_unmap_free_user); + +/** * bio_integrity_add_page - Attach integrity metadata * @bio: bio to update * @page: page containing integrity metadata diff --git a/block/blk-flush.c b/block/blk-flush.c index c17cf8ed8113..cca4f9131f79 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -185,7 +185,7 @@ static void blk_flush_complete_seq(struct request *rq, /* queue for flush */ if (list_empty(pending)) fq->flush_pending_since = jiffies; - list_move_tail(&rq->queuelist, pending); + list_add_tail(&rq->queuelist, pending); break; case REQ_FSEQ_DATA: @@ -263,6 +263,7 @@ static enum rq_end_io_ret flush_end_io(struct request *flush_rq, unsigned int seq = blk_flush_cur_seq(rq); BUG_ON(seq != REQ_FSEQ_PREFLUSH && seq != REQ_FSEQ_POSTFLUSH); + list_del_init(&rq->queuelist); blk_flush_complete_seq(rq, fq, seq, error); } diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 52abebf56027..08d7dfe8bd93 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -1552,6 +1552,9 @@ static void disk_destroy_zone_wplugs_hash_table(struct gendisk *disk) void disk_free_zone_resources(struct gendisk *disk) { + if (!disk->zone_wplugs_pool) + return; + cancel_work_sync(&disk->zone_wplugs_work); if (disk->zone_wplugs_wq) { diff --git a/block/sed-opal.c b/block/sed-opal.c index 14fe0fef811c..598fd3e7fcc8 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -314,7 +314,7 @@ static int read_sed_opal_key(const char *key_name, u_char *buffer, int buflen) &key_type_user, key_name, true); if (IS_ERR(kref)) - ret = PTR_ERR(kref); + return PTR_ERR(kref); key = key_ref_to_ptr(kref); down_read(&key->sem); diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h index ddd072cbc738..2133085deda7 100644 --- a/drivers/acpi/acpica/acevents.h +++ b/drivers/acpi/acpica/acevents.h @@ -191,6 +191,10 @@ void acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, acpi_adr_space_type space_id, u32 function); +void +acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *node, + acpi_adr_space_type space_id); + acpi_status acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function); diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c index 18fdf2bc2d49..dc6004daf624 100644 --- a/drivers/acpi/acpica/evregion.c +++ b/drivers/acpi/acpica/evregion.c @@ -20,10 +20,6 @@ extern u8 acpi_gbl_default_address_spaces[]; /* Local prototypes */ -static void -acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *device_node, - acpi_adr_space_type space_id); - static acpi_status acpi_ev_reg_run(acpi_handle obj_handle, u32 level, void *context, void **return_value); @@ -818,7 +814,7 @@ acpi_ev_reg_run(acpi_handle obj_handle, * ******************************************************************************/ -static void +void acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *device_node, acpi_adr_space_type space_id) { diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c index 3197e6303c5b..624361a5f34d 100644 --- a/drivers/acpi/acpica/evxfregn.c +++ b/drivers/acpi/acpica/evxfregn.c @@ -306,3 +306,57 @@ acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id) } ACPI_EXPORT_SYMBOL(acpi_execute_reg_methods) + +/******************************************************************************* + * + * FUNCTION: acpi_execute_orphan_reg_method + * + * PARAMETERS: device - Handle for the device + * space_id - The address space ID + * + * RETURN: Status + * + * DESCRIPTION: Execute an "orphan" _REG method that appears under an ACPI + * device. This is a _REG method that has no corresponding region + * within the device's scope. + * + ******************************************************************************/ +acpi_status +acpi_execute_orphan_reg_method(acpi_handle device, acpi_adr_space_type space_id) +{ + struct acpi_namespace_node *node; + acpi_status status; + + ACPI_FUNCTION_TRACE(acpi_execute_orphan_reg_method); + + /* Parameter validation */ + + if (!device) { + return_ACPI_STATUS(AE_BAD_PARAMETER); + } + + status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE); + if (ACPI_FAILURE(status)) { + return_ACPI_STATUS(status); + } + + /* Convert and validate the device handle */ + + node = acpi_ns_validate_handle(device); + if (node) { + + /* + * If an "orphan" _REG method is present in the device's scope + * for the given address space ID, run it. + */ + + acpi_ev_execute_orphan_reg_method(node, space_id); + } else { + status = AE_BAD_PARAMETER; + } + + (void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE); + return_ACPI_STATUS(status); +} + +ACPI_EXPORT_SYMBOL(acpi_execute_orphan_reg_method) diff --git a/drivers/acpi/acpica/exregion.c b/drivers/acpi/acpica/exregion.c index 8907b8bf4267..c49b9f8de723 100644 --- a/drivers/acpi/acpica/exregion.c +++ b/drivers/acpi/acpica/exregion.c @@ -44,7 +44,6 @@ acpi_ex_system_memory_space_handler(u32 function, struct acpi_mem_mapping *mm = mem_info->cur_mm; u32 length; acpi_size map_length; - acpi_size page_boundary_map_length; #ifdef ACPI_MISALIGNMENT_NOT_SUPPORTED u32 remainder; #endif @@ -138,26 +137,8 @@ acpi_ex_system_memory_space_handler(u32 function, map_length = (acpi_size) ((mem_info->address + mem_info->length) - address); - /* - * If mapping the entire remaining portion of the region will cross - * a page boundary, just map up to the page boundary, do not cross. - * On some systems, crossing a page boundary while mapping regions - * can cause warnings if the pages have different attributes - * due to resource management. - * - * This has the added benefit of constraining a single mapping to - * one page, which is similar to the original code that used a 4k - * maximum window. - */ - page_boundary_map_length = (acpi_size) - (ACPI_ROUND_UP(address, ACPI_DEFAULT_PAGE_SIZE) - address); - if (page_boundary_map_length == 0) { - page_boundary_map_length = ACPI_DEFAULT_PAGE_SIZE; - } - - if (map_length > page_boundary_map_length) { - map_length = page_boundary_map_length; - } + if (map_length > ACPI_DEFAULT_PAGE_SIZE) + map_length = ACPI_DEFAULT_PAGE_SIZE; /* Create a new mapping starting at the address given */ diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 68dd17f96f63..299ec653388c 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1507,6 +1507,9 @@ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device, if (call_reg && !test_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags)) { acpi_execute_reg_methods(scope_handle, ACPI_ADR_SPACE_EC); + if (scope_handle != ec->handle) + acpi_execute_orphan_reg_method(ec->handle, ACPI_ADR_SPACE_EC); + set_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags); } diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 2a0e9fc7b74c..601b670356e5 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -302,6 +302,10 @@ void acpi_mipi_check_crs_csi2(acpi_handle handle); void acpi_mipi_scan_crs_csi2(void); void acpi_mipi_init_crs_csi2_swnodes(void); void acpi_mipi_crs_csi2_cleanup(void); +#ifdef CONFIG_X86 bool acpi_graph_ignore_port(acpi_handle handle); +#else +static inline bool acpi_graph_ignore_port(acpi_handle handle) { return false; } +#endif #endif /* _ACPI_INTERNAL_H_ */ diff --git a/drivers/acpi/mipi-disco-img.c b/drivers/acpi/mipi-disco-img.c index d05413a0672a..92b658f92dc0 100644 --- a/drivers/acpi/mipi-disco-img.c +++ b/drivers/acpi/mipi-disco-img.c @@ -725,14 +725,20 @@ void acpi_mipi_crs_csi2_cleanup(void) acpi_mipi_del_crs_csi2(csi2); } -static const struct dmi_system_id dmi_ignore_port_nodes[] = { - { - .matches = { - DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "XPS 9315"), - }, - }, - { } +#ifdef CONFIG_X86 +#include <asm/cpu_device_id.h> +#include <asm/intel-family.h> + +/* CPU matches for Dell generations with broken ACPI MIPI DISCO info */ +static const struct x86_cpu_id dell_broken_mipi_disco_cpu_gens[] = { + X86_MATCH_VFM(INTEL_TIGERLAKE, NULL), + X86_MATCH_VFM(INTEL_TIGERLAKE_L, NULL), + X86_MATCH_VFM(INTEL_ALDERLAKE, NULL), + X86_MATCH_VFM(INTEL_ALDERLAKE_L, NULL), + X86_MATCH_VFM(INTEL_RAPTORLAKE, NULL), + X86_MATCH_VFM(INTEL_RAPTORLAKE_P, NULL), + X86_MATCH_VFM(INTEL_RAPTORLAKE_S, NULL), + {} }; static const char *strnext(const char *s1, const char *s2) @@ -761,7 +767,10 @@ bool acpi_graph_ignore_port(acpi_handle handle) static bool dmi_tested, ignore_port; if (!dmi_tested) { - ignore_port = dmi_first_match(dmi_ignore_port_nodes); + if (dmi_name_in_vendors("Dell Inc.") && + x86_match_cpu(dell_broken_mipi_disco_cpu_gens)) + ignore_port = true; + dmi_tested = true; } @@ -794,3 +803,4 @@ out_free: kfree(orig_path); return false; } +#endif diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c index d67881b50bca..a0cfc857fb55 100644 --- a/drivers/acpi/thermal.c +++ b/drivers/acpi/thermal.c @@ -168,11 +168,17 @@ static int acpi_thermal_get_polling_frequency(struct acpi_thermal *tz) static int acpi_thermal_temp(struct acpi_thermal *tz, int temp_deci_k) { + int temp; + if (temp_deci_k == THERMAL_TEMP_INVALID) return THERMAL_TEMP_INVALID; - return deci_kelvin_to_millicelsius_with_offset(temp_deci_k, + temp = deci_kelvin_to_millicelsius_with_offset(temp_deci_k, tz->kelvin_offset); + if (temp <= 0) + return THERMAL_TEMP_INVALID; + + return temp; } static bool acpi_thermal_trip_valid(struct acpi_thermal_trip *acpi_trip) diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c index 7dca73417e2b..2fe0934dcd64 100644 --- a/drivers/acpi/x86/utils.c +++ b/drivers/acpi/x86/utils.c @@ -206,16 +206,16 @@ bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *s } /* - * AMD systems from Renoir and Lucienne *require* that the NVME controller + * AMD systems from Renoir onwards *require* that the NVME controller * is put into D3 over a Modern Standby / suspend-to-idle cycle. * * This is "typically" accomplished using the `StorageD3Enable` * property in the _DSD that is checked via the `acpi_storage_d3` function - * but this property was introduced after many of these systems launched - * and most OEM systems don't have it in their BIOS. + * but some OEM systems still don't have it in their BIOS. * * The Microsoft documentation for StorageD3Enable mentioned that Windows has - * a hardcoded allowlist for D3 support, which was used for these platforms. + * a hardcoded allowlist for D3 support as well as a registry key to override + * the BIOS, which has been used for these cases. * * This allows quirking on Linux in a similar fashion. * @@ -228,19 +228,15 @@ bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *s * https://bugzilla.kernel.org/show_bug.cgi?id=216773 * https://bugzilla.kernel.org/show_bug.cgi?id=217003 * 2) On at least one HP system StorageD3Enable is missing on the second NVME - disk in the system. + * disk in the system. + * 3) On at least one HP Rembrandt system StorageD3Enable is missing on the only + * NVME device. */ -static const struct x86_cpu_id storage_d3_cpu_ids[] = { - X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 24, NULL), /* Picasso */ - X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 96, NULL), /* Renoir */ - X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 104, NULL), /* Lucienne */ - X86_MATCH_VENDOR_FAM_MODEL(AMD, 25, 80, NULL), /* Cezanne */ - {} -}; - bool force_storage_d3(void) { - return x86_match_cpu(storage_d3_cpu_ids); + if (!cpu_feature_enabled(X86_FEATURE_ZEN)) + return false; + return acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0; } /* diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 07d66d2c5f0d..5eb38fbbbecd 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1735,6 +1735,14 @@ static void ahci_update_initial_lpm_policy(struct ata_port *ap) if (ap->pflags & ATA_PFLAG_EXTERNAL) return; + /* If no LPM states are supported by the HBA, do not bother with LPM */ + if ((ap->host->flags & ATA_HOST_NO_PART) && + (ap->host->flags & ATA_HOST_NO_SSC) && + (ap->host->flags & ATA_HOST_NO_DEVSLP)) { + ata_port_dbg(ap, "no LPM states supported, not enabling LPM\n"); + return; + } + /* user modified policy via module param */ if (mobile_lpm_policy != -1) { policy = mobile_lpm_policy; diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index cdf29b178ddc..bb4d30d377ae 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1831,11 +1831,11 @@ static unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf) 2 }; - /* set scsi removable (RMB) bit per ata bit, or if the - * AHCI port says it's external (Hotplug-capable, eSATA). + /* + * Set the SCSI Removable Media Bit (RMB) if the ATA removable media + * device bit (obsolete since ATA-8 ACS) is set. */ - if (ata_id_removable(args->id) || - (args->dev->link->ap->pflags & ATA_PFLAG_EXTERNAL)) + if (ata_id_removable(args->id)) hdr[1] |= (1 << 7); if (args->dev->class == ATA_DEV_ZAC) { diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c index 817838e2f70e..3cb455a32d92 100644 --- a/drivers/ata/pata_macio.c +++ b/drivers/ata/pata_macio.c @@ -915,10 +915,13 @@ static const struct scsi_host_template pata_macio_sht = { .sg_tablesize = MAX_DCMDS, /* We may not need that strict one */ .dma_boundary = ATA_DMA_BOUNDARY, - /* Not sure what the real max is but we know it's less than 64K, let's - * use 64K minus 256 + /* + * The SCSI core requires the segment size to cover at least a page, so + * for 64K page size kernels this must be at least 64K. However the + * hardware can't handle 64K, so pata_macio_qc_prep() will split large + * requests. */ - .max_segment_size = MAX_DBDMA_SEG, + .max_segment_size = SZ_64K, .device_configure = pata_macio_device_configure, .sdev_groups = ata_common_sdev_groups, .can_queue = ATA_DEF_QUEUE, diff --git a/drivers/base/core.c b/drivers/base/core.c index 131d96c6090b..2b4c0624b704 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2739,8 +2739,11 @@ static ssize_t uevent_show(struct device *dev, struct device_attribute *attr, if (!env) return -ENOMEM; + /* Synchronize with really_probe() */ + device_lock(dev); /* let the kset specific function add its keys */ retval = kset->uevent_ops->uevent(&dev->kobj, env); + device_unlock(dev); if (retval) goto out; @@ -2845,15 +2848,6 @@ static void devm_attr_group_remove(struct device *dev, void *res) sysfs_remove_group(&dev->kobj, group); } -static void devm_attr_groups_remove(struct device *dev, void *res) -{ - union device_attr_group_devres *devres = res; - const struct attribute_group **groups = devres->groups; - - dev_dbg(dev, "%s: removing groups %p\n", __func__, groups); - sysfs_remove_groups(&dev->kobj, groups); -} - /** * devm_device_add_group - given a device, create a managed attribute group * @dev: The device to create the group for @@ -2886,42 +2880,6 @@ int devm_device_add_group(struct device *dev, const struct attribute_group *grp) } EXPORT_SYMBOL_GPL(devm_device_add_group); -/** - * devm_device_add_groups - create a bunch of managed attribute groups - * @dev: The device to create the group for - * @groups: The attribute groups to create, NULL terminated - * - * This function creates a bunch of managed attribute groups. If an error - * occurs when creating a group, all previously created groups will be - * removed, unwinding everything back to the original state when this - * function was called. It will explicitly warn and error if any of the - * attribute files being created already exist. - * - * Returns 0 on success or error code from sysfs_create_group on failure. - */ -int devm_device_add_groups(struct device *dev, - const struct attribute_group **groups) -{ - union device_attr_group_devres *devres; - int error; - - devres = devres_alloc(devm_attr_groups_remove, - sizeof(*devres), GFP_KERNEL); - if (!devres) - return -ENOMEM; - - error = sysfs_create_groups(&dev->kobj, groups); - if (error) { - devres_free(devres); - return error; - } - - devres->groups = groups; - devres_add(dev, devres); - return 0; -} -EXPORT_SYMBOL_GPL(devm_device_add_groups); - static int device_add_attrs(struct device *dev) { const struct class *class = dev->class; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 93780f41646b..1153721bc7c2 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -302,6 +302,21 @@ static int lo_read_simple(struct loop_device *lo, struct request *rq, return 0; } +static void loop_clear_limits(struct loop_device *lo, int mode) +{ + struct queue_limits lim = queue_limits_start_update(lo->lo_queue); + + if (mode & FALLOC_FL_ZERO_RANGE) + lim.max_write_zeroes_sectors = 0; + + if (mode & FALLOC_FL_PUNCH_HOLE) { + lim.max_hw_discard_sectors = 0; + lim.discard_granularity = 0; + } + + queue_limits_commit_update(lo->lo_queue, &lim); +} + static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos, int mode) { @@ -320,6 +335,14 @@ static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos, ret = file->f_op->fallocate(file, mode, pos, blk_rq_bytes(rq)); if (unlikely(ret && ret != -EINVAL && ret != -EOPNOTSUPP)) return -EIO; + + /* + * We initially configure the limits in a hope that fallocate is + * supported and clear them here if that turns out not to be true. + */ + if (unlikely(ret == -EOPNOTSUPP)) + loop_clear_limits(lo, mode); + return ret; } diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 22a79a62cc4e..b87aa80a46dd 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -589,10 +589,11 @@ static inline int was_interrupted(int result) } /* - * Returns BLK_STS_RESOURCE if the caller should retry after a delay. Returns - * -EAGAIN if the caller should requeue @cmd. Returns -EIO if sending failed. + * Returns BLK_STS_RESOURCE if the caller should retry after a delay. + * Returns BLK_STS_IOERR if sending failed. */ -static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) +static blk_status_t nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, + int index) { struct request *req = blk_mq_rq_from_pdu(cmd); struct nbd_config *config = nbd->config; @@ -614,13 +615,13 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) type = req_to_nbd_cmd_type(req); if (type == U32_MAX) - return -EIO; + return BLK_STS_IOERR; if (rq_data_dir(req) == WRITE && (config->flags & NBD_FLAG_READ_ONLY)) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Write on read-only\n"); - return -EIO; + return BLK_STS_IOERR; } if (req->cmd_flags & REQ_FUA) @@ -674,11 +675,11 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) nsock->sent = sent; } set_bit(NBD_CMD_REQUEUED, &cmd->flags); - return (__force int)BLK_STS_RESOURCE; + return BLK_STS_RESOURCE; } dev_err_ratelimited(disk_to_dev(nbd->disk), "Send control failed (result %d)\n", result); - return -EAGAIN; + goto requeue; } send_pages: if (type != NBD_CMD_WRITE) @@ -715,12 +716,12 @@ send_pages: nsock->pending = req; nsock->sent = sent; set_bit(NBD_CMD_REQUEUED, &cmd->flags); - return (__force int)BLK_STS_RESOURCE; + return BLK_STS_RESOURCE; } dev_err(disk_to_dev(nbd->disk), "Send data failed (result %d)\n", result); - return -EAGAIN; + goto requeue; } /* * The completion might already have come in, @@ -737,7 +738,16 @@ out: trace_nbd_payload_sent(req, handle); nsock->pending = NULL; nsock->sent = 0; - return 0; + __set_bit(NBD_CMD_INFLIGHT, &cmd->flags); + return BLK_STS_OK; + +requeue: + /* retry on a different socket */ + dev_err_ratelimited(disk_to_dev(nbd->disk), + "Request send failed, requeueing\n"); + nbd_mark_nsock_dead(nbd, nsock, 1); + nbd_requeue_cmd(cmd); + return BLK_STS_OK; } static int nbd_read_reply(struct nbd_device *nbd, struct socket *sock, @@ -1018,7 +1028,7 @@ static blk_status_t nbd_handle_cmd(struct nbd_cmd *cmd, int index) struct nbd_device *nbd = cmd->nbd; struct nbd_config *config; struct nbd_sock *nsock; - int ret; + blk_status_t ret; lockdep_assert_held(&cmd->lock); @@ -1072,28 +1082,11 @@ again: ret = BLK_STS_OK; goto out; } - /* - * Some failures are related to the link going down, so anything that - * returns EAGAIN can be retried on a different socket. - */ ret = nbd_send_cmd(nbd, cmd, index); - /* - * Access to this flag is protected by cmd->lock, thus it's safe to set - * the flag after nbd_send_cmd() succeed to send request to server. - */ - if (!ret) - __set_bit(NBD_CMD_INFLIGHT, &cmd->flags); - else if (ret == -EAGAIN) { - dev_err_ratelimited(disk_to_dev(nbd->disk), - "Request send failed, requeueing\n"); - nbd_mark_nsock_dead(nbd, nsock, 1); - nbd_requeue_cmd(cmd); - ret = BLK_STS_OK; - } out: mutex_unlock(&nsock->tx_lock); nbd_config_put(nbd); - return ret < 0 ? BLK_STS_IOERR : (__force blk_status_t)ret; + return ret; } static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 631dca2e4e84..75f189e42f88 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1824,8 +1824,8 @@ static int null_validate_conf(struct nullb_device *dev) dev->queue_mode = NULL_Q_MQ; } - dev->blocksize = round_down(dev->blocksize, 512); - dev->blocksize = clamp_t(unsigned int, dev->blocksize, 512, 4096); + if (blk_validate_block_size(dev->blocksize)) + return -EINVAL; if (dev->use_per_node_hctx) { if (dev->submit_queues != nr_online_nodes) diff --git a/drivers/clk/clkdev.c b/drivers/clk/clkdev.c index 6a77d7e201a9..2f83fb97c6fb 100644 --- a/drivers/clk/clkdev.c +++ b/drivers/clk/clkdev.c @@ -204,8 +204,15 @@ fail: pr_err("%pV:%s: %s ID is greater than %zu\n", &vaf, con_id, failure, max_size); va_end(ap_copy); - kfree(cla); - return NULL; + + /* + * Don't fail in this case, but as the entry won't ever match just + * fill it with something that also won't match. + */ + strscpy(cla->con_id, "bad", sizeof(cla->con_id)); + strscpy(cla->dev_id, "bad", sizeof(cla->dev_id)); + + return &cla->cl; } static struct clk_lookup * diff --git a/drivers/clk/sifive/sifive-prci.c b/drivers/clk/sifive/sifive-prci.c index 25b8e1a80ddc..b32a59fe55e7 100644 --- a/drivers/clk/sifive/sifive-prci.c +++ b/drivers/clk/sifive/sifive-prci.c @@ -4,7 +4,6 @@ * Copyright (C) 2020 Zong Li */ -#include <linux/clkdev.h> #include <linux/delay.h> #include <linux/io.h> #include <linux/module.h> @@ -537,13 +536,6 @@ static int __prci_register_clocks(struct device *dev, struct __prci_data *pd, return r; } - r = clk_hw_register_clkdev(&pic->hw, pic->name, dev_name(dev)); - if (r) { - dev_warn(dev, "Failed to register clkdev for %s: %d\n", - init.name, r); - return r; - } - pd->hw_clks.hws[i] = &pic->hw; } diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 65d3f79104bd..15de5e3d96fd 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1302,12 +1302,17 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b, no_turbo = !!clamp_t(int, input, 0, 1); - if (no_turbo == global.no_turbo) - goto unlock_driver; - - if (global.turbo_disabled) { - pr_notice_once("Turbo disabled by BIOS or unavailable on processor\n"); + WRITE_ONCE(global.turbo_disabled, turbo_is_disabled()); + if (global.turbo_disabled && !no_turbo) { + pr_notice("Turbo disabled by BIOS or unavailable on processor\n"); count = -EPERM; + if (global.no_turbo) + goto unlock_driver; + else + no_turbo = 1; + } + + if (no_turbo == global.no_turbo) { goto unlock_driver; } @@ -1762,7 +1767,7 @@ static u64 atom_get_val(struct cpudata *cpudata, int pstate) u32 vid; val = (u64)pstate << 8; - if (READ_ONCE(global.no_turbo) && !global.turbo_disabled) + if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled)) val |= (u64)1 << 32; vid_fp = cpudata->vid.min + mul_fp( @@ -1927,7 +1932,7 @@ static u64 core_get_val(struct cpudata *cpudata, int pstate) u64 val; val = (u64)pstate << 8; - if (READ_ONCE(global.no_turbo) && !global.turbo_disabled) + if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled)) val |= (u64)1 << 32; return val; diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 002a5ec80620..9fc99cfbef08 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -394,7 +394,7 @@ config LS2X_APB_DMA config MCF_EDMA tristate "Freescale eDMA engine support, ColdFire mcf5441x SoCs" - depends on M5441x || COMPILE_TEST + depends on M5441x || (COMPILE_TEST && FSL_EDMA=n) select DMA_ENGINE select DMA_VIRTUAL_CHANNELS help diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index 8dc029c86551..fc049c9c9892 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -611,11 +611,13 @@ static void irq_process_work_list(struct idxd_irq_entry *irq_entry) spin_unlock(&irq_entry->list_lock); - list_for_each_entry(desc, &flist, list) { + list_for_each_entry_safe(desc, n, &flist, list) { /* * Check against the original status as ABORT is software defined * and 0xff, which DSA_COMP_STATUS_MASK can mask out. */ + list_del(&desc->list); + if (unlikely(desc->completion->status == IDXD_COMP_DESC_ABORT)) { idxd_desc_complete(desc, IDXD_COMPLETE_ABORT, true); continue; diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c index 9c364e92cb82..e8f45a7fded4 100644 --- a/drivers/dma/ioat/init.c +++ b/drivers/dma/ioat/init.c @@ -534,18 +534,6 @@ err_out: return err; } -static int ioat_register(struct ioatdma_device *ioat_dma) -{ - int err = dma_async_device_register(&ioat_dma->dma_dev); - - if (err) { - ioat_disable_interrupts(ioat_dma); - dma_pool_destroy(ioat_dma->completion_pool); - } - - return err; -} - static void ioat_dma_remove(struct ioatdma_device *ioat_dma) { struct dma_device *dma = &ioat_dma->dma_dev; @@ -1181,9 +1169,9 @@ static int ioat3_dma_probe(struct ioatdma_device *ioat_dma, int dca) ioat_chan->reg_base + IOAT_DCACTRL_OFFSET); } - err = ioat_register(ioat_dma); + err = dma_async_device_register(&ioat_dma->dma_dev); if (err) - return err; + goto err_disable_interrupts; ioat_kobject_add(ioat_dma, &ioat_ktype); @@ -1192,20 +1180,29 @@ static int ioat3_dma_probe(struct ioatdma_device *ioat_dma, int dca) /* disable relaxed ordering */ err = pcie_capability_read_word(pdev, PCI_EXP_DEVCTL, &val16); - if (err) - return pcibios_err_to_errno(err); + if (err) { + err = pcibios_err_to_errno(err); + goto err_disable_interrupts; + } /* clear relaxed ordering enable */ val16 &= ~PCI_EXP_DEVCTL_RELAX_EN; err = pcie_capability_write_word(pdev, PCI_EXP_DEVCTL, val16); - if (err) - return pcibios_err_to_errno(err); + if (err) { + err = pcibios_err_to_errno(err); + goto err_disable_interrupts; + } if (ioat_dma->cap & IOAT_CAP_DPS) writeb(ioat_pending_level + 1, ioat_dma->reg_base + IOAT_PREFETCH_LIMIT_OFFSET); return 0; + +err_disable_interrupts: + ioat_disable_interrupts(ioat_dma); + dma_pool_destroy(ioat_dma->completion_pool); + return err; } static void ioat_shutdown(struct pci_dev *pdev) @@ -1350,6 +1347,8 @@ static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) void __iomem * const *iomap; struct device *dev = &pdev->dev; struct ioatdma_device *device; + unsigned int i; + u8 version; int err; err = pcim_enable_device(pdev); @@ -1363,6 +1362,10 @@ static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (!iomap) return -ENOMEM; + version = readb(iomap[IOAT_MMIO_BAR] + IOAT_VER_OFFSET); + if (version < IOAT_VER_3_0) + return -ENODEV; + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (err) return err; @@ -1373,17 +1376,18 @@ static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) pci_set_master(pdev); pci_set_drvdata(pdev, device); - device->version = readb(device->reg_base + IOAT_VER_OFFSET); + device->version = version; if (device->version >= IOAT_VER_3_4) ioat_dca_enabled = 0; - if (device->version >= IOAT_VER_3_0) { - if (is_skx_ioat(pdev)) - device->version = IOAT_VER_3_2; - err = ioat3_dma_probe(device, ioat_dca_enabled); - } else - return -ENODEV; + if (is_skx_ioat(pdev)) + device->version = IOAT_VER_3_2; + + err = ioat3_dma_probe(device, ioat_dca_enabled); if (err) { + for (i = 0; i < IOAT_MAX_CHANS; i++) + kfree(device->idx[i]); + kfree(device); dev_err(dev, "Intel(R) I/OAT DMA Engine init failed\n"); return -ENODEV; } @@ -1445,6 +1449,7 @@ module_init(ioat_init_module); static void __exit ioat_exit_module(void) { pci_unregister_driver(&ioat_pci_driver); + kmem_cache_destroy(ioat_sed_cache); kmem_cache_destroy(ioat_cache); } module_exit(ioat_exit_module); diff --git a/drivers/dma/ti/k3-udma-glue.c b/drivers/dma/ti/k3-udma-glue.c index b96b448a0e69..dd1a068f905d 100644 --- a/drivers/dma/ti/k3-udma-glue.c +++ b/drivers/dma/ti/k3-udma-glue.c @@ -200,12 +200,9 @@ of_k3_udma_glue_parse_chn_by_id(struct device_node *udmax_np, struct k3_udma_glu ret = of_k3_udma_glue_parse(udmax_np, common); if (ret) - goto out_put_spec; + return ret; ret = of_k3_udma_glue_parse_chn_common(common, thread_id, tx_chn); - -out_put_spec: - of_node_put(udmax_np); return ret; } diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c index e143a7330816..718842fdaf98 100644 --- a/drivers/dma/xilinx/xdma.c +++ b/drivers/dma/xilinx/xdma.c @@ -885,11 +885,11 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id) u32 st; bool repeat_tx; + spin_lock(&xchan->vchan.lock); + if (xchan->stop_requested) complete(&xchan->last_interrupt); - spin_lock(&xchan->vchan.lock); - /* get submitted request */ vd = vchan_next_desc(&xchan->vchan); if (!vd) diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 1f3520d76861..a17f3c0cdfa6 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -81,7 +81,7 @@ int __amd64_read_pci_cfg_dword(struct pci_dev *pdev, int offset, amd64_warn("%s: error reading F%dx%03x.\n", func, PCI_FUNC(pdev->devfn), offset); - return err; + return pcibios_err_to_errno(err); } int __amd64_write_pci_cfg_dword(struct pci_dev *pdev, int offset, @@ -94,7 +94,7 @@ int __amd64_write_pci_cfg_dword(struct pci_dev *pdev, int offset, amd64_warn("%s: error writing to F%dx%03x.\n", func, PCI_FUNC(pdev->devfn), offset); - return err; + return pcibios_err_to_errno(err); } /* @@ -1025,8 +1025,10 @@ static int gpu_get_node_map(struct amd64_pvt *pvt) } ret = pci_read_config_dword(pdev, REG_LOCAL_NODE_TYPE_MAP, &tmp); - if (ret) + if (ret) { + ret = pcibios_err_to_errno(ret); goto out; + } gpu_node_map.node_count = FIELD_GET(LNTM_NODE_COUNT, tmp); gpu_node_map.base_node_id = FIELD_GET(LNTM_BASE_NODE_ID, tmp); diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index cdd8480e7368..dbe9fe5f2ca6 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -800,7 +800,7 @@ static int errcmd_enable_error_reporting(bool enable) rc = pci_read_config_word(imc->pdev, ERRCMD_OFFSET, &errcmd); if (rc) - return rc; + return pcibios_err_to_errno(rc); if (enable) errcmd |= ERRCMD_CE | ERRSTS_UE; @@ -809,7 +809,7 @@ static int errcmd_enable_error_reporting(bool enable) rc = pci_write_config_word(imc->pdev, ERRCMD_OFFSET, errcmd); if (rc) - return rc; + return pcibios_err_to_errno(rc); return 0; } diff --git a/drivers/firewire/Kconfig b/drivers/firewire/Kconfig index 869598b20e3a..5268b3f0a25a 100644 --- a/drivers/firewire/Kconfig +++ b/drivers/firewire/Kconfig @@ -11,7 +11,7 @@ config FIREWIRE This is the new-generation IEEE 1394 (FireWire) driver stack a.k.a. Juju, a new implementation designed for robustness and simplicity. - See http://ieee1394.wiki.kernel.org/index.php/Juju_Migration + See http://ieee1394.docs.kernel.org/en/latest/migration.html for information about migration from the older Linux 1394 stack to the new driver stack. diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c index 127d87e3a153..f8b99dd6cd82 100644 --- a/drivers/firewire/core-card.c +++ b/drivers/firewire/core-card.c @@ -222,14 +222,14 @@ static int reset_bus(struct fw_card *card, bool short_reset) int reg = short_reset ? 5 : 1; int bit = short_reset ? PHY_BUS_SHORT_RESET : PHY_BUS_RESET; - trace_bus_reset_initiate(card->generation, short_reset); + trace_bus_reset_initiate(card->index, card->generation, short_reset); return card->driver->update_phy_reg(card, reg, 0, bit); } void fw_schedule_bus_reset(struct fw_card *card, bool delayed, bool short_reset) { - trace_bus_reset_schedule(card->generation, short_reset); + trace_bus_reset_schedule(card->index, card->generation, short_reset); /* We don't try hard to sort out requests of long vs. short resets. */ card->br_short = short_reset; @@ -249,7 +249,7 @@ static void br_work(struct work_struct *work) /* Delay for 2s after last reset per IEEE 1394 clause 8.2.1. */ if (card->reset_jiffies != 0 && time_before64(get_jiffies_64(), card->reset_jiffies + 2 * HZ)) { - trace_bus_reset_postpone(card->generation, card->br_short); + trace_bus_reset_postpone(card->index, card->generation, card->br_short); if (!queue_delayed_work(fw_workqueue, &card->br_work, 2 * HZ)) fw_card_put(card); diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index 55993c9e0b90..9a7dc90330a3 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -1559,7 +1559,7 @@ static void outbound_phy_packet_callback(struct fw_packet *packet, struct client *e_client = e->client; u32 rcode; - trace_async_phy_outbound_complete((uintptr_t)packet, status, packet->generation, + trace_async_phy_outbound_complete((uintptr_t)packet, card->index, status, packet->generation, packet->timestamp); switch (status) { @@ -1659,8 +1659,8 @@ static int ioctl_send_phy_packet(struct client *client, union ioctl_arg *arg) memcpy(pp->data, a->data, sizeof(a->data)); } - trace_async_phy_outbound_initiate((uintptr_t)&e->p, e->p.generation, e->p.header[1], - e->p.header[2]); + trace_async_phy_outbound_initiate((uintptr_t)&e->p, card->index, e->p.generation, + e->p.header[1], e->p.header[2]); card->driver->send_request(card, &e->p); diff --git a/drivers/firewire/core-topology.c b/drivers/firewire/core-topology.c index 837cc44d8d9f..8107eebd4296 100644 --- a/drivers/firewire/core-topology.c +++ b/drivers/firewire/core-topology.c @@ -508,7 +508,7 @@ void fw_core_handle_bus_reset(struct fw_card *card, int node_id, int generation, struct fw_node *local_node; unsigned long flags; - trace_bus_reset_handle(generation, node_id, bm_abdicate, self_ids, self_id_count); + trace_bus_reset_handle(card->index, generation, node_id, bm_abdicate, self_ids, self_id_count); spin_lock_irqsave(&card->lock, flags); diff --git a/drivers/firewire/core-transaction.c b/drivers/firewire/core-transaction.c index 571fdff65c2b..76ab6a209768 100644 --- a/drivers/firewire/core-transaction.c +++ b/drivers/firewire/core-transaction.c @@ -174,8 +174,8 @@ static void transmit_complete_callback(struct fw_packet *packet, struct fw_transaction *t = container_of(packet, struct fw_transaction, packet); - trace_async_request_outbound_complete((uintptr_t)t, packet->generation, packet->speed, - status, packet->timestamp); + trace_async_request_outbound_complete((uintptr_t)t, card->index, packet->generation, + packet->speed, status, packet->timestamp); switch (status) { case ACK_COMPLETE: @@ -398,7 +398,8 @@ void __fw_send_request(struct fw_card *card, struct fw_transaction *t, int tcode spin_unlock_irqrestore(&card->lock, flags); - trace_async_request_outbound_initiate((uintptr_t)t, generation, speed, t->packet.header, payload, + trace_async_request_outbound_initiate((uintptr_t)t, card->index, generation, speed, + t->packet.header, payload, tcode_is_read_request(tcode) ? 0 : length / 4); card->driver->send_request(card, &t->packet); @@ -463,7 +464,7 @@ static DECLARE_COMPLETION(phy_config_done); static void transmit_phy_packet_callback(struct fw_packet *packet, struct fw_card *card, int status) { - trace_async_phy_outbound_complete((uintptr_t)packet, packet->generation, status, + trace_async_phy_outbound_complete((uintptr_t)packet, card->index, packet->generation, status, packet->timestamp); complete(&phy_config_done); } @@ -503,7 +504,7 @@ void fw_send_phy_config(struct fw_card *card, phy_config_packet.generation = generation; reinit_completion(&phy_config_done); - trace_async_phy_outbound_initiate((uintptr_t)&phy_config_packet, + trace_async_phy_outbound_initiate((uintptr_t)&phy_config_packet, card->index, phy_config_packet.generation, phy_config_packet.header[1], phy_config_packet.header[2]); @@ -674,7 +675,7 @@ static void free_response_callback(struct fw_packet *packet, { struct fw_request *request = container_of(packet, struct fw_request, response); - trace_async_response_outbound_complete((uintptr_t)request, packet->generation, + trace_async_response_outbound_complete((uintptr_t)request, card->index, packet->generation, packet->speed, status, packet->timestamp); // Decrease the reference count since not at in-flight. @@ -879,9 +880,10 @@ void fw_send_response(struct fw_card *card, // Increase the reference count so that the object is kept during in-flight. fw_request_get(request); - trace_async_response_outbound_initiate((uintptr_t)request, request->response.generation, - request->response.speed, request->response.header, - data, data ? data_length / 4 : 0); + trace_async_response_outbound_initiate((uintptr_t)request, card->index, + request->response.generation, request->response.speed, + request->response.header, data, + data ? data_length / 4 : 0); card->driver->send_response(card, &request->response); } @@ -995,7 +997,7 @@ void fw_core_handle_request(struct fw_card *card, struct fw_packet *p) tcode = async_header_get_tcode(p->header); if (tcode_is_link_internal(tcode)) { - trace_async_phy_inbound((uintptr_t)p, p->generation, p->ack, p->timestamp, + trace_async_phy_inbound((uintptr_t)p, card->index, p->generation, p->ack, p->timestamp, p->header[1], p->header[2]); fw_cdev_handle_phy_packet(card, p); return; @@ -1007,8 +1009,8 @@ void fw_core_handle_request(struct fw_card *card, struct fw_packet *p) return; } - trace_async_request_inbound((uintptr_t)request, p->generation, p->speed, p->ack, - p->timestamp, p->header, request->data, + trace_async_request_inbound((uintptr_t)request, card->index, p->generation, p->speed, + p->ack, p->timestamp, p->header, request->data, tcode_is_read_request(tcode) ? 0 : request->length / 4); offset = async_header_get_offset(p->header); @@ -1078,8 +1080,8 @@ void fw_core_handle_response(struct fw_card *card, struct fw_packet *p) } spin_unlock_irqrestore(&card->lock, flags); - trace_async_response_inbound((uintptr_t)t, p->generation, p->speed, p->ack, p->timestamp, - p->header, data, data_length / 4); + trace_async_response_inbound((uintptr_t)t, card->index, p->generation, p->speed, p->ack, + p->timestamp, p->header, data, data_length / 4); if (!t) { timed_out: diff --git a/drivers/firmware/efi/memmap.c b/drivers/firmware/efi/memmap.c index 3365944f7965..34109fd86c55 100644 --- a/drivers/firmware/efi/memmap.c +++ b/drivers/firmware/efi/memmap.c @@ -15,10 +15,6 @@ #include <asm/early_ioremap.h> #include <asm/efi.h> -#ifndef __efi_memmap_free -#define __efi_memmap_free(phys, size, flags) do { } while (0) -#endif - /** * __efi_memmap_init - Common code for mapping the EFI memory map * @data: EFI memory map data @@ -51,11 +47,6 @@ int __init __efi_memmap_init(struct efi_memory_map_data *data) return -ENOMEM; } - if (efi.memmap.flags & (EFI_MEMMAP_MEMBLOCK | EFI_MEMMAP_SLAB)) - __efi_memmap_free(efi.memmap.phys_map, - efi.memmap.desc_size * efi.memmap.nr_map, - efi.memmap.flags); - map.phys_map = data->phys_map; map.nr_map = data->size / data->desc_size; map.map_end = map.map + data->size; diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c index d9629ff87861..2328ca58bba6 100644 --- a/drivers/firmware/psci/psci.c +++ b/drivers/firmware/psci/psci.c @@ -497,10 +497,12 @@ int psci_cpu_suspend_enter(u32 state) static int psci_system_suspend(unsigned long unused) { + int err; phys_addr_t pa_cpu_resume = __pa_symbol(cpu_resume); - return invoke_psci_fn(PSCI_FN_NATIVE(1_0, SYSTEM_SUSPEND), + err = invoke_psci_fn(PSCI_FN_NATIVE(1_0, SYSTEM_SUSPEND), pa_cpu_resume, 0, 0); + return psci_to_linux_errno(err); } static int psci_system_suspend_enter(suspend_state_t state) diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 3dbddec07028..1c28a48915bb 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -1576,7 +1576,7 @@ config GPIO_TPS68470 are "output only" GPIOs. config GPIO_TQMX86 - tristate "TQ-Systems QTMX86 GPIO" + tristate "TQ-Systems TQMx86 GPIO" depends on MFD_TQMX86 || COMPILE_TEST depends on HAS_IOPORT_MAP select GPIOLIB_IRQCHIP diff --git a/drivers/gpio/gpio-gw-pld.c b/drivers/gpio/gpio-gw-pld.c index 899335da93c7..7e29a2d8de1a 100644 --- a/drivers/gpio/gpio-gw-pld.c +++ b/drivers/gpio/gpio-gw-pld.c @@ -130,5 +130,6 @@ static struct i2c_driver gw_pld_driver = { }; module_i2c_driver(gw_pld_driver); +MODULE_DESCRIPTION("Gateworks I2C PLD GPIO expander"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Linus Walleij <[email protected]>"); diff --git a/drivers/gpio/gpio-mc33880.c b/drivers/gpio/gpio-mc33880.c index cd9b16dbe1a9..94f6fefc011b 100644 --- a/drivers/gpio/gpio-mc33880.c +++ b/drivers/gpio/gpio-mc33880.c @@ -168,5 +168,6 @@ static void __exit mc33880_exit(void) module_exit(mc33880_exit); MODULE_AUTHOR("Mocean Laboratories <[email protected]>"); +MODULE_DESCRIPTION("MC33880 high-side/low-side switch GPIO driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpio/gpio-pcf857x.c b/drivers/gpio/gpio-pcf857x.c index 53b69abe6787..7c57eaeb0afe 100644 --- a/drivers/gpio/gpio-pcf857x.c +++ b/drivers/gpio/gpio-pcf857x.c @@ -438,5 +438,6 @@ static void __exit pcf857x_exit(void) } module_exit(pcf857x_exit); +MODULE_DESCRIPTION("Driver for pcf857x, pca857x, and pca967x I2C GPIO expanders"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("David Brownell"); diff --git a/drivers/gpio/gpio-pl061.c b/drivers/gpio/gpio-pl061.c index 9fc1f3dd4190..a211a02d4b4a 100644 --- a/drivers/gpio/gpio-pl061.c +++ b/drivers/gpio/gpio-pl061.c @@ -438,4 +438,5 @@ static struct amba_driver pl061_gpio_driver = { }; module_amba_driver(pl061_gpio_driver); +MODULE_DESCRIPTION("Driver for the ARM PrimeCell(tm) General Purpose Input/Output (PL061)"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpio/gpio-tqmx86.c b/drivers/gpio/gpio-tqmx86.c index 3a28c1f273c3..f2e7e8754d95 100644 --- a/drivers/gpio/gpio-tqmx86.c +++ b/drivers/gpio/gpio-tqmx86.c @@ -6,6 +6,7 @@ * Vadim V.Vlasov <[email protected]> */ +#include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/errno.h> #include <linux/gpio/driver.h> @@ -28,16 +29,25 @@ #define TQMX86_GPIIC 3 /* GPI Interrupt Configuration Register */ #define TQMX86_GPIIS 4 /* GPI Interrupt Status Register */ +#define TQMX86_GPII_NONE 0 #define TQMX86_GPII_FALLING BIT(0) #define TQMX86_GPII_RISING BIT(1) +/* Stored in irq_type as a trigger type, but not actually valid as a register + * value, so the name doesn't use "GPII" + */ +#define TQMX86_INT_BOTH (BIT(0) | BIT(1)) #define TQMX86_GPII_MASK (BIT(0) | BIT(1)) #define TQMX86_GPII_BITS 2 +/* Stored in irq_type with GPII bits */ +#define TQMX86_INT_UNMASKED BIT(2) struct tqmx86_gpio_data { struct gpio_chip chip; void __iomem *io_base; int irq; + /* Lock must be held for accessing output and irq_type fields */ raw_spinlock_t spinlock; + DECLARE_BITMAP(output, TQMX86_NGPIO); u8 irq_type[TQMX86_NGPI]; }; @@ -64,15 +74,10 @@ static void tqmx86_gpio_set(struct gpio_chip *chip, unsigned int offset, { struct tqmx86_gpio_data *gpio = gpiochip_get_data(chip); unsigned long flags; - u8 val; raw_spin_lock_irqsave(&gpio->spinlock, flags); - val = tqmx86_gpio_read(gpio, TQMX86_GPIOD); - if (value) - val |= BIT(offset); - else - val &= ~BIT(offset); - tqmx86_gpio_write(gpio, val, TQMX86_GPIOD); + __assign_bit(offset, gpio->output, value); + tqmx86_gpio_write(gpio, bitmap_get_value8(gpio->output, 0), TQMX86_GPIOD); raw_spin_unlock_irqrestore(&gpio->spinlock, flags); } @@ -107,21 +112,38 @@ static int tqmx86_gpio_get_direction(struct gpio_chip *chip, return GPIO_LINE_DIRECTION_OUT; } +static void tqmx86_gpio_irq_config(struct tqmx86_gpio_data *gpio, int offset) + __must_hold(&gpio->spinlock) +{ + u8 type = TQMX86_GPII_NONE, gpiic; + + if (gpio->irq_type[offset] & TQMX86_INT_UNMASKED) { + type = gpio->irq_type[offset] & TQMX86_GPII_MASK; + + if (type == TQMX86_INT_BOTH) + type = tqmx86_gpio_get(&gpio->chip, offset + TQMX86_NGPO) + ? TQMX86_GPII_FALLING + : TQMX86_GPII_RISING; + } + + gpiic = tqmx86_gpio_read(gpio, TQMX86_GPIIC); + gpiic &= ~(TQMX86_GPII_MASK << (offset * TQMX86_GPII_BITS)); + gpiic |= type << (offset * TQMX86_GPII_BITS); + tqmx86_gpio_write(gpio, gpiic, TQMX86_GPIIC); +} + static void tqmx86_gpio_irq_mask(struct irq_data *data) { unsigned int offset = (data->hwirq - TQMX86_NGPO); struct tqmx86_gpio_data *gpio = gpiochip_get_data( irq_data_get_irq_chip_data(data)); unsigned long flags; - u8 gpiic, mask; - - mask = TQMX86_GPII_MASK << (offset * TQMX86_GPII_BITS); raw_spin_lock_irqsave(&gpio->spinlock, flags); - gpiic = tqmx86_gpio_read(gpio, TQMX86_GPIIC); - gpiic &= ~mask; - tqmx86_gpio_write(gpio, gpiic, TQMX86_GPIIC); + gpio->irq_type[offset] &= ~TQMX86_INT_UNMASKED; + tqmx86_gpio_irq_config(gpio, offset); raw_spin_unlock_irqrestore(&gpio->spinlock, flags); + gpiochip_disable_irq(&gpio->chip, irqd_to_hwirq(data)); } @@ -131,16 +153,12 @@ static void tqmx86_gpio_irq_unmask(struct irq_data *data) struct tqmx86_gpio_data *gpio = gpiochip_get_data( irq_data_get_irq_chip_data(data)); unsigned long flags; - u8 gpiic, mask; - - mask = TQMX86_GPII_MASK << (offset * TQMX86_GPII_BITS); gpiochip_enable_irq(&gpio->chip, irqd_to_hwirq(data)); + raw_spin_lock_irqsave(&gpio->spinlock, flags); - gpiic = tqmx86_gpio_read(gpio, TQMX86_GPIIC); - gpiic &= ~mask; - gpiic |= gpio->irq_type[offset] << (offset * TQMX86_GPII_BITS); - tqmx86_gpio_write(gpio, gpiic, TQMX86_GPIIC); + gpio->irq_type[offset] |= TQMX86_INT_UNMASKED; + tqmx86_gpio_irq_config(gpio, offset); raw_spin_unlock_irqrestore(&gpio->spinlock, flags); } @@ -151,7 +169,7 @@ static int tqmx86_gpio_irq_set_type(struct irq_data *data, unsigned int type) unsigned int offset = (data->hwirq - TQMX86_NGPO); unsigned int edge_type = type & IRQF_TRIGGER_MASK; unsigned long flags; - u8 new_type, gpiic; + u8 new_type; switch (edge_type) { case IRQ_TYPE_EDGE_RISING: @@ -161,19 +179,16 @@ static int tqmx86_gpio_irq_set_type(struct irq_data *data, unsigned int type) new_type = TQMX86_GPII_FALLING; break; case IRQ_TYPE_EDGE_BOTH: - new_type = TQMX86_GPII_FALLING | TQMX86_GPII_RISING; + new_type = TQMX86_INT_BOTH; break; default: return -EINVAL; /* not supported */ } - gpio->irq_type[offset] = new_type; - raw_spin_lock_irqsave(&gpio->spinlock, flags); - gpiic = tqmx86_gpio_read(gpio, TQMX86_GPIIC); - gpiic &= ~((TQMX86_GPII_MASK) << (offset * TQMX86_GPII_BITS)); - gpiic |= new_type << (offset * TQMX86_GPII_BITS); - tqmx86_gpio_write(gpio, gpiic, TQMX86_GPIIC); + gpio->irq_type[offset] &= ~TQMX86_GPII_MASK; + gpio->irq_type[offset] |= new_type; + tqmx86_gpio_irq_config(gpio, offset); raw_spin_unlock_irqrestore(&gpio->spinlock, flags); return 0; @@ -184,8 +199,8 @@ static void tqmx86_gpio_irq_handler(struct irq_desc *desc) struct gpio_chip *chip = irq_desc_get_handler_data(desc); struct tqmx86_gpio_data *gpio = gpiochip_get_data(chip); struct irq_chip *irq_chip = irq_desc_get_chip(desc); - unsigned long irq_bits; - int i = 0; + unsigned long irq_bits, flags; + int i; u8 irq_status; chained_irq_enter(irq_chip, desc); @@ -194,6 +209,34 @@ static void tqmx86_gpio_irq_handler(struct irq_desc *desc) tqmx86_gpio_write(gpio, irq_status, TQMX86_GPIIS); irq_bits = irq_status; + + raw_spin_lock_irqsave(&gpio->spinlock, flags); + for_each_set_bit(i, &irq_bits, TQMX86_NGPI) { + /* + * Edge-both triggers are implemented by flipping the edge + * trigger after each interrupt, as the controller only supports + * either rising or falling edge triggers, but not both. + * + * Internally, the TQMx86 GPIO controller has separate status + * registers for rising and falling edge interrupts. GPIIC + * configures which bits from which register are visible in the + * interrupt status register GPIIS and defines what triggers the + * parent IRQ line. Writing to GPIIS always clears both rising + * and falling interrupt flags internally, regardless of the + * currently configured trigger. + * + * In consequence, we can cleanly implement the edge-both + * trigger in software by first clearing the interrupt and then + * setting the new trigger based on the current GPIO input in + * tqmx86_gpio_irq_config() - even if an edge arrives between + * reading the input and setting the trigger, we will have a new + * interrupt pending. + */ + if ((gpio->irq_type[i] & TQMX86_GPII_MASK) == TQMX86_INT_BOTH) + tqmx86_gpio_irq_config(gpio, i); + } + raw_spin_unlock_irqrestore(&gpio->spinlock, flags); + for_each_set_bit(i, &irq_bits, TQMX86_NGPI) generic_handle_domain_irq(gpio->chip.irq.domain, i + TQMX86_NGPO); @@ -277,6 +320,13 @@ static int tqmx86_gpio_probe(struct platform_device *pdev) tqmx86_gpio_write(gpio, (u8)~TQMX86_DIR_INPUT_MASK, TQMX86_GPIODD); + /* + * Reading the previous output state is not possible with TQMx86 hardware. + * Initialize all outputs to 0 to have a defined state that matches the + * shadow register. + */ + tqmx86_gpio_write(gpio, 0, TQMX86_GPIOD); + chip = &gpio->chip; chip->label = "gpio-tqmx86"; chip->owner = THIS_MODULE; diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 026444eeb5c6..d0aa277fc3bf 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -450,6 +450,7 @@ config DRM_PRIVACY_SCREEN config DRM_WERROR bool "Compile the drm subsystem with warnings as errors" depends on DRM && EXPERT + depends on !WERROR default n help A kernel build should not cause any compiler warnings, and this diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 055ba2ea4c12..662d0f28f358 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -41,8 +41,6 @@ #include <linux/dma-buf.h> #include <linux/dma-fence-array.h> #include <linux/pci-p2pdma.h> -#include <linux/pm_runtime.h> -#include "amdgpu_trace.h" /** * amdgpu_dma_buf_attach - &dma_buf_ops.attach implementation @@ -58,42 +56,11 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf, struct drm_gem_object *obj = dmabuf->priv; struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); - int r; if (pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0) attach->peer2peer = false; - r = pm_runtime_get_sync(adev_to_drm(adev)->dev); - trace_amdgpu_runpm_reference_dumps(1, __func__); - if (r < 0) - goto out; - return 0; - -out: - pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); - trace_amdgpu_runpm_reference_dumps(0, __func__); - return r; -} - -/** - * amdgpu_dma_buf_detach - &dma_buf_ops.detach implementation - * - * @dmabuf: DMA-buf where we remove the attachment from - * @attach: the attachment to remove - * - * Called when an attachment is removed from the DMA-buf. - */ -static void amdgpu_dma_buf_detach(struct dma_buf *dmabuf, - struct dma_buf_attachment *attach) -{ - struct drm_gem_object *obj = dmabuf->priv; - struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); - struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); - - pm_runtime_mark_last_busy(adev_to_drm(adev)->dev); - pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); - trace_amdgpu_runpm_reference_dumps(0, __func__); } /** @@ -267,7 +234,6 @@ static int amdgpu_dma_buf_begin_cpu_access(struct dma_buf *dma_buf, const struct dma_buf_ops amdgpu_dmabuf_ops = { .attach = amdgpu_dma_buf_attach, - .detach = amdgpu_dma_buf_detach, .pin = amdgpu_dma_buf_pin, .unpin = amdgpu_dma_buf_unpin, .map_dma_buf = amdgpu_dma_buf_map, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 10832b470448..bc3ac73b6b8d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -181,7 +181,6 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amd amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr, seq, flags | AMDGPU_FENCE_FLAG_INT); pm_runtime_get_noresume(adev_to_drm(adev)->dev); - trace_amdgpu_runpm_reference_dumps(1, __func__); ptr = &ring->fence_drv.fences[seq & ring->fence_drv.num_fences_mask]; if (unlikely(rcu_dereference_protected(*ptr, 1))) { struct dma_fence *old; @@ -309,7 +308,6 @@ bool amdgpu_fence_process(struct amdgpu_ring *ring) dma_fence_put(fence); pm_runtime_mark_last_busy(adev_to_drm(adev)->dev); pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); - trace_amdgpu_runpm_reference_dumps(0, __func__); } while (last_seq != seq); return true; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 67c234bcf89f..3adaa4670103 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -108,6 +108,7 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size, memset(&bp, 0, sizeof(bp)); *obj = NULL; + flags |= AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE; bp.size = size; bp.byte_align = alignment; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index be4629cdac04..08b9dfb65335 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -684,12 +684,17 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid, struct amdgpu_ring *ring = &adev->gfx.kiq[inst].ring; struct amdgpu_kiq *kiq = &adev->gfx.kiq[inst]; unsigned int ndw; - signed long r; + int r; uint32_t seq; - if (!adev->gmc.flush_pasid_uses_kiq || !ring->sched.ready || - !down_read_trylock(&adev->reset_domain->sem)) { + /* + * A GPU reset should flush all TLBs anyway, so no need to do + * this while one is ongoing. + */ + if (!down_read_trylock(&adev->reset_domain->sem)) + return 0; + if (!adev->gmc.flush_pasid_uses_kiq || !ring->sched.ready) { if (adev->gmc.flush_tlb_needs_extra_type_2) adev->gmc.gmc_funcs->flush_gpu_tlb_pasid(adev, pasid, 2, all_hub, @@ -703,43 +708,40 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid, adev->gmc.gmc_funcs->flush_gpu_tlb_pasid(adev, pasid, flush_type, all_hub, inst); - return 0; - } + r = 0; + } else { + /* 2 dwords flush + 8 dwords fence */ + ndw = kiq->pmf->invalidate_tlbs_size + 8; - /* 2 dwords flush + 8 dwords fence */ - ndw = kiq->pmf->invalidate_tlbs_size + 8; + if (adev->gmc.flush_tlb_needs_extra_type_2) + ndw += kiq->pmf->invalidate_tlbs_size; - if (adev->gmc.flush_tlb_needs_extra_type_2) - ndw += kiq->pmf->invalidate_tlbs_size; + if (adev->gmc.flush_tlb_needs_extra_type_0) + ndw += kiq->pmf->invalidate_tlbs_size; - if (adev->gmc.flush_tlb_needs_extra_type_0) - ndw += kiq->pmf->invalidate_tlbs_size; + spin_lock(&adev->gfx.kiq[inst].ring_lock); + amdgpu_ring_alloc(ring, ndw); + if (adev->gmc.flush_tlb_needs_extra_type_2) + kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 2, all_hub); - spin_lock(&adev->gfx.kiq[inst].ring_lock); - amdgpu_ring_alloc(ring, ndw); - if (adev->gmc.flush_tlb_needs_extra_type_2) - kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 2, all_hub); + if (flush_type == 2 && adev->gmc.flush_tlb_needs_extra_type_0) + kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 0, all_hub); - if (flush_type == 2 && adev->gmc.flush_tlb_needs_extra_type_0) - kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 0, all_hub); + kiq->pmf->kiq_invalidate_tlbs(ring, pasid, flush_type, all_hub); + r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT); + if (r) { + amdgpu_ring_undo(ring); + spin_unlock(&adev->gfx.kiq[inst].ring_lock); + goto error_unlock_reset; + } - kiq->pmf->kiq_invalidate_tlbs(ring, pasid, flush_type, all_hub); - r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT); - if (r) { - amdgpu_ring_undo(ring); + amdgpu_ring_commit(ring); spin_unlock(&adev->gfx.kiq[inst].ring_lock); - goto error_unlock_reset; - } - - amdgpu_ring_commit(ring); - spin_unlock(&adev->gfx.kiq[inst].ring_lock); - r = amdgpu_fence_wait_polling(ring, seq, usec_timeout); - if (r < 1) { - dev_err(adev->dev, "wait for kiq fence error: %ld.\n", r); - r = -ETIME; - goto error_unlock_reset; + if (amdgpu_fence_wait_polling(ring, seq, usec_timeout) < 1) { + dev_err(adev->dev, "timeout waiting for kiq fence\n"); + r = -ETIME; + } } - r = 0; error_unlock_reset: up_read(&adev->reset_domain->sem); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 8d8c39be6129..c556c8b653fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -604,8 +604,6 @@ int amdgpu_bo_create(struct amdgpu_device *adev, if (!amdgpu_bo_support_uswc(bo->flags)) bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC; - bo->flags |= AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE; - bo->tbo.bdev = &adev->mman.bdev; if (bp->domain & (AMDGPU_GEM_DOMAIN_GWS | AMDGPU_GEM_DOMAIN_OA | AMDGPU_GEM_DOMAIN_GDS)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h index 7aafeb763e5d..383fce40d4dd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h @@ -554,21 +554,6 @@ TRACE_EVENT(amdgpu_reset_reg_dumps, __entry->value) ); -TRACE_EVENT(amdgpu_runpm_reference_dumps, - TP_PROTO(uint32_t index, const char *func), - TP_ARGS(index, func), - TP_STRUCT__entry( - __field(uint32_t, index) - __string(func, func) - ), - TP_fast_assign( - __entry->index = index; - __assign_str(func); - ), - TP_printk("amdgpu runpm reference dump 0x%x: 0x%s\n", - __entry->index, - __get_str(func)) -); #undef AMDGPU_JOB_GET_TIMELINE_NAME #endif diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c index 7b16e8cca86a..f5b9f443cfdd 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c @@ -4195,9 +4195,10 @@ static u32 gfx_v9_4_3_get_cu_active_bitmap(struct amdgpu_device *adev, int xcc_i static int gfx_v9_4_3_get_cu_info(struct amdgpu_device *adev, struct amdgpu_cu_info *cu_info) { - int i, j, k, counter, xcc_id, active_cu_number = 0; - u32 mask, bitmap, ao_bitmap, ao_cu_mask = 0; + int i, j, k, prev_counter, counter, xcc_id, active_cu_number = 0; + u32 mask, bitmap, ao_bitmap, ao_cu_mask = 0, tmp; unsigned disable_masks[4 * 4]; + bool is_symmetric_cus; if (!adev || !cu_info) return -EINVAL; @@ -4215,6 +4216,7 @@ static int gfx_v9_4_3_get_cu_info(struct amdgpu_device *adev, mutex_lock(&adev->grbm_idx_mutex); for (xcc_id = 0; xcc_id < NUM_XCC(adev->gfx.xcc_mask); xcc_id++) { + is_symmetric_cus = true; for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { mask = 1; @@ -4242,6 +4244,15 @@ static int gfx_v9_4_3_get_cu_info(struct amdgpu_device *adev, ao_cu_mask |= (ao_bitmap << (i * 16 + j * 8)); cu_info->ao_cu_bitmap[i][j] = ao_bitmap; } + if (i && is_symmetric_cus && prev_counter != counter) + is_symmetric_cus = false; + prev_counter = counter; + } + if (is_symmetric_cus) { + tmp = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regCP_CPC_DEBUG); + tmp = REG_SET_FIELD(tmp, CP_CPC_DEBUG, CPC_HARVESTING_RELAUNCH_DISABLE, 1); + tmp = REG_SET_FIELD(tmp, CP_CPC_DEBUG, CPC_HARVESTING_DISPATCH_DISABLE, 1); + WREG32_SOC15(GC, GET_INST(GC, xcc_id), regCP_CPC_DEBUG, tmp); } gfx_v9_4_3_xcc_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff, xcc_id); diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 0d1407f25005..32d4519541c6 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -154,18 +154,18 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, void *pkt, int size, int api_status_off) { - int ndw = size / 4; - signed long r; - union MESAPI__MISC *x_pkt = pkt; - struct MES_API_STATUS *api_status; + union MESAPI__QUERY_MES_STATUS mes_status_pkt; + signed long timeout = 3000000; /* 3000 ms */ struct amdgpu_device *adev = mes->adev; struct amdgpu_ring *ring = &mes->ring; - unsigned long flags; - signed long timeout = 3000000; /* 3000 ms */ + struct MES_API_STATUS *api_status; + union MESAPI__MISC *x_pkt = pkt; const char *op_str, *misc_op_str; - u32 fence_offset; - u64 fence_gpu_addr; - u64 *fence_ptr; + unsigned long flags; + u64 status_gpu_addr; + u32 status_offset; + u64 *status_ptr; + signed long r; int ret; if (x_pkt->header.opcode >= MES_SCH_API_MAX) @@ -177,28 +177,38 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, /* Worst case in sriov where all other 15 VF timeout, each VF needs about 600ms */ timeout = 15 * 600 * 1000; } - BUG_ON(size % 4 != 0); - ret = amdgpu_device_wb_get(adev, &fence_offset); + ret = amdgpu_device_wb_get(adev, &status_offset); if (ret) return ret; - fence_gpu_addr = - adev->wb.gpu_addr + (fence_offset * 4); - fence_ptr = (u64 *)&adev->wb.wb[fence_offset]; - *fence_ptr = 0; + + status_gpu_addr = adev->wb.gpu_addr + (status_offset * 4); + status_ptr = (u64 *)&adev->wb.wb[status_offset]; + *status_ptr = 0; spin_lock_irqsave(&mes->ring_lock, flags); - if (amdgpu_ring_alloc(ring, ndw)) { - spin_unlock_irqrestore(&mes->ring_lock, flags); - amdgpu_device_wb_free(adev, fence_offset); - return -ENOMEM; - } + r = amdgpu_ring_alloc(ring, (size + sizeof(mes_status_pkt)) / 4); + if (r) + goto error_unlock_free; api_status = (struct MES_API_STATUS *)((char *)pkt + api_status_off); - api_status->api_completion_fence_addr = fence_gpu_addr; + api_status->api_completion_fence_addr = status_gpu_addr; api_status->api_completion_fence_value = 1; - amdgpu_ring_write_multiple(ring, pkt, ndw); + amdgpu_ring_write_multiple(ring, pkt, size / 4); + + memset(&mes_status_pkt, 0, sizeof(mes_status_pkt)); + mes_status_pkt.header.type = MES_API_TYPE_SCHEDULER; + mes_status_pkt.header.opcode = MES_SCH_API_QUERY_SCHEDULER_STATUS; + mes_status_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS; + mes_status_pkt.api_status.api_completion_fence_addr = + ring->fence_drv.gpu_addr; + mes_status_pkt.api_status.api_completion_fence_value = + ++ring->fence_drv.sync_seq; + + amdgpu_ring_write_multiple(ring, &mes_status_pkt, + sizeof(mes_status_pkt) / 4); + amdgpu_ring_commit(ring); spin_unlock_irqrestore(&mes->ring_lock, flags); @@ -206,15 +216,16 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, misc_op_str = mes_v11_0_get_misc_op_string(x_pkt); if (misc_op_str) - dev_dbg(adev->dev, "MES msg=%s (%s) was emitted\n", op_str, misc_op_str); + dev_dbg(adev->dev, "MES msg=%s (%s) was emitted\n", op_str, + misc_op_str); else if (op_str) dev_dbg(adev->dev, "MES msg=%s was emitted\n", op_str); else - dev_dbg(adev->dev, "MES msg=%d was emitted\n", x_pkt->header.opcode); + dev_dbg(adev->dev, "MES msg=%d was emitted\n", + x_pkt->header.opcode); - r = amdgpu_mes_fence_wait_polling(fence_ptr, (u64)1, timeout); - amdgpu_device_wb_free(adev, fence_offset); - if (r < 1) { + r = amdgpu_fence_wait_polling(ring, ring->fence_drv.sync_seq, timeout); + if (r < 1 || !*status_ptr) { if (misc_op_str) dev_err(adev->dev, "MES failed to respond to msg=%s (%s)\n", @@ -229,10 +240,19 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, while (halt_if_hws_hang) schedule(); - return -ETIMEDOUT; + r = -ETIMEDOUT; + goto error_wb_free; } + amdgpu_device_wb_free(adev, status_offset); return 0; + +error_unlock_free: + spin_unlock_irqrestore(&mes->ring_lock, flags); + +error_wb_free: + amdgpu_device_wb_free(adev, status_offset); + return r; } static int convert_to_mes_queue_type(int queue_type) diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c index f08a32c18694..40b28298af30 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c @@ -32,7 +32,9 @@ #include "mp/mp_14_0_2_sh_mask.h" MODULE_FIRMWARE("amdgpu/psp_14_0_2_sos.bin"); +MODULE_FIRMWARE("amdgpu/psp_14_0_2_ta.bin"); MODULE_FIRMWARE("amdgpu/psp_14_0_3_sos.bin"); +MODULE_FIRMWARE("amdgpu/psp_14_0_3_ta.bin"); /* For large FW files the time to complete can be very long */ #define USBC_PD_POLLING_LIMIT_S 240 @@ -66,6 +68,9 @@ static int psp_v14_0_init_microcode(struct psp_context *psp) err = psp_init_sos_microcode(psp, ucode_prefix); if (err) return err; + err = psp_init_ta_microcode(psp, ucode_prefix); + if (err) + return err; break; default: BUG(); diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig index 5fcd4f778dc3..47b8b49da8a7 100644 --- a/drivers/gpu/drm/amd/display/Kconfig +++ b/drivers/gpu/drm/amd/display/Kconfig @@ -8,7 +8,7 @@ config DRM_AMD_DC depends on BROKEN || !CC_IS_CLANG || ARM64 || RISCV || SPARC64 || X86_64 select SND_HDA_COMPONENT if SND_HDA_CORE # !CC_IS_CLANG: https://github.com/ClangBuiltLinux/linux/issues/1752 - select DRM_AMD_DC_FP if ARCH_HAS_KERNEL_FPU_SUPPORT && (!ARM64 || !CC_IS_CLANG) + select DRM_AMD_DC_FP if ARCH_HAS_KERNEL_FPU_SUPPORT && !(CC_IS_CLANG && (ARM64 || RISCV)) help Choose this option if you want to use the new display engine support for AMDGPU. This adds required support for Vega and 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 f1d67c6f4b98..e9ac20bed0f2 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -9169,9 +9169,6 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) trace_amdgpu_dm_atomic_commit_tail_begin(state); - if (dm->dc->caps.ips_support && dm->dc->idle_optimizations_allowed) - dc_allow_idle_optimizations(dm->dc, false); - drm_atomic_helper_update_legacy_modeset_state(dev, state); drm_dp_mst_atomic_wait_for_dependencies(state); @@ -11440,6 +11437,12 @@ void amdgpu_dm_trigger_timing_sync(struct drm_device *dev) mutex_unlock(&adev->dm.dc_lock); } +static inline void amdgpu_dm_exit_ips_for_hw_access(struct dc *dc) +{ + if (dc->ctx->dmub_srv && !dc->ctx->dmub_srv->idle_exit_counter) + dc_exit_ips_for_hw_access(dc); +} + void dm_write_reg_func(const struct dc_context *ctx, uint32_t address, u32 value, const char *func_name) { @@ -11450,6 +11453,8 @@ void dm_write_reg_func(const struct dc_context *ctx, uint32_t address, return; } #endif + + amdgpu_dm_exit_ips_for_hw_access(ctx->dc); cgs_write_register(ctx->cgs_device, address, value); trace_amdgpu_dc_wreg(&ctx->perf_trace->write_count, address, value); } @@ -11473,6 +11478,8 @@ uint32_t dm_read_reg_func(const struct dc_context *ctx, uint32_t address, return 0; } + amdgpu_dm_exit_ips_for_hw_access(ctx->dc); + value = cgs_read_register(ctx->cgs_device, address); trace_amdgpu_dc_rreg(&ctx->perf_trace->read_count, address, value); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c index 60f251cf973b..beed7adbbd43 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c @@ -177,7 +177,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = { .urgent_latency_pixel_data_only_us = 4.0, .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, .urgent_latency_vm_data_only_us = 4.0, - .dram_clock_change_latency_us = 11.72, + .dram_clock_change_latency_us = 34.0, .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c index e4f333d4fb54..a201dbb743d7 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c @@ -215,7 +215,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_51_soc = { .urgent_latency_pixel_data_only_us = 4.0, .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, .urgent_latency_vm_data_only_us = 4.0, - .dram_clock_change_latency_us = 11.72, + .dram_clock_change_latency_us = 34, .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c index 5295f52e4fc8..dcced89c07b3 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c @@ -1439,3 +1439,75 @@ void dcn35_set_long_vblank(struct pipe_ctx **pipe_ctx, } } } + +static bool should_avoid_empty_tu(struct pipe_ctx *pipe_ctx) +{ + /* Calculate average pixel count per TU, return false if under ~2.00 to + * avoid empty TUs. This is only required for DPIA tunneling as empty TUs + * are legal to generate for native DP links. Assume TU size 64 as there + * is currently no scenario where it's reprogrammed from HW default. + * MTPs have no such limitation, so this does not affect MST use cases. + */ + unsigned int pix_clk_mhz; + unsigned int symclk_mhz; + unsigned int avg_pix_per_tu_x1000; + unsigned int tu_size_bytes = 64; + struct dc_crtc_timing *timing = &pipe_ctx->stream->timing; + struct dc_link_settings *link_settings = &pipe_ctx->link_config.dp_link_settings; + const struct dc *dc = pipe_ctx->stream->link->dc; + + if (pipe_ctx->stream->link->ep_type != DISPLAY_ENDPOINT_USB4_DPIA) + return false; + + // Not necessary for MST configurations + if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) + return false; + + pix_clk_mhz = timing->pix_clk_100hz / 10000; + + // If this is true, can't block due to dynamic ODM + if (pix_clk_mhz > dc->clk_mgr->bw_params->clk_table.entries[0].dispclk_mhz) + return false; + + switch (link_settings->link_rate) { + case LINK_RATE_LOW: + symclk_mhz = 162; + break; + case LINK_RATE_HIGH: + symclk_mhz = 270; + break; + case LINK_RATE_HIGH2: + symclk_mhz = 540; + break; + case LINK_RATE_HIGH3: + symclk_mhz = 810; + break; + default: + // We shouldn't be tunneling any other rates, something is wrong + ASSERT(0); + return false; + } + + avg_pix_per_tu_x1000 = (1000 * pix_clk_mhz * tu_size_bytes) + / (symclk_mhz * link_settings->lane_count); + + // Add small empirically-decided margin to account for potential jitter + return (avg_pix_per_tu_x1000 < 2020); +} + +bool dcn35_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx) +{ + struct dc *dc = pipe_ctx->stream->ctx->dc; + + if (!is_h_timing_divisible_by_2(pipe_ctx->stream)) + return false; + + if (should_avoid_empty_tu(pipe_ctx)) + return false; + + if (dc_is_dp_signal(pipe_ctx->stream->signal) && !dc->link_srv->dp_is_128b_132b_signal(pipe_ctx) && + dc->debug.enable_dp_dig_pixel_rate_div_policy) + return true; + + return false; +} diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h index a731c8880d60..f0ea7d1511ae 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h @@ -95,4 +95,6 @@ void dcn35_set_static_screen_control(struct pipe_ctx **pipe_ctx, void dcn35_set_long_vblank(struct pipe_ctx **pipe_ctx, int num_pipes, uint32_t v_total_min, uint32_t v_total_max); +bool dcn35_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx); + #endif /* __DC_HWSS_DCN35_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c index df3bf77f3fb4..199781233fd5 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c @@ -158,7 +158,7 @@ static const struct hwseq_private_funcs dcn35_private_funcs = { .setup_hpo_hw_control = dcn35_setup_hpo_hw_control, .calculate_dccg_k1_k2_values = dcn32_calculate_dccg_k1_k2_values, .set_pixels_per_cycle = dcn32_set_pixels_per_cycle, - .is_dp_dig_pixel_rate_div_policy = dcn32_is_dp_dig_pixel_rate_div_policy, + .is_dp_dig_pixel_rate_div_policy = dcn35_is_dp_dig_pixel_rate_div_policy, .dsc_pg_control = dcn35_dsc_pg_control, .dsc_pg_status = dcn32_dsc_pg_status, .enable_plane = dcn35_enable_plane, diff --git a/drivers/gpu/drm/amd/include/pptable.h b/drivers/gpu/drm/amd/include/pptable.h index 2e8e6c9875f6..f83ace2d7ec3 100644 --- a/drivers/gpu/drm/amd/include/pptable.h +++ b/drivers/gpu/drm/amd/include/pptable.h @@ -477,31 +477,30 @@ typedef struct _ATOM_PPLIB_STATE_V2 } ATOM_PPLIB_STATE_V2; typedef struct _StateArray{ - //how many states we have - UCHAR ucNumEntries; - - ATOM_PPLIB_STATE_V2 states[1]; + //how many states we have + UCHAR ucNumEntries; + + ATOM_PPLIB_STATE_V2 states[] /* __counted_by(ucNumEntries) */; }StateArray; typedef struct _ClockInfoArray{ - //how many clock levels we have - UCHAR ucNumEntries; - - //sizeof(ATOM_PPLIB_CLOCK_INFO) - UCHAR ucEntrySize; - - UCHAR clockInfo[]; + //how many clock levels we have + UCHAR ucNumEntries; + + //sizeof(ATOM_PPLIB_CLOCK_INFO) + UCHAR ucEntrySize; + + UCHAR clockInfo[]; }ClockInfoArray; typedef struct _NonClockInfoArray{ + //how many non-clock levels we have. normally should be same as number of states + UCHAR ucNumEntries; + //sizeof(ATOM_PPLIB_NONCLOCK_INFO) + UCHAR ucEntrySize; - //how many non-clock levels we have. normally should be same as number of states - UCHAR ucNumEntries; - //sizeof(ATOM_PPLIB_NONCLOCK_INFO) - UCHAR ucEntrySize; - - ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[]; + ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[] __counted_by(ucNumEntries); }NonClockInfoArray; typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Record @@ -513,8 +512,10 @@ typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Record typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Table { - UCHAR ucNumEntries; // Number of entries. - ATOM_PPLIB_Clock_Voltage_Dependency_Record entries[1]; // Dynamically allocate entries. + // Number of entries. + UCHAR ucNumEntries; + // Dynamically allocate entries. + ATOM_PPLIB_Clock_Voltage_Dependency_Record entries[] __counted_by(ucNumEntries); }ATOM_PPLIB_Clock_Voltage_Dependency_Table; typedef struct _ATOM_PPLIB_Clock_Voltage_Limit_Record @@ -529,8 +530,10 @@ typedef struct _ATOM_PPLIB_Clock_Voltage_Limit_Record typedef struct _ATOM_PPLIB_Clock_Voltage_Limit_Table { - UCHAR ucNumEntries; // Number of entries. - ATOM_PPLIB_Clock_Voltage_Limit_Record entries[1]; // Dynamically allocate entries. + // Number of entries. + UCHAR ucNumEntries; + // Dynamically allocate entries. + ATOM_PPLIB_Clock_Voltage_Limit_Record entries[] __counted_by(ucNumEntries); }ATOM_PPLIB_Clock_Voltage_Limit_Table; union _ATOM_PPLIB_CAC_Leakage_Record @@ -553,8 +556,10 @@ typedef union _ATOM_PPLIB_CAC_Leakage_Record ATOM_PPLIB_CAC_Leakage_Record; typedef struct _ATOM_PPLIB_CAC_Leakage_Table { - UCHAR ucNumEntries; // Number of entries. - ATOM_PPLIB_CAC_Leakage_Record entries[1]; // Dynamically allocate entries. + // Number of entries. + UCHAR ucNumEntries; + // Dynamically allocate entries. + ATOM_PPLIB_CAC_Leakage_Record entries[] __counted_by(ucNumEntries); }ATOM_PPLIB_CAC_Leakage_Table; typedef struct _ATOM_PPLIB_PhaseSheddingLimits_Record @@ -568,8 +573,10 @@ typedef struct _ATOM_PPLIB_PhaseSheddingLimits_Record typedef struct _ATOM_PPLIB_PhaseSheddingLimits_Table { - UCHAR ucNumEntries; // Number of entries. - ATOM_PPLIB_PhaseSheddingLimits_Record entries[1]; // Dynamically allocate entries. + // Number of entries. + UCHAR ucNumEntries; + // Dynamically allocate entries. + ATOM_PPLIB_PhaseSheddingLimits_Record entries[] __counted_by(ucNumEntries); }ATOM_PPLIB_PhaseSheddingLimits_Table; typedef struct _VCEClockInfo{ @@ -580,8 +587,8 @@ typedef struct _VCEClockInfo{ }VCEClockInfo; typedef struct _VCEClockInfoArray{ - UCHAR ucNumEntries; - VCEClockInfo entries[1]; + UCHAR ucNumEntries; + VCEClockInfo entries[] __counted_by(ucNumEntries); }VCEClockInfoArray; typedef struct _ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record @@ -592,8 +599,8 @@ typedef struct _ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record typedef struct _ATOM_PPLIB_VCE_Clock_Voltage_Limit_Table { - UCHAR numEntries; - ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record entries[1]; + UCHAR numEntries; + ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record entries[] __counted_by(numEntries); }ATOM_PPLIB_VCE_Clock_Voltage_Limit_Table; typedef struct _ATOM_PPLIB_VCE_State_Record @@ -604,8 +611,8 @@ typedef struct _ATOM_PPLIB_VCE_State_Record typedef struct _ATOM_PPLIB_VCE_State_Table { - UCHAR numEntries; - ATOM_PPLIB_VCE_State_Record entries[1]; + UCHAR numEntries; + ATOM_PPLIB_VCE_State_Record entries[] __counted_by(numEntries); }ATOM_PPLIB_VCE_State_Table; @@ -626,8 +633,8 @@ typedef struct _UVDClockInfo{ }UVDClockInfo; typedef struct _UVDClockInfoArray{ - UCHAR ucNumEntries; - UVDClockInfo entries[1]; + UCHAR ucNumEntries; + UVDClockInfo entries[] __counted_by(ucNumEntries); }UVDClockInfoArray; typedef struct _ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record @@ -638,8 +645,8 @@ typedef struct _ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record typedef struct _ATOM_PPLIB_UVD_Clock_Voltage_Limit_Table { - UCHAR numEntries; - ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record entries[1]; + UCHAR numEntries; + ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record entries[] __counted_by(numEntries); }ATOM_PPLIB_UVD_Clock_Voltage_Limit_Table; typedef struct _ATOM_PPLIB_UVD_Table @@ -657,8 +664,8 @@ typedef struct _ATOM_PPLIB_SAMClk_Voltage_Limit_Record }ATOM_PPLIB_SAMClk_Voltage_Limit_Record; typedef struct _ATOM_PPLIB_SAMClk_Voltage_Limit_Table{ - UCHAR numEntries; - ATOM_PPLIB_SAMClk_Voltage_Limit_Record entries[]; + UCHAR numEntries; + ATOM_PPLIB_SAMClk_Voltage_Limit_Record entries[] __counted_by(numEntries); }ATOM_PPLIB_SAMClk_Voltage_Limit_Table; typedef struct _ATOM_PPLIB_SAMU_Table @@ -675,8 +682,8 @@ typedef struct _ATOM_PPLIB_ACPClk_Voltage_Limit_Record }ATOM_PPLIB_ACPClk_Voltage_Limit_Record; typedef struct _ATOM_PPLIB_ACPClk_Voltage_Limit_Table{ - UCHAR numEntries; - ATOM_PPLIB_ACPClk_Voltage_Limit_Record entries[1]; + UCHAR numEntries; + ATOM_PPLIB_ACPClk_Voltage_Limit_Record entries[] __counted_by(numEntries); }ATOM_PPLIB_ACPClk_Voltage_Limit_Table; typedef struct _ATOM_PPLIB_ACP_Table @@ -743,9 +750,9 @@ typedef struct ATOM_PPLIB_VQ_Budgeting_Record{ } ATOM_PPLIB_VQ_Budgeting_Record; typedef struct ATOM_PPLIB_VQ_Budgeting_Table { - UCHAR revid; - UCHAR numEntries; - ATOM_PPLIB_VQ_Budgeting_Record entries[1]; + UCHAR revid; + UCHAR numEntries; + ATOM_PPLIB_VQ_Budgeting_Record entries[] __counted_by(numEntries); } ATOM_PPLIB_VQ_Budgeting_Table; #pragma pack() diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c index 6bb42d04b247..e8b6989a40f3 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c @@ -164,6 +164,8 @@ static void sumo_construct_vid_mapping_table(struct amdgpu_device *adev, for (i = 0; i < SUMO_MAX_HARDWARE_POWERLEVELS; i++) { if (table[i].ulSupportedSCLK != 0) { + if (table[i].usVoltageIndex >= SUMO_MAX_NUMBER_VOLTAGES) + continue; vid_mapping_table->entries[table[i].usVoltageIndex].vid_7bit = table[i].usVoltageID; vid_mapping_table->entries[table[i].usVoltageIndex].vid_2bit = diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c index bc241b593db1..b6257f34a7c6 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c @@ -226,15 +226,17 @@ static int smu_v13_0_4_system_features_control(struct smu_context *smu, bool en) struct amdgpu_device *adev = smu->adev; int ret = 0; - if (!en && adev->in_s4) { - /* Adds a GFX reset as workaround just before sending the - * MP1_UNLOAD message to prevent GC/RLC/PMFW from entering - * an invalid state. - */ - ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GfxDeviceDriverReset, - SMU_RESET_MODE_2, NULL); - if (ret) - return ret; + if (!en && !adev->in_s0ix) { + if (adev->in_s4) { + /* Adds a GFX reset as workaround just before sending the + * MP1_UNLOAD message to prevent GC/RLC/PMFW from entering + * an invalid state. + */ + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GfxDeviceDriverReset, + SMU_RESET_MODE_2, NULL); + if (ret) + return ret; + } ret = smu_cmn_send_smc_msg(smu, SMU_MSG_PrepareMp1ForUnload, NULL); } diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.c b/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.c index d8e449e6ebda..50cb8f7ee6b2 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.c @@ -72,11 +72,6 @@ struct gamma_curve_sector { u32 segment_width; }; -struct gamma_curve_segment { - u32 start; - u32 end; -}; - static struct gamma_curve_sector sector_tbl[] = { { 0, 4, 4 }, { 16, 4, 4 }, diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_dev.c b/drivers/gpu/drm/arm/display/komeda/komeda_dev.c index 14ee79becacb..5ba62e637a61 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_dev.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_dev.c @@ -12,10 +12,8 @@ #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/dma-mapping.h> -#ifdef CONFIG_DEBUG_FS #include <linux/debugfs.h> #include <linux/seq_file.h> -#endif #include <drm/drm_print.h> @@ -43,7 +41,6 @@ static int komeda_register_show(struct seq_file *sf, void *x) DEFINE_SHOW_ATTRIBUTE(komeda_register); -#ifdef CONFIG_DEBUG_FS static void komeda_debugfs_init(struct komeda_dev *mdev) { if (!debugfs_initialized()) @@ -55,7 +52,6 @@ static void komeda_debugfs_init(struct komeda_dev *mdev) debugfs_create_x16("err_verbosity", 0664, mdev->debugfs_root, &mdev->err_verbosity); } -#endif static ssize_t core_id_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -265,9 +261,7 @@ struct komeda_dev *komeda_dev_create(struct device *dev) mdev->err_verbosity = KOMEDA_DEV_PRINT_ERR_EVENTS; -#ifdef CONFIG_DEBUG_FS komeda_debugfs_init(mdev); -#endif return mdev; @@ -286,9 +280,7 @@ void komeda_dev_destroy(struct komeda_dev *mdev) sysfs_remove_group(&dev->kobj, &komeda_sysfs_attr_group); -#ifdef CONFIG_DEBUG_FS debugfs_remove_recursive(mdev->debugfs_root); -#endif if (mdev->aclk) clk_prepare_enable(mdev->aclk); diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c index f3e744172673..f4e76b46ca32 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c @@ -259,7 +259,7 @@ komeda_component_get_avail_scaler(struct komeda_component *c, u32 avail_scalers; pipe_st = komeda_pipeline_get_state(c->pipeline, state); - if (!pipe_st) + if (IS_ERR_OR_NULL(pipe_st)) return NULL; avail_scalers = (pipe_st->active_comps & KOMEDA_PIPELINE_SCALERS) ^ diff --git a/drivers/gpu/drm/bridge/panel.c b/drivers/gpu/drm/bridge/panel.c index 32506524d9a2..fe5fb08c9fc4 100644 --- a/drivers/gpu/drm/bridge/panel.c +++ b/drivers/gpu/drm/bridge/panel.c @@ -360,9 +360,12 @@ EXPORT_SYMBOL(drm_panel_bridge_set_orientation); static void devm_drm_panel_bridge_release(struct device *dev, void *res) { - struct drm_bridge **bridge = res; + struct drm_bridge *bridge = *(struct drm_bridge **)res; - drm_panel_bridge_remove(*bridge); + if (!bridge) + return; + + drm_bridge_remove(bridge); } /** diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index aa93129c3397..2166208a961d 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -202,6 +202,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_MATCH(DMI_BOARD_NAME, "NEXT"), }, .driver_data = (void *)&lcd800x1280_rightside_up, + }, { /* AYA NEO KUN */ + .matches = { + DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AYANEO"), + DMI_MATCH(DMI_BOARD_NAME, "KUN"), + }, + .driver_data = (void *)&lcd1600x2560_rightside_up, }, { /* Chuwi HiBook (CWI514) */ .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Hampoo"), diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c index f48c4343f469..3e6d4c6aa877 100644 --- a/drivers/gpu/drm/exynos/exynos_dp.c +++ b/drivers/gpu/drm/exynos/exynos_dp.c @@ -285,7 +285,6 @@ struct platform_driver dp_driver = { .remove_new = exynos_dp_remove, .driver = { .name = "exynos-dp", - .owner = THIS_MODULE, .pm = pm_ptr(&exynos_dp_pm_ops), .of_match_table = exynos_dp_match, }, diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c index fab135308b70..11a720fef32b 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c @@ -309,6 +309,7 @@ static int vidi_get_modes(struct drm_connector *connector) struct vidi_context *ctx = ctx_from_connector(connector); struct edid *edid; int edid_len; + int count; /* * the edid data comes from user side and it would be set @@ -328,7 +329,11 @@ static int vidi_get_modes(struct drm_connector *connector) drm_connector_update_edid_property(connector, edid); - return drm_add_edid_modes(connector, edid); + count = drm_add_edid_modes(connector, edid); + + kfree(edid); + + return count; } static const struct drm_connector_helper_funcs vidi_connector_helper_funcs = { diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index e968824a4c72..1e26cd4f8347 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -887,11 +887,11 @@ static int hdmi_get_modes(struct drm_connector *connector) int ret; if (!hdata->ddc_adpt) - return 0; + goto no_edid; edid = drm_get_edid(connector, hdata->ddc_adpt); if (!edid) - return 0; + goto no_edid; hdata->dvi_mode = !connector->display_info.is_hdmi; DRM_DEV_DEBUG_KMS(hdata->dev, "%s : width[%d] x height[%d]\n", @@ -906,6 +906,9 @@ static int hdmi_get_modes(struct drm_connector *connector) kfree(edid); return ret; + +no_edid: + return drm_add_modes_noedid(connector, 640, 480); } static int hdmi_find_phy_conf(struct hdmi_context *hdata, u32 pixel_clock) diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index e05e25cd4a94..5b3b6ae1e3d7 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -442,6 +442,10 @@ bool intel_dp_has_bigjoiner(struct intel_dp *intel_dp) struct intel_encoder *encoder = &intel_dig_port->base; struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + /* eDP MSO is not compatible with joiner */ + if (intel_dp->mso_link_count) + return false; + return DISPLAY_VER(dev_priv) >= 12 || (DISPLAY_VER(dev_priv) == 11 && encoder->port != PORT_A); diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index b5f605751b0a..de811e2265da 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -952,6 +952,13 @@ static void mtk_drm_remove(struct platform_device *pdev) of_node_put(private->comp_node[i]); } +static void mtk_drm_shutdown(struct platform_device *pdev) +{ + struct mtk_drm_private *private = platform_get_drvdata(pdev); + + drm_atomic_helper_shutdown(private->drm); +} + static int mtk_drm_sys_prepare(struct device *dev) { struct mtk_drm_private *private = dev_get_drvdata(dev); @@ -983,6 +990,7 @@ static const struct dev_pm_ops mtk_drm_pm_ops = { static struct platform_driver mtk_drm_platform_driver = { .probe = mtk_drm_probe, .remove_new = mtk_drm_remove, + .shutdown = mtk_drm_shutdown, .driver = { .name = "mediatek-drm", .pm = &mtk_drm_pm_ops, diff --git a/drivers/gpu/drm/nouveau/dispnv04/disp.c b/drivers/gpu/drm/nouveau/dispnv04/disp.c index 13705c5f1497..4b7497a8755c 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv04/disp.c @@ -68,7 +68,7 @@ nv04_display_fini(struct drm_device *dev, bool runtime, bool suspend) if (nv_two_heads(dev)) NVWriteCRTC(dev, 1, NV_PCRTC_INTR_EN_0, 0); - if (!runtime) + if (!runtime && !drm->headless) cancel_work_sync(&drm->hpd_work); if (!suspend) diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 88728a0b2c25..674dc567e179 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -2680,7 +2680,7 @@ nv50_display_fini(struct drm_device *dev, bool runtime, bool suspend) nv50_mstm_fini(nouveau_encoder(encoder)); } - if (!runtime) + if (!runtime && !drm->headless) cancel_work_sync(&drm->hpd_work); } diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c index 79cfab53f80e..8c3c1f1e01c5 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bios.c +++ b/drivers/gpu/drm/nouveau/nouveau_bios.c @@ -43,11 +43,6 @@ #define BIOSLOG(sip, fmt, arg...) NV_DEBUG(sip->dev, fmt, ##arg) #define LOG_OLD_VALUE(x) -struct init_exec { - bool execute; - bool repeat; -}; - static bool nv_cksum(const uint8_t *data, unsigned int length) { /* diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index aed5d5b51b43..d4725a968827 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -450,6 +450,9 @@ nouveau_display_hpd_resume(struct drm_device *dev) { struct nouveau_drm *drm = nouveau_drm(dev); + if (drm->headless) + return; + spin_lock_irq(&drm->hpd_lock); drm->hpd_pending = ~0; spin_unlock_irq(&drm->hpd_lock); @@ -635,7 +638,7 @@ nouveau_display_fini(struct drm_device *dev, bool suspend, bool runtime) } drm_connector_list_iter_end(&conn_iter); - if (!runtime) + if (!runtime && !drm->headless) cancel_work_sync(&drm->hpd_work); drm_kms_helper_poll_disable(dev); @@ -729,6 +732,7 @@ nouveau_display_create(struct drm_device *dev) /* no display hw */ if (ret == -ENODEV) { ret = 0; + drm->headless = true; goto disp_create_err; } diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index e239c6bf4afa..25fca98a20bc 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -276,6 +276,7 @@ struct nouveau_drm { /* modesetting */ struct nvbios vbios; struct nouveau_display *display; + bool headless; struct work_struct hpd_work; spinlock_t hpd_lock; u32 hpd_pending; diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c index e8f385b9c618..28bfc48a9127 100644 --- a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c +++ b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c @@ -643,7 +643,9 @@ static int st7789v_probe(struct spi_device *spi) if (ret) return dev_err_probe(dev, ret, "Failed to get backlight\n"); - of_drm_get_panel_orientation(spi->dev.of_node, &ctx->orientation); + ret = of_drm_get_panel_orientation(spi->dev.of_node, &ctx->orientation); + if (ret) + return dev_err_probe(&spi->dev, ret, "Failed to get orientation\n"); drm_panel_add(&ctx->panel); diff --git a/drivers/gpu/drm/radeon/sumo_dpm.c b/drivers/gpu/drm/radeon/sumo_dpm.c index 21d27e6235f3..b11f7c5bbcbe 100644 --- a/drivers/gpu/drm/radeon/sumo_dpm.c +++ b/drivers/gpu/drm/radeon/sumo_dpm.c @@ -1619,6 +1619,8 @@ void sumo_construct_vid_mapping_table(struct radeon_device *rdev, for (i = 0; i < SUMO_MAX_HARDWARE_POWERLEVELS; i++) { if (table[i].ulSupportedSCLK != 0) { + if (table[i].usVoltageIndex >= SUMO_MAX_NUMBER_VOLTAGES) + continue; vid_mapping_table->entries[table[i].usVoltageIndex].vid_7bit = table[i].usVoltageID; vid_mapping_table->entries[table[i].usVoltageIndex].vid_2bit = diff --git a/drivers/gpu/drm/renesas/shmobile/shmob_drm_drv.c b/drivers/gpu/drm/renesas/shmobile/shmob_drm_drv.c index e83c3e52251d..0250d5f00bf1 100644 --- a/drivers/gpu/drm/renesas/shmobile/shmob_drm_drv.c +++ b/drivers/gpu/drm/renesas/shmobile/shmob_drm_drv.c @@ -171,6 +171,13 @@ static void shmob_drm_remove(struct platform_device *pdev) drm_kms_helper_poll_fini(ddev); } +static void shmob_drm_shutdown(struct platform_device *pdev) +{ + struct shmob_drm_device *sdev = platform_get_drvdata(pdev); + + drm_atomic_helper_shutdown(&sdev->ddev); +} + static int shmob_drm_probe(struct platform_device *pdev) { struct shmob_drm_platform_data *pdata = pdev->dev.platform_data; @@ -273,6 +280,7 @@ static const struct of_device_id shmob_drm_of_table[] __maybe_unused = { static struct platform_driver shmob_drm_platform_driver = { .probe = shmob_drm_probe, .remove_new = shmob_drm_remove, + .shutdown = shmob_drm_shutdown, .driver = { .name = "shmob-drm", .of_match_table = of_match_ptr(shmob_drm_of_table), diff --git a/drivers/gpu/drm/vmwgfx/Kconfig b/drivers/gpu/drm/vmwgfx/Kconfig index faddae3d6ac2..6f1ac940cbae 100644 --- a/drivers/gpu/drm/vmwgfx/Kconfig +++ b/drivers/gpu/drm/vmwgfx/Kconfig @@ -2,7 +2,7 @@ config DRM_VMWGFX tristate "DRM driver for VMware Virtual GPU" depends on DRM && PCI && MMU - depends on X86 || ARM64 + depends on (X86 && HYPERVISOR_GUEST) || ARM64 select DRM_TTM select DRM_TTM_HELPER select MAPPING_DIRTY_HELPERS diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 8f1730aeacc9..823d8d2da17c 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -746,7 +746,7 @@ static int vmw_setup_pci_resources(struct vmw_private *dev, dev->vram_size = pci_resource_len(pdev, 2); drm_info(&dev->drm, - "Register MMIO at 0x%pa size is %llu kiB\n", + "Register MMIO at 0x%pa size is %llu KiB\n", &rmmio_start, (uint64_t)rmmio_size / 1024); dev->rmmio = devm_ioremap(dev->drm.dev, rmmio_start, @@ -765,7 +765,7 @@ static int vmw_setup_pci_resources(struct vmw_private *dev, fifo_size = pci_resource_len(pdev, 2); drm_info(&dev->drm, - "FIFO at %pa size is %llu kiB\n", + "FIFO at %pa size is %llu KiB\n", &fifo_start, (uint64_t)fifo_size / 1024); dev->fifo_mem = devm_memremap(dev->drm.dev, fifo_start, @@ -790,7 +790,7 @@ static int vmw_setup_pci_resources(struct vmw_private *dev, * SVGA_REG_VRAM_SIZE. */ drm_info(&dev->drm, - "VRAM at %pa size is %llu kiB\n", + "VRAM at %pa size is %llu KiB\n", &dev->vram_start, (uint64_t)dev->vram_size / 1024); return 0; @@ -960,13 +960,6 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) vmw_read(dev_priv, SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB); - /* - * Workaround for low memory 2D VMs to compensate for the - * allocation taken by fbdev - */ - if (!(dev_priv->capabilities & SVGA_CAP_3D)) - mem_size *= 3; - dev_priv->max_mob_pages = mem_size * 1024 / PAGE_SIZE; dev_priv->max_primary_mem = vmw_read(dev_priv, SVGA_REG_MAX_PRIMARY_MEM); @@ -991,13 +984,13 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) dev_priv->max_primary_mem = dev_priv->vram_size; } drm_info(&dev_priv->drm, - "Legacy memory limits: VRAM = %llu kB, FIFO = %llu kB, surface = %u kB\n", + "Legacy memory limits: VRAM = %llu KiB, FIFO = %llu KiB, surface = %u KiB\n", (u64)dev_priv->vram_size / 1024, (u64)dev_priv->fifo_mem_size / 1024, dev_priv->memory_size / 1024); drm_info(&dev_priv->drm, - "MOB limits: max mob size = %u kB, max mob pages = %u\n", + "MOB limits: max mob size = %u KiB, max mob pages = %u\n", dev_priv->max_mob_size / 1024, dev_priv->max_mob_pages); ret = vmw_dma_masks(dev_priv); @@ -1015,7 +1008,7 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) (unsigned)dev_priv->max_gmr_pages); } drm_info(&dev_priv->drm, - "Maximum display memory size is %llu kiB\n", + "Maximum display memory size is %llu KiB\n", (uint64_t)dev_priv->max_primary_mem / 1024); /* Need mmio memory to check for fifo pitchlock cap. */ diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 4ecaea0026fc..a1ce41e1c468 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -1043,9 +1043,6 @@ void vmw_kms_cursor_snoop(struct vmw_surface *srf, int vmw_kms_write_svga(struct vmw_private *vmw_priv, unsigned width, unsigned height, unsigned pitch, unsigned bpp, unsigned depth); -bool vmw_kms_validate_mode_vram(struct vmw_private *dev_priv, - uint32_t pitch, - uint32_t height); int vmw_kms_present(struct vmw_private *dev_priv, struct drm_file *file_priv, struct vmw_framebuffer *vfb, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c index a0b47c9b33f5..5bd967fbcf55 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c @@ -94,14 +94,14 @@ static int vmw_gmrid_man_get_node(struct ttm_resource_manager *man, } else new_max_pages = gman->max_gmr_pages * 2; if (new_max_pages > gman->max_gmr_pages && new_max_pages >= gman->used_gmr_pages) { - DRM_WARN("vmwgfx: increasing guest mob limits to %u kB.\n", + DRM_WARN("vmwgfx: increasing guest mob limits to %u KiB.\n", ((new_max_pages) << (PAGE_SHIFT - 10))); gman->max_gmr_pages = new_max_pages; } else { char buf[256]; snprintf(buf, sizeof(buf), - "vmwgfx, error: guest graphics is out of memory (mob limit at: %ukB).\n", + "vmwgfx, error: guest graphics is out of memory (mob limit at: %u KiB).\n", ((gman->max_gmr_pages) << (PAGE_SHIFT - 10))); vmw_host_printf(buf); DRM_WARN("%s", buf); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 13b2820cae51..00c4ff684130 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -224,7 +224,7 @@ static bool vmw_du_cursor_plane_has_changed(struct vmw_plane_state *old_vps, new_image = vmw_du_cursor_plane_acquire_image(new_vps); changed = false; - if (old_image && new_image) + if (old_image && new_image && old_image != new_image) changed = memcmp(old_image, new_image, size) != 0; return changed; @@ -2171,13 +2171,12 @@ int vmw_kms_write_svga(struct vmw_private *vmw_priv, return 0; } +static bool vmw_kms_validate_mode_vram(struct vmw_private *dev_priv, - uint32_t pitch, - uint32_t height) + u64 pitch, + u64 height) { - return ((u64) pitch * (u64) height) < (u64) - ((dev_priv->active_display_unit == vmw_du_screen_target) ? - dev_priv->max_primary_mem : dev_priv->vram_size); + return (pitch * height) < (u64)dev_priv->vram_size; } /** @@ -2873,25 +2872,18 @@ out_unref: enum drm_mode_status vmw_connector_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { + enum drm_mode_status ret; struct drm_device *dev = connector->dev; struct vmw_private *dev_priv = vmw_priv(dev); - u32 max_width = dev_priv->texture_max_width; - u32 max_height = dev_priv->texture_max_height; u32 assumed_cpp = 4; if (dev_priv->assume_16bpp) assumed_cpp = 2; - if (dev_priv->active_display_unit == vmw_du_screen_target) { - max_width = min(dev_priv->stdu_max_width, max_width); - max_height = min(dev_priv->stdu_max_height, max_height); - } - - if (max_width < mode->hdisplay) - return MODE_BAD_HVALUE; - - if (max_height < mode->vdisplay) - return MODE_BAD_VVALUE; + ret = drm_mode_validate_size(mode, dev_priv->texture_max_width, + dev_priv->texture_max_height); + if (ret != MODE_OK) + return ret; if (!vmw_kms_validate_mode_vram(dev_priv, mode->hdisplay * assumed_cpp, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c index 2041c4d48daa..a04e0736318d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c @@ -43,7 +43,14 @@ #define vmw_connector_to_stdu(x) \ container_of(x, struct vmw_screen_target_display_unit, base.connector) - +/* + * Some renderers such as llvmpipe will align the width and height of their + * buffers to match their tile size. We need to keep this in mind when exposing + * modes to userspace so that this possible over-allocation will not exceed + * graphics memory. 64x64 pixels seems to be a reasonable upper bound for the + * tile size of current renderers. + */ +#define GPU_TILE_SIZE 64 enum stdu_content_type { SAME_AS_DISPLAY = 0, @@ -85,11 +92,6 @@ struct vmw_stdu_update { SVGA3dCmdUpdateGBScreenTarget body; }; -struct vmw_stdu_dma { - SVGA3dCmdHeader header; - SVGA3dCmdSurfaceDMA body; -}; - struct vmw_stdu_surface_copy { SVGA3dCmdHeader header; SVGA3dCmdSurfaceCopy body; @@ -414,6 +416,7 @@ static void vmw_stdu_crtc_atomic_disable(struct drm_crtc *crtc, { struct vmw_private *dev_priv; struct vmw_screen_target_display_unit *stdu; + struct drm_crtc_state *new_crtc_state; int ret; if (!crtc) { @@ -423,6 +426,7 @@ static void vmw_stdu_crtc_atomic_disable(struct drm_crtc *crtc, stdu = vmw_crtc_to_stdu(crtc); dev_priv = vmw_priv(crtc->dev); + new_crtc_state = drm_atomic_get_new_crtc_state(state, crtc); if (dev_priv->vkms_enabled) drm_crtc_vblank_off(crtc); @@ -434,6 +438,14 @@ static void vmw_stdu_crtc_atomic_disable(struct drm_crtc *crtc, (void) vmw_stdu_update_st(dev_priv, stdu); + /* Don't destroy the Screen Target if we are only setting the + * display as inactive + */ + if (new_crtc_state->enable && + !new_crtc_state->active && + !new_crtc_state->mode_changed) + return; + ret = vmw_stdu_destroy_st(dev_priv, stdu); if (ret) DRM_ERROR("Failed to destroy Screen Target\n"); @@ -829,7 +841,41 @@ static void vmw_stdu_connector_destroy(struct drm_connector *connector) vmw_stdu_destroy(vmw_connector_to_stdu(connector)); } +static enum drm_mode_status +vmw_stdu_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) +{ + enum drm_mode_status ret; + struct drm_device *dev = connector->dev; + struct vmw_private *dev_priv = vmw_priv(dev); + u64 assumed_cpp = dev_priv->assume_16bpp ? 2 : 4; + /* Align width and height to account for GPU tile over-alignment */ + u64 required_mem = ALIGN(mode->hdisplay, GPU_TILE_SIZE) * + ALIGN(mode->vdisplay, GPU_TILE_SIZE) * + assumed_cpp; + required_mem = ALIGN(required_mem, PAGE_SIZE); + + ret = drm_mode_validate_size(mode, dev_priv->stdu_max_width, + dev_priv->stdu_max_height); + if (ret != MODE_OK) + return ret; + + ret = drm_mode_validate_size(mode, dev_priv->texture_max_width, + dev_priv->texture_max_height); + if (ret != MODE_OK) + return ret; + if (required_mem > dev_priv->max_primary_mem) + return MODE_MEM; + + if (required_mem > dev_priv->max_mob_pages * PAGE_SIZE) + return MODE_MEM; + + if (required_mem > dev_priv->max_mob_size) + return MODE_MEM; + + return MODE_OK; +} static const struct drm_connector_funcs vmw_stdu_connector_funcs = { .dpms = vmw_du_connector_dpms, @@ -845,7 +891,7 @@ static const struct drm_connector_funcs vmw_stdu_connector_funcs = { static const struct drm_connector_helper_funcs vmw_stdu_connector_helper_funcs = { .get_modes = vmw_connector_get_modes, - .mode_valid = vmw_connector_mode_valid + .mode_valid = vmw_stdu_connector_mode_valid }; diff --git a/drivers/gpu/drm/xe/xe_gt_idle.c b/drivers/gpu/drm/xe/xe_gt_idle.c index 8fc0f3f6ecc5..944770fb2daf 100644 --- a/drivers/gpu/drm/xe/xe_gt_idle.c +++ b/drivers/gpu/drm/xe/xe_gt_idle.c @@ -147,6 +147,13 @@ static const struct attribute *gt_idle_attrs[] = { static void gt_idle_sysfs_fini(struct drm_device *drm, void *arg) { struct kobject *kobj = arg; + struct xe_gt *gt = kobj_to_gt(kobj->parent); + + if (gt_to_xe(gt)->info.skip_guc_pc) { + XE_WARN_ON(xe_force_wake_get(gt_to_fw(gt), XE_FW_GT)); + xe_gt_idle_disable_c6(gt); + xe_force_wake_put(gt_to_fw(gt), XE_FW_GT); + } sysfs_remove_files(kobj, gt_idle_attrs); kobject_put(kobj); @@ -199,7 +206,7 @@ void xe_gt_idle_enable_c6(struct xe_gt *gt) void xe_gt_idle_disable_c6(struct xe_gt *gt) { xe_device_assert_mem_access(gt_to_xe(gt)); - xe_force_wake_assert_held(gt_to_fw(gt), XE_FORCEWAKE_ALL); + xe_force_wake_assert_held(gt_to_fw(gt), XE_FW_GT); xe_mmio_write32(gt, PG_ENABLE, 0); xe_mmio_write32(gt, RC_CONTROL, 0); diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c index 79116ad58620..6c2cfc54442c 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c @@ -1274,6 +1274,9 @@ static void pf_reset_vf_lmtt(struct xe_device *xe, unsigned int vfid) struct xe_tile *tile; unsigned int tid; + xe_assert(xe, IS_DGFX(xe)); + xe_assert(xe, IS_SRIOV_PF(xe)); + for_each_tile(tile, xe, tid) { lmtt = &tile->sriov.pf.lmtt; xe_lmtt_drop_pages(lmtt, vfid); @@ -1292,6 +1295,9 @@ static int pf_update_vf_lmtt(struct xe_device *xe, unsigned int vfid) unsigned int tid; int err; + xe_assert(xe, IS_DGFX(xe)); + xe_assert(xe, IS_SRIOV_PF(xe)); + total = 0; for_each_tile(tile, xe, tid) total += pf_get_vf_config_lmem(tile->primary_gt, vfid); @@ -1337,6 +1343,7 @@ fail: static void pf_release_vf_config_lmem(struct xe_gt *gt, struct xe_gt_sriov_config *config) { + xe_gt_assert(gt, IS_DGFX(gt_to_xe(gt))); xe_gt_assert(gt, !xe_gt_is_media_type(gt)); lockdep_assert_held(xe_gt_sriov_pf_master_mutex(gt)); @@ -1355,6 +1362,7 @@ static int pf_provision_vf_lmem(struct xe_gt *gt, unsigned int vfid, u64 size) int err; xe_gt_assert(gt, vfid); + xe_gt_assert(gt, IS_DGFX(xe)); xe_gt_assert(gt, !xe_gt_is_media_type(gt)); size = round_up(size, pf_get_lmem_alignment(gt)); @@ -1745,10 +1753,14 @@ static void pf_reset_config_sched(struct xe_gt *gt, struct xe_gt_sriov_config *c static void pf_release_vf_config(struct xe_gt *gt, unsigned int vfid) { struct xe_gt_sriov_config *config = pf_pick_vf_config(gt, vfid); + struct xe_device *xe = gt_to_xe(gt); if (!xe_gt_is_media_type(gt)) { pf_release_vf_config_ggtt(gt, config); - pf_release_vf_config_lmem(gt, config); + if (IS_DGFX(xe)) { + pf_release_vf_config_lmem(gt, config); + pf_update_vf_lmtt(xe, vfid); + } } pf_release_config_ctxs(gt, config); pf_release_config_dbs(gt, config); diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c index 240e7a4bbff1..5faca4fc2fef 100644 --- a/drivers/gpu/drm/xe/xe_guc.c +++ b/drivers/gpu/drm/xe/xe_guc.c @@ -631,8 +631,6 @@ int xe_guc_enable_communication(struct xe_guc *guc) struct xe_device *xe = guc_to_xe(guc); int err; - guc_enable_irq(guc); - if (IS_SRIOV_VF(xe) && xe_device_has_memirq(xe)) { struct xe_gt *gt = guc_to_gt(guc); struct xe_tile *tile = gt_to_tile(gt); @@ -640,6 +638,8 @@ int xe_guc_enable_communication(struct xe_guc *guc) err = xe_memirq_init_guc(&tile->sriov.vf.memirq, guc); if (err) return err; + } else { + guc_enable_irq(guc); } xe_mmio_rmw32(guc_to_gt(guc), PMINTRMSK, diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c index 509649d0e65e..23382ced4ea7 100644 --- a/drivers/gpu/drm/xe/xe_guc_pc.c +++ b/drivers/gpu/drm/xe/xe_guc_pc.c @@ -895,12 +895,6 @@ int xe_guc_pc_stop(struct xe_guc_pc *pc) static void xe_guc_pc_fini(struct drm_device *drm, void *arg) { struct xe_guc_pc *pc = arg; - struct xe_device *xe = pc_to_xe(pc); - - if (xe->info.skip_guc_pc) { - xe_gt_idle_disable_c6(pc_to_gt(pc)); - return; - } XE_WARN_ON(xe_force_wake_get(gt_to_fw(pc_to_gt(pc)), XE_FORCEWAKE_ALL)); XE_WARN_ON(xe_guc_pc_gucrc_disable(pc)); diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c index d42b3f33bd7a..aca7a9af6e84 100644 --- a/drivers/gpu/drm/xe/xe_ring_ops.c +++ b/drivers/gpu/drm/xe/xe_ring_ops.c @@ -80,6 +80,16 @@ static int emit_store_imm_ggtt(u32 addr, u32 value, u32 *dw, int i) return i; } +static int emit_flush_dw(u32 *dw, int i) +{ + dw[i++] = MI_FLUSH_DW | MI_FLUSH_IMM_DW; + dw[i++] = 0; + dw[i++] = 0; + dw[i++] = 0; + + return i; +} + static int emit_flush_imm_ggtt(u32 addr, u32 value, bool invalidate_tlb, u32 *dw, int i) { @@ -234,10 +244,12 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc i = emit_bb_start(batch_addr, ppgtt_flag, dw, i); - if (job->user_fence.used) + if (job->user_fence.used) { + i = emit_flush_dw(dw, i); i = emit_store_imm_ppgtt_posted(job->user_fence.addr, job->user_fence.value, dw, i); + } i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, false, dw, i); @@ -293,10 +305,12 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc, i = emit_bb_start(batch_addr, ppgtt_flag, dw, i); - if (job->user_fence.used) + if (job->user_fence.used) { + i = emit_flush_dw(dw, i); i = emit_store_imm_ppgtt_posted(job->user_fence.addr, job->user_fence.value, dw, i); + } i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, false, dw, i); diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index 02de2bf4f790..37e6d25593c2 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -1204,8 +1204,8 @@ static __u8 *asus_report_fixup(struct hid_device *hdev, __u8 *rdesc, } /* match many more n-key devices */ - if (drvdata->quirks & QUIRK_ROG_NKEY_KEYBOARD) { - for (int i = 0; i < *rsize + 1; i++) { + if (drvdata->quirks & QUIRK_ROG_NKEY_KEYBOARD && *rsize > 15) { + for (int i = 0; i < *rsize - 15; i++) { /* offset to the count from 0x5a report part always 14 */ if (rdesc[i] == 0x85 && rdesc[i + 1] == 0x5a && rdesc[i + 14] == 0x95 && rdesc[i + 15] == 0x05) { diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index b1fa0378e8f4..74efda212c55 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1448,7 +1448,6 @@ static void implement(const struct hid_device *hid, u8 *report, hid_warn(hid, "%s() called with too large value %d (n: %d)! (%s)\n", __func__, value, n, current->comm); - WARN_ON(1); value &= m; } } diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index 87a961cae775..d5abfe652fb5 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -3366,6 +3366,8 @@ static const char *keys[KEY_MAX + 1] = { [KEY_CAMERA_ACCESS_ENABLE] = "CameraAccessEnable", [KEY_CAMERA_ACCESS_DISABLE] = "CameraAccessDisable", [KEY_CAMERA_ACCESS_TOGGLE] = "CameraAccessToggle", + [KEY_ACCESSIBILITY] = "Accessibility", + [KEY_DO_NOT_DISTURB] = "DoNotDisturb", [KEY_DICTATE] = "Dictate", [KEY_MICMUTE] = "MicrophoneMute", [KEY_BRIGHTNESS_MIN] = "BrightnessMin", diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 61d2a21affa2..72d56ee7ce1b 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -423,6 +423,8 @@ #define I2C_DEVICE_ID_HP_SPECTRE_X360_13_AW0020NG 0x29DF #define I2C_DEVICE_ID_ASUS_TP420IA_TOUCHSCREEN 0x2BC8 #define I2C_DEVICE_ID_ASUS_GV301RA_TOUCHSCREEN 0x2C82 +#define I2C_DEVICE_ID_ASUS_UX3402_TOUCHSCREEN 0x2F2C +#define I2C_DEVICE_ID_ASUS_UX6404_TOUCHSCREEN 0x4116 #define USB_DEVICE_ID_ASUS_UX550VE_TOUCHSCREEN 0x2544 #define USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN 0x2706 #define I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN 0x261A diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index e03d300d2bac..c9094a4f281e 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -377,6 +377,10 @@ static const struct hid_device_id hid_battery_quirks[] = { HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_ASUS_GV301RA_TOUCHSCREEN), HID_BATTERY_QUIRK_IGNORE }, + { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_ASUS_UX3402_TOUCHSCREEN), + HID_BATTERY_QUIRK_IGNORE }, + { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_ASUS_UX6404_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), @@ -833,9 +837,18 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel break; } + if ((usage->hid & 0xf0) == 0x90) { /* SystemControl*/ + switch (usage->hid & 0xf) { + case 0xb: map_key_clear(KEY_DO_NOT_DISTURB); break; + default: goto ignore; + } + break; + } + if ((usage->hid & 0xf0) == 0xa0) { /* SystemControl */ switch (usage->hid & 0xf) { case 0x9: map_key_clear(KEY_MICMUTE); break; + case 0xa: map_key_clear(KEY_ACCESSIBILITY); break; default: goto ignore; } break; diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index 3c3c497b6b91..37958edec55f 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -1284,8 +1284,10 @@ static int logi_dj_recv_switch_to_dj_mode(struct dj_receiver_dev *djrcv_dev, */ msleep(50); - if (retval) + if (retval) { + kfree(dj_report); return retval; + } } /* diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index b81d5bcc76a7..400d70e6dbe2 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -27,6 +27,7 @@ #include "usbhid/usbhid.h" #include "hid-ids.h" +MODULE_DESCRIPTION("Support for Logitech devices relying on the HID++ specification"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Benjamin Tissoires <[email protected]>"); MODULE_AUTHOR("Nestor Lopez Casado <[email protected]>"); diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c index b4a97803eca3..3062daf68d31 100644 --- a/drivers/hid/hid-nintendo.c +++ b/drivers/hid/hid-nintendo.c @@ -2725,13 +2725,13 @@ static int nintendo_hid_probe(struct hid_device *hdev, ret = joycon_power_supply_create(ctlr); if (ret) { hid_err(hdev, "Failed to create power_supply; ret=%d\n", ret); - goto err_close; + goto err_ida; } ret = joycon_input_create(ctlr); if (ret) { hid_err(hdev, "Failed to create input device; ret=%d\n", ret); - goto err_close; + goto err_ida; } ctlr->ctlr_state = JOYCON_CTLR_STATE_READ; @@ -2739,6 +2739,8 @@ static int nintendo_hid_probe(struct hid_device *hdev, hid_dbg(hdev, "probe - success\n"); return 0; +err_ida: + ida_free(&nintendo_player_id_allocator, ctlr->player_id); err_close: hid_hw_close(hdev); err_stop: diff --git a/drivers/hid/hid-nvidia-shield.c b/drivers/hid/hid-nvidia-shield.c index 58b15750dbb0..ff9078ad1961 100644 --- a/drivers/hid/hid-nvidia-shield.c +++ b/drivers/hid/hid-nvidia-shield.c @@ -283,7 +283,9 @@ static struct input_dev *shield_haptics_create( return haptics; input_set_capability(haptics, EV_FF, FF_RUMBLE); - input_ff_create_memless(haptics, NULL, play_effect); + ret = input_ff_create_memless(haptics, NULL, play_effect); + if (ret) + goto err; ret = input_register_device(haptics); if (ret) diff --git a/drivers/hid/i2c-hid/i2c-hid-of-elan.c b/drivers/hid/i2c-hid/i2c-hid-of-elan.c index 5b91fb106cfc..091e37933225 100644 --- a/drivers/hid/i2c-hid/i2c-hid-of-elan.c +++ b/drivers/hid/i2c-hid/i2c-hid-of-elan.c @@ -31,6 +31,7 @@ struct i2c_hid_of_elan { struct regulator *vcc33; struct regulator *vccio; struct gpio_desc *reset_gpio; + bool no_reset_on_power_off; const struct elan_i2c_hid_chip_data *chip_data; }; @@ -40,17 +41,17 @@ static int elan_i2c_hid_power_up(struct i2chid_ops *ops) container_of(ops, struct i2c_hid_of_elan, ops); int ret; + gpiod_set_value_cansleep(ihid_elan->reset_gpio, 1); + if (ihid_elan->vcc33) { ret = regulator_enable(ihid_elan->vcc33); if (ret) - return ret; + goto err_deassert_reset; } ret = regulator_enable(ihid_elan->vccio); - if (ret) { - regulator_disable(ihid_elan->vcc33); - return ret; - } + if (ret) + goto err_disable_vcc33; if (ihid_elan->chip_data->post_power_delay_ms) msleep(ihid_elan->chip_data->post_power_delay_ms); @@ -60,6 +61,15 @@ static int elan_i2c_hid_power_up(struct i2chid_ops *ops) msleep(ihid_elan->chip_data->post_gpio_reset_on_delay_ms); return 0; + +err_disable_vcc33: + if (ihid_elan->vcc33) + regulator_disable(ihid_elan->vcc33); +err_deassert_reset: + if (ihid_elan->no_reset_on_power_off) + gpiod_set_value_cansleep(ihid_elan->reset_gpio, 0); + + return ret; } static void elan_i2c_hid_power_down(struct i2chid_ops *ops) @@ -67,7 +77,14 @@ static void elan_i2c_hid_power_down(struct i2chid_ops *ops) struct i2c_hid_of_elan *ihid_elan = container_of(ops, struct i2c_hid_of_elan, ops); - gpiod_set_value_cansleep(ihid_elan->reset_gpio, 1); + /* + * Do not assert reset when the hardware allows for it to remain + * deasserted regardless of the state of the (shared) power supply to + * avoid wasting power when the supply is left on. + */ + if (!ihid_elan->no_reset_on_power_off) + gpiod_set_value_cansleep(ihid_elan->reset_gpio, 1); + if (ihid_elan->chip_data->post_gpio_reset_off_delay_ms) msleep(ihid_elan->chip_data->post_gpio_reset_off_delay_ms); @@ -79,6 +96,7 @@ static void elan_i2c_hid_power_down(struct i2chid_ops *ops) static int i2c_hid_of_elan_probe(struct i2c_client *client) { struct i2c_hid_of_elan *ihid_elan; + int ret; ihid_elan = devm_kzalloc(&client->dev, sizeof(*ihid_elan), GFP_KERNEL); if (!ihid_elan) @@ -93,21 +111,38 @@ static int i2c_hid_of_elan_probe(struct i2c_client *client) if (IS_ERR(ihid_elan->reset_gpio)) return PTR_ERR(ihid_elan->reset_gpio); + ihid_elan->no_reset_on_power_off = of_property_read_bool(client->dev.of_node, + "no-reset-on-power-off"); + ihid_elan->vccio = devm_regulator_get(&client->dev, "vccio"); - if (IS_ERR(ihid_elan->vccio)) - return PTR_ERR(ihid_elan->vccio); + if (IS_ERR(ihid_elan->vccio)) { + ret = PTR_ERR(ihid_elan->vccio); + goto err_deassert_reset; + } ihid_elan->chip_data = device_get_match_data(&client->dev); if (ihid_elan->chip_data->main_supply_name) { ihid_elan->vcc33 = devm_regulator_get(&client->dev, ihid_elan->chip_data->main_supply_name); - if (IS_ERR(ihid_elan->vcc33)) - return PTR_ERR(ihid_elan->vcc33); + if (IS_ERR(ihid_elan->vcc33)) { + ret = PTR_ERR(ihid_elan->vcc33); + goto err_deassert_reset; + } } - return i2c_hid_core_probe(client, &ihid_elan->ops, - ihid_elan->chip_data->hid_descriptor_address, 0); + ret = i2c_hid_core_probe(client, &ihid_elan->ops, + ihid_elan->chip_data->hid_descriptor_address, 0); + if (ret) + goto err_deassert_reset; + + return 0; + +err_deassert_reset: + if (ihid_elan->no_reset_on_power_off) + gpiod_set_value_cansleep(ihid_elan->reset_gpio, 0); + + return ret; } static const struct elan_i2c_hid_chip_data elan_ekth6915_chip_data = { diff --git a/drivers/hid/intel-ish-hid/ishtp/loader.c b/drivers/hid/intel-ish-hid/ishtp/loader.c index 993f8b390e57..fcca070bdecb 100644 --- a/drivers/hid/intel-ish-hid/ishtp/loader.c +++ b/drivers/hid/intel-ish-hid/ishtp/loader.c @@ -84,8 +84,8 @@ static int loader_write_message(struct ishtp_device *dev, void *buf, int len) static int loader_xfer_cmd(struct ishtp_device *dev, void *req, int req_len, void *resp, int resp_len) { - struct loader_msg_header *req_hdr = req; - struct loader_msg_header *resp_hdr = resp; + union loader_msg_header req_hdr; + union loader_msg_header resp_hdr; struct device *devc = dev->devc; int rv; @@ -93,34 +93,37 @@ static int loader_xfer_cmd(struct ishtp_device *dev, void *req, int req_len, dev->fw_loader_rx_size = resp_len; rv = loader_write_message(dev, req, req_len); + req_hdr.val32 = le32_to_cpup(req); + if (rv < 0) { - dev_err(devc, "write cmd %u failed:%d\n", req_hdr->command, rv); + dev_err(devc, "write cmd %u failed:%d\n", req_hdr.command, rv); return rv; } /* Wait the ACK */ wait_event_interruptible_timeout(dev->wait_loader_recvd_msg, dev->fw_loader_received, ISHTP_LOADER_TIMEOUT); + resp_hdr.val32 = le32_to_cpup(resp); dev->fw_loader_rx_size = 0; dev->fw_loader_rx_buf = NULL; if (!dev->fw_loader_received) { - dev_err(devc, "wait response of cmd %u timeout\n", req_hdr->command); + dev_err(devc, "wait response of cmd %u timeout\n", req_hdr.command); return -ETIMEDOUT; } - if (!resp_hdr->is_response) { - dev_err(devc, "not a response for %u\n", req_hdr->command); + if (!resp_hdr.is_response) { + dev_err(devc, "not a response for %u\n", req_hdr.command); return -EBADMSG; } - if (req_hdr->command != resp_hdr->command) { - dev_err(devc, "unexpected cmd response %u:%u\n", req_hdr->command, - resp_hdr->command); + if (req_hdr.command != resp_hdr.command) { + dev_err(devc, "unexpected cmd response %u:%u\n", req_hdr.command, + resp_hdr.command); return -EBADMSG; } - if (resp_hdr->status) { - dev_err(devc, "cmd %u failed %u\n", req_hdr->command, resp_hdr->status); + if (resp_hdr.status) { + dev_err(devc, "cmd %u failed %u\n", req_hdr.command, resp_hdr.status); return -EIO; } @@ -138,12 +141,13 @@ static void release_dma_bufs(struct ishtp_device *dev, struct loader_xfer_dma_fragment *fragment, void **dma_bufs, u32 fragment_size) { + dma_addr_t dma_addr; int i; for (i = 0; i < FRAGMENT_MAX_NUM; i++) { if (dma_bufs[i]) { - dma_free_coherent(dev->devc, fragment_size, dma_bufs[i], - fragment->fragment_tbl[i].ddr_adrs); + dma_addr = le64_to_cpu(fragment->fragment_tbl[i].ddr_adrs); + dma_free_coherent(dev->devc, fragment_size, dma_bufs[i], dma_addr); dma_bufs[i] = NULL; } } @@ -156,29 +160,33 @@ static void release_dma_bufs(struct ishtp_device *dev, * @fragment: The ISHTP firmware fragment descriptor * @dma_bufs: The array of DMA fragment buffers * @fragment_size: The size of a single DMA fragment + * @fragment_count: Number of fragments * * Return: 0 on success, negative error code on failure */ static int prepare_dma_bufs(struct ishtp_device *dev, const struct firmware *ish_fw, struct loader_xfer_dma_fragment *fragment, - void **dma_bufs, u32 fragment_size) + void **dma_bufs, u32 fragment_size, u32 fragment_count) { + dma_addr_t dma_addr; u32 offset = 0; + u32 length; int i; - for (i = 0; i < fragment->fragment_cnt && offset < ish_fw->size; i++) { - dma_bufs[i] = dma_alloc_coherent(dev->devc, fragment_size, - &fragment->fragment_tbl[i].ddr_adrs, GFP_KERNEL); + for (i = 0; i < fragment_count && offset < ish_fw->size; i++) { + dma_bufs[i] = dma_alloc_coherent(dev->devc, fragment_size, &dma_addr, GFP_KERNEL); if (!dma_bufs[i]) return -ENOMEM; - fragment->fragment_tbl[i].length = clamp(ish_fw->size - offset, 0, fragment_size); - fragment->fragment_tbl[i].fw_off = offset; - memcpy(dma_bufs[i], ish_fw->data + offset, fragment->fragment_tbl[i].length); + fragment->fragment_tbl[i].ddr_adrs = cpu_to_le64(dma_addr); + length = clamp(ish_fw->size - offset, 0, fragment_size); + fragment->fragment_tbl[i].length = cpu_to_le32(length); + fragment->fragment_tbl[i].fw_off = cpu_to_le32(offset); + memcpy(dma_bufs[i], ish_fw->data + offset, length); clflush_cache_range(dma_bufs[i], fragment_size); - offset += fragment->fragment_tbl[i].length; + offset += length; } return 0; @@ -206,17 +214,17 @@ void ishtp_loader_work(struct work_struct *work) { DEFINE_RAW_FLEX(struct loader_xfer_dma_fragment, fragment, fragment_tbl, FRAGMENT_MAX_NUM); struct ishtp_device *dev = container_of(work, struct ishtp_device, work_fw_loader); - struct loader_xfer_query query = { - .header.command = LOADER_CMD_XFER_QUERY, - }; - struct loader_start start = { - .header.command = LOADER_CMD_START, - }; + union loader_msg_header query_hdr = { .command = LOADER_CMD_XFER_QUERY, }; + union loader_msg_header start_hdr = { .command = LOADER_CMD_START, }; + union loader_msg_header fragment_hdr = { .command = LOADER_CMD_XFER_FRAGMENT, }; + struct loader_xfer_query query = { .header = cpu_to_le32(query_hdr.val32), }; + struct loader_start start = { .header = cpu_to_le32(start_hdr.val32), }; union loader_recv_message recv_msg; char *filename = dev->driver_data->fw_filename; const struct firmware *ish_fw; void *dma_bufs[FRAGMENT_MAX_NUM] = {}; u32 fragment_size; + u32 fragment_count; int retry = ISHTP_LOADER_RETRY_TIMES; int rv; @@ -226,23 +234,24 @@ void ishtp_loader_work(struct work_struct *work) return; } - fragment->fragment.header.command = LOADER_CMD_XFER_FRAGMENT; - fragment->fragment.xfer_mode = LOADER_XFER_MODE_DMA; - fragment->fragment.is_last = 1; - fragment->fragment.size = ish_fw->size; + fragment->fragment.header = cpu_to_le32(fragment_hdr.val32); + fragment->fragment.xfer_mode = cpu_to_le32(LOADER_XFER_MODE_DMA); + fragment->fragment.is_last = cpu_to_le32(1); + fragment->fragment.size = cpu_to_le32(ish_fw->size); /* Calculate the size of a single DMA fragment */ fragment_size = PFN_ALIGN(DIV_ROUND_UP(ish_fw->size, FRAGMENT_MAX_NUM)); /* Calculate the count of DMA fragments */ - fragment->fragment_cnt = DIV_ROUND_UP(ish_fw->size, fragment_size); + fragment_count = DIV_ROUND_UP(ish_fw->size, fragment_size); + fragment->fragment_cnt = cpu_to_le32(fragment_count); - rv = prepare_dma_bufs(dev, ish_fw, fragment, dma_bufs, fragment_size); + rv = prepare_dma_bufs(dev, ish_fw, fragment, dma_bufs, fragment_size, fragment_count); if (rv) { dev_err(dev->devc, "prepare DMA buffer failed.\n"); goto out; } do { - query.image_size = ish_fw->size; + query.image_size = cpu_to_le32(ish_fw->size); rv = loader_xfer_cmd(dev, &query, sizeof(query), recv_msg.raw_data, sizeof(struct loader_xfer_query_ack)); if (rv) @@ -255,7 +264,7 @@ void ishtp_loader_work(struct work_struct *work) recv_msg.query_ack.version_build); rv = loader_xfer_cmd(dev, fragment, - struct_size(fragment, fragment_tbl, fragment->fragment_cnt), + struct_size(fragment, fragment_tbl, fragment_count), recv_msg.raw_data, sizeof(struct loader_xfer_fragment_ack)); if (rv) continue; /* try again if failed */ diff --git a/drivers/hid/intel-ish-hid/ishtp/loader.h b/drivers/hid/intel-ish-hid/ishtp/loader.h index 7aa45ebc3f7b..308b96085a4d 100644 --- a/drivers/hid/intel-ish-hid/ishtp/loader.h +++ b/drivers/hid/intel-ish-hid/ishtp/loader.h @@ -30,19 +30,23 @@ struct work_struct; #define LOADER_XFER_MODE_DMA BIT(0) /** - * struct loader_msg_header - ISHTP firmware loader message header + * union loader_msg_header - ISHTP firmware loader message header * @command: Command type * @is_response: Indicates if the message is a response * @has_next: Indicates if there is a next message * @reserved: Reserved for future use * @status: Status of the message - */ -struct loader_msg_header { - __le32 command:7; - __le32 is_response:1; - __le32 has_next:1; - __le32 reserved:15; - __le32 status:8; + * @val32: entire header as a 32-bit value + */ +union loader_msg_header { + struct { + __u32 command:7; + __u32 is_response:1; + __u32 has_next:1; + __u32 reserved:15; + __u32 status:8; + }; + __u32 val32; }; /** @@ -51,7 +55,7 @@ struct loader_msg_header { * @image_size: Size of the image */ struct loader_xfer_query { - struct loader_msg_header header; + __le32 header; __le32 image_size; }; @@ -103,7 +107,7 @@ struct loader_capability { * @capability: Loader capability */ struct loader_xfer_query_ack { - struct loader_msg_header header; + __le32 header; __le16 version_major; __le16 version_minor; __le16 version_hotfix; @@ -122,7 +126,7 @@ struct loader_xfer_query_ack { * @is_last: Is last */ struct loader_xfer_fragment { - struct loader_msg_header header; + __le32 header; __le32 xfer_mode; __le32 offset; __le32 size; @@ -134,7 +138,7 @@ struct loader_xfer_fragment { * @header: Header of the message */ struct loader_xfer_fragment_ack { - struct loader_msg_header header; + __le32 header; }; /** @@ -170,7 +174,7 @@ struct loader_xfer_dma_fragment { * @header: Header of the message */ struct loader_start { - struct loader_msg_header header; + __le32 header; }; /** @@ -178,10 +182,11 @@ struct loader_start { * @header: Header of the message */ struct loader_start_ack { - struct loader_msg_header header; + __le32 header; }; union loader_recv_message { + __le32 header; struct loader_xfer_query_ack query_ack; struct loader_xfer_fragment_ack fragment_ack; struct loader_start_ack start_ack; diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index a8ad728354cb..e0d676c74f14 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -45,8 +45,8 @@ int hv_init(void) * This involves a hypercall. */ int hv_post_message(union hv_connection_id connection_id, - enum hv_message_type message_type, - void *payload, size_t payload_size) + enum hv_message_type message_type, + void *payload, size_t payload_size) { struct hv_input_post_message *aligned_msg; unsigned long flags; @@ -86,7 +86,7 @@ int hv_post_message(union hv_connection_id connection_id, status = HV_STATUS_INVALID_PARAMETER; } else { status = hv_do_hypercall(HVCALL_POST_MESSAGE, - aligned_msg, NULL); + aligned_msg, NULL); } local_irq_restore(flags); @@ -111,7 +111,7 @@ int hv_synic_alloc(void) hv_context.hv_numa_map = kcalloc(nr_node_ids, sizeof(struct cpumask), GFP_KERNEL); - if (hv_context.hv_numa_map == NULL) { + if (!hv_context.hv_numa_map) { pr_err("Unable to allocate NUMA map\n"); goto err; } @@ -120,11 +120,11 @@ int hv_synic_alloc(void) hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu); tasklet_init(&hv_cpu->msg_dpc, - vmbus_on_msg_dpc, (unsigned long) hv_cpu); + vmbus_on_msg_dpc, (unsigned long)hv_cpu); if (ms_hyperv.paravisor_present && hv_isolation_type_tdx()) { hv_cpu->post_msg_page = (void *)get_zeroed_page(GFP_ATOMIC); - if (hv_cpu->post_msg_page == NULL) { + if (!hv_cpu->post_msg_page) { pr_err("Unable to allocate post msg page\n"); goto err; } @@ -147,14 +147,14 @@ int hv_synic_alloc(void) if (!ms_hyperv.paravisor_present && !hv_root_partition) { hv_cpu->synic_message_page = (void *)get_zeroed_page(GFP_ATOMIC); - if (hv_cpu->synic_message_page == NULL) { + if (!hv_cpu->synic_message_page) { pr_err("Unable to allocate SYNIC message page\n"); goto err; } hv_cpu->synic_event_page = (void *)get_zeroed_page(GFP_ATOMIC); - if (hv_cpu->synic_event_page == NULL) { + if (!hv_cpu->synic_event_page) { pr_err("Unable to allocate SYNIC event page\n"); free_page((unsigned long)hv_cpu->synic_message_page); @@ -203,14 +203,13 @@ err: return ret; } - void hv_synic_free(void) { int cpu, ret; for_each_present_cpu(cpu) { - struct hv_per_cpu_context *hv_cpu - = per_cpu_ptr(hv_context.cpu_context, cpu); + struct hv_per_cpu_context *hv_cpu = + per_cpu_ptr(hv_context.cpu_context, cpu); /* It's better to leak the page if the encryption fails. */ if (ms_hyperv.paravisor_present && hv_isolation_type_tdx()) { @@ -262,8 +261,8 @@ void hv_synic_free(void) */ void hv_synic_enable_regs(unsigned int cpu) { - struct hv_per_cpu_context *hv_cpu - = per_cpu_ptr(hv_context.cpu_context, cpu); + struct hv_per_cpu_context *hv_cpu = + per_cpu_ptr(hv_context.cpu_context, cpu); union hv_synic_simp simp; union hv_synic_siefp siefp; union hv_synic_sint shared_sint; @@ -277,8 +276,8 @@ void hv_synic_enable_regs(unsigned int cpu) /* Mask out vTOM bit. ioremap_cache() maps decrypted */ u64 base = (simp.base_simp_gpa << HV_HYP_PAGE_SHIFT) & ~ms_hyperv.shared_gpa_boundary; - hv_cpu->synic_message_page - = (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE); + hv_cpu->synic_message_page = + (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE); if (!hv_cpu->synic_message_page) pr_err("Fail to map synic message page.\n"); } else { @@ -296,8 +295,8 @@ void hv_synic_enable_regs(unsigned int cpu) /* Mask out vTOM bit. ioremap_cache() maps decrypted */ u64 base = (siefp.base_siefp_gpa << HV_HYP_PAGE_SHIFT) & ~ms_hyperv.shared_gpa_boundary; - hv_cpu->synic_event_page - = (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE); + hv_cpu->synic_event_page = + (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE); if (!hv_cpu->synic_event_page) pr_err("Fail to map synic event page.\n"); } else { @@ -348,8 +347,8 @@ int hv_synic_init(unsigned int cpu) */ void hv_synic_disable_regs(unsigned int cpu) { - struct hv_per_cpu_context *hv_cpu - = per_cpu_ptr(hv_context.cpu_context, cpu); + struct hv_per_cpu_context *hv_cpu = + per_cpu_ptr(hv_context.cpu_context, cpu); union hv_synic_sint shared_sint; union hv_synic_simp simp; union hv_synic_siefp siefp; diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index e000fa3b9f97..0e7427c2baf5 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -25,6 +25,7 @@ #include <linux/notifier.h> #include <linux/percpu_counter.h> #include <linux/page_reporting.h> +#include <linux/sizes.h> #include <linux/hyperv.h> #include <asm/hyperv-tlfs.h> @@ -41,8 +42,6 @@ * Begin protocol definitions. */ - - /* * Protocol versions. The low word is the minor version, the high word the major * version. @@ -71,8 +70,6 @@ enum { DYNMEM_PROTOCOL_VERSION_CURRENT = DYNMEM_PROTOCOL_VERSION_WIN10 }; - - /* * Message Types */ @@ -101,7 +98,6 @@ enum dm_message_type { DM_VERSION_1_MAX = 12 }; - /* * Structures defining the dynamic memory management * protocol. @@ -115,7 +111,6 @@ union dm_version { __u32 version; } __packed; - union dm_caps { struct { __u64 balloon:1; @@ -148,8 +143,6 @@ union dm_mem_page_range { __u64 page_range; } __packed; - - /* * The header for all dynamic memory messages: * @@ -174,7 +167,6 @@ struct dm_message { __u8 data[]; /* enclosed message */ } __packed; - /* * Specific message types supporting the dynamic memory protocol. */ @@ -271,7 +263,6 @@ struct dm_status { __u32 io_diff; } __packed; - /* * Message to ask the guest to allocate memory - balloon up message. * This message is sent from the host to the guest. The guest may not be @@ -286,14 +277,13 @@ struct dm_balloon { __u32 reservedz; } __packed; - /* * Balloon response message; this message is sent from the guest * to the host in response to the balloon message. * * reservedz: Reserved; must be set to zero. * more_pages: If FALSE, this is the last message of the transaction. - * if TRUE there will atleast one more message from the guest. + * if TRUE there will be at least one more message from the guest. * * range_count: The number of ranges in the range array. * @@ -314,7 +304,7 @@ struct dm_balloon_response { * to the guest to give guest more memory. * * more_pages: If FALSE, this is the last message of the transaction. - * if TRUE there will atleast one more message from the guest. + * if TRUE there will be at least one more message from the guest. * * reservedz: Reserved; must be set to zero. * @@ -342,7 +332,6 @@ struct dm_unballoon_response { struct dm_header hdr; } __packed; - /* * Hot add request message. Message sent from the host to the guest. * @@ -390,7 +379,6 @@ enum dm_info_type { MAX_INFO_TYPE }; - /* * Header for the information message. */ @@ -425,11 +413,11 @@ struct dm_info_msg { * The range start_pfn : end_pfn specifies the range * that the host has asked us to hot add. The range * start_pfn : ha_end_pfn specifies the range that we have - * currently hot added. We hot add in multiples of 128M - * chunks; it is possible that we may not be able to bring - * online all the pages in the region. The range + * currently hot added. We hot add in chunks equal to the + * memory block size; it is possible that we may not be able + * to bring online all the pages in the region. The range * covered_start_pfn:covered_end_pfn defines the pages that can - * be brough online. + * be brought online. */ struct hv_hotadd_state { @@ -480,10 +468,10 @@ static unsigned long last_post_time; static int hv_hypercall_multi_failure; -module_param(hot_add, bool, (S_IRUGO | S_IWUSR)); +module_param(hot_add, bool, 0644); MODULE_PARM_DESC(hot_add, "If set attempt memory hot_add"); -module_param(pressure_report_delay, uint, (S_IRUGO | S_IWUSR)); +module_param(pressure_report_delay, uint, 0644); MODULE_PARM_DESC(pressure_report_delay, "Delay in secs in reporting pressure"); static atomic_t trans_id = ATOMIC_INIT(0); @@ -502,11 +490,13 @@ enum hv_dm_state { DM_INIT_ERROR }; - static __u8 recv_buffer[HV_HYP_PAGE_SIZE]; static __u8 balloon_up_send_buffer[HV_HYP_PAGE_SIZE]; + +static unsigned long ha_pages_in_chunk; +#define HA_BYTES_IN_CHUNK (ha_pages_in_chunk << PAGE_SHIFT) + #define PAGES_IN_2M (2 * 1024 * 1024 / PAGE_SIZE) -#define HA_CHUNK (128 * 1024 * 1024 / PAGE_SIZE) struct hv_dynmem_device { struct hv_device *dev; @@ -595,12 +585,12 @@ static inline bool has_pfn_is_backed(struct hv_hotadd_state *has, struct hv_hotadd_gap *gap; /* The page is not backed. */ - if ((pfn < has->covered_start_pfn) || (pfn >= has->covered_end_pfn)) + if (pfn < has->covered_start_pfn || pfn >= has->covered_end_pfn) return false; /* Check for gaps. */ list_for_each_entry(gap, &has->gap_list, list) { - if ((pfn >= gap->start_pfn) && (pfn < gap->end_pfn)) + if (pfn >= gap->start_pfn && pfn < gap->end_pfn) return false; } @@ -724,28 +714,21 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size, unsigned long processed_pfn; unsigned long total_pfn = pfn_count; - for (i = 0; i < (size/HA_CHUNK); i++) { - start_pfn = start + (i * HA_CHUNK); + for (i = 0; i < (size/ha_pages_in_chunk); i++) { + start_pfn = start + (i * ha_pages_in_chunk); scoped_guard(spinlock_irqsave, &dm_device.ha_lock) { - has->ha_end_pfn += HA_CHUNK; - - if (total_pfn > HA_CHUNK) { - processed_pfn = HA_CHUNK; - total_pfn -= HA_CHUNK; - } else { - processed_pfn = total_pfn; - total_pfn = 0; - } - - has->covered_end_pfn += processed_pfn; + has->ha_end_pfn += ha_pages_in_chunk; + processed_pfn = umin(total_pfn, ha_pages_in_chunk); + total_pfn -= processed_pfn; + has->covered_end_pfn += processed_pfn; } reinit_completion(&dm_device.ol_waitevent); nid = memory_add_physaddr_to_nid(PFN_PHYS(start_pfn)); ret = add_memory(nid, PFN_PHYS((start_pfn)), - (HA_CHUNK << PAGE_SHIFT), MHP_MERGE_RESOURCE); + HA_BYTES_IN_CHUNK, MHP_MERGE_RESOURCE); if (ret) { pr_err("hot_add memory failed error is %d\n", ret); @@ -760,7 +743,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size, do_hot_add = false; } scoped_guard(spinlock_irqsave, &dm_device.ha_lock) { - has->ha_end_pfn -= HA_CHUNK; + has->ha_end_pfn -= ha_pages_in_chunk; has->covered_end_pfn -= processed_pfn; } break; @@ -787,8 +770,8 @@ static void hv_online_page(struct page *pg, unsigned int order) guard(spinlock_irqsave)(&dm_device.ha_lock); list_for_each_entry(has, &dm_device.ha_region_list, list) { /* The page belongs to a different HAS. */ - if ((pfn < has->start_pfn) || - (pfn + (1UL << order) > has->end_pfn)) + if (pfn < has->start_pfn || + (pfn + (1UL << order) > has->end_pfn)) continue; hv_bring_pgs_online(has, pfn, 1UL << order); @@ -800,7 +783,7 @@ static int pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt) { struct hv_hotadd_state *has; struct hv_hotadd_gap *gap; - unsigned long residual, new_inc; + unsigned long residual; int ret = 0; guard(spinlock_irqsave)(&dm_device.ha_lock); @@ -836,15 +819,9 @@ static int pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt) * our current limit; extend it. */ if ((start_pfn + pfn_cnt) > has->end_pfn) { + /* Extend the region by multiples of ha_pages_in_chunk */ residual = (start_pfn + pfn_cnt - has->end_pfn); - /* - * Extend the region by multiples of HA_CHUNK. - */ - new_inc = (residual / HA_CHUNK) * HA_CHUNK; - if (residual % HA_CHUNK) - new_inc += HA_CHUNK; - - has->end_pfn += new_inc; + has->end_pfn += ALIGN(residual, ha_pages_in_chunk); } ret = 1; @@ -855,7 +832,7 @@ static int pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt) } static unsigned long handle_pg_range(unsigned long pg_start, - unsigned long pg_count) + unsigned long pg_count) { unsigned long start_pfn = pg_start; unsigned long pfn_cnt = pg_count; @@ -866,7 +843,7 @@ static unsigned long handle_pg_range(unsigned long pg_start, unsigned long res = 0, flags; pr_debug("Hot adding %lu pages starting at pfn 0x%lx.\n", pg_count, - pg_start); + pg_start); spin_lock_irqsave(&dm_device.ha_lock, flags); list_for_each_entry(has, &dm_device.ha_region_list, list) { @@ -902,22 +879,19 @@ static unsigned long handle_pg_range(unsigned long pg_start, if (start_pfn > has->start_pfn && online_section_nr(pfn_to_section_nr(start_pfn))) hv_bring_pgs_online(has, start_pfn, pgs_ol); - } - if ((has->ha_end_pfn < has->end_pfn) && (pfn_cnt > 0)) { + if (has->ha_end_pfn < has->end_pfn && pfn_cnt > 0) { /* * We have some residual hot add range * that needs to be hot added; hot add * it now. Hot add a multiple of - * HA_CHUNK that fully covers the pages + * ha_pages_in_chunk that fully covers the pages * we have. */ size = (has->end_pfn - has->ha_end_pfn); if (pfn_cnt <= size) { - size = ((pfn_cnt / HA_CHUNK) * HA_CHUNK); - if (pfn_cnt % HA_CHUNK) - size += HA_CHUNK; + size = ALIGN(pfn_cnt, ha_pages_in_chunk); } else { pfn_cnt = size; } @@ -1010,10 +984,7 @@ static void hot_add_req(struct work_struct *dummy) rg_start = dm->ha_wrk.ha_region_range.finfo.start_page; rg_sz = dm->ha_wrk.ha_region_range.finfo.page_cnt; - if ((rg_start == 0) && (!dm->host_specified_ha_region)) { - unsigned long region_size; - unsigned long region_start; - + if (rg_start == 0 && !dm->host_specified_ha_region) { /* * The host has not specified the hot-add region. * Based on the hot-add page range being specified, @@ -1021,19 +992,13 @@ static void hot_add_req(struct work_struct *dummy) * that need to be hot-added while ensuring the alignment * and size requirements of Linux as it relates to hot-add. */ - region_size = (pfn_cnt / HA_CHUNK) * HA_CHUNK; - if (pfn_cnt % HA_CHUNK) - region_size += HA_CHUNK; - - region_start = (pg_start / HA_CHUNK) * HA_CHUNK; - - rg_start = region_start; - rg_sz = region_size; + rg_start = ALIGN_DOWN(pg_start, ha_pages_in_chunk); + rg_sz = ALIGN(pfn_cnt, ha_pages_in_chunk); } if (do_hot_add) resp.page_count = process_hot_add(pg_start, pfn_cnt, - rg_start, rg_sz); + rg_start, rg_sz); dm->num_pages_added += resp.page_count; #endif @@ -1211,11 +1176,10 @@ static void post_status(struct hv_dynmem_device *dm) sizeof(struct dm_status), (unsigned long)NULL, VM_PKT_DATA_INBAND, 0); - } static void free_balloon_pages(struct hv_dynmem_device *dm, - union dm_mem_page_range *range_array) + union dm_mem_page_range *range_array) { int num_pages = range_array->finfo.page_cnt; __u64 start_frame = range_array->finfo.start_page; @@ -1231,8 +1195,6 @@ static void free_balloon_pages(struct hv_dynmem_device *dm, } } - - static unsigned int alloc_balloon_pages(struct hv_dynmem_device *dm, unsigned int num_pages, struct dm_balloon_response *bl_resp, @@ -1278,7 +1240,6 @@ static unsigned int alloc_balloon_pages(struct hv_dynmem_device *dm, page_to_pfn(pg); bl_resp->range_array[i].finfo.page_cnt = alloc_unit; bl_resp->hdr.size += sizeof(union dm_mem_page_range); - } return i * alloc_unit; @@ -1332,7 +1293,7 @@ static void balloon_up(struct work_struct *dummy) if (num_ballooned == 0 || num_ballooned == num_pages) { pr_debug("Ballooned %u out of %u requested pages.\n", - num_pages, dm_device.balloon_wrk.num_pages); + num_pages, dm_device.balloon_wrk.num_pages); bl_resp->more_pages = 0; done = true; @@ -1366,16 +1327,15 @@ static void balloon_up(struct work_struct *dummy) for (i = 0; i < bl_resp->range_count; i++) free_balloon_pages(&dm_device, - &bl_resp->range_array[i]); + &bl_resp->range_array[i]); done = true; } } - } static void balloon_down(struct hv_dynmem_device *dm, - struct dm_unballoon_request *req) + struct dm_unballoon_request *req) { union dm_mem_page_range *range_array = req->range_array; int range_count = req->range_count; @@ -1389,7 +1349,7 @@ static void balloon_down(struct hv_dynmem_device *dm, } pr_debug("Freed %u ballooned pages.\n", - prev_pages_ballooned - dm->num_pages_ballooned); + prev_pages_ballooned - dm->num_pages_ballooned); if (req->more_pages == 1) return; @@ -1414,8 +1374,7 @@ static int dm_thread_func(void *dm_dev) struct hv_dynmem_device *dm = dm_dev; while (!kthread_should_stop()) { - wait_for_completion_interruptible_timeout( - &dm_device.config_event, 1*HZ); + wait_for_completion_interruptible_timeout(&dm_device.config_event, 1 * HZ); /* * The host expects us to post information on the memory * pressure every second. @@ -1439,9 +1398,8 @@ static int dm_thread_func(void *dm_dev) return 0; } - static void version_resp(struct hv_dynmem_device *dm, - struct dm_version_response *vresp) + struct dm_version_response *vresp) { struct dm_version_request version_req; int ret; @@ -1502,7 +1460,7 @@ version_error: } static void cap_resp(struct hv_dynmem_device *dm, - struct dm_capabilities_resp_msg *cap_resp) + struct dm_capabilities_resp_msg *cap_resp) { if (!cap_resp->is_accepted) { pr_err("Capabilities not accepted by host\n"); @@ -1535,7 +1493,7 @@ static void balloon_onchannelcallback(void *context) switch (dm_hdr->type) { case DM_VERSION_RESPONSE: version_resp(dm, - (struct dm_version_response *)dm_msg); + (struct dm_version_response *)dm_msg); break; case DM_CAPABILITIES_RESPONSE: @@ -1565,7 +1523,7 @@ static void balloon_onchannelcallback(void *context) dm->state = DM_BALLOON_DOWN; balloon_down(dm, - (struct dm_unballoon_request *)recv_buffer); + (struct dm_unballoon_request *)recv_buffer); break; case DM_MEM_HOT_ADD_REQUEST: @@ -1603,17 +1561,15 @@ static void balloon_onchannelcallback(void *context) default: pr_warn_ratelimited("Unhandled message: type: %d\n", dm_hdr->type); - } } - } #define HV_LARGE_REPORTING_ORDER 9 #define HV_LARGE_REPORTING_LEN (HV_HYP_PAGE_SIZE << \ HV_LARGE_REPORTING_ORDER) static int hv_free_page_report(struct page_reporting_dev_info *pr_dev_info, - struct scatterlist *sgl, unsigned int nents) + struct scatterlist *sgl, unsigned int nents) { unsigned long flags; struct hv_memory_hint *hint; @@ -1648,7 +1604,7 @@ static int hv_free_page_report(struct page_reporting_dev_info *pr_dev_info, */ /* page reporting for pages 2MB or higher */ - if (order >= HV_LARGE_REPORTING_ORDER ) { + if (order >= HV_LARGE_REPORTING_ORDER) { range->page.largepage = 1; range->page_size = HV_GPA_PAGE_RANGE_PAGE_SIZE_2MB; range->base_large_pfn = page_to_hvpfn( @@ -1662,23 +1618,21 @@ static int hv_free_page_report(struct page_reporting_dev_info *pr_dev_info, range->page.additional_pages = (sg->length / HV_HYP_PAGE_SIZE) - 1; } - } status = hv_do_rep_hypercall(HV_EXT_CALL_MEMORY_HEAT_HINT, nents, 0, hint, NULL); local_irq_restore(flags); if (!hv_result_success(status)) { - pr_err("Cold memory discard hypercall failed with status %llx\n", - status); + status); if (hv_hypercall_multi_failure > 0) hv_hypercall_multi_failure++; if (hv_result(status) == HV_STATUS_INVALID_PARAMETER) { pr_err("Underlying Hyper-V does not support order less than 9. Hypercall failed\n"); pr_err("Defaulting to page_reporting_order %d\n", - pageblock_order); + pageblock_order); page_reporting_order = pageblock_order; hv_hypercall_multi_failure++; return -EINVAL; @@ -1712,7 +1666,7 @@ static void enable_page_reporting(void) pr_err("Failed to enable cold memory discard: %d\n", ret); } else { pr_info("Cold memory discard hint enabled with order %d\n", - page_reporting_order); + page_reporting_order); } } @@ -1795,7 +1749,7 @@ static int balloon_connect_vsp(struct hv_device *dev) if (ret) goto out; - t = wait_for_completion_timeout(&dm_device.host_event, 5*HZ); + t = wait_for_completion_timeout(&dm_device.host_event, 5 * HZ); if (t == 0) { ret = -ETIMEDOUT; goto out; @@ -1831,10 +1785,13 @@ static int balloon_connect_vsp(struct hv_device *dev) cap_msg.caps.cap_bits.hot_add = hot_add_enabled(); /* - * Specify our alignment requirements as it relates - * memory hot-add. Specify 128MB alignment. + * Specify our alignment requirements for memory hot-add. The value is + * the log base 2 of the number of megabytes in a chunk. For example, + * with 256 MiB chunks, the value is 8. The number of MiB in a chunk + * must be a power of 2. */ - cap_msg.caps.cap_bits.hot_add_alignment = 7; + cap_msg.caps.cap_bits.hot_add_alignment = + ilog2(HA_BYTES_IN_CHUNK / SZ_1M); /* * Currently the host does not use these @@ -1850,7 +1807,7 @@ static int balloon_connect_vsp(struct hv_device *dev) if (ret) goto out; - t = wait_for_completion_timeout(&dm_device.host_event, 5*HZ); + t = wait_for_completion_timeout(&dm_device.host_event, 5 * HZ); if (t == 0) { ret = -ETIMEDOUT; goto out; @@ -1891,8 +1848,8 @@ static int hv_balloon_debug_show(struct seq_file *f, void *offset) char *sname; seq_printf(f, "%-22s: %u.%u\n", "host_version", - DYNMEM_MAJOR_VERSION(dm->version), - DYNMEM_MINOR_VERSION(dm->version)); + DYNMEM_MAJOR_VERSION(dm->version), + DYNMEM_MINOR_VERSION(dm->version)); seq_printf(f, "%-22s:", "capabilities"); if (ballooning_enabled()) @@ -1941,10 +1898,10 @@ static int hv_balloon_debug_show(struct seq_file *f, void *offset) seq_printf(f, "%-22s: %u\n", "pages_ballooned", dm->num_pages_ballooned); seq_printf(f, "%-22s: %lu\n", "total_pages_committed", - get_pages_committed(dm)); + get_pages_committed(dm)); seq_printf(f, "%-22s: %llu\n", "max_dynamic_page_count", - dm->max_dynamic_page_count); + dm->max_dynamic_page_count); return 0; } @@ -1954,7 +1911,7 @@ DEFINE_SHOW_ATTRIBUTE(hv_balloon_debug); static void hv_balloon_debugfs_init(struct hv_dynmem_device *b) { debugfs_create_file("hv-balloon", 0444, NULL, b, - &hv_balloon_debug_fops); + &hv_balloon_debug_fops); } static void hv_balloon_debugfs_exit(struct hv_dynmem_device *b) @@ -1984,8 +1941,23 @@ static int balloon_probe(struct hv_device *dev, hot_add = false; #ifdef CONFIG_MEMORY_HOTPLUG + /* + * Hot-add must operate in chunks that are of size equal to the + * memory block size because that's what the core add_memory() + * interface requires. The Hyper-V interface requires that the memory + * block size be a power of 2, which is guaranteed by the check in + * memory_dev_init(). + */ + ha_pages_in_chunk = memory_block_size_bytes() / PAGE_SIZE; do_hot_add = hot_add; #else + /* + * Without MEMORY_HOTPLUG, the guest returns a failure status for all + * hot add requests from Hyper-V, and the chunk size is used only to + * specify alignment to Hyper-V as required by the host/guest protocol. + * Somewhat arbitrarily, use 128 MiB. + */ + ha_pages_in_chunk = SZ_128M / PAGE_SIZE; do_hot_add = false; #endif dm_device.dev = dev; @@ -2097,7 +2069,6 @@ static int balloon_suspend(struct hv_device *hv_dev) tasklet_enable(&hv_dev->channel->callback_event); return 0; - } static int balloon_resume(struct hv_device *dev) @@ -2156,7 +2127,6 @@ static struct hv_driver balloon_drv = { static int __init init_balloon_drv(void) { - return vmbus_driver_register(&balloon_drv); } diff --git a/drivers/i2c/busses/i2c-at91-slave.c b/drivers/i2c/busses/i2c-at91-slave.c index d6eeea5166c0..131a67d9d4a6 100644 --- a/drivers/i2c/busses/i2c-at91-slave.c +++ b/drivers/i2c/busses/i2c-at91-slave.c @@ -106,8 +106,7 @@ static int at91_unreg_slave(struct i2c_client *slave) static u32 at91_twi_func(struct i2c_adapter *adapter) { - return I2C_FUNC_SLAVE | I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL - | I2C_FUNC_SMBUS_READ_BLOCK_DATA; + return I2C_FUNC_SLAVE; } static const struct i2c_algorithm at91_twi_algorithm_slave = { diff --git a/drivers/i2c/busses/i2c-designware-slave.c b/drivers/i2c/busses/i2c-designware-slave.c index 2e079cf20bb5..78e2c47e3d7d 100644 --- a/drivers/i2c/busses/i2c-designware-slave.c +++ b/drivers/i2c/busses/i2c-designware-slave.c @@ -220,7 +220,7 @@ static const struct i2c_algorithm i2c_dw_algo = { void i2c_dw_configure_slave(struct dw_i2c_dev *dev) { - dev->functionality = I2C_FUNC_SLAVE | DW_IC_DEFAULT_FUNCTIONALITY; + dev->functionality = I2C_FUNC_SLAVE; dev->slave_cfg = DW_IC_CON_RX_FIFO_FULL_HLD_CTRL | DW_IC_CON_RESTART_EN | DW_IC_CON_STOP_DET_IFADDRESSED; diff --git a/drivers/i2c/busses/i2c-ocores.c b/drivers/i2c/busses/i2c-ocores.c index 56a4dabf5a38..4ad670a80a63 100644 --- a/drivers/i2c/busses/i2c-ocores.c +++ b/drivers/i2c/busses/i2c-ocores.c @@ -431,8 +431,8 @@ static int ocores_init(struct device *dev, struct ocores_i2c *i2c) oc_setreg(i2c, OCI2C_PREHIGH, prescale >> 8); /* Init the device */ - oc_setreg(i2c, OCI2C_CMD, OCI2C_CMD_IACK); oc_setreg(i2c, OCI2C_CONTROL, ctrl | OCI2C_CTRL_EN); + oc_setreg(i2c, OCI2C_CMD, OCI2C_CMD_IACK); return 0; } diff --git a/drivers/iio/adc/ad7173.c b/drivers/iio/adc/ad7173.c index a7826bba0852..b26d4575e256 100644 --- a/drivers/iio/adc/ad7173.c +++ b/drivers/iio/adc/ad7173.c @@ -145,6 +145,7 @@ struct ad7173_device_info { unsigned int id; char *name; bool has_temp; + bool has_input_buf; bool has_int_ref; bool has_ref2; u8 num_gpios; @@ -212,18 +213,21 @@ static const struct ad7173_device_info ad7173_device_info[] = { .num_configs = 4, .num_gpios = 2, .has_temp = true, + .has_input_buf = true, .has_int_ref = true, .clock = 2 * HZ_PER_MHZ, .sinc5_data_rates = ad7173_sinc5_data_rates, .num_sinc5_data_rates = ARRAY_SIZE(ad7173_sinc5_data_rates), }, [ID_AD7172_4] = { + .name = "ad7172-4", .id = AD7172_4_ID, .num_inputs = 9, .num_channels = 8, .num_configs = 8, .num_gpios = 4, .has_temp = false, + .has_input_buf = true, .has_ref2 = true, .clock = 2 * HZ_PER_MHZ, .sinc5_data_rates = ad7173_sinc5_data_rates, @@ -237,6 +241,7 @@ static const struct ad7173_device_info ad7173_device_info[] = { .num_configs = 8, .num_gpios = 4, .has_temp = true, + .has_input_buf = true, .has_int_ref = true, .has_ref2 = true, .clock = 2 * HZ_PER_MHZ, @@ -251,18 +256,21 @@ static const struct ad7173_device_info ad7173_device_info[] = { .num_configs = 4, .num_gpios = 2, .has_temp = true, + .has_input_buf = true, .has_int_ref = true, .clock = 16 * HZ_PER_MHZ, .sinc5_data_rates = ad7175_sinc5_data_rates, .num_sinc5_data_rates = ARRAY_SIZE(ad7175_sinc5_data_rates), }, [ID_AD7175_8] = { + .name = "ad7175-8", .id = AD7175_8_ID, .num_inputs = 17, .num_channels = 16, .num_configs = 8, .num_gpios = 4, .has_temp = true, + .has_input_buf = true, .has_int_ref = true, .has_ref2 = true, .clock = 16 * HZ_PER_MHZ, @@ -277,18 +285,21 @@ static const struct ad7173_device_info ad7173_device_info[] = { .num_configs = 4, .num_gpios = 2, .has_temp = false, + .has_input_buf = false, .has_int_ref = true, .clock = 16 * HZ_PER_MHZ, .sinc5_data_rates = ad7175_sinc5_data_rates, .num_sinc5_data_rates = ARRAY_SIZE(ad7175_sinc5_data_rates), }, [ID_AD7177_2] = { + .name = "ad7177-2", .id = AD7177_ID, .num_inputs = 5, .num_channels = 4, .num_configs = 4, .num_gpios = 2, .has_temp = true, + .has_input_buf = true, .has_int_ref = true, .clock = 16 * HZ_PER_MHZ, .odr_start_value = AD7177_ODR_START_VALUE, @@ -532,6 +543,7 @@ static int ad7173_append_status(struct ad_sigma_delta *sd, bool append) unsigned int interface_mode = st->interface_mode; int ret; + interface_mode &= ~AD7173_INTERFACE_DATA_STAT; interface_mode |= AD7173_INTERFACE_DATA_STAT_EN(append); ret = ad_sd_write_reg(&st->sd, AD7173_REG_INTERFACE_MODE, 2, interface_mode); if (ret) @@ -705,7 +717,7 @@ static int ad7173_write_raw(struct iio_dev *indio_dev, { struct ad7173_state *st = iio_priv(indio_dev); struct ad7173_channel_config *cfg; - unsigned int freq, i, reg; + unsigned int freq, i; int ret; ret = iio_device_claim_direct_mode(indio_dev); @@ -721,16 +733,7 @@ static int ad7173_write_raw(struct iio_dev *indio_dev, cfg = &st->channels[chan->address].cfg; cfg->odr = i; - - if (!cfg->live) - break; - - ret = ad_sd_read_reg(&st->sd, AD7173_REG_FILTER(cfg->cfg_slot), 2, ®); - if (ret) - break; - reg &= ~AD7173_FILTER_ODR0_MASK; - reg |= FIELD_PREP(AD7173_FILTER_ODR0_MASK, i); - ret = ad_sd_write_reg(&st->sd, AD7173_REG_FILTER(cfg->cfg_slot), 2, reg); + cfg->live = false; break; default: @@ -792,8 +795,7 @@ static const struct iio_chan_spec ad7173_channel_template = { .type = IIO_VOLTAGE, .indexed = 1, .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | - BIT(IIO_CHAN_INFO_SCALE), - .info_mask_shared_by_all = BIT(IIO_CHAN_INFO_SAMP_FREQ), + BIT(IIO_CHAN_INFO_SCALE) | BIT(IIO_CHAN_INFO_SAMP_FREQ), .scan_type = { .sign = 'u', .realbits = 24, @@ -804,12 +806,11 @@ static const struct iio_chan_spec ad7173_channel_template = { static const struct iio_chan_spec ad7173_temp_iio_channel_template = { .type = IIO_TEMP, - .indexed = 1, .channel = AD7173_AIN_TEMP_POS, .channel2 = AD7173_AIN_TEMP_NEG, .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | - BIT(IIO_CHAN_INFO_SCALE) | BIT(IIO_CHAN_INFO_OFFSET), - .info_mask_shared_by_all = BIT(IIO_CHAN_INFO_SAMP_FREQ), + BIT(IIO_CHAN_INFO_SCALE) | BIT(IIO_CHAN_INFO_OFFSET) | + BIT(IIO_CHAN_INFO_SAMP_FREQ), .scan_type = { .sign = 'u', .realbits = 24, @@ -932,7 +933,7 @@ static int ad7173_fw_parse_channel_config(struct iio_dev *indio_dev) AD7173_CH_ADDRESS(chan_arr[chan_index].channel, chan_arr[chan_index].channel2); chan_st_priv->cfg.bipolar = false; - chan_st_priv->cfg.input_buf = true; + chan_st_priv->cfg.input_buf = st->info->has_input_buf; chan_st_priv->cfg.ref_sel = AD7173_SETUP_REF_SEL_INT_REF; st->adc_mode |= AD7173_ADC_MODE_REF_EN; @@ -989,7 +990,7 @@ static int ad7173_fw_parse_channel_config(struct iio_dev *indio_dev) chan_st_priv->ain = AD7173_CH_ADDRESS(ain[0], ain[1]); chan_st_priv->chan_reg = chan_index; - chan_st_priv->cfg.input_buf = true; + chan_st_priv->cfg.input_buf = st->info->has_input_buf; chan_st_priv->cfg.odr = 0; chan_st_priv->cfg.bipolar = fwnode_property_read_bool(child, "bipolar"); diff --git a/drivers/iio/adc/ad9467.c b/drivers/iio/adc/ad9467.c index e85b763b9ffc..8f5b9c3f6e3d 100644 --- a/drivers/iio/adc/ad9467.c +++ b/drivers/iio/adc/ad9467.c @@ -243,11 +243,11 @@ static void __ad9467_get_scale(struct ad9467_state *st, int index, } static const struct iio_chan_spec ad9434_channels[] = { - AD9467_CHAN(0, 0, 12, 'S'), + AD9467_CHAN(0, 0, 12, 's'), }; static const struct iio_chan_spec ad9467_channels[] = { - AD9467_CHAN(0, 0, 16, 'S'), + AD9467_CHAN(0, 0, 16, 's'), }; static const struct ad9467_chip_info ad9467_chip_tbl = { diff --git a/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c b/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c index fa205f17bd90..f44458c380d9 100644 --- a/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c +++ b/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c @@ -60,11 +60,15 @@ EXPORT_SYMBOL_NS_GPL(inv_sensors_timestamp_init, IIO_INV_SENSORS_TIMESTAMP); int inv_sensors_timestamp_update_odr(struct inv_sensors_timestamp *ts, uint32_t period, bool fifo) { + uint32_t mult; + /* when FIFO is on, prevent odr change if one is already pending */ if (fifo && ts->new_mult != 0) return -EAGAIN; - ts->new_mult = period / ts->chip.clock_period; + mult = period / ts->chip.clock_period; + if (mult != ts->mult) + ts->new_mult = mult; return 0; } diff --git a/drivers/iio/dac/ad5592r-base.c b/drivers/iio/dac/ad5592r-base.c index 076bc9ecfb49..4763402dbcd6 100644 --- a/drivers/iio/dac/ad5592r-base.c +++ b/drivers/iio/dac/ad5592r-base.c @@ -415,7 +415,7 @@ static int ad5592r_read_raw(struct iio_dev *iio_dev, s64 tmp = *val * (3767897513LL / 25LL); *val = div_s64_rem(tmp, 1000000000LL, val2); - return IIO_VAL_INT_PLUS_MICRO; + return IIO_VAL_INT_PLUS_NANO; } mutex_lock(&st->lock); diff --git a/drivers/iio/imu/bmi323/bmi323_core.c b/drivers/iio/imu/bmi323/bmi323_core.c index 5d42ab9b176a..67d74a1a1b26 100644 --- a/drivers/iio/imu/bmi323/bmi323_core.c +++ b/drivers/iio/imu/bmi323/bmi323_core.c @@ -1391,7 +1391,7 @@ static irqreturn_t bmi323_trigger_handler(int irq, void *p) &data->buffer.channels, ARRAY_SIZE(data->buffer.channels)); if (ret) - return IRQ_NONE; + goto out; } else { for_each_set_bit(bit, indio_dev->active_scan_mask, BMI323_CHAN_MAX) { @@ -1400,13 +1400,14 @@ static irqreturn_t bmi323_trigger_handler(int irq, void *p) &data->buffer.channels[index++], BMI323_BYTES_PER_SAMPLE); if (ret) - return IRQ_NONE; + goto out; } } iio_push_to_buffers_with_timestamp(indio_dev, &data->buffer, iio_get_time_ns(indio_dev)); +out: iio_trigger_notify_done(indio_dev->trig); return IRQ_HANDLED; diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c index 83d8504ebfff..4b2566693614 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c @@ -130,10 +130,6 @@ static int inv_icm42600_accel_update_scan_mode(struct iio_dev *indio_dev, /* update data FIFO write */ inv_sensors_timestamp_apply_odr(ts, 0, 0, 0); ret = inv_icm42600_buffer_set_fifo_en(st, fifo_en | st->fifo.en); - if (ret) - goto out_unlock; - - ret = inv_icm42600_buffer_update_watermark(st); out_unlock: mutex_unlock(&st->lock); diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c index 63b85ec88c13..a8cf74c84c3c 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c @@ -222,10 +222,15 @@ int inv_icm42600_buffer_update_watermark(struct inv_icm42600_state *st) latency_accel = period_accel * wm_accel; /* 0 value for watermark means that the sensor is turned off */ + if (wm_gyro == 0 && wm_accel == 0) + return 0; + if (latency_gyro == 0) { watermark = wm_accel; + st->fifo.watermark.eff_accel = wm_accel; } else if (latency_accel == 0) { watermark = wm_gyro; + st->fifo.watermark.eff_gyro = wm_gyro; } else { /* compute the smallest latency that is a multiple of both */ if (latency_gyro <= latency_accel) @@ -241,6 +246,13 @@ int inv_icm42600_buffer_update_watermark(struct inv_icm42600_state *st) watermark = latency / period; if (watermark < 1) watermark = 1; + /* update effective watermark */ + st->fifo.watermark.eff_gyro = latency / period_gyro; + if (st->fifo.watermark.eff_gyro < 1) + st->fifo.watermark.eff_gyro = 1; + st->fifo.watermark.eff_accel = latency / period_accel; + if (st->fifo.watermark.eff_accel < 1) + st->fifo.watermark.eff_accel = 1; } /* compute watermark value in bytes */ @@ -514,7 +526,7 @@ int inv_icm42600_buffer_fifo_parse(struct inv_icm42600_state *st) /* handle gyroscope timestamp and FIFO data parsing */ if (st->fifo.nb.gyro > 0) { ts = &gyro_st->ts; - inv_sensors_timestamp_interrupt(ts, st->fifo.nb.gyro, + inv_sensors_timestamp_interrupt(ts, st->fifo.watermark.eff_gyro, st->timestamp.gyro); ret = inv_icm42600_gyro_parse_fifo(st->indio_gyro); if (ret) @@ -524,7 +536,7 @@ int inv_icm42600_buffer_fifo_parse(struct inv_icm42600_state *st) /* handle accelerometer timestamp and FIFO data parsing */ if (st->fifo.nb.accel > 0) { ts = &accel_st->ts; - inv_sensors_timestamp_interrupt(ts, st->fifo.nb.accel, + inv_sensors_timestamp_interrupt(ts, st->fifo.watermark.eff_accel, st->timestamp.accel); ret = inv_icm42600_accel_parse_fifo(st->indio_accel); if (ret) @@ -577,6 +589,9 @@ int inv_icm42600_buffer_init(struct inv_icm42600_state *st) unsigned int val; int ret; + st->fifo.watermark.eff_gyro = 1; + st->fifo.watermark.eff_accel = 1; + /* * Default FIFO configuration (bits 7 to 5) * - use invalid value diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.h b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.h index 8b85ee333bf8..f6c85daf42b0 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.h +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.h @@ -32,6 +32,8 @@ struct inv_icm42600_fifo { struct { unsigned int gyro; unsigned int accel; + unsigned int eff_gyro; + unsigned int eff_accel; } watermark; size_t count; struct { diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_core.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_core.c index 96116a68ab29..62fdae530334 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_core.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_core.c @@ -537,6 +537,7 @@ static int inv_icm42600_irq_init(struct inv_icm42600_state *st, int irq, if (ret) return ret; + irq_type |= IRQF_ONESHOT; return devm_request_threaded_irq(dev, irq, inv_icm42600_irq_timestamp, inv_icm42600_irq_handler, irq_type, "inv_icm42600", st); diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c index e6f8de80128c..938af5b640b0 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c @@ -130,10 +130,6 @@ static int inv_icm42600_gyro_update_scan_mode(struct iio_dev *indio_dev, /* update data FIFO write */ inv_sensors_timestamp_apply_odr(ts, 0, 0, 0); ret = inv_icm42600_buffer_set_fifo_en(st, fifo_en | st->fifo.en); - if (ret) - goto out_unlock; - - ret = inv_icm42600_buffer_update_watermark(st); out_unlock: mutex_unlock(&st->lock); diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c index 0dc0f22a5582..3d3b27f28c9d 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c @@ -100,8 +100,8 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p) goto end_session; /* Each FIFO data contains all sensors, so same number for FIFO and sensor data */ fifo_period = NSEC_PER_SEC / INV_MPU6050_DIVIDER_TO_FIFO_RATE(st->chip_config.divider); - inv_sensors_timestamp_interrupt(&st->timestamp, nb, pf->timestamp); - inv_sensors_timestamp_apply_odr(&st->timestamp, fifo_period, nb, 0); + inv_sensors_timestamp_interrupt(&st->timestamp, 1, pf->timestamp); + inv_sensors_timestamp_apply_odr(&st->timestamp, fifo_period, 1, 0); /* clear internal data buffer for avoiding kernel data leak */ memset(data, 0, sizeof(data)); diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c index 1b603567ccc8..84273660ca2e 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c @@ -300,6 +300,7 @@ int inv_mpu6050_probe_trigger(struct iio_dev *indio_dev, int irq_type) if (!st->trig) return -ENOMEM; + irq_type |= IRQF_ONESHOT; ret = devm_request_threaded_irq(&indio_dev->dev, st->irq, &inv_mpu6050_interrupt_timestamp, &inv_mpu6050_interrupt_handle, diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c index 52d773261828..485e6fc44a04 100644 --- a/drivers/iio/inkern.c +++ b/drivers/iio/inkern.c @@ -721,7 +721,7 @@ int iio_read_channel_processed_scale(struct iio_channel *chan, int *val, return ret; *val *= scale; - return 0; + return ret; } else { ret = iio_channel_read(chan, val, NULL, IIO_CHAN_INFO_RAW); if (ret < 0) diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index 09f53d987c7d..221fa2c552ae 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -1394,12 +1394,12 @@ static int bmp580_read_temp(struct bmp280_data *data, int *val, int *val2) /* * Temperature is returned in Celsius degrees in fractional - * form down 2^16. We rescale by x1000 to return milli Celsius - * to respect IIO ABI. + * form down 2^16. We rescale by x1000 to return millidegrees + * Celsius to respect IIO ABI. */ - *val = raw_temp * 1000; - *val2 = 16; - return IIO_VAL_FRACTIONAL_LOG2; + raw_temp = sign_extend32(raw_temp, 23); + *val = ((s64)raw_temp * 1000) / (1 << 16); + return IIO_VAL_INT; } static int bmp580_read_press(struct bmp280_data *data, int *val, int *val2) diff --git a/drivers/iio/temperature/mlx90635.c b/drivers/iio/temperature/mlx90635.c index 1f5c962c1818..f7f88498ba0e 100644 --- a/drivers/iio/temperature/mlx90635.c +++ b/drivers/iio/temperature/mlx90635.c @@ -947,9 +947,9 @@ static int mlx90635_probe(struct i2c_client *client) "failed to allocate regmap\n"); regmap_ee = devm_regmap_init_i2c(client, &mlx90635_regmap_ee); - if (IS_ERR(regmap)) - return dev_err_probe(&client->dev, PTR_ERR(regmap), - "failed to allocate regmap\n"); + if (IS_ERR(regmap_ee)) + return dev_err_probe(&client->dev, PTR_ERR(regmap_ee), + "failed to allocate EEPROM regmap\n"); mlx90635 = iio_priv(indio_dev); i2c_set_clientdata(client, indio_dev); diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h index 9dca451ed522..6974922e5609 100644 --- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h +++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h @@ -107,8 +107,6 @@ struct bnxt_re_gsi_context { struct bnxt_re_sqp_entries *sqp_tbl; }; -#define BNXT_RE_MIN_MSIX 2 -#define BNXT_RE_MAX_MSIX 9 #define BNXT_RE_AEQ_IDX 0 #define BNXT_RE_NQ_IDX 1 #define BNXT_RE_GEN_P5_MAX_VF 64 @@ -168,7 +166,7 @@ struct bnxt_re_dev { struct bnxt_qplib_rcfw rcfw; /* NQ */ - struct bnxt_qplib_nq nq[BNXT_RE_MAX_MSIX]; + struct bnxt_qplib_nq nq[BNXT_MAX_ROCE_MSIX]; /* Device Resources */ struct bnxt_qplib_dev_attr dev_attr; diff --git a/drivers/infiniband/hw/mana/mr.c b/drivers/infiniband/hw/mana/mr.c index 4f13423ecdbd..887b09dd86e7 100644 --- a/drivers/infiniband/hw/mana/mr.c +++ b/drivers/infiniband/hw/mana/mr.c @@ -112,6 +112,7 @@ struct ib_mr *mana_ib_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 length, "start 0x%llx, iova 0x%llx length 0x%llx access_flags 0x%x", start, iova, length, access_flags); + access_flags &= ~IB_ACCESS_OPTIONAL; if (access_flags & ~VALID_MR_FLAGS) return ERR_PTR(-EINVAL); diff --git a/drivers/infiniband/hw/mana/qp.c b/drivers/infiniband/hw/mana/qp.c index ba13c5abf8ef..2d411a16a127 100644 --- a/drivers/infiniband/hw/mana/qp.c +++ b/drivers/infiniband/hw/mana/qp.c @@ -21,7 +21,7 @@ static int mana_ib_cfg_vport_steering(struct mana_ib_dev *dev, gc = mdev_to_gc(dev); - req_buf_size = struct_size(req, indir_tab, MANA_INDIRECT_TABLE_SIZE); + req_buf_size = struct_size(req, indir_tab, MANA_INDIRECT_TABLE_DEF_SIZE); req = kzalloc(req_buf_size, GFP_KERNEL); if (!req) return -ENOMEM; @@ -41,18 +41,18 @@ static int mana_ib_cfg_vport_steering(struct mana_ib_dev *dev, if (log_ind_tbl_size) req->rss_enable = true; - req->num_indir_entries = MANA_INDIRECT_TABLE_SIZE; + req->num_indir_entries = MANA_INDIRECT_TABLE_DEF_SIZE; req->indir_tab_offset = offsetof(struct mana_cfg_rx_steer_req_v2, indir_tab); req->update_indir_tab = true; req->cqe_coalescing_enable = 1; /* The ind table passed to the hardware must have - * MANA_INDIRECT_TABLE_SIZE entries. Adjust the verb + * MANA_INDIRECT_TABLE_DEF_SIZE entries. Adjust the verb * ind_table to MANA_INDIRECT_TABLE_SIZE if required */ ibdev_dbg(&dev->ib_dev, "ind table size %u\n", 1 << log_ind_tbl_size); - for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++) { + for (i = 0; i < MANA_INDIRECT_TABLE_DEF_SIZE; i++) { req->indir_tab[i] = ind_table[i % (1 << log_ind_tbl_size)]; ibdev_dbg(&dev->ib_dev, "index %u handle 0x%llx\n", i, req->indir_tab[i]); @@ -137,7 +137,7 @@ static int mana_ib_create_qp_rss(struct ib_qp *ibqp, struct ib_pd *pd, } ind_tbl_size = 1 << ind_tbl->log_ind_tbl_size; - if (ind_tbl_size > MANA_INDIRECT_TABLE_SIZE) { + if (ind_tbl_size > MANA_INDIRECT_TABLE_DEF_SIZE) { ibdev_dbg(&mdev->ib_dev, "Indirect table size %d exceeding limit\n", ind_tbl_size); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 2366c46eebc8..43660c831b22 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -3759,10 +3759,10 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) spin_lock_init(&dev->dm.lock); dev->dm.dev = mdev; return 0; -err: - mlx5r_macsec_dealloc_gids(dev); err_mp: mlx5_ib_cleanup_multiport_master(dev); +err: + mlx5r_macsec_dealloc_gids(dev); return err; } diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index ecc111ed5d86..d3c1f63791a2 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -246,6 +246,7 @@ static void set_cache_mkc(struct mlx5_cache_ent *ent, void *mkc) MLX5_SET(mkc, mkc, access_mode_1_0, ent->rb_key.access_mode & 0x3); MLX5_SET(mkc, mkc, access_mode_4_2, (ent->rb_key.access_mode >> 2) & 0x7); + MLX5_SET(mkc, mkc, ma_translation_mode, !!ent->rb_key.ats); MLX5_SET(mkc, mkc, translations_octword_size, get_mkc_octo_size(ent->rb_key.access_mode, @@ -641,10 +642,8 @@ static int mlx5_cache_ent_insert(struct mlx5_mkey_cache *cache, new = &((*new)->rb_left); if (cmp < 0) new = &((*new)->rb_right); - if (cmp == 0) { - mutex_unlock(&cache->rb_lock); + if (cmp == 0) return -EEXIST; - } } /* Add new node and rebalance tree. */ @@ -719,6 +718,8 @@ static struct mlx5_ib_mr *_mlx5_mr_cache_alloc(struct mlx5_ib_dev *dev, } mr->mmkey.cache_ent = ent; mr->mmkey.type = MLX5_MKEY_MR; + mr->mmkey.rb_key = ent->rb_key; + mr->mmkey.cacheable = true; init_waitqueue_head(&mr->mmkey.wait); return mr; } @@ -1169,7 +1170,6 @@ static struct mlx5_ib_mr *alloc_cacheable_mr(struct ib_pd *pd, mr->ibmr.pd = pd; mr->umem = umem; mr->page_shift = order_base_2(page_size); - mr->mmkey.cacheable = true; set_mr_fields(dev, mr, umem->length, access_flags, iova); return mr; diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c index a056ea835da5..84be0c3d5699 100644 --- a/drivers/infiniband/hw/mlx5/srq.c +++ b/drivers/infiniband/hw/mlx5/srq.c @@ -199,17 +199,20 @@ int mlx5_ib_create_srq(struct ib_srq *ib_srq, int err; struct mlx5_srq_attr in = {}; __u32 max_srq_wqes = 1 << MLX5_CAP_GEN(dev->mdev, log_max_srq_sz); + __u32 max_sge_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_rq) / + sizeof(struct mlx5_wqe_data_seg); if (init_attr->srq_type != IB_SRQT_BASIC && init_attr->srq_type != IB_SRQT_XRC && init_attr->srq_type != IB_SRQT_TM) return -EOPNOTSUPP; - /* Sanity check SRQ size before proceeding */ - if (init_attr->attr.max_wr >= max_srq_wqes) { - mlx5_ib_dbg(dev, "max_wr %d, cap %d\n", - init_attr->attr.max_wr, - max_srq_wqes); + /* Sanity check SRQ and sge size before proceeding */ + if (init_attr->attr.max_wr >= max_srq_wqes || + init_attr->attr.max_sge > max_sge_sz) { + mlx5_ib_dbg(dev, "max_wr %d,wr_cap %d,max_sge %d, sge_cap:%d\n", + init_attr->attr.max_wr, max_srq_wqes, + init_attr->attr.max_sge, max_sge_sz); return -EINVAL; } diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index c6a7fa3054fa..6596a85723c9 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -344,6 +344,19 @@ static enum resp_states rxe_resp_check_length(struct rxe_qp *qp, * receive buffer later. For rmda operations additional * length checks are performed in check_rkey. */ + if ((qp_type(qp) == IB_QPT_GSI) || (qp_type(qp) == IB_QPT_UD)) { + unsigned int payload = payload_size(pkt); + unsigned int recv_buffer_len = 0; + int i; + + for (i = 0; i < qp->resp.wqe->dma.num_sge; i++) + recv_buffer_len += qp->resp.wqe->dma.sge[i].length; + if (payload + 40 > recv_buffer_len) { + rxe_dbg_qp(qp, "The receive buffer is too small for this UD packet.\n"); + return RESPST_ERR_LENGTH; + } + } + if (pkt->mask & RXE_PAYLOAD_MASK && ((qp_type(qp) == IB_QPT_RC) || (qp_type(qp) == IB_QPT_UC))) { unsigned int mtu = qp->mtu; diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index c7d4d8ab5a09..de6238ee4379 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -812,7 +812,7 @@ static void copy_inline_data_to_wqe(struct rxe_send_wqe *wqe, int i; for (i = 0; i < ibwr->num_sge; i++, sge++) { - memcpy(p, ib_virt_dma_to_page(sge->addr), sge->length); + memcpy(p, ib_virt_dma_to_ptr(sge->addr), sge->length); p += sge->length; } } diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 70f0654c58b6..2b8370ecf42a 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -209,6 +209,7 @@ static const struct xpad_device { { 0x0738, 0xf738, "Super SFIV FightStick TE S", 0, XTYPE_XBOX360 }, { 0x07ff, 0xffff, "Mad Catz GamePad", 0, XTYPE_XBOX360 }, { 0x0b05, 0x1a38, "ASUS ROG RAIKIRI", 0, XTYPE_XBOXONE }, + { 0x0b05, 0x1abb, "ASUS ROG RAIKIRI PRO", 0, XTYPE_XBOXONE }, { 0x0c12, 0x0005, "Intec wireless", 0, XTYPE_XBOX }, { 0x0c12, 0x8801, "Nyko Xbox Controller", 0, XTYPE_XBOX }, { 0x0c12, 0x8802, "Zeroplus Xbox Controller", 0, XTYPE_XBOX }, diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index 4e38229404b4..b4723ea395eb 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -1477,15 +1477,46 @@ static void elantech_disconnect(struct psmouse *psmouse) } /* + * Some hw_version 4 models fail to properly activate absolute mode on + * resume without going through disable/enable cycle. + */ +static const struct dmi_system_id elantech_needs_reenable[] = { +#if defined(CONFIG_DMI) && defined(CONFIG_X86) + { + /* Lenovo N24 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "81AF"), + }, + }, +#endif + { } +}; + +/* * Put the touchpad back into absolute mode when reconnecting */ static int elantech_reconnect(struct psmouse *psmouse) { + int err; + psmouse_reset(psmouse); if (elantech_detect(psmouse, 0)) return -1; + if (dmi_check_system(elantech_needs_reenable)) { + err = ps2_command(&psmouse->ps2dev, NULL, PSMOUSE_CMD_DISABLE); + if (err) + psmouse_warn(psmouse, "failed to deactivate mouse on %s: %d\n", + psmouse->ps2dev.serio->phys, err); + + err = ps2_command(&psmouse->ps2dev, NULL, PSMOUSE_CMD_ENABLE); + if (err) + psmouse_warn(psmouse, "failed to reactivate mouse on %s: %d\n", + psmouse->ps2dev.serio->phys, err); + } + if (elantech_set_absolute_mode(psmouse)) { psmouse_err(psmouse, "failed to put touchpad back into absolute mode.\n"); diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h index dfc6c581873b..5b50475ec414 100644 --- a/drivers/input/serio/i8042-acpipnpio.h +++ b/drivers/input/serio/i8042-acpipnpio.h @@ -76,7 +76,7 @@ static inline void i8042_write_command(int val) #define SERIO_QUIRK_PROBE_DEFER BIT(5) #define SERIO_QUIRK_RESET_ALWAYS BIT(6) #define SERIO_QUIRK_RESET_NEVER BIT(7) -#define SERIO_QUIRK_DIECT BIT(8) +#define SERIO_QUIRK_DIRECT BIT(8) #define SERIO_QUIRK_DUMBKBD BIT(9) #define SERIO_QUIRK_NOLOOP BIT(10) #define SERIO_QUIRK_NOTIMEOUT BIT(11) @@ -1332,6 +1332,20 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, + { + /* + * The Ayaneo Kun is a handheld device where some the buttons + * are handled by an AT keyboard. The keyboard is usually + * detected as raw, but sometimes, usually after a cold boot, + * it is detected as translated. Make sure that the keyboard + * is always in raw mode. + */ + .matches = { + DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AYANEO"), + DMI_MATCH(DMI_BOARD_NAME, "KUN"), + }, + .driver_data = (void *)(SERIO_QUIRK_DIRECT) + }, { } }; @@ -1655,7 +1669,7 @@ static void __init i8042_check_quirks(void) if (quirks & SERIO_QUIRK_RESET_NEVER) i8042_reset = I8042_RESET_NEVER; } - if (quirks & SERIO_QUIRK_DIECT) + if (quirks & SERIO_QUIRK_DIRECT) i8042_direct = true; if (quirks & SERIO_QUIRK_DUMBKBD) i8042_dumbkbd = true; diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c index d2bbb436a77d..4d13db13b9e5 100644 --- a/drivers/input/touchscreen/ads7846.c +++ b/drivers/input/touchscreen/ads7846.c @@ -1111,6 +1111,16 @@ static const struct of_device_id ads7846_dt_ids[] = { }; MODULE_DEVICE_TABLE(of, ads7846_dt_ids); +static const struct spi_device_id ads7846_spi_ids[] = { + { "tsc2046", 7846 }, + { "ads7843", 7843 }, + { "ads7845", 7845 }, + { "ads7846", 7846 }, + { "ads7873", 7873 }, + { }, +}; +MODULE_DEVICE_TABLE(spi, ads7846_spi_ids); + static const struct ads7846_platform_data *ads7846_get_props(struct device *dev) { struct ads7846_platform_data *pdata; @@ -1386,10 +1396,10 @@ static struct spi_driver ads7846_driver = { }, .probe = ads7846_probe, .remove = ads7846_remove, + .id_table = ads7846_spi_ids, }; module_spi_driver(ads7846_driver); MODULE_DESCRIPTION("ADS7846 TouchScreen Driver"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("spi:ads7846"); diff --git a/drivers/input/touchscreen/ili210x.c b/drivers/input/touchscreen/ili210x.c index 31ffdc2a93f3..79bdb2b10949 100644 --- a/drivers/input/touchscreen/ili210x.c +++ b/drivers/input/touchscreen/ili210x.c @@ -261,8 +261,8 @@ static int ili251x_read_touch_data(struct i2c_client *client, u8 *data) if (!error && data[0] == 2) { error = i2c_master_recv(client, data + ILI251X_DATA_SIZE1, ILI251X_DATA_SIZE2); - if (error >= 0 && error != ILI251X_DATA_SIZE2) - error = -EIO; + if (error >= 0) + error = error == ILI251X_DATA_SIZE2 ? 0 : -EIO; } return error; diff --git a/drivers/input/touchscreen/silead.c b/drivers/input/touchscreen/silead.c index bbd366dcb69a..6a42b27c4599 100644 --- a/drivers/input/touchscreen/silead.c +++ b/drivers/input/touchscreen/silead.c @@ -71,7 +71,6 @@ struct silead_ts_data { struct regulator_bulk_data regulators[2]; char fw_name[64]; struct touchscreen_properties prop; - u32 max_fingers; u32 chip_id; struct input_mt_pos pos[SILEAD_MAX_FINGERS]; int slots[SILEAD_MAX_FINGERS]; @@ -136,7 +135,7 @@ static int silead_ts_request_input_dev(struct silead_ts_data *data) touchscreen_parse_properties(data->input, true, &data->prop); silead_apply_efi_fw_min_max(data); - input_mt_init_slots(data->input, data->max_fingers, + input_mt_init_slots(data->input, SILEAD_MAX_FINGERS, INPUT_MT_DIRECT | INPUT_MT_DROP_UNUSED | INPUT_MT_TRACK); @@ -256,10 +255,10 @@ static void silead_ts_read_data(struct i2c_client *client) return; } - if (buf[0] > data->max_fingers) { + if (buf[0] > SILEAD_MAX_FINGERS) { dev_warn(dev, "More touches reported then supported %d > %d\n", - buf[0], data->max_fingers); - buf[0] = data->max_fingers; + buf[0], SILEAD_MAX_FINGERS); + buf[0] = SILEAD_MAX_FINGERS; } if (silead_ts_handle_pen_data(data, buf)) @@ -315,7 +314,6 @@ sync: static int silead_ts_init(struct i2c_client *client) { - struct silead_ts_data *data = i2c_get_clientdata(client); int error; error = i2c_smbus_write_byte_data(client, SILEAD_REG_RESET, @@ -325,7 +323,7 @@ static int silead_ts_init(struct i2c_client *client) usleep_range(SILEAD_CMD_SLEEP_MIN, SILEAD_CMD_SLEEP_MAX); error = i2c_smbus_write_byte_data(client, SILEAD_REG_TOUCH_NR, - data->max_fingers); + SILEAD_MAX_FINGERS); if (error) goto i2c_write_err; usleep_range(SILEAD_CMD_SLEEP_MIN, SILEAD_CMD_SLEEP_MAX); @@ -591,13 +589,6 @@ static void silead_ts_read_props(struct i2c_client *client) const char *str; int error; - error = device_property_read_u32(dev, "silead,max-fingers", - &data->max_fingers); - if (error) { - dev_dbg(dev, "Max fingers read error %d\n", error); - data->max_fingers = 5; /* Most devices handle up-to 5 fingers */ - } - error = device_property_read_string(dev, "firmware-name", &str); if (!error) snprintf(data->fw_name, sizeof(data->fw_name), diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index 2fde1302a584..2d5945c982bd 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -129,7 +129,8 @@ static inline int check_feature_gpt_level(void) static inline bool amd_iommu_gt_ppr_supported(void) { return (check_feature(FEATURE_GT) && - check_feature(FEATURE_PPR)); + check_feature(FEATURE_PPR) && + check_feature(FEATURE_EPHSUP)); } static inline u64 iommu_virt_to_phys(void *vaddr) diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index a18e74878f68..161248067776 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -1626,8 +1626,17 @@ static void __init free_pci_segments(void) } } +static void __init free_sysfs(struct amd_iommu *iommu) +{ + if (iommu->iommu.dev) { + iommu_device_unregister(&iommu->iommu); + iommu_device_sysfs_remove(&iommu->iommu); + } +} + static void __init free_iommu_one(struct amd_iommu *iommu) { + free_sysfs(iommu); free_cwwb_sem(iommu); free_command_buffer(iommu); free_event_buffer(iommu); @@ -3353,7 +3362,7 @@ int amd_iommu_reenable(int mode) return 0; } -int __init amd_iommu_enable_faulting(unsigned int cpu) +int amd_iommu_enable_faulting(unsigned int cpu) { /* We enable MSI later when PCI is initialized */ return 0; diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 52d83730a22a..c2703599bb16 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -2032,7 +2032,6 @@ static int do_attach(struct iommu_dev_data *dev_data, struct protection_domain *domain) { struct amd_iommu *iommu = get_amd_iommu_from_dev_data(dev_data); - struct pci_dev *pdev; int ret = 0; /* Update data structures */ @@ -2047,30 +2046,13 @@ static int do_attach(struct iommu_dev_data *dev_data, domain->dev_iommu[iommu->index] += 1; domain->dev_cnt += 1; - pdev = dev_is_pci(dev_data->dev) ? to_pci_dev(dev_data->dev) : NULL; + /* Setup GCR3 table */ if (pdom_is_sva_capable(domain)) { ret = init_gcr3_table(dev_data, domain); if (ret) return ret; - - if (pdev) { - pdev_enable_caps(pdev); - - /* - * Device can continue to function even if IOPF - * enablement failed. Hence in error path just - * disable device PRI support. - */ - if (amd_iommu_iopf_add_device(iommu, dev_data)) - pdev_disable_cap_pri(pdev); - } - } else if (pdev) { - pdev_enable_cap_ats(pdev); } - /* Update device table */ - amd_iommu_dev_update_dte(dev_data, true); - return ret; } @@ -2163,6 +2145,11 @@ static void detach_device(struct device *dev) do_detach(dev_data); +out: + spin_unlock(&dev_data->lock); + + spin_unlock_irqrestore(&domain->lock, flags); + /* Remove IOPF handler */ if (ppr) amd_iommu_iopf_remove_device(iommu, dev_data); @@ -2170,10 +2157,6 @@ static void detach_device(struct device *dev) if (dev_is_pci(dev)) pdev_disable_caps(to_pci_dev(dev)); -out: - spin_unlock(&dev_data->lock); - - spin_unlock_irqrestore(&domain->lock, flags); } static struct iommu_device *amd_iommu_probe_device(struct device *dev) @@ -2485,6 +2468,7 @@ static int amd_iommu_attach_device(struct iommu_domain *dom, struct iommu_dev_data *dev_data = dev_iommu_priv_get(dev); struct protection_domain *domain = to_pdomain(dom); struct amd_iommu *iommu = get_amd_iommu_from_dev(dev); + struct pci_dev *pdev; int ret; /* @@ -2517,7 +2501,23 @@ static int amd_iommu_attach_device(struct iommu_domain *dom, } #endif - iommu_completion_wait(iommu); + pdev = dev_is_pci(dev_data->dev) ? to_pci_dev(dev_data->dev) : NULL; + if (pdev && pdom_is_sva_capable(domain)) { + pdev_enable_caps(pdev); + + /* + * Device can continue to function even if IOPF + * enablement failed. Hence in error path just + * disable device PRI support. + */ + if (amd_iommu_iopf_add_device(iommu, dev_data)) + pdev_disable_cap_pri(pdev); + } else if (pdev) { + pdev_enable_cap_ats(pdev); + } + + /* Update device table */ + amd_iommu_dev_update_dte(dev_data, true); return ret; } diff --git a/drivers/iommu/amd/ppr.c b/drivers/iommu/amd/ppr.c index 091423bb8aac..7c67d69f0b8c 100644 --- a/drivers/iommu/amd/ppr.c +++ b/drivers/iommu/amd/ppr.c @@ -222,8 +222,7 @@ int amd_iommu_iopf_init(struct amd_iommu *iommu) if (iommu->iopf_queue) return ret; - snprintf(iommu->iopfq_name, sizeof(iommu->iopfq_name), - "amdiommu-%#x-iopfq", + snprintf(iommu->iopfq_name, sizeof(iommu->iopfq_name), "amdvi-%#x", PCI_SEG_DEVID_TO_SBDF(iommu->pci_seg->id, iommu->devid)); iommu->iopf_queue = iopf_queue_alloc(iommu->iopfq_name); @@ -249,40 +248,26 @@ void amd_iommu_page_response(struct device *dev, struct iopf_fault *evt, int amd_iommu_iopf_add_device(struct amd_iommu *iommu, struct iommu_dev_data *dev_data) { - unsigned long flags; int ret = 0; if (!dev_data->pri_enabled) return ret; - raw_spin_lock_irqsave(&iommu->lock, flags); - - if (!iommu->iopf_queue) { - ret = -EINVAL; - goto out_unlock; - } + if (!iommu->iopf_queue) + return -EINVAL; ret = iopf_queue_add_device(iommu->iopf_queue, dev_data->dev); if (ret) - goto out_unlock; + return ret; dev_data->ppr = true; - -out_unlock: - raw_spin_unlock_irqrestore(&iommu->lock, flags); - return ret; + return 0; } /* Its assumed that caller has verified that device was added to iopf queue */ void amd_iommu_iopf_remove_device(struct amd_iommu *iommu, struct iommu_dev_data *dev_data) { - unsigned long flags; - - raw_spin_lock_irqsave(&iommu->lock, flags); - iopf_queue_remove_device(iommu->iopf_queue, dev_data->dev); dev_data->ppr = false; - - raw_spin_unlock_irqrestore(&iommu->lock, flags); } diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index f731e4b2a417..43520e7275cc 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -686,15 +686,15 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, struct device *dev /* Check the domain allows at least some access to the device... */ if (map) { - dma_addr_t base = dma_range_map_min(map); - if (base > domain->geometry.aperture_end || + if (dma_range_map_min(map) > domain->geometry.aperture_end || dma_range_map_max(map) < domain->geometry.aperture_start) { pr_warn("specified DMA range outside IOMMU capability\n"); return -EFAULT; } - /* ...then finally give it a kicking to make sure it fits */ - base_pfn = max(base, domain->geometry.aperture_start) >> order; } + /* ...then finally give it a kicking to make sure it fits */ + base_pfn = max_t(unsigned long, base_pfn, + domain->geometry.aperture_start >> order); /* start_pfn is always nonzero for an already-initialised domain */ mutex_lock(&cookie->mutex); diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 40ebf1726393..3c755d5dad6e 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1846,28 +1846,22 @@ static int its_vlpi_map(struct irq_data *d, struct its_cmd_info *info) { struct its_device *its_dev = irq_data_get_irq_chip_data(d); u32 event = its_get_event_id(d); - int ret = 0; if (!info->map) return -EINVAL; - raw_spin_lock(&its_dev->event_map.vlpi_lock); - if (!its_dev->event_map.vm) { struct its_vlpi_map *maps; maps = kcalloc(its_dev->event_map.nr_lpis, sizeof(*maps), GFP_ATOMIC); - if (!maps) { - ret = -ENOMEM; - goto out; - } + if (!maps) + return -ENOMEM; its_dev->event_map.vm = info->map->vm; its_dev->event_map.vlpi_maps = maps; } else if (its_dev->event_map.vm != info->map->vm) { - ret = -EINVAL; - goto out; + return -EINVAL; } /* Get our private copy of the mapping information */ @@ -1899,46 +1893,32 @@ static int its_vlpi_map(struct irq_data *d, struct its_cmd_info *info) its_dev->event_map.nr_vlpis++; } -out: - raw_spin_unlock(&its_dev->event_map.vlpi_lock); - return ret; + return 0; } static int its_vlpi_get(struct irq_data *d, struct its_cmd_info *info) { struct its_device *its_dev = irq_data_get_irq_chip_data(d); struct its_vlpi_map *map; - int ret = 0; - - raw_spin_lock(&its_dev->event_map.vlpi_lock); map = get_vlpi_map(d); - if (!its_dev->event_map.vm || !map) { - ret = -EINVAL; - goto out; - } + if (!its_dev->event_map.vm || !map) + return -EINVAL; /* Copy our mapping information to the incoming request */ *info->map = *map; -out: - raw_spin_unlock(&its_dev->event_map.vlpi_lock); - return ret; + return 0; } static int its_vlpi_unmap(struct irq_data *d) { struct its_device *its_dev = irq_data_get_irq_chip_data(d); u32 event = its_get_event_id(d); - int ret = 0; - - raw_spin_lock(&its_dev->event_map.vlpi_lock); - if (!its_dev->event_map.vm || !irqd_is_forwarded_to_vcpu(d)) { - ret = -EINVAL; - goto out; - } + if (!its_dev->event_map.vm || !irqd_is_forwarded_to_vcpu(d)) + return -EINVAL; /* Drop the virtual mapping */ its_send_discard(its_dev, event); @@ -1962,9 +1942,7 @@ static int its_vlpi_unmap(struct irq_data *d) kfree(its_dev->event_map.vlpi_maps); } -out: - raw_spin_unlock(&its_dev->event_map.vlpi_lock); - return ret; + return 0; } static int its_vlpi_prop_update(struct irq_data *d, struct its_cmd_info *info) @@ -1992,6 +1970,8 @@ static int its_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu_info) if (!is_v4(its_dev->its)) return -EINVAL; + guard(raw_spinlock_irq)(&its_dev->event_map.vlpi_lock); + /* Unmap request? */ if (!info) return its_vlpi_unmap(d); diff --git a/drivers/irqchip/irq-riscv-intc.c b/drivers/irqchip/irq-riscv-intc.c index 9e71c4428814..4f3a12383a1e 100644 --- a/drivers/irqchip/irq-riscv-intc.c +++ b/drivers/irqchip/irq-riscv-intc.c @@ -253,8 +253,9 @@ IRQCHIP_DECLARE(andes, "andestech,cpu-intc", riscv_intc_init); static int __init riscv_intc_acpi_init(union acpi_subtable_headers *header, const unsigned long end) { - struct fwnode_handle *fn; struct acpi_madt_rintc *rintc; + struct fwnode_handle *fn; + int rc; rintc = (struct acpi_madt_rintc *)header; @@ -273,7 +274,11 @@ static int __init riscv_intc_acpi_init(union acpi_subtable_headers *header, return -ENOMEM; } - return riscv_intc_init_common(fn, &riscv_intc_chip); + rc = riscv_intc_init_common(fn, &riscv_intc_chip); + if (rc) + irq_domain_free_fwnode(fn); + + return rc; } IRQCHIP_ACPI_DECLARE(riscv_intc, ACPI_MADT_TYPE_RINTC, NULL, diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c index 8fb183ced1e7..9e22f7e378f5 100644 --- a/drivers/irqchip/irq-sifive-plic.c +++ b/drivers/irqchip/irq-sifive-plic.c @@ -85,7 +85,7 @@ struct plic_handler { struct plic_priv *priv; }; static int plic_parent_irq __ro_after_init; -static bool plic_cpuhp_setup_done __ro_after_init; +static bool plic_global_setup_done __ro_after_init; static DEFINE_PER_CPU(struct plic_handler, plic_handlers); static int plic_irq_set_type(struct irq_data *d, unsigned int type); @@ -487,10 +487,8 @@ static int plic_probe(struct platform_device *pdev) unsigned long plic_quirks = 0; struct plic_handler *handler; u32 nr_irqs, parent_hwirq; - struct irq_domain *domain; struct plic_priv *priv; irq_hw_number_t hwirq; - bool cpuhp_setup; if (is_of_node(dev->fwnode)) { const struct of_device_id *id; @@ -549,14 +547,6 @@ static int plic_probe(struct platform_device *pdev) continue; } - /* Find parent domain and register chained handler */ - domain = irq_find_matching_fwnode(riscv_get_intc_hwnode(), DOMAIN_BUS_ANY); - if (!plic_parent_irq && domain) { - plic_parent_irq = irq_create_mapping(domain, RV_IRQ_EXT); - if (plic_parent_irq) - irq_set_chained_handler(plic_parent_irq, plic_handle_irq); - } - /* * When running in M-mode we need to ignore the S-mode handler. * Here we assume it always comes later, but that might be a @@ -597,25 +587,35 @@ done: goto fail_cleanup_contexts; /* - * We can have multiple PLIC instances so setup cpuhp state + * We can have multiple PLIC instances so setup global state * and register syscore operations only once after context * handlers of all online CPUs are initialized. */ - if (!plic_cpuhp_setup_done) { - cpuhp_setup = true; + if (!plic_global_setup_done) { + struct irq_domain *domain; + bool global_setup = true; + for_each_online_cpu(cpu) { handler = per_cpu_ptr(&plic_handlers, cpu); if (!handler->present) { - cpuhp_setup = false; + global_setup = false; break; } } - if (cpuhp_setup) { + + if (global_setup) { + /* Find parent domain and register chained handler */ + domain = irq_find_matching_fwnode(riscv_get_intc_hwnode(), DOMAIN_BUS_ANY); + if (domain) + plic_parent_irq = irq_create_mapping(domain, RV_IRQ_EXT); + if (plic_parent_irq) + irq_set_chained_handler(plic_parent_irq, plic_handle_irq); + cpuhp_setup_state(CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING, "irqchip/sifive/plic:starting", plic_starting_cpu, plic_dying_cpu); register_syscore_ops(&plic_irq_syscore_ops); - plic_cpuhp_setup_done = true; + plic_global_setup_done = true; } } diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c index 24fcff682b24..ba1be15cfd8e 100644 --- a/drivers/leds/led-class.c +++ b/drivers/leds/led-class.c @@ -552,12 +552,6 @@ int led_classdev_register_ext(struct device *parent, led_init_core(led_cdev); #ifdef CONFIG_LEDS_TRIGGERS - /* - * If no default trigger was given and hw_control_trigger is set, - * make it the default trigger. - */ - if (!led_cdev->default_trigger && led_cdev->hw_control_trigger) - led_cdev->default_trigger = led_cdev->hw_control_trigger; led_trigger_set_default(led_cdev); #endif diff --git a/drivers/media/pci/intel/ipu6/ipu6-isys-queue.c b/drivers/media/pci/intel/ipu6/ipu6-isys-queue.c index 40a8ebfcfce2..4bd4e324abc9 100644 --- a/drivers/media/pci/intel/ipu6/ipu6-isys-queue.c +++ b/drivers/media/pci/intel/ipu6/ipu6-isys-queue.c @@ -301,10 +301,10 @@ static int ipu6_isys_stream_start(struct ipu6_isys_video *av, out_requeue: if (bl && bl->nbufs) ipu6_isys_buffer_list_queue(bl, - (IPU6_ISYS_BUFFER_LIST_FL_INCOMING | - error) ? + IPU6_ISYS_BUFFER_LIST_FL_INCOMING | + (error ? IPU6_ISYS_BUFFER_LIST_FL_SET_STATE : - 0, error ? VB2_BUF_STATE_ERROR : + 0), error ? VB2_BUF_STATE_ERROR : VB2_BUF_STATE_QUEUED); flush_firmware_streamon_fail(stream); diff --git a/drivers/media/pci/intel/ipu6/ipu6-isys.c b/drivers/media/pci/intel/ipu6/ipu6-isys.c index 5992138c7290..8b9b77719bb1 100644 --- a/drivers/media/pci/intel/ipu6/ipu6-isys.c +++ b/drivers/media/pci/intel/ipu6/ipu6-isys.c @@ -678,6 +678,12 @@ static int isys_notifier_bound(struct v4l2_async_notifier *notifier, container_of(asc, struct sensor_async_sd, asc); int ret; + if (s_asd->csi2.port >= isys->pdata->ipdata->csi2.nports) { + dev_err(&isys->adev->auxdev.dev, "invalid csi2 port %u\n", + s_asd->csi2.port); + return -EINVAL; + } + ret = ipu_bridge_instantiate_vcm(sd->dev); if (ret) { dev_err(&isys->adev->auxdev.dev, "instantiate vcm failed\n"); @@ -925,39 +931,18 @@ static const struct dev_pm_ops isys_pm_ops = { .resume = isys_resume, }; -static void isys_remove(struct auxiliary_device *auxdev) +static void free_fw_msg_bufs(struct ipu6_isys *isys) { - struct ipu6_bus_device *adev = auxdev_to_adev(auxdev); - struct ipu6_isys *isys = dev_get_drvdata(&auxdev->dev); - struct ipu6_device *isp = adev->isp; + struct device *dev = &isys->adev->auxdev.dev; struct isys_fw_msgs *fwmsg, *safe; - unsigned int i; list_for_each_entry_safe(fwmsg, safe, &isys->framebuflist, head) - dma_free_attrs(&auxdev->dev, sizeof(struct isys_fw_msgs), - fwmsg, fwmsg->dma_addr, 0); + dma_free_attrs(dev, sizeof(struct isys_fw_msgs), fwmsg, + fwmsg->dma_addr, 0); list_for_each_entry_safe(fwmsg, safe, &isys->framebuflist_fw, head) - dma_free_attrs(&auxdev->dev, sizeof(struct isys_fw_msgs), - fwmsg, fwmsg->dma_addr, 0); - - isys_unregister_devices(isys); - isys_notifier_cleanup(isys); - - cpu_latency_qos_remove_request(&isys->pm_qos); - - if (!isp->secure_mode) { - ipu6_cpd_free_pkg_dir(adev); - ipu6_buttress_unmap_fw_image(adev, &adev->fw_sgt); - release_firmware(adev->fw); - } - - for (i = 0; i < IPU6_ISYS_MAX_STREAMS; i++) - mutex_destroy(&isys->streams[i].mutex); - - isys_iwake_watermark_cleanup(isys); - mutex_destroy(&isys->stream_mutex); - mutex_destroy(&isys->mutex); + dma_free_attrs(dev, sizeof(struct isys_fw_msgs), fwmsg, + fwmsg->dma_addr, 0); } static int alloc_fw_msg_bufs(struct ipu6_isys *isys, int amount) @@ -1140,12 +1125,14 @@ static int isys_probe(struct auxiliary_device *auxdev, ret = isys_register_devices(isys); if (ret) - goto out_remove_pkg_dir_shared_buffer; + goto free_fw_msg_bufs; ipu6_mmu_hw_cleanup(adev->mmu); return 0; +free_fw_msg_bufs: + free_fw_msg_bufs(isys); out_remove_pkg_dir_shared_buffer: if (!isp->secure_mode) ipu6_cpd_free_pkg_dir(adev); @@ -1167,6 +1154,34 @@ release_firmware: return ret; } +static void isys_remove(struct auxiliary_device *auxdev) +{ + struct ipu6_bus_device *adev = auxdev_to_adev(auxdev); + struct ipu6_isys *isys = dev_get_drvdata(&auxdev->dev); + struct ipu6_device *isp = adev->isp; + unsigned int i; + + free_fw_msg_bufs(isys); + + isys_unregister_devices(isys); + isys_notifier_cleanup(isys); + + cpu_latency_qos_remove_request(&isys->pm_qos); + + if (!isp->secure_mode) { + ipu6_cpd_free_pkg_dir(adev); + ipu6_buttress_unmap_fw_image(adev, &adev->fw_sgt); + release_firmware(adev->fw); + } + + for (i = 0; i < IPU6_ISYS_MAX_STREAMS; i++) + mutex_destroy(&isys->streams[i].mutex); + + isys_iwake_watermark_cleanup(isys); + mutex_destroy(&isys->stream_mutex); + mutex_destroy(&isys->mutex); +} + struct fwmsg { int type; char *msg; diff --git a/drivers/media/pci/intel/ipu6/ipu6.c b/drivers/media/pci/intel/ipu6/ipu6.c index d2bebd208461..bbd646378ab3 100644 --- a/drivers/media/pci/intel/ipu6/ipu6.c +++ b/drivers/media/pci/intel/ipu6/ipu6.c @@ -285,7 +285,7 @@ EXPORT_SYMBOL_NS_GPL(ipu6_configure_spc, INTEL_IPU6); #define IPU6_ISYS_CSI2_NPORTS 4 #define IPU6SE_ISYS_CSI2_NPORTS 4 #define IPU6_TGL_ISYS_CSI2_NPORTS 8 -#define IPU6EP_MTL_ISYS_CSI2_NPORTS 4 +#define IPU6EP_MTL_ISYS_CSI2_NPORTS 6 static void ipu6_internal_pdata_init(struct ipu6_device *isp) { @@ -727,9 +727,6 @@ static void ipu6_pci_remove(struct pci_dev *pdev) pm_runtime_forbid(&pdev->dev); pm_runtime_get_noresume(&pdev->dev); - pci_release_regions(pdev); - pci_disable_device(pdev); - release_firmware(isp->cpd_fw); ipu6_mmu_cleanup(psys_mmu); diff --git a/drivers/media/pci/intel/ivsc/mei_csi.c b/drivers/media/pci/intel/ivsc/mei_csi.c index 89b582a221ab..f04a89584334 100644 --- a/drivers/media/pci/intel/ivsc/mei_csi.c +++ b/drivers/media/pci/intel/ivsc/mei_csi.c @@ -677,10 +677,13 @@ static int mei_csi_probe(struct mei_cl_device *cldev, return -ENODEV; ret = ipu_bridge_init(&ipu->dev, ipu_bridge_parse_ssdb); + put_device(&ipu->dev); if (ret < 0) return ret; - if (WARN_ON(!dev_fwnode(dev))) + if (!dev_fwnode(dev)) { + dev_err(dev, "mei-csi probed without device fwnode!\n"); return -ENXIO; + } csi = devm_kzalloc(dev, sizeof(struct mei_csi), GFP_KERNEL); if (!csi) diff --git a/drivers/media/pci/mgb4/mgb4_core.c b/drivers/media/pci/mgb4/mgb4_core.c index 60498a5abebf..ab4f07e2e560 100644 --- a/drivers/media/pci/mgb4/mgb4_core.c +++ b/drivers/media/pci/mgb4/mgb4_core.c @@ -642,9 +642,6 @@ static void mgb4_remove(struct pci_dev *pdev) struct mgb4_dev *mgbdev = pci_get_drvdata(pdev); int i; -#ifdef CONFIG_DEBUG_FS - debugfs_remove_recursive(mgbdev->debugfs); -#endif #if IS_REACHABLE(CONFIG_HWMON) hwmon_device_unregister(mgbdev->hwmon_dev); #endif @@ -659,6 +656,10 @@ static void mgb4_remove(struct pci_dev *pdev) if (mgbdev->vin[i]) mgb4_vin_free(mgbdev->vin[i]); +#ifdef CONFIG_DEBUG_FS + debugfs_remove_recursive(mgbdev->debugfs); +#endif + device_remove_groups(&mgbdev->pdev->dev, mgb4_pci_groups); free_spi(mgbdev); free_i2c(mgbdev); diff --git a/drivers/media/pci/saa7134/saa7134-cards.c b/drivers/media/pci/saa7134/saa7134-cards.c index 1280696f65f2..e80fb4ebfda6 100644 --- a/drivers/media/pci/saa7134/saa7134-cards.c +++ b/drivers/media/pci/saa7134/saa7134-cards.c @@ -5152,7 +5152,7 @@ struct saa7134_board saa7134_boards[] = { }, }, [SAA7134_BOARD_AVERMEDIA_STUDIO_507UA] = { - /* Andy Shevchenko <[email protected]> */ + /* Andy Shevchenko <[email protected]> */ .name = "Avermedia AVerTV Studio 507UA", .audio_clock = 0x00187de7, .tuner_type = TUNER_PHILIPS_FM1216ME_MK3, /* Should be MK5 */ diff --git a/drivers/mfd/axp20x.c b/drivers/mfd/axp20x.c index f2c0f144c0fc..dacd3c96c9f5 100644 --- a/drivers/mfd/axp20x.c +++ b/drivers/mfd/axp20x.c @@ -210,6 +210,7 @@ static const struct regmap_access_table axp313a_volatile_table = { static const struct regmap_range axp717_writeable_ranges[] = { regmap_reg_range(AXP717_IRQ0_EN, AXP717_IRQ4_EN), + regmap_reg_range(AXP717_IRQ0_STATE, AXP717_IRQ4_STATE), regmap_reg_range(AXP717_DCDC_OUTPUT_CONTROL, AXP717_CPUSLDO_CONTROL), }; diff --git a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gp.c b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gp.c index 32af2b14ff34..34c9be437432 100644 --- a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gp.c +++ b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gp.c @@ -69,8 +69,10 @@ static int gp_aux_bus_probe(struct pci_dev *pdev, const struct pci_device_id *id aux_bus->aux_device_wrapper[1] = kzalloc(sizeof(*aux_bus->aux_device_wrapper[1]), GFP_KERNEL); - if (!aux_bus->aux_device_wrapper[1]) - return -ENOMEM; + if (!aux_bus->aux_device_wrapper[1]) { + retval = -ENOMEM; + goto err_aux_dev_add_0; + } retval = ida_alloc(&gp_client_ida, GFP_KERNEL); if (retval < 0) @@ -111,6 +113,7 @@ static int gp_aux_bus_probe(struct pci_dev *pdev, const struct pci_device_id *id err_aux_dev_add_1: auxiliary_device_uninit(&aux_bus->aux_device_wrapper[1]->aux_dev); + goto err_aux_dev_add_0; err_aux_dev_init_1: ida_free(&gp_client_ida, aux_bus->aux_device_wrapper[1]->aux_dev.id); @@ -120,6 +123,7 @@ err_ida_alloc_1: err_aux_dev_add_0: auxiliary_device_uninit(&aux_bus->aux_device_wrapper[0]->aux_dev); + goto err_ret; err_aux_dev_init_0: ida_free(&gp_client_ida, aux_bus->aux_device_wrapper[0]->aux_dev.id); @@ -127,6 +131,7 @@ err_aux_dev_init_0: err_ida_alloc_0: kfree(aux_bus->aux_device_wrapper[0]); +err_ret: return retval; } diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index 79e6f3c1341f..40c3fe26f76d 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -329,7 +329,7 @@ static ssize_t mei_write(struct file *file, const char __user *ubuf, } if (!mei_cl_is_connected(cl)) { - cl_err(dev, cl, "is not connected"); + cl_dbg(dev, cl, "is not connected"); rets = -ENODEV; goto out; } diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 7f59dd38c32f..6589635f8ba3 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -385,8 +385,10 @@ static int mei_me_pci_resume(struct device *device) } err = mei_restart(dev); - if (err) + if (err) { + free_irq(pdev->irq, dev); return err; + } /* Start timer if stopped in suspend */ schedule_delayed_work(&dev->timer_work, HZ); diff --git a/drivers/misc/mei/platform-vsc.c b/drivers/misc/mei/platform-vsc.c index b543e6b9f3cf..1ec65d87488a 100644 --- a/drivers/misc/mei/platform-vsc.c +++ b/drivers/misc/mei/platform-vsc.c @@ -399,41 +399,32 @@ static void mei_vsc_remove(struct platform_device *pdev) static int mei_vsc_suspend(struct device *dev) { - struct mei_device *mei_dev = dev_get_drvdata(dev); - struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev); + struct mei_device *mei_dev; + int ret = 0; - mei_stop(mei_dev); + mei_dev = dev_get_drvdata(dev); + if (!mei_dev) + return -ENODEV; - mei_disable_interrupts(mei_dev); + mutex_lock(&mei_dev->device_lock); - vsc_tp_free_irq(hw->tp); + if (!mei_write_is_idle(mei_dev)) + ret = -EAGAIN; - return 0; + mutex_unlock(&mei_dev->device_lock); + + return ret; } static int mei_vsc_resume(struct device *dev) { - struct mei_device *mei_dev = dev_get_drvdata(dev); - struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev); - int ret; - - ret = vsc_tp_request_irq(hw->tp); - if (ret) - return ret; - - ret = mei_restart(mei_dev); - if (ret) - goto err_free; + struct mei_device *mei_dev; - /* start timer if stopped in suspend */ - schedule_delayed_work(&mei_dev->timer_work, HZ); + mei_dev = dev_get_drvdata(dev); + if (!mei_dev) + return -ENODEV; return 0; - -err_free: - vsc_tp_free_irq(hw->tp); - - return ret; } static DEFINE_SIMPLE_DEV_PM_OPS(mei_vsc_pm_ops, mei_vsc_suspend, mei_vsc_resume); diff --git a/drivers/misc/mei/vsc-fw-loader.c b/drivers/misc/mei/vsc-fw-loader.c index ffa4ccd96a10..596a9d695dfc 100644 --- a/drivers/misc/mei/vsc-fw-loader.c +++ b/drivers/misc/mei/vsc-fw-loader.c @@ -252,7 +252,7 @@ static int vsc_get_sensor_name(struct vsc_fw_loader *fw_loader, { struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER }; union acpi_object obj = { - .type = ACPI_TYPE_INTEGER, + .integer.type = ACPI_TYPE_INTEGER, .integer.value = 1, }; struct acpi_object_list arg_list = { diff --git a/drivers/net/arcnet/com20020-isa.c b/drivers/net/arcnet/com20020-isa.c index 293a621e654c..fef2ac2852a8 100644 --- a/drivers/net/arcnet/com20020-isa.c +++ b/drivers/net/arcnet/com20020-isa.c @@ -137,6 +137,7 @@ module_param(backplane, int, 0); module_param(clockp, int, 0); module_param(clockm, int, 0); +MODULE_DESCRIPTION("ARCnet COM20020 chipset ISA driver"); MODULE_LICENSE("GPL"); static struct net_device *my_dev; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 3c3fcce4acd4..d19aabf5d4fb 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -5773,6 +5773,9 @@ static int bond_ethtool_get_ts_info(struct net_device *bond_dev, if (real_dev) { ret = ethtool_get_ts_info_by_layer(real_dev, info); } else { + info->phc_index = -1; + info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; /* Check if all slaves support software tx timestamping */ rcu_read_lock(); bond_for_each_slave_rcu(bond, slave, iter) { diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index 2e31db55d927..7f9b60a42d29 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -187,9 +187,8 @@ config CAN_SLCAN slcand) can be found in the can-utils at the linux-can project, see https://github.com/linux-can/can-utils for details. - The slcan driver supports up to 10 CAN netdevices by default which - can be changed by the 'maxdev=xx' module option. This driver can - also be built as a module. If so, the module will be called slcan. + This driver can also be built as a module. If so, the module + will be called slcan. config CAN_SUN4I tristate "Allwinner A10 CAN controller" diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 7b5028b67cd5..a60d9efd5f8d 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -29,10 +29,10 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices"); #define KVASER_PCIEFD_CAN_TX_MAX_COUNT 17U #define KVASER_PCIEFD_MAX_CAN_CHANNELS 8UL #define KVASER_PCIEFD_DMA_COUNT 2U - #define KVASER_PCIEFD_DMA_SIZE (4U * 1024U) #define KVASER_PCIEFD_VENDOR 0x1a07 + /* Altera based devices */ #define KVASER_PCIEFD_4HS_DEVICE_ID 0x000d #define KVASER_PCIEFD_2HS_V2_DEVICE_ID 0x000e @@ -550,7 +550,7 @@ static void kvaser_pciefd_disable_err_gen(struct kvaser_pciefd_can *can) spin_unlock_irqrestore(&can->lock, irq); } -static void kvaser_pciefd_set_tx_irq(struct kvaser_pciefd_can *can) +static inline void kvaser_pciefd_set_tx_irq(struct kvaser_pciefd_can *can) { u32 msk; @@ -711,17 +711,17 @@ static void kvaser_pciefd_pwm_start(struct kvaser_pciefd_can *can) static int kvaser_pciefd_open(struct net_device *netdev) { - int err; + int ret; struct kvaser_pciefd_can *can = netdev_priv(netdev); - err = open_candev(netdev); - if (err) - return err; + ret = open_candev(netdev); + if (ret) + return ret; - err = kvaser_pciefd_bus_on(can); - if (err) { + ret = kvaser_pciefd_bus_on(can); + if (ret) { close_candev(netdev); - return err; + return ret; } return 0; @@ -1032,15 +1032,15 @@ static int kvaser_pciefd_reg_candev(struct kvaser_pciefd *pcie) int i; for (i = 0; i < pcie->nr_channels; i++) { - int err = register_candev(pcie->can[i]->can.dev); + int ret = register_candev(pcie->can[i]->can.dev); - if (err) { + if (ret) { int j; /* Unregister all successfully registered devices. */ for (j = 0; j < i; j++) unregister_candev(pcie->can[j]->can.dev); - return err; + return ret; } } @@ -1619,7 +1619,7 @@ static int kvaser_pciefd_read_packet(struct kvaser_pciefd *pcie, int *start_pos, /* Position does not point to the end of the package, * corrupted packet size? */ - if ((*start_pos + size) != pos) + if (unlikely((*start_pos + size) != pos)) return -EIO; /* Point to the next packet header, if any */ @@ -1640,31 +1640,24 @@ static int kvaser_pciefd_read_buffer(struct kvaser_pciefd *pcie, int dma_buf) return res; } -static void kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie) +static u32 kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie) { u32 irq = ioread32(KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG); - if (irq & KVASER_PCIEFD_SRB_IRQ_DPD0) { + if (irq & KVASER_PCIEFD_SRB_IRQ_DPD0) kvaser_pciefd_read_buffer(pcie, 0); - /* Reset DMA buffer 0 */ - iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0, - KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG); - } - if (irq & KVASER_PCIEFD_SRB_IRQ_DPD1) { + if (irq & KVASER_PCIEFD_SRB_IRQ_DPD1) kvaser_pciefd_read_buffer(pcie, 1); - /* Reset DMA buffer 1 */ - iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1, - KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG); - } - if (irq & KVASER_PCIEFD_SRB_IRQ_DOF0 || - irq & KVASER_PCIEFD_SRB_IRQ_DOF1 || - irq & KVASER_PCIEFD_SRB_IRQ_DUF0 || - irq & KVASER_PCIEFD_SRB_IRQ_DUF1) + if (unlikely(irq & KVASER_PCIEFD_SRB_IRQ_DOF0 || + irq & KVASER_PCIEFD_SRB_IRQ_DOF1 || + irq & KVASER_PCIEFD_SRB_IRQ_DUF0 || + irq & KVASER_PCIEFD_SRB_IRQ_DUF1)) dev_err(&pcie->pci->dev, "DMA IRQ error 0x%08X\n", irq); iowrite32(irq, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG); + return irq; } static void kvaser_pciefd_transmit_irq(struct kvaser_pciefd_can *can) @@ -1691,27 +1684,33 @@ static irqreturn_t kvaser_pciefd_irq_handler(int irq, void *dev) { struct kvaser_pciefd *pcie = (struct kvaser_pciefd *)dev; const struct kvaser_pciefd_irq_mask *irq_mask = pcie->driver_data->irq_mask; - u32 board_irq = ioread32(KVASER_PCIEFD_PCI_IRQ_ADDR(pcie)); + u32 pci_irq = ioread32(KVASER_PCIEFD_PCI_IRQ_ADDR(pcie)); + u32 srb_irq = 0; int i; - if (!(board_irq & irq_mask->all)) + if (!(pci_irq & irq_mask->all)) return IRQ_NONE; - if (board_irq & irq_mask->kcan_rx0) - kvaser_pciefd_receive_irq(pcie); + if (pci_irq & irq_mask->kcan_rx0) + srb_irq = kvaser_pciefd_receive_irq(pcie); for (i = 0; i < pcie->nr_channels; i++) { - if (!pcie->can[i]) { - dev_err(&pcie->pci->dev, - "IRQ mask points to unallocated controller\n"); - break; - } - - /* Check that mask matches channel (i) IRQ mask */ - if (board_irq & irq_mask->kcan_tx[i]) + if (pci_irq & irq_mask->kcan_tx[i]) kvaser_pciefd_transmit_irq(pcie->can[i]); } + if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD0) { + /* Reset DMA buffer 0, may trigger new interrupt */ + iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0, + KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG); + } + + if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD1) { + /* Reset DMA buffer 1, may trigger new interrupt */ + iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1, + KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG); + } + return IRQ_HANDLED; } @@ -1733,7 +1732,7 @@ static void kvaser_pciefd_teardown_can_ctrls(struct kvaser_pciefd *pcie) static int kvaser_pciefd_probe(struct pci_dev *pdev, const struct pci_device_id *id) { - int err; + int ret; struct kvaser_pciefd *pcie; const struct kvaser_pciefd_irq_mask *irq_mask; void __iomem *irq_en_base; @@ -1747,39 +1746,52 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, pcie->driver_data = (const struct kvaser_pciefd_driver_data *)id->driver_data; irq_mask = pcie->driver_data->irq_mask; - err = pci_enable_device(pdev); - if (err) - return err; + ret = pci_enable_device(pdev); + if (ret) + return ret; - err = pci_request_regions(pdev, KVASER_PCIEFD_DRV_NAME); - if (err) + ret = pci_request_regions(pdev, KVASER_PCIEFD_DRV_NAME); + if (ret) goto err_disable_pci; pcie->reg_base = pci_iomap(pdev, 0, 0); if (!pcie->reg_base) { - err = -ENOMEM; + ret = -ENOMEM; goto err_release_regions; } - err = kvaser_pciefd_setup_board(pcie); - if (err) + ret = kvaser_pciefd_setup_board(pcie); + if (ret) goto err_pci_iounmap; - err = kvaser_pciefd_setup_dma(pcie); - if (err) + ret = kvaser_pciefd_setup_dma(pcie); + if (ret) goto err_pci_iounmap; pci_set_master(pdev); - err = kvaser_pciefd_setup_can_ctrls(pcie); - if (err) + ret = kvaser_pciefd_setup_can_ctrls(pcie); + if (ret) goto err_teardown_can_ctrls; - err = request_irq(pcie->pci->irq, kvaser_pciefd_irq_handler, - IRQF_SHARED, KVASER_PCIEFD_DRV_NAME, pcie); - if (err) + ret = pci_alloc_irq_vectors(pcie->pci, 1, 1, PCI_IRQ_INTX | PCI_IRQ_MSI); + if (ret < 0) { + dev_err(&pcie->pci->dev, "Failed to allocate IRQ vectors.\n"); goto err_teardown_can_ctrls; + } + + ret = pci_irq_vector(pcie->pci, 0); + if (ret < 0) + goto err_pci_free_irq_vectors; + + pcie->pci->irq = ret; + ret = request_irq(pcie->pci->irq, kvaser_pciefd_irq_handler, + IRQF_SHARED, KVASER_PCIEFD_DRV_NAME, pcie); + if (ret) { + dev_err(&pcie->pci->dev, "Failed to request IRQ %d\n", pcie->pci->irq); + goto err_pci_free_irq_vectors; + } iowrite32(KVASER_PCIEFD_SRB_IRQ_DPD0 | KVASER_PCIEFD_SRB_IRQ_DPD1, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG); @@ -1797,8 +1809,8 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG); - err = kvaser_pciefd_reg_candev(pcie); - if (err) + ret = kvaser_pciefd_reg_candev(pcie); + if (ret) goto err_free_irq; return 0; @@ -1808,6 +1820,9 @@ err_free_irq: iowrite32(0, irq_en_base); free_irq(pcie->pci->irq, pcie); +err_pci_free_irq_vectors: + pci_free_irq_vectors(pcie->pci); + err_teardown_can_ctrls: kvaser_pciefd_teardown_can_ctrls(pcie); iowrite32(0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CTRL_REG); @@ -1822,7 +1837,7 @@ err_release_regions: err_disable_pci: pci_disable_device(pdev); - return err; + return ret; } static void kvaser_pciefd_remove_all_ctrls(struct kvaser_pciefd *pcie) @@ -1853,7 +1868,7 @@ static void kvaser_pciefd_remove(struct pci_dev *pdev) iowrite32(0, KVASER_PCIEFD_PCI_IEN_ADDR(pcie)); free_irq(pcie->pci->irq, pcie); - + pci_free_irq_vectors(pcie->pci); pci_iounmap(pdev, pcie->reg_base); pci_release_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 14b231c4d7ec..7f63f866083e 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -379,38 +379,72 @@ m_can_txe_fifo_read(struct m_can_classdev *cdev, u32 fgi, u32 offset, u32 *val) return cdev->ops->read_fifo(cdev, addr_offset, val, 1); } -static void m_can_config_endisable(struct m_can_classdev *cdev, bool enable) -{ - u32 cccr = m_can_read(cdev, M_CAN_CCCR); - u32 timeout = 10; - u32 val = 0; - - /* Clear the Clock stop request if it was set */ - if (cccr & CCCR_CSR) - cccr &= ~CCCR_CSR; - - if (enable) { - /* enable m_can configuration */ - m_can_write(cdev, M_CAN_CCCR, cccr | CCCR_INIT); - udelay(5); - /* CCCR.CCE can only be set/reset while CCCR.INIT = '1' */ - m_can_write(cdev, M_CAN_CCCR, cccr | CCCR_INIT | CCCR_CCE); - } else { - m_can_write(cdev, M_CAN_CCCR, cccr & ~(CCCR_INIT | CCCR_CCE)); +static int m_can_cccr_update_bits(struct m_can_classdev *cdev, u32 mask, u32 val) +{ + u32 val_before = m_can_read(cdev, M_CAN_CCCR); + u32 val_after = (val_before & ~mask) | val; + size_t tries = 10; + + if (!(mask & CCCR_INIT) && !(val_before & CCCR_INIT)) { + dev_err(cdev->dev, + "refusing to configure device when in normal mode\n"); + return -EBUSY; } - /* there's a delay for module initialization */ - if (enable) - val = CCCR_INIT | CCCR_CCE; + /* The chip should be in standby mode when changing the CCCR register, + * and some chips set the CSR and CSA bits when in standby. Furthermore, + * the CSR and CSA bits should be written as zeros, even when they read + * ones. + */ + val_after &= ~(CCCR_CSR | CCCR_CSA); - while ((m_can_read(cdev, M_CAN_CCCR) & (CCCR_INIT | CCCR_CCE)) != val) { - if (timeout == 0) { - netdev_warn(cdev->net, "Failed to init module\n"); - return; - } - timeout--; - udelay(1); + while (tries--) { + u32 val_read; + + /* Write the desired value in each try, as setting some bits in + * the CCCR register require other bits to be set first. E.g. + * setting the NISO bit requires setting the CCE bit first. + */ + m_can_write(cdev, M_CAN_CCCR, val_after); + + val_read = m_can_read(cdev, M_CAN_CCCR) & ~(CCCR_CSR | CCCR_CSA); + + if (val_read == val_after) + return 0; + + usleep_range(1, 5); } + + return -ETIMEDOUT; +} + +static int m_can_config_enable(struct m_can_classdev *cdev) +{ + int err; + + /* CCCR_INIT must be set in order to set CCCR_CCE, but access to + * configuration registers should only be enabled when in standby mode, + * where CCCR_INIT is always set. + */ + err = m_can_cccr_update_bits(cdev, CCCR_CCE, CCCR_CCE); + if (err) + netdev_err(cdev->net, "failed to enable configuration mode\n"); + + return err; +} + +static int m_can_config_disable(struct m_can_classdev *cdev) +{ + int err; + + /* Only clear CCCR_CCE, since CCCR_INIT cannot be cleared while in + * standby mode + */ + err = m_can_cccr_update_bits(cdev, CCCR_CCE, 0); + if (err) + netdev_err(cdev->net, "failed to disable configuration registers\n"); + + return err; } static void m_can_interrupt_enable(struct m_can_classdev *cdev, u32 interrupts) @@ -1403,7 +1437,9 @@ static int m_can_chip_config(struct net_device *dev) interrupts &= ~(IR_ARA | IR_ELO | IR_DRX | IR_TEFF | IR_TFE | IR_TCF | IR_HPM | IR_RF1F | IR_RF1W | IR_RF1N | IR_RF0F); - m_can_config_endisable(cdev, true); + err = m_can_config_enable(cdev); + if (err) + return err; /* RX Buffer/FIFO Element Size 64 bytes data field */ m_can_write(cdev, M_CAN_RXESC, @@ -1521,7 +1557,9 @@ static int m_can_chip_config(struct net_device *dev) FIELD_PREP(TSCC_TCP_MASK, 0xf) | FIELD_PREP(TSCC_TSS_MASK, TSCC_TSS_INTERNAL)); - m_can_config_endisable(cdev, false); + err = m_can_config_disable(cdev); + if (err) + return err; if (cdev->ops->init) cdev->ops->init(cdev); @@ -1550,7 +1588,11 @@ static int m_can_start(struct net_device *dev) cdev->tx_fifo_putidx = FIELD_GET(TXFQS_TFQPI_MASK, m_can_read(cdev, M_CAN_TXFQS)); - return 0; + ret = m_can_cccr_update_bits(cdev, CCCR_INIT, 0); + if (ret) + netdev_err(dev, "failed to enter normal mode\n"); + + return ret; } static int m_can_set_mode(struct net_device *dev, enum can_mode mode) @@ -1599,43 +1641,37 @@ static int m_can_check_core_release(struct m_can_classdev *cdev) } /* Selectable Non ISO support only in version 3.2.x - * This function checks if the bit is writable. + * Return 1 if the bit is writable, 0 if it is not, or negative on error. */ -static bool m_can_niso_supported(struct m_can_classdev *cdev) +static int m_can_niso_supported(struct m_can_classdev *cdev) { - u32 cccr_reg, cccr_poll = 0; - int niso_timeout = -ETIMEDOUT; - int i; + int ret, niso; - m_can_config_endisable(cdev, true); - cccr_reg = m_can_read(cdev, M_CAN_CCCR); - cccr_reg |= CCCR_NISO; - m_can_write(cdev, M_CAN_CCCR, cccr_reg); + ret = m_can_config_enable(cdev); + if (ret) + return ret; - for (i = 0; i <= 10; i++) { - cccr_poll = m_can_read(cdev, M_CAN_CCCR); - if (cccr_poll == cccr_reg) { - niso_timeout = 0; - break; - } + /* First try to set the NISO bit. */ + niso = m_can_cccr_update_bits(cdev, CCCR_NISO, CCCR_NISO); - usleep_range(1, 5); + /* Then clear the it again. */ + ret = m_can_cccr_update_bits(cdev, CCCR_NISO, 0); + if (ret) { + dev_err(cdev->dev, "failed to revert the NON-ISO bit in CCCR\n"); + return ret; } - /* Clear NISO */ - cccr_reg &= ~(CCCR_NISO); - m_can_write(cdev, M_CAN_CCCR, cccr_reg); - - m_can_config_endisable(cdev, false); + ret = m_can_config_disable(cdev); + if (ret) + return ret; - /* return false if time out (-ETIMEDOUT), else return true */ - return !niso_timeout; + return niso == 0; } static int m_can_dev_setup(struct m_can_classdev *cdev) { struct net_device *dev = cdev->net; - int m_can_version, err; + int m_can_version, err, niso; m_can_version = m_can_check_core_release(cdev); /* return if unsupported version */ @@ -1684,9 +1720,11 @@ static int m_can_dev_setup(struct m_can_classdev *cdev) cdev->can.bittiming_const = &m_can_bittiming_const_31X; cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X; - cdev->can.ctrlmode_supported |= - (m_can_niso_supported(cdev) ? - CAN_CTRLMODE_FD_NON_ISO : 0); + niso = m_can_niso_supported(cdev); + if (niso < 0) + return niso; + if (niso) + cdev->can.ctrlmode_supported |= CAN_CTRLMODE_FD_NON_ISO; break; default: dev_err(cdev->dev, "Unsupported version number: %2d", @@ -1694,21 +1732,26 @@ static int m_can_dev_setup(struct m_can_classdev *cdev) return -EINVAL; } - if (cdev->ops->init) - cdev->ops->init(cdev); - - return 0; + /* Forcing standby mode should be redundant, as the chip should be in + * standby after a reset. Write the INIT bit anyways, should the chip + * be configured by previous stage. + */ + return m_can_cccr_update_bits(cdev, CCCR_INIT, CCCR_INIT); } static void m_can_stop(struct net_device *dev) { struct m_can_classdev *cdev = netdev_priv(dev); + int ret; /* disable all interrupts */ m_can_disable_all_interrupts(cdev); /* Set init mode to disengage from the network */ - m_can_config_endisable(cdev, true); + ret = m_can_cccr_update_bits(cdev, CCCR_INIT, CCCR_INIT); + if (ret) + netdev_err(dev, "failed to enter standby mode: %pe\n", + ERR_PTR(ret)); /* set the state as STOPPED */ cdev->can.state = CAN_STATE_STOPPED; diff --git a/drivers/net/can/m_can/tcan4x5x-core.c b/drivers/net/can/m_can/tcan4x5x-core.c index a42600dac70d..d723206ac7c9 100644 --- a/drivers/net/can/m_can/tcan4x5x-core.c +++ b/drivers/net/can/m_can/tcan4x5x-core.c @@ -453,10 +453,17 @@ static int tcan4x5x_can_probe(struct spi_device *spi) goto out_power; } - ret = tcan4x5x_init(mcan_class); + tcan4x5x_check_wake(priv); + + ret = tcan4x5x_write_tcan_reg(mcan_class, TCAN4X5X_INT_EN, 0); if (ret) { - dev_err(&spi->dev, "tcan initialization failed %pe\n", - ERR_PTR(ret)); + dev_err(&spi->dev, "Disabling interrupts failed %pe\n", ERR_PTR(ret)); + goto out_power; + } + + ret = tcan4x5x_clear_interrupts(mcan_class); + if (ret) { + dev_err(&spi->dev, "Clearing interrupts failed %pe\n", ERR_PTR(ret)); goto out_power; } diff --git a/drivers/net/can/mscan/mscan.c b/drivers/net/can/mscan/mscan.c index a6829cdc0e81..8c2a7bc64d3d 100644 --- a/drivers/net/can/mscan/mscan.c +++ b/drivers/net/can/mscan/mscan.c @@ -34,12 +34,6 @@ static const struct can_bittiming_const mscan_bittiming_const = { .brp_inc = 1, }; -struct mscan_state { - u8 mode; - u8 canrier; - u8 cantier; -}; - static enum can_state state_map[] = { CAN_STATE_ERROR_ACTIVE, CAN_STATE_ERROR_WARNING, diff --git a/drivers/net/can/sja1000/plx_pci.c b/drivers/net/can/sja1000/plx_pci.c index 5de1ebb0c6f0..67e5316c6372 100644 --- a/drivers/net/can/sja1000/plx_pci.c +++ b/drivers/net/can/sja1000/plx_pci.c @@ -122,7 +122,6 @@ struct plx_pci_card { #define TEWS_PCI_VENDOR_ID 0x1498 #define TEWS_PCI_DEVICE_ID_TMPC810 0x032A -#define CTI_PCI_VENDOR_ID 0x12c4 #define CTI_PCI_DEVICE_ID_CRG001 0x0900 #define MOXA_PCI_VENDOR_ID 0x1393 @@ -358,7 +357,7 @@ static const struct pci_device_id plx_pci_tbl[] = { { /* Connect Tech Inc. CANpro/104-Plus Opto (CRG001) card */ PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9030, - CTI_PCI_VENDOR_ID, CTI_PCI_DEVICE_ID_CRG001, + PCI_SUBVENDOR_ID_CONNECT_TECH, CTI_PCI_DEVICE_ID_CRG001, 0, 0, (kernel_ulong_t)&plx_pci_card_info_cti }, diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c index e1b8533a602e..148d974ebb21 100644 --- a/drivers/net/can/spi/hi311x.c +++ b/drivers/net/can/spi/hi311x.c @@ -830,7 +830,6 @@ static int hi3110_can_probe(struct spi_device *spi) struct device *dev = &spi->dev; struct net_device *net; struct hi3110_priv *priv; - const void *match; struct clk *clk; u32 freq; int ret; @@ -874,11 +873,7 @@ static int hi3110_can_probe(struct spi_device *spi) CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_BERR_REPORTING; - match = device_get_match_data(dev); - if (match) - priv->model = (enum hi3110_model)(uintptr_t)match; - else - priv->model = spi_get_device_id(spi)->driver_data; + priv->model = (enum hi3110_model)(uintptr_t)spi_get_device_match_data(spi); priv->net = net; priv->clk = clk; diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index 79c4bab5f724..3b8736ff0345 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -28,7 +28,6 @@ #include <linux/device.h> #include <linux/ethtool.h> #include <linux/freezer.h> -#include <linux/gpio.h> #include <linux/gpio/driver.h> #include <linux/interrupt.h> #include <linux/io.h> @@ -482,9 +481,9 @@ static int mcp251x_gpio_get_direction(struct gpio_chip *chip, unsigned int offset) { if (mcp251x_gpio_is_input(offset)) - return GPIOF_DIR_IN; + return GPIO_LINE_DIRECTION_IN; - return GPIOF_DIR_OUT; + return GPIO_LINE_DIRECTION_OUT; } static int mcp251x_gpio_get(struct gpio_chip *chip, unsigned int offset) @@ -1301,7 +1300,6 @@ MODULE_DEVICE_TABLE(spi, mcp251x_id_table); static int mcp251x_can_probe(struct spi_device *spi) { - const void *match = device_get_match_data(&spi->dev); struct net_device *net; struct mcp251x_priv *priv; struct clk *clk; @@ -1339,10 +1337,7 @@ static int mcp251x_can_probe(struct spi_device *spi) priv->can.clock.freq = freq / 2; priv->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LOOPBACK | CAN_CTRLMODE_LISTENONLY; - if (match) - priv->model = (enum mcp251x_model)(uintptr_t)match; - else - priv->model = spi_get_device_id(spi)->driver_data; + priv->model = (enum mcp251x_model)(uintptr_t)spi_get_device_match_data(spi); priv->net = net; priv->clk = clk; diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index 1d9057dc44f2..c116d3255207 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -1618,11 +1618,20 @@ static int mcp251xfd_open(struct net_device *ndev) clear_bit(MCP251XFD_FLAGS_DOWN, priv->flags); can_rx_offload_enable(&priv->offload); + priv->wq = alloc_ordered_workqueue("%s-mcp251xfd_wq", + WQ_FREEZABLE | WQ_MEM_RECLAIM, + dev_name(&spi->dev)); + if (!priv->wq) { + err = -ENOMEM; + goto out_can_rx_offload_disable; + } + INIT_WORK(&priv->tx_work, mcp251xfd_tx_obj_write_sync); + err = request_threaded_irq(spi->irq, NULL, mcp251xfd_irq, IRQF_SHARED | IRQF_ONESHOT, dev_name(&spi->dev), priv); if (err) - goto out_can_rx_offload_disable; + goto out_destroy_workqueue; err = mcp251xfd_chip_interrupts_enable(priv); if (err) @@ -1634,6 +1643,8 @@ static int mcp251xfd_open(struct net_device *ndev) out_free_irq: free_irq(spi->irq, priv); + out_destroy_workqueue: + destroy_workqueue(priv->wq); out_can_rx_offload_disable: can_rx_offload_disable(&priv->offload); set_bit(MCP251XFD_FLAGS_DOWN, priv->flags); @@ -1661,6 +1672,7 @@ static int mcp251xfd_stop(struct net_device *ndev) hrtimer_cancel(&priv->tx_irq_timer); mcp251xfd_chip_interrupts_disable(priv); free_irq(ndev->irq, priv); + destroy_workqueue(priv->wq); can_rx_offload_disable(&priv->offload); mcp251xfd_timestamp_stop(priv); mcp251xfd_chip_stop(priv, CAN_STATE_STOPPED); @@ -1989,7 +2001,6 @@ MODULE_DEVICE_TABLE(spi, mcp251xfd_id_table); static int mcp251xfd_probe(struct spi_device *spi) { - const void *match; struct net_device *ndev; struct mcp251xfd_priv *priv; struct gpio_desc *rx_int; @@ -2081,13 +2092,7 @@ static int mcp251xfd_probe(struct spi_device *spi) priv->pll_enable = pll_enable; priv->reg_vdd = reg_vdd; priv->reg_xceiver = reg_xceiver; - - match = device_get_match_data(&spi->dev); - if (match) - priv->devtype_data = *(struct mcp251xfd_devtype_data *)match; - else - priv->devtype_data = *(struct mcp251xfd_devtype_data *) - spi_get_device_id(spi)->driver_data; + priv->devtype_data = *(struct mcp251xfd_devtype_data *)spi_get_device_match_data(spi); /* Errata Reference: * mcp2517fd: DS80000792C 5., mcp2518fd: DS80000789C 4. diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c index 160528d3cc26..b1de8052a45c 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c @@ -131,6 +131,39 @@ mcp251xfd_tx_obj_from_skb(const struct mcp251xfd_priv *priv, tx_obj->xfer[0].len = len; } +static void mcp251xfd_tx_failure_drop(const struct mcp251xfd_priv *priv, + struct mcp251xfd_tx_ring *tx_ring, + int err) +{ + struct net_device *ndev = priv->ndev; + struct net_device_stats *stats = &ndev->stats; + unsigned int frame_len = 0; + u8 tx_head; + + tx_ring->head--; + stats->tx_dropped++; + tx_head = mcp251xfd_get_tx_head(tx_ring); + can_free_echo_skb(ndev, tx_head, &frame_len); + netdev_completed_queue(ndev, 1, frame_len); + netif_wake_queue(ndev); + + if (net_ratelimit()) + netdev_err(priv->ndev, "ERROR in %s: %d\n", __func__, err); +} + +void mcp251xfd_tx_obj_write_sync(struct work_struct *work) +{ + struct mcp251xfd_priv *priv = container_of(work, struct mcp251xfd_priv, + tx_work); + struct mcp251xfd_tx_obj *tx_obj = priv->tx_work_obj; + struct mcp251xfd_tx_ring *tx_ring = priv->tx; + int err; + + err = spi_sync(priv->spi, &tx_obj->msg); + if (err) + mcp251xfd_tx_failure_drop(priv, tx_ring, err); +} + static int mcp251xfd_tx_obj_write(const struct mcp251xfd_priv *priv, struct mcp251xfd_tx_obj *tx_obj) { @@ -162,6 +195,11 @@ static bool mcp251xfd_tx_busy(const struct mcp251xfd_priv *priv, return false; } +static bool mcp251xfd_work_busy(struct work_struct *work) +{ + return work_busy(work); +} + netdev_tx_t mcp251xfd_start_xmit(struct sk_buff *skb, struct net_device *ndev) { @@ -175,7 +213,8 @@ netdev_tx_t mcp251xfd_start_xmit(struct sk_buff *skb, if (can_dev_dropped_skb(ndev, skb)) return NETDEV_TX_OK; - if (mcp251xfd_tx_busy(priv, tx_ring)) + if (mcp251xfd_tx_busy(priv, tx_ring) || + mcp251xfd_work_busy(&priv->tx_work)) return NETDEV_TX_BUSY; tx_obj = mcp251xfd_get_tx_obj_next(tx_ring); @@ -193,13 +232,13 @@ netdev_tx_t mcp251xfd_start_xmit(struct sk_buff *skb, netdev_sent_queue(priv->ndev, frame_len); err = mcp251xfd_tx_obj_write(priv, tx_obj); - if (err) - goto out_err; - - return NETDEV_TX_OK; - - out_err: - netdev_err(priv->ndev, "ERROR in %s: %d\n", __func__, err); + if (err == -EBUSY) { + netif_stop_queue(ndev); + priv->tx_work_obj = tx_obj; + queue_work(priv->wq, &priv->tx_work); + } else if (err) { + mcp251xfd_tx_failure_drop(priv, tx_ring, err); + } return NETDEV_TX_OK; } diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h index 24510b3b8020..b35bfebd23f2 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h @@ -633,6 +633,10 @@ struct mcp251xfd_priv { struct mcp251xfd_rx_ring *rx[MCP251XFD_FIFO_RX_NUM]; struct mcp251xfd_tx_ring tx[MCP251XFD_FIFO_TX_NUM]; + struct workqueue_struct *wq; + struct work_struct tx_work; + struct mcp251xfd_tx_obj *tx_work_obj; + DECLARE_BITMAP(flags, __MCP251XFD_FLAGS_SIZE__); u8 rx_ring_num; @@ -952,6 +956,7 @@ void mcp251xfd_skb_set_timestamp(const struct mcp251xfd_priv *priv, void mcp251xfd_timestamp_init(struct mcp251xfd_priv *priv); void mcp251xfd_timestamp_stop(struct mcp251xfd_priv *priv); +void mcp251xfd_tx_obj_write_sync(struct work_struct *work); netdev_tx_t mcp251xfd_start_xmit(struct sk_buff *skb, struct net_device *ndev); diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig index bd58c636d465..3e1fba12c0c3 100644 --- a/drivers/net/can/usb/Kconfig +++ b/drivers/net/can/usb/Kconfig @@ -91,6 +91,7 @@ config CAN_KVASER_USB - Kvaser Leaf Light R v2 - Kvaser Mini PCI Express HS - Kvaser Mini PCI Express 2xHS + - Kvaser Mini PCIe 1xCAN - Kvaser USBcan Light 2xHS - Kvaser USBcan II HS/HS - Kvaser USBcan II HS/LS @@ -111,12 +112,14 @@ config CAN_KVASER_USB - Kvaser USBcan Light 4xHS - Kvaser USBcan Pro 2xHS v2 - Kvaser USBcan Pro 4xHS + - Kvaser USBcan Pro 5xCAN - Kvaser USBcan Pro 5xHS - Kvaser U100 - Kvaser U100P - Kvaser U100S - ATI Memorator Pro 2xHS v2 - ATI USBcan Pro 2xHS v2 + - Vining 800 If unsure, say N. diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c index 8faf8a462c05..7faec0eef1ca 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -89,6 +89,9 @@ #define USB_HYBRID_CANLIN_PRODUCT_ID 0x0115 #define USB_HYBRID_PRO_CANLIN_PRODUCT_ID 0x0116 #define USB_LEAF_V3_PRODUCT_ID 0x0117 +#define USB_VINING_800_PRODUCT_ID 0x0119 +#define USB_USBCAN_PRO_5XCAN_PRODUCT_ID 0x011A +#define USB_MINI_PCIE_1XCAN_PRODUCT_ID 0x011B static const struct kvaser_usb_driver_info kvaser_usb_driver_info_hydra = { .quirks = KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP, @@ -238,6 +241,12 @@ static const struct usb_device_id kvaser_usb_table[] = { .driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra }, { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_V3_PRODUCT_ID), .driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_VINING_800_PRODUCT_ID), + .driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_5XCAN_PRODUCT_ID), + .driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_1XCAN_PRODUCT_ID), + .driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra }, { } }; MODULE_DEVICE_TABLE(usb, kvaser_usb_table); @@ -294,7 +303,7 @@ int kvaser_usb_send_cmd_async(struct kvaser_usb_net_priv *priv, void *cmd, } usb_free_urb(urb); - return 0; + return err; } int kvaser_usb_can_rx_over_error(struct net_device *netdev) diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index fae0120473f8..d944911d7f05 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -6,7 +6,7 @@ * Copyright (C) 2017 - 2018 Sandvik Mining and Construction Oy * * Description: - * This driver is developed for Axi CAN IP and for Zynq CANPS Controller. + * This driver is developed for AXI CAN IP, AXI CANFD IP, CANPS and CANFD PS Controller. */ #include <linux/bitfield.h> diff --git a/drivers/net/dsa/lan9303_i2c.c b/drivers/net/dsa/lan9303_i2c.c index bbbec322bc4f..c62d27cdc117 100644 --- a/drivers/net/dsa/lan9303_i2c.c +++ b/drivers/net/dsa/lan9303_i2c.c @@ -89,7 +89,7 @@ static void lan9303_i2c_shutdown(struct i2c_client *client) /*-------------------------------------------------------------------------*/ static const struct i2c_device_id lan9303_i2c_id[] = { - { "lan9303", 0 }, + { "lan9303" }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(i2c, lan9303_i2c_id); diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index a557049e34f5..fcd4505f4925 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -236,7 +236,9 @@ #define GSWIP_TABLE_ACTIVE_VLAN 0x01 #define GSWIP_TABLE_VLAN_MAPPING 0x02 #define GSWIP_TABLE_MAC_BRIDGE 0x0b -#define GSWIP_TABLE_MAC_BRIDGE_STATIC 0x01 /* Static not, aging entry */ +#define GSWIP_TABLE_MAC_BRIDGE_KEY3_FID GENMASK(5, 0) /* Filtering identifier */ +#define GSWIP_TABLE_MAC_BRIDGE_VAL0_PORT GENMASK(7, 4) /* Port on learned entries */ +#define GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC BIT(0) /* Static, non-aging entry */ #define XRX200_GPHY_FW_ALIGN (16 * 1024) @@ -653,14 +655,8 @@ static int gswip_add_single_port_br(struct gswip_priv *priv, int port, bool add) struct gswip_pce_table_entry vlan_active = {0,}; struct gswip_pce_table_entry vlan_mapping = {0,}; unsigned int cpu_port = priv->hw_info->cpu_port; - unsigned int max_ports = priv->hw_info->max_ports; int err; - if (port >= max_ports) { - dev_err(priv->dev, "single port for %i supported\n", port); - return -EIO; - } - vlan_active.index = port + 1; vlan_active.table = GSWIP_TABLE_ACTIVE_VLAN; vlan_active.key[0] = 0; /* vid */ @@ -695,13 +691,18 @@ static int gswip_port_enable(struct dsa_switch *ds, int port, struct gswip_priv *priv = ds->priv; int err; - if (!dsa_is_user_port(ds, port)) - return 0; - if (!dsa_is_cpu_port(ds, port)) { + u32 mdio_phy = 0; + err = gswip_add_single_port_br(priv, port, true); if (err) return err; + + if (phydev) + mdio_phy = phydev->mdio.addr & GSWIP_MDIO_PHY_ADDR_MASK; + + gswip_mdio_mask(priv, GSWIP_MDIO_PHY_ADDR_MASK, mdio_phy, + GSWIP_MDIO_PHYp(port)); } /* RMON Counter Enable for port */ @@ -714,16 +715,6 @@ static int gswip_port_enable(struct dsa_switch *ds, int port, gswip_switch_mask(priv, 0, GSWIP_SDMA_PCTRL_EN, GSWIP_SDMA_PCTRLp(port)); - if (!dsa_is_cpu_port(ds, port)) { - u32 mdio_phy = 0; - - if (phydev) - mdio_phy = phydev->mdio.addr & GSWIP_MDIO_PHY_ADDR_MASK; - - gswip_mdio_mask(priv, GSWIP_MDIO_PHY_ADDR_MASK, mdio_phy, - GSWIP_MDIO_PHYp(port)); - } - return 0; } @@ -731,9 +722,6 @@ static void gswip_port_disable(struct dsa_switch *ds, int port) { struct gswip_priv *priv = ds->priv; - if (!dsa_is_user_port(ds, port)) - return; - gswip_switch_mask(priv, GSWIP_FDMA_PCTRL_EN, 0, GSWIP_FDMA_PCTRLp(port)); gswip_switch_mask(priv, GSWIP_SDMA_PCTRL_EN, 0, @@ -792,7 +780,7 @@ static int gswip_port_vlan_filtering(struct dsa_switch *ds, int port, } if (vlan_filtering) { - /* Use port based VLAN tag */ + /* Use tag based VLAN */ gswip_switch_mask(priv, GSWIP_PCE_VCTRL_VSR, GSWIP_PCE_VCTRL_UVR | GSWIP_PCE_VCTRL_VIMR | @@ -801,7 +789,7 @@ static int gswip_port_vlan_filtering(struct dsa_switch *ds, int port, gswip_switch_mask(priv, GSWIP_PCE_PCTRL_0_TVM, 0, GSWIP_PCE_PCTRL_0p(port)); } else { - /* Use port based VLAN tag */ + /* Use port based VLAN */ gswip_switch_mask(priv, GSWIP_PCE_VCTRL_UVR | GSWIP_PCE_VCTRL_VIMR | GSWIP_PCE_VCTRL_VEMR, @@ -836,7 +824,7 @@ static int gswip_setup(struct dsa_switch *ds) err = gswip_pce_load_microcode(priv); if (err) { - dev_err(priv->dev, "writing PCE microcode failed, %i", err); + dev_err(priv->dev, "writing PCE microcode failed, %i\n", err); return err; } @@ -898,8 +886,6 @@ static int gswip_setup(struct dsa_switch *ds) ds->mtu_enforcement_ingress = true; - gswip_port_enable(ds, cpu_port, NULL); - ds->configure_vlan_while_not_filtering = false; return 0; @@ -1314,10 +1300,11 @@ static void gswip_port_fast_age(struct dsa_switch *ds, int port) if (!mac_bridge.valid) continue; - if (mac_bridge.val[1] & GSWIP_TABLE_MAC_BRIDGE_STATIC) + if (mac_bridge.val[1] & GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC) continue; - if (((mac_bridge.val[0] & GENMASK(7, 4)) >> 4) != port) + if (port != FIELD_GET(GSWIP_TABLE_MAC_BRIDGE_VAL0_PORT, + mac_bridge.val[0])) continue; mac_bridge.valid = false; @@ -1383,7 +1370,8 @@ static int gswip_port_fdb(struct dsa_switch *ds, int port, } if (fid == -1) { - dev_err(priv->dev, "Port not part of a bridge\n"); + dev_err(priv->dev, "no FID found for bridge %s\n", + bridge->name); return -EINVAL; } @@ -1392,9 +1380,9 @@ static int gswip_port_fdb(struct dsa_switch *ds, int port, mac_bridge.key[0] = addr[5] | (addr[4] << 8); mac_bridge.key[1] = addr[3] | (addr[2] << 8); mac_bridge.key[2] = addr[1] | (addr[0] << 8); - mac_bridge.key[3] = fid; + mac_bridge.key[3] = FIELD_PREP(GSWIP_TABLE_MAC_BRIDGE_KEY3_FID, fid); mac_bridge.val[0] = add ? BIT(port) : 0; /* port map */ - mac_bridge.val[1] = GSWIP_TABLE_MAC_BRIDGE_STATIC; + mac_bridge.val[1] = GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC; mac_bridge.valid = add; err = gswip_pce_table_entry_write(priv, &mac_bridge); @@ -1423,7 +1411,7 @@ static int gswip_port_fdb_dump(struct dsa_switch *ds, int port, { struct gswip_priv *priv = ds->priv; struct gswip_pce_table_entry mac_bridge = {0,}; - unsigned char addr[6]; + unsigned char addr[ETH_ALEN]; int i; int err; @@ -1448,14 +1436,15 @@ static int gswip_port_fdb_dump(struct dsa_switch *ds, int port, addr[2] = (mac_bridge.key[1] >> 8) & 0xff; addr[1] = mac_bridge.key[2] & 0xff; addr[0] = (mac_bridge.key[2] >> 8) & 0xff; - if (mac_bridge.val[1] & GSWIP_TABLE_MAC_BRIDGE_STATIC) { + if (mac_bridge.val[1] & GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC) { if (mac_bridge.val[0] & BIT(port)) { err = cb(addr, 0, true, data); if (err) return err; } } else { - if (((mac_bridge.val[0] & GENMASK(7, 4)) >> 4) == port) { + if (port == FIELD_GET(GSWIP_TABLE_MAC_BRIDGE_VAL0_PORT, + mac_bridge.val[0])) { err = cb(addr, 0, false, data); if (err) return err; @@ -1474,12 +1463,11 @@ static int gswip_port_max_mtu(struct dsa_switch *ds, int port) static int gswip_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu) { struct gswip_priv *priv = ds->priv; - int cpu_port = priv->hw_info->cpu_port; /* CPU port always has maximum mtu of user ports, so use it to set * switch frame size, including 8 byte special header. */ - if (port == cpu_port) { + if (dsa_is_cpu_port(ds, port)) { new_mtu += 8; gswip_switch_w(priv, VLAN_ETH_HLEN + new_mtu + ETH_FCS_LEN, GSWIP_MAC_FLEN); @@ -1516,6 +1504,7 @@ static void gswip_xrx200_phylink_get_caps(struct dsa_switch *ds, int port, case 2: case 3: case 4: + case 6: __set_bit(PHY_INTERFACE_MODE_INTERNAL, config->supported_interfaces); break; @@ -1547,6 +1536,7 @@ static void gswip_xrx300_phylink_get_caps(struct dsa_switch *ds, int port, case 2: case 3: case 4: + case 6: __set_bit(PHY_INTERFACE_MODE_INTERNAL, config->supported_interfaces); break; @@ -1790,7 +1780,7 @@ static u32 gswip_bcm_ram_entry_read(struct gswip_priv *priv, u32 table, err = gswip_switch_r_timeout(priv, GSWIP_BM_RAM_CTRL, GSWIP_BM_RAM_CTRL_BAS); if (err) { - dev_err(priv->dev, "timeout while reading table: %u, index: %u", + dev_err(priv->dev, "timeout while reading table: %u, index: %u\n", table, index); return 0; } @@ -1929,11 +1919,9 @@ static int gswip_gphy_fw_load(struct gswip_priv *priv, struct gswip_gphy_fw *gph msleep(200); ret = request_firmware(&fw, gphy_fw->fw_name, dev); - if (ret) { - dev_err(dev, "failed to load firmware: %s, error: %i\n", - gphy_fw->fw_name, ret); - return ret; - } + if (ret) + return dev_err_probe(dev, ret, "failed to load firmware: %s\n", + gphy_fw->fw_name); /* GPHY cores need the firmware code in a persistent and contiguous * memory area with a 16 kB boundary aligned start address. @@ -1946,9 +1934,9 @@ static int gswip_gphy_fw_load(struct gswip_priv *priv, struct gswip_gphy_fw *gph dev_addr = ALIGN(dma_addr, XRX200_GPHY_FW_ALIGN); memcpy(fw_addr, fw->data, fw->size); } else { - dev_err(dev, "failed to alloc firmware memory\n"); release_firmware(fw); - return -ENOMEM; + return dev_err_probe(dev, -ENOMEM, + "failed to alloc firmware memory\n"); } release_firmware(fw); @@ -1975,8 +1963,8 @@ static int gswip_gphy_fw_probe(struct gswip_priv *priv, gphy_fw->clk_gate = devm_clk_get(dev, gphyname); if (IS_ERR(gphy_fw->clk_gate)) { - dev_err(dev, "Failed to lookup gate clock\n"); - return PTR_ERR(gphy_fw->clk_gate); + return dev_err_probe(dev, PTR_ERR(gphy_fw->clk_gate), + "Failed to lookup gate clock\n"); } ret = of_property_read_u32(gphy_fw_np, "reg", &gphy_fw->fw_addr_offset); @@ -1996,8 +1984,8 @@ static int gswip_gphy_fw_probe(struct gswip_priv *priv, gphy_fw->fw_name = priv->gphy_fw_name_cfg->ge_firmware_name; break; default: - dev_err(dev, "Unknown GPHY mode %d\n", gphy_mode); - return -EINVAL; + return dev_err_probe(dev, -EINVAL, "Unknown GPHY mode %d\n", + gphy_mode); } gphy_fw->reset = of_reset_control_array_get_exclusive(gphy_fw_np); @@ -2019,7 +2007,7 @@ static void gswip_gphy_fw_remove(struct gswip_priv *priv, ret = regmap_write(priv->rcu_regmap, gphy_fw->fw_addr_offset, 0); if (ret) - dev_err(priv->dev, "can not reset GPHY FW pointer"); + dev_err(priv->dev, "can not reset GPHY FW pointer\n"); clk_disable_unprepare(gphy_fw->clk_gate); @@ -2048,8 +2036,9 @@ static int gswip_gphy_fw_list(struct gswip_priv *priv, priv->gphy_fw_name_cfg = &xrx200a2x_gphy_data; break; default: - dev_err(dev, "unknown GSWIP version: 0x%x", version); - return -ENOENT; + return dev_err_probe(dev, -ENOENT, + "unknown GSWIP version: 0x%x\n", + version); } } @@ -2057,10 +2046,9 @@ static int gswip_gphy_fw_list(struct gswip_priv *priv, if (match && match->data) priv->gphy_fw_name_cfg = match->data; - if (!priv->gphy_fw_name_cfg) { - dev_err(dev, "GPHY compatible type not supported"); - return -ENOENT; - } + if (!priv->gphy_fw_name_cfg) + return dev_err_probe(dev, -ENOENT, + "GPHY compatible type not supported\n"); priv->num_gphy_fw = of_get_available_child_count(gphy_fw_list_np); if (!priv->num_gphy_fw) @@ -2161,8 +2149,8 @@ static int gswip_probe(struct platform_device *pdev) return -EINVAL; break; default: - dev_err(dev, "unknown GSWIP version: 0x%x", version); - return -ENOENT; + return dev_err_probe(dev, -ENOENT, + "unknown GSWIP version: 0x%x\n", version); } /* bring up the mdio bus */ @@ -2170,28 +2158,27 @@ static int gswip_probe(struct platform_device *pdev) if (gphy_fw_np) { err = gswip_gphy_fw_list(priv, gphy_fw_np, version); of_node_put(gphy_fw_np); - if (err) { - dev_err(dev, "gphy fw probe failed\n"); - return err; - } + if (err) + return dev_err_probe(dev, err, + "gphy fw probe failed\n"); } /* bring up the mdio bus */ err = gswip_mdio(priv); if (err) { - dev_err(dev, "mdio probe failed\n"); + dev_err_probe(dev, err, "mdio probe failed\n"); goto gphy_fw_remove; } err = dsa_register_switch(priv->ds); if (err) { - dev_err(dev, "dsa switch register failed: %i\n", err); + dev_err_probe(dev, err, "dsa switch registration failed\n"); goto gphy_fw_remove; } if (!dsa_is_cpu_port(priv->ds, priv->hw_info->cpu_port)) { - dev_err(dev, "wrong CPU port defined, HW only supports port: %i", - priv->hw_info->cpu_port); - err = -EINVAL; + err = dev_err_probe(dev, -EINVAL, + "wrong CPU port defined, HW only supports port: %i\n", + priv->hw_info->cpu_port); goto disable_switch; } diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index f8ad7833f5d9..425e20daf1e9 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -355,10 +355,8 @@ int ksz9477_reset_switch(struct ksz_device *dev) SPI_AUTO_EDGE_DETECTION, 0); /* default configuration */ - ksz_read8(dev, REG_SW_LUE_CTRL_1, &data8); - data8 = SW_AGING_ENABLE | SW_LINK_AUTO_AGING | - SW_SRC_ADDR_FILTER | SW_FLUSH_STP_TABLE | SW_FLUSH_MSTP_TABLE; - ksz_write8(dev, REG_SW_LUE_CTRL_1, data8); + ksz_write8(dev, REG_SW_LUE_CTRL_1, + SW_AGING_ENABLE | SW_LINK_AUTO_AGING | SW_SRC_ADDR_FILTER); /* disable interrupts */ ksz_write32(dev, REG_SW_INT_MASK__4, SWITCH_INT_MASK); @@ -429,6 +427,57 @@ void ksz9477_freeze_mib(struct ksz_device *dev, int port, bool freeze) mutex_unlock(&p->mib.cnt_mutex); } +int ksz9477_errata_monitor(struct ksz_device *dev, int port, + u64 tx_late_col) +{ + u32 pmavbc; + u8 status; + u16 pqm; + int ret; + + ret = ksz_pread8(dev, port, REG_PORT_STATUS_0, &status); + if (ret) + return ret; + if (!(FIELD_GET(PORT_INTF_SPEED_MASK, status) == PORT_INTF_SPEED_NONE) && + !(status & PORT_INTF_FULL_DUPLEX)) { + /* Errata DS80000754 recommends monitoring potential faults in + * half-duplex mode. The switch might not be able to communicate anymore + * in these states. + * If you see this message, please read the errata-sheet for more information: + * https://ww1.microchip.com/downloads/aemDocuments/documents/UNG/ProductDocuments/Errata/KSZ9477S-Errata-DS80000754.pdf + * To workaround this issue, half-duplex mode should be avoided. + * A software reset could be implemented to recover from this state. + */ + dev_warn_once(dev->dev, + "Half-duplex detected on port %d, transmission halt may occur\n", + port); + if (tx_late_col != 0) { + /* Transmission halt with late collisions */ + dev_crit_once(dev->dev, + "TX late collisions detected, transmission may be halted on port %d\n", + port); + } + ret = ksz_read8(dev, REG_SW_LUE_CTRL_0, &status); + if (ret) + return ret; + if (status & SW_VLAN_ENABLE) { + ret = ksz_pread16(dev, port, REG_PORT_QM_TX_CNT_0__4, &pqm); + if (ret) + return ret; + ret = ksz_read32(dev, REG_PMAVBC, &pmavbc); + if (ret) + return ret; + if ((FIELD_GET(PMAVBC_MASK, pmavbc) <= PMAVBC_MIN) || + (FIELD_GET(PORT_QM_TX_CNT_M, pqm) >= PORT_QM_TX_CNT_MAX)) { + /* Transmission halt with Half-Duplex and VLAN */ + dev_crit_once(dev->dev, + "resources out of limits, transmission may be halted\n"); + } + } + } + return ret; +} + void ksz9477_port_init_cnt(struct ksz_device *dev, int port) { struct ksz_port_mib *mib = &dev->ports[port].mib; @@ -1299,6 +1348,10 @@ int ksz9477_setup(struct dsa_switch *ds) /* Enable REG_SW_MTU__2 reg by setting SW_JUMBO_PACKET */ ksz_cfg(dev, REG_SW_MAC_CTRL_1, SW_JUMBO_PACKET, true); + /* Use collision based back pressure mode. */ + ksz_cfg(dev, REG_SW_MAC_CTRL_1, SW_BACK_PRESSURE, + SW_BACK_PRESSURE_COLLISION); + /* Now we can configure default MTU value */ ret = regmap_update_bits(ksz_regmap_16(dev), REG_SW_MTU__2, REG_SW_MTU_MASK, VLAN_ETH_FRAME_LEN + ETH_FCS_LEN); diff --git a/drivers/net/dsa/microchip/ksz9477.h b/drivers/net/dsa/microchip/ksz9477.h index ce1e656b800b..239a281da10b 100644 --- a/drivers/net/dsa/microchip/ksz9477.h +++ b/drivers/net/dsa/microchip/ksz9477.h @@ -36,6 +36,8 @@ int ksz9477_port_mirror_add(struct ksz_device *dev, int port, bool ingress, struct netlink_ext_ack *extack); void ksz9477_port_mirror_del(struct ksz_device *dev, int port, struct dsa_mall_mirror_tc_entry *mirror); +int ksz9477_errata_monitor(struct ksz_device *dev, int port, + u64 tx_late_col); void ksz9477_get_caps(struct ksz_device *dev, int port, struct phylink_config *config); int ksz9477_fdb_dump(struct ksz_device *dev, int port, diff --git a/drivers/net/dsa/microchip/ksz9477_i2c.c b/drivers/net/dsa/microchip/ksz9477_i2c.c index 82bebee4615c..7d7560f23a73 100644 --- a/drivers/net/dsa/microchip/ksz9477_i2c.c +++ b/drivers/net/dsa/microchip/ksz9477_i2c.c @@ -72,8 +72,8 @@ static void ksz9477_i2c_shutdown(struct i2c_client *i2c) } static const struct i2c_device_id ksz9477_i2c_id[] = { - { "ksz9477-switch", 0 }, - {}, + { "ksz9477-switch" }, + {} }; MODULE_DEVICE_TABLE(i2c, ksz9477_i2c_id); diff --git a/drivers/net/dsa/microchip/ksz9477_reg.h b/drivers/net/dsa/microchip/ksz9477_reg.h index f3a205ee483f..d5354c600ea1 100644 --- a/drivers/net/dsa/microchip/ksz9477_reg.h +++ b/drivers/net/dsa/microchip/ksz9477_reg.h @@ -247,6 +247,7 @@ #define REG_SW_MAC_CTRL_1 0x0331 #define SW_BACK_PRESSURE BIT(5) +#define SW_BACK_PRESSURE_COLLISION 0 #define FAIR_FLOW_CTRL BIT(4) #define NO_EXC_COLLISION_DROP BIT(3) #define SW_JUMBO_PACKET BIT(2) @@ -842,8 +843,8 @@ #define REG_PORT_STATUS_0 0x0030 -#define PORT_INTF_SPEED_M 0x3 -#define PORT_INTF_SPEED_S 3 +#define PORT_INTF_SPEED_MASK GENMASK(4, 3) +#define PORT_INTF_SPEED_NONE GENMASK(1, 0) #define PORT_INTF_FULL_DUPLEX BIT(2) #define PORT_TX_FLOW_CTRL BIT(1) #define PORT_RX_FLOW_CTRL BIT(0) @@ -1167,6 +1168,11 @@ #define PORT_RMII_CLK_SEL BIT(7) #define PORT_MII_SEL_EDGE BIT(5) +#define REG_PMAVBC 0x03AC + +#define PMAVBC_MASK GENMASK(26, 16) +#define PMAVBC_MIN 0x580 + /* 4 - MAC */ #define REG_PORT_MAC_CTRL_0 0x0400 @@ -1494,6 +1500,7 @@ #define PORT_QM_TX_CNT_USED_S 0 #define PORT_QM_TX_CNT_M (BIT(11) - 1) +#define PORT_QM_TX_CNT_MAX 0x200 #define REG_PORT_QM_TX_CNT_1__4 0x0A14 diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 2818e24e2a51..baa1eeb9a1b0 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -1382,6 +1382,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .tc_cbs_supported = true, .ops = &ksz9477_dev_ops, .phylink_mac_ops = &ksz9477_phylink_mac_ops, + .phy_errata_9477 = true, .mib_names = ksz9477_mib_names, .mib_cnt = ARRAY_SIZE(ksz9477_mib_names), .reg_mib_cnt = MIB_COUNTER_NUM, @@ -1416,6 +1417,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .num_ipms = 8, .ops = &ksz9477_dev_ops, .phylink_mac_ops = &ksz9477_phylink_mac_ops, + .phy_errata_9477 = true, .mib_names = ksz9477_mib_names, .mib_cnt = ARRAY_SIZE(ksz9477_mib_names), .reg_mib_cnt = MIB_COUNTER_NUM, @@ -1450,6 +1452,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .num_ipms = 8, .ops = &ksz9477_dev_ops, .phylink_mac_ops = &ksz9477_phylink_mac_ops, + .phy_errata_9477 = true, .mib_names = ksz9477_mib_names, .mib_cnt = ARRAY_SIZE(ksz9477_mib_names), .reg_mib_cnt = MIB_COUNTER_NUM, @@ -1540,6 +1543,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .tc_cbs_supported = true, .ops = &ksz9477_dev_ops, .phylink_mac_ops = &ksz9477_phylink_mac_ops, + .phy_errata_9477 = true, .mib_names = ksz9477_mib_names, .mib_cnt = ARRAY_SIZE(ksz9477_mib_names), .reg_mib_cnt = MIB_COUNTER_NUM, @@ -1820,6 +1824,7 @@ void ksz_r_mib_stats64(struct ksz_device *dev, int port) struct rtnl_link_stats64 *stats; struct ksz_stats_raw *raw; struct ksz_port_mib *mib; + int ret; mib = &dev->ports[port].mib; stats = &mib->stats64; @@ -1861,6 +1866,12 @@ void ksz_r_mib_stats64(struct ksz_device *dev, int port) pstats->rx_pause_frames = raw->rx_pause; spin_unlock(&mib->stats64_lock); + + if (dev->info->phy_errata_9477) { + ret = ksz9477_errata_monitor(dev, port, raw->tx_late_col); + if (ret) + dev_err(dev->dev, "Failed to monitor transmission halt\n"); + } } void ksz88xx_r_mib_stats64(struct ksz_device *dev, int port) @@ -2185,7 +2196,7 @@ static void ksz_irq_bus_sync_unlock(struct irq_data *d) struct ksz_device *dev = kirq->dev; int ret; - ret = ksz_write32(dev, kirq->reg_mask, kirq->masked); + ret = ksz_write8(dev, kirq->reg_mask, kirq->masked); if (ret) dev_err(dev->dev, "failed to change IRQ mask\n"); @@ -3906,6 +3917,13 @@ static int ksz_hsr_join(struct dsa_switch *ds, int port, struct net_device *hsr, return -EOPNOTSUPP; } + /* KSZ9477 can only perform HSR offloading for up to two ports */ + if (hweight8(dev->hsr_ports) >= 2) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot offload more than two ports - using software HSR"); + return -EOPNOTSUPP; + } + /* Self MAC address filtering, to avoid frames traversing * the HSR ring more than once. */ diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index c784fd23a993..ee7db46e469d 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -66,6 +66,7 @@ struct ksz_chip_data { bool tc_cbs_supported; const struct ksz_dev_ops *ops; const struct phylink_mac_ops *phylink_mac_ops; + bool phy_errata_9477; bool ksz87xx_eee_link_erratum; const struct ksz_mib_names *mib_names; int mib_cnt; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 598434d8d6e4..ec18e68bf3a8 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1302,13 +1302,62 @@ mt7530_stp_state_set(struct dsa_switch *ds, int port, u8 state) FID_PST(FID_BRIDGED, stp_state)); } +static void mt7530_update_port_member(struct mt7530_priv *priv, int port, + const struct net_device *bridge_dev, + bool join) __must_hold(&priv->reg_mutex) +{ + struct dsa_port *dp = dsa_to_port(priv->ds, port), *other_dp; + struct mt7530_port *p = &priv->ports[port], *other_p; + struct dsa_port *cpu_dp = dp->cpu_dp; + u32 port_bitmap = BIT(cpu_dp->index); + int other_port; + bool isolated; + + dsa_switch_for_each_user_port(other_dp, priv->ds) { + other_port = other_dp->index; + other_p = &priv->ports[other_port]; + + if (dp == other_dp) + continue; + + /* Add/remove this port to/from the port matrix of the other + * ports in the same bridge. If the port is disabled, port + * matrix is kept and not being setup until the port becomes + * enabled. + */ + if (!dsa_port_offloads_bridge_dev(other_dp, bridge_dev)) + continue; + + isolated = p->isolated && other_p->isolated; + + if (join && !isolated) { + other_p->pm |= PCR_MATRIX(BIT(port)); + port_bitmap |= BIT(other_port); + } else { + other_p->pm &= ~PCR_MATRIX(BIT(port)); + } + + if (other_p->enable) + mt7530_rmw(priv, MT7530_PCR_P(other_port), + PCR_MATRIX_MASK, other_p->pm); + } + + /* Add/remove the all other ports to this port matrix. For !join + * (leaving the bridge), only the CPU port will remain in the port matrix + * of this port. + */ + p->pm = PCR_MATRIX(port_bitmap); + if (priv->ports[port].enable) + mt7530_rmw(priv, MT7530_PCR_P(port), PCR_MATRIX_MASK, p->pm); +} + static int mt7530_port_pre_bridge_flags(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack) { if (flags.mask & ~(BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD | - BR_BCAST_FLOOD)) + BR_BCAST_FLOOD | BR_ISOLATED)) return -EINVAL; return 0; @@ -1337,6 +1386,17 @@ mt7530_port_bridge_flags(struct dsa_switch *ds, int port, mt7530_rmw(priv, MT753X_MFC, BC_FFP(BIT(port)), flags.val & BR_BCAST_FLOOD ? BC_FFP(BIT(port)) : 0); + if (flags.mask & BR_ISOLATED) { + struct dsa_port *dp = dsa_to_port(ds, port); + struct net_device *bridge_dev = dsa_port_bridge_dev_get(dp); + + priv->ports[port].isolated = !!(flags.val & BR_ISOLATED); + + mutex_lock(&priv->reg_mutex); + mt7530_update_port_member(priv, port, bridge_dev, true); + mutex_unlock(&priv->reg_mutex); + } + return 0; } @@ -1345,39 +1405,11 @@ mt7530_port_bridge_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge, bool *tx_fwd_offload, struct netlink_ext_ack *extack) { - struct dsa_port *dp = dsa_to_port(ds, port), *other_dp; - struct dsa_port *cpu_dp = dp->cpu_dp; - u32 port_bitmap = BIT(cpu_dp->index); struct mt7530_priv *priv = ds->priv; mutex_lock(&priv->reg_mutex); - dsa_switch_for_each_user_port(other_dp, ds) { - int other_port = other_dp->index; - - if (dp == other_dp) - continue; - - /* Add this port to the port matrix of the other ports in the - * same bridge. If the port is disabled, port matrix is kept - * and not being setup until the port becomes enabled. - */ - if (!dsa_port_offloads_bridge(other_dp, &bridge)) - continue; - - if (priv->ports[other_port].enable) - mt7530_set(priv, MT7530_PCR_P(other_port), - PCR_MATRIX(BIT(port))); - priv->ports[other_port].pm |= PCR_MATRIX(BIT(port)); - - port_bitmap |= BIT(other_port); - } - - /* Add the all other ports to this port matrix. */ - if (priv->ports[port].enable) - mt7530_rmw(priv, MT7530_PCR_P(port), - PCR_MATRIX_MASK, PCR_MATRIX(port_bitmap)); - priv->ports[port].pm |= PCR_MATRIX(port_bitmap); + mt7530_update_port_member(priv, port, bridge.dev, true); /* Set to fallback mode for independent VLAN learning */ mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK, @@ -1478,38 +1510,11 @@ static void mt7530_port_bridge_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge) { - struct dsa_port *dp = dsa_to_port(ds, port), *other_dp; - struct dsa_port *cpu_dp = dp->cpu_dp; struct mt7530_priv *priv = ds->priv; mutex_lock(&priv->reg_mutex); - dsa_switch_for_each_user_port(other_dp, ds) { - int other_port = other_dp->index; - - if (dp == other_dp) - continue; - - /* Remove this port from the port matrix of the other ports - * in the same bridge. If the port is disabled, port matrix - * is kept and not being setup until the port becomes enabled. - */ - if (!dsa_port_offloads_bridge(other_dp, &bridge)) - continue; - - if (priv->ports[other_port].enable) - mt7530_clear(priv, MT7530_PCR_P(other_port), - PCR_MATRIX(BIT(port))); - priv->ports[other_port].pm &= ~PCR_MATRIX(BIT(port)); - } - - /* Set the cpu port to be the only one in the port matrix of - * this port. - */ - if (priv->ports[port].enable) - mt7530_rmw(priv, MT7530_PCR_P(port), PCR_MATRIX_MASK, - PCR_MATRIX(BIT(cpu_dp->index))); - priv->ports[port].pm = PCR_MATRIX(BIT(cpu_dp->index)); + mt7530_update_port_member(priv, port, bridge.dev, false); /* When a port is removed from the bridge, the port would be set up * back to the default as is at initial boot which is a VLAN-unaware diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index 2ea4e24628c6..28592123070b 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -721,6 +721,7 @@ struct mt7530_fdb { */ struct mt7530_port { bool enable; + bool isolated; u32 pm; u16 pvid; struct phylink_pcs *sgmii_pcs; diff --git a/drivers/net/dsa/qca/qca8k-common.c b/drivers/net/dsa/qca/qca8k-common.c index 7f80035c5441..560c74c4ac3d 100644 --- a/drivers/net/dsa/qca/qca8k-common.c +++ b/drivers/net/dsa/qca/qca8k-common.c @@ -614,11 +614,57 @@ void qca8k_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) qca8k_port_configure_learning(ds, port, learning); } +static int qca8k_update_port_member(struct qca8k_priv *priv, int port, + const struct net_device *bridge_dev, + bool join) +{ + bool isolated = !!(priv->port_isolated_map & BIT(port)), other_isolated; + struct dsa_port *dp = dsa_to_port(priv->ds, port), *other_dp; + u32 port_mask = BIT(dp->cpu_dp->index); + int i, ret; + + for (i = 0; i < QCA8K_NUM_PORTS; i++) { + if (i == port) + continue; + if (dsa_is_cpu_port(priv->ds, i)) + continue; + + other_dp = dsa_to_port(priv->ds, i); + if (!dsa_port_offloads_bridge_dev(other_dp, bridge_dev)) + continue; + + other_isolated = !!(priv->port_isolated_map & BIT(i)); + + /* Add/remove this port to/from the portvlan mask of the other + * ports in the bridge + */ + if (join && !(isolated && other_isolated)) { + port_mask |= BIT(i); + ret = regmap_set_bits(priv->regmap, + QCA8K_PORT_LOOKUP_CTRL(i), + BIT(port)); + } else { + ret = regmap_clear_bits(priv->regmap, + QCA8K_PORT_LOOKUP_CTRL(i), + BIT(port)); + } + + if (ret) + return ret; + } + + /* Add/remove all other ports to/from this port's portvlan mask */ + ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port), + QCA8K_PORT_LOOKUP_MEMBER, port_mask); + + return ret; +} + int qca8k_port_pre_bridge_flags(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack) { - if (flags.mask & ~BR_LEARNING) + if (flags.mask & ~(BR_LEARNING | BR_ISOLATED)) return -EINVAL; return 0; @@ -628,6 +674,7 @@ int qca8k_port_bridge_flags(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack) { + struct qca8k_priv *priv = ds->priv; int ret; if (flags.mask & BR_LEARNING) { @@ -637,6 +684,20 @@ int qca8k_port_bridge_flags(struct dsa_switch *ds, int port, return ret; } + if (flags.mask & BR_ISOLATED) { + struct dsa_port *dp = dsa_to_port(ds, port); + struct net_device *bridge_dev = dsa_port_bridge_dev_get(dp); + + if (flags.val & BR_ISOLATED) + priv->port_isolated_map |= BIT(port); + else + priv->port_isolated_map &= ~BIT(port); + + ret = qca8k_update_port_member(priv, port, bridge_dev, true); + if (ret) + return ret; + } + return 0; } @@ -646,62 +707,21 @@ int qca8k_port_bridge_join(struct dsa_switch *ds, int port, struct netlink_ext_ack *extack) { struct qca8k_priv *priv = ds->priv; - int port_mask, cpu_port; - int i, ret; - - cpu_port = dsa_to_port(ds, port)->cpu_dp->index; - port_mask = BIT(cpu_port); - - for (i = 0; i < QCA8K_NUM_PORTS; i++) { - if (dsa_is_cpu_port(ds, i)) - continue; - if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) - continue; - /* Add this port to the portvlan mask of the other ports - * in the bridge - */ - ret = regmap_set_bits(priv->regmap, - QCA8K_PORT_LOOKUP_CTRL(i), - BIT(port)); - if (ret) - return ret; - if (i != port) - port_mask |= BIT(i); - } - /* Add all other ports to this ports portvlan mask */ - ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port), - QCA8K_PORT_LOOKUP_MEMBER, port_mask); - - return ret; + return qca8k_update_port_member(priv, port, bridge.dev, true); } void qca8k_port_bridge_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge) { struct qca8k_priv *priv = ds->priv; - int cpu_port, i; - - cpu_port = dsa_to_port(ds, port)->cpu_dp->index; - - for (i = 0; i < QCA8K_NUM_PORTS; i++) { - if (dsa_is_cpu_port(ds, i)) - continue; - if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) - continue; - /* Remove this port to the portvlan mask of the other ports - * in the bridge - */ - regmap_clear_bits(priv->regmap, - QCA8K_PORT_LOOKUP_CTRL(i), - BIT(port)); - } + int err; - /* Set the cpu port to be the only one in the portvlan mask of - * this port - */ - qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port), - QCA8K_PORT_LOOKUP_MEMBER, BIT(cpu_port)); + err = qca8k_update_port_member(priv, port, bridge.dev, false); + if (err) + dev_err(priv->dev, + "Failed to update switch config for bridge leave: %d\n", + err); } void qca8k_port_fast_age(struct dsa_switch *ds, int port) diff --git a/drivers/net/dsa/qca/qca8k-leds.c b/drivers/net/dsa/qca/qca8k-leds.c index 811ebeeff4ed..43ac68052baf 100644 --- a/drivers/net/dsa/qca/qca8k-leds.c +++ b/drivers/net/dsa/qca/qca8k-leds.c @@ -431,8 +431,11 @@ qca8k_parse_port_leds(struct qca8k_priv *priv, struct fwnode_handle *port, int p init_data.devicename = kasprintf(GFP_KERNEL, "%s:0%d", priv->internal_mdio_bus->id, port_num); - if (!init_data.devicename) + if (!init_data.devicename) { + fwnode_handle_put(led); + fwnode_handle_put(leds); return -ENOMEM; + } ret = devm_led_classdev_register_ext(priv->dev, &port_led->cdev, &init_data); if (ret) @@ -441,6 +444,7 @@ qca8k_parse_port_leds(struct qca8k_priv *priv, struct fwnode_handle *port, int p kfree(init_data.devicename); } + fwnode_handle_put(leds); return 0; } @@ -471,9 +475,13 @@ qca8k_setup_led_ctrl(struct qca8k_priv *priv) * the correct port for LED setup. */ ret = qca8k_parse_port_leds(priv, port, qca8k_port_to_phy(port_num)); - if (ret) + if (ret) { + fwnode_handle_put(port); + fwnode_handle_put(ports); return ret; + } } + fwnode_handle_put(ports); return 0; } diff --git a/drivers/net/dsa/qca/qca8k.h b/drivers/net/dsa/qca/qca8k.h index 2184d8d2d5a9..3664a2e2f1f6 100644 --- a/drivers/net/dsa/qca/qca8k.h +++ b/drivers/net/dsa/qca/qca8k.h @@ -451,6 +451,7 @@ struct qca8k_priv { * Bit 1: port enabled. Bit 0: port disabled. */ u8 port_enabled_map; + u8 port_isolated_map; struct qca8k_ports_config ports_config; struct regmap *regmap; struct mii_bus *bus; diff --git a/drivers/net/dsa/xrs700x/xrs700x_i2c.c b/drivers/net/dsa/xrs700x/xrs700x_i2c.c index c1179d7311f7..9b731dea78c1 100644 --- a/drivers/net/dsa/xrs700x/xrs700x_i2c.c +++ b/drivers/net/dsa/xrs700x/xrs700x_i2c.c @@ -127,8 +127,8 @@ static void xrs700x_i2c_shutdown(struct i2c_client *i2c) } static const struct i2c_device_id xrs700x_i2c_id[] = { - { "xrs700x-switch", 0 }, - {}, + { "xrs700x-switch" }, + {} }; MODULE_DEVICE_TABLE(i2c, xrs700x_i2c_id); diff --git a/drivers/net/ethernet/amd/7990.c b/drivers/net/ethernet/amd/7990.c index ef512cf89abf..27792a52b6cf 100644 --- a/drivers/net/ethernet/amd/7990.c +++ b/drivers/net/ethernet/amd/7990.c @@ -667,4 +667,5 @@ void lance_poll(struct net_device *dev) EXPORT_SYMBOL_GPL(lance_poll); #endif +MODULE_DESCRIPTION("LANCE Ethernet IC generic routines"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/amd/a2065.c b/drivers/net/ethernet/amd/a2065.c index 68983b717145..1ca26a8c40eb 100644 --- a/drivers/net/ethernet/amd/a2065.c +++ b/drivers/net/ethernet/amd/a2065.c @@ -781,4 +781,5 @@ static void __exit a2065_cleanup_module(void) module_init(a2065_init_module); module_exit(a2065_cleanup_module); +MODULE_DESCRIPTION("Commodore A2065 Ethernet driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/amd/ariadne.c b/drivers/net/ethernet/amd/ariadne.c index 38153e633231..fa201da567ed 100644 --- a/drivers/net/ethernet/amd/ariadne.c +++ b/drivers/net/ethernet/amd/ariadne.c @@ -790,4 +790,5 @@ static void __exit ariadne_cleanup_module(void) module_init(ariadne_init_module); module_exit(ariadne_cleanup_module); +MODULE_DESCRIPTION("Ariadne Ethernet Driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/amd/atarilance.c b/drivers/net/ethernet/amd/atarilance.c index 751454d305c6..8c8cc7d0f42d 100644 --- a/drivers/net/ethernet/amd/atarilance.c +++ b/drivers/net/ethernet/amd/atarilance.c @@ -79,6 +79,7 @@ static int lance_debug = 1; #endif module_param(lance_debug, int, 0); MODULE_PARM_DESC(lance_debug, "atarilance debug level (0-3)"); +MODULE_DESCRIPTION("Atari LANCE Ethernet driver"); MODULE_LICENSE("GPL"); /* Print debug messages on probing? */ diff --git a/drivers/net/ethernet/amd/hplance.c b/drivers/net/ethernet/amd/hplance.c index 055fda11c572..df42294530cb 100644 --- a/drivers/net/ethernet/amd/hplance.c +++ b/drivers/net/ethernet/amd/hplance.c @@ -234,4 +234,5 @@ static void __exit hplance_cleanup_module(void) module_init(hplance_init_module); module_exit(hplance_cleanup_module); +MODULE_DESCRIPTION("HP300 on-board LANCE Ethernet driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/amd/lance.c b/drivers/net/ethernet/amd/lance.c index 6cf38180cc01..b1e6620ad41d 100644 --- a/drivers/net/ethernet/amd/lance.c +++ b/drivers/net/ethernet/amd/lance.c @@ -385,6 +385,7 @@ static void __exit lance_cleanup_module(void) } module_exit(lance_cleanup_module); #endif /* MODULE */ +MODULE_DESCRIPTION("AMD LANCE/PCnet Ethernet driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/amd/mvme147.c b/drivers/net/ethernet/amd/mvme147.c index 410c7b67eba4..c156566c0906 100644 --- a/drivers/net/ethernet/amd/mvme147.c +++ b/drivers/net/ethernet/amd/mvme147.c @@ -178,6 +178,7 @@ static int m147lance_close(struct net_device *dev) return 0; } +MODULE_DESCRIPTION("MVME147 LANCE Ethernet driver"); MODULE_LICENSE("GPL"); static struct net_device *dev_mvme147_lance; diff --git a/drivers/net/ethernet/amd/sun3lance.c b/drivers/net/ethernet/amd/sun3lance.c index 246f34c43765..c60df4a21158 100644 --- a/drivers/net/ethernet/amd/sun3lance.c +++ b/drivers/net/ethernet/amd/sun3lance.c @@ -74,6 +74,7 @@ static int lance_debug = 1; #endif module_param(lance_debug, int, 0); MODULE_PARM_DESC(lance_debug, "SUN3 Lance debug level (0-3)"); +MODULE_DESCRIPTION("Sun3/Sun3x on-board LANCE Ethernet driver"); MODULE_LICENSE("GPL"); #define DPRINTK(n,a) \ diff --git a/drivers/net/ethernet/arc/Kconfig b/drivers/net/ethernet/arc/Kconfig index 0a67612af228..0d400a7d8d91 100644 --- a/drivers/net/ethernet/arc/Kconfig +++ b/drivers/net/ethernet/arc/Kconfig @@ -23,16 +23,6 @@ config ARC_EMAC_CORE select PHYLIB select CRC32 -config ARC_EMAC - tristate "ARC EMAC support" - select ARC_EMAC_CORE - depends on OF_IRQ - depends on ARC || COMPILE_TEST - help - On some legacy ARC (Synopsys) FPGA boards such as ARCAngel4/ML50x - non-standard on-chip ethernet device ARC EMAC 10/100 is used. - Say Y here if you have such a board. If unsure, say N. - config EMAC_ROCKCHIP tristate "Rockchip EMAC support" select ARC_EMAC_CORE diff --git a/drivers/net/ethernet/arc/Makefile b/drivers/net/ethernet/arc/Makefile index d63ada577c8e..23586eefec44 100644 --- a/drivers/net/ethernet/arc/Makefile +++ b/drivers/net/ethernet/arc/Makefile @@ -5,5 +5,4 @@ arc_emac-objs := emac_main.o emac_mdio.o obj-$(CONFIG_ARC_EMAC_CORE) += arc_emac.o -obj-$(CONFIG_ARC_EMAC) += emac_arc.o obj-$(CONFIG_EMAC_ROCKCHIP) += emac_rockchip.o diff --git a/drivers/net/ethernet/arc/emac_arc.c b/drivers/net/ethernet/arc/emac_arc.c deleted file mode 100644 index a3afddb23ee8..000000000000 --- a/drivers/net/ethernet/arc/emac_arc.c +++ /dev/null @@ -1,88 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/** - * DOC: emac_arc.c - ARC EMAC specific glue layer - * - * Copyright (C) 2014 Romain Perier - * - * Romain Perier <[email protected]> - */ - -#include <linux/etherdevice.h> -#include <linux/module.h> -#include <linux/of_net.h> -#include <linux/platform_device.h> - -#include "emac.h" - -#define DRV_NAME "emac_arc" - -static int emac_arc_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct arc_emac_priv *priv; - phy_interface_t interface; - struct net_device *ndev; - int err; - - if (!dev->of_node) - return -ENODEV; - - ndev = alloc_etherdev(sizeof(struct arc_emac_priv)); - if (!ndev) - return -ENOMEM; - platform_set_drvdata(pdev, ndev); - SET_NETDEV_DEV(ndev, dev); - - priv = netdev_priv(ndev); - priv->drv_name = DRV_NAME; - - err = of_get_phy_mode(dev->of_node, &interface); - if (err) { - if (err == -ENODEV) - interface = PHY_INTERFACE_MODE_MII; - else - goto out_netdev; - } - - priv->clk = devm_clk_get(dev, "hclk"); - if (IS_ERR(priv->clk)) { - dev_err(dev, "failed to retrieve host clock from device tree\n"); - err = -EINVAL; - goto out_netdev; - } - - err = arc_emac_probe(ndev, interface); -out_netdev: - if (err) - free_netdev(ndev); - return err; -} - -static void emac_arc_remove(struct platform_device *pdev) -{ - struct net_device *ndev = platform_get_drvdata(pdev); - - arc_emac_remove(ndev); - free_netdev(ndev); -} - -static const struct of_device_id emac_arc_dt_ids[] = { - { .compatible = "snps,arc-emac" }, - { /* Sentinel */ } -}; -MODULE_DEVICE_TABLE(of, emac_arc_dt_ids); - -static struct platform_driver emac_arc_driver = { - .probe = emac_arc_probe, - .remove_new = emac_arc_remove, - .driver = { - .name = DRV_NAME, - .of_match_table = emac_arc_dt_ids, - }, -}; - -module_platform_driver(emac_arc_driver); - -MODULE_AUTHOR("Romain Perier <[email protected]>"); -MODULE_DESCRIPTION("ARC EMAC platform driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 7dc00c0d8992..1bd0c5973252 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -736,11 +736,6 @@ tx_done: return NETDEV_TX_OK; tx_dma_error: - if (BNXT_TX_PTP_IS_SET(lflags)) { - atomic64_inc(&bp->ptp_cfg->stats.ts_err); - atomic_inc(&bp->ptp_cfg->tx_avail); - } - last_frag = i; /* start back at beginning and unmap skb */ @@ -762,6 +757,10 @@ tx_dma_error: tx_free: dev_kfree_skb_any(skb); tx_kick_pending: + if (BNXT_TX_PTP_IS_SET(lflags)) { + atomic64_inc(&bp->ptp_cfg->stats.ts_err); + atomic_inc(&bp->ptp_cfg->tx_avail); + } if (txr->kick_pending) bnxt_txr_db_kick(bp, txr, txr->tx_prod); txr->tx_buf_ring[txr->tx_prod].skb = NULL; @@ -3317,37 +3316,12 @@ static void bnxt_free_tx_skbs(struct bnxt *bp) } } -static void bnxt_free_one_rx_ring_skbs(struct bnxt *bp, int ring_nr) +static void bnxt_free_one_rx_ring(struct bnxt *bp, struct bnxt_rx_ring_info *rxr) { - struct bnxt_rx_ring_info *rxr = &bp->rx_ring[ring_nr]; struct pci_dev *pdev = bp->pdev; - struct bnxt_tpa_idx_map *map; - int i, max_idx, max_agg_idx; + int i, max_idx; max_idx = bp->rx_nr_pages * RX_DESC_CNT; - max_agg_idx = bp->rx_agg_nr_pages * RX_DESC_CNT; - if (!rxr->rx_tpa) - goto skip_rx_tpa_free; - - for (i = 0; i < bp->max_tpa; i++) { - struct bnxt_tpa_info *tpa_info = &rxr->rx_tpa[i]; - u8 *data = tpa_info->data; - - if (!data) - continue; - - dma_unmap_single_attrs(&pdev->dev, tpa_info->mapping, - bp->rx_buf_use_size, bp->rx_dir, - DMA_ATTR_WEAK_ORDERING); - - tpa_info->data = NULL; - - skb_free_frag(data); - } - -skip_rx_tpa_free: - if (!rxr->rx_buf_ring) - goto skip_rx_buf_free; for (i = 0; i < max_idx; i++) { struct bnxt_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[i]; @@ -3367,12 +3341,15 @@ skip_rx_tpa_free: skb_free_frag(data); } } +} -skip_rx_buf_free: - if (!rxr->rx_agg_ring) - goto skip_rx_agg_free; +static void bnxt_free_one_rx_agg_ring(struct bnxt *bp, struct bnxt_rx_ring_info *rxr) +{ + int i, max_idx; + + max_idx = bp->rx_agg_nr_pages * RX_DESC_CNT; - for (i = 0; i < max_agg_idx; i++) { + for (i = 0; i < max_idx; i++) { struct bnxt_sw_rx_agg_bd *rx_agg_buf = &rxr->rx_agg_ring[i]; struct page *page = rx_agg_buf->page; @@ -3384,6 +3361,45 @@ skip_rx_buf_free: page_pool_recycle_direct(rxr->page_pool, page); } +} + +static void bnxt_free_one_rx_ring_skbs(struct bnxt *bp, int ring_nr) +{ + struct bnxt_rx_ring_info *rxr = &bp->rx_ring[ring_nr]; + struct pci_dev *pdev = bp->pdev; + struct bnxt_tpa_idx_map *map; + int i; + + if (!rxr->rx_tpa) + goto skip_rx_tpa_free; + + for (i = 0; i < bp->max_tpa; i++) { + struct bnxt_tpa_info *tpa_info = &rxr->rx_tpa[i]; + u8 *data = tpa_info->data; + + if (!data) + continue; + + dma_unmap_single_attrs(&pdev->dev, tpa_info->mapping, + bp->rx_buf_use_size, bp->rx_dir, + DMA_ATTR_WEAK_ORDERING); + + tpa_info->data = NULL; + + skb_free_frag(data); + } + +skip_rx_tpa_free: + if (!rxr->rx_buf_ring) + goto skip_rx_buf_free; + + bnxt_free_one_rx_ring(bp, rxr); + +skip_rx_buf_free: + if (!rxr->rx_agg_ring) + goto skip_rx_agg_free; + + bnxt_free_one_rx_agg_ring(bp, rxr); skip_rx_agg_free: map = rxr->rx_tpa_idx_map; @@ -3980,6 +3996,62 @@ static int bnxt_alloc_cp_rings(struct bnxt *bp) return 0; } +static void bnxt_init_rx_ring_struct(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr) +{ + struct bnxt_ring_mem_info *rmem; + struct bnxt_ring_struct *ring; + + ring = &rxr->rx_ring_struct; + rmem = &ring->ring_mem; + rmem->nr_pages = bp->rx_nr_pages; + rmem->page_size = HW_RXBD_RING_SIZE; + rmem->pg_arr = (void **)rxr->rx_desc_ring; + rmem->dma_arr = rxr->rx_desc_mapping; + rmem->vmem_size = SW_RXBD_RING_SIZE * bp->rx_nr_pages; + rmem->vmem = (void **)&rxr->rx_buf_ring; + + ring = &rxr->rx_agg_ring_struct; + rmem = &ring->ring_mem; + rmem->nr_pages = bp->rx_agg_nr_pages; + rmem->page_size = HW_RXBD_RING_SIZE; + rmem->pg_arr = (void **)rxr->rx_agg_desc_ring; + rmem->dma_arr = rxr->rx_agg_desc_mapping; + rmem->vmem_size = SW_RXBD_AGG_RING_SIZE * bp->rx_agg_nr_pages; + rmem->vmem = (void **)&rxr->rx_agg_ring; +} + +static void bnxt_reset_rx_ring_struct(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr) +{ + struct bnxt_ring_mem_info *rmem; + struct bnxt_ring_struct *ring; + int i; + + rxr->page_pool->p.napi = NULL; + rxr->page_pool = NULL; + + ring = &rxr->rx_ring_struct; + rmem = &ring->ring_mem; + rmem->pg_tbl = NULL; + rmem->pg_tbl_map = 0; + for (i = 0; i < rmem->nr_pages; i++) { + rmem->pg_arr[i] = NULL; + rmem->dma_arr[i] = 0; + } + *rmem->vmem = NULL; + + ring = &rxr->rx_agg_ring_struct; + rmem = &ring->ring_mem; + rmem->pg_tbl = NULL; + rmem->pg_tbl_map = 0; + for (i = 0; i < rmem->nr_pages; i++) { + rmem->pg_arr[i] = NULL; + rmem->dma_arr[i] = 0; + } + *rmem->vmem = NULL; +} + static void bnxt_init_ring_struct(struct bnxt *bp) { int i, j; @@ -4062,37 +4134,55 @@ static void bnxt_init_rxbd_pages(struct bnxt_ring_struct *ring, u32 type) } } -static int bnxt_alloc_one_rx_ring(struct bnxt *bp, int ring_nr) +static void bnxt_alloc_one_rx_ring_skb(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr, + int ring_nr) { - struct bnxt_rx_ring_info *rxr = &bp->rx_ring[ring_nr]; - struct net_device *dev = bp->dev; u32 prod; int i; prod = rxr->rx_prod; for (i = 0; i < bp->rx_ring_size; i++) { if (bnxt_alloc_rx_data(bp, rxr, prod, GFP_KERNEL)) { - netdev_warn(dev, "init'ed rx ring %d with %d/%d skbs only\n", + netdev_warn(bp->dev, "init'ed rx ring %d with %d/%d skbs only\n", ring_nr, i, bp->rx_ring_size); break; } prod = NEXT_RX(prod); } rxr->rx_prod = prod; +} - if (!(bp->flags & BNXT_FLAG_AGG_RINGS)) - return 0; +static void bnxt_alloc_one_rx_ring_page(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr, + int ring_nr) +{ + u32 prod; + int i; prod = rxr->rx_agg_prod; for (i = 0; i < bp->rx_agg_ring_size; i++) { if (bnxt_alloc_rx_page(bp, rxr, prod, GFP_KERNEL)) { - netdev_warn(dev, "init'ed rx ring %d with %d/%d pages only\n", + netdev_warn(bp->dev, "init'ed rx ring %d with %d/%d pages only\n", ring_nr, i, bp->rx_ring_size); break; } prod = NEXT_RX_AGG(prod); } rxr->rx_agg_prod = prod; +} + +static int bnxt_alloc_one_rx_ring(struct bnxt *bp, int ring_nr) +{ + struct bnxt_rx_ring_info *rxr = &bp->rx_ring[ring_nr]; + int i; + + bnxt_alloc_one_rx_ring_skb(bp, rxr, ring_nr); + + if (!(bp->flags & BNXT_FLAG_AGG_RINGS)) + return 0; + + bnxt_alloc_one_rx_ring_page(bp, rxr, ring_nr); if (rxr->rx_tpa) { dma_addr_t mapping; @@ -4111,9 +4201,9 @@ static int bnxt_alloc_one_rx_ring(struct bnxt *bp, int ring_nr) return 0; } -static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr) +static void bnxt_init_one_rx_ring_rxbd(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr) { - struct bnxt_rx_ring_info *rxr; struct bnxt_ring_struct *ring; u32 type; @@ -4123,28 +4213,43 @@ static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr) if (NET_IP_ALIGN == 2) type |= RX_BD_FLAGS_SOP; - rxr = &bp->rx_ring[ring_nr]; ring = &rxr->rx_ring_struct; bnxt_init_rxbd_pages(ring, type); - - netif_queue_set_napi(bp->dev, ring_nr, NETDEV_QUEUE_TYPE_RX, - &rxr->bnapi->napi); - - if (BNXT_RX_PAGE_MODE(bp) && bp->xdp_prog) { - bpf_prog_add(bp->xdp_prog, 1); - rxr->xdp_prog = bp->xdp_prog; - } ring->fw_ring_id = INVALID_HW_RING_ID; +} + +static void bnxt_init_one_rx_agg_ring_rxbd(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr) +{ + struct bnxt_ring_struct *ring; + u32 type; ring = &rxr->rx_agg_ring_struct; ring->fw_ring_id = INVALID_HW_RING_ID; - if ((bp->flags & BNXT_FLAG_AGG_RINGS)) { type = ((u32)BNXT_RX_PAGE_SIZE << RX_BD_LEN_SHIFT) | RX_BD_TYPE_RX_AGG_BD | RX_BD_FLAGS_SOP; bnxt_init_rxbd_pages(ring, type); } +} + +static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr) +{ + struct bnxt_rx_ring_info *rxr; + + rxr = &bp->rx_ring[ring_nr]; + bnxt_init_one_rx_ring_rxbd(bp, rxr); + + netif_queue_set_napi(bp->dev, ring_nr, NETDEV_QUEUE_TYPE_RX, + &rxr->bnapi->napi); + + if (BNXT_RX_PAGE_MODE(bp) && bp->xdp_prog) { + bpf_prog_add(bp->xdp_prog, 1); + rxr->xdp_prog = bp->xdp_prog; + } + + bnxt_init_one_rx_agg_ring_rxbd(bp, rxr); return bnxt_alloc_one_rx_ring(bp, ring_nr); } @@ -6869,6 +6974,48 @@ static void bnxt_set_db(struct bnxt *bp, struct bnxt_db_info *db, u32 ring_type, bnxt_set_db_mask(bp, db, ring_type); } +static int bnxt_hwrm_rx_ring_alloc(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr) +{ + struct bnxt_ring_struct *ring = &rxr->rx_ring_struct; + struct bnxt_napi *bnapi = rxr->bnapi; + u32 type = HWRM_RING_ALLOC_RX; + u32 map_idx = bnapi->index; + int rc; + + rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx); + if (rc) + return rc; + + bnxt_set_db(bp, &rxr->rx_db, type, map_idx, ring->fw_ring_id); + bp->grp_info[map_idx].rx_fw_ring_id = ring->fw_ring_id; + + return 0; +} + +static int bnxt_hwrm_rx_agg_ring_alloc(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr) +{ + struct bnxt_ring_struct *ring = &rxr->rx_agg_ring_struct; + u32 type = HWRM_RING_ALLOC_AGG; + u32 grp_idx = ring->grp_idx; + u32 map_idx; + int rc; + + map_idx = grp_idx + bp->rx_nr_rings; + rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx); + if (rc) + return rc; + + bnxt_set_db(bp, &rxr->rx_agg_db, type, map_idx, + ring->fw_ring_id); + bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod); + bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod); + bp->grp_info[grp_idx].agg_fw_ring_id = ring->fw_ring_id; + + return 0; +} + static int bnxt_hwrm_ring_alloc(struct bnxt *bp) { bool agg_rings = !!(bp->flags & BNXT_FLAG_AGG_RINGS); @@ -6934,24 +7081,21 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp) bnxt_set_db(bp, &txr->tx_db, type, map_idx, ring->fw_ring_id); } - type = HWRM_RING_ALLOC_RX; for (i = 0; i < bp->rx_nr_rings; i++) { struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; - struct bnxt_ring_struct *ring = &rxr->rx_ring_struct; - struct bnxt_napi *bnapi = rxr->bnapi; - u32 map_idx = bnapi->index; - rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx); + rc = bnxt_hwrm_rx_ring_alloc(bp, rxr); if (rc) goto err_out; - bnxt_set_db(bp, &rxr->rx_db, type, map_idx, ring->fw_ring_id); /* If we have agg rings, post agg buffers first. */ if (!agg_rings) bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod); - bp->grp_info[map_idx].rx_fw_ring_id = ring->fw_ring_id; if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { struct bnxt_cp_ring_info *cpr2 = rxr->rx_cpr; + struct bnxt_napi *bnapi = rxr->bnapi; u32 type2 = HWRM_RING_ALLOC_CMPL; + struct bnxt_ring_struct *ring; + u32 map_idx = bnapi->index; ring = &cpr2->cp_ring_struct; ring->handle = BNXT_SET_NQ_HDL(cpr2); @@ -6965,23 +7109,10 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp) } if (agg_rings) { - type = HWRM_RING_ALLOC_AGG; for (i = 0; i < bp->rx_nr_rings; i++) { - struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; - struct bnxt_ring_struct *ring = - &rxr->rx_agg_ring_struct; - u32 grp_idx = ring->grp_idx; - u32 map_idx = grp_idx + bp->rx_nr_rings; - - rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx); + rc = bnxt_hwrm_rx_agg_ring_alloc(bp, &bp->rx_ring[i]); if (rc) goto err_out; - - bnxt_set_db(bp, &rxr->rx_agg_db, type, map_idx, - ring->fw_ring_id); - bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod); - bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod); - bp->grp_info[grp_idx].agg_fw_ring_id = ring->fw_ring_id; } } err_out: @@ -7021,6 +7152,50 @@ exit: return 0; } +static void bnxt_hwrm_rx_ring_free(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr, + bool close_path) +{ + struct bnxt_ring_struct *ring = &rxr->rx_ring_struct; + u32 grp_idx = rxr->bnapi->index; + u32 cmpl_ring_id; + + if (ring->fw_ring_id == INVALID_HW_RING_ID) + return; + + cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr); + hwrm_ring_free_send_msg(bp, ring, + RING_FREE_REQ_RING_TYPE_RX, + close_path ? cmpl_ring_id : + INVALID_HW_RING_ID); + ring->fw_ring_id = INVALID_HW_RING_ID; + bp->grp_info[grp_idx].rx_fw_ring_id = INVALID_HW_RING_ID; +} + +static void bnxt_hwrm_rx_agg_ring_free(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr, + bool close_path) +{ + struct bnxt_ring_struct *ring = &rxr->rx_agg_ring_struct; + u32 grp_idx = rxr->bnapi->index; + u32 type, cmpl_ring_id; + + if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) + type = RING_FREE_REQ_RING_TYPE_RX_AGG; + else + type = RING_FREE_REQ_RING_TYPE_RX; + + if (ring->fw_ring_id == INVALID_HW_RING_ID) + return; + + cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr); + hwrm_ring_free_send_msg(bp, ring, type, + close_path ? cmpl_ring_id : + INVALID_HW_RING_ID); + ring->fw_ring_id = INVALID_HW_RING_ID; + bp->grp_info[grp_idx].agg_fw_ring_id = INVALID_HW_RING_ID; +} + static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path) { u32 type; @@ -7045,42 +7220,8 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path) } for (i = 0; i < bp->rx_nr_rings; i++) { - struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; - struct bnxt_ring_struct *ring = &rxr->rx_ring_struct; - u32 grp_idx = rxr->bnapi->index; - - if (ring->fw_ring_id != INVALID_HW_RING_ID) { - u32 cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr); - - hwrm_ring_free_send_msg(bp, ring, - RING_FREE_REQ_RING_TYPE_RX, - close_path ? cmpl_ring_id : - INVALID_HW_RING_ID); - ring->fw_ring_id = INVALID_HW_RING_ID; - bp->grp_info[grp_idx].rx_fw_ring_id = - INVALID_HW_RING_ID; - } - } - - if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) - type = RING_FREE_REQ_RING_TYPE_RX_AGG; - else - type = RING_FREE_REQ_RING_TYPE_RX; - for (i = 0; i < bp->rx_nr_rings; i++) { - struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; - struct bnxt_ring_struct *ring = &rxr->rx_agg_ring_struct; - u32 grp_idx = rxr->bnapi->index; - - if (ring->fw_ring_id != INVALID_HW_RING_ID) { - u32 cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr); - - hwrm_ring_free_send_msg(bp, ring, type, - close_path ? cmpl_ring_id : - INVALID_HW_RING_ID); - ring->fw_ring_id = INVALID_HW_RING_ID; - bp->grp_info[grp_idx].agg_fw_ring_id = - INVALID_HW_RING_ID; - } + bnxt_hwrm_rx_ring_free(bp, &bp->rx_ring[i], close_path); + bnxt_hwrm_rx_agg_ring_free(bp, &bp->rx_ring[i], close_path); } /* The completion rings are about to be freed. After that the @@ -9004,6 +9145,7 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp) memcpy(vf->mac_addr, resp->mac_address, ETH_ALEN); #endif } + bp->tso_max_segs = le16_to_cpu(resp->max_tso_segs); hwrm_func_qcaps_exit: hwrm_req_drop(bp, req); @@ -14828,6 +14970,224 @@ static const struct netdev_stat_ops bnxt_stat_ops = { .get_base_stats = bnxt_get_base_stats, }; +static int bnxt_alloc_rx_agg_bmap(struct bnxt *bp, struct bnxt_rx_ring_info *rxr) +{ + u16 mem_size; + + rxr->rx_agg_bmap_size = bp->rx_agg_ring_mask + 1; + mem_size = rxr->rx_agg_bmap_size / 8; + rxr->rx_agg_bmap = kzalloc(mem_size, GFP_KERNEL); + if (!rxr->rx_agg_bmap) + return -ENOMEM; + + return 0; +} + +static int bnxt_queue_mem_alloc(struct net_device *dev, void *qmem, int idx) +{ + struct bnxt_rx_ring_info *rxr, *clone; + struct bnxt *bp = netdev_priv(dev); + struct bnxt_ring_struct *ring; + int rc; + + rxr = &bp->rx_ring[idx]; + clone = qmem; + memcpy(clone, rxr, sizeof(*rxr)); + bnxt_init_rx_ring_struct(bp, clone); + bnxt_reset_rx_ring_struct(bp, clone); + + clone->rx_prod = 0; + clone->rx_agg_prod = 0; + clone->rx_sw_agg_prod = 0; + clone->rx_next_cons = 0; + + rc = bnxt_alloc_rx_page_pool(bp, clone, rxr->page_pool->p.nid); + if (rc) + return rc; + + ring = &clone->rx_ring_struct; + rc = bnxt_alloc_ring(bp, &ring->ring_mem); + if (rc) + goto err_free_rx_ring; + + if (bp->flags & BNXT_FLAG_AGG_RINGS) { + ring = &clone->rx_agg_ring_struct; + rc = bnxt_alloc_ring(bp, &ring->ring_mem); + if (rc) + goto err_free_rx_agg_ring; + + rc = bnxt_alloc_rx_agg_bmap(bp, clone); + if (rc) + goto err_free_rx_agg_ring; + } + + bnxt_init_one_rx_ring_rxbd(bp, clone); + bnxt_init_one_rx_agg_ring_rxbd(bp, clone); + + bnxt_alloc_one_rx_ring_skb(bp, clone, idx); + if (bp->flags & BNXT_FLAG_AGG_RINGS) + bnxt_alloc_one_rx_ring_page(bp, clone, idx); + + return 0; + +err_free_rx_agg_ring: + bnxt_free_ring(bp, &clone->rx_agg_ring_struct.ring_mem); +err_free_rx_ring: + bnxt_free_ring(bp, &clone->rx_ring_struct.ring_mem); + clone->page_pool->p.napi = NULL; + page_pool_destroy(clone->page_pool); + clone->page_pool = NULL; + return rc; +} + +static void bnxt_queue_mem_free(struct net_device *dev, void *qmem) +{ + struct bnxt_rx_ring_info *rxr = qmem; + struct bnxt *bp = netdev_priv(dev); + struct bnxt_ring_struct *ring; + + bnxt_free_one_rx_ring(bp, rxr); + bnxt_free_one_rx_agg_ring(bp, rxr); + + /* At this point, this NAPI instance has another page pool associated + * with it. Disconnect here before freeing the old page pool to avoid + * warnings. + */ + rxr->page_pool->p.napi = NULL; + page_pool_destroy(rxr->page_pool); + rxr->page_pool = NULL; + + ring = &rxr->rx_ring_struct; + bnxt_free_ring(bp, &ring->ring_mem); + + ring = &rxr->rx_agg_ring_struct; + bnxt_free_ring(bp, &ring->ring_mem); + + kfree(rxr->rx_agg_bmap); + rxr->rx_agg_bmap = NULL; +} + +static void bnxt_copy_rx_ring(struct bnxt *bp, + struct bnxt_rx_ring_info *dst, + struct bnxt_rx_ring_info *src) +{ + struct bnxt_ring_mem_info *dst_rmem, *src_rmem; + struct bnxt_ring_struct *dst_ring, *src_ring; + int i; + + dst_ring = &dst->rx_ring_struct; + dst_rmem = &dst_ring->ring_mem; + src_ring = &src->rx_ring_struct; + src_rmem = &src_ring->ring_mem; + + WARN_ON(dst_rmem->nr_pages != src_rmem->nr_pages); + WARN_ON(dst_rmem->page_size != src_rmem->page_size); + WARN_ON(dst_rmem->flags != src_rmem->flags); + WARN_ON(dst_rmem->depth != src_rmem->depth); + WARN_ON(dst_rmem->vmem_size != src_rmem->vmem_size); + WARN_ON(dst_rmem->ctx_mem != src_rmem->ctx_mem); + + dst_rmem->pg_tbl = src_rmem->pg_tbl; + dst_rmem->pg_tbl_map = src_rmem->pg_tbl_map; + *dst_rmem->vmem = *src_rmem->vmem; + for (i = 0; i < dst_rmem->nr_pages; i++) { + dst_rmem->pg_arr[i] = src_rmem->pg_arr[i]; + dst_rmem->dma_arr[i] = src_rmem->dma_arr[i]; + } + + if (!(bp->flags & BNXT_FLAG_AGG_RINGS)) + return; + + dst_ring = &dst->rx_agg_ring_struct; + dst_rmem = &dst_ring->ring_mem; + src_ring = &src->rx_agg_ring_struct; + src_rmem = &src_ring->ring_mem; + + WARN_ON(dst_rmem->nr_pages != src_rmem->nr_pages); + WARN_ON(dst_rmem->page_size != src_rmem->page_size); + WARN_ON(dst_rmem->flags != src_rmem->flags); + WARN_ON(dst_rmem->depth != src_rmem->depth); + WARN_ON(dst_rmem->vmem_size != src_rmem->vmem_size); + WARN_ON(dst_rmem->ctx_mem != src_rmem->ctx_mem); + WARN_ON(dst->rx_agg_bmap_size != src->rx_agg_bmap_size); + + dst_rmem->pg_tbl = src_rmem->pg_tbl; + dst_rmem->pg_tbl_map = src_rmem->pg_tbl_map; + *dst_rmem->vmem = *src_rmem->vmem; + for (i = 0; i < dst_rmem->nr_pages; i++) { + dst_rmem->pg_arr[i] = src_rmem->pg_arr[i]; + dst_rmem->dma_arr[i] = src_rmem->dma_arr[i]; + } + + dst->rx_agg_bmap = src->rx_agg_bmap; +} + +static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx) +{ + struct bnxt *bp = netdev_priv(dev); + struct bnxt_rx_ring_info *rxr, *clone; + struct bnxt_cp_ring_info *cpr; + int rc; + + rxr = &bp->rx_ring[idx]; + clone = qmem; + + rxr->rx_prod = clone->rx_prod; + rxr->rx_agg_prod = clone->rx_agg_prod; + rxr->rx_sw_agg_prod = clone->rx_sw_agg_prod; + rxr->rx_next_cons = clone->rx_next_cons; + rxr->page_pool = clone->page_pool; + + bnxt_copy_rx_ring(bp, rxr, clone); + + rc = bnxt_hwrm_rx_ring_alloc(bp, rxr); + if (rc) + return rc; + rc = bnxt_hwrm_rx_agg_ring_alloc(bp, rxr); + if (rc) + goto err_free_hwrm_rx_ring; + + bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod); + if (bp->flags & BNXT_FLAG_AGG_RINGS) + bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod); + + napi_enable(&rxr->bnapi->napi); + + cpr = &rxr->bnapi->cp_ring; + cpr->sw_stats->rx.rx_resets++; + + return 0; + +err_free_hwrm_rx_ring: + bnxt_hwrm_rx_ring_free(bp, rxr, false); + return rc; +} + +static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx) +{ + struct bnxt *bp = netdev_priv(dev); + struct bnxt_rx_ring_info *rxr; + + rxr = &bp->rx_ring[idx]; + napi_disable(&rxr->bnapi->napi); + bnxt_hwrm_rx_ring_free(bp, rxr, false); + bnxt_hwrm_rx_agg_ring_free(bp, rxr, false); + rxr->rx_next_cons = 0; + + memcpy(qmem, rxr, sizeof(*rxr)); + bnxt_init_rx_ring_struct(bp, qmem); + + return 0; +} + +static const struct netdev_queue_mgmt_ops bnxt_queue_mgmt_ops = { + .ndo_queue_mem_size = sizeof(struct bnxt_rx_ring_info), + .ndo_queue_mem_alloc = bnxt_queue_mem_alloc, + .ndo_queue_mem_free = bnxt_queue_mem_free, + .ndo_queue_start = bnxt_queue_start, + .ndo_queue_stop = bnxt_queue_stop, +}; + static void bnxt_remove_one(struct pci_dev *pdev) { struct net_device *dev = pci_get_drvdata(pdev); @@ -15293,6 +15653,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->stat_ops = &bnxt_stat_ops; dev->watchdog_timeo = BNXT_TX_TIMEOUT; dev->ethtool_ops = &bnxt_ethtool_ops; + dev->queue_mgmt_ops = &bnxt_queue_mgmt_ops; pci_set_drvdata(pdev, dev); rc = bnxt_alloc_hwrm_resources(bp); @@ -15371,6 +15732,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->priv_flags |= IFF_UNICAST_FLT; netif_set_tso_max_size(dev, GSO_MAX_SIZE); + if (bp->tso_max_segs) + netif_set_tso_max_segs(dev, bp->tso_max_segs); dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_RX_SG; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 656ab81c0272..9cf0acfa04e5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1434,6 +1434,57 @@ struct bnxt_l2_filter { atomic_t refcnt; }; +/* Compat version of hwrm_port_phy_qcfg_output capped at 96 bytes. The + * first 95 bytes are identical to hwrm_port_phy_qcfg_output in bnxt_hsi.h. + * The last valid byte in the compat version is different. + */ +struct hwrm_port_phy_qcfg_output_compat { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 link; + u8 active_fec_signal_mode; + __le16 link_speed; + u8 duplex_cfg; + u8 pause; + __le16 support_speeds; + __le16 force_link_speed; + u8 auto_mode; + u8 auto_pause; + __le16 auto_link_speed; + __le16 auto_link_speed_mask; + u8 wirespeed; + u8 lpbk; + u8 force_pause; + u8 module_status; + __le32 preemphasis; + u8 phy_maj; + u8 phy_min; + u8 phy_bld; + u8 phy_type; + u8 media_type; + u8 xcvr_pkg_type; + u8 eee_config_phy_addr; + u8 parallel_detect; + __le16 link_partner_adv_speeds; + u8 link_partner_adv_auto_mode; + u8 link_partner_adv_pause; + __le16 adv_eee_link_speed_mask; + __le16 link_partner_adv_eee_link_speed_mask; + __le32 xcvr_identifier_type_tx_lpi_timer; + __le16 fec_cfg; + u8 duplex_state; + u8 option_flags; + char phy_vendor_name[16]; + char phy_vendor_partnumber[16]; + __le16 support_pam4_speeds; + __le16 force_pam4_link_speed; + __le16 auto_pam4_link_speed_mask; + u8 link_partner_pam4_adv_speeds; + u8 valid; +}; + struct bnxt_link_info { u8 phy_type; u8 media_type; @@ -2267,6 +2318,7 @@ struct bnxt { u8 rss_hash_key_updated:1; u16 max_mtu; + u16 tso_max_segs; u8 max_tc; u8 max_lltc; /* lossless TCs */ struct bnxt_queue_info q_info[BNXT_MAX_QUEUE]; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index 06ea86c80be1..f219709f9563 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -2,7 +2,7 @@ * * Copyright (c) 2014-2016 Broadcom Corporation * Copyright (c) 2014-2018 Broadcom Limited - * Copyright (c) 2018-2023 Broadcom Inc. + * Copyright (c) 2018-2024 Broadcom Inc. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -500,7 +500,11 @@ struct cmd_nums { #define HWRM_TFC_IF_TBL_GET 0x399UL #define HWRM_TFC_TBL_SCOPE_CONFIG_GET 0x39aUL #define HWRM_TFC_RESC_USAGE_QUERY 0x39bUL + #define HWRM_QUEUE_PFCWD_TIMEOUT_QCAPS 0x39cUL + #define HWRM_QUEUE_PFCWD_TIMEOUT_CFG 0x39dUL + #define HWRM_QUEUE_PFCWD_TIMEOUT_QCFG 0x39eUL #define HWRM_SV 0x400UL + #define HWRM_DBG_LOG_BUFFER_FLUSH 0xff0fUL #define HWRM_DBG_READ_DIRECT 0xff10UL #define HWRM_DBG_READ_INDIRECT 0xff11UL #define HWRM_DBG_WRITE_DIRECT 0xff12UL @@ -609,8 +613,8 @@ struct hwrm_err_output { #define HWRM_VERSION_MAJOR 1 #define HWRM_VERSION_MINOR 10 #define HWRM_VERSION_UPDATE 3 -#define HWRM_VERSION_RSVD 39 -#define HWRM_VERSION_STR "1.10.3.39" +#define HWRM_VERSION_RSVD 44 +#define HWRM_VERSION_STR "1.10.3.44" /* hwrm_ver_get_input (size:192b/24B) */ struct hwrm_ver_get_input { @@ -664,6 +668,7 @@ struct hwrm_ver_get_output { #define VER_GET_RESP_DEV_CAPS_CFG_CFA_TFLIB_SUPPORTED 0x2000UL #define VER_GET_RESP_DEV_CAPS_CFG_CFA_TRUFLOW_SUPPORTED 0x4000UL #define VER_GET_RESP_DEV_CAPS_CFG_SECURE_BOOT_CAPABLE 0x8000UL + #define VER_GET_RESP_DEV_CAPS_CFG_SECURE_SOC_CAPABLE 0x10000UL u8 roce_fw_maj_8b; u8 roce_fw_min_8b; u8 roce_fw_bld_8b; @@ -843,7 +848,9 @@ struct hwrm_async_event_cmpl { #define ASYNC_EVENT_CMPL_EVENT_ID_HW_DOORBELL_RECOVERY_READ_ERROR 0x49UL #define ASYNC_EVENT_CMPL_EVENT_ID_CTX_ERROR 0x4aUL #define ASYNC_EVENT_CMPL_EVENT_ID_UDCC_SESSION_CHANGE 0x4bUL - #define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID 0x4cUL + #define ASYNC_EVENT_CMPL_EVENT_ID_DBG_BUF_PRODUCER 0x4cUL + #define ASYNC_EVENT_CMPL_EVENT_ID_PEER_MMAP_CHANGE 0x4dUL + #define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID 0x4eUL #define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG 0xfeUL #define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR 0xffUL #define ASYNC_EVENT_CMPL_EVENT_ID_LAST ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR @@ -1326,13 +1333,13 @@ struct hwrm_async_event_cmpl_error_report_base { u8 timestamp_lo; __le16 timestamp_hi; __le32 event_data1; - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_MASK 0xffUL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_SFT 0 - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_RESERVED 0x0UL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM 0x1UL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL 0x2UL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_NVM 0x3UL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD 0x4UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_MASK 0xffUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_RESERVED 0x0UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM 0x1UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL 0x2UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_NVM 0x3UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD 0x4UL #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_THERMAL_THRESHOLD 0x5UL #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED 0x6UL #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED @@ -1814,6 +1821,9 @@ struct hwrm_func_qcaps_output { #define FUNC_QCAPS_RESP_FLAGS_EXT2_SW_MAX_RESOURCE_LIMITS_SUPPORTED 0x800000UL #define FUNC_QCAPS_RESP_FLAGS_EXT2_TF_INGRESS_NIC_FLOW_SUPPORTED 0x1000000UL #define FUNC_QCAPS_RESP_FLAGS_EXT2_LPBK_STATS_SUPPORTED 0x2000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT2_TF_EGRESS_NIC_FLOW_SUPPORTED 0x4000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT2_MULTI_LOSSLESS_QUEUES_SUPPORTED 0x8000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT2_PEER_MMAP_SUPPORTED 0x10000000UL __le16 tunnel_disable_flag; #define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_VXLAN 0x1UL #define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_NGE 0x2UL @@ -1828,7 +1838,7 @@ struct hwrm_func_qcaps_output { #define FUNC_QCAPS_RESP_XID_PARTITION_CAP_RX_CK 0x2UL u8 device_serial_number[8]; __le16 ctxs_per_partition; - u8 unused_2[2]; + __le16 max_tso_segs; __le32 roce_vf_max_av; __le32 roce_vf_max_cq; __le32 roce_vf_max_mrw; @@ -2449,6 +2459,7 @@ struct hwrm_func_drv_rgtr_input { #define FUNC_DRV_RGTR_REQ_FLAGS_NPAR_1_2_SUPPORT 0x200UL #define FUNC_DRV_RGTR_REQ_FLAGS_ASYM_QUEUE_CFG_SUPPORT 0x400UL #define FUNC_DRV_RGTR_REQ_FLAGS_TF_INGRESS_NIC_FLOW_MODE 0x800UL + #define FUNC_DRV_RGTR_REQ_FLAGS_TF_EGRESS_NIC_FLOW_MODE 0x1000UL __le32 enables; #define FUNC_DRV_RGTR_REQ_ENABLES_OS_TYPE 0x1UL #define FUNC_DRV_RGTR_REQ_ENABLES_VER 0x2UL @@ -3660,22 +3671,24 @@ struct hwrm_func_backing_store_cfg_v2_input { __le16 target_id; __le64 resp_addr; __le16 type; - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_QP 0x0UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ 0x1UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ 0x2UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_VNIC 0x3UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_STAT 0x4UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SP_TQM_RING 0x5UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_FP_TQM_RING 0x6UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MRAV 0xeUL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TIM 0xfUL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MP_TQM_RING 0x15UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SQ_DB_SHADOW 0x16UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RQ_DB_SHADOW 0x17UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ_DB_SHADOW 0x18UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ_DB_SHADOW 0x19UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TBL_SCOPE 0x1cUL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_XID_PARTITION 0x1dUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TX_CK 0x13UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RX_CK 0x14UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SQ_DB_SHADOW 0x16UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RQ_DB_SHADOW 0x17UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ_DB_SHADOW 0x18UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ_DB_SHADOW 0x19UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TBL_SCOPE 0x1cUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_XID_PARTITION 0x1dUL #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT_TRACE 0x1eUL #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT2_TRACE 0x1fUL #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT_TRACE 0x20UL @@ -3772,18 +3785,20 @@ struct hwrm_func_backing_store_qcfg_v2_output { __le16 seq_id; __le16 resp_len; __le16 type; - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_QP 0x0UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRQ 0x1UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CQ 0x2UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_VNIC 0x3UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_STAT 0x4UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SP_TQM_RING 0x5UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_FP_TQM_RING 0x6UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MRAV 0xeUL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TIM 0xfUL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MP_TQM_RING 0x15UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TBL_SCOPE 0x1cUL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_XID_PARTITION 0x1dUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TX_CK 0x13UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RX_CK 0x14UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TBL_SCOPE 0x1cUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_XID_PARTITION 0x1dUL #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT_TRACE 0x1eUL #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT2_TRACE 0x1fUL #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT_TRACE 0x20UL @@ -3876,22 +3891,24 @@ struct hwrm_func_backing_store_qcaps_v2_input { __le16 target_id; __le64 resp_addr; __le16 type; - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QP 0x0UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ 0x1UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ 0x2UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_VNIC 0x3UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_STAT 0x4UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SP_TQM_RING 0x5UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING 0x6UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV 0xeUL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM 0xfUL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING 0x15UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SQ_DB_SHADOW 0x16UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RQ_DB_SHADOW 0x17UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ_DB_SHADOW 0x18UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ_DB_SHADOW 0x19UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TBL_SCOPE 0x1cUL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_XID_PARTITION 0x1dUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TX_CK 0x13UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RX_CK 0x14UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SQ_DB_SHADOW 0x16UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RQ_DB_SHADOW 0x17UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ_DB_SHADOW 0x18UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ_DB_SHADOW 0x19UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TBL_SCOPE 0x1cUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_XID_PARTITION 0x1dUL #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT_TRACE 0x1eUL #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT2_TRACE 0x1fUL #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT_TRACE 0x20UL @@ -3911,22 +3928,24 @@ struct hwrm_func_backing_store_qcaps_v2_output { __le16 seq_id; __le16 resp_len; __le16 type; - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_QP 0x0UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ 0x1UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ 0x2UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_VNIC 0x3UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_STAT 0x4UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SP_TQM_RING 0x5UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_FP_TQM_RING 0x6UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MRAV 0xeUL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TIM 0xfUL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MP_TQM_RING 0x15UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SQ_DB_SHADOW 0x16UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RQ_DB_SHADOW 0x17UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ_DB_SHADOW 0x18UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ_DB_SHADOW 0x19UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TBL_SCOPE 0x1cUL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_XID_PARTITION 0x1dUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TX_CK 0x13UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RX_CK 0x14UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SQ_DB_SHADOW 0x16UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RQ_DB_SHADOW 0x17UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ_DB_SHADOW 0x18UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ_DB_SHADOW 0x19UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TBL_SCOPE 0x1cUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_XID_PARTITION 0x1dUL #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT_TRACE 0x1eUL #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT2_TRACE 0x1fUL #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT_TRACE 0x20UL @@ -4202,7 +4221,8 @@ struct hwrm_port_phy_cfg_input { #define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB_PAM4_112 0x3eaUL #define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_200GB_PAM4_112 0x7d2UL #define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_112 0xfa2UL - #define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_LAST PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_112 + #define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_800GB_PAM4_112 0x1f42UL + #define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_LAST PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_800GB_PAM4_112 __le16 auto_link_speeds2_mask; #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_1GB 0x1UL #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_10GB 0x2UL @@ -4217,6 +4237,7 @@ struct hwrm_port_phy_cfg_input { #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_100GB_PAM4_112 0x400UL #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_200GB_PAM4_112 0x800UL #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_400GB_PAM4_112 0x1000UL + #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_800GB_PAM4_112 0x2000UL u8 unused_2[6]; }; @@ -4292,6 +4313,7 @@ struct hwrm_port_phy_qcfg_output { #define PORT_PHY_QCFG_RESP_LINK_SPEED_100GB 0x3e8UL #define PORT_PHY_QCFG_RESP_LINK_SPEED_200GB 0x7d0UL #define PORT_PHY_QCFG_RESP_LINK_SPEED_400GB 0xfa0UL + #define PORT_PHY_QCFG_RESP_LINK_SPEED_800GB 0x1f40UL #define PORT_PHY_QCFG_RESP_LINK_SPEED_10MB 0xffffUL #define PORT_PHY_QCFG_RESP_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_LINK_SPEED_10MB u8 duplex_cfg; @@ -4451,7 +4473,13 @@ struct hwrm_port_phy_qcfg_output { #define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASESR4 0x35UL #define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASELR4 0x36UL #define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER4 0x37UL - #define PORT_PHY_QCFG_RESP_PHY_TYPE_LAST PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER4 + #define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASECR8 0x38UL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASESR8 0x39UL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASELR8 0x3aUL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEER8 0x3bUL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEFR8 0x3cUL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEDR8 0x3dUL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_LAST PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEDR8 u8 media_type; #define PORT_PHY_QCFG_RESP_MEDIA_TYPE_UNKNOWN 0x0UL #define PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP 0x1UL @@ -5049,33 +5077,43 @@ struct hwrm_port_qstats_ext_output { u8 valid; }; -/* hwrm_port_lpbk_qstats_input (size:128b/16B) */ +/* hwrm_port_lpbk_qstats_input (size:256b/32B) */ struct hwrm_port_lpbk_qstats_input { __le16 req_type; __le16 cmpl_ring; __le16 seq_id; __le16 target_id; __le64 resp_addr; + __le16 lpbk_stat_size; + u8 flags; + #define PORT_LPBK_QSTATS_REQ_FLAGS_COUNTER_MASK 0x1UL + u8 unused_0[5]; + __le64 lpbk_stat_host_addr; }; -/* hwrm_port_lpbk_qstats_output (size:768b/96B) */ +/* hwrm_port_lpbk_qstats_output (size:128b/16B) */ struct hwrm_port_lpbk_qstats_output { __le16 error_code; __le16 req_type; __le16 seq_id; __le16 resp_len; + __le16 lpbk_stat_size; + u8 unused_0[5]; + u8 valid; +}; + +/* port_lpbk_stats (size:640b/80B) */ +struct port_lpbk_stats { __le64 lpbk_ucast_frames; __le64 lpbk_mcast_frames; __le64 lpbk_bcast_frames; __le64 lpbk_ucast_bytes; __le64 lpbk_mcast_bytes; __le64 lpbk_bcast_bytes; - __le64 tx_stat_discard; - __le64 tx_stat_error; - __le64 rx_stat_discard; - __le64 rx_stat_error; - u8 unused_0[7]; - u8 valid; + __le64 lpbk_tx_discards; + __le64 lpbk_tx_errors; + __le64 lpbk_rx_discards; + __le64 lpbk_rx_errors; }; /* hwrm_port_ecn_qstats_input (size:256b/32B) */ @@ -5140,13 +5178,15 @@ struct hwrm_port_clr_stats_output { u8 valid; }; -/* hwrm_port_lpbk_clr_stats_input (size:128b/16B) */ +/* hwrm_port_lpbk_clr_stats_input (size:192b/24B) */ struct hwrm_port_lpbk_clr_stats_input { __le16 req_type; __le16 cmpl_ring; __le16 seq_id; __le16 target_id; __le64 resp_addr; + __le16 port_id; + u8 unused_0[6]; }; /* hwrm_port_lpbk_clr_stats_output (size:128b/16B) */ @@ -5287,10 +5327,11 @@ struct hwrm_port_phy_qcaps_output { #define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_100G 0x2UL #define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_200G 0x4UL __le16 flags2; - #define PORT_PHY_QCAPS_RESP_FLAGS2_PAUSE_UNSUPPORTED 0x1UL - #define PORT_PHY_QCAPS_RESP_FLAGS2_PFC_UNSUPPORTED 0x2UL - #define PORT_PHY_QCAPS_RESP_FLAGS2_BANK_ADDR_SUPPORTED 0x4UL - #define PORT_PHY_QCAPS_RESP_FLAGS2_SPEEDS2_SUPPORTED 0x8UL + #define PORT_PHY_QCAPS_RESP_FLAGS2_PAUSE_UNSUPPORTED 0x1UL + #define PORT_PHY_QCAPS_RESP_FLAGS2_PFC_UNSUPPORTED 0x2UL + #define PORT_PHY_QCAPS_RESP_FLAGS2_BANK_ADDR_SUPPORTED 0x4UL + #define PORT_PHY_QCAPS_RESP_FLAGS2_SPEEDS2_SUPPORTED 0x8UL + #define PORT_PHY_QCAPS_RESP_FLAGS2_REMOTE_LPBK_UNSUPPORTED 0x10UL u8 internal_port_cnt; u8 unused_0; __le16 supported_speeds2_force_mode; @@ -7443,17 +7484,17 @@ struct hwrm_cfa_l2_filter_cfg_input { __le16 target_id; __le64 resp_addr; __le32 flags; - #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH 0x1UL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_TX 0x0UL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX 0x1UL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_LAST CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX - #define CFA_L2_FILTER_CFG_REQ_FLAGS_DROP 0x2UL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_MASK 0xcUL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_SFT 2 - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_NO_ROCE_L2 (0x0UL << 2) - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_L2 (0x1UL << 2) - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE (0x2UL << 2) - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_LAST CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE + #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH 0x1UL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_TX 0x0UL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX 0x1UL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_LAST CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX + #define CFA_L2_FILTER_CFG_REQ_FLAGS_DROP 0x2UL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_MASK 0xcUL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_SFT 2 + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_NO_ROCE_L2 (0x0UL << 2) + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_L2 (0x1UL << 2) + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE (0x2UL << 2) + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_LAST CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_MASK 0x30UL #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_SFT 4 #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_NO_UPDATE (0x0UL << 4) @@ -8520,17 +8561,17 @@ struct hwrm_tunnel_dst_port_query_input { __le16 target_id; __le64 resp_addr; u8 tunnel_type; - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN 0x1UL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GENEVE 0x5UL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_CUSTOM_GRE 0xdUL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ECPRI 0xeUL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_SRV6 0xfUL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE 0x10UL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GRE 0x11UL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN 0x1UL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GENEVE 0x5UL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_CUSTOM_GRE 0xdUL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ECPRI 0xeUL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_SRV6 0xfUL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE 0x10UL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GRE 0x11UL #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR 0x12UL #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL @@ -8576,17 +8617,17 @@ struct hwrm_tunnel_dst_port_alloc_input { __le16 target_id; __le64 resp_addr; u8 tunnel_type; - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN 0x1UL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE 0x5UL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_CUSTOM_GRE 0xdUL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ECPRI 0xeUL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_SRV6 0xfUL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE 0x10UL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GRE 0x11UL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN 0x1UL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE 0x5UL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_CUSTOM_GRE 0xdUL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ECPRI 0xeUL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_SRV6 0xfUL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE 0x10UL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GRE 0x11UL #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR 0x12UL #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL @@ -8635,17 +8676,17 @@ struct hwrm_tunnel_dst_port_free_input { __le16 target_id; __le64 resp_addr; u8 tunnel_type; - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN 0x1UL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE 0x5UL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_CUSTOM_GRE 0xdUL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ECPRI 0xeUL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_SRV6 0xfUL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE 0x10UL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GRE 0x11UL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN 0x1UL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE 0x5UL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_CUSTOM_GRE 0xdUL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ECPRI 0xeUL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_SRV6 0xfUL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE 0x10UL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GRE 0x11UL #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR 0x12UL #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL @@ -9109,6 +9150,7 @@ struct hwrm_struct_hdr { #define STRUCT_HDR_STRUCT_ID_LLDP_GENERIC 0x424UL #define STRUCT_HDR_STRUCT_ID_LLDP_DEVICE 0x426UL #define STRUCT_HDR_STRUCT_ID_POWER_BKUP 0x427UL + #define STRUCT_HDR_STRUCT_ID_PEER_MMAP 0x429UL #define STRUCT_HDR_STRUCT_ID_AFM_OPAQUE 0x1UL #define STRUCT_HDR_STRUCT_ID_PORT_DESCRIPTION 0xaUL #define STRUCT_HDR_STRUCT_ID_RSS_V2 0x64UL @@ -9758,6 +9800,9 @@ struct hwrm_dbg_coredump_initiate_input { __le16 instance; __le16 unused_0; u8 seg_flags; + #define DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_LIVE_DATA 0x1UL + #define DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_CRASH_DATA 0x2UL + #define DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_COLLECT_CTX_L1_CACHE 0x4UL u8 unused_1[7]; }; @@ -10433,13 +10478,13 @@ struct hwrm_selftest_irq_output { /* dbc_dbc (size:64b/8B) */ struct dbc_dbc { - u32 index; + __le32 index; #define DBC_DBC_INDEX_MASK 0xffffffUL #define DBC_DBC_INDEX_SFT 0 #define DBC_DBC_EPOCH 0x1000000UL #define DBC_DBC_TOGGLE_MASK 0x6000000UL #define DBC_DBC_TOGGLE_SFT 25 - u32 type_path_xid; + __le32 type_path_xid; #define DBC_DBC_XID_MASK 0xfffffUL #define DBC_DBC_XID_SFT 0 #define DBC_DBC_PATH_MASK 0x3000000UL diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c index 1df3d56cc4b5..d2fd2d04ed47 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c @@ -680,7 +680,7 @@ static int __hwrm_send(struct bnxt *bp, struct bnxt_hwrm_ctx *ctx) req_type); else if (rc && rc != HWRM_ERR_CODE_PF_UNAVAILABLE) hwrm_err(bp, ctx, "hwrm req_type 0x%x seq id 0x%x error 0x%x\n", - req_type, token->seq_id, rc); + req_type, le16_to_cpu(ctx->req->seq_id), rc); rc = __hwrm_to_stderr(rc); exit: if (token) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index 175192ebaa77..22898d3d088b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -950,8 +950,11 @@ static int bnxt_hwrm_fwd_resp(struct bnxt *bp, struct bnxt_vf_info *vf, struct hwrm_fwd_resp_input *req; int rc; - if (BNXT_FWD_RESP_SIZE_ERR(msg_size)) + if (BNXT_FWD_RESP_SIZE_ERR(msg_size)) { + netdev_warn_once(bp->dev, "HWRM fwd response too big (%d bytes)\n", + msg_size); return -EINVAL; + } rc = hwrm_req_init(bp, req, HWRM_FWD_RESP); if (!rc) { @@ -1085,7 +1088,7 @@ static int bnxt_vf_set_link(struct bnxt *bp, struct bnxt_vf_info *vf) rc = bnxt_hwrm_exec_fwd_resp( bp, vf, sizeof(struct hwrm_port_phy_qcfg_input)); } else { - struct hwrm_port_phy_qcfg_output phy_qcfg_resp = {0}; + struct hwrm_port_phy_qcfg_output_compat phy_qcfg_resp = {}; struct hwrm_port_phy_qcfg_input *phy_qcfg_req; phy_qcfg_req = @@ -1096,6 +1099,11 @@ static int bnxt_vf_set_link(struct bnxt *bp, struct bnxt_vf_info *vf) mutex_unlock(&bp->link_lock); phy_qcfg_resp.resp_len = cpu_to_le16(sizeof(phy_qcfg_resp)); phy_qcfg_resp.seq_id = phy_qcfg_req->seq_id; + /* New SPEEDS2 fields are beyond the legacy structure, so + * clear the SPEEDS2_SUPPORTED flag. + */ + phy_qcfg_resp.option_flags &= + ~PORT_PHY_QCAPS_RESP_FLAGS2_SPEEDS2_SUPPORTED; phy_qcfg_resp.valid = 1; if (vf->flags & BNXT_VF_LINK_UP) { diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index aa5700ac9c00..122663ff7834 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -645,6 +645,10 @@ #define GEM_T2OFST_OFFSET 0 /* offset value */ #define GEM_T2OFST_SIZE 7 +/* Bitfields in queue pointer registers */ +#define MACB_QUEUE_DISABLE_OFFSET 0 /* disable queue */ +#define MACB_QUEUE_DISABLE_SIZE 1 + /* Offset for screener type 2 compare values (T2CMPOFST). * Note the offset is applied after the specified point, * e.g. GEM_T2COMPOFST_ETYPE denotes the EtherType field, so an offset @@ -733,6 +737,7 @@ #define MACB_CAPS_NEEDS_RSTONUBR 0x00000100 #define MACB_CAPS_MIIONRGMII 0x00000200 #define MACB_CAPS_NEED_TSUCLK 0x00000400 +#define MACB_CAPS_QUEUE_DISABLE 0x00000800 #define MACB_CAPS_PCS 0x01000000 #define MACB_CAPS_HIGH_SPEED 0x02000000 #define MACB_CAPS_CLK_HW_CHG 0x04000000 @@ -1254,6 +1259,8 @@ struct macb { u32 (*macb_reg_readl)(struct macb *bp, int offset); void (*macb_reg_writel)(struct macb *bp, int offset, u32 value); + struct macb_dma_desc *rx_ring_tieoff; + dma_addr_t rx_ring_tieoff_dma; size_t rx_buffer_size; unsigned int rx_ring_size; @@ -1299,6 +1306,7 @@ struct macb { unsigned int jumbo_max_len; u32 wol; + u32 wolopts; /* holds value of rx watermark value for pbuf_rxcutthru register */ u32 rx_watermark; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 241ce9a2fa99..cecc3d6e630f 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -38,6 +38,7 @@ #include <linux/ptp_classify.h> #include <linux/reset.h> #include <linux/firmware/xlnx-zynqmp.h> +#include <linux/inetdevice.h> #include "macb.h" /* This structure is only used for MACB on SiFive FU540 devices */ @@ -84,8 +85,7 @@ struct sifive_fu540_macb_mgmt { #define GEM_MTU_MIN_SIZE ETH_MIN_MTU #define MACB_NETIF_LSO NETIF_F_TSO -#define MACB_WOL_HAS_MAGIC_PACKET (0x1 << 0) -#define MACB_WOL_ENABLED (0x1 << 1) +#define MACB_WOL_ENABLED BIT(0) #define HS_SPEED_10000M 4 #define MACB_SERDES_RATE_10G 1 @@ -2477,6 +2477,12 @@ static void macb_free_consistent(struct macb *bp) unsigned int q; int size; + if (bp->rx_ring_tieoff) { + dma_free_coherent(&bp->pdev->dev, macb_dma_desc_get_size(bp), + bp->rx_ring_tieoff, bp->rx_ring_tieoff_dma); + bp->rx_ring_tieoff = NULL; + } + bp->macbgem_ops.mog_free_rx_buffers(bp); for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { @@ -2568,6 +2574,16 @@ static int macb_alloc_consistent(struct macb *bp) if (bp->macbgem_ops.mog_alloc_rx_buffers(bp)) goto out_err; + /* Required for tie off descriptor for PM cases */ + if (!(bp->caps & MACB_CAPS_QUEUE_DISABLE)) { + bp->rx_ring_tieoff = dma_alloc_coherent(&bp->pdev->dev, + macb_dma_desc_get_size(bp), + &bp->rx_ring_tieoff_dma, + GFP_KERNEL); + if (!bp->rx_ring_tieoff) + goto out_err; + } + return 0; out_err: @@ -2575,6 +2591,19 @@ out_err: return -ENOMEM; } +static void macb_init_tieoff(struct macb *bp) +{ + struct macb_dma_desc *desc = bp->rx_ring_tieoff; + + if (bp->caps & MACB_CAPS_QUEUE_DISABLE) + return; + /* Setup a wrapping descriptor with no free slots + * (WRAP and USED) to tie off/disable unused RX queues. + */ + macb_set_addr(bp, desc, MACB_BIT(RX_WRAP) | MACB_BIT(RX_USED)); + desc->ctrl = 0; +} + static void gem_init_rings(struct macb *bp) { struct macb_queue *queue; @@ -2598,6 +2627,7 @@ static void gem_init_rings(struct macb *bp) gem_rx_refill(queue); } + macb_init_tieoff(bp); } static void macb_init_rings(struct macb *bp) @@ -2615,6 +2645,8 @@ static void macb_init_rings(struct macb *bp) bp->queues[0].tx_head = 0; bp->queues[0].tx_tail = 0; desc->ctrl |= MACB_BIT(TX_WRAP); + + macb_init_tieoff(bp); } static void macb_reset_hw(struct macb *bp) @@ -3246,13 +3278,11 @@ static void macb_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) { struct macb *bp = netdev_priv(netdev); - if (bp->wol & MACB_WOL_HAS_MAGIC_PACKET) { - phylink_ethtool_get_wol(bp->phylink, wol); - wol->supported |= WAKE_MAGIC; + phylink_ethtool_get_wol(bp->phylink, wol); + wol->supported |= (WAKE_MAGIC | WAKE_ARP); - if (bp->wol & MACB_WOL_ENABLED) - wol->wolopts |= WAKE_MAGIC; - } + /* Add macb wolopts to phy wolopts */ + wol->wolopts |= bp->wolopts; } static int macb_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) @@ -3262,22 +3292,15 @@ static int macb_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) /* Pass the order to phylink layer */ ret = phylink_ethtool_set_wol(bp->phylink, wol); - /* Don't manage WoL on MAC if handled by the PHY - * or if there's a failure in talking to the PHY - */ - if (!ret || ret != -EOPNOTSUPP) + /* Don't manage WoL on MAC, if PHY set_wol() fails */ + if (ret && ret != -EOPNOTSUPP) return ret; - if (!(bp->wol & MACB_WOL_HAS_MAGIC_PACKET) || - (wol->wolopts & ~WAKE_MAGIC)) - return -EOPNOTSUPP; - - if (wol->wolopts & WAKE_MAGIC) - bp->wol |= MACB_WOL_ENABLED; - else - bp->wol &= ~MACB_WOL_ENABLED; + bp->wolopts = (wol->wolopts & WAKE_MAGIC) ? WAKE_MAGIC : 0; + bp->wolopts |= (wol->wolopts & WAKE_ARP) ? WAKE_ARP : 0; + bp->wol = (wol->wolopts) ? MACB_WOL_ENABLED : 0; - device_set_wakeup_enable(&bp->pdev->dev, bp->wol & MACB_WOL_ENABLED); + device_set_wakeup_enable(&bp->pdev->dev, bp->wol); return 0; } @@ -4917,7 +4940,8 @@ static const struct macb_config sama7g5_emac_config = { static const struct macb_config versal_config = { .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_JUMBO | - MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_BD_RD_PREFETCH | MACB_CAPS_NEED_TSUCLK, + MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_BD_RD_PREFETCH | MACB_CAPS_NEED_TSUCLK | + MACB_CAPS_QUEUE_DISABLE, .dma_burst_length = 16, .clk_init = macb_clk_init, .init = init_reset_optional, @@ -5053,9 +5077,7 @@ static int macb_probe(struct platform_device *pdev) bp->max_tx_length = GEM_MAX_TX_LEN; bp->wol = 0; - if (of_property_read_bool(np, "magic-packet")) - bp->wol |= MACB_WOL_HAS_MAGIC_PACKET; - device_set_wakeup_capable(&pdev->dev, bp->wol & MACB_WOL_HAS_MAGIC_PACKET); + device_set_wakeup_capable(&pdev->dev, 1); bp->usrio = macb_config->usrio; @@ -5211,10 +5233,13 @@ static int __maybe_unused macb_suspend(struct device *dev) { struct net_device *netdev = dev_get_drvdata(dev); struct macb *bp = netdev_priv(netdev); + struct in_ifaddr *ifa = NULL; struct macb_queue *queue; + struct in_device *idev; unsigned long flags; unsigned int q; int err; + u32 tmp; if (!device_may_wakeup(&bp->dev->dev)) phy_exit(bp->sgmii_phy); @@ -5223,18 +5248,54 @@ static int __maybe_unused macb_suspend(struct device *dev) return 0; if (bp->wol & MACB_WOL_ENABLED) { + /* Check for IP address in WOL ARP mode */ + idev = __in_dev_get_rcu(bp->dev); + if (idev && idev->ifa_list) + ifa = rcu_access_pointer(idev->ifa_list); + if ((bp->wolopts & WAKE_ARP) && !ifa) { + netdev_err(netdev, "IP address not assigned as required by WoL walk ARP\n"); + return -EOPNOTSUPP; + } spin_lock_irqsave(&bp->lock, flags); - /* Flush all status bits */ - macb_writel(bp, TSR, -1); - macb_writel(bp, RSR, -1); + + /* Disable Tx and Rx engines before disabling the queues, + * this is mandatory as per the IP spec sheet + */ + tmp = macb_readl(bp, NCR); + macb_writel(bp, NCR, tmp & ~(MACB_BIT(TE) | MACB_BIT(RE))); for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { + /* Disable RX queues */ + if (bp->caps & MACB_CAPS_QUEUE_DISABLE) { + queue_writel(queue, RBQP, MACB_BIT(QUEUE_DISABLE)); + } else { + /* Tie off RX queues */ + queue_writel(queue, RBQP, + lower_32_bits(bp->rx_ring_tieoff_dma)); +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + queue_writel(queue, RBQPH, + upper_32_bits(bp->rx_ring_tieoff_dma)); +#endif + } /* Disable all interrupts */ queue_writel(queue, IDR, -1); queue_readl(queue, ISR); if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) queue_writel(queue, ISR, -1); } + /* Enable Receive engine */ + macb_writel(bp, NCR, tmp | MACB_BIT(RE)); + /* Flush all status bits */ + macb_writel(bp, TSR, -1); + macb_writel(bp, RSR, -1); + + tmp = (bp->wolopts & WAKE_MAGIC) ? MACB_BIT(MAG) : 0; + if (bp->wolopts & WAKE_ARP) { + tmp |= MACB_BIT(ARP); + /* write IP address into register */ + tmp |= MACB_BFEXT(IP, be32_to_cpu(ifa->ifa_local)); + } + /* Change interrupt handler and * Enable WoL IRQ on queue 0 */ @@ -5250,7 +5311,7 @@ static int __maybe_unused macb_suspend(struct device *dev) return err; } queue_writel(bp->queues, IER, GEM_BIT(WOL)); - gem_writel(bp, WOL, MACB_BIT(MAG)); + gem_writel(bp, WOL, tmp); } else { err = devm_request_irq(dev, bp->queues[0].irq, macb_wol_interrupt, IRQF_SHARED, netdev->name, bp->queues); @@ -5262,7 +5323,7 @@ static int __maybe_unused macb_suspend(struct device *dev) return err; } queue_writel(bp->queues, IER, MACB_BIT(WOL)); - macb_writel(bp, WOL, MACB_BIT(MAG)); + macb_writel(bp, WOL, tmp); } spin_unlock_irqrestore(&bp->lock, flags); diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c index 96c6ea12279f..989b4ddae342 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c @@ -272,13 +272,12 @@ lio_vf_rep_copy_packet(struct octeon_device *oct, pg_info->page_offset; memcpy(skb->data, va, MIN_SKB_SIZE); skb_put(skb, MIN_SKB_SIZE); + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, + pg_info->page, + pg_info->page_offset + MIN_SKB_SIZE, + len - MIN_SKB_SIZE, + LIO_RXBUFFER_SZ); } - - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, - pg_info->page, - pg_info->page_offset + MIN_SKB_SIZE, - len - MIN_SKB_SIZE, - LIO_RXBUFFER_SZ); } else { struct octeon_skb_page_info *pg_info = ((struct octeon_skb_page_info *)(skb->cb)); diff --git a/drivers/net/ethernet/cirrus/mac89x0.c b/drivers/net/ethernet/cirrus/mac89x0.c index 887876f35f10..84b300fee2bb 100644 --- a/drivers/net/ethernet/cirrus/mac89x0.c +++ b/drivers/net/ethernet/cirrus/mac89x0.c @@ -554,6 +554,7 @@ static int set_mac_address(struct net_device *dev, void *addr) return 0; } +MODULE_DESCRIPTION("Macintosh CS89x0-based Ethernet driver"); MODULE_LICENSE("GPL"); static void mac89x0_device_remove(struct platform_device *pdev) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 881ece735dcf..fb19295529a2 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1361,6 +1361,12 @@ fec_stop(struct net_device *ndev) writel(FEC_ECR_ETHEREN, fep->hwp + FEC_ECNTRL); writel(rmii_mode, fep->hwp + FEC_R_CNTRL); } + + if (fep->bufdesc_ex) { + val = readl(fep->hwp + FEC_ECNTRL); + val |= FEC_ECR_EN1588; + writel(val, fep->hwp + FEC_ECNTRL); + } } static void diff --git a/drivers/net/ethernet/google/gve/Makefile b/drivers/net/ethernet/google/gve/Makefile index b9a6be76531b..9ed07080b38a 100644 --- a/drivers/net/ethernet/google/gve/Makefile +++ b/drivers/net/ethernet/google/gve/Makefile @@ -1,4 +1,4 @@ # Makefile for the Google virtual Ethernet (gve) driver obj-$(CONFIG_GVE) += gve.o -gve-objs := gve_main.o gve_tx.o gve_tx_dqo.o gve_rx.o gve_rx_dqo.o gve_ethtool.o gve_adminq.o gve_utils.o +gve-objs := gve_main.o gve_tx.o gve_tx_dqo.o gve_rx.o gve_rx_dqo.o gve_ethtool.o gve_adminq.o gve_utils.o gve_flow_rule.o diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index ae1e21c9b0a5..84ac004d3953 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0 OR MIT) * Google virtual Ethernet (gve) driver * - * Copyright (C) 2015-2021 Google, Inc. + * Copyright (C) 2015-2024 Google LLC */ #ifndef _GVE_H_ @@ -60,6 +60,11 @@ #define GVE_DEFAULT_RX_BUFFER_OFFSET 2048 +#define GVE_FLOW_RULES_CACHE_SIZE \ + (GVE_ADMINQ_BUFFER_SIZE / sizeof(struct gve_adminq_queried_flow_rule)) +#define GVE_FLOW_RULE_IDS_CACHE_SIZE \ + (GVE_ADMINQ_BUFFER_SIZE / sizeof(((struct gve_adminq_queried_flow_rule *)0)->location)) + #define GVE_XDP_ACTIONS 5 #define GVE_GQ_TX_MIN_PKT_DESC_BYTES 182 @@ -678,6 +683,39 @@ enum gve_queue_format { GVE_DQO_QPL_FORMAT = 0x4, }; +struct gve_flow_spec { + __be32 src_ip[4]; + __be32 dst_ip[4]; + union { + struct { + __be16 src_port; + __be16 dst_port; + }; + __be32 spi; + }; + union { + u8 tos; + u8 tclass; + }; +}; + +struct gve_flow_rule { + u32 location; + u16 flow_type; + u16 action; + struct gve_flow_spec key; + struct gve_flow_spec mask; +}; + +struct gve_flow_rules_cache { + bool rules_cache_synced; /* False if the driver's rules_cache is outdated */ + struct gve_adminq_queried_flow_rule *rules_cache; + __be32 *rule_ids_cache; + /* The total number of queried rules that stored in the caches */ + u32 rules_cache_num; + u32 rule_ids_cache_num; +}; + struct gve_priv { struct net_device *dev; struct gve_tx_ring *tx; /* array of tx_cfg.num_queues */ @@ -724,6 +762,7 @@ struct gve_priv { union gve_adminq_command *adminq; dma_addr_t adminq_bus_addr; struct dma_pool *adminq_pool; + struct mutex adminq_lock; /* Protects adminq command execution */ u32 adminq_mask; /* masks prod_cnt to adminq size */ u32 adminq_prod_cnt; /* free-running count of AQ cmds executed */ u32 adminq_cmd_fail; /* free-running count of AQ cmds failed */ @@ -743,6 +782,8 @@ struct gve_priv { u32 adminq_report_link_speed_cnt; u32 adminq_get_ptype_map_cnt; u32 adminq_verify_driver_compatibility_cnt; + u32 adminq_query_flow_rules_cnt; + u32 adminq_cfg_flow_rule_cnt; /* Global stats */ u32 interface_up_cnt; /* count of times interface turned up since last reset */ @@ -785,6 +826,11 @@ struct gve_priv { u16 header_buf_size; /* device configured, header-split supported if non-zero */ bool header_split_enabled; /* True if the header split is enabled by the user */ + + u32 max_flow_rules; + u32 num_flow_rules; + + struct gve_flow_rules_cache flow_rules_cache; }; enum gve_service_task_flags_bit { @@ -1124,6 +1170,12 @@ int gve_adjust_config(struct gve_priv *priv, int gve_adjust_queues(struct gve_priv *priv, struct gve_queue_config new_rx_config, struct gve_queue_config new_tx_config); +/* flow steering rule */ +int gve_get_flow_rule_entry(struct gve_priv *priv, struct ethtool_rxnfc *cmd); +int gve_get_flow_rule_ids(struct gve_priv *priv, struct ethtool_rxnfc *cmd, u32 *rule_locs); +int gve_add_flow_rule(struct gve_priv *priv, struct ethtool_rxnfc *cmd); +int gve_del_flow_rule(struct gve_priv *priv, struct ethtool_rxnfc *cmd); +int gve_flow_rules_reset(struct gve_priv *priv); /* report stats handling */ void gve_handle_report_stats(struct gve_priv *priv); /* exported by ethtool.c */ diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c index 8ca0def176ef..c5bbc1b7524e 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.c +++ b/drivers/net/ethernet/google/gve/gve_adminq.c @@ -44,6 +44,7 @@ void gve_parse_device_option(struct gve_priv *priv, struct gve_device_option_jumbo_frames **dev_op_jumbo_frames, struct gve_device_option_dqo_qpl **dev_op_dqo_qpl, struct gve_device_option_buffer_sizes **dev_op_buffer_sizes, + struct gve_device_option_flow_steering **dev_op_flow_steering, struct gve_device_option_modify_ring **dev_op_modify_ring) { u32 req_feat_mask = be32_to_cpu(option->required_features_mask); @@ -189,6 +190,23 @@ void gve_parse_device_option(struct gve_priv *priv, if (option_length == GVE_DEVICE_OPTION_NO_MIN_RING_SIZE) priv->default_min_ring_size = true; break; + case GVE_DEV_OPT_ID_FLOW_STEERING: + if (option_length < sizeof(**dev_op_flow_steering) || + req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_FLOW_STEERING) { + dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT, + "Flow Steering", + (int)sizeof(**dev_op_flow_steering), + GVE_DEV_OPT_REQ_FEAT_MASK_FLOW_STEERING, + option_length, req_feat_mask); + break; + } + + if (option_length > sizeof(**dev_op_flow_steering)) + dev_warn(&priv->pdev->dev, + GVE_DEVICE_OPTION_TOO_BIG_FMT, + "Flow Steering"); + *dev_op_flow_steering = (void *)(option + 1); + break; default: /* If we don't recognize the option just continue * without doing anything. @@ -208,6 +226,7 @@ gve_process_device_options(struct gve_priv *priv, struct gve_device_option_jumbo_frames **dev_op_jumbo_frames, struct gve_device_option_dqo_qpl **dev_op_dqo_qpl, struct gve_device_option_buffer_sizes **dev_op_buffer_sizes, + struct gve_device_option_flow_steering **dev_op_flow_steering, struct gve_device_option_modify_ring **dev_op_modify_ring) { const int num_options = be16_to_cpu(descriptor->num_device_options); @@ -230,7 +249,7 @@ gve_process_device_options(struct gve_priv *priv, dev_op_gqi_rda, dev_op_gqi_qpl, dev_op_dqo_rda, dev_op_jumbo_frames, dev_op_dqo_qpl, dev_op_buffer_sizes, - dev_op_modify_ring); + dev_op_flow_steering, dev_op_modify_ring); dev_opt = next_opt; } @@ -268,6 +287,8 @@ int gve_adminq_alloc(struct device *dev, struct gve_priv *priv) priv->adminq_report_stats_cnt = 0; priv->adminq_report_link_speed_cnt = 0; priv->adminq_get_ptype_map_cnt = 0; + priv->adminq_query_flow_rules_cnt = 0; + priv->adminq_cfg_flow_rule_cnt = 0; /* Setup Admin queue with the device */ if (priv->pdev->revision < 0x1) { @@ -284,6 +305,7 @@ int gve_adminq_alloc(struct device *dev, struct gve_priv *priv) &priv->reg_bar0->adminq_base_address_lo); iowrite32be(GVE_DRIVER_STATUS_RUN_MASK, &priv->reg_bar0->driver_status); } + mutex_init(&priv->adminq_lock); gve_set_admin_queue_ok(priv); return 0; } @@ -460,6 +482,8 @@ static int gve_adminq_issue_cmd(struct gve_priv *priv, memcpy(cmd, cmd_orig, sizeof(*cmd_orig)); opcode = be32_to_cpu(READ_ONCE(cmd->opcode)); + if (opcode == GVE_ADMINQ_EXTENDED_COMMAND) + opcode = be32_to_cpu(cmd->extended_command.inner_opcode); switch (opcode) { case GVE_ADMINQ_DESCRIBE_DEVICE: @@ -504,6 +528,12 @@ static int gve_adminq_issue_cmd(struct gve_priv *priv, case GVE_ADMINQ_VERIFY_DRIVER_COMPATIBILITY: priv->adminq_verify_driver_compatibility_cnt++; break; + case GVE_ADMINQ_QUERY_FLOW_RULES: + priv->adminq_query_flow_rules_cnt++; + break; + case GVE_ADMINQ_CONFIGURE_FLOW_RULE: + priv->adminq_cfg_flow_rule_cnt++; + break; default: dev_err(&priv->pdev->dev, "unknown AQ command opcode %d\n", opcode); } @@ -511,28 +541,58 @@ static int gve_adminq_issue_cmd(struct gve_priv *priv, return 0; } -/* This function is not threadsafe - the caller is responsible for any - * necessary locks. - * The caller is also responsible for making sure there are no commands - * waiting to be executed. - */ static int gve_adminq_execute_cmd(struct gve_priv *priv, union gve_adminq_command *cmd_orig) { u32 tail, head; int err; + mutex_lock(&priv->adminq_lock); tail = ioread32be(&priv->reg_bar0->adminq_event_counter); head = priv->adminq_prod_cnt; - if (tail != head) - // This is not a valid path - return -EINVAL; + if (tail != head) { + err = -EINVAL; + goto out; + } err = gve_adminq_issue_cmd(priv, cmd_orig); if (err) - return err; + goto out; - return gve_adminq_kick_and_wait(priv); + err = gve_adminq_kick_and_wait(priv); + +out: + mutex_unlock(&priv->adminq_lock); + return err; +} + +static int gve_adminq_execute_extended_cmd(struct gve_priv *priv, u32 opcode, + size_t cmd_size, void *cmd_orig) +{ + union gve_adminq_command cmd; + dma_addr_t inner_cmd_bus; + void *inner_cmd; + int err; + + inner_cmd = dma_alloc_coherent(&priv->pdev->dev, cmd_size, + &inner_cmd_bus, GFP_KERNEL); + if (!inner_cmd) + return -ENOMEM; + + memcpy(inner_cmd, cmd_orig, cmd_size); + + memset(&cmd, 0, sizeof(cmd)); + cmd.opcode = cpu_to_be32(GVE_ADMINQ_EXTENDED_COMMAND); + cmd.extended_command = (struct gve_adminq_extended_command) { + .inner_opcode = cpu_to_be32(opcode), + .inner_length = cpu_to_be32(cmd_size), + .inner_command_addr = cpu_to_be64(inner_cmd_bus), + }; + + err = gve_adminq_execute_cmd(priv, &cmd); + + dma_free_coherent(&priv->pdev->dev, cmd_size, inner_cmd, inner_cmd_bus); + return err; } /* The device specifies that the management vector can either be the first irq @@ -805,6 +865,8 @@ static void gve_enable_supported_features(struct gve_priv *priv, *dev_op_dqo_qpl, const struct gve_device_option_buffer_sizes *dev_op_buffer_sizes, + const struct gve_device_option_flow_steering + *dev_op_flow_steering, const struct gve_device_option_modify_ring *dev_op_modify_ring) { @@ -857,10 +919,23 @@ static void gve_enable_supported_features(struct gve_priv *priv, priv->min_tx_desc_cnt = be16_to_cpu(dev_op_modify_ring->min_tx_ring_size); } } + + if (dev_op_flow_steering && + (supported_features_mask & GVE_SUP_FLOW_STEERING_MASK)) { + if (dev_op_flow_steering->max_flow_rules) { + priv->max_flow_rules = + be32_to_cpu(dev_op_flow_steering->max_flow_rules); + priv->dev->hw_features |= NETIF_F_NTUPLE; + dev_info(&priv->pdev->dev, + "FLOW STEERING device option enabled with max rule limit of %u.\n", + priv->max_flow_rules); + } + } } int gve_adminq_describe_device(struct gve_priv *priv) { + struct gve_device_option_flow_steering *dev_op_flow_steering = NULL; struct gve_device_option_buffer_sizes *dev_op_buffer_sizes = NULL; struct gve_device_option_jumbo_frames *dev_op_jumbo_frames = NULL; struct gve_device_option_modify_ring *dev_op_modify_ring = NULL; @@ -897,6 +972,7 @@ int gve_adminq_describe_device(struct gve_priv *priv) &dev_op_gqi_qpl, &dev_op_dqo_rda, &dev_op_jumbo_frames, &dev_op_dqo_qpl, &dev_op_buffer_sizes, + &dev_op_flow_steering, &dev_op_modify_ring); if (err) goto free_device_descriptor; @@ -958,7 +1034,8 @@ int gve_adminq_describe_device(struct gve_priv *priv) gve_enable_supported_features(priv, supported_features_mask, dev_op_jumbo_frames, dev_op_dqo_qpl, - dev_op_buffer_sizes, dev_op_modify_ring); + dev_op_buffer_sizes, dev_op_flow_steering, + dev_op_modify_ring); free_device_descriptor: dma_pool_free(priv->adminq_pool, descriptor, descriptor_bus); @@ -1121,3 +1198,130 @@ err: ptype_map_bus); return err; } + +static int +gve_adminq_configure_flow_rule(struct gve_priv *priv, + struct gve_adminq_configure_flow_rule *flow_rule_cmd) +{ + int err = gve_adminq_execute_extended_cmd(priv, + GVE_ADMINQ_CONFIGURE_FLOW_RULE, + sizeof(struct gve_adminq_configure_flow_rule), + flow_rule_cmd); + + if (err) { + dev_err(&priv->pdev->dev, "Timeout to configure the flow rule, trigger reset"); + gve_reset(priv, true); + } else { + priv->flow_rules_cache.rules_cache_synced = false; + } + + return err; +} + +int gve_adminq_add_flow_rule(struct gve_priv *priv, struct gve_adminq_flow_rule *rule, u32 loc) +{ + struct gve_adminq_configure_flow_rule flow_rule_cmd = { + .opcode = cpu_to_be16(GVE_FLOW_RULE_CFG_ADD), + .location = cpu_to_be32(loc), + .rule = *rule, + }; + + return gve_adminq_configure_flow_rule(priv, &flow_rule_cmd); +} + +int gve_adminq_del_flow_rule(struct gve_priv *priv, u32 loc) +{ + struct gve_adminq_configure_flow_rule flow_rule_cmd = { + .opcode = cpu_to_be16(GVE_FLOW_RULE_CFG_DEL), + .location = cpu_to_be32(loc), + }; + + return gve_adminq_configure_flow_rule(priv, &flow_rule_cmd); +} + +int gve_adminq_reset_flow_rules(struct gve_priv *priv) +{ + struct gve_adminq_configure_flow_rule flow_rule_cmd = { + .opcode = cpu_to_be16(GVE_FLOW_RULE_CFG_RESET), + }; + + return gve_adminq_configure_flow_rule(priv, &flow_rule_cmd); +} + +/* In the dma memory that the driver allocated for the device to query the flow rules, the device + * will first write it with a struct of gve_query_flow_rules_descriptor. Next to it, the device + * will write an array of rules or rule ids with the count that specified in the descriptor. + * For GVE_FLOW_RULE_QUERY_STATS, the device will only write the descriptor. + */ +static int gve_adminq_process_flow_rules_query(struct gve_priv *priv, u16 query_opcode, + struct gve_query_flow_rules_descriptor *descriptor) +{ + struct gve_flow_rules_cache *flow_rules_cache = &priv->flow_rules_cache; + u32 num_queried_rules, total_memory_len, rule_info_len; + void *rule_info; + + total_memory_len = be32_to_cpu(descriptor->total_length); + num_queried_rules = be32_to_cpu(descriptor->num_queried_rules); + rule_info = (void *)(descriptor + 1); + + switch (query_opcode) { + case GVE_FLOW_RULE_QUERY_RULES: + rule_info_len = num_queried_rules * sizeof(*flow_rules_cache->rules_cache); + if (sizeof(*descriptor) + rule_info_len != total_memory_len) { + dev_err(&priv->dev->dev, "flow rules query is out of memory.\n"); + return -ENOMEM; + } + + memcpy(flow_rules_cache->rules_cache, rule_info, rule_info_len); + flow_rules_cache->rules_cache_num = num_queried_rules; + break; + case GVE_FLOW_RULE_QUERY_IDS: + rule_info_len = num_queried_rules * sizeof(*flow_rules_cache->rule_ids_cache); + if (sizeof(*descriptor) + rule_info_len != total_memory_len) { + dev_err(&priv->dev->dev, "flow rule ids query is out of memory.\n"); + return -ENOMEM; + } + + memcpy(flow_rules_cache->rule_ids_cache, rule_info, rule_info_len); + flow_rules_cache->rule_ids_cache_num = num_queried_rules; + break; + case GVE_FLOW_RULE_QUERY_STATS: + priv->num_flow_rules = be32_to_cpu(descriptor->num_flow_rules); + priv->max_flow_rules = be32_to_cpu(descriptor->max_flow_rules); + return 0; + default: + return -EINVAL; + } + + return 0; +} + +int gve_adminq_query_flow_rules(struct gve_priv *priv, u16 query_opcode, u32 starting_loc) +{ + struct gve_query_flow_rules_descriptor *descriptor; + union gve_adminq_command cmd; + dma_addr_t descriptor_bus; + int err = 0; + + memset(&cmd, 0, sizeof(cmd)); + descriptor = dma_pool_alloc(priv->adminq_pool, GFP_KERNEL, &descriptor_bus); + if (!descriptor) + return -ENOMEM; + + cmd.opcode = cpu_to_be32(GVE_ADMINQ_QUERY_FLOW_RULES); + cmd.query_flow_rules = (struct gve_adminq_query_flow_rules) { + .opcode = cpu_to_be16(query_opcode), + .starting_rule_id = cpu_to_be32(starting_loc), + .available_length = cpu_to_be64(GVE_ADMINQ_BUFFER_SIZE), + .rule_descriptor_addr = cpu_to_be64(descriptor_bus), + }; + err = gve_adminq_execute_cmd(priv, &cmd); + if (err) + goto out; + + err = gve_adminq_process_flow_rules_query(priv, query_opcode, descriptor); + +out: + dma_pool_free(priv->adminq_pool, descriptor, descriptor_bus); + return err; +} diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h index e64f0dbe744d..ed1370c9b197 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.h +++ b/drivers/net/ethernet/google/gve/gve_adminq.h @@ -25,6 +25,19 @@ enum gve_adminq_opcodes { GVE_ADMINQ_REPORT_LINK_SPEED = 0xD, GVE_ADMINQ_GET_PTYPE_MAP = 0xE, GVE_ADMINQ_VERIFY_DRIVER_COMPATIBILITY = 0xF, + GVE_ADMINQ_QUERY_FLOW_RULES = 0x10, + + /* For commands that are larger than 56 bytes */ + GVE_ADMINQ_EXTENDED_COMMAND = 0xFF, +}; + +/* The normal adminq command is restricted to be 56 bytes at maximum. For the + * longer adminq command, it is wrapped by GVE_ADMINQ_EXTENDED_COMMAND with + * inner opcode of gve_adminq_extended_cmd_opcodes specified. The inner command + * is written in the dma memory allocated by GVE_ADMINQ_EXTENDED_COMMAND. + */ +enum gve_adminq_extended_cmd_opcodes { + GVE_ADMINQ_CONFIGURE_FLOW_RULE = 0x101, }; /* Admin queue status codes */ @@ -143,6 +156,14 @@ struct gve_device_option_modify_ring { static_assert(sizeof(struct gve_device_option_modify_ring) == 12); +struct gve_device_option_flow_steering { + __be32 supported_features_mask; + __be32 reserved; + __be32 max_flow_rules; +}; + +static_assert(sizeof(struct gve_device_option_flow_steering) == 12); + /* Terminology: * * RDA - Raw DMA Addressing - Buffers associated with SKBs are directly DMA @@ -160,6 +181,7 @@ enum gve_dev_opt_id { GVE_DEV_OPT_ID_DQO_QPL = 0x7, GVE_DEV_OPT_ID_JUMBO_FRAMES = 0x8, GVE_DEV_OPT_ID_BUFFER_SIZES = 0xa, + GVE_DEV_OPT_ID_FLOW_STEERING = 0xb, }; enum gve_dev_opt_req_feat_mask { @@ -171,12 +193,14 @@ enum gve_dev_opt_req_feat_mask { GVE_DEV_OPT_REQ_FEAT_MASK_DQO_QPL = 0x0, GVE_DEV_OPT_REQ_FEAT_MASK_BUFFER_SIZES = 0x0, GVE_DEV_OPT_REQ_FEAT_MASK_MODIFY_RING = 0x0, + GVE_DEV_OPT_REQ_FEAT_MASK_FLOW_STEERING = 0x0, }; enum gve_sup_feature_mask { GVE_SUP_MODIFY_RING_MASK = 1 << 0, GVE_SUP_JUMBO_FRAMES_MASK = 1 << 2, GVE_SUP_BUFFER_SIZES_MASK = 1 << 4, + GVE_SUP_FLOW_STEERING_MASK = 1 << 5, }; #define GVE_DEV_OPT_LEN_GQI_RAW_ADDRESSING 0x0 @@ -208,6 +232,14 @@ enum gve_driver_capbility { #define GVE_DRIVER_CAPABILITY_FLAGS3 0x0 #define GVE_DRIVER_CAPABILITY_FLAGS4 0x0 +struct gve_adminq_extended_command { + __be32 inner_opcode; + __be32 inner_length; + __be64 inner_command_addr; +}; + +static_assert(sizeof(struct gve_adminq_extended_command) == 16); + struct gve_driver_info { u8 os_type; /* 0x01 = Linux */ u8 driver_major; @@ -412,6 +444,71 @@ struct gve_adminq_get_ptype_map { __be64 ptype_map_addr; }; +/* Flow-steering related definitions */ +enum gve_adminq_flow_rule_cfg_opcode { + GVE_FLOW_RULE_CFG_ADD = 0, + GVE_FLOW_RULE_CFG_DEL = 1, + GVE_FLOW_RULE_CFG_RESET = 2, +}; + +enum gve_adminq_flow_rule_query_opcode { + GVE_FLOW_RULE_QUERY_RULES = 0, + GVE_FLOW_RULE_QUERY_IDS = 1, + GVE_FLOW_RULE_QUERY_STATS = 2, +}; + +enum gve_adminq_flow_type { + GVE_FLOW_TYPE_TCPV4, + GVE_FLOW_TYPE_UDPV4, + GVE_FLOW_TYPE_SCTPV4, + GVE_FLOW_TYPE_AHV4, + GVE_FLOW_TYPE_ESPV4, + GVE_FLOW_TYPE_TCPV6, + GVE_FLOW_TYPE_UDPV6, + GVE_FLOW_TYPE_SCTPV6, + GVE_FLOW_TYPE_AHV6, + GVE_FLOW_TYPE_ESPV6, +}; + +/* Flow-steering command */ +struct gve_adminq_flow_rule { + __be16 flow_type; + __be16 action; /* RX queue id */ + struct gve_flow_spec key; + struct gve_flow_spec mask; +}; + +struct gve_adminq_configure_flow_rule { + __be16 opcode; + u8 padding[2]; + struct gve_adminq_flow_rule rule; + __be32 location; +}; + +static_assert(sizeof(struct gve_adminq_configure_flow_rule) == 92); + +struct gve_query_flow_rules_descriptor { + __be32 num_flow_rules; + __be32 max_flow_rules; + __be32 num_queried_rules; + __be32 total_length; +}; + +struct gve_adminq_queried_flow_rule { + __be32 location; + struct gve_adminq_flow_rule flow_rule; +}; + +struct gve_adminq_query_flow_rules { + __be16 opcode; + u8 padding[2]; + __be32 starting_rule_id; + __be64 available_length; /* The dma memory length that the driver allocated */ + __be64 rule_descriptor_addr; /* The dma memory address */ +}; + +static_assert(sizeof(struct gve_adminq_query_flow_rules) == 24); + union gve_adminq_command { struct { __be32 opcode; @@ -432,6 +529,8 @@ union gve_adminq_command { struct gve_adminq_get_ptype_map get_ptype_map; struct gve_adminq_verify_driver_compatibility verify_driver_compatibility; + struct gve_adminq_query_flow_rules query_flow_rules; + struct gve_adminq_extended_command extended_command; }; }; u8 reserved[64]; @@ -465,6 +564,10 @@ int gve_adminq_verify_driver_compatibility(struct gve_priv *priv, u64 driver_info_len, dma_addr_t driver_info_addr); int gve_adminq_report_link_speed(struct gve_priv *priv); +int gve_adminq_add_flow_rule(struct gve_priv *priv, struct gve_adminq_flow_rule *rule, u32 loc); +int gve_adminq_del_flow_rule(struct gve_priv *priv, u32 loc); +int gve_adminq_reset_flow_rules(struct gve_priv *priv); +int gve_adminq_query_flow_rules(struct gve_priv *priv, u16 query_opcode, u32 starting_loc); struct gve_ptype_lut; int gve_adminq_get_ptype_map_dqo(struct gve_priv *priv, diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index fe1741d482b4..3480ff5c7ed6 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: (GPL-2.0 OR MIT) /* Google virtual Ethernet (gve) driver * - * Copyright (C) 2015-2021 Google, Inc. + * Copyright (C) 2015-2024 Google LLC */ #include <linux/rtnetlink.h> @@ -74,7 +74,8 @@ static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] = { "adminq_create_tx_queue_cnt", "adminq_create_rx_queue_cnt", "adminq_destroy_tx_queue_cnt", "adminq_destroy_rx_queue_cnt", "adminq_dcfg_device_resources_cnt", "adminq_set_driver_parameter_cnt", - "adminq_report_stats_cnt", "adminq_report_link_speed_cnt", "adminq_get_ptype_map_cnt" + "adminq_report_stats_cnt", "adminq_report_link_speed_cnt", "adminq_get_ptype_map_cnt", + "adminq_query_flow_rules", "adminq_cfg_flow_rule", }; static const char gve_gstrings_priv_flags[][ETH_GSTRING_LEN] = { @@ -450,6 +451,8 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = priv->adminq_report_stats_cnt; data[i++] = priv->adminq_report_link_speed_cnt; data[i++] = priv->adminq_get_ptype_map_cnt; + data[i++] = priv->adminq_query_flow_rules_cnt; + data[i++] = priv->adminq_cfg_flow_rule_cnt; } static void gve_get_channels(struct net_device *netdev, @@ -772,6 +775,69 @@ static int gve_set_coalesce(struct net_device *netdev, return 0; } +static int gve_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd) +{ + struct gve_priv *priv = netdev_priv(netdev); + int err = 0; + + if (!(netdev->features & NETIF_F_NTUPLE)) + return -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_SRXCLSRLINS: + err = gve_add_flow_rule(priv, cmd); + break; + case ETHTOOL_SRXCLSRLDEL: + err = gve_del_flow_rule(priv, cmd); + break; + case ETHTOOL_SRXFH: + err = -EOPNOTSUPP; + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + +static int gve_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, u32 *rule_locs) +{ + struct gve_priv *priv = netdev_priv(netdev); + int err = 0; + + switch (cmd->cmd) { + case ETHTOOL_GRXRINGS: + cmd->data = priv->rx_cfg.num_queues; + break; + case ETHTOOL_GRXCLSRLCNT: + if (!priv->max_flow_rules) + return -EOPNOTSUPP; + + err = gve_adminq_query_flow_rules(priv, GVE_FLOW_RULE_QUERY_STATS, 0); + if (err) + return err; + + cmd->rule_cnt = priv->num_flow_rules; + cmd->data = priv->max_flow_rules; + break; + case ETHTOOL_GRXCLSRULE: + err = gve_get_flow_rule_entry(priv, cmd); + break; + case ETHTOOL_GRXCLSRLALL: + err = gve_get_flow_rule_ids(priv, cmd, (u32 *)rule_locs); + break; + case ETHTOOL_GRXFH: + err = -EOPNOTSUPP; + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + const struct ethtool_ops gve_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS, .supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT, @@ -783,6 +849,8 @@ const struct ethtool_ops gve_ethtool_ops = { .get_msglevel = gve_get_msglevel, .set_channels = gve_set_channels, .get_channels = gve_get_channels, + .set_rxnfc = gve_set_rxnfc, + .get_rxnfc = gve_get_rxnfc, .get_link = ethtool_op_get_link, .get_coalesce = gve_get_coalesce, .set_coalesce = gve_set_coalesce, diff --git a/drivers/net/ethernet/google/gve/gve_flow_rule.c b/drivers/net/ethernet/google/gve/gve_flow_rule.c new file mode 100644 index 000000000000..0bb8cd1876a3 --- /dev/null +++ b/drivers/net/ethernet/google/gve/gve_flow_rule.c @@ -0,0 +1,298 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Google virtual Ethernet (gve) driver + * + * Copyright (C) 2015-2024 Google LLC + */ + +#include "gve.h" +#include "gve_adminq.h" + +static +int gve_fill_ethtool_flow_spec(struct ethtool_rx_flow_spec *fsp, + struct gve_adminq_queried_flow_rule *rule) +{ + struct gve_adminq_flow_rule *flow_rule = &rule->flow_rule; + static const u16 flow_type_lut[] = { + [GVE_FLOW_TYPE_TCPV4] = TCP_V4_FLOW, + [GVE_FLOW_TYPE_UDPV4] = UDP_V4_FLOW, + [GVE_FLOW_TYPE_SCTPV4] = SCTP_V4_FLOW, + [GVE_FLOW_TYPE_AHV4] = AH_V4_FLOW, + [GVE_FLOW_TYPE_ESPV4] = ESP_V4_FLOW, + [GVE_FLOW_TYPE_TCPV6] = TCP_V6_FLOW, + [GVE_FLOW_TYPE_UDPV6] = UDP_V6_FLOW, + [GVE_FLOW_TYPE_SCTPV6] = SCTP_V6_FLOW, + [GVE_FLOW_TYPE_AHV6] = AH_V6_FLOW, + [GVE_FLOW_TYPE_ESPV6] = ESP_V6_FLOW, + }; + + if (be16_to_cpu(flow_rule->flow_type) >= ARRAY_SIZE(flow_type_lut)) + return -EINVAL; + + fsp->flow_type = flow_type_lut[be16_to_cpu(flow_rule->flow_type)]; + + memset(&fsp->h_u, 0, sizeof(fsp->h_u)); + memset(&fsp->h_ext, 0, sizeof(fsp->h_ext)); + memset(&fsp->m_u, 0, sizeof(fsp->m_u)); + memset(&fsp->m_ext, 0, sizeof(fsp->m_ext)); + + switch (fsp->flow_type) { + case TCP_V4_FLOW: + case UDP_V4_FLOW: + case SCTP_V4_FLOW: + fsp->h_u.tcp_ip4_spec.ip4src = flow_rule->key.src_ip[0]; + fsp->h_u.tcp_ip4_spec.ip4dst = flow_rule->key.dst_ip[0]; + fsp->h_u.tcp_ip4_spec.psrc = flow_rule->key.src_port; + fsp->h_u.tcp_ip4_spec.pdst = flow_rule->key.dst_port; + fsp->h_u.tcp_ip4_spec.tos = flow_rule->key.tos; + fsp->m_u.tcp_ip4_spec.ip4src = flow_rule->mask.src_ip[0]; + fsp->m_u.tcp_ip4_spec.ip4dst = flow_rule->mask.dst_ip[0]; + fsp->m_u.tcp_ip4_spec.psrc = flow_rule->mask.src_port; + fsp->m_u.tcp_ip4_spec.pdst = flow_rule->mask.dst_port; + fsp->m_u.tcp_ip4_spec.tos = flow_rule->mask.tos; + break; + case AH_V4_FLOW: + case ESP_V4_FLOW: + fsp->h_u.ah_ip4_spec.ip4src = flow_rule->key.src_ip[0]; + fsp->h_u.ah_ip4_spec.ip4dst = flow_rule->key.dst_ip[0]; + fsp->h_u.ah_ip4_spec.spi = flow_rule->key.spi; + fsp->h_u.ah_ip4_spec.tos = flow_rule->key.tos; + fsp->m_u.ah_ip4_spec.ip4src = flow_rule->mask.src_ip[0]; + fsp->m_u.ah_ip4_spec.ip4dst = flow_rule->mask.dst_ip[0]; + fsp->m_u.ah_ip4_spec.spi = flow_rule->mask.spi; + fsp->m_u.ah_ip4_spec.tos = flow_rule->mask.tos; + break; + case TCP_V6_FLOW: + case UDP_V6_FLOW: + case SCTP_V6_FLOW: + memcpy(fsp->h_u.tcp_ip6_spec.ip6src, &flow_rule->key.src_ip, + sizeof(struct in6_addr)); + memcpy(fsp->h_u.tcp_ip6_spec.ip6dst, &flow_rule->key.dst_ip, + sizeof(struct in6_addr)); + fsp->h_u.tcp_ip6_spec.psrc = flow_rule->key.src_port; + fsp->h_u.tcp_ip6_spec.pdst = flow_rule->key.dst_port; + fsp->h_u.tcp_ip6_spec.tclass = flow_rule->key.tclass; + memcpy(fsp->m_u.tcp_ip6_spec.ip6src, &flow_rule->mask.src_ip, + sizeof(struct in6_addr)); + memcpy(fsp->m_u.tcp_ip6_spec.ip6dst, &flow_rule->mask.dst_ip, + sizeof(struct in6_addr)); + fsp->m_u.tcp_ip6_spec.psrc = flow_rule->mask.src_port; + fsp->m_u.tcp_ip6_spec.pdst = flow_rule->mask.dst_port; + fsp->m_u.tcp_ip6_spec.tclass = flow_rule->mask.tclass; + break; + case AH_V6_FLOW: + case ESP_V6_FLOW: + memcpy(fsp->h_u.ah_ip6_spec.ip6src, &flow_rule->key.src_ip, + sizeof(struct in6_addr)); + memcpy(fsp->h_u.ah_ip6_spec.ip6dst, &flow_rule->key.dst_ip, + sizeof(struct in6_addr)); + fsp->h_u.ah_ip6_spec.spi = flow_rule->key.spi; + fsp->h_u.ah_ip6_spec.tclass = flow_rule->key.tclass; + memcpy(fsp->m_u.ah_ip6_spec.ip6src, &flow_rule->mask.src_ip, + sizeof(struct in6_addr)); + memcpy(fsp->m_u.ah_ip6_spec.ip6dst, &flow_rule->mask.dst_ip, + sizeof(struct in6_addr)); + fsp->m_u.ah_ip6_spec.spi = flow_rule->mask.spi; + fsp->m_u.ah_ip6_spec.tclass = flow_rule->mask.tclass; + break; + default: + return -EINVAL; + } + + fsp->ring_cookie = be16_to_cpu(flow_rule->action); + + return 0; +} + +static int gve_generate_flow_rule(struct gve_priv *priv, struct ethtool_rx_flow_spec *fsp, + struct gve_adminq_flow_rule *rule) +{ + static const u16 flow_type_lut[] = { + [TCP_V4_FLOW] = GVE_FLOW_TYPE_TCPV4, + [UDP_V4_FLOW] = GVE_FLOW_TYPE_UDPV4, + [SCTP_V4_FLOW] = GVE_FLOW_TYPE_SCTPV4, + [AH_V4_FLOW] = GVE_FLOW_TYPE_AHV4, + [ESP_V4_FLOW] = GVE_FLOW_TYPE_ESPV4, + [TCP_V6_FLOW] = GVE_FLOW_TYPE_TCPV6, + [UDP_V6_FLOW] = GVE_FLOW_TYPE_UDPV6, + [SCTP_V6_FLOW] = GVE_FLOW_TYPE_SCTPV6, + [AH_V6_FLOW] = GVE_FLOW_TYPE_AHV6, + [ESP_V6_FLOW] = GVE_FLOW_TYPE_ESPV6, + }; + u32 flow_type; + + if (fsp->ring_cookie == RX_CLS_FLOW_DISC) + return -EOPNOTSUPP; + + if (fsp->ring_cookie >= priv->rx_cfg.num_queues) + return -EINVAL; + + rule->action = cpu_to_be16(fsp->ring_cookie); + + flow_type = fsp->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS); + if (!flow_type || flow_type >= ARRAY_SIZE(flow_type_lut)) + return -EINVAL; + + rule->flow_type = cpu_to_be16(flow_type_lut[flow_type]); + + switch (flow_type) { + case TCP_V4_FLOW: + case UDP_V4_FLOW: + case SCTP_V4_FLOW: + rule->key.src_ip[0] = fsp->h_u.tcp_ip4_spec.ip4src; + rule->key.dst_ip[0] = fsp->h_u.tcp_ip4_spec.ip4dst; + rule->key.src_port = fsp->h_u.tcp_ip4_spec.psrc; + rule->key.dst_port = fsp->h_u.tcp_ip4_spec.pdst; + rule->mask.src_ip[0] = fsp->m_u.tcp_ip4_spec.ip4src; + rule->mask.dst_ip[0] = fsp->m_u.tcp_ip4_spec.ip4dst; + rule->mask.src_port = fsp->m_u.tcp_ip4_spec.psrc; + rule->mask.dst_port = fsp->m_u.tcp_ip4_spec.pdst; + break; + case AH_V4_FLOW: + case ESP_V4_FLOW: + rule->key.src_ip[0] = fsp->h_u.tcp_ip4_spec.ip4src; + rule->key.dst_ip[0] = fsp->h_u.tcp_ip4_spec.ip4dst; + rule->key.spi = fsp->h_u.ah_ip4_spec.spi; + rule->mask.src_ip[0] = fsp->m_u.tcp_ip4_spec.ip4src; + rule->mask.dst_ip[0] = fsp->m_u.tcp_ip4_spec.ip4dst; + rule->mask.spi = fsp->m_u.ah_ip4_spec.spi; + break; + case TCP_V6_FLOW: + case UDP_V6_FLOW: + case SCTP_V6_FLOW: + memcpy(&rule->key.src_ip, fsp->h_u.tcp_ip6_spec.ip6src, + sizeof(struct in6_addr)); + memcpy(&rule->key.dst_ip, fsp->h_u.tcp_ip6_spec.ip6dst, + sizeof(struct in6_addr)); + rule->key.src_port = fsp->h_u.tcp_ip6_spec.psrc; + rule->key.dst_port = fsp->h_u.tcp_ip6_spec.pdst; + memcpy(&rule->mask.src_ip, fsp->m_u.tcp_ip6_spec.ip6src, + sizeof(struct in6_addr)); + memcpy(&rule->mask.dst_ip, fsp->m_u.tcp_ip6_spec.ip6dst, + sizeof(struct in6_addr)); + rule->mask.src_port = fsp->m_u.tcp_ip6_spec.psrc; + rule->mask.dst_port = fsp->m_u.tcp_ip6_spec.pdst; + break; + case AH_V6_FLOW: + case ESP_V6_FLOW: + memcpy(&rule->key.src_ip, fsp->h_u.usr_ip6_spec.ip6src, + sizeof(struct in6_addr)); + memcpy(&rule->key.dst_ip, fsp->h_u.usr_ip6_spec.ip6dst, + sizeof(struct in6_addr)); + rule->key.spi = fsp->h_u.ah_ip6_spec.spi; + memcpy(&rule->mask.src_ip, fsp->m_u.usr_ip6_spec.ip6src, + sizeof(struct in6_addr)); + memcpy(&rule->mask.dst_ip, fsp->m_u.usr_ip6_spec.ip6dst, + sizeof(struct in6_addr)); + rule->key.spi = fsp->h_u.ah_ip6_spec.spi; + break; + default: + /* not doing un-parsed flow types */ + return -EINVAL; + } + + return 0; +} + +int gve_get_flow_rule_entry(struct gve_priv *priv, struct ethtool_rxnfc *cmd) +{ + struct gve_adminq_queried_flow_rule *rules_cache = priv->flow_rules_cache.rules_cache; + struct ethtool_rx_flow_spec *fsp = (struct ethtool_rx_flow_spec *)&cmd->fs; + u32 *cache_num = &priv->flow_rules_cache.rules_cache_num; + struct gve_adminq_queried_flow_rule *rule = NULL; + int err = 0; + u32 i; + + if (!priv->max_flow_rules) + return -EOPNOTSUPP; + + if (!priv->flow_rules_cache.rules_cache_synced || + fsp->location < be32_to_cpu(rules_cache[0].location) || + fsp->location > be32_to_cpu(rules_cache[*cache_num - 1].location)) { + err = gve_adminq_query_flow_rules(priv, GVE_FLOW_RULE_QUERY_RULES, fsp->location); + if (err) + return err; + + priv->flow_rules_cache.rules_cache_synced = true; + } + + for (i = 0; i < *cache_num; i++) { + if (fsp->location == be32_to_cpu(rules_cache[i].location)) { + rule = &rules_cache[i]; + break; + } + } + + if (!rule) + return -EINVAL; + + err = gve_fill_ethtool_flow_spec(fsp, rule); + + return err; +} + +int gve_get_flow_rule_ids(struct gve_priv *priv, struct ethtool_rxnfc *cmd, u32 *rule_locs) +{ + __be32 *rule_ids_cache = priv->flow_rules_cache.rule_ids_cache; + u32 *cache_num = &priv->flow_rules_cache.rule_ids_cache_num; + u32 starting_rule_id = 0; + u32 i = 0, j = 0; + int err = 0; + + if (!priv->max_flow_rules) + return -EOPNOTSUPP; + + do { + err = gve_adminq_query_flow_rules(priv, GVE_FLOW_RULE_QUERY_IDS, + starting_rule_id); + if (err) + return err; + + for (i = 0; i < *cache_num; i++) { + if (j >= cmd->rule_cnt) + return -EMSGSIZE; + + rule_locs[j++] = be32_to_cpu(rule_ids_cache[i]); + starting_rule_id = be32_to_cpu(rule_ids_cache[i]) + 1; + } + } while (*cache_num != 0); + cmd->data = priv->max_flow_rules; + + return err; +} + +int gve_add_flow_rule(struct gve_priv *priv, struct ethtool_rxnfc *cmd) +{ + struct ethtool_rx_flow_spec *fsp = &cmd->fs; + struct gve_adminq_flow_rule *rule = NULL; + int err; + + if (!priv->max_flow_rules) + return -EOPNOTSUPP; + + rule = kvzalloc(sizeof(*rule), GFP_KERNEL); + if (!rule) + return -ENOMEM; + + err = gve_generate_flow_rule(priv, fsp, rule); + if (err) + goto out; + + err = gve_adminq_add_flow_rule(priv, rule, fsp->location); + +out: + kvfree(rule); + if (err) + dev_err(&priv->pdev->dev, "Failed to add the flow rule: %u", fsp->location); + + return err; +} + +int gve_del_flow_rule(struct gve_priv *priv, struct ethtool_rxnfc *cmd) +{ + struct ethtool_rx_flow_spec *fsp = (struct ethtool_rx_flow_spec *)&cmd->fs; + + if (!priv->max_flow_rules) + return -EOPNOTSUPP; + + return gve_adminq_del_flow_rule(priv, fsp->location); +} diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index cabf7d4bcecb..9744b426940e 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: (GPL-2.0 OR MIT) /* Google virtual Ethernet (gve) driver * - * Copyright (C) 2015-2021 Google, Inc. + * Copyright (C) 2015-2024 Google LLC */ #include <linux/bpf.h> @@ -141,6 +141,49 @@ static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s) } } +static int gve_alloc_flow_rule_caches(struct gve_priv *priv) +{ + struct gve_flow_rules_cache *flow_rules_cache = &priv->flow_rules_cache; + int err = 0; + + if (!priv->max_flow_rules) + return 0; + + flow_rules_cache->rules_cache = + kvcalloc(GVE_FLOW_RULES_CACHE_SIZE, sizeof(*flow_rules_cache->rules_cache), + GFP_KERNEL); + if (!flow_rules_cache->rules_cache) { + dev_err(&priv->pdev->dev, "Cannot alloc flow rules cache\n"); + return -ENOMEM; + } + + flow_rules_cache->rule_ids_cache = + kvcalloc(GVE_FLOW_RULE_IDS_CACHE_SIZE, sizeof(*flow_rules_cache->rule_ids_cache), + GFP_KERNEL); + if (!flow_rules_cache->rule_ids_cache) { + dev_err(&priv->pdev->dev, "Cannot alloc flow rule ids cache\n"); + err = -ENOMEM; + goto free_rules_cache; + } + + return 0; + +free_rules_cache: + kvfree(flow_rules_cache->rules_cache); + flow_rules_cache->rules_cache = NULL; + return err; +} + +static void gve_free_flow_rule_caches(struct gve_priv *priv) +{ + struct gve_flow_rules_cache *flow_rules_cache = &priv->flow_rules_cache; + + kvfree(flow_rules_cache->rule_ids_cache); + flow_rules_cache->rule_ids_cache = NULL; + kvfree(flow_rules_cache->rules_cache); + flow_rules_cache->rules_cache = NULL; +} + static int gve_alloc_counter_array(struct gve_priv *priv) { priv->counter_array = @@ -521,9 +564,12 @@ static int gve_setup_device_resources(struct gve_priv *priv) { int err; - err = gve_alloc_counter_array(priv); + err = gve_alloc_flow_rule_caches(priv); if (err) return err; + err = gve_alloc_counter_array(priv); + if (err) + goto abort_with_flow_rule_caches; err = gve_alloc_notify_blocks(priv); if (err) goto abort_with_counter; @@ -575,6 +621,8 @@ abort_with_ntfy_blocks: gve_free_notify_blocks(priv); abort_with_counter: gve_free_counter_array(priv); +abort_with_flow_rule_caches: + gve_free_flow_rule_caches(priv); return err; } @@ -587,6 +635,12 @@ static void gve_teardown_device_resources(struct gve_priv *priv) /* Tell device its resources are being freed */ if (gve_get_device_resources_ok(priv)) { + err = gve_flow_rules_reset(priv); + if (err) { + dev_err(&priv->pdev->dev, + "Failed to reset flow rules: err=%d\n", err); + gve_trigger_reset(priv); + } /* detach the stats report */ err = gve_adminq_report_stats(priv, 0, 0x0, GVE_STATS_REPORT_TIMER_PERIOD); if (err) { @@ -606,6 +660,7 @@ static void gve_teardown_device_resources(struct gve_priv *priv) kvfree(priv->ptype_lut_dqo); priv->ptype_lut_dqo = NULL; + gve_free_flow_rule_caches(priv); gve_free_counter_array(priv); gve_free_notify_blocks(priv); gve_free_stats_report(priv); @@ -1730,6 +1785,14 @@ static int gve_xdp(struct net_device *dev, struct netdev_bpf *xdp) } } +int gve_flow_rules_reset(struct gve_priv *priv) +{ + if (!priv->max_flow_rules) + return 0; + + return gve_adminq_reset_flow_rules(priv); +} + int gve_adjust_config(struct gve_priv *priv, struct gve_tx_alloc_rings_cfg *tx_alloc_cfg, struct gve_rx_alloc_rings_cfg *rx_alloc_cfg) @@ -2003,15 +2066,21 @@ static int gve_set_features(struct net_device *netdev, netdev->features ^= NETIF_F_LRO; if (netif_carrier_ok(netdev)) { err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg); - if (err) { - /* Revert the change on error. */ - netdev->features = orig_features; - return err; - } + if (err) + goto revert_features; } } + if ((netdev->features & NETIF_F_NTUPLE) && !(features & NETIF_F_NTUPLE)) { + err = gve_flow_rules_reset(priv); + if (err) + goto revert_features; + } return 0; + +revert_features: + netdev->features = orig_features; + return err; } static const struct net_device_ops gve_netdev_ops = { diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index c1c912de59c7..1154c1d8f66f 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -647,11 +647,13 @@ static void gve_rx_skb_hash(struct sk_buff *skb, skb_set_hash(skb, le32_to_cpu(compl_desc->hash), hash_type); } -static void gve_rx_free_skb(struct gve_rx_ring *rx) +static void gve_rx_free_skb(struct napi_struct *napi, struct gve_rx_ring *rx) { if (!rx->ctx.skb_head) return; + if (rx->ctx.skb_head == napi->skb) + napi->skb = NULL; dev_kfree_skb_any(rx->ctx.skb_head); rx->ctx.skb_head = NULL; rx->ctx.skb_tail = NULL; @@ -950,7 +952,7 @@ int gve_rx_poll_dqo(struct gve_notify_block *block, int budget) err = gve_rx_dqo(napi, rx, compl_desc, complq->head, rx->q_num); if (err < 0) { - gve_rx_free_skb(rx); + gve_rx_free_skb(napi, rx); u64_stats_update_begin(&rx->statss); if (err == -ENOMEM) rx->rx_skb_alloc_fail++; @@ -993,7 +995,7 @@ int gve_rx_poll_dqo(struct gve_notify_block *block, int budget) /* gve_rx_complete_skb() will consume skb if successful */ if (gve_rx_complete_skb(rx, napi, compl_desc, feat) != 0) { - gve_rx_free_skb(rx); + gve_rx_free_skb(napi, rx); u64_stats_update_begin(&rx->statss); rx->rx_desc_err_dropped_pkt++; u64_stats_update_end(&rx->statss); diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c index fe1b26a4d736..0b3cca3fc792 100644 --- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c @@ -555,28 +555,18 @@ static int gve_prep_tso(struct sk_buff *skb) if (unlikely(skb_shinfo(skb)->gso_size < GVE_TX_MIN_TSO_MSS_DQO)) return -1; + if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) + return -EINVAL; + /* Needed because we will modify header. */ err = skb_cow_head(skb, 0); if (err < 0) return err; tcp = tcp_hdr(skb); - - /* Remove payload length from checksum. */ paylen = skb->len - skb_transport_offset(skb); - - switch (skb_shinfo(skb)->gso_type) { - case SKB_GSO_TCPV4: - case SKB_GSO_TCPV6: - csum_replace_by_diff(&tcp->check, - (__force __wsum)htonl(paylen)); - - /* Compute length of segmentation header. */ - header_len = skb_tcp_all_headers(skb); - break; - default: - return -EINVAL; - } + csum_replace_by_diff(&tcp->check, (__force __wsum)htonl(paylen)); + header_len = skb_tcp_all_headers(skb); if (unlikely(header_len > GVE_TX_MAX_HDR_SIZE_DQO)) return -EINVAL; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index ff71fb1eced9..a5fc0209d628 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -3535,6 +3535,9 @@ static int hns3_alloc_ring_buffers(struct hns3_enet_ring *ring) ret = hns3_alloc_and_attach_buffer(ring, i); if (ret) goto out_buffer_fail; + + if (!(i % HNS3_RESCHED_BD_NUM)) + cond_resched(); } return 0; @@ -5107,6 +5110,7 @@ int hns3_init_all_ring(struct hns3_nic_priv *priv) } u64_stats_init(&priv->ring[i].syncp); + cond_resched(); } return 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index acd756b0c7c9..d36c4ed16d8d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -214,6 +214,8 @@ enum hns3_nic_state { #define HNS3_CQ_MODE_EQE 1U #define HNS3_CQ_MODE_CQE 0U +#define HNS3_RESCHED_BD_NUM 1024 + enum hns3_pkt_l2t_type { HNS3_L2_TYPE_UNICAST, HNS3_L2_TYPE_MULTICAST, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 43cc6ee4d87d..82574ce0194f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -3086,9 +3086,7 @@ static void hclge_push_link_status(struct hclge_dev *hdev) static void hclge_update_link_status(struct hclge_dev *hdev) { - struct hnae3_handle *rhandle = &hdev->vport[0].roce; struct hnae3_handle *handle = &hdev->vport[0].nic; - struct hnae3_client *rclient = hdev->roce_client; struct hnae3_client *client = hdev->nic_client; int state; int ret; @@ -3112,8 +3110,15 @@ static void hclge_update_link_status(struct hclge_dev *hdev) client->ops->link_status_change(handle, state); hclge_config_mac_tnl_int(hdev, state); - if (rclient && rclient->ops->link_status_change) - rclient->ops->link_status_change(rhandle, state); + + if (test_bit(HCLGE_STATE_ROCE_REGISTERED, &hdev->state)) { + struct hnae3_handle *rhandle = &hdev->vport[0].roce; + struct hnae3_client *rclient = hdev->roce_client; + + if (rclient && rclient->ops->link_status_change) + rclient->ops->link_status_change(rhandle, + state); + } hclge_push_link_status(hdev); } @@ -11319,6 +11324,12 @@ clear_roce: return ret; } +static bool hclge_uninit_need_wait(struct hclge_dev *hdev) +{ + return test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) || + test_bit(HCLGE_STATE_LINK_UPDATING, &hdev->state); +} + static void hclge_uninit_client_instance(struct hnae3_client *client, struct hnae3_ae_dev *ae_dev) { @@ -11327,7 +11338,7 @@ static void hclge_uninit_client_instance(struct hnae3_client *client, if (hdev->roce_client) { clear_bit(HCLGE_STATE_ROCE_REGISTERED, &hdev->state); - while (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) + while (hclge_uninit_need_wait(hdev)) msleep(HCLGE_WAIT_RESET_DONE); hdev->roce_client->ops->uninit_instance(&vport->roce, 0); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 5e9a93bdb518..23ebeb143987 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2482,6 +2482,18 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) (tx_pool->consumer_index + 1) % tx_pool->num_buffers; tx_buff = &tx_pool->tx_buff[bufidx]; + + /* Sanity checks on our free map to make sure it points to an index + * that is not being occupied by another skb. If skb memory is + * not freed then we see congestion control kick in and halt tx. + */ + if (unlikely(tx_buff->skb)) { + dev_warn_ratelimited(dev, "TX free map points to untracked skb (%s %d idx=%d)\n", + skb_is_gso(skb) ? "tso_pool" : "tx_pool", + queue_num, bufidx); + dev_kfree_skb_any(tx_buff->skb); + } + tx_buff->skb = skb; tx_buff->index = bufidx; tx_buff->pool_index = queue_num; @@ -4061,6 +4073,12 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter, bool do_h_free) adapter->num_active_tx_scrqs = 0; } + /* Clean any remaining outstanding SKBs + * we freed the irq so we won't be hearing + * from them + */ + clean_tx_pools(adapter); + if (adapter->rx_scrq) { for (i = 0; i < adapter->num_active_rx_scrqs; i++) { if (!adapter->rx_scrq[i]) diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index 704e9ad5144e..f774781ab514 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -794,10 +794,8 @@ int ice_devlink_rate_init_tx_topology(struct devlink *devlink, struct ice_vsi *v tc_node = pi->root->children[0]; mutex_lock(&pi->sched_lock); - devl_lock(devlink); for (i = 0; i < tc_node->num_children; i++) ice_traverse_tx_tree(devlink, tc_node->children[i], tc_node, pf); - devl_unlock(devlink); mutex_unlock(&pi->sched_lock); return 0; diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c index 13e6790d3cae..c9fbeebf7fb9 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c @@ -407,7 +407,7 @@ int ice_devlink_create_vf_port(struct ice_vf *vf) devlink_port_attrs_set(devlink_port, &attrs); devlink = priv_to_devlink(pf); - err = devlink_port_register(devlink, devlink_port, vsi->idx); + err = devl_port_register(devlink, devlink_port, vsi->idx); if (err) { dev_err(dev, "Failed to create devlink port for VF %d, error %d\n", vf->vf_id, err); @@ -426,5 +426,5 @@ int ice_devlink_create_vf_port(struct ice_vf *vf) void ice_devlink_destroy_vf_port(struct ice_vf *vf) { devl_rate_leaf_destroy(&vf->devlink_port); - devlink_port_unregister(&vf->devlink_port); + devl_port_unregister(&vf->devlink_port); } diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c index ce5034ed2b24..f182179529b7 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -1339,6 +1339,7 @@ ice_dwnld_cfg_bufs_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 start, for (i = 0; i < count; i++) { bool last = false; + int try_cnt = 0; int status; bh = (struct ice_buf_hdr *)(bufs + start + i); @@ -1346,8 +1347,26 @@ ice_dwnld_cfg_bufs_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 start, if (indicate_last) last = ice_is_last_download_buffer(bh, i, count); - status = ice_aq_download_pkg(hw, bh, ICE_PKG_BUF_SIZE, last, - &offset, &info, NULL); + while (1) { + status = ice_aq_download_pkg(hw, bh, ICE_PKG_BUF_SIZE, + last, &offset, &info, + NULL); + if (hw->adminq.sq_last_status != ICE_AQ_RC_ENOSEC && + hw->adminq.sq_last_status != ICE_AQ_RC_EBADSIG) + break; + + try_cnt++; + + if (try_cnt == 5) + break; + + msleep(20); + } + + if (try_cnt) + dev_dbg(ice_hw_to_dev(hw), + "ice_aq_download_pkg number of retries: %d\n", + try_cnt); /* Save AQ status from download package */ if (status) { diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index b102db8b829a..4f539b1c7781 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -117,17 +117,10 @@ static int ice_eswitch_setup_repr(struct ice_pf *pf, struct ice_repr *repr) struct ice_vsi *vsi = repr->src_vsi; struct metadata_dst *dst; - ice_remove_vsi_fltr(&pf->hw, vsi->idx); repr->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX, GFP_KERNEL); if (!repr->dst) - goto err_add_mac_fltr; - - if (ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof)) - goto err_dst_free; - - if (ice_vsi_add_vlan_zero(vsi)) - goto err_update_security; + return -ENOMEM; netif_keep_dst(uplink_vsi->netdev); @@ -136,16 +129,48 @@ static int ice_eswitch_setup_repr(struct ice_pf *pf, struct ice_repr *repr) dst->u.port_info.lower_dev = uplink_vsi->netdev; return 0; +} -err_update_security: +/** + * ice_eswitch_cfg_vsi - configure VSI to work in slow-path + * @vsi: VSI structure of representee + * @mac: representee MAC + * + * Return: 0 on success, non-zero on error. + */ +int ice_eswitch_cfg_vsi(struct ice_vsi *vsi, const u8 *mac) +{ + int err; + + ice_remove_vsi_fltr(&vsi->back->hw, vsi->idx); + + err = ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof); + if (err) + goto err_update_security; + + err = ice_vsi_add_vlan_zero(vsi); + if (err) + goto err_vlan_zero; + + return 0; + +err_vlan_zero: ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof); -err_dst_free: - metadata_dst_free(repr->dst); - repr->dst = NULL; -err_add_mac_fltr: - ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac, ICE_FWD_TO_VSI); +err_update_security: + ice_fltr_add_mac_and_broadcast(vsi, mac, ICE_FWD_TO_VSI); - return -ENODEV; + return err; +} + +/** + * ice_eswitch_decfg_vsi - unroll changes done to VSI for switchdev + * @vsi: VSI structure of representee + * @mac: representee MAC + */ +void ice_eswitch_decfg_vsi(struct ice_vsi *vsi, const u8 *mac) +{ + ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof); + ice_fltr_add_mac_and_broadcast(vsi, mac, ICE_FWD_TO_VSI); } /** @@ -153,16 +178,16 @@ err_add_mac_fltr: * @repr_id: representor ID * @vsi: VSI for which port representor is configured */ -void ice_eswitch_update_repr(unsigned long repr_id, struct ice_vsi *vsi) +void ice_eswitch_update_repr(unsigned long *repr_id, struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; struct ice_repr *repr; - int ret; + int err; if (!ice_is_switchdev_running(pf)) return; - repr = xa_load(&pf->eswitch.reprs, repr_id); + repr = xa_load(&pf->eswitch.reprs, *repr_id); if (!repr) return; @@ -172,12 +197,19 @@ void ice_eswitch_update_repr(unsigned long repr_id, struct ice_vsi *vsi) if (repr->br_port) repr->br_port->vsi = vsi; - ret = ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof); - if (ret) { - ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac, - ICE_FWD_TO_VSI); + err = ice_eswitch_cfg_vsi(vsi, repr->parent_mac); + if (err) dev_err(ice_pf_to_dev(pf), "Failed to update VSI of port representor %d", repr->id); + + /* The VSI number is different, reload the PR with new id */ + if (repr->id != vsi->vsi_num) { + xa_erase(&pf->eswitch.reprs, repr->id); + repr->id = vsi->vsi_num; + if (xa_insert(&pf->eswitch.reprs, repr->id, repr, GFP_KERNEL)) + dev_err(ice_pf_to_dev(pf), "Failed to reload port representor %d", + repr->id); + *repr_id = repr->id; } } @@ -423,6 +455,7 @@ static void ice_eswitch_start_reprs(struct ice_pf *pf) int ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf) { + struct devlink *devlink = priv_to_devlink(pf); struct ice_repr *repr; int err; @@ -437,7 +470,9 @@ ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf) ice_eswitch_stop_reprs(pf); + devl_lock(devlink); repr = ice_repr_add_vf(vf); + devl_unlock(devlink); if (IS_ERR(repr)) { err = PTR_ERR(repr); goto err_create_repr; @@ -460,7 +495,9 @@ ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf) err_xa_alloc: ice_eswitch_release_repr(pf, repr); err_setup_repr: + devl_lock(devlink); ice_repr_rem_vf(repr); + devl_unlock(devlink); err_create_repr: if (xa_empty(&pf->eswitch.reprs)) ice_eswitch_disable_switchdev(pf); @@ -484,6 +521,7 @@ void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf) ice_eswitch_disable_switchdev(pf); ice_eswitch_release_repr(pf, repr); + devl_lock(devlink); ice_repr_rem_vf(repr); if (xa_empty(&pf->eswitch.reprs)) { @@ -491,12 +529,11 @@ void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf) * no point in keeping the nodes */ ice_devlink_rate_clear_tx_topology(ice_get_main_vsi(pf)); - devl_lock(devlink); devl_rate_nodes_destroy(devlink); - devl_unlock(devlink); } else { ice_eswitch_start_reprs(pf); } + devl_unlock(devlink); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.h b/drivers/net/ethernet/intel/ice/ice_eswitch.h index e2e5c0c75e7d..09194d514f9b 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.h +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.h @@ -18,7 +18,7 @@ ice_eswitch_mode_set(struct devlink *devlink, u16 mode, struct netlink_ext_ack *extack); bool ice_is_eswitch_mode_switchdev(struct ice_pf *pf); -void ice_eswitch_update_repr(unsigned long repr_id, struct ice_vsi *vsi); +void ice_eswitch_update_repr(unsigned long *repr_id, struct ice_vsi *vsi); void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf); @@ -28,6 +28,9 @@ netdev_tx_t ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev); struct net_device *ice_eswitch_get_target(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc); + +int ice_eswitch_cfg_vsi(struct ice_vsi *vsi, const u8 *mac); +void ice_eswitch_decfg_vsi(struct ice_vsi *vsi, const u8 *mac); #else /* CONFIG_ICE_SWITCHDEV */ static inline void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf) { } @@ -44,7 +47,7 @@ ice_eswitch_set_target_vsi(struct sk_buff *skb, struct ice_tx_offload_params *off) { } static inline void -ice_eswitch_update_repr(unsigned long repr_id, struct ice_vsi *vsi) { } +ice_eswitch_update_repr(unsigned long *repr_id, struct ice_vsi *vsi) { } static inline int ice_eswitch_configure(struct ice_pf *pf) { @@ -85,5 +88,12 @@ ice_eswitch_get_target(struct ice_rx_ring *rx_ring, { return rx_ring->netdev; } + +static inline int ice_eswitch_cfg_vsi(struct ice_vsi *vsi, const u8 *mac) +{ + return -EOPNOTSUPP; +} + +static inline void ice_eswitch_decfg_vsi(struct ice_vsi *vsi, const u8 *mac) { } #endif /* CONFIG_ICE_SWITCHDEV */ #endif /* _ICE_ESWITCH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c index ac5beecd028b..f5aceb32bf4d 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c @@ -896,7 +896,8 @@ ice_eswitch_br_port_deinit(struct ice_esw_br *bridge, if (br_port->type == ICE_ESWITCH_BR_UPLINK_PORT && vsi->back) { vsi->back->br_port = NULL; } else { - struct ice_repr *repr = ice_repr_get_by_vsi(vsi); + struct ice_repr *repr = + ice_repr_get(vsi->back, br_port->repr_id); if (repr) repr->br_port = NULL; @@ -937,6 +938,7 @@ ice_eswitch_br_vf_repr_port_init(struct ice_esw_br *bridge, br_port->vsi = repr->src_vsi; br_port->vsi_idx = br_port->vsi->idx; br_port->type = ICE_ESWITCH_BR_VF_REPR_PORT; + br_port->repr_id = repr->id; repr->br_port = br_port; err = xa_insert(&bridge->ports, br_port->vsi_idx, br_port, GFP_KERNEL); diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.h b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h index 85a8fadb2928..c15c7344d7f8 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch_br.h +++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h @@ -46,6 +46,7 @@ struct ice_esw_br_port { enum ice_esw_br_port_type type; u16 vsi_idx; u16 pvid; + u32 repr_id; struct xarray vlans; }; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 7d9a4e856f61..080efb7473aa 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -805,6 +805,9 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup) } switch (vsi->port_info->phy.link_info.link_speed) { + case ICE_AQ_LINK_SPEED_200GB: + speed = "200 G"; + break; case ICE_AQ_LINK_SPEED_100GB: speed = "100 G"; break; @@ -4136,7 +4139,7 @@ bool ice_is_wol_supported(struct ice_hw *hw) 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; + int i, err = 0, timeout = 50; if (!new_rx && !new_tx) return -EINVAL; @@ -4162,6 +4165,14 @@ int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked) ice_vsi_close(vsi); ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT); + + ice_for_each_traffic_class(i) { + if (vsi->tc_cfg.ena_tc & BIT(i)) + netdev_set_tc_queue(vsi->netdev, + vsi->tc_cfg.tc_info[i].netdev_tc, + vsi->tc_cfg.tc_info[i].qcount_tx, + vsi->tc_cfg.tc_info[i].qoffset); + } ice_pf_dcb_recfg(pf, locked); ice_vsi_open(vsi); done: @@ -5564,7 +5575,7 @@ static int ice_suspend(struct device *dev) */ disabled = ice_service_task_stop(pf); - ice_unplug_aux_dev(pf); + ice_deinit_rdma(pf); /* Already suspended?, then there is nothing to do */ if (test_and_set_bit(ICE_SUSPENDED, pf->state)) { @@ -5644,6 +5655,11 @@ static int ice_resume(struct device *dev) if (ret) dev_err(dev, "Cannot restore interrupt scheme: %d\n", ret); + ret = ice_init_rdma(pf); + if (ret) + dev_err(dev, "Reinitialize RDMA during resume failed: %d\n", + ret); + clear_bit(ICE_DOWN, pf->state); /* Now perform PF reset and rebuild */ reset_type = ICE_RESET_PFR; diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c index d367f4c66dcd..bdda3401e343 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.c +++ b/drivers/net/ethernet/intel/ice/ice_repr.c @@ -285,9 +285,7 @@ ice_repr_reg_netdev(struct net_device *netdev) static void ice_repr_remove_node(struct devlink_port *devlink_port) { - devl_lock(devlink_port->devlink); devl_rate_leaf_destroy(devlink_port); - devl_unlock(devlink_port->devlink); } /** @@ -308,6 +306,7 @@ static void ice_repr_rem(struct ice_repr *repr) void ice_repr_rem_vf(struct ice_repr *repr) { ice_repr_remove_node(&repr->vf->devlink_port); + ice_eswitch_decfg_vsi(repr->src_vsi, repr->parent_mac); unregister_netdev(repr->netdev); ice_devlink_destroy_vf_port(repr->vf); ice_virtchnl_set_dflt_ops(repr->vf); @@ -403,11 +402,17 @@ struct ice_repr *ice_repr_add_vf(struct ice_vf *vf) if (err) goto err_netdev; + err = ice_eswitch_cfg_vsi(repr->src_vsi, repr->parent_mac); + if (err) + goto err_cfg_vsi; + ice_virtchnl_set_repr_ops(vf); ice_repr_set_tx_topology(vf->pf); return repr; +err_cfg_vsi: + unregister_netdev(repr->netdev); err_netdev: ice_repr_rem(repr); err_repr_add: @@ -415,12 +420,9 @@ err_repr_add: return ERR_PTR(err); } -struct ice_repr *ice_repr_get_by_vsi(struct ice_vsi *vsi) +struct ice_repr *ice_repr_get(struct ice_pf *pf, u32 id) { - if (!vsi->vf) - return NULL; - - return xa_load(&vsi->back->eswitch.reprs, vsi->vf->repr_id); + return xa_load(&pf->eswitch.reprs, id); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_repr.h b/drivers/net/ethernet/intel/ice/ice_repr.h index cff730b15ca0..488661b2900b 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.h +++ b/drivers/net/ethernet/intel/ice/ice_repr.h @@ -35,9 +35,8 @@ void ice_repr_stop_tx_queues(struct ice_repr *repr); struct ice_repr *ice_netdev_to_repr(const struct net_device *netdev); bool ice_is_port_repr_netdev(const struct net_device *netdev); -struct ice_repr *ice_repr_get_by_vsi(struct ice_vsi *vsi); - void ice_repr_inc_tx_stats(struct ice_repr *repr, unsigned int len, int xmit_status); void ice_repr_inc_rx_stats(struct net_device *netdev, unsigned int len); +struct ice_repr *ice_repr_get(struct ice_pf *pf, u32 id); #endif diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 94d6670d0901..1191031b2a43 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -1899,7 +1899,8 @@ ice_aq_alloc_free_vsi_list(struct ice_hw *hw, u16 *vsi_list_id, lkup_type == ICE_SW_LKUP_ETHERTYPE_MAC || lkup_type == ICE_SW_LKUP_PROMISC || lkup_type == ICE_SW_LKUP_PROMISC_VLAN || - lkup_type == ICE_SW_LKUP_DFLT) { + lkup_type == ICE_SW_LKUP_DFLT || + lkup_type == ICE_SW_LKUP_LAST) { sw_buf->res_type = cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_REP); } else if (lkup_type == ICE_SW_LKUP_VLAN) { if (opc == ice_aqc_opc_alloc_res) @@ -2922,7 +2923,8 @@ ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi, lkup_type == ICE_SW_LKUP_ETHERTYPE_MAC || lkup_type == ICE_SW_LKUP_PROMISC || lkup_type == ICE_SW_LKUP_PROMISC_VLAN || - lkup_type == ICE_SW_LKUP_DFLT) + lkup_type == ICE_SW_LKUP_DFLT || + lkup_type == ICE_SW_LKUP_LAST) rule_type = remove ? ICE_AQC_SW_RULES_T_VSI_LIST_CLEAR : ICE_AQC_SW_RULES_T_VSI_LIST_SET; else if (lkup_type == ICE_SW_LKUP_VLAN) diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index 8bd24b33f3a6..e6923f8121a9 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -1353,6 +1353,7 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule, struct ice_tc_flower_fltr *fltr) { struct ice_tc_flower_lyr_2_4_hdrs *headers = &fltr->outer_headers; + struct netlink_ext_ack *extack = fltr->extack; struct flow_match_control enc_control; fltr->tunnel_type = ice_tc_tun_get_type(dev); @@ -1373,6 +1374,9 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule, flow_rule_match_enc_control(rule, &enc_control); + if (flow_rule_has_enc_control_flags(enc_control.mask->flags, extack)) + return -EOPNOTSUPP; + if (enc_control.key->addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { struct flow_match_ipv4_addrs match; diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 48a8d462d76a..5635e9da2212 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -948,7 +948,7 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) goto out_unlock; } - ice_eswitch_update_repr(vf->repr_id, vsi); + ice_eswitch_update_repr(&vf->repr_id, vsi); /* if the VF has been reset allow it to come up again */ ice_mbx_clear_malvf(&vf->mbx_info); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index fce2930ae6af..3af03a211c3c 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -9139,6 +9139,10 @@ static int igb_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) return -EIO; break; case SIOCSMIIREG: + if (igb_write_phy_reg(&adapter->hw, data->reg_num & 0x1F, + data->val_in)) + return -EIO; + break; default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 305e05294a26..87b655b839c1 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -7032,6 +7032,8 @@ static int igc_probe(struct pci_dev *pdev, device_set_wakeup_enable(&adapter->pdev->dev, adapter->flags & IGC_FLAG_WOL_SUPPORTED); + igc_ptp_init(adapter); + igc_tsn_clear_schedule(adapter); /* reset the hardware with the new settings */ @@ -7053,9 +7055,6 @@ static int igc_probe(struct pci_dev *pdev, /* Check if Media Autosense is enabled */ adapter->ei = *ei; - /* do hw tstamp init after resetting */ - igc_ptp_init(adapter); - /* print pcie link status and MAC address */ pcie_print_link_status(pdev); netdev_info(netdev, "MAC: %pM\n", netdev->dev_addr); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index e91486c48de3..9adf4301c9b1 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -4014,7 +4014,10 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, } } - skb = build_skb(data, frag_size); + if (frag_size) + skb = build_skb(data, frag_size); + else + skb = slab_build_skb(data); if (!skb) { netdev_warn(port->dev, "skb build failed\n"); goto err_drop_frame; @@ -6904,6 +6907,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, /* 9704 == 9728 - 20 and rounding to 8 */ dev->max_mtu = MVPP2_BM_JUMBO_PKT_SIZE; device_set_node(&dev->dev, port_fwnode); + dev->dev_port = port->id; port->pcs_gmac.ops = &mvpp2_phylink_gmac_pcs_ops; port->pcs_gmac.neg_mode = true; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile index 5664f768cb0c..64a97a0a10ed 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile @@ -9,10 +9,9 @@ obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o otx2_ptp.o rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \ otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \ otx2_devlink.o qos_sq.o qos.o -rvu_nicvf-y := otx2_vf.o otx2_devlink.o +rvu_nicvf-y := otx2_vf.o rvu_nicpf-$(CONFIG_DCB) += otx2_dcbnl.o -rvu_nicvf-$(CONFIG_DCB) += otx2_dcbnl.o rvu_nicpf-$(CONFIG_MACSEC) += cn10k_macsec.o ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index a85ac039d779..87d5776e3b88 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -648,14 +648,14 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl, int prio, bool txschq_for } else if (lvl == NIX_TXSCH_LVL_TL4) { parent = schq_list[NIX_TXSCH_LVL_TL3][prio]; req->reg[0] = NIX_AF_TL4X_PARENT(schq); - req->regval[0] = parent << 16; + req->regval[0] = (u64)parent << 16; req->num_regs++; req->reg[1] = NIX_AF_TL4X_SCHEDULE(schq); req->regval[1] = dwrr_val; } else if (lvl == NIX_TXSCH_LVL_TL3) { parent = schq_list[NIX_TXSCH_LVL_TL2][prio]; req->reg[0] = NIX_AF_TL3X_PARENT(schq); - req->regval[0] = parent << 16; + req->regval[0] = (u64)parent << 16; req->num_regs++; req->reg[1] = NIX_AF_TL3X_SCHEDULE(schq); req->regval[1] = dwrr_val; @@ -670,11 +670,11 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl, int prio, bool txschq_for } else if (lvl == NIX_TXSCH_LVL_TL2) { parent = schq_list[NIX_TXSCH_LVL_TL1][prio]; req->reg[0] = NIX_AF_TL2X_PARENT(schq); - req->regval[0] = parent << 16; + req->regval[0] = (u64)parent << 16; req->num_regs++; req->reg[1] = NIX_AF_TL2X_SCHEDULE(schq); - req->regval[1] = TXSCH_TL1_DFLT_RR_PRIO << 24 | dwrr_val; + req->regval[1] = (u64)hw->txschq_aggr_lvl_rr_prio << 24 | dwrr_val; if (lvl == hw->txschq_link_cfg_lvl) { req->num_regs++; @@ -698,7 +698,7 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl, int prio, bool txschq_for req->num_regs++; req->reg[1] = NIX_AF_TL1X_TOPOLOGY(schq); - req->regval[1] = (TXSCH_TL1_DFLT_RR_PRIO << 1); + req->regval[1] = hw->txschq_aggr_lvl_rr_prio << 1; req->num_regs++; req->reg[2] = NIX_AF_TL1X_CIR(schq); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 24fbbef265a6..f27a3456ae64 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -346,12 +346,9 @@ struct otx2_flow_config { u16 *def_ent; u16 nr_flows; #define OTX2_DEFAULT_FLOWCOUNT 16 -#define OTX2_MAX_UNICAST_FLOWS 8 +#define OTX2_DEFAULT_UNICAST_FLOWS 4 #define OTX2_MAX_VLAN_FLOWS 1 #define OTX2_MAX_TC_FLOWS OTX2_DEFAULT_FLOWCOUNT -#define OTX2_MCAM_COUNT (OTX2_DEFAULT_FLOWCOUNT + \ - OTX2_MAX_UNICAST_FLOWS + \ - OTX2_MAX_VLAN_FLOWS) u16 unicast_offset; u16 rx_vlan_offset; u16 vf_vlan_offset; @@ -365,6 +362,7 @@ struct otx2_flow_config { u16 max_flows; refcount_t mark_flows; struct list_head flow_list_tc; + u8 ucast_flt_cnt; bool ntuple; }; @@ -1067,6 +1065,7 @@ int otx2_handle_ntuple_tc_features(struct net_device *netdev, int otx2_smq_flush(struct otx2_nic *pfvf, int smq); void otx2_free_bufs(struct otx2_nic *pfvf, struct otx2_pool *pool, u64 iova, int size); +int otx2_mcam_entry_init(struct otx2_nic *pfvf); /* tc support */ int otx2_init_tc(struct otx2_nic *nic); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c index 28fb643d2917..aa01110f04a3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c @@ -54,6 +54,7 @@ int otx2_pfc_txschq_config(struct otx2_nic *pfvf) return 0; } +EXPORT_SYMBOL(otx2_pfc_txschq_config); static int otx2_pfc_txschq_alloc_one(struct otx2_nic *pfvf, u8 prio) { @@ -122,6 +123,7 @@ int otx2_pfc_txschq_alloc(struct otx2_nic *pfvf) return 0; } +EXPORT_SYMBOL(otx2_pfc_txschq_alloc); static int otx2_pfc_txschq_stop_one(struct otx2_nic *pfvf, u8 prio) { @@ -260,6 +262,7 @@ update_sq_smq_map: return 0; } +EXPORT_SYMBOL(otx2_pfc_txschq_update); int otx2_pfc_txschq_stop(struct otx2_nic *pfvf) { @@ -282,6 +285,7 @@ int otx2_pfc_txschq_stop(struct otx2_nic *pfvf) return 0; } +EXPORT_SYMBOL(otx2_pfc_txschq_stop); int otx2_config_priority_flow_ctrl(struct otx2_nic *pfvf) { @@ -321,6 +325,7 @@ unlock: mutex_unlock(&pfvf->mbox.lock); return err; } +EXPORT_SYMBOL(otx2_config_priority_flow_ctrl); void otx2_update_bpid_in_rqctx(struct otx2_nic *pfvf, int vlan_prio, int qidx, bool pfc_enable) @@ -385,6 +390,7 @@ out: "Updating BPIDs in CQ and Aura contexts of RQ%d failed with err %d\n", qidx, err); } +EXPORT_SYMBOL(otx2_update_bpid_in_rqctx); static int otx2_dcbnl_ieee_getpfc(struct net_device *dev, struct ieee_pfc *pfc) { @@ -472,3 +478,4 @@ int otx2_dcbnl_set_ops(struct net_device *dev) return 0; } +EXPORT_SYMBOL(otx2_dcbnl_set_ops); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c index 99ddf31269d9..53f14aa944bd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c @@ -64,9 +64,68 @@ static int otx2_dl_mcam_count_get(struct devlink *devlink, u32 id, return 0; } +static int otx2_dl_ucast_flt_cnt_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) +{ + struct otx2_devlink *otx2_dl = devlink_priv(devlink); + struct otx2_nic *pfvf = otx2_dl->pfvf; + int err; + + pfvf->flow_cfg->ucast_flt_cnt = ctx->val.vu8; + + otx2_mcam_flow_del(pfvf); + err = otx2_mcam_entry_init(pfvf); + if (err) + return err; + + return 0; +} + +static int otx2_dl_ucast_flt_cnt_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct otx2_devlink *otx2_dl = devlink_priv(devlink); + struct otx2_nic *pfvf = otx2_dl->pfvf; + + ctx->val.vu8 = pfvf->flow_cfg ? pfvf->flow_cfg->ucast_flt_cnt : 0; + + return 0; +} + +static int otx2_dl_ucast_flt_cnt_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + struct otx2_devlink *otx2_dl = devlink_priv(devlink); + struct otx2_nic *pfvf = otx2_dl->pfvf; + + /* Check for UNICAST filter support*/ + if (!(pfvf->flags & OTX2_FLAG_UCAST_FLTR_SUPPORT)) { + NL_SET_ERR_MSG_MOD(extack, + "Unicast filter not enabled"); + return -EINVAL; + } + + if (!pfvf->flow_cfg) { + NL_SET_ERR_MSG_MOD(extack, + "pfvf->flow_cfg not initialized"); + return -EINVAL; + } + + if (pfvf->flow_cfg->nr_flows) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot modify count when there are active rules"); + return -EINVAL; + } + + return 0; +} + enum otx2_dl_param_id { OTX2_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, OTX2_DEVLINK_PARAM_ID_MCAM_COUNT, + OTX2_DEVLINK_PARAM_ID_UCAST_FLT_CNT, }; static const struct devlink_param otx2_dl_params[] = { @@ -75,6 +134,11 @@ static const struct devlink_param otx2_dl_params[] = { BIT(DEVLINK_PARAM_CMODE_RUNTIME), otx2_dl_mcam_count_get, otx2_dl_mcam_count_set, otx2_dl_mcam_count_validate), + DEVLINK_PARAM_DRIVER(OTX2_DEVLINK_PARAM_ID_UCAST_FLT_CNT, + "unicast_filter_count", DEVLINK_PARAM_TYPE_U8, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + otx2_dl_ucast_flt_cnt_get, otx2_dl_ucast_flt_cnt_set, + otx2_dl_ucast_flt_cnt_validate), }; static const struct devlink_ops otx2_devlink_ops = { @@ -113,6 +177,7 @@ err_dl: devlink_free(dl); return err; } +EXPORT_SYMBOL(otx2_register_dl); void otx2_unregister_dl(struct otx2_nic *pfvf) { @@ -124,3 +189,4 @@ void otx2_unregister_dl(struct otx2_nic *pfvf) ARRAY_SIZE(otx2_dl_params)); devlink_free(dl); } +EXPORT_SYMBOL(otx2_unregister_dl); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c index bc5819237ed7..98c31a16c70b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c @@ -12,8 +12,6 @@ #define OTX2_DEFAULT_ACTION 0x1 -static int otx2_mcam_entry_init(struct otx2_nic *pfvf); - struct otx2_flow { struct ethtool_rx_flow_spec flow_spec; struct list_head list; @@ -161,7 +159,7 @@ exit: } EXPORT_SYMBOL(otx2_alloc_mcam_entries); -static int otx2_mcam_entry_init(struct otx2_nic *pfvf) +int otx2_mcam_entry_init(struct otx2_nic *pfvf) { struct otx2_flow_config *flow_cfg = pfvf->flow_cfg; struct npc_get_field_status_req *freq; @@ -172,7 +170,7 @@ static int otx2_mcam_entry_init(struct otx2_nic *pfvf) int ent, count; vf_vlan_max_flows = pfvf->total_vfs * OTX2_PER_VF_VLAN_FLOWS; - count = OTX2_MAX_UNICAST_FLOWS + + count = flow_cfg->ucast_flt_cnt + OTX2_MAX_VLAN_FLOWS + vf_vlan_max_flows; flow_cfg->def_ent = devm_kmalloc_array(pfvf->dev, count, @@ -214,7 +212,7 @@ static int otx2_mcam_entry_init(struct otx2_nic *pfvf) flow_cfg->vf_vlan_offset = 0; flow_cfg->unicast_offset = vf_vlan_max_flows; flow_cfg->rx_vlan_offset = flow_cfg->unicast_offset + - OTX2_MAX_UNICAST_FLOWS; + flow_cfg->ucast_flt_cnt; pfvf->flags |= OTX2_FLAG_UCAST_FLTR_SUPPORT; /* Check if NPC_DMAC field is supported @@ -255,6 +253,7 @@ static int otx2_mcam_entry_init(struct otx2_nic *pfvf) refcount_set(&flow_cfg->mark_flows, 1); return 0; } +EXPORT_SYMBOL(otx2_mcam_entry_init); /* TODO : revisit on size */ #define OTX2_DMAC_FLTR_BITMAP_SZ (4 * 2048 + 32) @@ -302,6 +301,8 @@ int otx2_mcam_flow_init(struct otx2_nic *pf) INIT_LIST_HEAD(&pf->flow_cfg->flow_list); INIT_LIST_HEAD(&pf->flow_cfg->flow_list_tc); + pf->flow_cfg->ucast_flt_cnt = OTX2_DEFAULT_UNICAST_FLOWS; + /* Allocate bare minimum number of MCAM entries needed for * unicast and ntuple filters. */ @@ -314,7 +315,7 @@ int otx2_mcam_flow_init(struct otx2_nic *pf) return 0; pf->mac_table = devm_kzalloc(pf->dev, sizeof(struct otx2_mac_table) - * OTX2_MAX_UNICAST_FLOWS, GFP_KERNEL); + * pf->flow_cfg->ucast_flt_cnt, GFP_KERNEL); if (!pf->mac_table) return -ENOMEM; @@ -356,7 +357,7 @@ static int otx2_do_add_macfilter(struct otx2_nic *pf, const u8 *mac) return -ENOMEM; /* dont have free mcam entries or uc list is greater than alloted */ - if (netdev_uc_count(pf->netdev) > OTX2_MAX_UNICAST_FLOWS) + if (netdev_uc_count(pf->netdev) > pf->flow_cfg->ucast_flt_cnt) return -ENOMEM; mutex_lock(&pf->mbox.lock); @@ -367,7 +368,7 @@ static int otx2_do_add_macfilter(struct otx2_nic *pf, const u8 *mac) } /* unicast offset starts with 32 0..31 for ntuple */ - for (i = 0; i < OTX2_MAX_UNICAST_FLOWS; i++) { + for (i = 0; i < pf->flow_cfg->ucast_flt_cnt; i++) { if (pf->mac_table[i].inuse) continue; ether_addr_copy(pf->mac_table[i].addr, mac); @@ -410,7 +411,7 @@ static bool otx2_get_mcamentry_for_mac(struct otx2_nic *pf, const u8 *mac, { int i; - for (i = 0; i < OTX2_MAX_UNICAST_FLOWS; i++) { + for (i = 0; i < pf->flow_cfg->ucast_flt_cnt; i++) { if (!pf->mac_table[i].inuse) continue; @@ -1394,6 +1395,7 @@ int otx2_destroy_mcam_flows(struct otx2_nic *pfvf) } pfvf->flags &= ~OTX2_FLAG_MCAM_ENTRIES_ALLOC; + flow_cfg->max_flows = 0; mutex_unlock(&pfvf->mbox.lock); return 0; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index f5bce3e326cc..ff05ea20409a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1714,7 +1714,7 @@ static void otx2_do_set_rx_mode(struct otx2_nic *pf) return; if ((netdev->flags & IFF_PROMISC) || - (netdev_uc_count(netdev) > OTX2_MAX_UNICAST_FLOWS)) { + (netdev_uc_count(netdev) > pf->flow_cfg->ucast_flt_cnt)) { promisc = true; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h index 45a32e4b49d1..e3aee6e36215 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h @@ -139,33 +139,34 @@ #define NIX_LF_CINTX_ENA_W1C(a) (NIX_LFBASE | 0xD50 | (a) << 12) /* NIX AF transmit scheduler registers */ -#define NIX_AF_SMQX_CFG(a) (0x700 | (a) << 16) -#define NIX_AF_TL1X_SCHEDULE(a) (0xC00 | (a) << 16) -#define NIX_AF_TL1X_CIR(a) (0xC20 | (a) << 16) -#define NIX_AF_TL1X_TOPOLOGY(a) (0xC80 | (a) << 16) -#define NIX_AF_TL2X_PARENT(a) (0xE88 | (a) << 16) -#define NIX_AF_TL2X_SCHEDULE(a) (0xE00 | (a) << 16) -#define NIX_AF_TL2X_TOPOLOGY(a) (0xE80 | (a) << 16) -#define NIX_AF_TL2X_CIR(a) (0xE20 | (a) << 16) -#define NIX_AF_TL2X_PIR(a) (0xE30 | (a) << 16) -#define NIX_AF_TL3X_PARENT(a) (0x1088 | (a) << 16) -#define NIX_AF_TL3X_SCHEDULE(a) (0x1000 | (a) << 16) -#define NIX_AF_TL3X_SHAPE(a) (0x1010 | (a) << 16) -#define NIX_AF_TL3X_CIR(a) (0x1020 | (a) << 16) -#define NIX_AF_TL3X_PIR(a) (0x1030 | (a) << 16) -#define NIX_AF_TL3X_TOPOLOGY(a) (0x1080 | (a) << 16) -#define NIX_AF_TL4X_PARENT(a) (0x1288 | (a) << 16) -#define NIX_AF_TL4X_SCHEDULE(a) (0x1200 | (a) << 16) -#define NIX_AF_TL4X_SHAPE(a) (0x1210 | (a) << 16) -#define NIX_AF_TL4X_CIR(a) (0x1220 | (a) << 16) -#define NIX_AF_TL4X_PIR(a) (0x1230 | (a) << 16) -#define NIX_AF_TL4X_TOPOLOGY(a) (0x1280 | (a) << 16) -#define NIX_AF_MDQX_SCHEDULE(a) (0x1400 | (a) << 16) -#define NIX_AF_MDQX_SHAPE(a) (0x1410 | (a) << 16) -#define NIX_AF_MDQX_CIR(a) (0x1420 | (a) << 16) -#define NIX_AF_MDQX_PIR(a) (0x1430 | (a) << 16) -#define NIX_AF_MDQX_PARENT(a) (0x1480 | (a) << 16) -#define NIX_AF_TL3_TL2X_LINKX_CFG(a, b) (0x1700 | (a) << 16 | (b) << 3) +#define NIX_AF_SMQX_CFG(a) (0x700 | (u64)(a) << 16) +#define NIX_AF_TL4X_SDP_LINK_CFG(a) (0xB10 | (u64)(a) << 16) +#define NIX_AF_TL1X_SCHEDULE(a) (0xC00 | (u64)(a) << 16) +#define NIX_AF_TL1X_CIR(a) (0xC20 | (u64)(a) << 16) +#define NIX_AF_TL1X_TOPOLOGY(a) (0xC80 | (u64)(a) << 16) +#define NIX_AF_TL2X_PARENT(a) (0xE88 | (u64)(a) << 16) +#define NIX_AF_TL2X_SCHEDULE(a) (0xE00 | (u64)(a) << 16) +#define NIX_AF_TL2X_TOPOLOGY(a) (0xE80 | (u64)(a) << 16) +#define NIX_AF_TL2X_CIR(a) (0xE20 | (u64)(a) << 16) +#define NIX_AF_TL2X_PIR(a) (0xE30 | (u64)(a) << 16) +#define NIX_AF_TL3X_PARENT(a) (0x1088 | (u64)(a) << 16) +#define NIX_AF_TL3X_SCHEDULE(a) (0x1000 | (u64)(a) << 16) +#define NIX_AF_TL3X_SHAPE(a) (0x1010 | (u64)(a) << 16) +#define NIX_AF_TL3X_CIR(a) (0x1020 | (u64)(a) << 16) +#define NIX_AF_TL3X_PIR(a) (0x1030 | (u64)(a) << 16) +#define NIX_AF_TL3X_TOPOLOGY(a) (0x1080 | (u64)(a) << 16) +#define NIX_AF_TL4X_PARENT(a) (0x1288 | (u64)(a) << 16) +#define NIX_AF_TL4X_SCHEDULE(a) (0x1200 | (u64)(a) << 16) +#define NIX_AF_TL4X_SHAPE(a) (0x1210 | (u64)(a) << 16) +#define NIX_AF_TL4X_CIR(a) (0x1220 | (u64)(a) << 16) +#define NIX_AF_TL4X_PIR(a) (0x1230 | (u64)(a) << 16) +#define NIX_AF_TL4X_TOPOLOGY(a) (0x1280 | (u64)(a) << 16) +#define NIX_AF_MDQX_SCHEDULE(a) (0x1400 | (u64)(a) << 16) +#define NIX_AF_MDQX_SHAPE(a) (0x1410 | (u64)(a) << 16) +#define NIX_AF_MDQX_CIR(a) (0x1420 | (u64)(a) << 16) +#define NIX_AF_MDQX_PIR(a) (0x1430 | (u64)(a) << 16) +#define NIX_AF_MDQX_PARENT(a) (0x1480 | (u64)(a) << 16) +#define NIX_AF_TL3_TL2X_LINKX_CFG(a, b) (0x1700 | (u64)(a) << 16 | (b) << 3) /* LMT LF registers */ #define LMT_LFBASE BIT_ULL(RVU_FUNC_BLKADDR_SHIFT) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index a16e9f244117..3eb85949677a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -513,7 +513,7 @@ process_cqe: static void otx2_adjust_adaptive_coalese(struct otx2_nic *pfvf, struct otx2_cq_poll *cq_poll) { - struct dim_sample dim_sample; + struct dim_sample dim_sample = { 0 }; u64 rx_frames, rx_bytes; u64 tx_frames, tx_bytes; @@ -1174,8 +1174,11 @@ bool otx2_sq_append_skb(struct net_device *netdev, struct otx2_snd_queue *sq, if (skb_shinfo(skb)->gso_size && !is_hw_tso_supported(pfvf, skb)) { /* Insert vlan tag before giving pkt to tso */ - if (skb_vlan_tag_present(skb)) + if (skb_vlan_tag_present(skb)) { skb = __vlan_hwaccel_push_inside(skb); + if (!skb) + return true; + } otx2_sq_append_tso(pfvf, sq, skb, qidx); return true; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c index edac008099c0..0f844c14485a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c @@ -153,7 +153,6 @@ static void __otx2_qos_txschq_cfg(struct otx2_nic *pfvf, num_regs++; otx2_config_sched_shaping(pfvf, node, cfg, &num_regs); - } else if (level == NIX_TXSCH_LVL_TL4) { otx2_config_sched_shaping(pfvf, node, cfg, &num_regs); } else if (level == NIX_TXSCH_LVL_TL3) { @@ -176,7 +175,7 @@ static void __otx2_qos_txschq_cfg(struct otx2_nic *pfvf, /* check if node is root */ if (node->qid == OTX2_QOS_QID_INNER && !node->parent) { cfg->reg[num_regs] = NIX_AF_TL2X_SCHEDULE(node->schq); - cfg->regval[num_regs] = TXSCH_TL1_DFLT_RR_PRIO << 24 | + cfg->regval[num_regs] = (u64)hw->txschq_aggr_lvl_rr_prio << 24 | mtu_to_dwrr_weight(pfvf, pfvf->tx_max_pktlen); num_regs++; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index c84ce54a84a0..13d78d9b3197 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -80,7 +80,9 @@ static const struct mtk_reg_map mtk_reg_map = { .fq_blen = 0x1b2c, }, .gdm1_cnt = 0x2400, - .gdma_to_ppe = 0x4444, + .gdma_to_ppe = { + [0] = 0x4444, + }, .ppe_base = 0x0c00, .wdma_base = { [0] = 0x2800, @@ -144,7 +146,10 @@ static const struct mtk_reg_map mt7986_reg_map = { .tx_sch_rate = 0x4798, }, .gdm1_cnt = 0x1c00, - .gdma_to_ppe = 0x3333, + .gdma_to_ppe = { + [0] = 0x3333, + [1] = 0x4444, + }, .ppe_base = 0x2000, .wdma_base = { [0] = 0x4800, @@ -192,7 +197,11 @@ static const struct mtk_reg_map mt7988_reg_map = { .tx_sch_rate = 0x4798, }, .gdm1_cnt = 0x1c00, - .gdma_to_ppe = 0x3333, + .gdma_to_ppe = { + [0] = 0x3333, + [1] = 0x4444, + [2] = 0xcccc, + }, .ppe_base = 0x2000, .wdma_base = { [0] = 0x4800, @@ -2015,6 +2024,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, struct mtk_rx_dma_v2 *rxd, trxd; int done = 0, bytes = 0; dma_addr_t dma_addr = DMA_MAPPING_ERROR; + int ppe_idx = 0; while (done < budget) { unsigned int pktlen, *rxdcsum; @@ -2058,6 +2068,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, goto release_desc; netdev = eth->netdev[mac]; + ppe_idx = eth->mac[mac]->ppe_idx; if (unlikely(test_bit(MTK_RESETTING, ð->state))) goto release_desc; @@ -2181,7 +2192,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, } if (reason == MTK_PPE_CPU_REASON_HIT_UNBIND_RATE_REACHED) - mtk_ppe_check_skb(eth->ppe[0], skb, hash); + mtk_ppe_check_skb(eth->ppe[ppe_idx], skb, hash); skb_record_rx_queue(skb, 0); napi_gro_receive(napi, skb); @@ -3276,37 +3287,27 @@ static int mtk_start_dma(struct mtk_eth *eth) return 0; } -static void mtk_gdm_config(struct mtk_eth *eth, u32 config) +static void mtk_gdm_config(struct mtk_eth *eth, u32 id, u32 config) { - int i; + u32 val; if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) return; - for (i = 0; i < MTK_MAX_DEVS; i++) { - u32 val; - - if (!eth->netdev[i]) - continue; + val = mtk_r32(eth, MTK_GDMA_FWD_CFG(id)); - val = mtk_r32(eth, MTK_GDMA_FWD_CFG(i)); + /* default setup the forward port to send frame to PDMA */ + val &= ~0xffff; - /* default setup the forward port to send frame to PDMA */ - val &= ~0xffff; + /* Enable RX checksum */ + val |= MTK_GDMA_ICS_EN | MTK_GDMA_TCS_EN | MTK_GDMA_UCS_EN; - /* Enable RX checksum */ - val |= MTK_GDMA_ICS_EN | MTK_GDMA_TCS_EN | MTK_GDMA_UCS_EN; + val |= config; - val |= config; + if (eth->netdev[id] && netdev_uses_dsa(eth->netdev[id])) + val |= MTK_GDMA_SPECIAL_TAG; - if (netdev_uses_dsa(eth->netdev[i])) - val |= MTK_GDMA_SPECIAL_TAG; - - mtk_w32(eth, val, MTK_GDMA_FWD_CFG(i)); - } - /* Reset and enable PSE */ - mtk_w32(eth, RST_GL_PSE, MTK_RST_GL); - mtk_w32(eth, 0, MTK_RST_GL); + mtk_w32(eth, val, MTK_GDMA_FWD_CFG(id)); } @@ -3366,7 +3367,10 @@ static int mtk_open(struct net_device *dev) { struct mtk_mac *mac = netdev_priv(dev); struct mtk_eth *eth = mac->hw; - int i, err; + struct mtk_mac *target_mac; + int i, err, ppe_num; + + ppe_num = eth->soc->ppe_num; err = phylink_of_phy_connect(mac->phylink, mac->of_node, 0); if (err) { @@ -3390,18 +3394,38 @@ static int mtk_open(struct net_device *dev) for (i = 0; i < ARRAY_SIZE(eth->ppe); i++) mtk_ppe_start(eth->ppe[i]); - gdm_config = soc->offload_version ? soc->reg_map->gdma_to_ppe - : MTK_GDMA_TO_PDMA; - mtk_gdm_config(eth, gdm_config); + for (i = 0; i < MTK_MAX_DEVS; i++) { + if (!eth->netdev[i]) + break; + + target_mac = netdev_priv(eth->netdev[i]); + if (!soc->offload_version) { + target_mac->ppe_idx = 0; + gdm_config = MTK_GDMA_TO_PDMA; + } else if (ppe_num >= 3 && target_mac->id == 2) { + target_mac->ppe_idx = 2; + gdm_config = soc->reg_map->gdma_to_ppe[2]; + } else if (ppe_num >= 2 && target_mac->id == 1) { + target_mac->ppe_idx = 1; + gdm_config = soc->reg_map->gdma_to_ppe[1]; + } else { + target_mac->ppe_idx = 0; + gdm_config = soc->reg_map->gdma_to_ppe[0]; + } + mtk_gdm_config(eth, target_mac->id, gdm_config); + } + /* Reset and enable PSE */ + mtk_w32(eth, RST_GL_PSE, MTK_RST_GL); + mtk_w32(eth, 0, MTK_RST_GL); napi_enable(ð->tx_napi); napi_enable(ð->rx_napi); mtk_tx_irq_enable(eth, MTK_TX_DONE_INT); mtk_rx_irq_enable(eth, soc->rx.irq_done_mask); refcount_set(ð->dma_refcnt, 1); - } - else + } else { refcount_inc(ð->dma_refcnt); + } phylink_start(mac->phylink); netif_tx_start_all_queues(dev); @@ -3478,7 +3502,8 @@ static int mtk_stop(struct net_device *dev) if (!refcount_dec_and_test(ð->dma_refcnt)) return 0; - mtk_gdm_config(eth, MTK_GDMA_DROP_ALL); + for (i = 0; i < MTK_MAX_DEVS; i++) + mtk_gdm_config(eth, i, MTK_GDMA_DROP_ALL); mtk_tx_irq_disable(eth, MTK_TX_DONE_INT); mtk_rx_irq_disable(eth, eth->soc->rx.irq_done_mask); @@ -4959,23 +4984,24 @@ static int mtk_probe(struct platform_device *pdev) } if (eth->soc->offload_version) { - u32 num_ppe = mtk_is_netsys_v2_or_greater(eth) ? 2 : 1; + u8 ppe_num = eth->soc->ppe_num; - num_ppe = min_t(u32, ARRAY_SIZE(eth->ppe), num_ppe); - for (i = 0; i < num_ppe; i++) { - u32 ppe_addr = eth->soc->reg_map->ppe_base + i * 0x400; + ppe_num = min_t(u8, ARRAY_SIZE(eth->ppe), ppe_num); + for (i = 0; i < ppe_num; i++) { + u32 ppe_addr = eth->soc->reg_map->ppe_base; + ppe_addr += (i == 2 ? 0xc00 : i * 0x400); eth->ppe[i] = mtk_ppe_init(eth, eth->base + ppe_addr, i); if (!eth->ppe[i]) { err = -ENOMEM; goto err_deinit_ppe; } - } + err = mtk_eth_offload_init(eth, i); - err = mtk_eth_offload_init(eth); - if (err) - goto err_deinit_ppe; + if (err) + goto err_deinit_ppe; + } } for (i = 0; i < MTK_MAX_DEVS; i++) { @@ -5083,6 +5109,7 @@ static const struct mtk_soc_data mt7621_data = { .required_pctl = false, .version = 1, .offload_version = 1, + .ppe_num = 1, .hash_offset = 2, .foe_entry_size = MTK_FOE_ENTRY_V1_SIZE, .tx = { @@ -5111,6 +5138,7 @@ static const struct mtk_soc_data mt7622_data = { .required_pctl = false, .version = 1, .offload_version = 2, + .ppe_num = 1, .hash_offset = 2, .has_accounting = true, .foe_entry_size = MTK_FOE_ENTRY_V1_SIZE, @@ -5139,6 +5167,7 @@ static const struct mtk_soc_data mt7623_data = { .required_pctl = true, .version = 1, .offload_version = 1, + .ppe_num = 1, .hash_offset = 2, .foe_entry_size = MTK_FOE_ENTRY_V1_SIZE, .disable_pll_modes = true, @@ -5194,6 +5223,7 @@ static const struct mtk_soc_data mt7981_data = { .required_pctl = false, .version = 2, .offload_version = 2, + .ppe_num = 2, .hash_offset = 4, .has_accounting = true, .foe_entry_size = MTK_FOE_ENTRY_V2_SIZE, @@ -5223,6 +5253,7 @@ static const struct mtk_soc_data mt7986_data = { .required_pctl = false, .version = 2, .offload_version = 2, + .ppe_num = 2, .hash_offset = 4, .has_accounting = true, .foe_entry_size = MTK_FOE_ENTRY_V2_SIZE, @@ -5252,6 +5283,7 @@ static const struct mtk_soc_data mt7988_data = { .required_pctl = false, .version = 3, .offload_version = 2, + .ppe_num = 3, .hash_offset = 4, .has_accounting = true, .foe_entry_size = MTK_FOE_ENTRY_V3_SIZE, diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index f5174f6cb1bb..eb1708b43aa3 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -1132,7 +1132,7 @@ struct mtk_reg_map { u32 tx_sch_rate; /* tx scheduler rate control registers */ } qdma; u32 gdm1_cnt; - u32 gdma_to_ppe; + u32 gdma_to_ppe[3]; u32 ppe_base; u32 wdma_base[3]; u32 pse_iq_sta; @@ -1170,6 +1170,7 @@ struct mtk_soc_data { u8 offload_version; u8 hash_offset; u8 version; + u8 ppe_num; u16 foe_entry_size; netdev_features_t hw_features; bool has_accounting; @@ -1294,7 +1295,7 @@ struct mtk_eth { struct metadata_dst *dsa_meta[MTK_MAX_DSA_PORTS]; - struct mtk_ppe *ppe[2]; + struct mtk_ppe *ppe[3]; struct rhashtable flow_table; struct bpf_prog __rcu *prog; @@ -1319,6 +1320,7 @@ struct mtk_eth { struct mtk_mac { int id; phy_interface_t interface; + u8 ppe_idx; int speed; struct device_node *of_node; struct phylink *phylink; @@ -1440,7 +1442,7 @@ int mtk_gmac_sgmii_path_setup(struct mtk_eth *eth, int mac_id); int mtk_gmac_gephy_path_setup(struct mtk_eth *eth, int mac_id); int mtk_gmac_rgmii_path_setup(struct mtk_eth *eth, int mac_id); -int mtk_eth_offload_init(struct mtk_eth *eth); +int mtk_eth_offload_init(struct mtk_eth *eth, u8 id); int mtk_eth_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data); int mtk_flow_offload_cmd(struct mtk_eth *eth, struct flow_cls_offload *cls, diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c index aa262e6f4b85..f20bb390df3a 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c @@ -245,10 +245,10 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f, int ppe_index) { struct flow_rule *rule = flow_cls_offload_flow_rule(f); + struct net_device *idev = NULL, *odev = NULL; struct flow_action_entry *act; struct mtk_flow_data data = {}; struct mtk_foe_entry foe; - struct net_device *odev = NULL; struct mtk_flow_entry *entry; int offload_type = 0; int wed_index = -1; @@ -264,6 +264,17 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f, struct flow_match_meta match; flow_rule_match_meta(rule, &match); + if (mtk_is_netsys_v2_or_greater(eth)) { + idev = __dev_get_by_index(&init_net, match.key->ingress_ifindex); + if (idev && idev->netdev_ops == eth->netdev[0]->netdev_ops) { + struct mtk_mac *mac = netdev_priv(idev); + + if (WARN_ON(mac->ppe_idx >= eth->soc->ppe_num)) + return -EINVAL; + + ppe_index = mac->ppe_idx; + } + } } else { return -EOPNOTSUPP; } @@ -637,7 +648,9 @@ int mtk_eth_setup_tc(struct net_device *dev, enum tc_setup_type type, } } -int mtk_eth_offload_init(struct mtk_eth *eth) +int mtk_eth_offload_init(struct mtk_eth *eth, u8 id) { + if (!eth->ppe[id] || !eth->ppe[id]->foe_table) + return 0; return rhashtable_init(ð->flow_table, &mtk_flow_ht_params); } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 619e1c3ef7f9..0606f18e5bbe 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -450,7 +450,6 @@ static void mlx4_en_get_strings(struct net_device *dev, uint32_t stringset, uint8_t *data) { struct mlx4_en_priv *priv = netdev_priv(dev); - int index = 0; int i, strings = 0; struct bitmap_iterator it; @@ -459,10 +458,10 @@ static void mlx4_en_get_strings(struct net_device *dev, switch (stringset) { case ETH_SS_TEST: for (i = 0; i < MLX4_EN_NUM_SELF_TEST - 2; i++) - strcpy(data + i * ETH_GSTRING_LEN, mlx4_en_test_names[i]); + ethtool_puts(&data, mlx4_en_test_names[i]); if (priv->mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_UC_LOOPBACK) for (; i < MLX4_EN_NUM_SELF_TEST; i++) - strcpy(data + i * ETH_GSTRING_LEN, mlx4_en_test_names[i]); + ethtool_puts(&data, mlx4_en_test_names[i]); break; case ETH_SS_STATS: @@ -470,74 +469,56 @@ static void mlx4_en_get_strings(struct net_device *dev, for (i = 0; i < NUM_MAIN_STATS; i++, strings++, bitmap_iterator_inc(&it)) if (bitmap_iterator_test(&it)) - strcpy(data + (index++) * ETH_GSTRING_LEN, - main_strings[strings]); + ethtool_puts(&data, main_strings[strings]); for (i = 0; i < NUM_PORT_STATS; i++, strings++, bitmap_iterator_inc(&it)) if (bitmap_iterator_test(&it)) - strcpy(data + (index++) * ETH_GSTRING_LEN, - main_strings[strings]); + ethtool_puts(&data, main_strings[strings]); for (i = 0; i < NUM_PF_STATS; i++, strings++, bitmap_iterator_inc(&it)) if (bitmap_iterator_test(&it)) - strcpy(data + (index++) * ETH_GSTRING_LEN, - main_strings[strings]); + ethtool_puts(&data, main_strings[strings]); for (i = 0; i < NUM_FLOW_STATS; i++, strings++, bitmap_iterator_inc(&it)) if (bitmap_iterator_test(&it)) - strcpy(data + (index++) * ETH_GSTRING_LEN, - main_strings[strings]); + ethtool_puts(&data, main_strings[strings]); for (i = 0; i < NUM_PKT_STATS; i++, strings++, bitmap_iterator_inc(&it)) if (bitmap_iterator_test(&it)) - strcpy(data + (index++) * ETH_GSTRING_LEN, - main_strings[strings]); + ethtool_puts(&data, main_strings[strings]); for (i = 0; i < NUM_XDP_STATS; i++, strings++, bitmap_iterator_inc(&it)) if (bitmap_iterator_test(&it)) - strcpy(data + (index++) * ETH_GSTRING_LEN, - main_strings[strings]); + ethtool_puts(&data, main_strings[strings]); for (i = 0; i < NUM_PHY_STATS; i++, strings++, bitmap_iterator_inc(&it)) if (bitmap_iterator_test(&it)) - strcpy(data + (index++) * ETH_GSTRING_LEN, - main_strings[strings]); + ethtool_puts(&data, main_strings[strings]); for (i = 0; i < priv->tx_ring_num[TX]; i++) { - sprintf(data + (index++) * ETH_GSTRING_LEN, - "tx%d_packets", i); - sprintf(data + (index++) * ETH_GSTRING_LEN, - "tx%d_bytes", i); + ethtool_sprintf(&data, "tx%d_packets", i); + ethtool_sprintf(&data, "tx%d_bytes", i); } for (i = 0; i < priv->rx_ring_num; i++) { - sprintf(data + (index++) * ETH_GSTRING_LEN, - "rx%d_packets", i); - sprintf(data + (index++) * ETH_GSTRING_LEN, - "rx%d_bytes", i); - sprintf(data + (index++) * ETH_GSTRING_LEN, - "rx%d_dropped", i); - sprintf(data + (index++) * ETH_GSTRING_LEN, - "rx%d_xdp_drop", i); - sprintf(data + (index++) * ETH_GSTRING_LEN, - "rx%d_xdp_redirect", i); - sprintf(data + (index++) * ETH_GSTRING_LEN, - "rx%d_xdp_redirect_fail", i); - sprintf(data + (index++) * ETH_GSTRING_LEN, - "rx%d_xdp_tx", i); - sprintf(data + (index++) * ETH_GSTRING_LEN, - "rx%d_xdp_tx_full", i); + ethtool_sprintf(&data, "rx%d_packets", i); + ethtool_sprintf(&data, "rx%d_bytes", i); + ethtool_sprintf(&data, "rx%d_dropped", i); + ethtool_sprintf(&data, "rx%d_xdp_drop", i); + ethtool_sprintf(&data, "rx%d_xdp_redirect", i); + ethtool_sprintf(&data, "rx%d_xdp_redirect_fail", i); + ethtool_sprintf(&data, "rx%d_xdp_tx", i); + ethtool_sprintf(&data, "rx%d_xdp_tx_full", i); } break; case ETH_SS_PRIV_FLAGS: for (i = 0; i < ARRAY_SIZE(mlx4_en_priv_flags); i++) - strcpy(data + i * ETH_GSTRING_LEN, - mlx4_en_priv_flags[i]); + ethtool_puts(&data, mlx4_en_priv_flags[i]); break; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index bec784d25d7b..6a343a8f162f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -867,6 +867,8 @@ struct mlx5e_priv { /* priv data path fields - start */ struct mlx5e_selq selq; struct mlx5e_txqsq **txq2sq; + struct mlx5e_sq_stats **txq2sq_stats; + #ifdef CONFIG_MLX5_CORE_EN_DCB struct mlx5e_dcbx_dp dcbx_dp; #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c index 6743806b8480..f0744a45db92 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c @@ -170,6 +170,7 @@ int mlx5e_activate_qos_sq(void *data, u16 node_qid, u32 hw_id) mlx5e_tx_disable_queue(netdev_get_tx_queue(priv->netdev, qid)); priv->txq2sq[qid] = sq; + priv->txq2sq_stats[qid] = sq->stats; /* Make the change to txq2sq visible before the queue is started. * As mlx5e_xmit runs under a spinlock, there is an implicit ACQUIRE, @@ -186,6 +187,7 @@ int mlx5e_activate_qos_sq(void *data, u16 node_qid, u32 hw_id) void mlx5e_deactivate_qos_sq(struct mlx5e_priv *priv, u16 qid) { struct mlx5e_txqsq *sq; + u16 txq_ix; sq = mlx5e_get_qos_sq(priv, qid); if (!sq) /* Handle the case when the SQ failed to open. */ @@ -194,7 +196,10 @@ void mlx5e_deactivate_qos_sq(struct mlx5e_priv *priv, u16 qid) qos_dbg(sq->mdev, "Deactivate QoS SQ qid %u\n", qid); mlx5e_deactivate_txqsq(sq); - priv->txq2sq[mlx5e_qid_from_qos(&priv->channels, qid)] = NULL; + txq_ix = mlx5e_qid_from_qos(&priv->channels, qid); + + priv->txq2sq[txq_ix] = NULL; + priv->txq2sq_stats[txq_ix] = NULL; /* Make the change to txq2sq visible before the queue is started again. * As mlx5e_xmit runs under a spinlock, there is an implicit ACQUIRE, @@ -325,6 +330,7 @@ void mlx5e_qos_deactivate_queues(struct mlx5e_channel *c) { struct mlx5e_params *params = &c->priv->channels.params; struct mlx5e_txqsq __rcu **qos_sqs; + u16 txq_ix; int i; qos_sqs = mlx5e_state_dereference(c->priv, c->qos_sqs); @@ -342,8 +348,11 @@ void mlx5e_qos_deactivate_queues(struct mlx5e_channel *c) qos_dbg(c->mdev, "Deactivate QoS SQ qid %u\n", qid); mlx5e_deactivate_txqsq(sq); + txq_ix = mlx5e_qid_from_qos(&c->priv->channels, qid); + /* The queue is disabled, no synchronization with datapath is needed. */ - c->priv->txq2sq[mlx5e_qid_from_qos(&c->priv->channels, qid)] = NULL; + c->priv->txq2sq[txq_ix] = NULL; + c->priv->txq2sq_stats[txq_ix] = NULL; } } 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 fadfa8b50beb..b49d87a51f21 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -69,6 +69,8 @@ struct mlx5_tc_ct_priv { struct rhashtable ct_tuples_nat_ht; struct mlx5_flow_table *ct; struct mlx5_flow_table *ct_nat; + struct mlx5_flow_group *ct_nat_miss_group; + struct mlx5_flow_handle *ct_nat_miss_rule; struct mlx5e_post_act *post_act; struct mutex control_lock; /* guards parallel adds/dels */ struct mapping_ctx *zone_mapping; @@ -141,6 +143,8 @@ struct mlx5_ct_counter { enum { MLX5_CT_ENTRY_FLAG_VALID, + MLX5_CT_ENTRY_IN_CT_TABLE, + MLX5_CT_ENTRY_IN_CT_NAT_TABLE, }; struct mlx5_ct_entry { @@ -198,9 +202,15 @@ static const struct rhashtable_params tuples_nat_ht_params = { }; static bool -mlx5_tc_ct_entry_has_nat(struct mlx5_ct_entry *entry) +mlx5_tc_ct_entry_in_ct_table(struct mlx5_ct_entry *entry) { - return !!(entry->tuple_nat_node.next); + return test_bit(MLX5_CT_ENTRY_IN_CT_TABLE, &entry->flags); +} + +static bool +mlx5_tc_ct_entry_in_ct_nat_table(struct mlx5_ct_entry *entry) +{ + return test_bit(MLX5_CT_ENTRY_IN_CT_NAT_TABLE, &entry->flags); } static int @@ -526,8 +536,10 @@ static void mlx5_tc_ct_entry_del_rules(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_entry *entry) { - mlx5_tc_ct_entry_del_rule(ct_priv, entry, true); - mlx5_tc_ct_entry_del_rule(ct_priv, entry, false); + if (mlx5_tc_ct_entry_in_ct_nat_table(entry)) + mlx5_tc_ct_entry_del_rule(ct_priv, entry, true); + if (mlx5_tc_ct_entry_in_ct_table(entry)) + mlx5_tc_ct_entry_del_rule(ct_priv, entry, false); atomic_dec(&ct_priv->debugfs.stats.offloaded); } @@ -814,7 +826,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, &zone_rule->mh, zone_restore_id, nat, - mlx5_tc_ct_entry_has_nat(entry)); + mlx5_tc_ct_entry_in_ct_nat_table(entry)); if (err) { ct_dbg("Failed to create ct entry mod hdr"); goto err_mod_hdr; @@ -888,7 +900,7 @@ mlx5_tc_ct_entry_replace_rule(struct mlx5_tc_ct_priv *ct_priv, *old_attr = *attr; err = mlx5_tc_ct_entry_create_mod_hdr(ct_priv, attr, flow_rule, &mh, zone_restore_id, - nat, mlx5_tc_ct_entry_has_nat(entry)); + nat, mlx5_tc_ct_entry_in_ct_nat_table(entry)); if (err) { ct_dbg("Failed to create ct entry mod hdr"); goto err_mod_hdr; @@ -957,11 +969,13 @@ static void mlx5_tc_ct_entry_remove_from_tuples(struct mlx5_ct_entry *entry) { struct mlx5_tc_ct_priv *ct_priv = entry->ct_priv; - rhashtable_remove_fast(&ct_priv->ct_tuples_nat_ht, - &entry->tuple_nat_node, - tuples_nat_ht_params); - rhashtable_remove_fast(&ct_priv->ct_tuples_ht, &entry->tuple_node, - tuples_ht_params); + if (mlx5_tc_ct_entry_in_ct_nat_table(entry)) + rhashtable_remove_fast(&ct_priv->ct_tuples_nat_ht, + &entry->tuple_nat_node, + tuples_nat_ht_params); + if (mlx5_tc_ct_entry_in_ct_table(entry)) + rhashtable_remove_fast(&ct_priv->ct_tuples_ht, &entry->tuple_node, + tuples_ht_params); } static void mlx5_tc_ct_entry_del(struct mlx5_ct_entry *entry) @@ -1100,21 +1114,26 @@ mlx5_tc_ct_entry_add_rules(struct mlx5_tc_ct_priv *ct_priv, return err; } - err = mlx5_tc_ct_entry_add_rule(ct_priv, flow_rule, entry, false, - zone_restore_id); - if (err) - goto err_orig; + if (mlx5_tc_ct_entry_in_ct_table(entry)) { + err = mlx5_tc_ct_entry_add_rule(ct_priv, flow_rule, entry, false, + zone_restore_id); + if (err) + goto err_orig; + } - err = mlx5_tc_ct_entry_add_rule(ct_priv, flow_rule, entry, true, - zone_restore_id); - if (err) - goto err_nat; + if (mlx5_tc_ct_entry_in_ct_nat_table(entry)) { + err = mlx5_tc_ct_entry_add_rule(ct_priv, flow_rule, entry, true, + zone_restore_id); + if (err) + goto err_nat; + } atomic_inc(&ct_priv->debugfs.stats.offloaded); return 0; err_nat: - mlx5_tc_ct_entry_del_rule(ct_priv, entry, false); + if (mlx5_tc_ct_entry_in_ct_table(entry)) + mlx5_tc_ct_entry_del_rule(ct_priv, entry, false); err_orig: mlx5_tc_ct_counter_put(ct_priv, entry); return err; @@ -1128,15 +1147,19 @@ mlx5_tc_ct_entry_replace_rules(struct mlx5_tc_ct_priv *ct_priv, { int err; - err = mlx5_tc_ct_entry_replace_rule(ct_priv, flow_rule, entry, false, - zone_restore_id); - if (err) - return err; + if (mlx5_tc_ct_entry_in_ct_table(entry)) { + err = mlx5_tc_ct_entry_replace_rule(ct_priv, flow_rule, entry, false, + zone_restore_id); + if (err) + return err; + } - err = mlx5_tc_ct_entry_replace_rule(ct_priv, flow_rule, entry, true, - zone_restore_id); - if (err) - mlx5_tc_ct_entry_del_rule(ct_priv, entry, false); + if (mlx5_tc_ct_entry_in_ct_nat_table(entry)) { + err = mlx5_tc_ct_entry_replace_rule(ct_priv, flow_rule, entry, true, + zone_restore_id); + if (err && mlx5_tc_ct_entry_in_ct_table(entry)) + mlx5_tc_ct_entry_del_rule(ct_priv, entry, false); + } return err; } @@ -1224,18 +1247,24 @@ mlx5_tc_ct_block_flow_offload_add(struct mlx5_ct_ft *ft, if (err) goto err_entries; - err = rhashtable_lookup_insert_fast(&ct_priv->ct_tuples_ht, - &entry->tuple_node, - tuples_ht_params); - if (err) - goto err_tuple; - if (memcmp(&entry->tuple, &entry->tuple_nat, sizeof(entry->tuple))) { err = rhashtable_lookup_insert_fast(&ct_priv->ct_tuples_nat_ht, &entry->tuple_nat_node, tuples_nat_ht_params); if (err) goto err_tuple_nat; + + set_bit(MLX5_CT_ENTRY_IN_CT_NAT_TABLE, &entry->flags); + } + + if (!mlx5_tc_ct_entry_in_ct_nat_table(entry)) { + err = rhashtable_lookup_insert_fast(&ct_priv->ct_tuples_ht, + &entry->tuple_node, + tuples_ht_params); + if (err) + goto err_tuple; + + set_bit(MLX5_CT_ENTRY_IN_CT_TABLE, &entry->flags); } spin_unlock_bh(&ct_priv->ht_lock); @@ -1251,17 +1280,10 @@ mlx5_tc_ct_block_flow_offload_add(struct mlx5_ct_ft *ft, err_rules: spin_lock_bh(&ct_priv->ht_lock); - if (mlx5_tc_ct_entry_has_nat(entry)) - rhashtable_remove_fast(&ct_priv->ct_tuples_nat_ht, - &entry->tuple_nat_node, tuples_nat_ht_params); -err_tuple_nat: - rhashtable_remove_fast(&ct_priv->ct_tuples_ht, - &entry->tuple_node, - tuples_ht_params); err_tuple: - rhashtable_remove_fast(&ft->ct_entries_ht, - &entry->node, - cts_ht_params); + mlx5_tc_ct_entry_remove_from_tuples(entry); +err_tuple_nat: + rhashtable_remove_fast(&ft->ct_entries_ht, &entry->node, cts_ht_params); err_entries: spin_unlock_bh(&ct_priv->ht_lock); err_set: @@ -2149,6 +2171,76 @@ mlx5_ct_tc_remove_dbgfs(struct mlx5_tc_ct_priv *ct_priv) debugfs_remove_recursive(ct_priv->debugfs.root); } +static struct mlx5_flow_handle * +tc_ct_add_miss_rule(struct mlx5_flow_table *ft, + struct mlx5_flow_table *next_ft) +{ + struct mlx5_flow_destination dest = {}; + struct mlx5_flow_act act = {}; + + act.flags = FLOW_ACT_IGNORE_FLOW_LEVEL | FLOW_ACT_NO_APPEND; + act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + dest.ft = next_ft; + + return mlx5_add_flow_rules(ft, NULL, &act, &dest, 1); +} + +static int +tc_ct_add_ct_table_miss_rule(struct mlx5_flow_table *from, + struct mlx5_flow_table *to, + struct mlx5_flow_group **miss_group, + struct mlx5_flow_handle **miss_rule) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *group; + struct mlx5_flow_handle *rule; + unsigned int max_fte = from->max_fte; + u32 *flow_group_in; + int err = 0; + + flow_group_in = kvzalloc(inlen, GFP_KERNEL); + if (!flow_group_in) + return -ENOMEM; + + /* create miss group */ + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, + max_fte - 2); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, + max_fte - 1); + group = mlx5_create_flow_group(from, flow_group_in); + if (IS_ERR(group)) { + err = PTR_ERR(group); + goto err_miss_grp; + } + + /* add miss rule to next fdb */ + rule = tc_ct_add_miss_rule(from, to); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + goto err_miss_rule; + } + + *miss_group = group; + *miss_rule = rule; + kvfree(flow_group_in); + return 0; + +err_miss_rule: + mlx5_destroy_flow_group(group); +err_miss_grp: + kvfree(flow_group_in); + return err; +} + +static void +tc_ct_del_ct_table_miss_rule(struct mlx5_flow_group *miss_group, + struct mlx5_flow_handle *miss_rule) +{ + mlx5_del_flow_rules(miss_rule); + mlx5_destroy_flow_group(miss_group); +} + #define INIT_ERR_PREFIX "tc ct offload init failed" struct mlx5_tc_ct_priv * @@ -2212,6 +2304,12 @@ mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, goto err_ct_nat_tbl; } + err = tc_ct_add_ct_table_miss_rule(ct_priv->ct_nat, ct_priv->ct, + &ct_priv->ct_nat_miss_group, + &ct_priv->ct_nat_miss_rule); + if (err) + goto err_ct_zone_ht; + ct_priv->post_act = post_act; mutex_init(&ct_priv->control_lock); if (rhashtable_init(&ct_priv->zone_ht, &zone_params)) @@ -2273,6 +2371,7 @@ mlx5_tc_ct_clean(struct mlx5_tc_ct_priv *ct_priv) ct_priv->fs_ops->destroy(ct_priv->fs); kfree(ct_priv->fs); + tc_ct_del_ct_table_miss_rule(ct_priv->ct_nat_miss_group, ct_priv->ct_nat_miss_rule); mlx5_chains_destroy_global_table(chains, ct_priv->ct_nat); mlx5_chains_destroy_global_table(chains, ct_priv->ct); mapping_destroy(ct_priv->zone_mapping); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 8dfb57f712b0..721f35e59757 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -850,6 +850,12 @@ int mlx5e_tc_tun_parse(struct net_device *filter_dev, flow_rule_match_enc_control(rule, &match); addr_type = match.key->addr_type; + if (flow_rule_has_enc_control_flags(match.mask->flags, + extack)) { + err = -EOPNOTSUPP; + goto out; + } + /* For tunnel addr_type used same key id`s as for non-tunnel */ if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { struct flow_match_ipv4_addrs match; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index d1f0f868d494..5ec468268d1a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -6,6 +6,8 @@ #include "en.h" #include <linux/indirect_call_wrapper.h> +#include <net/ip6_checksum.h> +#include <net/tcp.h> #define MLX5E_TX_WQE_EMPTY_DS_COUNT (sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) @@ -479,6 +481,41 @@ mlx5e_set_eseg_swp(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg, } } +static inline void +mlx5e_swp_encap_csum_partial(struct mlx5_core_dev *mdev, struct sk_buff *skb, bool tunnel) +{ + const struct iphdr *ip = tunnel ? inner_ip_hdr(skb) : ip_hdr(skb); + const struct ipv6hdr *ip6; + struct tcphdr *th; + struct udphdr *uh; + int len; + + if (!MLX5_CAP_ETH(mdev, swp_csum_l4_partial) || !skb_is_gso(skb)) + return; + + if (skb_is_gso_tcp(skb)) { + th = inner_tcp_hdr(skb); + len = skb_shinfo(skb)->gso_size + inner_tcp_hdrlen(skb); + + if (ip->version == 4) { + th->check = ~tcp_v4_check(len, ip->saddr, ip->daddr, 0); + } else { + ip6 = tunnel ? inner_ipv6_hdr(skb) : ipv6_hdr(skb); + th->check = ~tcp_v6_check(len, &ip6->saddr, &ip6->daddr, 0); + } + } else if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) { + uh = (struct udphdr *)skb_inner_transport_header(skb); + len = skb_shinfo(skb)->gso_size + sizeof(struct udphdr); + + if (ip->version == 4) { + uh->check = ~udp_v4_check(len, ip->saddr, ip->daddr, 0); + } else { + ip6 = tunnel ? inner_ipv6_hdr(skb) : ipv6_hdr(skb); + uh->check = ~udp_v6_check(len, &ip6->saddr, &ip6->daddr, 0); + } + } +} + #define MLX5E_STOP_ROOM(wqebbs) ((wqebbs) * 2 - 1) static inline u16 mlx5e_stop_room_for_wqe(struct mlx5_core_dev *mdev, u16 wqe_size) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h index 359050f0b54d..3cc640669247 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h @@ -116,6 +116,7 @@ static inline bool mlx5e_ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg) { + struct mlx5_core_dev *mdev = sq->mdev; u8 inner_ipproto; if (!mlx5e_ipsec_eseg_meta(eseg)) @@ -125,9 +126,12 @@ mlx5e_ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, inner_ipproto = xfrm_offload(skb)->inner_ipproto; if (inner_ipproto) { eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM; - if (inner_ipproto == IPPROTO_TCP || inner_ipproto == IPPROTO_UDP) + if (inner_ipproto == IPPROTO_TCP || inner_ipproto == IPPROTO_UDP) { + mlx5e_swp_encap_csum_partial(mdev, skb, true); eseg->cs_flags |= MLX5_ETH_WQE_L4_INNER_CSUM; + } } else if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { + mlx5e_swp_encap_csum_partial(mdev, skb, false); eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM; sq->stats->csum_partial_inner++; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 44a64d062e42..0eba4c5bb2ec 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/debugfs.h> #include <linux/if_bridge.h> #include <linux/filter.h> +#include <net/netdev_queues.h> #include <net/page_pool/types.h> #include <net/pkt_sched.h> #include <net/xdp_sock_drv.h> @@ -3125,6 +3126,7 @@ static void mlx5e_build_txq_maps(struct mlx5e_priv *priv) struct mlx5e_txqsq *sq = &c->sq[tc]; priv->txq2sq[sq->txq_ix] = sq; + priv->txq2sq_stats[sq->txq_ix] = sq->stats; } } @@ -3139,6 +3141,7 @@ static void mlx5e_build_txq_maps(struct mlx5e_priv *priv) struct mlx5e_txqsq *sq = &c->ptpsq[tc].txqsq; priv->txq2sq[sq->txq_ix] = sq; + priv->txq2sq_stats[sq->txq_ix] = sq->stats; } out: @@ -4895,7 +4898,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, /* Verify if UDP port is being offloaded by HW */ if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, port)) - return features; + return vxlan_features_check(skb, features); #if IS_ENABLED(CONFIG_GENEVE) /* Support Geneve offload for default UDP port */ @@ -4910,7 +4913,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, } out: - /* Disable CSUM and GSO if the udp dport is not offloaded by HW */ + /* Disable CSUM and GSO if skb cannot be offloaded by HW */ return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } @@ -4921,7 +4924,6 @@ netdev_features_t mlx5e_features_check(struct sk_buff *skb, struct mlx5e_priv *priv = netdev_priv(netdev); features = vlan_features_check(skb, features); - features = vxlan_features_check(skb, features); /* Validate if the tunneled packet is being offloaded by HW */ if (skb->encapsulation && @@ -5297,6 +5299,136 @@ static bool mlx5e_tunnel_any_tx_proto_supported(struct mlx5_core_dev *mdev) return (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev)); } +static void mlx5e_get_queue_stats_rx(struct net_device *dev, int i, + struct netdev_queue_stats_rx *stats) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5e_channel_stats *channel_stats; + struct mlx5e_rq_stats *xskrq_stats; + struct mlx5e_rq_stats *rq_stats; + + ASSERT_RTNL(); + if (mlx5e_is_uplink_rep(priv)) + return; + + channel_stats = priv->channel_stats[i]; + xskrq_stats = &channel_stats->xskrq; + rq_stats = &channel_stats->rq; + + stats->packets = rq_stats->packets + xskrq_stats->packets; + stats->bytes = rq_stats->bytes + xskrq_stats->bytes; + stats->alloc_fail = rq_stats->buff_alloc_err + + xskrq_stats->buff_alloc_err; +} + +static void mlx5e_get_queue_stats_tx(struct net_device *dev, int i, + struct netdev_queue_stats_tx *stats) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5e_sq_stats *sq_stats; + + ASSERT_RTNL(); + /* no special case needed for ptp htb etc since txq2sq_stats is kept up + * to date for active sq_stats, otherwise get_base_stats takes care of + * inactive sqs. + */ + sq_stats = priv->txq2sq_stats[i]; + stats->packets = sq_stats->packets; + stats->bytes = sq_stats->bytes; +} + +static void mlx5e_get_base_stats(struct net_device *dev, + struct netdev_queue_stats_rx *rx, + struct netdev_queue_stats_tx *tx) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5e_ptp *ptp_channel; + int i, tc; + + ASSERT_RTNL(); + if (!mlx5e_is_uplink_rep(priv)) { + rx->packets = 0; + rx->bytes = 0; + rx->alloc_fail = 0; + + for (i = priv->channels.params.num_channels; i < priv->stats_nch; i++) { + struct netdev_queue_stats_rx rx_i = {0}; + + mlx5e_get_queue_stats_rx(dev, i, &rx_i); + + rx->packets += rx_i.packets; + rx->bytes += rx_i.bytes; + rx->alloc_fail += rx_i.alloc_fail; + } + + /* always report PTP RX stats from base as there is no + * corresponding channel to report them under in + * mlx5e_get_queue_stats_rx. + */ + if (priv->rx_ptp_opened) { + struct mlx5e_rq_stats *rq_stats = &priv->ptp_stats.rq; + + rx->packets += rq_stats->packets; + rx->bytes += rq_stats->bytes; + } + } + + tx->packets = 0; + tx->bytes = 0; + + for (i = 0; i < priv->stats_nch; i++) { + struct mlx5e_channel_stats *channel_stats = priv->channel_stats[i]; + + /* handle two cases: + * + * 1. channels which are active. In this case, + * report only deactivated TCs on these channels. + * + * 2. channels which were deactivated + * (i > priv->channels.params.num_channels) + * must have all of their TCs [0 .. priv->max_opened_tc) + * examined because deactivated channels will not be in the + * range of [0..real_num_tx_queues) and will not have their + * stats reported by mlx5e_get_queue_stats_tx. + */ + if (i < priv->channels.params.num_channels) + tc = mlx5e_get_dcb_num_tc(&priv->channels.params); + else + tc = 0; + + for (; tc < priv->max_opened_tc; tc++) { + struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[tc]; + + tx->packets += sq_stats->packets; + tx->bytes += sq_stats->bytes; + } + } + + /* if PTP TX was opened at some point and has since either: + * - been shutdown and set to NULL, or + * - simply disabled (bit unset) + * + * report stats directly from the ptp_stats structures as these queues + * are now unavailable and there is no txq index to retrieve these + * stats via calls to mlx5e_get_queue_stats_tx. + */ + ptp_channel = priv->channels.ptp; + if (priv->tx_ptp_opened && (!ptp_channel || !test_bit(MLX5E_PTP_STATE_TX, ptp_channel->state))) { + for (tc = 0; tc < priv->max_opened_tc; tc++) { + struct mlx5e_sq_stats *sq_stats = &priv->ptp_stats.sq[tc]; + + tx->packets += sq_stats->packets; + tx->bytes += sq_stats->bytes; + } + } +} + +static const struct netdev_stat_ops mlx5e_stat_ops = { + .get_queue_stats_rx = mlx5e_get_queue_stats_rx, + .get_queue_stats_tx = mlx5e_get_queue_stats_tx, + .get_base_stats = mlx5e_get_base_stats, +}; + static void mlx5e_build_nic_netdev(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -5314,6 +5446,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->watchdog_timeo = 15 * HZ; + netdev->stat_ops = &mlx5e_stat_ops; netdev->ethtool_ops = &mlx5e_ethtool_ops; netdev->vlan_features |= NETIF_F_SG; @@ -5849,9 +5982,13 @@ int mlx5e_priv_init(struct mlx5e_priv *priv, if (!priv->txq2sq) goto err_destroy_workqueue; + priv->txq2sq_stats = kcalloc_node(num_txqs, sizeof(*priv->txq2sq_stats), GFP_KERNEL, node); + if (!priv->txq2sq_stats) + goto err_free_txq2sq; + priv->tx_rates = kcalloc_node(num_txqs, sizeof(*priv->tx_rates), GFP_KERNEL, node); if (!priv->tx_rates) - goto err_free_txq2sq; + goto err_free_txq2sq_stats; priv->channel_stats = kcalloc_node(nch, sizeof(*priv->channel_stats), GFP_KERNEL, node); @@ -5862,6 +5999,8 @@ int mlx5e_priv_init(struct mlx5e_priv *priv, err_free_tx_rates: kfree(priv->tx_rates); +err_free_txq2sq_stats: + kfree(priv->txq2sq_stats); err_free_txq2sq: kfree(priv->txq2sq); err_destroy_workqueue: @@ -5885,6 +6024,7 @@ void mlx5e_priv_cleanup(struct mlx5e_priv *priv) kvfree(priv->channel_stats[i]); kfree(priv->channel_stats); kfree(priv->tx_rates); + kfree(priv->txq2sq_stats); kfree(priv->txq2sq); destroy_workqueue(priv->wq); mlx5e_selq_cleanup(&priv->selq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 43f018567faf..225da8d691fc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1182,9 +1182,8 @@ static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe, check = csum_partial(tcp, tcp->doff * 4, csum_unfold((__force __sum16)cqe->check_sum)); /* Almost done, don't forget the pseudo header */ - tcp->check = csum_tcpudp_magic(ipv4->saddr, ipv4->daddr, - tot_len - sizeof(struct iphdr), - IPPROTO_TCP, check); + tcp->check = tcp_v4_check(tot_len - sizeof(struct iphdr), + ipv4->saddr, ipv4->daddr, check); } else { u16 payload_len = tot_len - sizeof(struct ipv6hdr); struct ipv6hdr *ipv6 = ip_p; @@ -1199,8 +1198,8 @@ static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe, check = csum_partial(tcp, tcp->doff * 4, csum_unfold((__force __sum16)cqe->check_sum)); /* Almost done, don't forget the pseudo header */ - tcp->check = csum_ipv6_magic(&ipv6->saddr, &ipv6->daddr, payload_len, - IPPROTO_TCP, check); + tcp->check = tcp_v6_check(payload_len, &ipv6->saddr, + &ipv6->daddr, check); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index d2ebe56c3977..20146a2dc7f4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -531,7 +531,7 @@ static bool esw_qos_element_type_supported(struct mlx5_core_dev *dev, int type) switch (type) { case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR: return MLX5_CAP_QOS(dev, esw_element_type) & - ELEMENT_TYPE_CAP_MASK_TASR; + ELEMENT_TYPE_CAP_MASK_TSAR; case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT: return MLX5_CAP_QOS(dev, esw_element_type) & ELEMENT_TYPE_CAP_MASK_VPORT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 32cdacc34a0d..a47d6419160d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -3353,9 +3353,9 @@ static int mlx5_fs_mode_get(struct devlink *devlink, u32 id, struct mlx5_core_dev *dev = devlink_priv(devlink); if (dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS) - strcpy(ctx->val.vstr, "smfs"); + strscpy(ctx->val.vstr, "smfs", sizeof(ctx->val.vstr)); else - strcpy(ctx->val.vstr, "dmfs"); + strscpy(ctx->val.vstr, "dmfs", sizeof(ctx->val.vstr)); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig index a510bf2cff2f..74f7e27b490f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig @@ -33,6 +33,7 @@ config MLXSW_CORE_THERMAL config MLXSW_PCI tristate "PCI bus implementation for Mellanox Technologies Switch ASICs" depends on PCI && HAS_IOMEM && MLXSW_CORE + select PAGE_POOL default m help This is PCI bus implementation for Mellanox Technologies Switch ASICs. diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c index f0ceb196a6ce..431accdc6213 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c @@ -702,8 +702,8 @@ static struct mlxsw_driver mlxsw_m_driver = { }; static const struct i2c_device_id mlxsw_m_i2c_id[] = { - { "mlxsw_minimal", 0}, - { }, + { "mlxsw_minimal" }, + { } }; static struct i2c_driver mlxsw_m_i2c_driver = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index bf66d996e32e..0320dabd1380 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -13,6 +13,7 @@ #include <linux/if_vlan.h> #include <linux/log2.h> #include <linux/string.h> +#include <net/page_pool/helpers.h> #include "pci_hw.h" #include "pci.h" @@ -61,15 +62,11 @@ struct mlxsw_pci_mem_item { }; struct mlxsw_pci_queue_elem_info { + struct page *pages[MLXSW_PCI_WQE_SG_ENTRIES]; char *elem; /* pointer to actual dma mapped element mem chunk */ - union { - struct { - struct sk_buff *skb; - } sdq; - struct { - struct sk_buff *skb; - } rdq; - } u; + struct { + struct sk_buff *skb; + } sdq; }; struct mlxsw_pci_queue { @@ -88,10 +85,14 @@ struct mlxsw_pci_queue { enum mlxsw_pci_cqe_v v; struct mlxsw_pci_queue *dq; struct napi_struct napi; + struct page_pool *page_pool; } cq; struct { struct tasklet_struct tasklet; } eq; + struct { + struct mlxsw_pci_queue *cq; + } rdq; } u; }; @@ -110,6 +111,7 @@ struct mlxsw_pci { bool cff_support; enum mlxsw_cmd_mbox_config_profile_lag_mode lag_mode; enum mlxsw_cmd_mbox_config_profile_flood_mode flood_mode; + u8 num_sg_entries; /* Number of scatter/gather entries for packets. */ struct mlxsw_pci_queue_type_group queues[MLXSW_PCI_QUEUE_TYPE_COUNT]; u32 doorbell_offset; struct mlxsw_core *core; @@ -335,6 +337,29 @@ static void mlxsw_pci_sdq_fini(struct mlxsw_pci *mlxsw_pci, mlxsw_cmd_hw2sw_sdq(mlxsw_pci->core, q->num); } +#define MLXSW_PCI_SKB_HEADROOM (NET_SKB_PAD + NET_IP_ALIGN) + +#define MLXSW_PCI_RX_BUF_SW_OVERHEAD \ + (MLXSW_PCI_SKB_HEADROOM + \ + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) + +static void +mlxsw_pci_wqe_rx_frag_set(struct mlxsw_pci *mlxsw_pci, struct page *page, + char *wqe, int index, size_t frag_len) +{ + dma_addr_t mapaddr; + + mapaddr = page_pool_get_dma_addr(page); + + if (index == 0) { + mapaddr += MLXSW_PCI_SKB_HEADROOM; + frag_len = frag_len - MLXSW_PCI_RX_BUF_SW_OVERHEAD; + } + + mlxsw_pci_wqe_address_set(wqe, index, mapaddr); + mlxsw_pci_wqe_byte_count_set(wqe, index, frag_len); +} + static int mlxsw_pci_wqe_frag_map(struct mlxsw_pci *mlxsw_pci, char *wqe, int index, char *frag_data, size_t frag_len, int direction) @@ -364,43 +389,140 @@ static void mlxsw_pci_wqe_frag_unmap(struct mlxsw_pci *mlxsw_pci, char *wqe, dma_unmap_single(&pdev->dev, mapaddr, frag_len, direction); } -static int mlxsw_pci_rdq_skb_alloc(struct mlxsw_pci *mlxsw_pci, - struct mlxsw_pci_queue_elem_info *elem_info, - gfp_t gfp) +static struct sk_buff *mlxsw_pci_rdq_build_skb(struct page *pages[], + u16 byte_count) { - size_t buf_len = MLXSW_PORT_MAX_MTU; - char *wqe = elem_info->elem; + unsigned int linear_data_size; struct sk_buff *skb; - int err; + int page_index = 0; + bool linear_only; + void *data; + + data = page_address(pages[page_index]); + net_prefetch(data); + + skb = napi_build_skb(data, PAGE_SIZE); + if (unlikely(!skb)) + return ERR_PTR(-ENOMEM); - skb = __netdev_alloc_skb_ip_align(NULL, buf_len, gfp); - if (!skb) + linear_only = byte_count + MLXSW_PCI_RX_BUF_SW_OVERHEAD <= PAGE_SIZE; + linear_data_size = linear_only ? byte_count : + PAGE_SIZE - + MLXSW_PCI_RX_BUF_SW_OVERHEAD; + + skb_reserve(skb, MLXSW_PCI_SKB_HEADROOM); + skb_put(skb, linear_data_size); + + if (linear_only) + return skb; + + byte_count -= linear_data_size; + page_index++; + + while (byte_count > 0) { + unsigned int frag_size; + struct page *page; + + page = pages[page_index]; + frag_size = min(byte_count, PAGE_SIZE); + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, + page, 0, frag_size, PAGE_SIZE); + byte_count -= frag_size; + page_index++; + } + + return skb; +} + +static int mlxsw_pci_rdq_page_alloc(struct mlxsw_pci_queue *q, + struct mlxsw_pci_queue_elem_info *elem_info, + int index) +{ + struct mlxsw_pci_queue *cq = q->u.rdq.cq; + char *wqe = elem_info->elem; + struct page *page; + + page = page_pool_dev_alloc_pages(cq->u.cq.page_pool); + if (unlikely(!page)) return -ENOMEM; - err = mlxsw_pci_wqe_frag_map(mlxsw_pci, wqe, 0, skb->data, - buf_len, DMA_FROM_DEVICE); - if (err) - goto err_frag_map; + mlxsw_pci_wqe_rx_frag_set(q->pci, page, wqe, index, PAGE_SIZE); + elem_info->pages[index] = page; + return 0; +} + +static void mlxsw_pci_rdq_page_free(struct mlxsw_pci_queue *q, + struct mlxsw_pci_queue_elem_info *elem_info, + int index) +{ + struct mlxsw_pci_queue *cq = q->u.rdq.cq; + + page_pool_put_page(cq->u.cq.page_pool, elem_info->pages[index], -1, + false); +} + +static u8 mlxsw_pci_num_sg_entries_get(u16 byte_count) +{ + return DIV_ROUND_UP(byte_count + MLXSW_PCI_RX_BUF_SW_OVERHEAD, + PAGE_SIZE); +} + +static int +mlxsw_pci_elem_info_pages_ref_store(const struct mlxsw_pci_queue *q, + const struct mlxsw_pci_queue_elem_info *el, + u16 byte_count, struct page *pages[], + u8 *p_num_sg_entries) +{ + u8 num_sg_entries; + int i; + + num_sg_entries = mlxsw_pci_num_sg_entries_get(byte_count); + if (WARN_ON_ONCE(num_sg_entries > q->pci->num_sg_entries)) + return -EINVAL; + + for (i = 0; i < num_sg_entries; i++) + pages[i] = el->pages[i]; + + *p_num_sg_entries = num_sg_entries; + return 0; +} + +static int +mlxsw_pci_rdq_pages_alloc(struct mlxsw_pci_queue *q, + struct mlxsw_pci_queue_elem_info *elem_info, + u8 num_sg_entries) +{ + struct page *old_pages[MLXSW_PCI_WQE_SG_ENTRIES]; + struct mlxsw_pci_queue *cq = q->u.rdq.cq; + int i, err; + + for (i = 0; i < num_sg_entries; i++) { + old_pages[i] = elem_info->pages[i]; + err = mlxsw_pci_rdq_page_alloc(q, elem_info, i); + if (err) { + dev_err_ratelimited(&q->pci->pdev->dev, "Failed to alloc page\n"); + goto err_page_alloc; + } + } - elem_info->u.rdq.skb = skb; return 0; -err_frag_map: - dev_kfree_skb_any(skb); +err_page_alloc: + for (i--; i >= 0; i--) + page_pool_recycle_direct(cq->u.cq.page_pool, old_pages[i]); + return err; } -static void mlxsw_pci_rdq_skb_free(struct mlxsw_pci *mlxsw_pci, - struct mlxsw_pci_queue_elem_info *elem_info) +static void +mlxsw_pci_rdq_pages_recycle(struct mlxsw_pci_queue *q, struct page *pages[], + u8 num_sg_entries) { - struct sk_buff *skb; - char *wqe; - - skb = elem_info->u.rdq.skb; - wqe = elem_info->elem; + struct mlxsw_pci_queue *cq = q->u.rdq.cq; + int i; - mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, 0, DMA_FROM_DEVICE); - dev_kfree_skb_any(skb); + for (i = 0; i < num_sg_entries; i++) + page_pool_recycle_direct(cq->u.cq.page_pool, pages[i]); } static int mlxsw_pci_rdq_init(struct mlxsw_pci *mlxsw_pci, char *mbox, @@ -410,7 +532,7 @@ static int mlxsw_pci_rdq_init(struct mlxsw_pci *mlxsw_pci, char *mbox, u8 sdq_count = mlxsw_pci->num_sdqs; struct mlxsw_pci_queue *cq; u8 cq_num; - int i; + int i, j; int err; q->producer_counter = 0; @@ -434,15 +556,19 @@ static int mlxsw_pci_rdq_init(struct mlxsw_pci *mlxsw_pci, char *mbox, cq = mlxsw_pci_cq_get(mlxsw_pci, cq_num); cq->u.cq.dq = q; + q->u.rdq.cq = cq; mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q); for (i = 0; i < q->count; i++) { elem_info = mlxsw_pci_queue_elem_info_producer_get(q); BUG_ON(!elem_info); - err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info, GFP_KERNEL); - if (err) - goto rollback; + + for (j = 0; j < mlxsw_pci->num_sg_entries; j++) { + err = mlxsw_pci_rdq_page_alloc(q, elem_info, j); + if (err) + goto rollback; + } /* Everything is set up, ring doorbell to pass elem to HW */ q->producer_counter++; mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q); @@ -453,8 +579,11 @@ static int mlxsw_pci_rdq_init(struct mlxsw_pci *mlxsw_pci, char *mbox, rollback: for (i--; i >= 0; i--) { elem_info = mlxsw_pci_queue_elem_info_get(q, i); - mlxsw_pci_rdq_skb_free(mlxsw_pci, elem_info); + for (j--; j >= 0; j--) + mlxsw_pci_rdq_page_free(q, elem_info, j); + j = mlxsw_pci->num_sg_entries; } + q->u.rdq.cq = NULL; cq->u.cq.dq = NULL; mlxsw_cmd_hw2sw_rdq(mlxsw_pci->core, q->num); @@ -465,12 +594,13 @@ static void mlxsw_pci_rdq_fini(struct mlxsw_pci *mlxsw_pci, struct mlxsw_pci_queue *q) { struct mlxsw_pci_queue_elem_info *elem_info; - int i; + int i, j; mlxsw_cmd_hw2sw_rdq(mlxsw_pci->core, q->num); for (i = 0; i < q->count; i++) { elem_info = mlxsw_pci_queue_elem_info_get(q, i); - mlxsw_pci_rdq_skb_free(mlxsw_pci, elem_info); + for (j = 0; j < mlxsw_pci->num_sg_entries; j++) + mlxsw_pci_rdq_page_free(q, elem_info, j); } } @@ -515,7 +645,7 @@ static void mlxsw_pci_cqe_sdq_handle(struct mlxsw_pci *mlxsw_pci, struct mlxsw_pci_queue *q, u16 consumer_counter_limit, enum mlxsw_pci_cqe_v cqe_v, - char *cqe) + char *cqe, int budget) { struct pci_dev *pdev = mlxsw_pci->pdev; struct mlxsw_pci_queue_elem_info *elem_info; @@ -526,8 +656,8 @@ static void mlxsw_pci_cqe_sdq_handle(struct mlxsw_pci *mlxsw_pci, spin_lock(&q->lock); elem_info = mlxsw_pci_queue_elem_info_consumer_get(q); - tx_info = mlxsw_skb_cb(elem_info->u.sdq.skb)->tx_info; - skb = elem_info->u.sdq.skb; + tx_info = mlxsw_skb_cb(elem_info->sdq.skb)->tx_info; + skb = elem_info->sdq.skb; wqe = elem_info->elem; for (i = 0; i < MLXSW_PCI_WQE_SG_ENTRIES; i++) mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, i, DMA_TO_DEVICE); @@ -541,8 +671,8 @@ static void mlxsw_pci_cqe_sdq_handle(struct mlxsw_pci *mlxsw_pci, } if (skb) - dev_kfree_skb_any(skb); - elem_info->u.sdq.skb = NULL; + napi_consume_skb(skb, budget); + elem_info->sdq.skb = NULL; if (q->consumer_counter++ != consumer_counter_limit) dev_dbg_ratelimited(&pdev->dev, "Consumer counter does not match limit in SDQ\n"); @@ -604,27 +734,40 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, enum mlxsw_pci_cqe_v cqe_v, char *cqe) { struct pci_dev *pdev = mlxsw_pci->pdev; + struct page *pages[MLXSW_PCI_WQE_SG_ENTRIES]; struct mlxsw_pci_queue_elem_info *elem_info; struct mlxsw_rx_info rx_info = {}; - char wqe[MLXSW_PCI_WQE_SIZE]; struct sk_buff *skb; + u8 num_sg_entries; u16 byte_count; int err; elem_info = mlxsw_pci_queue_elem_info_consumer_get(q); - skb = elem_info->u.rdq.skb; - memcpy(wqe, elem_info->elem, MLXSW_PCI_WQE_SIZE); if (q->consumer_counter++ != consumer_counter_limit) dev_dbg_ratelimited(&pdev->dev, "Consumer counter does not match limit in RDQ\n"); - err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info, GFP_ATOMIC); - if (err) { - dev_err_ratelimited(&pdev->dev, "Failed to alloc skb for RDQ\n"); + byte_count = mlxsw_pci_cqe_byte_count_get(cqe); + if (mlxsw_pci_cqe_crc_get(cqe_v, cqe)) + byte_count -= ETH_FCS_LEN; + + err = mlxsw_pci_elem_info_pages_ref_store(q, elem_info, byte_count, + pages, &num_sg_entries); + if (err) + goto out; + + err = mlxsw_pci_rdq_pages_alloc(q, elem_info, num_sg_entries); + if (err) + goto out; + + skb = mlxsw_pci_rdq_build_skb(pages, byte_count); + if (IS_ERR(skb)) { + dev_err_ratelimited(&pdev->dev, "Failed to build skb for RDQ\n"); + mlxsw_pci_rdq_pages_recycle(q, pages, num_sg_entries); goto out; } - mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, 0, DMA_FROM_DEVICE); + skb_mark_for_recycle(skb); if (mlxsw_pci_cqe_lag_get(cqe_v, cqe)) { rx_info.is_lag = true; @@ -657,10 +800,6 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, mlxsw_pci_skb_cb_ts_set(mlxsw_pci, skb, cqe_v, cqe); - byte_count = mlxsw_pci_cqe_byte_count_get(cqe); - if (mlxsw_pci_cqe_crc_get(cqe_v, cqe)) - byte_count -= ETH_FCS_LEN; - skb_put(skb, byte_count); mlxsw_core_skb_receive(mlxsw_pci->core, skb, &rx_info); out: @@ -785,7 +924,7 @@ static int mlxsw_pci_napi_poll_cq_tx(struct napi_struct *napi, int budget) mlxsw_pci_queue_doorbell_consumer_ring(mlxsw_pci, q); mlxsw_pci_cqe_sdq_handle(mlxsw_pci, sdq, - wqe_counter, q->u.cq.v, ncqe); + wqe_counter, q->u.cq.v, ncqe, budget); work_done++; } @@ -832,19 +971,51 @@ static void mlxsw_pci_cq_napi_setup(struct mlxsw_pci_queue *q, mlxsw_pci_napi_poll_cq_rx); break; } - - napi_enable(&q->u.cq.napi); } static void mlxsw_pci_cq_napi_teardown(struct mlxsw_pci_queue *q) { - napi_disable(&q->u.cq.napi); netif_napi_del(&q->u.cq.napi); } +static int mlxsw_pci_cq_page_pool_init(struct mlxsw_pci_queue *q, + enum mlxsw_pci_cq_type cq_type) +{ + struct page_pool_params pp_params = {}; + struct mlxsw_pci *mlxsw_pci = q->pci; + struct page_pool *page_pool; + + if (cq_type != MLXSW_PCI_CQ_RDQ) + return 0; + + pp_params.flags = PP_FLAG_DMA_MAP; + pp_params.pool_size = MLXSW_PCI_WQE_COUNT * mlxsw_pci->num_sg_entries; + pp_params.nid = dev_to_node(&mlxsw_pci->pdev->dev); + pp_params.dev = &mlxsw_pci->pdev->dev; + pp_params.napi = &q->u.cq.napi; + pp_params.dma_dir = DMA_FROM_DEVICE; + + page_pool = page_pool_create(&pp_params); + if (IS_ERR(page_pool)) + return PTR_ERR(page_pool); + + q->u.cq.page_pool = page_pool; + return 0; +} + +static void mlxsw_pci_cq_page_pool_fini(struct mlxsw_pci_queue *q, + enum mlxsw_pci_cq_type cq_type) +{ + if (cq_type != MLXSW_PCI_CQ_RDQ) + return; + + page_pool_destroy(q->u.cq.page_pool); +} + static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox, struct mlxsw_pci_queue *q) { + enum mlxsw_pci_cq_type cq_type = mlxsw_pci_cq_type(mlxsw_pci, q); int i; int err; @@ -874,15 +1045,29 @@ static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox, err = mlxsw_cmd_sw2hw_cq(mlxsw_pci->core, mbox, q->num); if (err) return err; - mlxsw_pci_cq_napi_setup(q, mlxsw_pci_cq_type(mlxsw_pci, q)); + mlxsw_pci_cq_napi_setup(q, cq_type); + + err = mlxsw_pci_cq_page_pool_init(q, cq_type); + if (err) + goto err_page_pool_init; + + napi_enable(&q->u.cq.napi); mlxsw_pci_queue_doorbell_consumer_ring(mlxsw_pci, q); mlxsw_pci_queue_doorbell_arm_consumer_ring(mlxsw_pci, q); return 0; + +err_page_pool_init: + mlxsw_pci_cq_napi_teardown(q); + return err; } static void mlxsw_pci_cq_fini(struct mlxsw_pci *mlxsw_pci, struct mlxsw_pci_queue *q) { + enum mlxsw_pci_cq_type cq_type = mlxsw_pci_cq_type(mlxsw_pci, q); + + napi_disable(&q->u.cq.napi); + mlxsw_pci_cq_page_pool_fini(q, cq_type); mlxsw_pci_cq_napi_teardown(q); mlxsw_cmd_hw2sw_cq(mlxsw_pci->core, q->num); } @@ -1594,18 +1779,25 @@ static int mlxsw_pci_sys_ready_wait(struct mlxsw_pci *mlxsw_pci, return -EBUSY; } -static int mlxsw_pci_reset_at_pci_disable(struct mlxsw_pci *mlxsw_pci) +static int mlxsw_pci_reset_at_pci_disable(struct mlxsw_pci *mlxsw_pci, + bool pci_reset_sbr_supported) { struct pci_dev *pdev = mlxsw_pci->pdev; char mrsr_pl[MLXSW_REG_MRSR_LEN]; int err; + if (!pci_reset_sbr_supported) { + pci_dbg(pdev, "Performing PCI hot reset instead of \"all reset\"\n"); + goto sbr; + } + mlxsw_reg_mrsr_pack(mrsr_pl, MLXSW_REG_MRSR_COMMAND_RESET_AT_PCI_DISABLE); err = mlxsw_reg_write(mlxsw_pci->core, MLXSW_REG(mrsr), mrsr_pl); if (err) return err; +sbr: device_lock_assert(&pdev->dev); pci_cfg_access_lock(pdev); @@ -1633,6 +1825,7 @@ static int mlxsw_pci_reset(struct mlxsw_pci *mlxsw_pci, const struct pci_device_id *id) { struct pci_dev *pdev = mlxsw_pci->pdev; + bool pci_reset_sbr_supported = false; char mcam_pl[MLXSW_REG_MCAM_LEN]; bool pci_reset_supported = false; u32 sys_status; @@ -1652,13 +1845,17 @@ mlxsw_pci_reset(struct mlxsw_pci *mlxsw_pci, const struct pci_device_id *id) mlxsw_reg_mcam_pack(mcam_pl, MLXSW_REG_MCAM_FEATURE_GROUP_ENHANCED_FEATURES); err = mlxsw_reg_query(mlxsw_pci->core, MLXSW_REG(mcam), mcam_pl); - if (!err) + if (!err) { mlxsw_reg_mcam_unpack(mcam_pl, MLXSW_REG_MCAM_PCI_RESET, &pci_reset_supported); + mlxsw_reg_mcam_unpack(mcam_pl, MLXSW_REG_MCAM_PCI_RESET_SBR, + &pci_reset_sbr_supported); + } if (pci_reset_supported) { pci_dbg(pdev, "Starting PCI reset flow\n"); - err = mlxsw_pci_reset_at_pci_disable(mlxsw_pci); + err = mlxsw_pci_reset_at_pci_disable(mlxsw_pci, + pci_reset_sbr_supported); } else { pci_dbg(pdev, "Starting software reset flow\n"); err = mlxsw_pci_reset_sw(mlxsw_pci); @@ -1691,6 +1888,17 @@ static void mlxsw_pci_free_irq_vectors(struct mlxsw_pci *mlxsw_pci) pci_free_irq_vectors(mlxsw_pci->pdev); } +static void mlxsw_pci_num_sg_entries_set(struct mlxsw_pci *mlxsw_pci) +{ + u8 num_sg_entries; + + num_sg_entries = mlxsw_pci_num_sg_entries_get(MLXSW_PORT_MAX_MTU); + mlxsw_pci->num_sg_entries = min(num_sg_entries, + MLXSW_PCI_WQE_SG_ENTRIES); + + WARN_ON(num_sg_entries > MLXSW_PCI_WQE_SG_ENTRIES); +} + static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core, const struct mlxsw_config_profile *profile, struct mlxsw_res *res) @@ -1813,6 +2021,8 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core, if (err) goto err_requery_resources; + mlxsw_pci_num_sg_entries_set(mlxsw_pci); + err = mlxsw_pci_napi_devs_init(mlxsw_pci); if (err) goto err_napi_devs_init; @@ -1919,7 +2129,7 @@ static int mlxsw_pci_skb_transmit(void *bus_priv, struct sk_buff *skb, goto unlock; } mlxsw_skb_cb(skb)->tx_info = *tx_info; - elem_info->u.sdq.skb = skb; + elem_info->sdq.skb = skb; wqe = elem_info->elem; mlxsw_pci_wqe_c_set(wqe, 1); /* always report completion */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/port.h b/drivers/net/ethernet/mellanox/mlxsw/port.h index ac4d4ea51597..0a73b1a4526e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/port.h +++ b/drivers/net/ethernet/mellanox/mlxsw/port.h @@ -6,7 +6,8 @@ #include <linux/types.h> -#define MLXSW_PORT_MAX_MTU 10000 +#define MLXSW_PORT_MAX_MTU (10 * 1024) +#define MLXSW_PORT_ETH_FRAME_HDR (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN) #define MLXSW_PORT_DEFAULT_VID 1 diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 8adf86a6f5cc..3bb89045eaf5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -10671,6 +10671,8 @@ enum mlxsw_reg_mcam_mng_feature_cap_mask_bits { MLXSW_REG_MCAM_MCIA_128B = 34, /* If set, MRSR.command=6 is supported. */ MLXSW_REG_MCAM_PCI_RESET = 48, + /* If set, MRSR.command=6 is supported with Secondary Bus Reset. */ + MLXSW_REG_MCAM_PCI_RESET_SBR = 67, }; #define MLXSW_REG_BYTES_PER_DWORD 0x4 diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 030ed71f945d..f064789f3240 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -405,29 +405,12 @@ static int mlxsw_sp_port_dev_addr_init(struct mlxsw_sp_port *mlxsw_sp_port) mlxsw_sp_port->dev->dev_addr); } -static int mlxsw_sp_port_max_mtu_get(struct mlxsw_sp_port *mlxsw_sp_port, int *p_max_mtu) -{ - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - char pmtu_pl[MLXSW_REG_PMTU_LEN]; - int err; - - mlxsw_reg_pmtu_pack(pmtu_pl, mlxsw_sp_port->local_port, 0); - err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(pmtu), pmtu_pl); - if (err) - return err; - - *p_max_mtu = mlxsw_reg_pmtu_max_mtu_get(pmtu_pl); - return 0; -} - static int mlxsw_sp_port_mtu_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; char pmtu_pl[MLXSW_REG_PMTU_LEN]; - mtu += MLXSW_TXHDR_LEN + ETH_HLEN; - if (mtu > mlxsw_sp_port->max_mtu) - return -EINVAL; + mtu += MLXSW_PORT_ETH_FRAME_HDR; mlxsw_reg_pmtu_pack(pmtu_pl, mlxsw_sp_port->local_port, mtu); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmtu), pmtu_pl); @@ -1697,8 +1680,8 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u16 local_port, NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_TC; dev->hw_features |= NETIF_F_HW_TC | NETIF_F_LOOPBACK; - dev->min_mtu = 0; - dev->max_mtu = ETH_MAX_MTU; + dev->min_mtu = ETH_MIN_MTU; + dev->max_mtu = MLXSW_PORT_MAX_MTU - MLXSW_PORT_ETH_FRAME_HDR; /* Each packet needs to have a Tx header (metadata) on top all other * headers. @@ -1727,13 +1710,6 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u16 local_port, goto err_max_speed_get; } - err = mlxsw_sp_port_max_mtu_get(mlxsw_sp_port, &mlxsw_sp_port->max_mtu); - if (err) { - dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to get maximum MTU\n", - mlxsw_sp_port->local_port); - goto err_port_max_mtu_get; - } - err = mlxsw_sp_port_mtu_set(mlxsw_sp_port, ETH_DATA_LEN); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set MTU\n", @@ -1877,7 +1853,6 @@ err_port_ets_init: err_port_buffers_init: err_port_admin_status_set: err_port_mtu_set: -err_port_max_mtu_get: err_max_speed_get: err_port_speed_by_width_set: err_port_system_port_mapping_set: diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 3beb5d0847ab..bb0586b45c8d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -359,7 +359,6 @@ struct mlxsw_sp_port { u16 egr_types; struct mlxsw_sp_ptp_port_stats stats; } ptp; - int max_mtu; u32 max_speed; struct mlxsw_sp_hdroom *hdroom; u64 module_overheat_initial_val; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index c9f1c79f3f9d..2c0cfa79d138 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -399,11 +399,13 @@ void mlxsw_sp_hdroom_bufs_reset_sizes(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_hdroom *hdroom) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + unsigned int max_mtu = mlxsw_sp_port->dev->max_mtu; u16 reserve_cells; int i; + max_mtu += MLXSW_PORT_ETH_FRAME_HDR; /* Internal buffer. */ - reserve_cells = mlxsw_sp_hdroom_int_buf_size_get(mlxsw_sp, mlxsw_sp_port->max_mtu, + reserve_cells = mlxsw_sp_hdroom_int_buf_size_get(mlxsw_sp, max_mtu, mlxsw_sp_port->max_speed); reserve_cells = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, reserve_cells); hdroom->int_buf.reserve_cells = reserve_cells; @@ -613,7 +615,9 @@ static int mlxsw_sp_port_headroom_init(struct mlxsw_sp_port *mlxsw_sp_port) mlxsw_sp_hdroom_bufs_reset_sizes(mlxsw_sp_port, &hdroom); /* Buffer 9 is used for control traffic. */ - size9 = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, mlxsw_sp_port->max_mtu); + size9 = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, + mlxsw_sp_port->dev->max_mtu + + MLXSW_PORT_ETH_FRAME_HDR); hdroom.bufs.buf[9].size_cells = mlxsw_sp_bytes_cells(mlxsw_sp, size9); return __mlxsw_sp_hdroom_configure(mlxsw_sp_port, &hdroom, true); @@ -1607,8 +1611,8 @@ static void mlxsw_sp_sb_sr_occ_query_cb(struct mlxsw_core *mlxsw_core, int mlxsw_sp_sb_occ_snapshot(struct mlxsw_core *mlxsw_core, unsigned int sb_index) { + u16 local_port, local_port_1, first_local_port, last_local_port; struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); - u16 local_port, local_port_1, last_local_port; struct mlxsw_sp_sb_sr_occ_query_cb_ctx cb_ctx; u8 masked_count, current_page = 0; unsigned long cb_priv = 0; @@ -1628,6 +1632,7 @@ next_batch: masked_count = 0; mlxsw_reg_sbsr_pack(sbsr_pl, false); mlxsw_reg_sbsr_port_page_set(sbsr_pl, current_page); + first_local_port = current_page * MLXSW_REG_SBSR_NUM_PORTS_IN_PAGE; last_local_port = current_page * MLXSW_REG_SBSR_NUM_PORTS_IN_PAGE + MLXSW_REG_SBSR_NUM_PORTS_IN_PAGE - 1; @@ -1645,9 +1650,12 @@ next_batch: if (local_port != MLXSW_PORT_CPU_PORT) { /* Ingress quotas are not supported for the CPU port */ mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, - local_port, 1); + local_port - first_local_port, + 1); } - mlxsw_reg_sbsr_egress_port_mask_set(sbsr_pl, local_port, 1); + mlxsw_reg_sbsr_egress_port_mask_set(sbsr_pl, + local_port - first_local_port, + 1); for (i = 0; i < mlxsw_sp->sb_vals->pool_count; i++) { err = mlxsw_sp_sb_pm_occ_query(mlxsw_sp, local_port, i, &bulk_list); @@ -1684,7 +1692,7 @@ int mlxsw_sp_sb_occ_max_clear(struct mlxsw_core *mlxsw_core, unsigned int sb_index) { struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); - u16 local_port, last_local_port; + u16 local_port, first_local_port, last_local_port; LIST_HEAD(bulk_list); unsigned int masked_count; u8 current_page = 0; @@ -1702,6 +1710,7 @@ next_batch: masked_count = 0; mlxsw_reg_sbsr_pack(sbsr_pl, true); mlxsw_reg_sbsr_port_page_set(sbsr_pl, current_page); + first_local_port = current_page * MLXSW_REG_SBSR_NUM_PORTS_IN_PAGE; last_local_port = current_page * MLXSW_REG_SBSR_NUM_PORTS_IN_PAGE + MLXSW_REG_SBSR_NUM_PORTS_IN_PAGE - 1; @@ -1719,9 +1728,12 @@ next_batch: if (local_port != MLXSW_PORT_CPU_PORT) { /* Ingress quotas are not supported for the CPU port */ mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, - local_port, 1); + local_port - first_local_port, + 1); } - mlxsw_reg_sbsr_egress_port_mask_set(sbsr_pl, local_port, 1); + mlxsw_reg_sbsr_egress_port_mask_set(sbsr_pl, + local_port - first_local_port, + 1); for (i = 0; i < mlxsw_sp->sb_vals->pool_count; i++) { err = mlxsw_sp_sb_pm_occ_clear(mlxsw_sp, local_port, i, &bulk_list); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 40ba314fbc72..800dfb64ec83 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -11450,12 +11450,16 @@ static int mlxsw_sp_mp_hash_init(struct mlxsw_sp *mlxsw_sp) { bool old_inc_parsing_depth, new_inc_parsing_depth; struct mlxsw_sp_mp_hash_config config = {}; + struct net *net = mlxsw_sp_net(mlxsw_sp); char recr2_pl[MLXSW_REG_RECR2_LEN]; unsigned long bit; u32 seed; int err; - seed = jhash(mlxsw_sp->base_mac, sizeof(mlxsw_sp->base_mac), 0); + seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).user_seed; + if (!seed) + seed = jhash(mlxsw_sp->base_mac, sizeof(mlxsw_sp->base_mac), 0); + mlxsw_reg_recr2_pack(recr2_pl, seed); mlxsw_sp_mp4_hash_init(mlxsw_sp, &config); mlxsw_sp_mp6_hash_init(mlxsw_sp, &config); diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c index d0f4ff4ee075..0d1740d64676 100644 --- a/drivers/net/ethernet/microchip/lan743x_ethtool.c +++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c @@ -1127,8 +1127,12 @@ static void lan743x_ethtool_get_wol(struct net_device *netdev, if (netdev->phydev) phy_ethtool_get_wol(netdev->phydev, wol); - wol->supported |= WAKE_BCAST | WAKE_UCAST | WAKE_MCAST | - WAKE_MAGIC | WAKE_PHY | WAKE_ARP; + if (wol->supported != adapter->phy_wol_supported) + netif_warn(adapter, drv, adapter->netdev, + "PHY changed its supported WOL! old=%x, new=%x\n", + adapter->phy_wol_supported, wol->supported); + + wol->supported |= MAC_SUPPORTED_WAKES; if (adapter->is_pci11x1x) wol->supported |= WAKE_MAGICSECURE; @@ -1143,7 +1147,39 @@ static int lan743x_ethtool_set_wol(struct net_device *netdev, { struct lan743x_adapter *adapter = netdev_priv(netdev); + /* WAKE_MAGICSEGURE is a modifier of and only valid together with + * WAKE_MAGIC + */ + if ((wol->wolopts & WAKE_MAGICSECURE) && !(wol->wolopts & WAKE_MAGIC)) + return -EINVAL; + + if (netdev->phydev) { + struct ethtool_wolinfo phy_wol; + int ret; + + phy_wol.wolopts = wol->wolopts & adapter->phy_wol_supported; + + /* If WAKE_MAGICSECURE was requested, filter out WAKE_MAGIC + * for PHYs that do not support WAKE_MAGICSECURE + */ + if (wol->wolopts & WAKE_MAGICSECURE && + !(adapter->phy_wol_supported & WAKE_MAGICSECURE)) + phy_wol.wolopts &= ~WAKE_MAGIC; + + ret = phy_ethtool_set_wol(netdev->phydev, &phy_wol); + if (ret && (ret != -EOPNOTSUPP)) + return ret; + + if (ret == -EOPNOTSUPP) + adapter->phy_wolopts = 0; + else + adapter->phy_wolopts = phy_wol.wolopts; + } else { + adapter->phy_wolopts = 0; + } + adapter->wolopts = 0; + wol->wolopts &= ~adapter->phy_wolopts; if (wol->wolopts & WAKE_UCAST) adapter->wolopts |= WAKE_UCAST; if (wol->wolopts & WAKE_MCAST) @@ -1164,10 +1200,10 @@ static int lan743x_ethtool_set_wol(struct net_device *netdev, memset(adapter->sopass, 0, sizeof(u8) * SOPASS_MAX); } + wol->wolopts = adapter->wolopts | adapter->phy_wolopts; device_set_wakeup_enable(&adapter->pdev->dev, (bool)wol->wolopts); - return netdev->phydev ? phy_ethtool_set_wol(netdev->phydev, wol) - : -ENETDOWN; + return 0; } #endif /* CONFIG_PM */ diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 6be8a43c908a..e418539565b1 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -3118,6 +3118,17 @@ static int lan743x_netdev_open(struct net_device *netdev) if (ret) goto close_tx; } + +#ifdef CONFIG_PM + if (adapter->netdev->phydev) { + struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; + + phy_ethtool_get_wol(netdev->phydev, &wol); + adapter->phy_wol_supported = wol.supported; + adapter->phy_wolopts = wol.wolopts; + } +#endif + return 0; close_tx: @@ -3575,7 +3586,7 @@ static void lan743x_pm_set_wol(struct lan743x_adapter *adapter) /* clear wake settings */ pmtctl = lan743x_csr_read(adapter, PMT_CTL); - pmtctl |= PMT_CTL_WUPS_MASK_; + pmtctl |= PMT_CTL_WUPS_MASK_ | PMT_CTL_RES_CLR_WKP_MASK_; pmtctl &= ~(PMT_CTL_GPIO_WAKEUP_EN_ | PMT_CTL_EEE_WAKEUP_EN_ | PMT_CTL_WOL_EN_ | PMT_CTL_MAC_D3_RX_CLK_OVR_ | PMT_CTL_RX_FCT_RFE_D3_CLK_OVR_ | PMT_CTL_ETH_PHY_WAKE_EN_); @@ -3587,10 +3598,9 @@ static void lan743x_pm_set_wol(struct lan743x_adapter *adapter) pmtctl |= PMT_CTL_ETH_PHY_D3_COLD_OVR_ | PMT_CTL_ETH_PHY_D3_OVR_; - if (adapter->wolopts & WAKE_PHY) { - pmtctl |= PMT_CTL_ETH_PHY_EDPD_PLL_CTL_; + if (adapter->phy_wolopts) pmtctl |= PMT_CTL_ETH_PHY_WAKE_EN_; - } + if (adapter->wolopts & WAKE_MAGIC) { wucsr |= MAC_WUCSR_MPEN_; macrx |= MAC_RX_RXEN_; @@ -3686,7 +3696,7 @@ static int lan743x_pm_suspend(struct device *dev) lan743x_csr_write(adapter, MAC_WUCSR2, 0); lan743x_csr_write(adapter, MAC_WK_SRC, 0xFFFFFFFF); - if (adapter->wolopts) + if (adapter->wolopts || adapter->phy_wolopts) lan743x_pm_set_wol(adapter); if (adapter->is_pci11x1x) { @@ -3710,6 +3720,7 @@ static int lan743x_pm_resume(struct device *dev) struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); struct lan743x_adapter *adapter = netdev_priv(netdev); + u32 data; int ret; pci_set_power_state(pdev, PCI_D0); @@ -3728,6 +3739,30 @@ static int lan743x_pm_resume(struct device *dev) return ret; } + ret = lan743x_csr_read(adapter, MAC_WK_SRC); + netif_dbg(adapter, drv, adapter->netdev, + "Wakeup source : 0x%08X\n", ret); + + /* Clear the wol configuration and status bits. Note that + * the status bits are "Write One to Clear (W1C)" + */ + data = MAC_WUCSR_EEE_TX_WAKE_ | MAC_WUCSR_EEE_RX_WAKE_ | + MAC_WUCSR_RFE_WAKE_FR_ | MAC_WUCSR_PFDA_FR_ | MAC_WUCSR_WUFR_ | + MAC_WUCSR_MPR_ | MAC_WUCSR_BCAST_FR_; + lan743x_csr_write(adapter, MAC_WUCSR, data); + + data = MAC_WUCSR2_NS_RCD_ | MAC_WUCSR2_ARP_RCD_ | + MAC_WUCSR2_IPV6_TCPSYN_RCD_ | MAC_WUCSR2_IPV4_TCPSYN_RCD_; + lan743x_csr_write(adapter, MAC_WUCSR2, data); + + data = MAC_WK_SRC_ETH_PHY_WK_ | MAC_WK_SRC_IPV6_TCPSYN_RCD_WK_ | + MAC_WK_SRC_IPV4_TCPSYN_RCD_WK_ | MAC_WK_SRC_EEE_TX_WK_ | + MAC_WK_SRC_EEE_RX_WK_ | MAC_WK_SRC_RFE_FR_WK_ | + MAC_WK_SRC_PFDA_FR_WK_ | MAC_WK_SRC_MP_FR_WK_ | + MAC_WK_SRC_BCAST_FR_WK_ | MAC_WK_SRC_WU_FR_WK_ | + MAC_WK_SRC_WK_FR_SAVED_; + lan743x_csr_write(adapter, MAC_WK_SRC, data); + /* open netdev when netdev is at running state while resume. * For instance, it is true when system wakesup after pm-suspend * However, it is false when system wakes up after suspend GUI menu @@ -3736,9 +3771,6 @@ static int lan743x_pm_resume(struct device *dev) lan743x_netdev_open(netdev); netif_device_attach(netdev); - ret = lan743x_csr_read(adapter, MAC_WK_SRC); - netif_info(adapter, drv, adapter->netdev, - "Wakeup source : 0x%08X\n", ret); return 0; } diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h index 645bc048e52e..3b2585a384e2 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.h +++ b/drivers/net/ethernet/microchip/lan743x_main.h @@ -61,6 +61,7 @@ #define PMT_CTL_RX_FCT_RFE_D3_CLK_OVR_ BIT(18) #define PMT_CTL_GPIO_WAKEUP_EN_ BIT(15) #define PMT_CTL_EEE_WAKEUP_EN_ BIT(13) +#define PMT_CTL_RES_CLR_WKP_MASK_ GENMASK(9, 8) #define PMT_CTL_READY_ BIT(7) #define PMT_CTL_ETH_PHY_RST_ BIT(4) #define PMT_CTL_WOL_EN_ BIT(3) @@ -227,12 +228,31 @@ #define MAC_WUCSR (0x140) #define MAC_MP_SO_EN_ BIT(21) #define MAC_WUCSR_RFE_WAKE_EN_ BIT(14) +#define MAC_WUCSR_EEE_TX_WAKE_ BIT(13) +#define MAC_WUCSR_EEE_RX_WAKE_ BIT(11) +#define MAC_WUCSR_RFE_WAKE_FR_ BIT(9) +#define MAC_WUCSR_PFDA_FR_ BIT(7) +#define MAC_WUCSR_WUFR_ BIT(6) +#define MAC_WUCSR_MPR_ BIT(5) +#define MAC_WUCSR_BCAST_FR_ BIT(4) #define MAC_WUCSR_PFDA_EN_ BIT(3) #define MAC_WUCSR_WAKE_EN_ BIT(2) #define MAC_WUCSR_MPEN_ BIT(1) #define MAC_WUCSR_BCST_EN_ BIT(0) #define MAC_WK_SRC (0x144) +#define MAC_WK_SRC_ETH_PHY_WK_ BIT(17) +#define MAC_WK_SRC_IPV6_TCPSYN_RCD_WK_ BIT(16) +#define MAC_WK_SRC_IPV4_TCPSYN_RCD_WK_ BIT(15) +#define MAC_WK_SRC_EEE_TX_WK_ BIT(14) +#define MAC_WK_SRC_EEE_RX_WK_ BIT(13) +#define MAC_WK_SRC_RFE_FR_WK_ BIT(12) +#define MAC_WK_SRC_PFDA_FR_WK_ BIT(11) +#define MAC_WK_SRC_MP_FR_WK_ BIT(10) +#define MAC_WK_SRC_BCAST_FR_WK_ BIT(9) +#define MAC_WK_SRC_WU_FR_WK_ BIT(8) +#define MAC_WK_SRC_WK_FR_SAVED_ BIT(7) + #define MAC_MP_SO_HI (0x148) #define MAC_MP_SO_LO (0x14C) @@ -295,6 +315,10 @@ #define RFE_INDX(index) (0x580 + (index << 2)) #define MAC_WUCSR2 (0x600) +#define MAC_WUCSR2_NS_RCD_ BIT(7) +#define MAC_WUCSR2_ARP_RCD_ BIT(6) +#define MAC_WUCSR2_IPV6_TCPSYN_RCD_ BIT(5) +#define MAC_WUCSR2_IPV4_TCPSYN_RCD_ BIT(4) #define SGMII_ACC (0x720) #define SGMII_ACC_SGMII_BZY_ BIT(31) @@ -1018,6 +1042,8 @@ enum lan743x_sgmii_lsd { LINK_2500_SLAVE }; +#define MAC_SUPPORTED_WAKES (WAKE_BCAST | WAKE_UCAST | WAKE_MCAST | \ + WAKE_MAGIC | WAKE_ARP) struct lan743x_adapter { struct net_device *netdev; struct mii_bus *mdiobus; @@ -1025,6 +1051,8 @@ struct lan743x_adapter { #ifdef CONFIG_PM u32 wolopts; u8 sopass[SOPASS_MAX]; + u32 phy_wolopts; + u32 phy_wol_supported; #endif struct pci_dev *pdev; struct lan743x_csr csr; diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c index 06811c60d598..c0fc85ac5db3 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c @@ -376,7 +376,6 @@ static void lan966x_get_eth_mac_stats(struct net_device *dev, lan966x->stats[idx + SYS_COUNT_TX_PMAC_BC]; mac_stats->SingleCollisionFrames = lan966x->stats[idx + SYS_COUNT_TX_COL]; - mac_stats->MultipleCollisionFrames = 0; mac_stats->FramesReceivedOK = lan966x->stats[idx + SYS_COUNT_RX_UC] + lan966x->stats[idx + SYS_COUNT_RX_MC] + @@ -384,26 +383,19 @@ static void lan966x_get_eth_mac_stats(struct net_device *dev, mac_stats->FrameCheckSequenceErrors = lan966x->stats[idx + SYS_COUNT_RX_CRC] + lan966x->stats[idx + SYS_COUNT_RX_CRC]; - mac_stats->AlignmentErrors = 0; mac_stats->OctetsTransmittedOK = lan966x->stats[idx + SYS_COUNT_TX_OCT] + lan966x->stats[idx + SYS_COUNT_TX_PMAC_OCT]; mac_stats->FramesWithDeferredXmissions = lan966x->stats[idx + SYS_COUNT_TX_MM_HOLD]; - mac_stats->LateCollisions = 0; - mac_stats->FramesAbortedDueToXSColls = 0; - mac_stats->FramesLostDueToIntMACXmitError = 0; - mac_stats->CarrierSenseErrors = 0; mac_stats->OctetsReceivedOK = lan966x->stats[idx + SYS_COUNT_RX_OCT]; - mac_stats->FramesLostDueToIntMACRcvError = 0; mac_stats->MulticastFramesXmittedOK = lan966x->stats[idx + SYS_COUNT_TX_MC] + lan966x->stats[idx + SYS_COUNT_TX_PMAC_MC]; mac_stats->BroadcastFramesXmittedOK = lan966x->stats[idx + SYS_COUNT_TX_BC] + lan966x->stats[idx + SYS_COUNT_TX_PMAC_BC]; - mac_stats->FramesWithExcessiveDeferral = 0; mac_stats->MulticastFramesReceivedOK = lan966x->stats[idx + SYS_COUNT_RX_MC]; mac_stats->BroadcastFramesReceivedOK = diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c index a4414f63c9b1..a1471e38d118 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c @@ -581,7 +581,7 @@ static void lan966x_vcap_move(struct net_device *dev, lan966x_vcap_wait_update(lan966x, admin->tgt_inst); } -static struct vcap_operations lan966x_vcap_ops = { +static const struct vcap_operations lan966x_vcap_ops = { .validate_keyset = lan966x_vcap_validate_keyset, .add_default_fields = lan966x_vcap_add_default_fields, .cache_erase = lan966x_vcap_cache_erase, diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c index 187efa1fc904..967c8621c250 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c @@ -1507,7 +1507,7 @@ static void sparx5_vcap_move(struct net_device *ndev, struct vcap_admin *admin, } } -static struct vcap_operations sparx5_vcap_ops = { +static const struct vcap_operations sparx5_vcap_ops = { .validate_keyset = sparx5_vcap_validate_keyset, .add_default_fields = sparx5_vcap_add_default_fields, .cache_erase = sparx5_vcap_cache_erase, diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.h b/drivers/net/ethernet/microchip/vcap/vcap_api.h index 9eccfa633c1a..6069ad95c27e 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api.h +++ b/drivers/net/ethernet/microchip/vcap/vcap_api.h @@ -271,7 +271,7 @@ struct vcap_operations { /* VCAP API Client control interface */ struct vcap_control { - struct vcap_operations *ops; /* client supplied operations */ + const struct vcap_operations *ops; /* client supplied operations */ const struct vcap_info *vcaps; /* client supplied vcap models */ const struct vcap_statistics *stats; /* client supplied vcap stats */ struct list_head list; /* list of vcap instances */ 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 b23c11b0647c..9c9d38042125 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c @@ -221,7 +221,7 @@ static int vcap_test_port_info(struct net_device *ndev, return 0; } -static struct vcap_operations test_callbacks = { +static const struct vcap_operations test_callbacks = { .validate_keyset = test_val_keyset, .add_default_fields = test_add_def_fields, .cache_erase = test_cache_erase, diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c index fe4e166de8a0..51d9423b08a6 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c @@ -211,7 +211,7 @@ static int vcap_test_port_info(struct net_device *ndev, return 0; } -static struct vcap_operations test_callbacks = { +static const struct vcap_operations test_callbacks = { .validate_keyset = test_val_keyset, .add_default_fields = test_add_def_fields, .cache_erase = test_cache_erase, diff --git a/drivers/net/ethernet/microsoft/Kconfig b/drivers/net/ethernet/microsoft/Kconfig index 286f0d5697a1..901fbffbf718 100644 --- a/drivers/net/ethernet/microsoft/Kconfig +++ b/drivers/net/ethernet/microsoft/Kconfig @@ -18,7 +18,7 @@ if NET_VENDOR_MICROSOFT config MICROSOFT_MANA tristate "Microsoft Azure Network Adapter (MANA) support" depends on PCI_MSI - depends on X86_64 || (ARM64 && !CPU_BIG_ENDIAN && ARM64_4K_PAGES) + depends on X86_64 || (ARM64 && !CPU_BIG_ENDIAN) depends on PCI_HYPERV select AUXILIARY_BUS select PAGE_POOL diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 1332db9a08eb..e1d70d21e207 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -182,7 +182,7 @@ int mana_gd_alloc_memory(struct gdma_context *gc, unsigned int length, dma_addr_t dma_handle; void *buf; - if (length < PAGE_SIZE || !is_power_of_2(length)) + if (length < MANA_PAGE_SIZE || !is_power_of_2(length)) return -EINVAL; gmi->dev = gc->dev; @@ -717,7 +717,7 @@ EXPORT_SYMBOL_NS(mana_gd_destroy_dma_region, NET_MANA); static int mana_gd_create_dma_region(struct gdma_dev *gd, struct gdma_mem_info *gmi) { - unsigned int num_page = gmi->length / PAGE_SIZE; + unsigned int num_page = gmi->length / MANA_PAGE_SIZE; struct gdma_create_dma_region_req *req = NULL; struct gdma_create_dma_region_resp resp = {}; struct gdma_context *gc = gd->gdma_context; @@ -727,10 +727,10 @@ static int mana_gd_create_dma_region(struct gdma_dev *gd, int err; int i; - if (length < PAGE_SIZE || !is_power_of_2(length)) + if (length < MANA_PAGE_SIZE || !is_power_of_2(length)) return -EINVAL; - if (offset_in_page(gmi->virt_addr) != 0) + if (!MANA_PAGE_ALIGNED(gmi->virt_addr)) return -EINVAL; hwc = gc->hwc.driver_data; @@ -751,7 +751,7 @@ static int mana_gd_create_dma_region(struct gdma_dev *gd, req->page_addr_list_len = num_page; for (i = 0; i < num_page; i++) - req->page_addr_list[i] = gmi->dma_handle + i * PAGE_SIZE; + req->page_addr_list[i] = gmi->dma_handle + i * MANA_PAGE_SIZE; err = mana_gd_send_request(gc, req_msg_size, req, sizeof(resp), &resp); if (err) diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index bbc4f9e16c98..cafded2f9382 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -362,12 +362,12 @@ static int mana_hwc_create_cq(struct hw_channel_context *hwc, u16 q_depth, int err; eq_size = roundup_pow_of_two(GDMA_EQE_SIZE * q_depth); - if (eq_size < MINIMUM_SUPPORTED_PAGE_SIZE) - eq_size = MINIMUM_SUPPORTED_PAGE_SIZE; + if (eq_size < MANA_MIN_QSIZE) + eq_size = MANA_MIN_QSIZE; cq_size = roundup_pow_of_two(GDMA_CQE_SIZE * q_depth); - if (cq_size < MINIMUM_SUPPORTED_PAGE_SIZE) - cq_size = MINIMUM_SUPPORTED_PAGE_SIZE; + if (cq_size < MANA_MIN_QSIZE) + cq_size = MANA_MIN_QSIZE; hwc_cq = kzalloc(sizeof(*hwc_cq), GFP_KERNEL); if (!hwc_cq) @@ -429,7 +429,7 @@ static int mana_hwc_alloc_dma_buf(struct hw_channel_context *hwc, u16 q_depth, dma_buf->num_reqs = q_depth; - buf_size = PAGE_ALIGN(q_depth * max_msg_size); + buf_size = MANA_PAGE_ALIGN(q_depth * max_msg_size); gmi = &dma_buf->mem_info; err = mana_gd_alloc_memory(gc, buf_size, gmi); @@ -497,8 +497,8 @@ static int mana_hwc_create_wq(struct hw_channel_context *hwc, else queue_size = roundup_pow_of_two(GDMA_MAX_SQE_SIZE * q_depth); - if (queue_size < MINIMUM_SUPPORTED_PAGE_SIZE) - queue_size = MINIMUM_SUPPORTED_PAGE_SIZE; + if (queue_size < MANA_MIN_QSIZE) + queue_size = MANA_MIN_QSIZE; hwc_wq = kzalloc(sizeof(*hwc_wq), GFP_KERNEL); if (!hwc_wq) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index d087cf954f75..91f10910ea44 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -481,7 +481,7 @@ static int mana_get_tx_queue(struct net_device *ndev, struct sk_buff *skb, struct sock *sk = skb->sk; int txq; - txq = apc->indir_table[hash & MANA_INDIRECT_TABLE_MASK]; + txq = apc->indir_table[hash & (apc->indir_table_sz - 1)]; if (txq != old_q && sk && sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache)) @@ -721,6 +721,13 @@ static void mana_cleanup_port_context(struct mana_port_context *apc) apc->rxqs = NULL; } +static void mana_cleanup_indir_table(struct mana_port_context *apc) +{ + apc->indir_table_sz = 0; + kfree(apc->indir_table); + kfree(apc->rxobj_table); +} + static int mana_init_port_context(struct mana_port_context *apc) { apc->rxqs = kcalloc(apc->num_queues, sizeof(struct mana_rxq *), @@ -962,7 +969,16 @@ static int mana_query_vport_cfg(struct mana_port_context *apc, u32 vport_index, *max_sq = resp.max_num_sq; *max_rq = resp.max_num_rq; - *num_indir_entry = resp.num_indirection_ent; + if (resp.num_indirection_ent > 0 && + resp.num_indirection_ent <= MANA_INDIRECT_TABLE_MAX_SIZE && + is_power_of_2(resp.num_indirection_ent)) { + *num_indir_entry = resp.num_indirection_ent; + } else { + netdev_warn(apc->ndev, + "Setting indirection table size to default %d for vPort %d\n", + MANA_INDIRECT_TABLE_DEF_SIZE, apc->port_idx); + *num_indir_entry = MANA_INDIRECT_TABLE_DEF_SIZE; + } apc->port_handle = resp.vport; ether_addr_copy(apc->mac_addr, resp.mac_addr); @@ -1054,14 +1070,13 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc, bool update_default_rxobj, bool update_key, bool update_tab) { - u16 num_entries = MANA_INDIRECT_TABLE_SIZE; struct mana_cfg_rx_steer_req_v2 *req; struct mana_cfg_rx_steer_resp resp = {}; struct net_device *ndev = apc->ndev; u32 req_buf_size; int err; - req_buf_size = struct_size(req, indir_tab, num_entries); + req_buf_size = struct_size(req, indir_tab, apc->indir_table_sz); req = kzalloc(req_buf_size, GFP_KERNEL); if (!req) return -ENOMEM; @@ -1072,7 +1087,7 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc, req->hdr.req.msg_version = GDMA_MESSAGE_V2; req->vport = apc->port_handle; - req->num_indir_entries = num_entries; + req->num_indir_entries = apc->indir_table_sz; req->indir_tab_offset = offsetof(struct mana_cfg_rx_steer_req_v2, indir_tab); req->rx_enable = rx; @@ -1111,7 +1126,7 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc, } netdev_info(ndev, "Configured steering vPort %llu entries %u\n", - apc->port_handle, num_entries); + apc->port_handle, apc->indir_table_sz); out: kfree(req); return err; @@ -1889,10 +1904,10 @@ static int mana_create_txq(struct mana_port_context *apc, * to prevent overflow. */ txq_size = MAX_SEND_BUFFERS_PER_QUEUE * 32; - BUILD_BUG_ON(!PAGE_ALIGNED(txq_size)); + BUILD_BUG_ON(!MANA_PAGE_ALIGNED(txq_size)); cq_size = MAX_SEND_BUFFERS_PER_QUEUE * COMP_ENTRY_SIZE; - cq_size = PAGE_ALIGN(cq_size); + cq_size = MANA_PAGE_ALIGN(cq_size); gc = gd->gdma_context; @@ -2189,8 +2204,8 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, if (err) goto out; - rq_size = PAGE_ALIGN(rq_size); - cq_size = PAGE_ALIGN(cq_size); + rq_size = MANA_PAGE_ALIGN(rq_size); + cq_size = MANA_PAGE_ALIGN(cq_size); /* Create RQ */ memset(&spec, 0, sizeof(spec)); @@ -2344,11 +2359,33 @@ static int mana_create_vport(struct mana_port_context *apc, return mana_create_txq(apc, net); } +static int mana_rss_table_alloc(struct mana_port_context *apc) +{ + if (!apc->indir_table_sz) { + netdev_err(apc->ndev, + "Indirection table size not set for vPort %d\n", + apc->port_idx); + return -EINVAL; + } + + apc->indir_table = kcalloc(apc->indir_table_sz, sizeof(u32), GFP_KERNEL); + if (!apc->indir_table) + return -ENOMEM; + + apc->rxobj_table = kcalloc(apc->indir_table_sz, sizeof(mana_handle_t), GFP_KERNEL); + if (!apc->rxobj_table) { + kfree(apc->indir_table); + return -ENOMEM; + } + + return 0; +} + static void mana_rss_table_init(struct mana_port_context *apc) { int i; - for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++) + for (i = 0; i < apc->indir_table_sz; i++) apc->indir_table[i] = ethtool_rxfh_indir_default(i, apc->num_queues); } @@ -2361,7 +2398,7 @@ int mana_config_rss(struct mana_port_context *apc, enum TRI_STATE rx, int i; if (update_tab) { - for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++) { + for (i = 0; i < apc->indir_table_sz; i++) { queue_idx = apc->indir_table[i]; apc->rxobj_table[i] = apc->rxqs[queue_idx]->rxobj; } @@ -2466,7 +2503,6 @@ static int mana_init_port(struct net_device *ndev) struct mana_port_context *apc = netdev_priv(ndev); u32 max_txq, max_rxq, max_queues; int port_idx = apc->port_idx; - u32 num_indirect_entries; int err; err = mana_init_port_context(apc); @@ -2474,7 +2510,7 @@ static int mana_init_port(struct net_device *ndev) return err; err = mana_query_vport_cfg(apc, port_idx, &max_txq, &max_rxq, - &num_indirect_entries); + &apc->indir_table_sz); if (err) { netdev_err(ndev, "Failed to query info for vPort %d\n", port_idx); @@ -2493,8 +2529,7 @@ static int mana_init_port(struct net_device *ndev) return 0; reset_apc: - kfree(apc->rxqs); - apc->rxqs = NULL; + mana_cleanup_port_context(apc); return err; } @@ -2723,6 +2758,10 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, if (err) goto free_net; + err = mana_rss_table_alloc(apc); + if (err) + goto reset_apc; + netdev_lockdep_set_classes(ndev); ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; @@ -2739,14 +2778,15 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, err = register_netdev(ndev); if (err) { netdev_err(ndev, "Unable to register netdev.\n"); - goto reset_apc; + goto free_indir; } return 0; +free_indir: + mana_cleanup_indir_table(apc); reset_apc: - kfree(apc->rxqs); - apc->rxqs = NULL; + mana_cleanup_port_context(apc); free_net: *ndev_storage = NULL; netdev_err(ndev, "Failed to probe vPort %d: %d\n", port_idx, err); @@ -2798,6 +2838,8 @@ static int add_adev(struct gdma_dev *gd) if (ret) goto init_fail; + /* madev is owned by the auxiliary device */ + madev = NULL; ret = auxiliary_device_add(adev); if (ret) goto add_fail; @@ -2872,16 +2914,30 @@ int mana_probe(struct gdma_dev *gd, bool resuming) if (!resuming) { for (i = 0; i < ac->num_ports; i++) { err = mana_probe_port(ac, i, &ac->ports[i]); - if (err) + /* we log the port for which the probe failed and stop + * probes for subsequent ports. + * Note that we keep running ports, for which the probes + * were successful, unless add_adev fails too + */ + if (err) { + dev_err(dev, "Probe Failed for port %d\n", i); break; + } } } else { for (i = 0; i < ac->num_ports; i++) { rtnl_lock(); err = mana_attach(ac->ports[i]); rtnl_unlock(); - if (err) + /* we log the port for which the attach failed and stop + * attach for subsequent ports + * Note that we keep running ports, for which the attach + * were successful, unless add_adev fails too + */ + if (err) { + dev_err(dev, "Attach Failed for port %d\n", i); break; + } } } @@ -2897,6 +2953,7 @@ void mana_remove(struct gdma_dev *gd, bool suspending) { struct gdma_context *gc = gd->gdma_context; struct mana_context *ac = gd->driver_data; + struct mana_port_context *apc; struct device *dev = gc->dev; struct net_device *ndev; int err; @@ -2908,6 +2965,7 @@ void mana_remove(struct gdma_dev *gd, bool suspending) for (i = 0; i < ac->num_ports; i++) { ndev = ac->ports[i]; + apc = netdev_priv(ndev); if (!ndev) { if (i == 0) dev_err(dev, "No net device to remove\n"); @@ -2931,6 +2989,7 @@ void mana_remove(struct gdma_dev *gd, bool suspending) } unregister_netdevice(ndev); + mana_cleanup_indir_table(apc); rtnl_unlock(); diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index ab2413d71f6c..146d5db1792f 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -245,7 +245,9 @@ static u32 mana_get_rxfh_key_size(struct net_device *ndev) static u32 mana_rss_indir_size(struct net_device *ndev) { - return MANA_INDIRECT_TABLE_SIZE; + struct mana_port_context *apc = netdev_priv(ndev); + + return apc->indir_table_sz; } static int mana_get_rxfh(struct net_device *ndev, @@ -257,7 +259,7 @@ static int mana_get_rxfh(struct net_device *ndev, rxfh->hfunc = ETH_RSS_HASH_TOP; /* Toeplitz */ if (rxfh->indir) { - for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++) + for (i = 0; i < apc->indir_table_sz; i++) rxfh->indir[i] = apc->indir_table[i]; } @@ -273,8 +275,8 @@ static int mana_set_rxfh(struct net_device *ndev, { struct mana_port_context *apc = netdev_priv(ndev); bool update_hash = false, update_table = false; - u32 save_table[MANA_INDIRECT_TABLE_SIZE]; u8 save_key[MANA_HASH_KEY_SIZE]; + u32 *save_table; int i, err; if (!apc->port_is_up) @@ -284,13 +286,19 @@ static int mana_set_rxfh(struct net_device *ndev, rxfh->hfunc != ETH_RSS_HASH_TOP) return -EOPNOTSUPP; + save_table = kcalloc(apc->indir_table_sz, sizeof(u32), GFP_KERNEL); + if (!save_table) + return -ENOMEM; + if (rxfh->indir) { - for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++) - if (rxfh->indir[i] >= apc->num_queues) - return -EINVAL; + for (i = 0; i < apc->indir_table_sz; i++) + if (rxfh->indir[i] >= apc->num_queues) { + err = -EINVAL; + goto cleanup; + } update_table = true; - for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++) { + for (i = 0; i < apc->indir_table_sz; i++) { save_table[i] = apc->indir_table[i]; apc->indir_table[i] = rxfh->indir[i]; } @@ -306,7 +314,7 @@ static int mana_set_rxfh(struct net_device *ndev, if (err) { /* recover to original values */ if (update_table) { - for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++) + for (i = 0; i < apc->indir_table_sz; i++) apc->indir_table[i] = save_table[i]; } @@ -316,6 +324,9 @@ static int mana_set_rxfh(struct net_device *ndev, mana_config_rss(apc, TRI_STATE_TRUE, update_hash, update_table); } +cleanup: + kfree(save_table); + return err; } diff --git a/drivers/net/ethernet/microsoft/mana/shm_channel.c b/drivers/net/ethernet/microsoft/mana/shm_channel.c index 5553af9c8085..0f1679ebad96 100644 --- a/drivers/net/ethernet/microsoft/mana/shm_channel.c +++ b/drivers/net/ethernet/microsoft/mana/shm_channel.c @@ -6,6 +6,7 @@ #include <linux/io.h> #include <linux/mm.h> +#include <net/mana/gdma.h> #include <net/mana/shm_channel.h> #define PAGE_FRAME_L48_WIDTH_BYTES 6 @@ -155,8 +156,8 @@ int mana_smc_setup_hwc(struct shm_channel *sc, bool reset_vf, u64 eq_addr, return err; } - if (!PAGE_ALIGNED(eq_addr) || !PAGE_ALIGNED(cq_addr) || - !PAGE_ALIGNED(rq_addr) || !PAGE_ALIGNED(sq_addr)) + if (!MANA_PAGE_ALIGNED(eq_addr) || !MANA_PAGE_ALIGNED(cq_addr) || + !MANA_PAGE_ALIGNED(rq_addr) || !MANA_PAGE_ALIGNED(sq_addr)) return -EINVAL; if ((eq_msix_index & VECTOR_MASK) != eq_msix_index) @@ -183,7 +184,7 @@ int mana_smc_setup_hwc(struct shm_channel *sc, bool reset_vf, u64 eq_addr, /* EQ addr: low 48 bits of frame address */ shmem = (u64 *)ptr; - frame_addr = PHYS_PFN(eq_addr); + frame_addr = MANA_PFN(eq_addr); *shmem = frame_addr & PAGE_FRAME_L48_MASK; all_addr_h4bits |= (frame_addr >> PAGE_FRAME_L48_WIDTH_BITS) << (frame_addr_seq++ * PAGE_FRAME_H4_WIDTH_BITS); @@ -191,7 +192,7 @@ int mana_smc_setup_hwc(struct shm_channel *sc, bool reset_vf, u64 eq_addr, /* CQ addr: low 48 bits of frame address */ shmem = (u64 *)ptr; - frame_addr = PHYS_PFN(cq_addr); + frame_addr = MANA_PFN(cq_addr); *shmem = frame_addr & PAGE_FRAME_L48_MASK; all_addr_h4bits |= (frame_addr >> PAGE_FRAME_L48_WIDTH_BITS) << (frame_addr_seq++ * PAGE_FRAME_H4_WIDTH_BITS); @@ -199,7 +200,7 @@ int mana_smc_setup_hwc(struct shm_channel *sc, bool reset_vf, u64 eq_addr, /* RQ addr: low 48 bits of frame address */ shmem = (u64 *)ptr; - frame_addr = PHYS_PFN(rq_addr); + frame_addr = MANA_PFN(rq_addr); *shmem = frame_addr & PAGE_FRAME_L48_MASK; all_addr_h4bits |= (frame_addr >> PAGE_FRAME_L48_WIDTH_BITS) << (frame_addr_seq++ * PAGE_FRAME_H4_WIDTH_BITS); @@ -207,7 +208,7 @@ int mana_smc_setup_hwc(struct shm_channel *sc, bool reset_vf, u64 eq_addr, /* SQ addr: low 48 bits of frame address */ shmem = (u64 *)ptr; - frame_addr = PHYS_PFN(sq_addr); + frame_addr = MANA_PFN(sq_addr); *shmem = frame_addr & PAGE_FRAME_L48_MASK; all_addr_h4bits |= (frame_addr >> PAGE_FRAME_L48_WIDTH_BITS) << (frame_addr_seq++ * PAGE_FRAME_H4_WIDTH_BITS); diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 8e0a890381b6..46ffc2c20893 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -321,6 +321,10 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, flow_rule_match_enc_control(rule, &enc_ctl); + if (flow_rule_has_enc_control_flags(enc_ctl.mask->flags, + extack)) + return -EOPNOTSUPP; + if (enc_ctl.mask->addr_type != 0xffff) { NL_SET_ERR_MSG_MOD(extack, "unsupported offload: wildcarded protocols on tunnels are not supported"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/pensando/ionic/ionic.h b/drivers/net/ethernet/pensando/ionic/ionic.h index 2ccc2c2a06e3..1c61390677f7 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic.h +++ b/drivers/net/ethernet/pensando/ionic/ionic.h @@ -18,6 +18,8 @@ struct ionic_lif; #define PCI_DEVICE_ID_PENSANDO_IONIC_ETH_PF 0x1002 #define PCI_DEVICE_ID_PENSANDO_IONIC_ETH_VF 0x1003 +#define IONIC_ASIC_TYPE_ELBA 2 + #define DEVCMD_TIMEOUT 5 #define IONIC_ADMINQ_TIME_SLICE msecs_to_jiffies(100) @@ -47,6 +49,7 @@ struct ionic { struct ionic_dev_bar bars[IONIC_BARS_MAX]; unsigned int num_bars; struct ionic_identity ident; + struct workqueue_struct *wq; struct ionic_lif *lif; unsigned int nnqs_per_lif; unsigned int neqs_per_lif; @@ -54,6 +57,8 @@ struct ionic { unsigned int nrxqs_per_lif; unsigned int nintrs; DECLARE_BITMAP(intrs, IONIC_INTR_CTRL_REGS_MAX); + cpumask_var_t *affinity_masks; + struct delayed_work doorbell_check_dwork; struct work_struct nb_work; struct notifier_block nb; struct rw_semaphore vf_op_lock; /* lock for VF operations */ @@ -93,4 +98,6 @@ int ionic_port_identify(struct ionic *ionic); int ionic_port_init(struct ionic *ionic); int ionic_port_reset(struct ionic *ionic); +bool ionic_doorbell_wa(struct ionic *ionic); + #endif /* _IONIC_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c index a7146d50f814..b93791d6b593 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c @@ -377,6 +377,7 @@ static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) mod_timer(&ionic->watchdog_timer, round_jiffies(jiffies + ionic->watchdog_period)); + ionic_queue_doorbell_check(ionic, IONIC_NAPI_DEADLINE); return 0; @@ -411,6 +412,8 @@ static void ionic_remove(struct pci_dev *pdev) if (test_and_clear_bit(IONIC_LIF_F_FW_RESET, ionic->lif->state)) set_bit(IONIC_LIF_F_FW_STOPPING, ionic->lif->state); + if (ionic->lif->doorbell_wa) + cancel_delayed_work_sync(&ionic->doorbell_check_dwork); ionic_lif_unregister(ionic->lif); ionic_devlink_unregister(ionic); ionic_lif_deinit(ionic->lif); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index 874499337132..9e42d599840d 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -43,11 +43,99 @@ static void ionic_watchdog_cb(struct timer_list *t) work->type = IONIC_DW_TYPE_RX_MODE; netdev_dbg(lif->netdev, "deferred: rx_mode\n"); - ionic_lif_deferred_enqueue(&lif->deferred, work); + ionic_lif_deferred_enqueue(lif, work); } } -static void ionic_watchdog_init(struct ionic *ionic) +static void ionic_napi_schedule_do_softirq(struct napi_struct *napi) +{ + local_bh_disable(); + napi_schedule(napi); + local_bh_enable(); +} + +void ionic_doorbell_napi_work(struct work_struct *work) +{ + struct ionic_qcq *qcq = container_of(work, struct ionic_qcq, + doorbell_napi_work); + unsigned long now, then, dif; + + now = READ_ONCE(jiffies); + then = qcq->q.dbell_jiffies; + dif = now - then; + + if (dif > qcq->q.dbell_deadline) + ionic_napi_schedule_do_softirq(&qcq->napi); +} + +static int ionic_get_preferred_cpu(struct ionic *ionic, + struct ionic_intr_info *intr) +{ + int cpu; + + cpu = cpumask_first_and(*intr->affinity_mask, cpu_online_mask); + if (cpu >= nr_cpu_ids) + cpu = cpumask_local_spread(0, dev_to_node(ionic->dev)); + + return cpu; +} + +static void ionic_queue_dbell_napi_work(struct ionic *ionic, + struct ionic_qcq *qcq) +{ + int cpu; + + if (!(qcq->flags & IONIC_QCQ_F_INTR)) + return; + + cpu = ionic_get_preferred_cpu(ionic, &qcq->intr); + queue_work_on(cpu, ionic->wq, &qcq->doorbell_napi_work); +} + +static void ionic_doorbell_check_dwork(struct work_struct *work) +{ + struct ionic *ionic = container_of(work, struct ionic, + doorbell_check_dwork.work); + struct ionic_lif *lif = ionic->lif; + + mutex_lock(&lif->queue_lock); + + if (test_bit(IONIC_LIF_F_FW_STOPPING, lif->state) || + test_bit(IONIC_LIF_F_FW_RESET, lif->state)) { + mutex_unlock(&lif->queue_lock); + return; + } + + ionic_napi_schedule_do_softirq(&lif->adminqcq->napi); + + if (test_bit(IONIC_LIF_F_UP, lif->state)) { + int i; + + for (i = 0; i < lif->nxqs; i++) { + ionic_queue_dbell_napi_work(ionic, lif->txqcqs[i]); + ionic_queue_dbell_napi_work(ionic, lif->rxqcqs[i]); + } + + if (lif->hwstamp_txq && + lif->hwstamp_txq->flags & IONIC_QCQ_F_INTR) + ionic_napi_schedule_do_softirq(&lif->hwstamp_txq->napi); + if (lif->hwstamp_rxq && + lif->hwstamp_rxq->flags & IONIC_QCQ_F_INTR) + ionic_napi_schedule_do_softirq(&lif->hwstamp_rxq->napi); + } + mutex_unlock(&lif->queue_lock); + + ionic_queue_doorbell_check(ionic, IONIC_NAPI_DEADLINE); +} + +bool ionic_doorbell_wa(struct ionic *ionic) +{ + u8 asic_type = ionic->idev.dev_info.asic_type; + + return !asic_type || asic_type == IONIC_ASIC_TYPE_ELBA; +} + +static int ionic_watchdog_init(struct ionic *ionic) { struct ionic_dev *idev = &ionic->idev; @@ -63,6 +151,31 @@ static void ionic_watchdog_init(struct ionic *ionic) idev->fw_status_ready = true; idev->fw_generation = IONIC_FW_STS_F_GENERATION & ioread8(&idev->dev_info_regs->fw_status); + + ionic->wq = alloc_workqueue("%s-wq", WQ_UNBOUND, 0, + dev_name(ionic->dev)); + if (!ionic->wq) { + dev_err(ionic->dev, "alloc_workqueue failed"); + return -ENOMEM; + } + + if (ionic_doorbell_wa(ionic)) + INIT_DELAYED_WORK(&ionic->doorbell_check_dwork, + ionic_doorbell_check_dwork); + + return 0; +} + +void ionic_queue_doorbell_check(struct ionic *ionic, int delay) +{ + int cpu; + + if (!ionic->lif->doorbell_wa) + return; + + cpu = ionic_get_preferred_cpu(ionic, &ionic->lif->adminqcq->intr); + queue_delayed_work_on(cpu, ionic->wq, &ionic->doorbell_check_dwork, + delay); } void ionic_init_devinfo(struct ionic *ionic) @@ -94,6 +207,7 @@ int ionic_dev_setup(struct ionic *ionic) struct device *dev = ionic->dev; int size; u32 sig; + int err; /* BAR0: dev_cmd and interrupts */ if (num_bars < 1) { @@ -129,7 +243,9 @@ int ionic_dev_setup(struct ionic *ionic) return -EFAULT; } - ionic_watchdog_init(ionic); + err = ionic_watchdog_init(ionic); + if (err) + return err; idev->db_pages = bar->vaddr; idev->phy_db_pages = bar->bus_addr; @@ -161,6 +277,7 @@ void ionic_dev_teardown(struct ionic *ionic) idev->phy_cmb_pages = 0; idev->cmb_npages = 0; + destroy_workqueue(ionic->wq); mutex_destroy(&idev->cmb_inuse_lock); } @@ -273,7 +390,7 @@ do_check_time: if (work) { work->type = IONIC_DW_TYPE_LIF_RESET; work->fw_status = fw_status_ready; - ionic_lif_deferred_enqueue(&lif->deferred, work); + ionic_lif_deferred_enqueue(lif, work); } } } @@ -703,10 +820,6 @@ void ionic_q_post(struct ionic_queue *q, bool ring_doorbell) 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); } } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h index f30eee4a5a80..c647033f3ad2 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h @@ -28,7 +28,7 @@ #define IONIC_DEV_INFO_REG_COUNT 32 #define IONIC_DEV_CMD_REG_COUNT 32 -#define IONIC_NAPI_DEADLINE (HZ / 200) /* 5ms */ +#define IONIC_NAPI_DEADLINE (HZ) /* 1 sec */ #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 */ @@ -280,9 +280,9 @@ struct ionic_intr_info { u64 rearm_count; unsigned int index; unsigned int vector; - unsigned int cpu; u32 dim_coal_hw; - cpumask_t affinity_mask; + cpumask_var_t *affinity_mask; + struct irq_affinity_notify aff_notify; }; struct ionic_cq { @@ -375,7 +375,9 @@ typedef void (*ionic_cq_done_cb)(void *done_arg); unsigned int ionic_cq_service(struct ionic_cq *cq, unsigned int work_to_do, ionic_cq_cb cb, ionic_cq_done_cb done_cb, void *done_arg); -unsigned int ionic_tx_cq_service(struct ionic_cq *cq, unsigned int work_to_do); +unsigned int ionic_tx_cq_service(struct ionic_cq *cq, + unsigned int work_to_do, + bool in_napi); int ionic_q_init(struct ionic_lif *lif, struct ionic_dev *idev, struct ionic_queue *q, unsigned int index, const char *name, @@ -386,6 +388,8 @@ bool ionic_q_is_posted(struct ionic_queue *q, unsigned int pos); int ionic_heartbeat_check(struct ionic *ionic); bool ionic_is_fw_running(struct ionic_dev *idev); +void ionic_doorbell_napi_work(struct work_struct *work); +void ionic_queue_doorbell_check(struct ionic *ionic, int delay); bool ionic_adminq_poke_doorbell(struct ionic_queue *q); bool ionic_txq_poke_doorbell(struct ionic_queue *q); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c index 91183965a6b7..185a03514ae3 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c @@ -11,6 +11,8 @@ #include "ionic_ethtool.h" #include "ionic_stats.h" +#define IONIC_MAX_RX_COPYBREAK min(U16_MAX, IONIC_MAX_BUF_LEN) + static void ionic_get_stats_strings(struct ionic_lif *lif, u8 *buf) { u32 i; @@ -872,10 +874,17 @@ static int ionic_set_tunable(struct net_device *dev, const void *data) { struct ionic_lif *lif = netdev_priv(dev); + u32 rx_copybreak; switch (tuna->id) { case ETHTOOL_RX_COPYBREAK: - lif->rx_copybreak = *(u32 *)data; + rx_copybreak = *(u32 *)data; + if (rx_copybreak > IONIC_MAX_RX_COPYBREAK) { + netdev_err(dev, "Max supported rx_copybreak size: %u\n", + IONIC_MAX_RX_COPYBREAK); + return -EINVAL; + } + lif->rx_copybreak = (u16)rx_copybreak; break; default: return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 23e1f6638b38..aa0cc31dfe6e 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -126,13 +126,13 @@ static void ionic_lif_deferred_work(struct work_struct *work) } while (true); } -void ionic_lif_deferred_enqueue(struct ionic_deferred *def, +void ionic_lif_deferred_enqueue(struct ionic_lif *lif, struct ionic_deferred_work *work) { - spin_lock_bh(&def->lock); - list_add_tail(&work->list, &def->list); - spin_unlock_bh(&def->lock); - schedule_work(&def->work); + spin_lock_bh(&lif->deferred.lock); + list_add_tail(&work->list, &lif->deferred.list); + spin_unlock_bh(&lif->deferred.lock); + queue_work(lif->ionic->wq, &lif->deferred.work); } static void ionic_link_status_check(struct ionic_lif *lif) @@ -207,19 +207,12 @@ void ionic_link_status_check_request(struct ionic_lif *lif, bool can_sleep) } work->type = IONIC_DW_TYPE_LINK_STATUS; - ionic_lif_deferred_enqueue(&lif->deferred, work); + ionic_lif_deferred_enqueue(lif, work); } else { ionic_link_status_check(lif); } } -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; @@ -272,6 +265,18 @@ static void ionic_intr_free(struct ionic *ionic, int index) clear_bit(index, ionic->intrs); } +static void ionic_irq_aff_notify(struct irq_affinity_notify *notify, + const cpumask_t *mask) +{ + struct ionic_intr_info *intr = container_of(notify, struct ionic_intr_info, aff_notify); + + cpumask_copy(*intr->affinity_mask, mask); +} + +static void ionic_irq_aff_release(struct kref __always_unused *ref) +{ +} + static int ionic_qcq_enable(struct ionic_qcq *qcq) { struct ionic_queue *q = &qcq->q; @@ -304,12 +309,12 @@ static int ionic_qcq_enable(struct ionic_qcq *qcq) if (ret) return ret; - if (qcq->napi.poll) - napi_enable(&qcq->napi); - if (qcq->flags & IONIC_QCQ_F_INTR) { + napi_enable(&qcq->napi); + irq_set_affinity_notifier(qcq->intr.vector, + &qcq->intr.aff_notify); irq_set_affinity_hint(qcq->intr.vector, - &qcq->intr.affinity_mask); + *qcq->intr.affinity_mask); ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, IONIC_INTR_MASK_CLEAR); } @@ -339,13 +344,15 @@ static int ionic_qcq_disable(struct ionic_lif *lif, struct ionic_qcq *qcq, int f if (qcq->flags & IONIC_QCQ_F_INTR) { struct ionic_dev *idev = &lif->ionic->idev; + if (lif->doorbell_wa) + cancel_work_sync(&qcq->doorbell_napi_work); cancel_work_sync(&qcq->dim.work); ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, IONIC_INTR_MASK_SET); synchronize_irq(qcq->intr.vector); + irq_set_affinity_notifier(qcq->intr.vector, NULL); 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 @@ -480,11 +487,11 @@ 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) { + cpumask_var_t *affinity_mask; int err; if (!(qcq->flags & IONIC_QCQ_F_INTR)) { @@ -516,10 +523,19 @@ static int ionic_alloc_qcq_interrupt(struct ionic_lif *lif, struct ionic_qcq *qc } /* try to get the irq on the local numa node first */ - qcq->intr.cpu = cpumask_local_spread(qcq->intr.index, - dev_to_node(lif->ionic->dev)); - if (qcq->intr.cpu != -1) - cpumask_set_cpu(qcq->intr.cpu, &qcq->intr.affinity_mask); + affinity_mask = &lif->ionic->affinity_masks[qcq->intr.index]; + if (cpumask_empty(*affinity_mask)) { + unsigned int cpu; + + cpu = cpumask_local_spread(qcq->intr.index, + dev_to_node(lif->ionic->dev)); + if (cpu != -1) + cpumask_set_cpu(cpu, *affinity_mask); + } + + qcq->intr.affinity_mask = affinity_mask; + qcq->intr.aff_notify.notify = ionic_irq_aff_notify; + qcq->intr.aff_notify.release = ionic_irq_aff_release; netdev_dbg(lif->netdev, "%s: Interrupt index %d\n", qcq->q.name, qcq->intr.index); return 0; @@ -676,6 +692,8 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, INIT_WORK(&new->dim.work, ionic_dim_work); new->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_CQE; + if (lif->doorbell_wa) + INIT_WORK(&new->doorbell_napi_work, ionic_doorbell_napi_work); *qcq = new; @@ -834,11 +852,8 @@ static int ionic_lif_txq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) q->dbell_deadline = IONIC_TX_DOORBELL_DEADLINE; q->dbell_jiffies = jiffies; - if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) { + 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; @@ -911,9 +926,6 @@ static int ionic_lif_rxq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) 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; @@ -1168,7 +1180,6 @@ 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; @@ -1184,6 +1195,7 @@ static int ionic_adminq_napi(struct napi_struct *napi, int budget) if (lif->adminqcq && lif->adminqcq->flags & IONIC_QCQ_F_INITED) a_work = ionic_cq_service(&lif->adminqcq->cq, budget, ionic_adminq_service, NULL, NULL); + spin_unlock_irqrestore(&lif->adminq_lock, irqflags); if (lif->hwstamp_rxq) @@ -1191,7 +1203,7 @@ static int ionic_adminq_napi(struct napi_struct *napi, int budget) ionic_rx_service, NULL, NULL); if (lif->hwstamp_txq) - tx_work = ionic_tx_cq_service(&lif->hwstamp_txq->cq, budget); + tx_work = ionic_tx_cq_service(&lif->hwstamp_txq->cq, budget, !!budget); work_done = max(max(n_work, a_work), max(rx_work, tx_work)); if (work_done < budget && napi_complete_done(napi, work_done)) { @@ -1205,15 +1217,14 @@ 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); + if (lif->doorbell_wa) { + if (!a_work) + ionic_adminq_poke_doorbell(&lif->adminqcq->q); + if (lif->hwstamp_rxq && !rx_work) + ionic_rxq_poke_doorbell(&lif->hwstamp_rxq->q); + if (lif->hwstamp_txq && !tx_work) + ionic_txq_poke_doorbell(&lif->hwstamp_txq->q); + } return work_done; } @@ -1385,7 +1396,7 @@ static void ionic_ndo_set_rx_mode(struct net_device *netdev) } work->type = IONIC_DW_TYPE_RX_MODE; netdev_dbg(lif->netdev, "deferred: rx_mode\n"); - ionic_lif_deferred_enqueue(&lif->deferred, work); + ionic_lif_deferred_enqueue(lif, work); } static __le64 ionic_netdev_features_to_nic(netdev_features_t features) @@ -3141,6 +3152,44 @@ err_out: return err; } +static int ionic_affinity_masks_alloc(struct ionic *ionic) +{ + cpumask_var_t *affinity_masks; + int nintrs = ionic->nintrs; + int i; + + affinity_masks = kcalloc(nintrs, sizeof(cpumask_var_t), GFP_KERNEL); + if (!affinity_masks) + return -ENOMEM; + + for (i = 0; i < nintrs; i++) { + if (!zalloc_cpumask_var_node(&affinity_masks[i], GFP_KERNEL, + dev_to_node(ionic->dev))) + goto err_out; + } + + ionic->affinity_masks = affinity_masks; + + return 0; + +err_out: + for (--i; i >= 0; i--) + free_cpumask_var(affinity_masks[i]); + kfree(affinity_masks); + + return -ENOMEM; +} + +static void ionic_affinity_masks_free(struct ionic *ionic) +{ + int i; + + for (i = 0; i < ionic->nintrs; i++) + free_cpumask_var(ionic->affinity_masks[i]); + kfree(ionic->affinity_masks); + ionic->affinity_masks = NULL; +} + int ionic_lif_alloc(struct ionic *ionic) { struct device *dev = ionic->dev; @@ -3232,11 +3281,15 @@ int ionic_lif_alloc(struct ionic *ionic) ionic_debugfs_add_lif(lif); + err = ionic_affinity_masks_alloc(ionic); + if (err) + goto err_out_free_lif_info; + /* allocate control queues and txrx queue arrays */ ionic_lif_queue_identify(lif); err = ionic_qcqs_alloc(lif); if (err) - goto err_out_free_lif_info; + goto err_out_free_affinity_masks; /* allocate rss indirection table */ tbl_sz = le16_to_cpu(lif->ionic->ident.lif.eth.rss_ind_tbl_sz); @@ -3258,6 +3311,8 @@ int ionic_lif_alloc(struct ionic *ionic) err_out_free_qcqs: ionic_qcqs_free(lif); +err_out_free_affinity_masks: + ionic_affinity_masks_free(lif->ionic); err_out_free_lif_info: dma_free_coherent(dev, lif->info_sz, lif->info, lif->info_pa); lif->info = NULL; @@ -3358,6 +3413,7 @@ int ionic_restart_lif(struct ionic_lif *lif) clear_bit(IONIC_LIF_F_FW_RESET, lif->state); ionic_link_status_check_request(lif, CAN_SLEEP); netif_device_attach(lif->netdev); + ionic_queue_doorbell_check(ionic, IONIC_NAPI_DEADLINE); return 0; @@ -3431,6 +3487,8 @@ void ionic_lif_free(struct ionic_lif *lif) if (!test_bit(IONIC_LIF_F_FW_RESET, lif->state)) ionic_lif_reset(lif); + ionic_affinity_masks_free(lif->ionic); + /* free lif info */ kfree(lif->identity); dma_free_coherent(dev, lif->info_sz, lif->info, lif->info_pa); @@ -3504,14 +3562,11 @@ static int ionic_lif_adminq_init(struct ionic_lif *lif) 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) { irq_set_affinity_hint(qcq->intr.vector, - &qcq->intr.affinity_mask); + *qcq->intr.affinity_mask); ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, IONIC_INTR_MASK_CLEAR); } @@ -3698,6 +3753,7 @@ int ionic_lif_init(struct ionic_lif *lif) goto err_out_notifyq_deinit; lif->rx_copybreak = IONIC_RX_COPYBREAK_DEFAULT; + lif->doorbell_wa = ionic_doorbell_wa(lif->ionic); set_bit(IONIC_LIF_F_INITED, lif->state); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index 08f4266fe2aa..3e1005293c4a 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -84,12 +84,11 @@ struct ionic_qcq { u32 cmb_pgid; u32 cmb_order; struct dim dim; - struct timer_list napi_deadline; struct ionic_queue q; struct ionic_cq cq; struct napi_struct napi; - struct ionic_qcq *napi_qcq; struct ionic_intr_info intr; + struct work_struct doorbell_napi_work; struct dentry *dentry; }; @@ -207,11 +206,12 @@ struct ionic_lif { unsigned int nxqs; unsigned int ntxq_descs; unsigned int nrxq_descs; - u32 rx_copybreak; u64 rxq_features; - u16 rx_mode; u64 hw_features; + u16 rx_copybreak; + u16 rx_mode; bool registered; + bool doorbell_wa; u16 lif_type; unsigned int link_down_count; unsigned int nmcast; @@ -226,11 +226,11 @@ struct ionic_lif { u32 info_sz; struct ionic_qtype_info qtype_info[IONIC_QTYPE_MAX]; - u16 rss_types; u8 rss_hash_key[IONIC_RSS_HASH_KEY_SIZE]; u8 *rss_ind_tbl; dma_addr_t rss_ind_tbl_pa; u32 rss_ind_tbl_sz; + u16 rss_types; struct ionic_rx_filters rx_filters; u32 rx_coalesce_usecs; /* what the user asked for */ @@ -333,7 +333,7 @@ static inline bool ionic_txq_hwstamp_enabled(struct ionic_queue *q) void ionic_link_status_check_request(struct ionic_lif *lif, bool can_sleep); void ionic_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *ns); -void ionic_lif_deferred_enqueue(struct ionic_deferred *def, +void ionic_lif_deferred_enqueue(struct ionic_lif *lif, struct ionic_deferred_work *work); int ionic_lif_alloc(struct ionic *ionic); int ionic_lif_init(struct ionic_lif *lif); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index c1259324b0be..0f817c3f92d8 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -287,7 +287,7 @@ bool ionic_notifyq_service(struct ionic_cq *cq) clear_bit(IONIC_LIF_F_FW_STOPPING, lif->state); } else { work->type = IONIC_DW_TYPE_LIF_RESET; - ionic_lif_deferred_enqueue(&lif->deferred, work); + ionic_lif_deferred_enqueue(lif, work); } } break; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 9e6dee2fc1d4..fc79baad4561 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -23,7 +23,8 @@ static void ionic_tx_desc_unmap_bufs(struct ionic_queue *q, static void ionic_tx_clean(struct ionic_queue *q, struct ionic_tx_desc_info *desc_info, - struct ionic_txq_comp *comp); + struct ionic_txq_comp *comp, + bool in_napi); static inline void ionic_txq_post(struct ionic_queue *q, bool ring_dbell) { @@ -480,6 +481,20 @@ int ionic_xdp_xmit(struct net_device *netdev, int n, return nxmit; } +static void ionic_xdp_rx_put_bufs(struct ionic_queue *q, + struct ionic_buf_info *buf_info, + int nbufs) +{ + int i; + + for (i = 0; i < nbufs; i++) { + dma_unmap_page(q->dev, buf_info->dma_addr, + IONIC_PAGE_SIZE, DMA_FROM_DEVICE); + buf_info->page = NULL; + buf_info++; + } +} + static bool ionic_run_xdp(struct ionic_rx_stats *stats, struct net_device *netdev, struct bpf_prog *xdp_prog, @@ -493,6 +508,7 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats, struct netdev_queue *nq; struct xdp_frame *xdpf; int remain_len; + int nbufs = 1; int frag_len; int err = 0; @@ -542,6 +558,7 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats, if (page_is_pfmemalloc(bi->page)) xdp_buff_set_frag_pfmemalloc(&xdp_buf); } while (remain_len > 0); + nbufs += sinfo->nr_frags; } xdp_action = bpf_prog_run_xdp(xdp_prog, &xdp_buf); @@ -574,9 +591,6 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats, goto out_xdp_abort; } - dma_unmap_page(rxq->dev, buf_info->dma_addr, - IONIC_PAGE_SIZE, DMA_FROM_DEVICE); - err = ionic_xdp_post_frame(txq, xdpf, XDP_TX, buf_info->page, buf_info->page_offset, @@ -586,23 +600,19 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats, netdev_dbg(netdev, "tx ionic_xdp_post_frame err %d\n", err); goto out_xdp_abort; } - buf_info->page = NULL; + ionic_xdp_rx_put_bufs(rxq, buf_info, nbufs); stats->xdp_tx++; /* the Tx completion will free the buffers */ break; case XDP_REDIRECT: - /* unmap the pages before handing them to a different device */ - dma_unmap_page(rxq->dev, buf_info->dma_addr, - IONIC_PAGE_SIZE, DMA_FROM_DEVICE); - err = xdp_do_redirect(netdev, &xdp_buf, xdp_prog); if (unlikely(err)) { netdev_dbg(netdev, "xdp_do_redirect err %d\n", err); goto out_xdp_abort; } - buf_info->page = NULL; + ionic_xdp_rx_put_bufs(rxq, buf_info, nbufs); rxq->xdp_flush = true; stats->xdp_redirect++; break; @@ -868,9 +878,6 @@ void ionic_rx_fill(struct ionic_queue *q) 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) @@ -935,7 +942,7 @@ int ionic_tx_napi(struct napi_struct *napi, int budget) u32 work_done = 0; u32 flags = 0; - work_done = ionic_tx_cq_service(cq, budget); + work_done = ionic_tx_cq_service(cq, budget, !!budget); if (unlikely(!budget)) return budget; @@ -953,8 +960,8 @@ 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); + if (!work_done && cq->bound_q->lif->doorbell_wa) + ionic_txq_poke_doorbell(&qcq->q); return work_done; } @@ -996,8 +1003,8 @@ 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); + if (!work_done && cq->bound_q->lif->doorbell_wa) + ionic_rxq_poke_doorbell(&qcq->q); return work_done; } @@ -1010,7 +1017,6 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) struct ionic_qcq *txqcq; struct ionic_lif *lif; struct ionic_cq *txcq; - bool resched = false; u32 rx_work_done = 0; u32 tx_work_done = 0; u32 flags = 0; @@ -1019,7 +1025,7 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) txqcq = lif->txqcqs[qi]; txcq = &lif->txqcqs[qi]->cq; - tx_work_done = ionic_tx_cq_service(txcq, IONIC_TX_BUDGET_DEFAULT); + tx_work_done = ionic_tx_cq_service(txcq, IONIC_TX_BUDGET_DEFAULT, !!budget); if (unlikely(!budget)) return budget; @@ -1042,12 +1048,12 @@ 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); + if (lif->doorbell_wa) { + if (!rx_work_done) + ionic_rxq_poke_doorbell(&rxqcq->q); + if (!tx_work_done) + ionic_txq_poke_doorbell(&txqcq->q); + } return rx_work_done; } @@ -1152,7 +1158,8 @@ static void ionic_tx_desc_unmap_bufs(struct ionic_queue *q, static void ionic_tx_clean(struct ionic_queue *q, struct ionic_tx_desc_info *desc_info, - struct ionic_txq_comp *comp) + struct ionic_txq_comp *comp, + bool in_napi) { struct ionic_tx_stats *stats = q_to_tx_stats(q); struct ionic_qcq *qcq = q_to_qcq(q); @@ -1204,11 +1211,13 @@ static void ionic_tx_clean(struct ionic_queue *q, desc_info->bytes = skb->len; stats->clean++; - napi_consume_skb(skb, 1); + napi_consume_skb(skb, likely(in_napi) ? 1 : 0); } static bool ionic_tx_service(struct ionic_cq *cq, - unsigned int *total_pkts, unsigned int *total_bytes) + unsigned int *total_pkts, + unsigned int *total_bytes, + bool in_napi) { struct ionic_tx_desc_info *desc_info; struct ionic_queue *q = cq->bound_q; @@ -1230,7 +1239,7 @@ static bool ionic_tx_service(struct ionic_cq *cq, desc_info->bytes = 0; index = q->tail_idx; q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); - ionic_tx_clean(q, desc_info, comp); + ionic_tx_clean(q, desc_info, comp, in_napi); if (desc_info->skb) { pkts++; bytes += desc_info->bytes; @@ -1244,7 +1253,9 @@ static bool ionic_tx_service(struct ionic_cq *cq, return true; } -unsigned int ionic_tx_cq_service(struct ionic_cq *cq, unsigned int work_to_do) +unsigned int ionic_tx_cq_service(struct ionic_cq *cq, + unsigned int work_to_do, + bool in_napi) { unsigned int work_done = 0; unsigned int bytes = 0; @@ -1253,7 +1264,7 @@ unsigned int ionic_tx_cq_service(struct ionic_cq *cq, unsigned int work_to_do) if (work_to_do == 0) return 0; - while (ionic_tx_service(cq, &pkts, &bytes)) { + while (ionic_tx_service(cq, &pkts, &bytes, in_napi)) { if (cq->tail_idx == cq->num_descs - 1) cq->done_color = !cq->done_color; cq->tail_idx = (cq->tail_idx + 1) & (cq->num_descs - 1); @@ -1279,7 +1290,7 @@ void ionic_tx_flush(struct ionic_cq *cq) { u32 work_done; - work_done = ionic_tx_cq_service(cq, cq->num_descs); + work_done = ionic_tx_cq_service(cq, cq->num_descs, false); if (work_done) ionic_intr_credits(cq->idev->intr_ctrl, cq->bound_intr->index, work_done, IONIC_INTR_CRED_RESET_COALESCE); @@ -1296,7 +1307,7 @@ void ionic_tx_empty(struct ionic_queue *q) desc_info = &q->tx_info[q->tail_idx]; desc_info->bytes = 0; q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); - ionic_tx_clean(q, desc_info, NULL); + ionic_tx_clean(q, desc_info, NULL, false); if (desc_info->skb) { pkts++; bytes += desc_info->bytes; diff --git a/drivers/net/ethernet/qualcomm/qca_debug.c b/drivers/net/ethernet/qualcomm/qca_debug.c index ff3b89e9028e..ad06da0fdaa0 100644 --- a/drivers/net/ethernet/qualcomm/qca_debug.c +++ b/drivers/net/ethernet/qualcomm/qca_debug.c @@ -98,10 +98,8 @@ qcaspi_info_show(struct seq_file *s, void *what) seq_printf(s, "IRQ : %d\n", qca->spi_dev->irq); - seq_printf(s, "INTR REQ : %u\n", - qca->intr_req); - seq_printf(s, "INTR SVC : %u\n", - qca->intr_svc); + seq_printf(s, "INTR : %lx\n", + qca->intr); seq_printf(s, "SPI max speed : %lu\n", (unsigned long)qca->spi_dev->max_speed_hz); diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 5799ecc88a87..8f7ce6b51a1c 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -35,6 +35,8 @@ #define MAX_DMA_BURST_LEN 5000 +#define SPI_INTR 0 + /* Modules parameters */ #define QCASPI_CLK_SPEED_MIN 1000000 #define QCASPI_CLK_SPEED_MAX 16000000 @@ -579,14 +581,14 @@ qcaspi_spi_thread(void *data) continue; } - if ((qca->intr_req == qca->intr_svc) && + if (!test_bit(SPI_INTR, &qca->intr) && !qca->txr.skb[qca->txr.head]) schedule(); set_current_state(TASK_RUNNING); - netdev_dbg(qca->net_dev, "have work to do. int: %d, tx_skb: %p\n", - qca->intr_req - qca->intr_svc, + netdev_dbg(qca->net_dev, "have work to do. int: %lu, tx_skb: %p\n", + qca->intr, qca->txr.skb[qca->txr.head]); qcaspi_qca7k_sync(qca, QCASPI_EVENT_UPDATE); @@ -600,8 +602,7 @@ qcaspi_spi_thread(void *data) msleep(QCASPI_QCA7K_REBOOT_TIME_MS); } - if (qca->intr_svc != qca->intr_req) { - qca->intr_svc = qca->intr_req; + if (test_and_clear_bit(SPI_INTR, &qca->intr)) { start_spi_intr_handling(qca, &intr_cause); if (intr_cause & SPI_INT_CPU_ON) { @@ -663,7 +664,7 @@ qcaspi_intr_handler(int irq, void *data) { struct qcaspi *qca = data; - qca->intr_req++; + set_bit(SPI_INTR, &qca->intr); if (qca->spi_thread) wake_up_process(qca->spi_thread); @@ -679,8 +680,7 @@ qcaspi_netdev_open(struct net_device *dev) if (!qca) return -EINVAL; - qca->intr_req = 1; - qca->intr_svc = 0; + set_bit(SPI_INTR, &qca->intr); qca->sync = QCASPI_SYNC_UNKNOWN; qcafrm_fsm_init_spi(&qca->frm_handle); diff --git a/drivers/net/ethernet/qualcomm/qca_spi.h b/drivers/net/ethernet/qualcomm/qca_spi.h index d59cb2352cee..8f4808695e82 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.h +++ b/drivers/net/ethernet/qualcomm/qca_spi.h @@ -81,8 +81,7 @@ struct qcaspi { struct qcafrm_handle frm_handle; struct sk_buff *rx_skb; - unsigned int intr_req; - unsigned int intr_svc; + unsigned long intr; u16 reset_count; #ifdef CONFIG_DEBUG_FS diff --git a/drivers/net/ethernet/renesas/Kconfig b/drivers/net/ethernet/renesas/Kconfig index b03fae7a0f72..9b7559c88bee 100644 --- a/drivers/net/ethernet/renesas/Kconfig +++ b/drivers/net/ethernet/renesas/Kconfig @@ -33,6 +33,7 @@ config RAVB select CRC32 select MII select MDIO_BITBANG + select PAGE_POOL select PHYLIB select RESET_CONTROLLER help @@ -58,4 +59,14 @@ config RENESAS_GEN4_PTP help Renesas R-Car Gen4 gPTP device driver. +config RTSN + tristate "Renesas Ethernet-TSN support" + depends on ARCH_RENESAS || COMPILE_TEST + depends on PTP_1588_CLOCK + select CRC32 + select PHYLIB + select RENESAS_GEN4_PTP + help + Renesas Ethernet-TSN device driver. + endif # NET_VENDOR_RENESAS diff --git a/drivers/net/ethernet/renesas/Makefile b/drivers/net/ethernet/renesas/Makefile index 9070acfd6aaf..f65fc76f8b4d 100644 --- a/drivers/net/ethernet/renesas/Makefile +++ b/drivers/net/ethernet/renesas/Makefile @@ -11,3 +11,5 @@ obj-$(CONFIG_RAVB) += ravb.o obj-$(CONFIG_RENESAS_ETHER_SWITCH) += rswitch.o obj-$(CONFIG_RENESAS_GEN4_PTP) += rcar_gen4_ptp.o + +obj-$(CONFIG_RTSN) += rtsn.o diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h index 6b2444d31fcc..9893c91af105 100644 --- a/drivers/net/ethernet/renesas/ravb.h +++ b/drivers/net/ethernet/renesas/ravb.h @@ -258,6 +258,7 @@ enum APSR_BIT { APSR_CMSW = 0x00000010, APSR_RDM = 0x00002000, APSR_TDM = 0x00004000, + APSR_MIISELECT = 0x01000000, /* R-Car V4M only */ }; /* RCR */ diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index c1546b916e4e..6605e4f4af53 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -579,6 +579,16 @@ static void ravb_emac_init_rcar(struct net_device *ndev) ravb_write(ndev, ECSIPR_ICDIP | ECSIPR_MPDIP | ECSIPR_LCHNGIP, ECSIPR); } +static void ravb_emac_init_rcar_gen4(struct net_device *ndev) +{ + struct ravb_private *priv = netdev_priv(ndev); + bool mii = priv->phy_interface == PHY_INTERFACE_MODE_MII; + + ravb_modify(ndev, APSR, APSR_MIISELECT, mii ? APSR_MIISELECT : 0); + + ravb_emac_init_rcar(ndev); +} + /* E-MAC init function */ static void ravb_emac_init(struct net_device *ndev) { @@ -2652,6 +2662,28 @@ static int ravb_mdio_release(struct ravb_private *priv) return 0; } +static const struct ravb_hw_info ravb_gen2_hw_info = { + .receive = ravb_rx_rcar, + .set_rate = ravb_set_rate_rcar, + .set_feature = ravb_set_features_rcar, + .dmac_init = ravb_dmac_init_rcar, + .emac_init = ravb_emac_init_rcar, + .gstrings_stats = ravb_gstrings_stats, + .gstrings_size = sizeof(ravb_gstrings_stats), + .net_hw_features = NETIF_F_RXCSUM, + .net_features = NETIF_F_RXCSUM, + .stats_len = ARRAY_SIZE(ravb_gstrings_stats), + .tccr_mask = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3, + .rx_max_frame_size = SZ_2K, + .rx_buffer_size = SZ_2K + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), + .rx_desc_size = sizeof(struct ravb_ex_rx_desc), + .aligned_tx = 1, + .gptp = 1, + .nc_queues = 1, + .magic_pkt = 1, +}; + static const struct ravb_hw_info ravb_gen3_hw_info = { .receive = ravb_rx_rcar, .set_rate = ravb_set_rate_rcar, @@ -2677,12 +2709,12 @@ static const struct ravb_hw_info ravb_gen3_hw_info = { .magic_pkt = 1, }; -static const struct ravb_hw_info ravb_gen2_hw_info = { +static const struct ravb_hw_info ravb_gen4_hw_info = { .receive = ravb_rx_rcar, .set_rate = ravb_set_rate_rcar, .set_feature = ravb_set_features_rcar, .dmac_init = ravb_dmac_init_rcar, - .emac_init = ravb_emac_init_rcar, + .emac_init = ravb_emac_init_rcar_gen4, .gstrings_stats = ravb_gstrings_stats, .gstrings_size = sizeof(ravb_gstrings_stats), .net_hw_features = NETIF_F_RXCSUM, @@ -2693,8 +2725,11 @@ static const struct ravb_hw_info ravb_gen2_hw_info = { .rx_buffer_size = SZ_2K + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), .rx_desc_size = sizeof(struct ravb_ex_rx_desc), - .aligned_tx = 1, - .gptp = 1, + .internal_delay = 1, + .tx_counters = 1, + .multi_irqs = 1, + .irq_en_dis = 1, + .ccc_gac = 1, .nc_queues = 1, .magic_pkt = 1, }; @@ -2751,7 +2786,7 @@ static const struct of_device_id ravb_match_table[] = { { .compatible = "renesas,etheravb-rcar-gen2", .data = &ravb_gen2_hw_info }, { .compatible = "renesas,etheravb-r8a7795", .data = &ravb_gen3_hw_info }, { .compatible = "renesas,etheravb-rcar-gen3", .data = &ravb_gen3_hw_info }, - { .compatible = "renesas,etheravb-rcar-gen4", .data = &ravb_gen3_hw_info }, + { .compatible = "renesas,etheravb-rcar-gen4", .data = &ravb_gen4_hw_info }, { .compatible = "renesas,etheravb-rzv2m", .data = &ravb_rzv2m_hw_info }, { .compatible = "renesas,rzg2l-gbeth", .data = &gbeth_hw_info }, { } diff --git a/drivers/net/ethernet/renesas/rtsn.c b/drivers/net/ethernet/renesas/rtsn.c new file mode 100644 index 000000000000..ad69d47463cb --- /dev/null +++ b/drivers/net/ethernet/renesas/rtsn.c @@ -0,0 +1,1391 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* Renesas Ethernet-TSN device driver + * + * Copyright (C) 2022 Renesas Electronics Corporation + * Copyright (C) 2023 Niklas Söderlund <[email protected]> + */ + +#include <linux/clk.h> +#include <linux/dma-mapping.h> +#include <linux/etherdevice.h> +#include <linux/ethtool.h> +#include <linux/module.h> +#include <linux/net_tstamp.h> +#include <linux/of.h> +#include <linux/of_mdio.h> +#include <linux/of_net.h> +#include <linux/phy.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/reset.h> +#include <linux/spinlock.h> + +#include "rtsn.h" +#include "rcar_gen4_ptp.h" + +struct rtsn_private { + struct net_device *ndev; + struct platform_device *pdev; + void __iomem *base; + struct rcar_gen4_ptp_private *ptp_priv; + struct clk *clk; + struct reset_control *reset; + + u32 num_tx_ring; + u32 num_rx_ring; + u32 tx_desc_bat_size; + dma_addr_t tx_desc_bat_dma; + struct rtsn_desc *tx_desc_bat; + u32 rx_desc_bat_size; + dma_addr_t rx_desc_bat_dma; + struct rtsn_desc *rx_desc_bat; + dma_addr_t tx_desc_dma; + dma_addr_t rx_desc_dma; + struct rtsn_ext_desc *tx_ring; + struct rtsn_ext_ts_desc *rx_ring; + struct sk_buff **tx_skb; + struct sk_buff **rx_skb; + spinlock_t lock; /* Register access lock */ + u32 cur_tx; + u32 dirty_tx; + u32 cur_rx; + u32 dirty_rx; + u8 ts_tag; + struct napi_struct napi; + struct rtnl_link_stats64 stats; + + struct mii_bus *mii; + phy_interface_t iface; + int link; + int speed; + + int tx_data_irq; + int rx_data_irq; +}; + +static u32 rtsn_read(struct rtsn_private *priv, enum rtsn_reg reg) +{ + return ioread32(priv->base + reg); +} + +static void rtsn_write(struct rtsn_private *priv, enum rtsn_reg reg, u32 data) +{ + iowrite32(data, priv->base + reg); +} + +static void rtsn_modify(struct rtsn_private *priv, enum rtsn_reg reg, + u32 clear, u32 set) +{ + rtsn_write(priv, reg, (rtsn_read(priv, reg) & ~clear) | set); +} + +static int rtsn_reg_wait(struct rtsn_private *priv, enum rtsn_reg reg, + u32 mask, u32 expected) +{ + u32 val; + + return readl_poll_timeout(priv->base + reg, val, + (val & mask) == expected, + RTSN_INTERVAL_US, RTSN_TIMEOUT_US); +} + +static void rtsn_ctrl_data_irq(struct rtsn_private *priv, bool enable) +{ + if (enable) { + rtsn_write(priv, TDIE0, TDIE_TDID_TDX(TX_CHAIN_IDX)); + rtsn_write(priv, RDIE0, RDIE_RDID_RDX(RX_CHAIN_IDX)); + } else { + rtsn_write(priv, TDID0, TDIE_TDID_TDX(TX_CHAIN_IDX)); + rtsn_write(priv, RDID0, RDIE_RDID_RDX(RX_CHAIN_IDX)); + } +} + +static void rtsn_get_timestamp(struct rtsn_private *priv, struct timespec64 *ts) +{ + struct rcar_gen4_ptp_private *ptp_priv = priv->ptp_priv; + + ptp_priv->info.gettime64(&ptp_priv->info, ts); +} + +static int rtsn_tx_free(struct net_device *ndev, bool free_txed_only) +{ + struct rtsn_private *priv = netdev_priv(ndev); + struct rtsn_ext_desc *desc; + struct sk_buff *skb; + int free_num = 0; + int entry, size; + + for (; priv->cur_tx - priv->dirty_tx > 0; priv->dirty_tx++) { + entry = priv->dirty_tx % priv->num_tx_ring; + desc = &priv->tx_ring[entry]; + if (free_txed_only && (desc->die_dt & DT_MASK) != DT_FEMPTY) + break; + + dma_rmb(); + size = le16_to_cpu(desc->info_ds) & TX_DS; + skb = priv->tx_skb[entry]; + if (skb) { + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { + struct skb_shared_hwtstamps shhwtstamps; + struct timespec64 ts; + + rtsn_get_timestamp(priv, &ts); + memset(&shhwtstamps, 0, sizeof(shhwtstamps)); + shhwtstamps.hwtstamp = timespec64_to_ktime(ts); + skb_tstamp_tx(skb, &shhwtstamps); + } + dma_unmap_single(ndev->dev.parent, + le32_to_cpu(desc->dptr), + size, DMA_TO_DEVICE); + dev_kfree_skb_any(priv->tx_skb[entry]); + free_num++; + + priv->stats.tx_packets++; + priv->stats.tx_bytes += size; + } + + desc->die_dt = DT_EEMPTY; + } + + desc = &priv->tx_ring[priv->num_tx_ring]; + desc->die_dt = DT_LINK; + + return free_num; +} + +static int rtsn_rx(struct net_device *ndev, int budget) +{ + struct rtsn_private *priv = netdev_priv(ndev); + unsigned int ndescriptors; + unsigned int rx_packets; + unsigned int i; + bool get_ts; + + get_ts = priv->ptp_priv->tstamp_rx_ctrl & + RCAR_GEN4_RXTSTAMP_TYPE_V2_L2_EVENT; + + ndescriptors = priv->dirty_rx + priv->num_rx_ring - priv->cur_rx; + rx_packets = 0; + for (i = 0; i < ndescriptors; i++) { + const unsigned int entry = priv->cur_rx % priv->num_rx_ring; + struct rtsn_ext_ts_desc *desc = &priv->rx_ring[entry]; + struct sk_buff *skb; + dma_addr_t dma_addr; + u16 pkt_len; + + /* Stop processing descriptors if budget is consumed. */ + if (rx_packets >= budget) + break; + + /* Stop processing descriptors on first empty. */ + if ((desc->die_dt & DT_MASK) == DT_FEMPTY) + break; + + dma_rmb(); + pkt_len = le16_to_cpu(desc->info_ds) & RX_DS; + + skb = priv->rx_skb[entry]; + priv->rx_skb[entry] = NULL; + dma_addr = le32_to_cpu(desc->dptr); + dma_unmap_single(ndev->dev.parent, dma_addr, PKT_BUF_SZ, + DMA_FROM_DEVICE); + + /* Get timestamp if enabled. */ + if (get_ts) { + struct skb_shared_hwtstamps *shhwtstamps; + struct timespec64 ts; + + shhwtstamps = skb_hwtstamps(skb); + memset(shhwtstamps, 0, sizeof(*shhwtstamps)); + + ts.tv_sec = (u64)le32_to_cpu(desc->ts_sec); + ts.tv_nsec = le32_to_cpu(desc->ts_nsec & cpu_to_le32(0x3fffffff)); + + shhwtstamps->hwtstamp = timespec64_to_ktime(ts); + } + + skb_put(skb, pkt_len); + skb->protocol = eth_type_trans(skb, ndev); + napi_gro_receive(&priv->napi, skb); + + /* Update statistics. */ + priv->stats.rx_packets++; + priv->stats.rx_bytes += pkt_len; + + /* Update counters. */ + priv->cur_rx++; + rx_packets++; + } + + /* Refill the RX ring buffers */ + for (; priv->cur_rx - priv->dirty_rx > 0; priv->dirty_rx++) { + const unsigned int entry = priv->dirty_rx % priv->num_rx_ring; + struct rtsn_ext_ts_desc *desc = &priv->rx_ring[entry]; + struct sk_buff *skb; + dma_addr_t dma_addr; + + desc->info_ds = cpu_to_le16(PKT_BUF_SZ); + + if (!priv->rx_skb[entry]) { + skb = napi_alloc_skb(&priv->napi, + PKT_BUF_SZ + RTSN_ALIGN - 1); + if (!skb) + break; + skb_reserve(skb, NET_IP_ALIGN); + dma_addr = dma_map_single(ndev->dev.parent, skb->data, + le16_to_cpu(desc->info_ds), + DMA_FROM_DEVICE); + if (dma_mapping_error(ndev->dev.parent, dma_addr)) + desc->info_ds = cpu_to_le16(0); + desc->dptr = cpu_to_le32(dma_addr); + skb_checksum_none_assert(skb); + priv->rx_skb[entry] = skb; + } + + dma_wmb(); + desc->die_dt = DT_FEMPTY | D_DIE; + } + + priv->rx_ring[priv->num_rx_ring].die_dt = DT_LINK; + + return rx_packets; +} + +static int rtsn_poll(struct napi_struct *napi, int budget) +{ + struct rtsn_private *priv; + struct net_device *ndev; + unsigned long flags; + int work_done; + + ndev = napi->dev; + priv = netdev_priv(ndev); + + /* Processing RX Descriptor Ring */ + work_done = rtsn_rx(ndev, budget); + + /* Processing TX Descriptor Ring */ + spin_lock_irqsave(&priv->lock, flags); + rtsn_tx_free(ndev, true); + netif_wake_subqueue(ndev, 0); + spin_unlock_irqrestore(&priv->lock, flags); + + /* Re-enable TX/RX interrupts */ + if (work_done < budget && napi_complete_done(napi, work_done)) { + spin_lock_irqsave(&priv->lock, flags); + rtsn_ctrl_data_irq(priv, true); + spin_unlock_irqrestore(&priv->lock, flags); + } + + return work_done; +} + +static int rtsn_desc_alloc(struct rtsn_private *priv) +{ + struct device *dev = &priv->pdev->dev; + unsigned int i; + + priv->tx_desc_bat_size = sizeof(struct rtsn_desc) * TX_NUM_CHAINS; + priv->tx_desc_bat = dma_alloc_coherent(dev, priv->tx_desc_bat_size, + &priv->tx_desc_bat_dma, + GFP_KERNEL); + + if (!priv->tx_desc_bat) + return -ENOMEM; + + for (i = 0; i < TX_NUM_CHAINS; i++) + priv->tx_desc_bat[i].die_dt = DT_EOS; + + priv->rx_desc_bat_size = sizeof(struct rtsn_desc) * RX_NUM_CHAINS; + priv->rx_desc_bat = dma_alloc_coherent(dev, priv->rx_desc_bat_size, + &priv->rx_desc_bat_dma, + GFP_KERNEL); + + if (!priv->rx_desc_bat) + return -ENOMEM; + + for (i = 0; i < RX_NUM_CHAINS; i++) + priv->rx_desc_bat[i].die_dt = DT_EOS; + + return 0; +} + +static void rtsn_desc_free(struct rtsn_private *priv) +{ + if (priv->tx_desc_bat) + dma_free_coherent(&priv->pdev->dev, priv->tx_desc_bat_size, + priv->tx_desc_bat, priv->tx_desc_bat_dma); + priv->tx_desc_bat = NULL; + + if (priv->rx_desc_bat) + dma_free_coherent(&priv->pdev->dev, priv->rx_desc_bat_size, + priv->rx_desc_bat, priv->rx_desc_bat_dma); + priv->rx_desc_bat = NULL; +} + +static void rtsn_chain_free(struct rtsn_private *priv) +{ + struct device *dev = &priv->pdev->dev; + + dma_free_coherent(dev, + sizeof(struct rtsn_ext_desc) * (priv->num_tx_ring + 1), + priv->tx_ring, priv->tx_desc_dma); + priv->tx_ring = NULL; + + dma_free_coherent(dev, + sizeof(struct rtsn_ext_ts_desc) * (priv->num_rx_ring + 1), + priv->rx_ring, priv->rx_desc_dma); + priv->rx_ring = NULL; + + kfree(priv->tx_skb); + priv->tx_skb = NULL; + + kfree(priv->rx_skb); + priv->rx_skb = NULL; +} + +static int rtsn_chain_init(struct rtsn_private *priv, int tx_size, int rx_size) +{ + struct net_device *ndev = priv->ndev; + struct sk_buff *skb; + int i; + + priv->num_tx_ring = tx_size; + priv->num_rx_ring = rx_size; + + priv->tx_skb = kcalloc(tx_size, sizeof(*priv->tx_skb), GFP_KERNEL); + priv->rx_skb = kcalloc(rx_size, sizeof(*priv->rx_skb), GFP_KERNEL); + + if (!priv->rx_skb || !priv->tx_skb) + goto error; + + for (i = 0; i < rx_size; i++) { + skb = netdev_alloc_skb(ndev, PKT_BUF_SZ + RTSN_ALIGN - 1); + if (!skb) + goto error; + skb_reserve(skb, NET_IP_ALIGN); + priv->rx_skb[i] = skb; + } + + /* Allocate TX, RX descriptors */ + priv->tx_ring = dma_alloc_coherent(ndev->dev.parent, + sizeof(struct rtsn_ext_desc) * (tx_size + 1), + &priv->tx_desc_dma, GFP_KERNEL); + priv->rx_ring = dma_alloc_coherent(ndev->dev.parent, + sizeof(struct rtsn_ext_ts_desc) * (rx_size + 1), + &priv->rx_desc_dma, GFP_KERNEL); + + if (!priv->tx_ring || !priv->rx_ring) + goto error; + + return 0; +error: + rtsn_chain_free(priv); + + return -ENOMEM; +} + +static void rtsn_chain_format(struct rtsn_private *priv) +{ + struct net_device *ndev = priv->ndev; + struct rtsn_ext_ts_desc *rx_desc; + struct rtsn_ext_desc *tx_desc; + struct rtsn_desc *bat_desc; + dma_addr_t dma_addr; + unsigned int i; + + priv->cur_tx = 0; + priv->cur_rx = 0; + priv->dirty_rx = 0; + priv->dirty_tx = 0; + + /* TX */ + memset(priv->tx_ring, 0, sizeof(*tx_desc) * priv->num_tx_ring); + for (i = 0, tx_desc = priv->tx_ring; i < priv->num_tx_ring; i++, tx_desc++) + tx_desc->die_dt = DT_EEMPTY | D_DIE; + + tx_desc->dptr = cpu_to_le32((u32)priv->tx_desc_dma); + tx_desc->die_dt = DT_LINK; + + bat_desc = &priv->tx_desc_bat[TX_CHAIN_IDX]; + bat_desc->die_dt = DT_LINK; + bat_desc->dptr = cpu_to_le32((u32)priv->tx_desc_dma); + + /* RX */ + memset(priv->rx_ring, 0, sizeof(*rx_desc) * priv->num_rx_ring); + for (i = 0, rx_desc = priv->rx_ring; i < priv->num_rx_ring; i++, rx_desc++) { + dma_addr = dma_map_single(ndev->dev.parent, + priv->rx_skb[i]->data, PKT_BUF_SZ, + DMA_FROM_DEVICE); + if (!dma_mapping_error(ndev->dev.parent, dma_addr)) + rx_desc->info_ds = cpu_to_le16(PKT_BUF_SZ); + rx_desc->dptr = cpu_to_le32((u32)dma_addr); + rx_desc->die_dt = DT_FEMPTY | D_DIE; + } + rx_desc->dptr = cpu_to_le32((u32)priv->rx_desc_dma); + rx_desc->die_dt = DT_LINK; + + bat_desc = &priv->rx_desc_bat[RX_CHAIN_IDX]; + bat_desc->die_dt = DT_LINK; + bat_desc->dptr = cpu_to_le32((u32)priv->rx_desc_dma); +} + +static int rtsn_dmac_init(struct rtsn_private *priv) +{ + int ret; + + ret = rtsn_chain_init(priv, TX_CHAIN_SIZE, RX_CHAIN_SIZE); + if (ret) + return ret; + + rtsn_chain_format(priv); + + return 0; +} + +static enum rtsn_mode rtsn_read_mode(struct rtsn_private *priv) +{ + return (rtsn_read(priv, OSR) & OSR_OPS) >> 1; +} + +static int rtsn_wait_mode(struct rtsn_private *priv, enum rtsn_mode mode) +{ + unsigned int i; + + /* Need to busy loop as mode changes can happen in atomic context. */ + for (i = 0; i < RTSN_TIMEOUT_US / RTSN_INTERVAL_US; i++) { + if (rtsn_read_mode(priv) == mode) + return 0; + + udelay(RTSN_INTERVAL_US); + } + + return -ETIMEDOUT; +} + +static int rtsn_change_mode(struct rtsn_private *priv, enum rtsn_mode mode) +{ + int ret; + + rtsn_write(priv, OCR, mode); + ret = rtsn_wait_mode(priv, mode); + if (ret) + netdev_err(priv->ndev, "Failed to switch operation mode\n"); + return ret; +} + +static int rtsn_get_data_irq_status(struct rtsn_private *priv) +{ + u32 val; + + val = rtsn_read(priv, TDIS0) | TDIS_TDS(TX_CHAIN_IDX); + val |= rtsn_read(priv, RDIS0) | RDIS_RDS(RX_CHAIN_IDX); + + return val; +} + +static irqreturn_t rtsn_irq(int irq, void *dev_id) +{ + struct rtsn_private *priv = dev_id; + int ret = IRQ_NONE; + + spin_lock(&priv->lock); + + if (rtsn_get_data_irq_status(priv)) { + /* Clear TX/RX irq status */ + rtsn_write(priv, TDIS0, TDIS_TDS(TX_CHAIN_IDX)); + rtsn_write(priv, RDIS0, RDIS_RDS(RX_CHAIN_IDX)); + + if (napi_schedule_prep(&priv->napi)) { + /* Disable TX/RX interrupts */ + rtsn_ctrl_data_irq(priv, false); + + __napi_schedule(&priv->napi); + } + + ret = IRQ_HANDLED; + } + + spin_unlock(&priv->lock); + + return ret; +} + +static int rtsn_request_irq(unsigned int irq, irq_handler_t handler, + unsigned long flags, struct rtsn_private *priv, + const char *ch) +{ + char *name; + int ret; + + name = devm_kasprintf(&priv->pdev->dev, GFP_KERNEL, "%s:%s", + priv->ndev->name, ch); + if (!name) + return -ENOMEM; + + ret = request_irq(irq, handler, flags, name, priv); + if (ret) + netdev_err(priv->ndev, "Cannot request IRQ %s\n", name); + + return ret; +} + +static void rtsn_free_irqs(struct rtsn_private *priv) +{ + free_irq(priv->tx_data_irq, priv); + free_irq(priv->rx_data_irq, priv); +} + +static int rtsn_request_irqs(struct rtsn_private *priv) +{ + int ret; + + priv->rx_data_irq = platform_get_irq_byname(priv->pdev, "rx"); + if (priv->rx_data_irq < 0) + return priv->rx_data_irq; + + priv->tx_data_irq = platform_get_irq_byname(priv->pdev, "tx"); + if (priv->tx_data_irq < 0) + return priv->tx_data_irq; + + ret = rtsn_request_irq(priv->tx_data_irq, rtsn_irq, 0, priv, "tx"); + if (ret) + return ret; + + ret = rtsn_request_irq(priv->rx_data_irq, rtsn_irq, 0, priv, "rx"); + if (ret) { + free_irq(priv->tx_data_irq, priv); + return ret; + } + + return 0; +} + +static int rtsn_reset(struct rtsn_private *priv) +{ + reset_control_reset(priv->reset); + mdelay(1); + + return rtsn_wait_mode(priv, OCR_OPC_DISABLE); +} + +static int rtsn_axibmi_init(struct rtsn_private *priv) +{ + int ret; + + ret = rtsn_reg_wait(priv, RR, RR_RST, RR_RST_COMPLETE); + if (ret) + return ret; + + /* Set AXIWC */ + rtsn_write(priv, AXIWC, AXIWC_DEFAULT); + + /* Set AXIRC */ + rtsn_write(priv, AXIRC, AXIRC_DEFAULT); + + /* TX Descriptor chain setting */ + rtsn_write(priv, TATLS0, TATLS0_TEDE | TATLS0_TATEN(TX_CHAIN_IDX)); + rtsn_write(priv, TATLS1, priv->tx_desc_bat_dma + TX_CHAIN_ADDR_OFFSET); + rtsn_write(priv, TATLR, TATLR_TATL); + + ret = rtsn_reg_wait(priv, TATLR, TATLR_TATL, 0); + if (ret) + return ret; + + /* RX Descriptor chain setting */ + rtsn_write(priv, RATLS0, + RATLS0_RETS | RATLS0_REDE | RATLS0_RATEN(RX_CHAIN_IDX)); + rtsn_write(priv, RATLS1, priv->rx_desc_bat_dma + RX_CHAIN_ADDR_OFFSET); + rtsn_write(priv, RATLR, RATLR_RATL); + + ret = rtsn_reg_wait(priv, RATLR, RATLR_RATL, 0); + if (ret) + return ret; + + /* Enable TX/RX interrupts */ + rtsn_ctrl_data_irq(priv, true); + + return 0; +} + +static void rtsn_mhd_init(struct rtsn_private *priv) +{ + /* TX General setting */ + rtsn_write(priv, TGC1, TGC1_STTV_DEFAULT | TGC1_TQTM_SFM); + rtsn_write(priv, TMS0, TMS_MFS_MAX); + + /* RX Filter IP */ + rtsn_write(priv, CFCR0, CFCR_SDID(RX_CHAIN_IDX)); + rtsn_write(priv, FMSCR, FMSCR_FMSIE(RX_CHAIN_IDX)); +} + +static int rtsn_get_phy_params(struct rtsn_private *priv) +{ + int ret; + + ret = of_get_phy_mode(priv->pdev->dev.of_node, &priv->iface); + if (ret) + return ret; + + switch (priv->iface) { + case PHY_INTERFACE_MODE_MII: + priv->speed = 100; + break; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + priv->speed = 1000; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static void rtsn_set_phy_interface(struct rtsn_private *priv) +{ + u32 val; + + switch (priv->iface) { + case PHY_INTERFACE_MODE_MII: + val = MPIC_PIS_MII; + break; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + val = MPIC_PIS_GMII; + break; + default: + return; + } + + rtsn_modify(priv, MPIC, MPIC_PIS_MASK, val); +} + +static void rtsn_set_rate(struct rtsn_private *priv) +{ + u32 val; + + switch (priv->speed) { + case 10: + val = MPIC_LSC_10M; + break; + case 100: + val = MPIC_LSC_100M; + break; + case 1000: + val = MPIC_LSC_1G; + break; + default: + return; + } + + rtsn_modify(priv, MPIC, MPIC_LSC_MASK, val); +} + +static int rtsn_rmac_init(struct rtsn_private *priv) +{ + const u8 *mac_addr = priv->ndev->dev_addr; + int ret; + + /* Set MAC address */ + rtsn_write(priv, MRMAC0, (mac_addr[0] << 8) | mac_addr[1]); + rtsn_write(priv, MRMAC1, (mac_addr[2] << 24) | (mac_addr[3] << 16) | + (mac_addr[4] << 8) | mac_addr[5]); + + /* Set xMII type */ + rtsn_set_phy_interface(priv); + rtsn_set_rate(priv); + + /* Enable MII */ + rtsn_modify(priv, MPIC, MPIC_PSMCS_MASK | MPIC_PSMHT_MASK, + MPIC_PSMCS_DEFAULT | MPIC_PSMHT_DEFAULT); + + /* Link verification */ + rtsn_modify(priv, MLVC, MLVC_PLV, MLVC_PLV); + ret = rtsn_reg_wait(priv, MLVC, MLVC_PLV, 0); + if (ret) + return ret; + + return ret; +} + +static int rtsn_hw_init(struct rtsn_private *priv) +{ + int ret; + + ret = rtsn_reset(priv); + if (ret) + return ret; + + /* Change to CONFIG mode */ + ret = rtsn_change_mode(priv, OCR_OPC_CONFIG); + if (ret) + return ret; + + ret = rtsn_axibmi_init(priv); + if (ret) + return ret; + + rtsn_mhd_init(priv); + + ret = rtsn_rmac_init(priv); + if (ret) + return ret; + + ret = rtsn_change_mode(priv, OCR_OPC_DISABLE); + if (ret) + return ret; + + /* Change to OPERATION mode */ + ret = rtsn_change_mode(priv, OCR_OPC_OPERATION); + + return ret; +} + +static int rtsn_mii_access(struct mii_bus *bus, bool read, int phyad, + int regad, u16 data) +{ + struct rtsn_private *priv = bus->priv; + u32 val; + int ret; + + val = MPSM_PDA(phyad) | MPSM_PRA(regad) | MPSM_PSME; + + if (!read) + val |= MPSM_PSMAD | MPSM_PRD_SET(data); + + rtsn_write(priv, MPSM, val); + + ret = rtsn_reg_wait(priv, MPSM, MPSM_PSME, 0); + if (ret) + return ret; + + if (read) + ret = MPSM_PRD_GET(rtsn_read(priv, MPSM)); + + return ret; +} + +static int rtsn_mii_read(struct mii_bus *bus, int addr, int regnum) +{ + return rtsn_mii_access(bus, true, addr, regnum, 0); +} + +static int rtsn_mii_write(struct mii_bus *bus, int addr, int regnum, u16 val) +{ + return rtsn_mii_access(bus, false, addr, regnum, val); +} + +static int rtsn_mdio_alloc(struct rtsn_private *priv) +{ + struct platform_device *pdev = priv->pdev; + struct device *dev = &pdev->dev; + struct device_node *mdio_node; + struct mii_bus *mii; + int ret; + + mii = mdiobus_alloc(); + if (!mii) + return -ENOMEM; + + mdio_node = of_get_child_by_name(dev->of_node, "mdio"); + if (!mdio_node) { + ret = -ENODEV; + goto out_free_bus; + } + + /* Enter config mode before registering the MDIO bus */ + ret = rtsn_reset(priv); + if (ret) + goto out_free_bus; + + ret = rtsn_change_mode(priv, OCR_OPC_CONFIG); + if (ret) + goto out_free_bus; + + rtsn_modify(priv, MPIC, MPIC_PSMCS_MASK | MPIC_PSMHT_MASK, + MPIC_PSMCS_DEFAULT | MPIC_PSMHT_DEFAULT); + + /* Register the MDIO bus */ + mii->name = "rtsn_mii"; + snprintf(mii->id, MII_BUS_ID_SIZE, "%s-%x", + pdev->name, pdev->id); + mii->priv = priv; + mii->read = rtsn_mii_read; + mii->write = rtsn_mii_write; + mii->parent = dev; + + ret = of_mdiobus_register(mii, mdio_node); + of_node_put(mdio_node); + if (ret) + goto out_free_bus; + + priv->mii = mii; + + return 0; + +out_free_bus: + mdiobus_free(mii); + return ret; +} + +static void rtsn_mdio_free(struct rtsn_private *priv) +{ + mdiobus_unregister(priv->mii); + mdiobus_free(priv->mii); + priv->mii = NULL; +} + +static void rtsn_adjust_link(struct net_device *ndev) +{ + struct rtsn_private *priv = netdev_priv(ndev); + struct phy_device *phydev = ndev->phydev; + bool new_state = false; + unsigned long flags; + + spin_lock_irqsave(&priv->lock, flags); + + if (phydev->link) { + if (phydev->speed != priv->speed) { + new_state = true; + priv->speed = phydev->speed; + } + + if (!priv->link) { + new_state = true; + priv->link = phydev->link; + } + } else if (priv->link) { + new_state = true; + priv->link = 0; + priv->speed = 0; + } + + if (new_state) { + /* Need to transition to CONFIG mode before reconfiguring and + * then back to the original mode. Any state change to/from + * CONFIG or OPERATION must go over DISABLED to stop Rx/Tx. + */ + enum rtsn_mode orgmode = rtsn_read_mode(priv); + + /* Transit to CONFIG */ + if (orgmode != OCR_OPC_CONFIG) { + if (orgmode != OCR_OPC_DISABLE && + rtsn_change_mode(priv, OCR_OPC_DISABLE)) + goto out; + if (rtsn_change_mode(priv, OCR_OPC_CONFIG)) + goto out; + } + + rtsn_set_rate(priv); + + /* Transition to original mode */ + if (orgmode != OCR_OPC_CONFIG) { + if (rtsn_change_mode(priv, OCR_OPC_DISABLE)) + goto out; + if (orgmode != OCR_OPC_DISABLE && + rtsn_change_mode(priv, orgmode)) + goto out; + } + } +out: + spin_unlock_irqrestore(&priv->lock, flags); + + if (new_state) + phy_print_status(phydev); +} + +static int rtsn_phy_init(struct rtsn_private *priv) +{ + struct device_node *np = priv->ndev->dev.parent->of_node; + struct phy_device *phydev; + struct device_node *phy; + + priv->link = 0; + + phy = of_parse_phandle(np, "phy-handle", 0); + if (!phy) + return -ENOENT; + + phydev = of_phy_connect(priv->ndev, phy, rtsn_adjust_link, 0, + priv->iface); + of_node_put(phy); + if (!phydev) + return -ENOENT; + + /* Only support full-duplex mode */ + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Half_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); + + phy_attached_info(phydev); + + return 0; +} + +static void rtsn_phy_deinit(struct rtsn_private *priv) +{ + phy_disconnect(priv->ndev->phydev); + priv->ndev->phydev = NULL; +} + +static int rtsn_init(struct rtsn_private *priv) +{ + int ret; + + ret = rtsn_desc_alloc(priv); + if (ret) + return ret; + + ret = rtsn_dmac_init(priv); + if (ret) + goto error_free_desc; + + ret = rtsn_hw_init(priv); + if (ret) + goto error_free_chain; + + ret = rtsn_phy_init(priv); + if (ret) + goto error_free_chain; + + ret = rtsn_request_irqs(priv); + if (ret) + goto error_free_phy; + + return 0; +error_free_phy: + rtsn_phy_deinit(priv); +error_free_chain: + rtsn_chain_free(priv); +error_free_desc: + rtsn_desc_free(priv); + return ret; +} + +static void rtsn_deinit(struct rtsn_private *priv) +{ + rtsn_free_irqs(priv); + rtsn_phy_deinit(priv); + rtsn_chain_free(priv); + rtsn_desc_free(priv); +} + +static void rtsn_parse_mac_address(struct device_node *np, + struct net_device *ndev) +{ + struct rtsn_private *priv = netdev_priv(ndev); + u8 addr[ETH_ALEN]; + u32 mrmac0; + u32 mrmac1; + + /* Try to read address from Device Tree. */ + if (!of_get_mac_address(np, addr)) { + eth_hw_addr_set(ndev, addr); + return; + } + + /* Try to read address from device. */ + mrmac0 = rtsn_read(priv, MRMAC0); + mrmac1 = rtsn_read(priv, MRMAC1); + + addr[0] = (mrmac0 >> 8) & 0xff; + addr[1] = (mrmac0 >> 0) & 0xff; + addr[2] = (mrmac1 >> 24) & 0xff; + addr[3] = (mrmac1 >> 16) & 0xff; + addr[4] = (mrmac1 >> 8) & 0xff; + addr[5] = (mrmac1 >> 0) & 0xff; + + if (is_valid_ether_addr(addr)) { + eth_hw_addr_set(ndev, addr); + return; + } + + /* Fallback to a random address */ + eth_hw_addr_random(ndev); +} + +static int rtsn_open(struct net_device *ndev) +{ + struct rtsn_private *priv = netdev_priv(ndev); + int ret; + + napi_enable(&priv->napi); + + ret = rtsn_init(priv); + if (ret) { + napi_disable(&priv->napi); + return ret; + } + + phy_start(ndev->phydev); + + netif_start_queue(ndev); + + return 0; +} + +static int rtsn_stop(struct net_device *ndev) +{ + struct rtsn_private *priv = netdev_priv(ndev); + + phy_stop(priv->ndev->phydev); + napi_disable(&priv->napi); + rtsn_change_mode(priv, OCR_OPC_DISABLE); + rtsn_deinit(priv); + + return 0; +} + +static netdev_tx_t rtsn_start_xmit(struct sk_buff *skb, struct net_device *ndev) +{ + struct rtsn_private *priv = netdev_priv(ndev); + struct rtsn_ext_desc *desc; + int ret = NETDEV_TX_OK; + unsigned long flags; + dma_addr_t dma_addr; + int entry; + + spin_lock_irqsave(&priv->lock, flags); + + /* Drop packet if it won't fit in a single descriptor. */ + if (skb->len >= TX_DS) { + priv->stats.tx_dropped++; + priv->stats.tx_errors++; + goto out; + } + + if (priv->cur_tx - priv->dirty_tx > priv->num_tx_ring) { + netif_stop_subqueue(ndev, 0); + ret = NETDEV_TX_BUSY; + goto out; + } + + if (skb_put_padto(skb, ETH_ZLEN)) + goto out; + + dma_addr = dma_map_single(ndev->dev.parent, skb->data, skb->len, + DMA_TO_DEVICE); + if (dma_mapping_error(ndev->dev.parent, dma_addr)) { + dev_kfree_skb_any(skb); + goto out; + } + + entry = priv->cur_tx % priv->num_tx_ring; + priv->tx_skb[entry] = skb; + desc = &priv->tx_ring[entry]; + desc->dptr = cpu_to_le32(dma_addr); + desc->info_ds = cpu_to_le16(skb->len); + desc->info1 = cpu_to_le64(skb->len); + + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + priv->ts_tag++; + desc->info_ds |= cpu_to_le16(TXC); + desc->info = priv->ts_tag; + } + + skb_tx_timestamp(skb); + dma_wmb(); + + desc->die_dt = DT_FSINGLE | D_DIE; + priv->cur_tx++; + + /* Start xmit */ + rtsn_write(priv, TRCR0, BIT(TX_CHAIN_IDX)); +out: + spin_unlock_irqrestore(&priv->lock, flags); + return ret; +} + +static void rtsn_get_stats64(struct net_device *ndev, + struct rtnl_link_stats64 *storage) +{ + struct rtsn_private *priv = netdev_priv(ndev); + *storage = priv->stats; +} + +static int rtsn_do_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd) +{ + if (!netif_running(ndev)) + return -ENODEV; + + return phy_do_ioctl_running(ndev, ifr, cmd); +} + +static int rtsn_hwtstamp_get(struct net_device *ndev, + struct kernel_hwtstamp_config *config) +{ + struct rcar_gen4_ptp_private *ptp_priv; + struct rtsn_private *priv; + + if (!netif_running(ndev)) + return -ENODEV; + + priv = netdev_priv(ndev); + ptp_priv = priv->ptp_priv; + + config->flags = 0; + + config->tx_type = + ptp_priv->tstamp_tx_ctrl ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; + + switch (ptp_priv->tstamp_rx_ctrl & RCAR_GEN4_RXTSTAMP_TYPE) { + case RCAR_GEN4_RXTSTAMP_TYPE_V2_L2_EVENT: + config->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; + break; + case RCAR_GEN4_RXTSTAMP_TYPE_ALL: + config->rx_filter = HWTSTAMP_FILTER_ALL; + break; + default: + config->rx_filter = HWTSTAMP_FILTER_NONE; + break; + } + + return 0; +} + +static int rtsn_hwtstamp_set(struct net_device *ndev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + struct rcar_gen4_ptp_private *ptp_priv; + struct rtsn_private *priv; + u32 tstamp_rx_ctrl; + u32 tstamp_tx_ctrl; + + if (!netif_running(ndev)) + return -ENODEV; + + priv = netdev_priv(ndev); + ptp_priv = priv->ptp_priv; + + if (config->flags) + return -EINVAL; + + switch (config->tx_type) { + case HWTSTAMP_TX_OFF: + tstamp_tx_ctrl = 0; + break; + case HWTSTAMP_TX_ON: + tstamp_tx_ctrl = RCAR_GEN4_TXTSTAMP_ENABLED; + break; + default: + return -ERANGE; + } + + switch (config->rx_filter) { + case HWTSTAMP_FILTER_NONE: + tstamp_rx_ctrl = 0; + break; + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + tstamp_rx_ctrl = RCAR_GEN4_RXTSTAMP_ENABLED | + RCAR_GEN4_RXTSTAMP_TYPE_V2_L2_EVENT; + break; + default: + config->rx_filter = HWTSTAMP_FILTER_ALL; + tstamp_rx_ctrl = RCAR_GEN4_RXTSTAMP_ENABLED | + RCAR_GEN4_RXTSTAMP_TYPE_ALL; + break; + } + + ptp_priv->tstamp_tx_ctrl = tstamp_tx_ctrl; + ptp_priv->tstamp_rx_ctrl = tstamp_rx_ctrl; + + return 0; +} + +static const struct net_device_ops rtsn_netdev_ops = { + .ndo_open = rtsn_open, + .ndo_stop = rtsn_stop, + .ndo_start_xmit = rtsn_start_xmit, + .ndo_get_stats64 = rtsn_get_stats64, + .ndo_eth_ioctl = rtsn_do_ioctl, + .ndo_validate_addr = eth_validate_addr, + .ndo_set_mac_address = eth_mac_addr, + .ndo_hwtstamp_set = rtsn_hwtstamp_set, + .ndo_hwtstamp_get = rtsn_hwtstamp_get, +}; + +static int rtsn_get_ts_info(struct net_device *ndev, + struct ethtool_ts_info *info) +{ + struct rtsn_private *priv = netdev_priv(ndev); + + info->phc_index = ptp_clock_index(priv->ptp_priv->clock); + info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON); + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL); + + return 0; +} + +static const struct ethtool_ops rtsn_ethtool_ops = { + .nway_reset = phy_ethtool_nway_reset, + .get_link = ethtool_op_get_link, + .get_ts_info = rtsn_get_ts_info, + .get_link_ksettings = phy_ethtool_get_link_ksettings, + .set_link_ksettings = phy_ethtool_set_link_ksettings, +}; + +static const struct of_device_id rtsn_match_table[] = { + { .compatible = "renesas,r8a779g0-ethertsn", }, + { /* Sentinel */ } +}; + +MODULE_DEVICE_TABLE(of, rtsn_match_table); + +static int rtsn_probe(struct platform_device *pdev) +{ + struct rtsn_private *priv; + struct net_device *ndev; + struct resource *res; + int ret; + + ndev = alloc_etherdev_mqs(sizeof(struct rtsn_private), TX_NUM_CHAINS, + RX_NUM_CHAINS); + if (!ndev) + return -ENOMEM; + + priv = netdev_priv(ndev); + priv->pdev = pdev; + priv->ndev = ndev; + priv->ptp_priv = rcar_gen4_ptp_alloc(pdev); + + spin_lock_init(&priv->lock); + platform_set_drvdata(pdev, priv); + + priv->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(priv->clk)) { + ret = PTR_ERR(priv->clk); + goto error_free; + } + + priv->reset = devm_reset_control_get(&pdev->dev, NULL); + if (IS_ERR(priv->reset)) { + ret = PTR_ERR(priv->reset); + goto error_free; + } + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "tsnes"); + if (!res) { + dev_err(&pdev->dev, "Can't find tsnes resource\n"); + ret = -EINVAL; + goto error_free; + } + + priv->base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(priv->base)) { + ret = PTR_ERR(priv->base); + goto error_free; + } + + SET_NETDEV_DEV(ndev, &pdev->dev); + + ndev->features = NETIF_F_RXCSUM; + ndev->hw_features = NETIF_F_RXCSUM; + ndev->base_addr = res->start; + ndev->netdev_ops = &rtsn_netdev_ops; + ndev->ethtool_ops = &rtsn_ethtool_ops; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "gptp"); + if (!res) { + dev_err(&pdev->dev, "Can't find gptp resource\n"); + ret = -EINVAL; + goto error_free; + } + + priv->ptp_priv->addr = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(priv->ptp_priv->addr)) { + ret = PTR_ERR(priv->ptp_priv->addr); + goto error_free; + } + + ret = rtsn_get_phy_params(priv); + if (ret) + goto error_free; + + pm_runtime_enable(&pdev->dev); + pm_runtime_get_sync(&pdev->dev); + + netif_napi_add(ndev, &priv->napi, rtsn_poll); + + rtsn_parse_mac_address(pdev->dev.of_node, ndev); + + dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + + device_set_wakeup_capable(&pdev->dev, 1); + + ret = rcar_gen4_ptp_register(priv->ptp_priv, RCAR_GEN4_PTP_REG_LAYOUT, + clk_get_rate(priv->clk)); + if (ret) + goto error_pm; + + ret = rtsn_mdio_alloc(priv); + if (ret) + goto error_ptp; + + ret = register_netdev(ndev); + if (ret) + goto error_mdio; + + netdev_info(ndev, "MAC address %pM\n", ndev->dev_addr); + + return 0; + +error_mdio: + rtsn_mdio_free(priv); +error_ptp: + rcar_gen4_ptp_unregister(priv->ptp_priv); +error_pm: + netif_napi_del(&priv->napi); + rtsn_change_mode(priv, OCR_OPC_DISABLE); + pm_runtime_put_sync(&pdev->dev); + pm_runtime_disable(&pdev->dev); +error_free: + free_netdev(ndev); + + return ret; +} + +static int rtsn_remove(struct platform_device *pdev) +{ + struct rtsn_private *priv = platform_get_drvdata(pdev); + + unregister_netdev(priv->ndev); + rtsn_mdio_free(priv); + rcar_gen4_ptp_unregister(priv->ptp_priv); + rtsn_change_mode(priv, OCR_OPC_DISABLE); + netif_napi_del(&priv->napi); + + pm_runtime_put_sync(&pdev->dev); + pm_runtime_disable(&pdev->dev); + + free_netdev(priv->ndev); + + return 0; +} + +static struct platform_driver rtsn_driver = { + .probe = rtsn_probe, + .remove = rtsn_remove, + .driver = { + .name = "rtsn", + .of_match_table = rtsn_match_table, + } +}; +module_platform_driver(rtsn_driver); + +MODULE_AUTHOR("Phong Hoang, Niklas Söderlund"); +MODULE_DESCRIPTION("Renesas Ethernet-TSN device driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/renesas/rtsn.h b/drivers/net/ethernet/renesas/rtsn.h new file mode 100644 index 000000000000..3183e80d7e6b --- /dev/null +++ b/drivers/net/ethernet/renesas/rtsn.h @@ -0,0 +1,464 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Renesas Ethernet-TSN device driver + * + * Copyright (C) 2022 Renesas Electronics Corporation + * Copyright (C) 2023 Niklas Söderlund <[email protected]> + */ + +#ifndef __RTSN_H__ +#define __RTSN_H__ + +#include <linux/types.h> + +#define AXIBMI 0x0000 +#define TSNMHD 0x1000 +#define RMSO 0x2000 +#define RMRO 0x3800 + +enum rtsn_reg { + AXIWC = AXIBMI + 0x0000, + AXIRC = AXIBMI + 0x0004, + TDPC0 = AXIBMI + 0x0010, + TFT = AXIBMI + 0x0090, + TATLS0 = AXIBMI + 0x00a0, + TATLS1 = AXIBMI + 0x00a4, + TATLR = AXIBMI + 0x00a8, + RATLS0 = AXIBMI + 0x00b0, + RATLS1 = AXIBMI + 0x00b4, + RATLR = AXIBMI + 0x00b8, + TSA0 = AXIBMI + 0x00c0, + TSS0 = AXIBMI + 0x00c4, + TRCR0 = AXIBMI + 0x0140, + RIDAUAS0 = AXIBMI + 0x0180, + RR = AXIBMI + 0x0200, + TATS = AXIBMI + 0x0210, + TATSR0 = AXIBMI + 0x0214, + TATSR1 = AXIBMI + 0x0218, + TATSR2 = AXIBMI + 0x021c, + RATS = AXIBMI + 0x0220, + RATSR0 = AXIBMI + 0x0224, + RATSR1 = AXIBMI + 0x0228, + RATSR2 = AXIBMI + 0x022c, + RIDASM0 = AXIBMI + 0x0240, + RIDASAM0 = AXIBMI + 0x0244, + RIDACAM0 = AXIBMI + 0x0248, + EIS0 = AXIBMI + 0x0300, + EIE0 = AXIBMI + 0x0304, + EID0 = AXIBMI + 0x0308, + EIS1 = AXIBMI + 0x0310, + EIE1 = AXIBMI + 0x0314, + EID1 = AXIBMI + 0x0318, + TCEIS0 = AXIBMI + 0x0340, + TCEIE0 = AXIBMI + 0x0344, + TCEID0 = AXIBMI + 0x0348, + RFSEIS0 = AXIBMI + 0x04c0, + RFSEIE0 = AXIBMI + 0x04c4, + RFSEID0 = AXIBMI + 0x04c8, + RFEIS0 = AXIBMI + 0x0540, + RFEIE0 = AXIBMI + 0x0544, + RFEID0 = AXIBMI + 0x0548, + RCEIS0 = AXIBMI + 0x05c0, + RCEIE0 = AXIBMI + 0x05c4, + RCEID0 = AXIBMI + 0x05c8, + RIDAOIS = AXIBMI + 0x0640, + RIDAOIE = AXIBMI + 0x0644, + RIDAOID = AXIBMI + 0x0648, + TSFEIS = AXIBMI + 0x06c0, + TSFEIE = AXIBMI + 0x06c4, + TSFEID = AXIBMI + 0x06c8, + TSCEIS = AXIBMI + 0x06d0, + TSCEIE = AXIBMI + 0x06d4, + TSCEID = AXIBMI + 0x06d8, + DIS = AXIBMI + 0x0b00, + DIE = AXIBMI + 0x0b04, + DID = AXIBMI + 0x0b08, + TDIS0 = AXIBMI + 0x0b10, + TDIE0 = AXIBMI + 0x0b14, + TDID0 = AXIBMI + 0x0b18, + RDIS0 = AXIBMI + 0x0b90, + RDIE0 = AXIBMI + 0x0b94, + RDID0 = AXIBMI + 0x0b98, + TSDIS = AXIBMI + 0x0c10, + TSDIE = AXIBMI + 0x0c14, + TSDID = AXIBMI + 0x0c18, + GPOUT = AXIBMI + 0x6000, + + OCR = TSNMHD + 0x0000, + OSR = TSNMHD + 0x0004, + SWR = TSNMHD + 0x0008, + SIS = TSNMHD + 0x000c, + GIS = TSNMHD + 0x0010, + GIE = TSNMHD + 0x0014, + GID = TSNMHD + 0x0018, + TIS1 = TSNMHD + 0x0020, + TIE1 = TSNMHD + 0x0024, + TID1 = TSNMHD + 0x0028, + TIS2 = TSNMHD + 0x0030, + TIE2 = TSNMHD + 0x0034, + TID2 = TSNMHD + 0x0038, + RIS = TSNMHD + 0x0040, + RIE = TSNMHD + 0x0044, + RID = TSNMHD + 0x0048, + TGC1 = TSNMHD + 0x0050, + TGC2 = TSNMHD + 0x0054, + TFS0 = TSNMHD + 0x0060, + TCF0 = TSNMHD + 0x0070, + TCR1 = TSNMHD + 0x0080, + TCR2 = TSNMHD + 0x0084, + TCR3 = TSNMHD + 0x0088, + TCR4 = TSNMHD + 0x008c, + TMS0 = TSNMHD + 0x0090, + TSR1 = TSNMHD + 0x00b0, + TSR2 = TSNMHD + 0x00b4, + TSR3 = TSNMHD + 0x00b8, + TSR4 = TSNMHD + 0x00bc, + TSR5 = TSNMHD + 0x00c0, + RGC = TSNMHD + 0x00d0, + RDFCR = TSNMHD + 0x00d4, + RCFCR = TSNMHD + 0x00d8, + REFCNCR = TSNMHD + 0x00dc, + RSR1 = TSNMHD + 0x00e0, + RSR2 = TSNMHD + 0x00e4, + RSR3 = TSNMHD + 0x00e8, + TCIS = TSNMHD + 0x01e0, + TCIE = TSNMHD + 0x01e4, + TCID = TSNMHD + 0x01e8, + TPTPC = TSNMHD + 0x01f0, + TTML = TSNMHD + 0x01f4, + TTJ = TSNMHD + 0x01f8, + TCC = TSNMHD + 0x0200, + TCS = TSNMHD + 0x0204, + TGS = TSNMHD + 0x020c, + TACST0 = TSNMHD + 0x0210, + TACST1 = TSNMHD + 0x0214, + TACST2 = TSNMHD + 0x0218, + TALIT0 = TSNMHD + 0x0220, + TALIT1 = TSNMHD + 0x0224, + TALIT2 = TSNMHD + 0x0228, + TAEN0 = TSNMHD + 0x0230, + TAEN1 = TSNMHD + 0x0234, + TASFE = TSNMHD + 0x0240, + TACLL0 = TSNMHD + 0x0250, + TACLL1 = TSNMHD + 0x0254, + TACLL2 = TSNMHD + 0x0258, + CACC = TSNMHD + 0x0260, + CCS = TSNMHD + 0x0264, + CAIV0 = TSNMHD + 0x0270, + CAUL0 = TSNMHD + 0x0290, + TOCST0 = TSNMHD + 0x0300, + TOCST1 = TSNMHD + 0x0304, + TOCST2 = TSNMHD + 0x0308, + TOLIT0 = TSNMHD + 0x0310, + TOLIT1 = TSNMHD + 0x0314, + TOLIT2 = TSNMHD + 0x0318, + TOEN0 = TSNMHD + 0x0320, + TOEN1 = TSNMHD + 0x0324, + TOSFE = TSNMHD + 0x0330, + TCLR0 = TSNMHD + 0x0340, + TCLR1 = TSNMHD + 0x0344, + TCLR2 = TSNMHD + 0x0348, + TSMS = TSNMHD + 0x0350, + COCC = TSNMHD + 0x0360, + COIV0 = TSNMHD + 0x03b0, + COUL0 = TSNMHD + 0x03d0, + QSTMACU0 = TSNMHD + 0x0400, + QSTMACD0 = TSNMHD + 0x0404, + QSTMAMU0 = TSNMHD + 0x0408, + QSTMAMD0 = TSNMHD + 0x040c, + QSFTVL0 = TSNMHD + 0x0410, + QSFTVLM0 = TSNMHD + 0x0414, + QSFTMSD0 = TSNMHD + 0x0418, + QSFTGMI0 = TSNMHD + 0x041c, + QSFTLS = TSNMHD + 0x0600, + QSFTLIS = TSNMHD + 0x0604, + QSFTLIE = TSNMHD + 0x0608, + QSFTLID = TSNMHD + 0x060c, + QSMSMC = TSNMHD + 0x0610, + QSGTMC = TSNMHD + 0x0614, + QSEIS = TSNMHD + 0x0618, + QSEIE = TSNMHD + 0x061c, + QSEID = TSNMHD + 0x0620, + QGACST0 = TSNMHD + 0x0630, + QGACST1 = TSNMHD + 0x0634, + QGACST2 = TSNMHD + 0x0638, + QGALIT1 = TSNMHD + 0x0640, + QGALIT2 = TSNMHD + 0x0644, + QGAEN0 = TSNMHD + 0x0648, + QGAEN1 = TSNMHD + 0x074c, + QGIGS = TSNMHD + 0x0650, + QGGC = TSNMHD + 0x0654, + QGATL0 = TSNMHD + 0x0664, + QGATL1 = TSNMHD + 0x0668, + QGATL2 = TSNMHD + 0x066c, + QGOCST0 = TSNMHD + 0x0670, + QGOCST1 = TSNMHD + 0x0674, + QGOCST2 = TSNMHD + 0x0678, + QGOLIT0 = TSNMHD + 0x067c, + QGOLIT1 = TSNMHD + 0x0680, + QGOLIT2 = TSNMHD + 0x0684, + QGOEN0 = TSNMHD + 0x0688, + QGOEN1 = TSNMHD + 0x068c, + QGTRO = TSNMHD + 0x0690, + QGTR1 = TSNMHD + 0x0694, + QGTR2 = TSNMHD + 0x0698, + QGFSMS = TSNMHD + 0x069c, + QTMIS = TSNMHD + 0x06e0, + QTMIE = TSNMHD + 0x06e4, + QTMID = TSNMHD + 0x06e8, + QMEC = TSNMHD + 0x0700, + QMMC = TSNMHD + 0x0704, + QRFDC = TSNMHD + 0x0708, + QYFDC = TSNMHD + 0x070c, + QVTCMC0 = TSNMHD + 0x0710, + QMCBSC0 = TSNMHD + 0x0750, + QMCIRC0 = TSNMHD + 0x0790, + QMEBSC0 = TSNMHD + 0x07d0, + QMEIRC0 = TSNMHD + 0x0710, + QMCFC = TSNMHD + 0x0850, + QMEIS = TSNMHD + 0x0860, + QMEIE = TSNMHD + 0x0864, + QMEID = TSNMHD + 0x086c, + QSMFC0 = TSNMHD + 0x0870, + QMSPPC0 = TSNMHD + 0x08b0, + QMSRPC0 = TSNMHD + 0x08f0, + QGPPC0 = TSNMHD + 0x0930, + QGRPC0 = TSNMHD + 0x0950, + QMDPC0 = TSNMHD + 0x0970, + QMGPC0 = TSNMHD + 0x09b0, + QMYPC0 = TSNMHD + 0x09f0, + QMRPC0 = TSNMHD + 0x0a30, + MQSTMACU = TSNMHD + 0x0a70, + MQSTMACD = TSNMHD + 0x0a74, + MQSTMAMU = TSNMHD + 0x0a78, + MQSTMAMD = TSNMHD + 0x0a7c, + MQSFTVL = TSNMHD + 0x0a80, + MQSFTVLM = TSNMHD + 0x0a84, + MQSFTMSD = TSNMHD + 0x0a88, + MQSFTGMI = TSNMHD + 0x0a8c, + + CFCR0 = RMSO + 0x0800, + FMSCR = RMSO + 0x0c10, + + MMC = RMRO + 0x0000, + MPSM = RMRO + 0x0010, + MPIC = RMRO + 0x0014, + MTFFC = RMRO + 0x0020, + MTPFC = RMRO + 0x0024, + MTATC0 = RMRO + 0x0040, + MRGC = RMRO + 0x0080, + MRMAC0 = RMRO + 0x0084, + MRMAC1 = RMRO + 0x0088, + MRAFC = RMRO + 0x008c, + MRSCE = RMRO + 0x0090, + MRSCP = RMRO + 0x0094, + MRSCC = RMRO + 0x0098, + MRFSCE = RMRO + 0x009c, + MRFSCP = RMRO + 0x00a0, + MTRC = RMRO + 0x00a4, + MPFC = RMRO + 0x0100, + MLVC = RMRO + 0x0340, + MEEEC = RMRO + 0x0350, + MLBC = RMRO + 0x0360, + MGMR = RMRO + 0x0400, + MMPFTCT = RMRO + 0x0410, + MAPFTCT = RMRO + 0x0414, + MPFRCT = RMRO + 0x0418, + MFCICT = RMRO + 0x041c, + MEEECT = RMRO + 0x0420, + MEIS = RMRO + 0x0500, + MEIE = RMRO + 0x0504, + MEID = RMRO + 0x0508, + MMIS0 = RMRO + 0x0510, + MMIE0 = RMRO + 0x0514, + MMID0 = RMRO + 0x0518, + MMIS1 = RMRO + 0x0520, + MMIE1 = RMRO + 0x0524, + MMID1 = RMRO + 0x0528, + MMIS2 = RMRO + 0x0530, + MMIE2 = RMRO + 0x0534, + MMID2 = RMRO + 0x0538, + MXMS = RMRO + 0x0600, + +}; + +/* AXIBMI */ +#define RR_RATRR BIT(0) +#define RR_TATRR BIT(1) +#define RR_RST (RR_RATRR | RR_TATRR) +#define RR_RST_COMPLETE 0x03 + +#define AXIWC_DEFAULT 0xffff +#define AXIRC_DEFAULT 0xffff + +#define TATLS0_TEDE BIT(1) +#define TATLS0_TATEN_SHIFT 24 +#define TATLS0_TATEN(n) ((n) << TATLS0_TATEN_SHIFT) +#define TATLR_TATL BIT(31) + +#define RATLS0_RETS BIT(2) +#define RATLS0_REDE BIT(3) +#define RATLS0_RATEN_SHIFT 24 +#define RATLS0_RATEN(n) ((n) << RATLS0_RATEN_SHIFT) +#define RATLR_RATL BIT(31) + +#define DIE_DID_TDICX(n) BIT((n)) +#define DIE_DID_RDICX(n) BIT((n) + 8) +#define TDIE_TDID_TDX(n) BIT(n) +#define RDIE_RDID_RDX(n) BIT(n) +#define TDIS_TDS(n) BIT(n) +#define RDIS_RDS(n) BIT(n) + +/* MHD */ +#define OSR_OPS 0x07 +#define SWR_SWR BIT(0) + +#define TGC1_TQTM_SFM 0xff00 +#define TGC1_STTV_DEFAULT 0x03 + +#define TMS_MFS_MAX 0x2800 + +/* RMAC System */ +#define CFCR_SDID(n) ((n) << 16) +#define FMSCR_FMSIE(n) ((n) << 0) + +/* RMAC */ +#define MPIC_PIS_MASK GENMASK(1, 0) +#define MPIC_PIS_MII 0 +#define MPIC_PIS_RMII 0x01 +#define MPIC_PIS_GMII 0x02 +#define MPIC_PIS_RGMII 0x03 +#define MPIC_LSC_SHIFT 2 +#define MPIC_LSC_MASK GENMASK(3, MPIC_LSC_SHIFT) +#define MPIC_LSC_10M (0 << MPIC_LSC_SHIFT) +#define MPIC_LSC_100M (0x01 << MPIC_LSC_SHIFT) +#define MPIC_LSC_1G (0x02 << MPIC_LSC_SHIFT) +#define MPIC_PSMCS_SHIFT 16 +#define MPIC_PSMCS_MASK GENMASK(21, MPIC_PSMCS_SHIFT) +#define MPIC_PSMCS_DEFAULT (0x0a << MPIC_PSMCS_SHIFT) +#define MPIC_PSMHT_SHIFT 24 +#define MPIC_PSMHT_MASK GENMASK(26, MPIC_PSMHT_SHIFT) +#define MPIC_PSMHT_DEFAULT (0x07 << MPIC_PSMHT_SHIFT) + +#define MLVC_PASE BIT(8) +#define MLVC_PSE BIT(16) +#define MLVC_PLV BIT(17) + +#define MPSM_PSME BIT(0) +#define MPSM_PSMAD BIT(1) +#define MPSM_PDA_SHIFT 3 +#define MPSM_PDA_MASK GENMASK(7, 3) +#define MPSM_PDA(n) (((n) << MPSM_PDA_SHIFT) & MPSM_PDA_MASK) +#define MPSM_PRA_SHIFT 8 +#define MPSM_PRA_MASK GENMASK(12, 8) +#define MPSM_PRA(n) (((n) << MPSM_PRA_SHIFT) & MPSM_PRA_MASK) +#define MPSM_PRD_SHIFT 16 +#define MPSM_PRD_SET(n) ((n) << MPSM_PRD_SHIFT) +#define MPSM_PRD_GET(n) ((n) >> MPSM_PRD_SHIFT) + +#define GPOUT_RDM BIT(13) +#define GPOUT_TDM BIT(14) + +/* RTSN */ +#define RTSN_INTERVAL_US 1000 +#define RTSN_TIMEOUT_US 1000000 + +#define TX_NUM_CHAINS 1 +#define RX_NUM_CHAINS 1 + +#define TX_CHAIN_SIZE 1024 +#define RX_CHAIN_SIZE 1024 + +#define TX_CHAIN_IDX 0 +#define RX_CHAIN_IDX 0 + +#define TX_CHAIN_ADDR_OFFSET (sizeof(struct rtsn_desc) * TX_CHAIN_IDX) +#define RX_CHAIN_ADDR_OFFSET (sizeof(struct rtsn_desc) * RX_CHAIN_IDX) + +#define PKT_BUF_SZ 1584 +#define RTSN_ALIGN 128 + +enum rtsn_mode { + OCR_OPC_DISABLE, + OCR_OPC_CONFIG, + OCR_OPC_OPERATION, +}; + +/* Descriptors */ +enum RX_DS_CC_BIT { + RX_DS = 0x0fff, /* Data size */ + RX_TR = 0x1000, /* Truncation indication */ + RX_EI = 0x2000, /* Error indication */ + RX_PS = 0xc000, /* Padding selection */ +}; + +enum TX_FS_TAGL_BIT { + TX_DS = 0x0fff, /* Data size */ + TX_TAGL = 0xf000, /* Frame tag LSBs */ +}; + +enum DIE_DT { + /* HW/SW arbitration */ + DT_FEMPTY_IS = 0x10, + DT_FEMPTY_IC = 0x20, + DT_FEMPTY_ND = 0x30, + DT_FEMPTY = 0x40, + DT_FEMPTY_START = 0x50, + DT_FEMPTY_MID = 0x60, + DT_FEMPTY_END = 0x70, + + /* Frame data */ + DT_FSINGLE = 0x80, + DT_FSTART = 0x90, + DT_FMID = 0xa0, + DT_FEND = 0xb0, + + /* Chain control */ + DT_LEMPTY = 0xc0, + DT_EEMPTY = 0xd0, + DT_LINK = 0xe0, + DT_EOS = 0xf0, + + DT_MASK = 0xf0, + D_DIE = 0x08, +}; + +struct rtsn_desc { + __le16 info_ds; + __u8 info; + u8 die_dt; + __le32 dptr; +} __packed; + +struct rtsn_ts_desc { + __le16 info_ds; + __u8 info; + u8 die_dt; + __le32 dptr; + __le32 ts_nsec; + __le32 ts_sec; +} __packed; + +struct rtsn_ext_desc { + __le16 info_ds; + __u8 info; + u8 die_dt; + __le32 dptr; + __le64 info1; +} __packed; + +struct rtsn_ext_ts_desc { + __le16 info_ds; + __u8 info; + u8 die_dt; + __le32 dptr; + __le64 info1; + __le32 ts_nsec; + __le32 ts_sec; +} __packed; + +enum EXT_INFO_DS_BIT { + TXC = 0x4000, +}; + +#endif diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c index 9d140203e273..0d93164988fc 100644 --- a/drivers/net/ethernet/sfc/tc.c +++ b/drivers/net/ethernet/sfc/tc.c @@ -387,11 +387,8 @@ static int efx_tc_flower_parse_match(struct efx_nic *efx, struct flow_match_control fm; flow_rule_match_enc_control(rule, &fm); - if (fm.mask->flags) { - NL_SET_ERR_MSG_FMT_MOD(extack, "Unsupported match on enc_control.flags %#x", - fm.mask->flags); + if (flow_rule_has_enc_control_flags(fm.mask->flags, extack)) return -EOPNOTSUPP; - } if (!IS_ALL_ONES(fm.mask->addr_type)) { NL_SET_ERR_MSG_FMT_MOD(extack, "Unsupported enc addr_type mask %u (key %u)", fm.mask->addr_type, diff --git a/drivers/net/ethernet/smsc/smc9194.c b/drivers/net/ethernet/smsc/smc9194.c index af661c65ffe2..e2e7b1c68563 100644 --- a/drivers/net/ethernet/smsc/smc9194.c +++ b/drivers/net/ethernet/smsc/smc9194.c @@ -1501,6 +1501,7 @@ static void smc_set_multicast_list(struct net_device *dev) #ifdef MODULE static struct net_device *devSMC9194; +MODULE_DESCRIPTION("SMC 9194 Ethernet driver"); MODULE_LICENSE("GPL"); module_param_hw(io, int, ioport, 0); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 56649edb18cd..094d34c4193c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -443,6 +443,16 @@ static void common_default_data(struct plat_stmmacenet_data *plat) plat->rx_queues_cfg[0].pkt_route = 0x0; } +static struct phylink_pcs *intel_mgbe_select_pcs(struct stmmac_priv *priv, + phy_interface_t interface) +{ + /* plat->mdio_bus_data->has_xpcs has been set true, so there + * should always be an XPCS. The original code would always + * return this if present. + */ + return &priv->hw->xpcs->pcs; +} + static int intel_mgbe_common_data(struct pci_dev *pdev, struct plat_stmmacenet_data *plat) { @@ -587,6 +597,7 @@ static int intel_mgbe_common_data(struct pci_dev *pdev, plat->phy_interface == PHY_INTERFACE_MODE_1000BASEX) { plat->mdio_bus_data->has_xpcs = true; plat->mdio_bus_data->default_an_inband = true; + plat->select_pcs = intel_mgbe_select_pcs; } /* Ensure mdio bus scan skips intel serdes and pcs-xpcs */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index d9eed415b0b7..80eb72bc6311 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -93,6 +93,7 @@ struct ethqos_emac_driver_data { bool has_emac_ge_3; const char *link_clk_name; bool has_integrated_pcs; + u32 dma_addr_width; struct dwmac4_addrs dwmac4_addrs; }; @@ -276,6 +277,7 @@ static const struct ethqos_emac_driver_data emac_v4_0_0_data = { .has_emac_ge_3 = true, .link_clk_name = "phyaux", .has_integrated_pcs = true, + .dma_addr_width = 36, .dwmac4_addrs = { .dma_chan = 0x00008100, .dma_chan_offset = 0x1000, @@ -845,6 +847,8 @@ static int qcom_ethqos_probe(struct platform_device *pdev) plat_dat->flags |= STMMAC_FLAG_RX_CLK_RUNS_IN_LPI; if (data->has_integrated_pcs) plat_dat->flags |= STMMAC_FLAG_HAS_INTEGRATED_PCS; + if (data->dma_addr_width) + plat_dat->host_dma_width = data->dma_addr_width; if (ethqos->serdes_phy) { plat_dat->serdes_powerup = qcom_ethqos_serdes_powerup; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rzn1.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rzn1.c index 848cf3c01f4a..59a7bd560f96 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rzn1.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rzn1.c @@ -39,6 +39,12 @@ static void rzn1_dwmac_pcs_exit(struct stmmac_priv *priv) miic_destroy(priv->hw->phylink_pcs); } +static struct phylink_pcs *rzn1_dwmac_select_pcs(struct stmmac_priv *priv, + phy_interface_t interface) +{ + return priv->hw->phylink_pcs; +} + static int rzn1_dwmac_probe(struct platform_device *pdev) { struct plat_stmmacenet_data *plat_dat; @@ -57,6 +63,7 @@ static int rzn1_dwmac_probe(struct platform_device *pdev) plat_dat->bsp_priv = plat_dat; plat_dat->pcs_init = rzn1_dwmac_pcs_init; plat_dat->pcs_exit = rzn1_dwmac_pcs_exit; + plat_dat->select_pcs = rzn1_dwmac_select_pcs; ret = stmmac_dvr_probe(dev, plat_dat, &stmmac_res); if (ret) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index b3d45f9dfb55..fdb4c773ec98 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -429,6 +429,12 @@ static void socfpga_dwmac_pcs_exit(struct stmmac_priv *priv) lynx_pcs_destroy(priv->hw->phylink_pcs); } +static struct phylink_pcs *socfpga_dwmac_select_pcs(struct stmmac_priv *priv, + phy_interface_t interface) +{ + return priv->hw->phylink_pcs; +} + static int socfpga_dwmac_probe(struct platform_device *pdev) { struct plat_stmmacenet_data *plat_dat; @@ -478,6 +484,7 @@ static int socfpga_dwmac_probe(struct platform_device *pdev) plat_dat->fix_mac_speed = socfpga_dwmac_fix_mac_speed; plat_dat->pcs_init = socfpga_dwmac_pcs_init; plat_dat->pcs_exit = socfpga_dwmac_pcs_exit; + plat_dat->select_pcs = socfpga_dwmac_select_pcs; ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (ret) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c index c92dfc4ecf57..23cf0a5b047f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c @@ -53,12 +53,23 @@ #define SYSCFG_MCU_ETH_SEL_MII 0 #define SYSCFG_MCU_ETH_SEL_RMII 1 -/* STM32MP1 register definitions +/* STM32MP2 register definitions */ +#define SYSCFG_MP2_ETH_MASK GENMASK(31, 0) + +#define SYSCFG_ETHCR_ETH_PTP_CLK_SEL BIT(2) +#define SYSCFG_ETHCR_ETH_CLK_SEL BIT(1) +#define SYSCFG_ETHCR_ETH_REF_CLK_SEL BIT(0) + +#define SYSCFG_ETHCR_ETH_SEL_MII 0 +#define SYSCFG_ETHCR_ETH_SEL_RGMII BIT(4) +#define SYSCFG_ETHCR_ETH_SEL_RMII BIT(6) + +/* STM32MPx register definitions * * Below table summarizes the clock requirement and clock sources for * supported phy interface modes. * __________________________________________________________________________ - *|PHY_MODE | Normal | PHY wo crystal| PHY wo crystal |No 125Mhz from PHY| + *|PHY_MODE | Normal | PHY wo crystal| PHY wo crystal |No 125MHz from PHY| *| | | 25MHz | 50MHz | | * --------------------------------------------------------------------------- *| MII | - | eth-ck | n/a | n/a | @@ -90,6 +101,7 @@ struct stm32_dwmac { int eth_ref_clk_sel_reg; int irq_pwr_wakeup; u32 mode_reg; /* MAC glue-logic mode register */ + u32 mode_mask; struct regmap *regmap; u32 speed; const struct stm32_ops *ops; @@ -102,8 +114,9 @@ struct stm32_ops { void (*resume)(struct stm32_dwmac *dwmac); int (*parse_data)(struct stm32_dwmac *dwmac, struct device *dev); - u32 syscfg_eth_mask; bool clk_rx_enable_in_suspend; + bool is_mp13, is_mp2; + u32 syscfg_clr_off; }; static int stm32_dwmac_clk_enable(struct stm32_dwmac *dwmac, bool resume) @@ -157,65 +170,187 @@ static int stm32_dwmac_init(struct plat_stmmacenet_data *plat_dat, bool resume) return stm32_dwmac_clk_enable(dwmac, resume); } -static int stm32mp1_set_mode(struct plat_stmmacenet_data *plat_dat) +static int stm32mp1_select_ethck_external(struct plat_stmmacenet_data *plat_dat) { struct stm32_dwmac *dwmac = plat_dat->bsp_priv; - u32 reg = dwmac->mode_reg, clk_rate; - int val; - clk_rate = clk_get_rate(dwmac->clk_eth_ck); - dwmac->enable_eth_ck = false; switch (plat_dat->mac_interface) { case PHY_INTERFACE_MODE_MII: - if (clk_rate == ETH_CK_F_25M && dwmac->ext_phyclk) - dwmac->enable_eth_ck = true; - val = SYSCFG_PMCR_ETH_SEL_MII; - pr_debug("SYSCFG init : PHY_INTERFACE_MODE_MII\n"); + dwmac->enable_eth_ck = dwmac->ext_phyclk; + return 0; + case PHY_INTERFACE_MODE_GMII: + dwmac->enable_eth_ck = dwmac->eth_clk_sel_reg || + dwmac->ext_phyclk; + return 0; + case PHY_INTERFACE_MODE_RMII: + dwmac->enable_eth_ck = dwmac->eth_ref_clk_sel_reg || + dwmac->ext_phyclk; + return 0; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + dwmac->enable_eth_ck = dwmac->eth_clk_sel_reg || + dwmac->ext_phyclk; + return 0; + default: + dwmac->enable_eth_ck = false; + dev_err(dwmac->dev, "Mode %s not supported", + phy_modes(plat_dat->mac_interface)); + return -EINVAL; + } +} + +static int stm32mp1_validate_ethck_rate(struct plat_stmmacenet_data *plat_dat) +{ + struct stm32_dwmac *dwmac = plat_dat->bsp_priv; + const u32 clk_rate = clk_get_rate(dwmac->clk_eth_ck); + + switch (plat_dat->mac_interface) { + case PHY_INTERFACE_MODE_MII: + case PHY_INTERFACE_MODE_GMII: + if (clk_rate == ETH_CK_F_25M) + return 0; + break; + case PHY_INTERFACE_MODE_RMII: + if (clk_rate == ETH_CK_F_25M || clk_rate == ETH_CK_F_50M) + return 0; + break; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + if (clk_rate == ETH_CK_F_25M || clk_rate == ETH_CK_F_125M) + return 0; + break; + default: + break; + } + + dev_err(dwmac->dev, "Mode %s does not match eth-ck frequency %d Hz", + phy_modes(plat_dat->mac_interface), clk_rate); + return -EINVAL; +} + +static int stm32mp1_configure_pmcr(struct plat_stmmacenet_data *plat_dat) +{ + struct stm32_dwmac *dwmac = plat_dat->bsp_priv; + u32 reg = dwmac->mode_reg; + int val = 0; + + switch (plat_dat->mac_interface) { + case PHY_INTERFACE_MODE_MII: + /* + * STM32MP15xx supports both MII and GMII, STM32MP13xx MII only. + * SYSCFG_PMCSETR ETH_SELMII is present only on STM32MP15xx and + * acts as a selector between 0:GMII and 1:MII. As STM32MP13xx + * supports only MII, ETH_SELMII is not present. + */ + if (!dwmac->ops->is_mp13) /* Select MII mode on STM32MP15xx */ + val |= SYSCFG_PMCR_ETH_SEL_MII; break; case PHY_INTERFACE_MODE_GMII: val = SYSCFG_PMCR_ETH_SEL_GMII; - if (clk_rate == ETH_CK_F_25M && - (dwmac->eth_clk_sel_reg || dwmac->ext_phyclk)) { - dwmac->enable_eth_ck = true; + if (dwmac->enable_eth_ck) val |= SYSCFG_PMCR_ETH_CLK_SEL; - } - pr_debug("SYSCFG init : PHY_INTERFACE_MODE_GMII\n"); break; case PHY_INTERFACE_MODE_RMII: val = SYSCFG_PMCR_ETH_SEL_RMII; - if ((clk_rate == ETH_CK_F_25M || clk_rate == ETH_CK_F_50M) && - (dwmac->eth_ref_clk_sel_reg || dwmac->ext_phyclk)) { - dwmac->enable_eth_ck = true; + if (dwmac->enable_eth_ck) val |= SYSCFG_PMCR_ETH_REF_CLK_SEL; - } - pr_debug("SYSCFG init : PHY_INTERFACE_MODE_RMII\n"); break; case PHY_INTERFACE_MODE_RGMII: case PHY_INTERFACE_MODE_RGMII_ID: case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_TXID: val = SYSCFG_PMCR_ETH_SEL_RGMII; - if ((clk_rate == ETH_CK_F_25M || clk_rate == ETH_CK_F_125M) && - (dwmac->eth_clk_sel_reg || dwmac->ext_phyclk)) { - dwmac->enable_eth_ck = true; + if (dwmac->enable_eth_ck) val |= SYSCFG_PMCR_ETH_CLK_SEL; - } - pr_debug("SYSCFG init : PHY_INTERFACE_MODE_RGMII\n"); break; default: - pr_debug("SYSCFG init : Do not manage %d interface\n", - plat_dat->mac_interface); + dev_err(dwmac->dev, "Mode %s not supported", + phy_modes(plat_dat->mac_interface)); /* Do not manage others interfaces */ return -EINVAL; } + dev_dbg(dwmac->dev, "Mode %s", phy_modes(plat_dat->mac_interface)); + + /* Shift value at correct ethernet MAC offset in SYSCFG_PMCSETR */ + val <<= ffs(dwmac->mode_mask) - ffs(SYSCFG_MP1_ETH_MASK); + /* Need to update PMCCLRR (clear register) */ - regmap_write(dwmac->regmap, reg + SYSCFG_PMCCLRR_OFFSET, - dwmac->ops->syscfg_eth_mask); + regmap_write(dwmac->regmap, dwmac->ops->syscfg_clr_off, + dwmac->mode_mask); /* Update PMCSETR (set register) */ return regmap_update_bits(dwmac->regmap, reg, - dwmac->ops->syscfg_eth_mask, val); + dwmac->mode_mask, val); +} + +static int stm32mp2_configure_syscfg(struct plat_stmmacenet_data *plat_dat) +{ + struct stm32_dwmac *dwmac = plat_dat->bsp_priv; + u32 reg = dwmac->mode_reg; + int val = 0; + + switch (plat_dat->mac_interface) { + case PHY_INTERFACE_MODE_MII: + /* ETH_REF_CLK_SEL bit in SYSCFG register is not applicable in MII mode */ + break; + case PHY_INTERFACE_MODE_RMII: + val = SYSCFG_ETHCR_ETH_SEL_RMII; + if (dwmac->enable_eth_ck) { + /* Internal clock ETH_CLK of 50MHz from RCC is used */ + val |= SYSCFG_ETHCR_ETH_REF_CLK_SEL; + } + break; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + val = SYSCFG_ETHCR_ETH_SEL_RGMII; + fallthrough; + case PHY_INTERFACE_MODE_GMII: + if (dwmac->enable_eth_ck) { + /* Internal clock ETH_CLK of 125MHz from RCC is used */ + val |= SYSCFG_ETHCR_ETH_CLK_SEL; + } + break; + default: + dev_err(dwmac->dev, "Mode %s not supported", + phy_modes(plat_dat->mac_interface)); + /* Do not manage others interfaces */ + return -EINVAL; + } + + dev_dbg(dwmac->dev, "Mode %s", phy_modes(plat_dat->mac_interface)); + + /* Select PTP (IEEE1588) clock selection from RCC (ck_ker_ethxptp) */ + val |= SYSCFG_ETHCR_ETH_PTP_CLK_SEL; + + /* Update ETHCR (set register) */ + return regmap_update_bits(dwmac->regmap, reg, + SYSCFG_MP2_ETH_MASK, val); +} + +static int stm32mp1_set_mode(struct plat_stmmacenet_data *plat_dat) +{ + struct stm32_dwmac *dwmac = plat_dat->bsp_priv; + int ret; + + ret = stm32mp1_select_ethck_external(plat_dat); + if (ret) + return ret; + + ret = stm32mp1_validate_ethck_rate(plat_dat); + if (ret) + return ret; + + if (!dwmac->ops->is_mp2) + return stm32mp1_configure_pmcr(plat_dat); + else + return stm32mp2_configure_syscfg(plat_dat); } static int stm32mcu_set_mode(struct plat_stmmacenet_data *plat_dat) @@ -227,21 +362,21 @@ static int stm32mcu_set_mode(struct plat_stmmacenet_data *plat_dat) switch (plat_dat->mac_interface) { case PHY_INTERFACE_MODE_MII: val = SYSCFG_MCU_ETH_SEL_MII; - pr_debug("SYSCFG init : PHY_INTERFACE_MODE_MII\n"); break; case PHY_INTERFACE_MODE_RMII: val = SYSCFG_MCU_ETH_SEL_RMII; - pr_debug("SYSCFG init : PHY_INTERFACE_MODE_RMII\n"); break; default: - pr_debug("SYSCFG init : Do not manage %d interface\n", - plat_dat->mac_interface); + dev_err(dwmac->dev, "Mode %s not supported", + phy_modes(plat_dat->mac_interface)); /* Do not manage others interfaces */ return -EINVAL; } + dev_dbg(dwmac->dev, "Mode %s", phy_modes(plat_dat->mac_interface)); + return regmap_update_bits(dwmac->regmap, reg, - dwmac->ops->syscfg_eth_mask, val << 23); + SYSCFG_MCU_ETH_MASK, val << 23); } static void stm32_dwmac_clk_disable(struct stm32_dwmac *dwmac, bool suspend) @@ -286,8 +421,22 @@ static int stm32_dwmac_parse_data(struct stm32_dwmac *dwmac, return PTR_ERR(dwmac->regmap); err = of_property_read_u32_index(np, "st,syscon", 1, &dwmac->mode_reg); - if (err) + if (err) { dev_err(dev, "Can't get sysconfig mode offset (%d)\n", err); + return err; + } + + if (dwmac->ops->is_mp2) + return 0; + + dwmac->mode_mask = SYSCFG_MP1_ETH_MASK; + err = of_property_read_u32_index(np, "st,syscon", 2, &dwmac->mode_mask); + if (err) { + if (dwmac->ops->is_mp13) + dev_err(dev, "Sysconfig register mask must be set (%d)\n", err); + else + dev_dbg(dev, "Warning sysconfig register mask not set\n"); + } return err; } @@ -305,7 +454,7 @@ static int stm32mp1_parse_data(struct stm32_dwmac *dwmac, /* Gigabit Ethernet 125MHz clock selection. */ dwmac->eth_clk_sel_reg = of_property_read_bool(np, "st,eth-clk-sel"); - /* Ethernet 50Mhz RMII clock selection */ + /* Ethernet 50MHz RMII clock selection */ dwmac->eth_ref_clk_sel_reg = of_property_read_bool(np, "st,eth-ref-clk-sel"); @@ -478,8 +627,7 @@ static SIMPLE_DEV_PM_OPS(stm32_dwmac_pm_ops, stm32_dwmac_suspend, stm32_dwmac_resume); static struct stm32_ops stm32mcu_dwmac_data = { - .set_mode = stm32mcu_set_mode, - .syscfg_eth_mask = SYSCFG_MCU_ETH_MASK + .set_mode = stm32mcu_set_mode }; static struct stm32_ops stm32mp1_dwmac_data = { @@ -487,13 +635,35 @@ static struct stm32_ops stm32mp1_dwmac_data = { .suspend = stm32mp1_suspend, .resume = stm32mp1_resume, .parse_data = stm32mp1_parse_data, - .syscfg_eth_mask = SYSCFG_MP1_ETH_MASK, + .syscfg_clr_off = 0x44, + .is_mp13 = false, + .clk_rx_enable_in_suspend = true +}; + +static struct stm32_ops stm32mp13_dwmac_data = { + .set_mode = stm32mp1_set_mode, + .suspend = stm32mp1_suspend, + .resume = stm32mp1_resume, + .parse_data = stm32mp1_parse_data, + .syscfg_clr_off = 0x08, + .is_mp13 = true, + .clk_rx_enable_in_suspend = true +}; + +static struct stm32_ops stm32mp25_dwmac_data = { + .set_mode = stm32mp1_set_mode, + .suspend = stm32mp1_suspend, + .resume = stm32mp1_resume, + .parse_data = stm32mp1_parse_data, + .is_mp2 = true, .clk_rx_enable_in_suspend = true }; static const struct of_device_id stm32_dwmac_match[] = { { .compatible = "st,stm32-dwmac", .data = &stm32mcu_dwmac_data}, { .compatible = "st,stm32mp1-dwmac", .data = &stm32mp1_dwmac_data}, + { .compatible = "st,stm32mp13-dwmac", .data = &stm32mp13_dwmac_data}, + { .compatible = "st,stm32mp25-dwmac", .data = &stm32mp25_dwmac_data}, { } }; MODULE_DEVICE_TABLE(of, stm32_dwmac_match); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index f05bd757dfe5..5ef52ef2698f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -218,6 +218,7 @@ static void timestamp_interrupt(struct stmmac_priv *priv) { u32 num_snapshot, ts_status, tsync_int; struct ptp_clock_event event; + u32 acr_value, channel; unsigned long flags; u64 ptp_time; int i; @@ -243,12 +244,15 @@ static void timestamp_interrupt(struct stmmac_priv *priv) num_snapshot = (ts_status & GMAC_TIMESTAMP_ATSNS_MASK) >> GMAC_TIMESTAMP_ATSNS_SHIFT; + acr_value = readl(priv->ptpaddr + PTP_ACR); + channel = ilog2(FIELD_GET(PTP_ACR_MASK, acr_value)); + for (i = 0; i < num_snapshot; i++) { read_lock_irqsave(&priv->ptp_lock, flags); get_ptptime(priv->ptpaddr, &ptp_time); read_unlock_irqrestore(&priv->ptp_lock, flags); event.type = PTP_CLOCK_EXTTS; - event.index = 0; + event.index = channel; event.timestamp = ptp_time; ptp_clock_event(priv->ptp_clock, &event); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index bbedf2a8c60f..83b654b7a9fd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -949,11 +949,15 @@ static struct phylink_pcs *stmmac_mac_select_pcs(struct phylink_config *config, phy_interface_t interface) { struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); + struct phylink_pcs *pcs; - if (priv->hw->xpcs) - return &priv->hw->xpcs->pcs; + if (priv->plat->select_pcs) { + pcs = priv->plat->select_pcs(priv, interface); + if (!IS_ERR(pcs)) + return pcs; + } - return priv->hw->phylink_pcs; + return NULL; } static void stmmac_mac_config(struct phylink_config *config, unsigned int mode, @@ -4233,18 +4237,32 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) { struct dma_desc *desc, *first, *mss_desc = NULL; struct stmmac_priv *priv = netdev_priv(dev); - int nfrags = skb_shinfo(skb)->nr_frags; - u32 queue = skb_get_queue_mapping(skb); + int tmp_pay_len = 0, first_tx, nfrags; unsigned int first_entry, tx_packets; struct stmmac_txq_stats *txq_stats; - int tmp_pay_len = 0, first_tx; struct stmmac_tx_queue *tx_q; - bool has_vlan, set_ic; + u32 pay_len, mss, queue; u8 proto_hdr_len, hdr; - u32 pay_len, mss; dma_addr_t des; + bool set_ic; int i; + /* Always insert VLAN tag to SKB payload for TSO frames. + * + * Never insert VLAN tag by HW, since segments splited by + * TSO engine will be un-tagged by mistake. + */ + if (skb_vlan_tag_present(skb)) { + skb = __vlan_hwaccel_push_inside(skb); + if (unlikely(!skb)) { + priv->xstats.tx_dropped++; + return NETDEV_TX_OK; + } + } + + nfrags = skb_shinfo(skb)->nr_frags; + queue = skb_get_queue_mapping(skb); + tx_q = &priv->dma_conf.tx_queue[queue]; txq_stats = &priv->xstats.txq_stats[queue]; first_tx = tx_q->cur_tx; @@ -4297,9 +4315,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) skb->data_len); } - /* Check if VLAN can be inserted by HW */ - has_vlan = stmmac_vlan_insert(priv, skb, tx_q); - first_entry = tx_q->cur_tx; WARN_ON(tx_q->tx_skbuff[first_entry]); @@ -4309,9 +4324,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) desc = &tx_q->dma_tx[first_entry]; first = desc; - if (has_vlan) - stmmac_set_desc_vlan(priv, first, STMMAC_VLAN_INSERT); - /* first descriptor: fill Headers on Buf1 */ des = dma_map_single(priv->device, skb->data, skb_headlen(skb), DMA_TO_DEVICE); @@ -7678,8 +7690,6 @@ int stmmac_dvr_probe(struct device *device, ndev->features |= NETIF_F_RXHASH; ndev->vlan_features |= ndev->features; - /* TSO doesn't work on VLANs yet */ - ndev->vlan_features &= ~NETIF_F_TSO; /* MTU range: 46 - hw-specific max */ ndev->min_mtu = ETH_ZLEN - ETH_HLEN; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 54797edc9b38..ad868e8d195d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -764,8 +764,8 @@ EXPORT_SYMBOL_GPL(stmmac_get_platform_resources); * Description: Call the platform's init callback (if any) and propagate * the return value. */ -int stmmac_pltfr_init(struct platform_device *pdev, - struct plat_stmmacenet_data *plat) +static int stmmac_pltfr_init(struct platform_device *pdev, + struct plat_stmmacenet_data *plat) { int ret = 0; @@ -774,7 +774,6 @@ int stmmac_pltfr_init(struct platform_device *pdev, return ret; } -EXPORT_SYMBOL_GPL(stmmac_pltfr_init); /** * stmmac_pltfr_exit @@ -782,13 +781,12 @@ EXPORT_SYMBOL_GPL(stmmac_pltfr_init); * @plat: driver data platform structure * Description: Call the platform's exit callback (if any). */ -void stmmac_pltfr_exit(struct platform_device *pdev, - struct plat_stmmacenet_data *plat) +static void stmmac_pltfr_exit(struct platform_device *pdev, + struct plat_stmmacenet_data *plat) { if (plat->exit) plat->exit(pdev, plat->bsp_priv); } -EXPORT_SYMBOL_GPL(stmmac_pltfr_exit); /** * stmmac_pltfr_probe diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h index bb6fc7e59aed..72dc1a32e46d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h @@ -17,11 +17,6 @@ devm_stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac); int stmmac_get_platform_resources(struct platform_device *pdev, struct stmmac_resources *stmmac_res); -int stmmac_pltfr_init(struct platform_device *pdev, - struct plat_stmmacenet_data *plat); -void stmmac_pltfr_exit(struct platform_device *pdev, - struct plat_stmmacenet_data *plat); - int stmmac_pltfr_probe(struct platform_device *pdev, struct plat_stmmacenet_data *plat, struct stmmac_resources *res); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 222540b55480..996f2bcd07a2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -343,10 +343,11 @@ static int tc_setup_cbs(struct stmmac_priv *priv, struct tc_cbs_qopt_offload *qopt) { u32 tx_queues_count = priv->plat->tx_queues_to_use; + s64 port_transmit_rate_kbps; u32 queue = qopt->queue; - u32 ptr, speed_div; u32 mode_to_use; u64 value; + u32 ptr; int ret; /* Queue 0 is not AVB capable */ @@ -355,30 +356,30 @@ static int tc_setup_cbs(struct stmmac_priv *priv, if (!priv->dma_cap.av) return -EOPNOTSUPP; - /* Port Transmit Rate and Speed Divider */ - switch (priv->speed) { - case SPEED_10000: - ptr = 32; - speed_div = 10000000; - break; - case SPEED_5000: - ptr = 32; - speed_div = 5000000; - break; - case SPEED_2500: - ptr = 8; - speed_div = 2500000; - break; - case SPEED_1000: - ptr = 8; - speed_div = 1000000; - break; - case SPEED_100: - ptr = 4; - speed_div = 100000; - break; - default: - return -EOPNOTSUPP; + port_transmit_rate_kbps = qopt->idleslope - qopt->sendslope; + + if (qopt->enable) { + /* Port Transmit Rate and Speed Divider */ + switch (div_s64(port_transmit_rate_kbps, 1000)) { + case SPEED_10000: + case SPEED_5000: + ptr = 32; + break; + case SPEED_2500: + case SPEED_1000: + ptr = 8; + break; + case SPEED_100: + ptr = 4; + break; + default: + netdev_err(priv->dev, + "Invalid portTransmitRate %lld (idleSlope - sendSlope)\n", + port_transmit_rate_kbps); + return -EINVAL; + } + } else { + ptr = 0; } mode_to_use = priv->plat->tx_queues_cfg[queue].mode_to_use; @@ -398,10 +399,10 @@ static int tc_setup_cbs(struct stmmac_priv *priv, } /* Final adjustments for HW */ - value = div_s64(qopt->idleslope * 1024ll * ptr, speed_div); + value = div_s64(qopt->idleslope * 1024ll * ptr, port_transmit_rate_kbps); priv->plat->tx_queues_cfg[queue].idle_slope = value & GENMASK(31, 0); - value = div_s64(-qopt->sendslope * 1024ll * ptr, speed_div); + value = div_s64(-qopt->sendslope * 1024ll * ptr, port_transmit_rate_kbps); priv->plat->tx_queues_cfg[queue].send_slope = value & GENMASK(31, 0); value = qopt->hicredit * 1024ll * 8; diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c index f8e133604146..131786aa4d5b 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c @@ -21,8 +21,6 @@ #include "dwc-xlgmac.h" #include "dwc-xlgmac-reg.h" -MODULE_LICENSE("Dual BSD/GPL"); - static int debug = -1; module_param(debug, int, 0644); MODULE_PARM_DESC(debug, "DWC ethernet debug level (0=none,...,16=all)"); @@ -725,3 +723,8 @@ void xlgmac_print_all_hw_features(struct xlgmac_pdata *pdata) XLGMAC_PR("=====================================================\n"); XLGMAC_PR("\n"); } + +MODULE_DESCRIPTION(XLGMAC_DRV_DESC); +MODULE_VERSION(XLGMAC_DRV_VERSION); +MODULE_AUTHOR("Jie Deng <[email protected]>"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c index fa8604d7b797..36fe538e3332 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c @@ -71,8 +71,3 @@ static struct pci_driver xlgmac_pci_driver = { }; module_pci_driver(xlgmac_pci_driver); - -MODULE_DESCRIPTION(XLGMAC_DRV_DESC); -MODULE_VERSION(XLGMAC_DRV_VERSION); -MODULE_AUTHOR("Jie Deng <[email protected]>"); -MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/ethernet/tehuti/Kconfig b/drivers/net/ethernet/tehuti/Kconfig index 8735633765a1..6db2c9817445 100644 --- a/drivers/net/ethernet/tehuti/Kconfig +++ b/drivers/net/ethernet/tehuti/Kconfig @@ -23,4 +23,19 @@ config TEHUTI help Tehuti Networks 10G Ethernet NIC +config TEHUTI_TN40 + tristate "Tehuti Networks TN40xx 10G Ethernet adapters" + depends on PCI + select PAGE_POOL + select FW_LOADER + select PHYLINK + help + This driver supports 10G Ethernet adapters using Tehuti Networks + TN40xx chips. Currently, adapters with Applied Micro Circuits + Corporation QT2025 are supported; Tehuti Networks TN9310, + DLink DXE-810S, ASUS XG-C100F, and Edimax EN-9320. + + To compile this driver as a module, choose M here: the module + will be called tn40xx. + endif # NET_VENDOR_TEHUTI diff --git a/drivers/net/ethernet/tehuti/Makefile b/drivers/net/ethernet/tehuti/Makefile index 13a0ddd62088..0d4f4d63a65c 100644 --- a/drivers/net/ethernet/tehuti/Makefile +++ b/drivers/net/ethernet/tehuti/Makefile @@ -4,3 +4,6 @@ # obj-$(CONFIG_TEHUTI) += tehuti.o + +tn40xx-y := tn40.o tn40_mdio.o tn40_phy.o +obj-$(CONFIG_TEHUTI_TN40) += tn40xx.o diff --git a/drivers/net/ethernet/tehuti/tn40.c b/drivers/net/ethernet/tehuti/tn40.c new file mode 100644 index 000000000000..11db9fde11fe --- /dev/null +++ b/drivers/net/ethernet/tehuti/tn40.c @@ -0,0 +1,1786 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Copyright (c) Tehuti Networks Ltd. */ + +#include <linux/bitfield.h> +#include <linux/ethtool.h> +#include <linux/firmware.h> +#include <linux/if_vlan.h> +#include <linux/iopoll.h> +#include <linux/netdevice.h> +#include <linux/pci.h> +#include <linux/phylink.h> +#include <linux/vmalloc.h> +#include <net/page_pool/helpers.h> + +#include "tn40.h" + +#define TN40_SHORT_PACKET_SIZE 60 +#define TN40_FIRMWARE_NAME "tehuti/bdx.bin" + +static void tn40_enable_interrupts(struct tn40_priv *priv) +{ + tn40_write_reg(priv, TN40_REG_IMR, priv->isr_mask); +} + +static void tn40_disable_interrupts(struct tn40_priv *priv) +{ + tn40_write_reg(priv, TN40_REG_IMR, 0); +} + +static int tn40_fifo_alloc(struct tn40_priv *priv, struct tn40_fifo *f, + int fsz_type, + u16 reg_cfg0, u16 reg_cfg1, + u16 reg_rptr, u16 reg_wptr) +{ + u16 memsz = TN40_FIFO_SIZE * (1 << fsz_type); + u64 cfg_base; + + memset(f, 0, sizeof(struct tn40_fifo)); + /* 1K extra space is allocated at the end of the fifo to simplify + * processing of descriptors that wraps around fifo's end. + */ + f->va = dma_alloc_coherent(&priv->pdev->dev, + memsz + TN40_FIFO_EXTRA_SPACE, &f->da, + GFP_KERNEL); + if (!f->va) + return -ENOMEM; + + f->reg_cfg0 = reg_cfg0; + f->reg_cfg1 = reg_cfg1; + f->reg_rptr = reg_rptr; + f->reg_wptr = reg_wptr; + f->rptr = 0; + f->wptr = 0; + f->memsz = memsz; + f->size_mask = memsz - 1; + cfg_base = lower_32_bits((f->da & TN40_TX_RX_CFG0_BASE) | fsz_type); + tn40_write_reg(priv, reg_cfg0, cfg_base); + tn40_write_reg(priv, reg_cfg1, upper_32_bits(f->da)); + return 0; +} + +static void tn40_fifo_free(struct tn40_priv *priv, struct tn40_fifo *f) +{ + dma_free_coherent(&priv->pdev->dev, + f->memsz + TN40_FIFO_EXTRA_SPACE, f->va, f->da); +} + +static struct tn40_rxdb *tn40_rxdb_alloc(int nelem) +{ + size_t size = sizeof(struct tn40_rxdb) + (nelem * sizeof(int)) + + (nelem * sizeof(struct tn40_rx_map)); + struct tn40_rxdb *db; + int i; + + db = vzalloc(size); + if (db) { + db->stack = (int *)(db + 1); + db->elems = (void *)(db->stack + nelem); + db->nelem = nelem; + db->top = nelem; + /* make the first alloc close to db struct */ + for (i = 0; i < nelem; i++) + db->stack[i] = nelem - i - 1; + } + return db; +} + +static void tn40_rxdb_free(struct tn40_rxdb *db) +{ + vfree(db); +} + +static int tn40_rxdb_alloc_elem(struct tn40_rxdb *db) +{ + return db->stack[--db->top]; +} + +static void *tn40_rxdb_addr_elem(struct tn40_rxdb *db, unsigned int n) +{ + return db->elems + n; +} + +static int tn40_rxdb_available(struct tn40_rxdb *db) +{ + return db->top; +} + +static void tn40_rxdb_free_elem(struct tn40_rxdb *db, unsigned int n) +{ + db->stack[db->top++] = n; +} + +/** + * tn40_create_rx_ring - Initialize RX all related HW and SW resources + * @priv: NIC private structure + * + * create_rx_ring creates rxf and rxd fifos, updates the relevant HW registers, + * preallocates skbs for rx. It assumes that Rx is disabled in HW funcs are + * grouped for better cache usage + * + * RxD fifo is smaller then RxF fifo by design. Upon high load, RxD will be + * filled and packets will be dropped by the NIC without getting into the host + * or generating interrupts. In this situation the host has no chance of + * processing all the packets. Dropping packets by the NIC is cheaper, since it + * takes 0 CPU cycles. + * + * Return: 0 on success and negative value on error. + */ +static int tn40_create_rx_ring(struct tn40_priv *priv) +{ + struct page_pool_params pp = { + .dev = &priv->pdev->dev, + .napi = &priv->napi, + .dma_dir = DMA_FROM_DEVICE, + .netdev = priv->ndev, + .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, + .max_len = PAGE_SIZE, + }; + int ret, pkt_size, nr; + + priv->page_pool = page_pool_create(&pp); + if (IS_ERR(priv->page_pool)) + return PTR_ERR(priv->page_pool); + + ret = tn40_fifo_alloc(priv, &priv->rxd_fifo0.m, priv->rxd_size, + TN40_REG_RXD_CFG0_0, TN40_REG_RXD_CFG1_0, + TN40_REG_RXD_RPTR_0, TN40_REG_RXD_WPTR_0); + if (ret) + goto err_destroy_page_pool; + + ret = tn40_fifo_alloc(priv, &priv->rxf_fifo0.m, priv->rxf_size, + TN40_REG_RXF_CFG0_0, TN40_REG_RXF_CFG1_0, + TN40_REG_RXF_RPTR_0, TN40_REG_RXF_WPTR_0); + if (ret) + goto err_free_rxd; + + pkt_size = priv->ndev->mtu + VLAN_ETH_HLEN; + priv->rxf_fifo0.m.pktsz = pkt_size; + nr = priv->rxf_fifo0.m.memsz / sizeof(struct tn40_rxf_desc); + priv->rxdb0 = tn40_rxdb_alloc(nr); + if (!priv->rxdb0) { + ret = -ENOMEM; + goto err_free_rxf; + } + return 0; +err_free_rxf: + tn40_fifo_free(priv, &priv->rxf_fifo0.m); +err_free_rxd: + tn40_fifo_free(priv, &priv->rxd_fifo0.m); +err_destroy_page_pool: + page_pool_destroy(priv->page_pool); + return ret; +} + +static void tn40_rx_free_buffers(struct tn40_priv *priv) +{ + struct tn40_rxdb *db = priv->rxdb0; + struct tn40_rx_map *dm; + u16 i; + + netdev_dbg(priv->ndev, "total =%d free =%d busy =%d\n", db->nelem, + tn40_rxdb_available(db), + db->nelem - tn40_rxdb_available(db)); + + for (i = 0; i < db->nelem; i++) { + dm = tn40_rxdb_addr_elem(db, i); + if (dm->page) + page_pool_put_full_page(priv->page_pool, dm->page, + false); + } +} + +static void tn40_destroy_rx_ring(struct tn40_priv *priv) +{ + if (priv->rxdb0) { + tn40_rx_free_buffers(priv); + tn40_rxdb_free(priv->rxdb0); + priv->rxdb0 = NULL; + } + tn40_fifo_free(priv, &priv->rxf_fifo0.m); + tn40_fifo_free(priv, &priv->rxd_fifo0.m); + page_pool_destroy(priv->page_pool); +} + +static void tn40_set_rx_desc(struct tn40_priv *priv, int idx, u64 dma) +{ + struct tn40_rxf_fifo *f = &priv->rxf_fifo0; + struct tn40_rxf_desc *rxfd; + int delta; + + rxfd = (struct tn40_rxf_desc *)(f->m.va + f->m.wptr); + rxfd->info = cpu_to_le32(0x10003); /* INFO =1 BC =3 */ + rxfd->va_lo = cpu_to_le32(idx); + rxfd->pa_lo = cpu_to_le32(lower_32_bits(dma)); + rxfd->pa_hi = cpu_to_le32(upper_32_bits(dma)); + rxfd->len = cpu_to_le32(f->m.pktsz); + f->m.wptr += sizeof(struct tn40_rxf_desc); + delta = f->m.wptr - f->m.memsz; + if (unlikely(delta >= 0)) { + f->m.wptr = delta; + if (delta > 0) { + memcpy(f->m.va, f->m.va + f->m.memsz, delta); + netdev_dbg(priv->ndev, + "wrapped rxd descriptor\n"); + } + } +} + +/** + * tn40_rx_alloc_buffers - Fill rxf fifo with buffers. + * + * @priv: NIC's private structure + * + * rx_alloc_buffers allocates buffers via the page pool API, builds rxf descs + * and pushes them (rxf descr) into the rxf fifo. The pages are stored in rxdb. + * To calculate the free space, we uses the cached values of RPTR and WPTR + * when needed. This function also updates RPTR and WPTR. + */ +static void tn40_rx_alloc_buffers(struct tn40_priv *priv) +{ + struct tn40_rxf_fifo *f = &priv->rxf_fifo0; + struct tn40_rxdb *db = priv->rxdb0; + struct tn40_rx_map *dm; + struct page *page; + int dno, i, idx; + + dno = tn40_rxdb_available(db) - 1; + for (i = dno; i > 0; i--) { + page = page_pool_dev_alloc_pages(priv->page_pool); + if (!page) + break; + + idx = tn40_rxdb_alloc_elem(db); + tn40_set_rx_desc(priv, idx, page_pool_get_dma_addr(page)); + dm = tn40_rxdb_addr_elem(db, idx); + dm->page = page; + } + if (i != dno) + tn40_write_reg(priv, f->m.reg_wptr, + f->m.wptr & TN40_TXF_WPTR_WR_PTR); + netdev_dbg(priv->ndev, "write_reg 0x%04x f->m.reg_wptr 0x%x\n", + f->m.reg_wptr, f->m.wptr & TN40_TXF_WPTR_WR_PTR); + netdev_dbg(priv->ndev, "read_reg 0x%04x f->m.reg_rptr=0x%x\n", + f->m.reg_rptr, tn40_read_reg(priv, f->m.reg_rptr)); + netdev_dbg(priv->ndev, "write_reg 0x%04x f->m.reg_wptr=0x%x\n", + f->m.reg_wptr, tn40_read_reg(priv, f->m.reg_wptr)); +} + +static void tn40_recycle_rx_buffer(struct tn40_priv *priv, + struct tn40_rxd_desc *rxdd) +{ + struct tn40_rxf_fifo *f = &priv->rxf_fifo0; + struct tn40_rx_map *dm; + int idx; + + idx = le32_to_cpu(rxdd->va_lo); + dm = tn40_rxdb_addr_elem(priv->rxdb0, idx); + tn40_set_rx_desc(priv, idx, page_pool_get_dma_addr(dm->page)); + + tn40_write_reg(priv, f->m.reg_wptr, f->m.wptr & TN40_TXF_WPTR_WR_PTR); +} + +static int tn40_rx_receive(struct tn40_priv *priv, int budget) +{ + struct tn40_rxd_fifo *f = &priv->rxd_fifo0; + u32 rxd_val1, rxd_err, pkt_id; + int tmp_len, size, done = 0; + struct tn40_rxdb *db = NULL; + struct tn40_rxd_desc *rxdd; + struct tn40_rx_map *dm; + struct sk_buff *skb; + u16 len, rxd_vlan; + int idx; + + f->m.wptr = tn40_read_reg(priv, f->m.reg_wptr) & TN40_TXF_WPTR_WR_PTR; + size = f->m.wptr - f->m.rptr; + if (size < 0) + size += f->m.memsz; /* Size is negative :-) */ + + while (size > 0) { + rxdd = (struct tn40_rxd_desc *)(f->m.va + f->m.rptr); + db = priv->rxdb0; + + /* We have a chicken and egg problem here. If the + * descriptor is wrapped we first need to copy the tail + * of the descriptor to the end of the buffer before + * extracting values from the descriptor. However in + * order to know if the descriptor is wrapped we need to + * obtain the length of the descriptor from (the + * wrapped) descriptor. Luckily the length is the first + * word of the descriptor. Descriptor lengths are + * multiples of 8 bytes so in case of a wrapped + * descriptor the first 8 bytes guaranteed to appear + * before the end of the buffer. We first obtain the + * length, we then copy the rest of the descriptor if + * needed and then extract the rest of the values from + * the descriptor. + * + * Do not change the order of operations as it will + * break the code!!! + */ + rxd_val1 = le32_to_cpu(rxdd->rxd_val1); + tmp_len = TN40_GET_RXD_BC(rxd_val1) << 3; + pkt_id = TN40_GET_RXD_PKT_ID(rxd_val1); + size -= tmp_len; + /* CHECK FOR A PARTIALLY ARRIVED DESCRIPTOR */ + if (size < 0) { + netdev_dbg(priv->ndev, + "%s partially arrived desc tmp_len %d\n", + __func__, tmp_len); + break; + } + /* make sure that the descriptor fully is arrived + * before reading the rest of the descriptor. + */ + rmb(); + + /* A special treatment is given to non-contiguous + * descriptors that start near the end, wraps around + * and continue at the beginning. The second part is + * copied right after the first, and then descriptor + * is interpreted as normal. The fifo has an extra + * space to allow such operations. + */ + + /* HAVE WE REACHED THE END OF THE QUEUE? */ + f->m.rptr += tmp_len; + tmp_len = f->m.rptr - f->m.memsz; + if (unlikely(tmp_len >= 0)) { + f->m.rptr = tmp_len; + if (tmp_len > 0) { + /* COPY PARTIAL DESCRIPTOR + * TO THE END OF THE QUEUE + */ + netdev_dbg(priv->ndev, + "wrapped desc rptr=%d tmp_len=%d\n", + f->m.rptr, tmp_len); + memcpy(f->m.va + f->m.memsz, f->m.va, tmp_len); + } + } + idx = le32_to_cpu(rxdd->va_lo); + dm = tn40_rxdb_addr_elem(db, idx); + prefetch(dm); + + len = le16_to_cpu(rxdd->len); + rxd_vlan = le16_to_cpu(rxdd->rxd_vlan); + /* CHECK FOR ERRORS */ + rxd_err = TN40_GET_RXD_ERR(rxd_val1); + if (unlikely(rxd_err)) { + u64_stats_update_begin(&priv->syncp); + priv->stats.rx_errors++; + u64_stats_update_end(&priv->syncp); + tn40_recycle_rx_buffer(priv, rxdd); + continue; + } + + skb = napi_build_skb(page_address(dm->page), PAGE_SIZE); + if (!skb) { + u64_stats_update_begin(&priv->syncp); + priv->stats.rx_dropped++; + u64_stats_update_end(&priv->syncp); + tn40_recycle_rx_buffer(priv, rxdd); + break; + } + skb_mark_for_recycle(skb); + skb_put(skb, len); + skb->protocol = eth_type_trans(skb, priv->ndev); + skb->ip_summed = + (pkt_id == 0) ? CHECKSUM_NONE : CHECKSUM_UNNECESSARY; + if (TN40_GET_RXD_VTAG(rxd_val1)) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), + TN40_GET_RXD_VLAN_TCI(rxd_vlan)); + + dm->page = NULL; + tn40_rxdb_free_elem(db, idx); + + napi_gro_receive(&priv->napi, skb); + + u64_stats_update_begin(&priv->syncp); + priv->stats.rx_bytes += len; + u64_stats_update_end(&priv->syncp); + + if (unlikely(++done >= budget)) + break; + } + u64_stats_update_begin(&priv->syncp); + priv->stats.rx_packets += done; + u64_stats_update_end(&priv->syncp); + /* FIXME: Do something to minimize pci accesses */ + tn40_write_reg(priv, f->m.reg_rptr, f->m.rptr & TN40_TXF_WPTR_WR_PTR); + tn40_rx_alloc_buffers(priv); + return done; +} + +/* TX HW/SW interaction overview + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * There are 2 types of TX communication channels between driver and NIC. + * 1) TX Free Fifo - TXF - Holds ack descriptors for sent packets. + * 2) TX Data Fifo - TXD - Holds descriptors of full buffers. + * + * Currently the NIC supports TSO, checksumming and gather DMA + * UFO and IP fragmentation is on the way. + * + * RX SW Data Structures + * ~~~~~~~~~~~~~~~~~~~~~ + * TXDB is used to keep track of all skbs owned by SW and their DMA addresses. + * For TX case, ownership lasts from getting the packet via hard_xmit and + * until the HW acknowledges sending the packet by TXF descriptors. + * TXDB is implemented as a cyclic buffer. + * + * FIFO objects keep info about the fifo's size and location, relevant HW + * registers, usage and skb db. Each RXD and RXF fifo has their own fifo + * structure. Implemented as simple struct. + * + * TX SW Execution Flow + * ~~~~~~~~~~~~~~~~~~~~ + * OS calls the driver's hard_xmit method with a packet to send. The driver + * creates DMA mappings, builds TXD descriptors and kicks the HW by updating + * TXD WPTR. + * + * When a packet is sent, The HW write a TXF descriptor and the SW + * frees the original skb. To prevent TXD fifo overflow without + * reading HW registers every time, the SW deploys "tx level" + * technique. Upon startup, the tx level is initialized to TXD fifo + * length. For every sent packet, the SW gets its TXD descriptor size + * (from a pre-calculated array) and subtracts it from tx level. The + * size is also stored in txdb. When a TXF ack arrives, the SW fetched + * the size of the original TXD descriptor from the txdb and adds it + * to the tx level. When the Tx level drops below some predefined + * threshold, the driver stops the TX queue. When the TX level rises + * above that level, the tx queue is enabled again. + * + * This technique avoids excessive reading of RPTR and WPTR registers. + * As our benchmarks shows, it adds 1.5 Gbit/sec to NIC's throughput. + */ +static void tn40_do_tx_db_ptr_next(struct tn40_txdb *db, + struct tn40_tx_map **pptr) +{ + ++*pptr; + if (unlikely(*pptr == db->end)) + *pptr = db->start; +} + +static void tn40_tx_db_inc_rptr(struct tn40_txdb *db) +{ + tn40_do_tx_db_ptr_next(db, &db->rptr); +} + +static void tn40_tx_db_inc_wptr(struct tn40_txdb *db) +{ + tn40_do_tx_db_ptr_next(db, &db->wptr); +} + +static int tn40_tx_db_init(struct tn40_txdb *d, int sz_type) +{ + int memsz = TN40_FIFO_SIZE * (1 << (sz_type + 1)); + + d->start = vzalloc(memsz); + if (!d->start) + return -ENOMEM; + /* In order to differentiate between an empty db state and a full db + * state at least one element should always be empty in order to + * avoid rptr == wptr, which means that the db is empty. + */ + d->size = memsz / sizeof(struct tn40_tx_map) - 1; + d->end = d->start + d->size + 1; /* just after last element */ + + /* All dbs are created empty */ + d->rptr = d->start; + d->wptr = d->start; + return 0; +} + +static void tn40_tx_db_close(struct tn40_txdb *d) +{ + if (d->start) { + vfree(d->start); + d->start = NULL; + } +} + +/* Sizes of tx desc (including padding if needed) as function of the SKB's + * frag number + * 7 - is number of lwords in txd with one phys buffer + * 3 - is number of lwords used for every additional phys buffer + * for (i = 0; i < TN40_MAX_PBL; i++) { + * lwords = 7 + (i * 3); + * if (lwords & 1) + * lwords++; pad it with 1 lword + * tn40_txd_sizes[i].bytes = lwords << 2; + * tn40_txd_sizes[i].qwords = lwords >> 1; + * } + */ +static struct { + u16 bytes; + u16 qwords; /* qword = 64 bit */ +} tn40_txd_sizes[] = { + {0x20, 0x04}, + {0x28, 0x05}, + {0x38, 0x07}, + {0x40, 0x08}, + {0x50, 0x0a}, + {0x58, 0x0b}, + {0x68, 0x0d}, + {0x70, 0x0e}, + {0x80, 0x10}, + {0x88, 0x11}, + {0x98, 0x13}, + {0xa0, 0x14}, + {0xb0, 0x16}, + {0xb8, 0x17}, + {0xc8, 0x19}, + {0xd0, 0x1a}, + {0xe0, 0x1c}, + {0xe8, 0x1d}, + {0xf8, 0x1f}, +}; + +static void tn40_pbl_set(struct tn40_pbl *pbl, dma_addr_t dma, int len) +{ + pbl->len = cpu_to_le32(len); + pbl->pa_lo = cpu_to_le32(lower_32_bits(dma)); + pbl->pa_hi = cpu_to_le32(upper_32_bits(dma)); +} + +static void tn40_txdb_set(struct tn40_txdb *db, dma_addr_t dma, int len) +{ + db->wptr->len = len; + db->wptr->addr.dma = dma; +} + +struct tn40_mapping_info { + dma_addr_t dma; + size_t size; +}; + +/** + * tn40_tx_map_skb - create and store DMA mappings for skb's data blocks + * @priv: NIC private structure + * @skb: socket buffer to map + * @txdd: pointer to tx descriptor to be updated + * @pkt_len: pointer to unsigned long value + * + * This function creates DMA mappings for skb's data blocks and writes them to + * PBL of a new tx descriptor. It also stores them in the tx db, so they could + * be unmapped after the data has been sent. It is the responsibility of the + * caller to make sure that there is enough space in the txdb. The last + * element holds a pointer to skb itself and is marked with a zero length. + * + * Return: 0 on success and negative value on error. + */ +static int tn40_tx_map_skb(struct tn40_priv *priv, struct sk_buff *skb, + struct tn40_txd_desc *txdd, unsigned int *pkt_len) +{ + struct tn40_mapping_info info[TN40_MAX_PBL]; + int nr_frags = skb_shinfo(skb)->nr_frags; + struct tn40_pbl *pbl = &txdd->pbl[0]; + struct tn40_txdb *db = &priv->txdb; + unsigned int size; + int i, len, ret; + dma_addr_t dma; + + netdev_dbg(priv->ndev, "TX skb %p skbLen %d dataLen %d frags %d\n", skb, + skb->len, skb->data_len, nr_frags); + if (nr_frags > TN40_MAX_PBL - 1) { + ret = skb_linearize(skb); + if (ret) + return ret; + nr_frags = skb_shinfo(skb)->nr_frags; + } + /* initial skb */ + len = skb->len - skb->data_len; + dma = dma_map_single(&priv->pdev->dev, skb->data, len, + DMA_TO_DEVICE); + ret = dma_mapping_error(&priv->pdev->dev, dma); + if (ret) + return ret; + + tn40_txdb_set(db, dma, len); + tn40_pbl_set(pbl++, db->wptr->addr.dma, db->wptr->len); + *pkt_len = db->wptr->len; + + for (i = 0; i < nr_frags; i++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + + size = skb_frag_size(frag); + dma = skb_frag_dma_map(&priv->pdev->dev, frag, 0, + size, DMA_TO_DEVICE); + + ret = dma_mapping_error(&priv->pdev->dev, dma); + if (ret) + goto mapping_error; + info[i].dma = dma; + info[i].size = size; + } + + for (i = 0; i < nr_frags; i++) { + tn40_tx_db_inc_wptr(db); + tn40_txdb_set(db, info[i].dma, info[i].size); + tn40_pbl_set(pbl++, db->wptr->addr.dma, db->wptr->len); + *pkt_len += db->wptr->len; + } + + /* SHORT_PKT_FIX */ + if (skb->len < TN40_SHORT_PACKET_SIZE) + ++nr_frags; + + /* Add skb clean up info. */ + tn40_tx_db_inc_wptr(db); + db->wptr->len = -tn40_txd_sizes[nr_frags].bytes; + db->wptr->addr.skb = skb; + tn40_tx_db_inc_wptr(db); + + return 0; + mapping_error: + dma_unmap_page(&priv->pdev->dev, db->wptr->addr.dma, db->wptr->len, + DMA_TO_DEVICE); + for (; i > 0; i--) + dma_unmap_page(&priv->pdev->dev, info[i - 1].dma, + info[i - 1].size, DMA_TO_DEVICE); + return -ENOMEM; +} + +static int tn40_create_tx_ring(struct tn40_priv *priv) +{ + int ret; + + ret = tn40_fifo_alloc(priv, &priv->txd_fifo0.m, priv->txd_size, + TN40_REG_TXD_CFG0_0, TN40_REG_TXD_CFG1_0, + TN40_REG_TXD_RPTR_0, TN40_REG_TXD_WPTR_0); + if (ret) + return ret; + + ret = tn40_fifo_alloc(priv, &priv->txf_fifo0.m, priv->txf_size, + TN40_REG_TXF_CFG0_0, TN40_REG_TXF_CFG1_0, + TN40_REG_TXF_RPTR_0, TN40_REG_TXF_WPTR_0); + if (ret) + goto err_free_txd; + + /* The TX db has to keep mappings for all packets sent (on + * TxD) and not yet reclaimed (on TxF). + */ + ret = tn40_tx_db_init(&priv->txdb, max(priv->txd_size, priv->txf_size)); + if (ret) + goto err_free_txf; + + /* SHORT_PKT_FIX */ + priv->b0_len = 64; + priv->b0_va = dma_alloc_coherent(&priv->pdev->dev, priv->b0_len, + &priv->b0_dma, GFP_KERNEL); + if (!priv->b0_va) + goto err_free_db; + + priv->tx_level = TN40_MAX_TX_LEVEL; + priv->tx_update_mark = priv->tx_level - 1024; + return 0; +err_free_db: + tn40_tx_db_close(&priv->txdb); +err_free_txf: + tn40_fifo_free(priv, &priv->txf_fifo0.m); +err_free_txd: + tn40_fifo_free(priv, &priv->txd_fifo0.m); + return -ENOMEM; +} + +/** + * tn40_tx_space - Calculate the available space in the TX fifo. + * @priv: NIC private structure + * + * Return: available space in TX fifo in bytes + */ +static int tn40_tx_space(struct tn40_priv *priv) +{ + struct tn40_txd_fifo *f = &priv->txd_fifo0; + int fsize; + + f->m.rptr = tn40_read_reg(priv, f->m.reg_rptr) & TN40_TXF_WPTR_WR_PTR; + fsize = f->m.rptr - f->m.wptr; + if (fsize <= 0) + fsize = f->m.memsz + fsize; + return fsize; +} + +#define TN40_TXD_FULL_CHECKSUM 7 + +static netdev_tx_t tn40_start_xmit(struct sk_buff *skb, struct net_device *ndev) +{ + struct tn40_priv *priv = netdev_priv(ndev); + struct tn40_txd_fifo *f = &priv->txd_fifo0; + int txd_checksum = TN40_TXD_FULL_CHECKSUM; + struct tn40_txd_desc *txdd; + int nr_frags, len, err; + unsigned int pkt_len; + int txd_vlan_id = 0; + int txd_lgsnd = 0; + int txd_vtag = 0; + int txd_mss = 0; + + /* Build tx descriptor */ + txdd = (struct tn40_txd_desc *)(f->m.va + f->m.wptr); + err = tn40_tx_map_skb(priv, skb, txdd, &pkt_len); + if (err) { + u64_stats_update_begin(&priv->syncp); + priv->stats.tx_dropped++; + u64_stats_update_end(&priv->syncp); + dev_kfree_skb(skb); + return NETDEV_TX_OK; + } + nr_frags = skb_shinfo(skb)->nr_frags; + if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) + txd_checksum = 0; + + if (skb_shinfo(skb)->gso_size) { + txd_mss = skb_shinfo(skb)->gso_size; + txd_lgsnd = 1; + netdev_dbg(priv->ndev, "skb %p pkt len %d gso size = %d\n", skb, + pkt_len, txd_mss); + } + if (skb_vlan_tag_present(skb)) { + /* Don't cut VLAN ID to 12 bits */ + txd_vlan_id = skb_vlan_tag_get(skb); + txd_vtag = 1; + } + txdd->va_hi = 0; + txdd->va_lo = 0; + txdd->length = cpu_to_le16(pkt_len); + txdd->mss = cpu_to_le16(txd_mss); + txdd->txd_val1 = + cpu_to_le32(TN40_TXD_W1_VAL + (tn40_txd_sizes[nr_frags].qwords, txd_checksum, + txd_vtag, txd_lgsnd, txd_vlan_id)); + netdev_dbg(priv->ndev, "=== w1 qwords[%d] %d =====\n", nr_frags, + tn40_txd_sizes[nr_frags].qwords); + netdev_dbg(priv->ndev, "=== TxD desc =====================\n"); + netdev_dbg(priv->ndev, "=== w1: 0x%x ================\n", + txdd->txd_val1); + netdev_dbg(priv->ndev, "=== w2: mss 0x%x len 0x%x\n", txdd->mss, + txdd->length); + /* SHORT_PKT_FIX */ + if (pkt_len < TN40_SHORT_PACKET_SIZE) { + struct tn40_pbl *pbl = &txdd->pbl[++nr_frags]; + + txdd->length = cpu_to_le16(TN40_SHORT_PACKET_SIZE); + txdd->txd_val1 = + cpu_to_le32(TN40_TXD_W1_VAL + (tn40_txd_sizes[nr_frags].qwords, + txd_checksum, txd_vtag, txd_lgsnd, + txd_vlan_id)); + pbl->len = cpu_to_le32(TN40_SHORT_PACKET_SIZE - pkt_len); + pbl->pa_lo = cpu_to_le32(lower_32_bits(priv->b0_dma)); + pbl->pa_hi = cpu_to_le32(upper_32_bits(priv->b0_dma)); + netdev_dbg(priv->ndev, "=== SHORT_PKT_FIX ==============\n"); + netdev_dbg(priv->ndev, "=== nr_frags : %d ==============\n", + nr_frags); + } + + /* Increment TXD write pointer. In case of fifo wrapping copy + * reminder of the descriptor to the beginning. + */ + f->m.wptr += tn40_txd_sizes[nr_frags].bytes; + len = f->m.wptr - f->m.memsz; + if (unlikely(len >= 0)) { + f->m.wptr = len; + if (len > 0) + memcpy(f->m.va, f->m.va + f->m.memsz, len); + } + /* Force memory writes to complete before letting the HW know + * there are new descriptors to fetch. + */ + wmb(); + + priv->tx_level -= tn40_txd_sizes[nr_frags].bytes; + if (priv->tx_level > priv->tx_update_mark) { + tn40_write_reg(priv, f->m.reg_wptr, + f->m.wptr & TN40_TXF_WPTR_WR_PTR); + } else { + if (priv->tx_noupd++ > TN40_NO_UPD_PACKETS) { + priv->tx_noupd = 0; + tn40_write_reg(priv, f->m.reg_wptr, + f->m.wptr & TN40_TXF_WPTR_WR_PTR); + } + } + + u64_stats_update_begin(&priv->syncp); + priv->stats.tx_packets++; + priv->stats.tx_bytes += pkt_len; + u64_stats_update_end(&priv->syncp); + if (priv->tx_level < TN40_MIN_TX_LEVEL) { + netdev_dbg(priv->ndev, "TX Q STOP level %d\n", priv->tx_level); + netif_stop_queue(ndev); + } + + return NETDEV_TX_OK; +} + +static void tn40_tx_cleanup(struct tn40_priv *priv) +{ + struct tn40_txf_fifo *f = &priv->txf_fifo0; + struct tn40_txdb *db = &priv->txdb; + int tx_level = 0; + + f->m.wptr = tn40_read_reg(priv, f->m.reg_wptr) & TN40_TXF_WPTR_MASK; + + netif_tx_lock(priv->ndev); + while (f->m.wptr != f->m.rptr) { + f->m.rptr += TN40_TXF_DESC_SZ; + f->m.rptr &= f->m.size_mask; + /* Unmap all fragments */ + /* First has to come tx_maps containing DMA */ + do { + dma_addr_t addr = db->rptr->addr.dma; + size_t size = db->rptr->len; + + netif_tx_unlock(priv->ndev); + dma_unmap_page(&priv->pdev->dev, addr, + size, DMA_TO_DEVICE); + netif_tx_lock(priv->ndev); + tn40_tx_db_inc_rptr(db); + } while (db->rptr->len > 0); + tx_level -= db->rptr->len; /* '-' Because the len is negative */ + + /* Now should come skb pointer - free it */ + dev_kfree_skb_any(db->rptr->addr.skb); + netdev_dbg(priv->ndev, "dev_kfree_skb_any %p %d\n", + db->rptr->addr.skb, -db->rptr->len); + tn40_tx_db_inc_rptr(db); + } + + /* Let the HW know which TXF descriptors were cleaned */ + tn40_write_reg(priv, f->m.reg_rptr, f->m.rptr & TN40_TXF_WPTR_WR_PTR); + + /* We reclaimed resources, so in case the Q is stopped by xmit + * callback, we resume the transmission and use tx_lock to + * synchronize with xmit. + */ + priv->tx_level += tx_level; + if (priv->tx_noupd) { + priv->tx_noupd = 0; + tn40_write_reg(priv, priv->txd_fifo0.m.reg_wptr, + priv->txd_fifo0.m.wptr & TN40_TXF_WPTR_WR_PTR); + } + if (unlikely(netif_queue_stopped(priv->ndev) && + netif_carrier_ok(priv->ndev) && + (priv->tx_level >= TN40_MAX_TX_LEVEL / 2))) { + netdev_dbg(priv->ndev, "TX Q WAKE level %d\n", priv->tx_level); + netif_wake_queue(priv->ndev); + } + netif_tx_unlock(priv->ndev); +} + +static void tn40_tx_free_skbs(struct tn40_priv *priv) +{ + struct tn40_txdb *db = &priv->txdb; + + while (db->rptr != db->wptr) { + if (likely(db->rptr->len)) + dma_unmap_page(&priv->pdev->dev, db->rptr->addr.dma, + db->rptr->len, DMA_TO_DEVICE); + else + dev_kfree_skb(db->rptr->addr.skb); + tn40_tx_db_inc_rptr(db); + } +} + +static void tn40_destroy_tx_ring(struct tn40_priv *priv) +{ + tn40_tx_free_skbs(priv); + tn40_fifo_free(priv, &priv->txd_fifo0.m); + tn40_fifo_free(priv, &priv->txf_fifo0.m); + tn40_tx_db_close(&priv->txdb); + /* SHORT_PKT_FIX */ + if (priv->b0_len) { + dma_free_coherent(&priv->pdev->dev, priv->b0_len, priv->b0_va, + priv->b0_dma); + priv->b0_len = 0; + } +} + +/** + * tn40_tx_push_desc - Push a descriptor to TxD fifo. + * + * @priv: NIC private structure + * @data: desc's data + * @size: desc's size + * + * This function pushes desc to TxD fifo and overlaps it if needed. + * + * This function does not check for available space, nor does it check + * that the data size is smaller than the fifo size. Checking for + * space is the responsibility of the caller. + */ +static void tn40_tx_push_desc(struct tn40_priv *priv, void *data, int size) +{ + struct tn40_txd_fifo *f = &priv->txd_fifo0; + int i = f->m.memsz - f->m.wptr; + + if (size == 0) + return; + + if (i > size) { + memcpy(f->m.va + f->m.wptr, data, size); + f->m.wptr += size; + } else { + memcpy(f->m.va + f->m.wptr, data, i); + f->m.wptr = size - i; + memcpy(f->m.va, data + i, f->m.wptr); + } + tn40_write_reg(priv, f->m.reg_wptr, f->m.wptr & TN40_TXF_WPTR_WR_PTR); +} + +/** + * tn40_tx_push_desc_safe - push descriptor to TxD fifo in a safe way. + * + * @priv: NIC private structure + * @data: descriptor data + * @size: descriptor size + * + * This function does check for available space and, if necessary, + * waits for the NIC to read existing data before writing new data. + */ +static void tn40_tx_push_desc_safe(struct tn40_priv *priv, void *data, int size) +{ + int timer = 0; + + while (size > 0) { + /* We subtract 8 because when the fifo is full rptr == + * wptr, which also means that fifo is empty, we can + * understand the difference, but could the HW do the + * same ??? + */ + int avail = tn40_tx_space(priv) - 8; + + if (avail <= 0) { + if (timer++ > 300) /* Prevent endless loop */ + break; + /* Give the HW a chance to clean the fifo */ + usleep_range(50, 60); + continue; + } + avail = min(avail, size); + netdev_dbg(priv->ndev, + "about to push %d bytes starting %p size %d\n", + avail, data, size); + tn40_tx_push_desc(priv, data, avail); + size -= avail; + data += avail; + } +} + +int tn40_set_link_speed(struct tn40_priv *priv, u32 speed) +{ + u32 val; + int i; + + netdev_dbg(priv->ndev, "speed %d\n", speed); + switch (speed) { + case SPEED_10000: + case SPEED_5000: + case SPEED_2500: + netdev_dbg(priv->ndev, "link_speed %d\n", speed); + + tn40_write_reg(priv, 0x1010, 0x217); /*ETHSD.REFCLK_CONF */ + tn40_write_reg(priv, 0x104c, 0x4c); /*ETHSD.L0_RX_PCNT */ + tn40_write_reg(priv, 0x1050, 0x4c); /*ETHSD.L1_RX_PCNT */ + tn40_write_reg(priv, 0x1054, 0x4c); /*ETHSD.L2_RX_PCNT */ + tn40_write_reg(priv, 0x1058, 0x4c); /*ETHSD.L3_RX_PCNT */ + tn40_write_reg(priv, 0x102c, 0x434); /*ETHSD.L0_TX_PCNT */ + tn40_write_reg(priv, 0x1030, 0x434); /*ETHSD.L1_TX_PCNT */ + tn40_write_reg(priv, 0x1034, 0x434); /*ETHSD.L2_TX_PCNT */ + tn40_write_reg(priv, 0x1038, 0x434); /*ETHSD.L3_TX_PCNT */ + tn40_write_reg(priv, 0x6300, 0x0400); /*MAC.PCS_CTRL */ + + tn40_write_reg(priv, 0x1018, 0x00); /*Mike2 */ + udelay(5); + tn40_write_reg(priv, 0x1018, 0x04); /*Mike2 */ + udelay(5); + tn40_write_reg(priv, 0x1018, 0x06); /*Mike2 */ + udelay(5); + /*MikeFix1 */ + /*L0: 0x103c , L1: 0x1040 , L2: 0x1044 , L3: 0x1048 =0x81644 */ + tn40_write_reg(priv, 0x103c, 0x81644); /*ETHSD.L0_TX_DCNT */ + tn40_write_reg(priv, 0x1040, 0x81644); /*ETHSD.L1_TX_DCNT */ + tn40_write_reg(priv, 0x1044, 0x81644); /*ETHSD.L2_TX_DCNT */ + tn40_write_reg(priv, 0x1048, 0x81644); /*ETHSD.L3_TX_DCNT */ + tn40_write_reg(priv, 0x1014, 0x043); /*ETHSD.INIT_STAT */ + for (i = 1000; i; i--) { + usleep_range(50, 60); + /*ETHSD.INIT_STAT */ + val = tn40_read_reg(priv, 0x1014); + if (val & (1 << 9)) { + /*ETHSD.INIT_STAT */ + tn40_write_reg(priv, 0x1014, 0x3); + /*ETHSD.INIT_STAT */ + val = tn40_read_reg(priv, 0x1014); + + break; + } + } + if (!i) + netdev_err(priv->ndev, "MAC init timeout!\n"); + + tn40_write_reg(priv, 0x6350, 0x0); /*MAC.PCS_IF_MODE */ + tn40_write_reg(priv, TN40_REG_CTRLST, 0xC13); /*0x93//0x13 */ + tn40_write_reg(priv, 0x111c, 0x7ff); /*MAC.MAC_RST_CNT */ + usleep_range(2000, 2100); + + tn40_write_reg(priv, 0x111c, 0x0); /*MAC.MAC_RST_CNT */ + break; + + case SPEED_1000: + case SPEED_100: + tn40_write_reg(priv, 0x1010, 0x613); /*ETHSD.REFCLK_CONF */ + tn40_write_reg(priv, 0x104c, 0x4d); /*ETHSD.L0_RX_PCNT */ + tn40_write_reg(priv, 0x1050, 0x0); /*ETHSD.L1_RX_PCNT */ + tn40_write_reg(priv, 0x1054, 0x0); /*ETHSD.L2_RX_PCNT */ + tn40_write_reg(priv, 0x1058, 0x0); /*ETHSD.L3_RX_PCNT */ + tn40_write_reg(priv, 0x102c, 0x35); /*ETHSD.L0_TX_PCNT */ + tn40_write_reg(priv, 0x1030, 0x0); /*ETHSD.L1_TX_PCNT */ + tn40_write_reg(priv, 0x1034, 0x0); /*ETHSD.L2_TX_PCNT */ + tn40_write_reg(priv, 0x1038, 0x0); /*ETHSD.L3_TX_PCNT */ + tn40_write_reg(priv, 0x6300, 0x01140); /*MAC.PCS_CTRL */ + + tn40_write_reg(priv, 0x1014, 0x043); /*ETHSD.INIT_STAT */ + for (i = 1000; i; i--) { + usleep_range(50, 60); + val = tn40_read_reg(priv, 0x1014); /*ETHSD.INIT_STAT */ + if (val & (1 << 9)) { + /*ETHSD.INIT_STAT */ + tn40_write_reg(priv, 0x1014, 0x3); + /*ETHSD.INIT_STAT */ + val = tn40_read_reg(priv, 0x1014); + + break; + } + } + if (!i) + netdev_err(priv->ndev, "MAC init timeout!\n"); + + tn40_write_reg(priv, 0x6350, 0x2b); /*MAC.PCS_IF_MODE 1g */ + tn40_write_reg(priv, 0x6310, 0x9801); /*MAC.PCS_DEV_AB */ + + tn40_write_reg(priv, 0x6314, 0x1); /*MAC.PCS_PART_AB */ + tn40_write_reg(priv, 0x6348, 0xc8); /*MAC.PCS_LINK_LO */ + tn40_write_reg(priv, 0x634c, 0xc8); /*MAC.PCS_LINK_HI */ + usleep_range(50, 60); + tn40_write_reg(priv, TN40_REG_CTRLST, 0xC13); /*0x93//0x13 */ + tn40_write_reg(priv, 0x111c, 0x7ff); /*MAC.MAC_RST_CNT */ + usleep_range(2000, 2100); + + tn40_write_reg(priv, 0x111c, 0x0); /*MAC.MAC_RST_CNT */ + tn40_write_reg(priv, 0x6300, 0x1140); /*MAC.PCS_CTRL */ + break; + + case 0: /* Link down */ + tn40_write_reg(priv, 0x104c, 0x0); /*ETHSD.L0_RX_PCNT */ + tn40_write_reg(priv, 0x1050, 0x0); /*ETHSD.L1_RX_PCNT */ + tn40_write_reg(priv, 0x1054, 0x0); /*ETHSD.L2_RX_PCNT */ + tn40_write_reg(priv, 0x1058, 0x0); /*ETHSD.L3_RX_PCNT */ + tn40_write_reg(priv, 0x102c, 0x0); /*ETHSD.L0_TX_PCNT */ + tn40_write_reg(priv, 0x1030, 0x0); /*ETHSD.L1_TX_PCNT */ + tn40_write_reg(priv, 0x1034, 0x0); /*ETHSD.L2_TX_PCNT */ + tn40_write_reg(priv, 0x1038, 0x0); /*ETHSD.L3_TX_PCNT */ + + tn40_write_reg(priv, TN40_REG_CTRLST, 0x800); + tn40_write_reg(priv, 0x111c, 0x7ff); /*MAC.MAC_RST_CNT */ + usleep_range(2000, 2100); + + tn40_write_reg(priv, 0x111c, 0x0); /*MAC.MAC_RST_CNT */ + break; + + default: + netdev_err(priv->ndev, + "Link speed was not identified yet (%d)\n", speed); + speed = 0; + break; + } + return speed; +} + +static void tn40_link_changed(struct tn40_priv *priv) +{ + u32 link = tn40_read_reg(priv, + TN40_REG_MAC_LNK_STAT) & TN40_MAC_LINK_STAT; + + netdev_dbg(priv->ndev, "link changed %u\n", link); +} + +static void tn40_isr_extra(struct tn40_priv *priv, u32 isr) +{ + if (isr & (TN40_IR_LNKCHG0 | TN40_IR_LNKCHG1 | TN40_IR_TMR0)) { + netdev_dbg(priv->ndev, "isr = 0x%x\n", isr); + tn40_link_changed(priv); + } +} + +static irqreturn_t tn40_isr_napi(int irq, void *dev) +{ + struct tn40_priv *priv = netdev_priv((struct net_device *)dev); + u32 isr; + + isr = tn40_read_reg(priv, TN40_REG_ISR_MSK0); + + if (unlikely(!isr)) { + tn40_enable_interrupts(priv); + return IRQ_NONE; /* Not our interrupt */ + } + + if (isr & TN40_IR_EXTRA) + tn40_isr_extra(priv, isr); + + if (isr & (TN40_IR_RX_DESC_0 | TN40_IR_TX_FREE_0 | TN40_IR_TMR1)) { + if (likely(napi_schedule_prep(&priv->napi))) { + __napi_schedule(&priv->napi); + return IRQ_HANDLED; + } + /* We get here if an interrupt has slept into the + * small time window between these lines in + * tn40_poll: tn40_enable_interrupts(priv); return 0; + * + * Currently interrupts are disabled (since we read + * the ISR register) and we have failed to register + * the next poll. So we read the regs to trigger the + * chip and allow further interrupts. + */ + tn40_read_reg(priv, TN40_REG_TXF_WPTR_0); + tn40_read_reg(priv, TN40_REG_RXD_WPTR_0); + } + + tn40_enable_interrupts(priv); + return IRQ_HANDLED; +} + +static int tn40_poll(struct napi_struct *napi, int budget) +{ + struct tn40_priv *priv = container_of(napi, struct tn40_priv, napi); + int work_done; + + tn40_tx_cleanup(priv); + + if (!budget) + return 0; + + work_done = tn40_rx_receive(priv, budget); + if (work_done == budget) + return budget; + + if (napi_complete_done(napi, work_done)) + tn40_enable_interrupts(priv); + return work_done; +} + +static int tn40_fw_load(struct tn40_priv *priv) +{ + const struct firmware *fw = NULL; + int master, ret; + u32 val; + + ret = request_firmware(&fw, TN40_FIRMWARE_NAME, &priv->pdev->dev); + if (ret) + return ret; + + master = tn40_read_reg(priv, TN40_REG_INIT_SEMAPHORE); + if (!tn40_read_reg(priv, TN40_REG_INIT_STATUS) && master) { + netdev_dbg(priv->ndev, "Loading FW...\n"); + tn40_tx_push_desc_safe(priv, (void *)fw->data, fw->size); + msleep(100); + } + ret = read_poll_timeout(tn40_read_reg, val, val, 2000, 400000, false, + priv, TN40_REG_INIT_STATUS); + if (master) + tn40_write_reg(priv, TN40_REG_INIT_SEMAPHORE, 1); + + if (ret) { + netdev_err(priv->ndev, "firmware loading failed\n"); + netdev_dbg(priv->ndev, "VPC: 0x%x VIC: 0x%x STATUS: 0x%xd\n", + tn40_read_reg(priv, TN40_REG_VPC), + tn40_read_reg(priv, TN40_REG_VIC), + tn40_read_reg(priv, TN40_REG_INIT_STATUS)); + ret = -EIO; + } else { + netdev_dbg(priv->ndev, "firmware loading success\n"); + } + release_firmware(fw); + return ret; +} + +static void tn40_restore_mac(struct net_device *ndev, struct tn40_priv *priv) +{ + u32 val; + + netdev_dbg(priv->ndev, "mac0 =%x mac1 =%x mac2 =%x\n", + tn40_read_reg(priv, TN40_REG_UNC_MAC0_A), + tn40_read_reg(priv, TN40_REG_UNC_MAC1_A), + tn40_read_reg(priv, TN40_REG_UNC_MAC2_A)); + + val = (ndev->dev_addr[0] << 8) | (ndev->dev_addr[1]); + tn40_write_reg(priv, TN40_REG_UNC_MAC2_A, val); + val = (ndev->dev_addr[2] << 8) | (ndev->dev_addr[3]); + tn40_write_reg(priv, TN40_REG_UNC_MAC1_A, val); + val = (ndev->dev_addr[4] << 8) | (ndev->dev_addr[5]); + tn40_write_reg(priv, TN40_REG_UNC_MAC0_A, val); + + /* More then IP MAC address */ + tn40_write_reg(priv, TN40_REG_MAC_ADDR_0, + (ndev->dev_addr[3] << 24) | (ndev->dev_addr[2] << 16) | + (ndev->dev_addr[1] << 8) | (ndev->dev_addr[0])); + tn40_write_reg(priv, TN40_REG_MAC_ADDR_1, + (ndev->dev_addr[5] << 8) | (ndev->dev_addr[4])); + + netdev_dbg(priv->ndev, "mac0 =%x mac1 =%x mac2 =%x\n", + tn40_read_reg(priv, TN40_REG_UNC_MAC0_A), + tn40_read_reg(priv, TN40_REG_UNC_MAC1_A), + tn40_read_reg(priv, TN40_REG_UNC_MAC2_A)); +} + +static void tn40_hw_start(struct tn40_priv *priv) +{ + tn40_write_reg(priv, TN40_REG_FRM_LENGTH, 0X3FE0); + tn40_write_reg(priv, TN40_REG_GMAC_RXF_A, 0X10fd); + /*MikeFix1 */ + /*L0: 0x103c , L1: 0x1040 , L2: 0x1044 , L3: 0x1048 =0x81644 */ + tn40_write_reg(priv, 0x103c, 0x81644); /*ETHSD.L0_TX_DCNT */ + tn40_write_reg(priv, 0x1040, 0x81644); /*ETHSD.L1_TX_DCNT */ + tn40_write_reg(priv, 0x1044, 0x81644); /*ETHSD.L2_TX_DCNT */ + tn40_write_reg(priv, 0x1048, 0x81644); /*ETHSD.L3_TX_DCNT */ + tn40_write_reg(priv, TN40_REG_RX_FIFO_SECTION, 0x10); + tn40_write_reg(priv, TN40_REG_TX_FIFO_SECTION, 0xE00010); + tn40_write_reg(priv, TN40_REG_RX_FULLNESS, 0); + tn40_write_reg(priv, TN40_REG_TX_FULLNESS, 0); + + tn40_write_reg(priv, TN40_REG_VGLB, 0); + tn40_write_reg(priv, TN40_REG_MAX_FRAME_A, + priv->rxf_fifo0.m.pktsz & TN40_MAX_FRAME_AB_VAL); + tn40_write_reg(priv, TN40_REG_RDINTCM0, priv->rdintcm); + tn40_write_reg(priv, TN40_REG_RDINTCM2, 0); + + /* old val = 0x300064 */ + tn40_write_reg(priv, TN40_REG_TDINTCM0, priv->tdintcm); + + /* Enable timer interrupt once in 2 secs. */ + tn40_restore_mac(priv->ndev, priv); + + /* Pause frame */ + tn40_write_reg(priv, 0x12E0, 0x28); + tn40_write_reg(priv, TN40_REG_PAUSE_QUANT, 0xFFFF); + tn40_write_reg(priv, 0x6064, 0xF); + + tn40_write_reg(priv, TN40_REG_GMAC_RXF_A, + TN40_GMAC_RX_FILTER_OSEN | TN40_GMAC_RX_FILTER_TXFC | + TN40_GMAC_RX_FILTER_AM | TN40_GMAC_RX_FILTER_AB); + + tn40_enable_interrupts(priv); +} + +static int tn40_hw_reset(struct tn40_priv *priv) +{ + u32 val; + + /* Reset sequences: read, write 1, read, write 0 */ + val = tn40_read_reg(priv, TN40_REG_CLKPLL); + tn40_write_reg(priv, TN40_REG_CLKPLL, (val | TN40_CLKPLL_SFTRST) + 0x8); + usleep_range(50, 60); + val = tn40_read_reg(priv, TN40_REG_CLKPLL); + tn40_write_reg(priv, TN40_REG_CLKPLL, val & ~TN40_CLKPLL_SFTRST); + + /* Check that the PLLs are locked and reset ended */ + val = read_poll_timeout(tn40_read_reg, val, + (val & TN40_CLKPLL_LKD) == TN40_CLKPLL_LKD, + 10000, 700000, false, priv, TN40_REG_CLKPLL); + if (val) + return -EIO; + + usleep_range(50, 60); + /* Do any PCI-E read transaction */ + tn40_read_reg(priv, TN40_REG_RXD_CFG0_0); + return 0; +} + +static void tn40_sw_reset(struct tn40_priv *priv) +{ + int i, ret; + u32 val; + + /* 1. load MAC (obsolete) */ + /* 2. disable Rx (and Tx) */ + tn40_write_reg(priv, TN40_REG_GMAC_RXF_A, 0); + msleep(100); + /* 3. Disable port */ + tn40_write_reg(priv, TN40_REG_DIS_PORT, 1); + /* 4. Disable queue */ + tn40_write_reg(priv, TN40_REG_DIS_QU, 1); + /* 5. Wait until hw is disabled */ + ret = read_poll_timeout(tn40_read_reg, val, val & 1, 10000, 500000, + false, priv, TN40_REG_RST_PORT); + if (ret) + netdev_err(priv->ndev, "SW reset timeout. continuing anyway\n"); + + /* 6. Disable interrupts */ + tn40_write_reg(priv, TN40_REG_RDINTCM0, 0); + tn40_write_reg(priv, TN40_REG_TDINTCM0, 0); + tn40_write_reg(priv, TN40_REG_IMR, 0); + tn40_read_reg(priv, TN40_REG_ISR); + + /* 7. Reset queue */ + tn40_write_reg(priv, TN40_REG_RST_QU, 1); + /* 8. Reset port */ + tn40_write_reg(priv, TN40_REG_RST_PORT, 1); + /* 9. Zero all read and write pointers */ + for (i = TN40_REG_TXD_WPTR_0; i <= TN40_REG_TXF_RPTR_3; i += 0x10) + tn40_write_reg(priv, i, 0); + /* 10. Unset port disable */ + tn40_write_reg(priv, TN40_REG_DIS_PORT, 0); + /* 11. Unset queue disable */ + tn40_write_reg(priv, TN40_REG_DIS_QU, 0); + /* 12. Unset queue reset */ + tn40_write_reg(priv, TN40_REG_RST_QU, 0); + /* 13. Unset port reset */ + tn40_write_reg(priv, TN40_REG_RST_PORT, 0); + /* 14. Enable Rx */ + /* Skipped. will be done later */ +} + +static int tn40_start(struct tn40_priv *priv) +{ + int ret; + + ret = tn40_create_tx_ring(priv); + if (ret) { + netdev_err(priv->ndev, "failed to tx init %d\n", ret); + return ret; + } + + ret = tn40_create_rx_ring(priv); + if (ret) { + netdev_err(priv->ndev, "failed to rx init %d\n", ret); + goto err_tx_ring; + } + + tn40_rx_alloc_buffers(priv); + if (tn40_rxdb_available(priv->rxdb0) != 1) { + ret = -ENOMEM; + netdev_err(priv->ndev, "failed to allocate rx buffers\n"); + goto err_rx_ring; + } + + ret = request_irq(priv->pdev->irq, &tn40_isr_napi, IRQF_SHARED, + priv->ndev->name, priv->ndev); + if (ret) { + netdev_err(priv->ndev, "failed to request irq %d\n", ret); + goto err_rx_ring; + } + + tn40_hw_start(priv); + return 0; +err_rx_ring: + tn40_destroy_rx_ring(priv); +err_tx_ring: + tn40_destroy_tx_ring(priv); + return ret; +} + +static void tn40_stop(struct tn40_priv *priv) +{ + tn40_disable_interrupts(priv); + free_irq(priv->pdev->irq, priv->ndev); + tn40_sw_reset(priv); + tn40_destroy_tx_ring(priv); + tn40_destroy_rx_ring(priv); +} + +static int tn40_close(struct net_device *ndev) +{ + struct tn40_priv *priv = netdev_priv(ndev); + + phylink_stop(priv->phylink); + phylink_disconnect_phy(priv->phylink); + + napi_disable(&priv->napi); + netif_napi_del(&priv->napi); + tn40_stop(priv); + return 0; +} + +static int tn40_open(struct net_device *dev) +{ + struct tn40_priv *priv = netdev_priv(dev); + int ret; + + ret = phylink_connect_phy(priv->phylink, priv->phydev); + if (ret) { + netdev_err(dev, "failed to connect to phy %d\n", ret); + return ret; + } + tn40_sw_reset(priv); + ret = tn40_start(priv); + if (ret) { + phylink_disconnect_phy(priv->phylink); + netdev_err(dev, "failed to start %d\n", ret); + return ret; + } + napi_enable(&priv->napi); + phylink_start(priv->phylink); + netif_start_queue(priv->ndev); + return 0; +} + +static void __tn40_vlan_rx_vid(struct net_device *ndev, uint16_t vid, + int enable) +{ + struct tn40_priv *priv = netdev_priv(ndev); + u32 reg, bit, val; + + netdev_dbg(priv->ndev, "vid =%d value =%d\n", (int)vid, enable); + reg = TN40_REG_VLAN_0 + (vid / 32) * 4; + bit = 1 << vid % 32; + val = tn40_read_reg(priv, reg); + netdev_dbg(priv->ndev, "reg =%x, val =%x, bit =%d\n", reg, val, bit); + if (enable) + val |= bit; + else + val &= ~bit; + netdev_dbg(priv->ndev, "new val %x\n", val); + tn40_write_reg(priv, reg, val); +} + +static int tn40_vlan_rx_add_vid(struct net_device *ndev, + __always_unused __be16 proto, u16 vid) +{ + __tn40_vlan_rx_vid(ndev, vid, 1); + return 0; +} + +static int tn40_vlan_rx_kill_vid(struct net_device *ndev, + __always_unused __be16 proto, u16 vid) +{ + __tn40_vlan_rx_vid(ndev, vid, 0); + return 0; +} + +static void tn40_setmulti(struct net_device *ndev) +{ + u32 rxf_val = TN40_GMAC_RX_FILTER_AM | TN40_GMAC_RX_FILTER_AB | + TN40_GMAC_RX_FILTER_OSEN | TN40_GMAC_RX_FILTER_TXFC; + struct tn40_priv *priv = netdev_priv(ndev); + int i; + + /* IMF - imperfect (hash) rx multicast filter */ + /* PMF - perfect rx multicast filter */ + + /* FIXME: RXE(OFF) */ + if (ndev->flags & IFF_PROMISC) { + rxf_val |= TN40_GMAC_RX_FILTER_PRM; + } else if (ndev->flags & IFF_ALLMULTI) { + /* set IMF to accept all multicast frames */ + for (i = 0; i < TN40_MAC_MCST_HASH_NUM; i++) + tn40_write_reg(priv, + TN40_REG_RX_MCST_HASH0 + i * 4, ~0); + } else if (netdev_mc_count(ndev)) { + struct netdev_hw_addr *mclist; + u32 reg, val; + u8 hash; + + /* Set IMF to deny all multicast frames */ + for (i = 0; i < TN40_MAC_MCST_HASH_NUM; i++) + tn40_write_reg(priv, + TN40_REG_RX_MCST_HASH0 + i * 4, 0); + + /* Set PMF to deny all multicast frames */ + for (i = 0; i < TN40_MAC_MCST_NUM; i++) { + tn40_write_reg(priv, + TN40_REG_RX_MAC_MCST0 + i * 8, 0); + tn40_write_reg(priv, + TN40_REG_RX_MAC_MCST1 + i * 8, 0); + } + /* Use PMF to accept first MAC_MCST_NUM (15) addresses */ + + /* TBD: Sort the addresses and write them in ascending + * order into RX_MAC_MCST regs. we skip this phase now + * and accept ALL multicast frames through IMF. Accept + * the rest of addresses throw IMF. + */ + netdev_for_each_mc_addr(mclist, ndev) { + hash = 0; + for (i = 0; i < ETH_ALEN; i++) + hash ^= mclist->addr[i]; + + reg = TN40_REG_RX_MCST_HASH0 + ((hash >> 5) << 2); + val = tn40_read_reg(priv, reg); + val |= (1 << (hash % 32)); + tn40_write_reg(priv, reg, val); + } + } else { + rxf_val |= TN40_GMAC_RX_FILTER_AB; + } + tn40_write_reg(priv, TN40_REG_GMAC_RXF_A, rxf_val); + /* Enable RX */ + /* FIXME: RXE(ON) */ +} + +static int tn40_set_mac(struct net_device *ndev, void *p) +{ + struct tn40_priv *priv = netdev_priv(ndev); + struct sockaddr *addr = p; + + eth_hw_addr_set(ndev, addr->sa_data); + tn40_restore_mac(ndev, priv); + return 0; +} + +static void tn40_mac_init(struct tn40_priv *priv) +{ + u8 addr[ETH_ALEN]; + u64 val; + + val = (u64)tn40_read_reg(priv, TN40_REG_UNC_MAC0_A); + val |= (u64)tn40_read_reg(priv, TN40_REG_UNC_MAC1_A) << 16; + val |= (u64)tn40_read_reg(priv, TN40_REG_UNC_MAC2_A) << 32; + + u64_to_ether_addr(val, addr); + eth_hw_addr_set(priv->ndev, addr); +} + +static void tn40_get_stats(struct net_device *ndev, + struct rtnl_link_stats64 *stats) +{ + struct tn40_priv *priv = netdev_priv(ndev); + unsigned int start; + + do { + start = u64_stats_fetch_begin(&priv->syncp); + stats->tx_packets = priv->stats.tx_packets; + stats->tx_bytes = priv->stats.tx_bytes; + stats->tx_dropped = priv->stats.tx_dropped; + + stats->rx_packets = priv->stats.rx_packets; + stats->rx_bytes = priv->stats.rx_bytes; + stats->rx_dropped = priv->stats.rx_dropped; + stats->rx_errors = priv->stats.rx_errors; + } while (u64_stats_fetch_retry(&priv->syncp, start)); +} + +static const struct net_device_ops tn40_netdev_ops = { + .ndo_open = tn40_open, + .ndo_stop = tn40_close, + .ndo_start_xmit = tn40_start_xmit, + .ndo_validate_addr = eth_validate_addr, + .ndo_set_rx_mode = tn40_setmulti, + .ndo_get_stats64 = tn40_get_stats, + .ndo_set_mac_address = tn40_set_mac, + .ndo_vlan_rx_add_vid = tn40_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = tn40_vlan_rx_kill_vid, +}; + +static int tn40_priv_init(struct tn40_priv *priv) +{ + int ret; + + tn40_set_link_speed(priv, 0); + + /* Set GPIO[9:0] to output 0 */ + tn40_write_reg(priv, 0x51E0, 0x30010006); /* GPIO_OE_ WR CMD */ + tn40_write_reg(priv, 0x51F0, 0x0); /* GPIO_OE_ DATA */ + tn40_write_reg(priv, TN40_REG_MDIO_CMD_STAT, 0x3ec8); + + /* we use tx descriptors to load a firmware. */ + ret = tn40_create_tx_ring(priv); + if (ret) + return ret; + ret = tn40_fw_load(priv); + tn40_destroy_tx_ring(priv); + return ret; +} + +static struct net_device *tn40_netdev_alloc(struct pci_dev *pdev) +{ + struct net_device *ndev; + + ndev = devm_alloc_etherdev(&pdev->dev, sizeof(struct tn40_priv)); + if (!ndev) + return NULL; + ndev->netdev_ops = &tn40_netdev_ops; + ndev->tx_queue_len = TN40_NDEV_TXQ_LEN; + ndev->mem_start = pci_resource_start(pdev, 0); + ndev->mem_end = pci_resource_end(pdev, 0); + ndev->min_mtu = ETH_ZLEN; + ndev->max_mtu = TN40_MAX_MTU; + + ndev->features = NETIF_F_IP_CSUM | + NETIF_F_SG | + NETIF_F_FRAGLIST | + NETIF_F_TSO | NETIF_F_GRO | + NETIF_F_RXCSUM | + NETIF_F_RXHASH | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_FILTER; + ndev->vlan_features = NETIF_F_IP_CSUM | + NETIF_F_SG | + NETIF_F_TSO | NETIF_F_GRO | NETIF_F_RXHASH; + + if (dma_get_mask(&pdev->dev) == DMA_BIT_MASK(64)) { + ndev->features |= NETIF_F_HIGHDMA; + ndev->vlan_features |= NETIF_F_HIGHDMA; + } + ndev->hw_features |= ndev->features; + + SET_NETDEV_DEV(ndev, &pdev->dev); + netif_stop_queue(ndev); + return ndev; +} + +static int tn40_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +{ + struct net_device *ndev; + struct tn40_priv *priv; + unsigned int nvec = 1; + void __iomem *regs; + int ret; + + ret = pci_enable_device(pdev); + if (ret) + return ret; + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (ret) { + dev_err(&pdev->dev, "failed to set DMA mask.\n"); + goto err_disable_device; + } + + ret = pci_request_regions(pdev, TN40_DRV_NAME); + if (ret) { + dev_err(&pdev->dev, "failed to request PCI regions.\n"); + goto err_disable_device; + } + + pci_set_master(pdev); + + regs = pci_iomap(pdev, 0, TN40_REGS_SIZE); + if (!regs) { + ret = -EIO; + dev_err(&pdev->dev, "failed to map PCI bar.\n"); + goto err_free_regions; + } + + ndev = tn40_netdev_alloc(pdev); + if (!ndev) { + ret = -ENOMEM; + dev_err(&pdev->dev, "failed to allocate netdev.\n"); + goto err_iounmap; + } + + priv = netdev_priv(ndev); + pci_set_drvdata(pdev, priv); + netif_napi_add(ndev, &priv->napi, tn40_poll); + + priv->regs = regs; + priv->pdev = pdev; + priv->ndev = ndev; + /* Initialize fifo sizes. */ + priv->txd_size = 3; + priv->txf_size = 3; + priv->rxd_size = 3; + priv->rxf_size = 3; + /* Initialize the initial coalescing registers. */ + priv->rdintcm = TN40_INT_REG_VAL(0x20, 1, 4, 12); + priv->tdintcm = TN40_INT_REG_VAL(0x20, 1, 0, 12); + + ret = tn40_hw_reset(priv); + if (ret) { + dev_err(&pdev->dev, "failed to reset HW.\n"); + goto err_unset_drvdata; + } + + ret = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_MSI); + if (ret < 0) { + dev_err(&pdev->dev, "failed to allocate irq.\n"); + goto err_unset_drvdata; + } + + ret = tn40_mdiobus_init(priv); + if (ret) { + dev_err(&pdev->dev, "failed to initialize mdio bus.\n"); + goto err_free_irq; + } + + priv->stats_flag = + ((tn40_read_reg(priv, TN40_FPGA_VER) & 0xFFF) != 308); + u64_stats_init(&priv->syncp); + + priv->isr_mask = TN40_IR_RX_FREE_0 | TN40_IR_LNKCHG0 | TN40_IR_PSE | + TN40_IR_TMR0 | TN40_IR_RX_DESC_0 | TN40_IR_TX_FREE_0 | + TN40_IR_TMR1; + + tn40_mac_init(priv); + ret = tn40_phy_register(priv); + if (ret) { + dev_err(&pdev->dev, "failed to set up PHY.\n"); + goto err_free_irq; + } + + ret = tn40_priv_init(priv); + if (ret) { + dev_err(&pdev->dev, "failed to initialize tn40_priv.\n"); + goto err_unregister_phydev; + } + + ret = register_netdev(ndev); + if (ret) { + dev_err(&pdev->dev, "failed to register netdev.\n"); + goto err_unregister_phydev; + } + return 0; +err_unregister_phydev: + tn40_phy_unregister(priv); +err_free_irq: + pci_free_irq_vectors(pdev); +err_unset_drvdata: + pci_set_drvdata(pdev, NULL); +err_iounmap: + iounmap(regs); +err_free_regions: + pci_release_regions(pdev); +err_disable_device: + pci_disable_device(pdev); + return ret; +} + +static void tn40_remove(struct pci_dev *pdev) +{ + struct tn40_priv *priv = pci_get_drvdata(pdev); + struct net_device *ndev = priv->ndev; + + unregister_netdev(ndev); + + tn40_phy_unregister(priv); + pci_free_irq_vectors(priv->pdev); + pci_set_drvdata(pdev, NULL); + iounmap(priv->regs); + pci_release_regions(pdev); + pci_disable_device(pdev); +} + +static const struct pci_device_id tn40_id_table[] = { + { PCI_DEVICE_SUB(PCI_VENDOR_ID_TEHUTI, 0x4022, + PCI_VENDOR_ID_TEHUTI, 0x3015) }, + { PCI_DEVICE_SUB(PCI_VENDOR_ID_TEHUTI, 0x4022, + PCI_VENDOR_ID_DLINK, 0x4d00) }, + { PCI_DEVICE_SUB(PCI_VENDOR_ID_TEHUTI, 0x4022, + PCI_VENDOR_ID_ASUSTEK, 0x8709) }, + { PCI_DEVICE_SUB(PCI_VENDOR_ID_TEHUTI, 0x4022, + PCI_VENDOR_ID_EDIMAX, 0x8103) }, + { } +}; + +static struct pci_driver tn40_driver = { + .name = TN40_DRV_NAME, + .id_table = tn40_id_table, + .probe = tn40_probe, + .remove = tn40_remove, +}; + +module_pci_driver(tn40_driver); + +MODULE_DEVICE_TABLE(pci, tn40_id_table); +MODULE_LICENSE("GPL"); +MODULE_FIRMWARE(TN40_FIRMWARE_NAME); +MODULE_DESCRIPTION("Tehuti Network TN40xx Driver"); diff --git a/drivers/net/ethernet/tehuti/tn40.h b/drivers/net/ethernet/tehuti/tn40.h new file mode 100644 index 000000000000..10368264f7b7 --- /dev/null +++ b/drivers/net/ethernet/tehuti/tn40.h @@ -0,0 +1,232 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) Tehuti Networks Ltd. */ + +#ifndef _TN40_H_ +#define _TN40_H_ + +#include "tn40_regs.h" + +#define TN40_DRV_NAME "tn40xx" + +#define TN40_MDIO_SPEED_1MHZ (1) +#define TN40_MDIO_SPEED_6MHZ (6) + +/* netdev tx queue len for Luxor. The default value is 1000. + * ifconfig eth1 txqueuelen 3000 - to change it at runtime. + */ +#define TN40_NDEV_TXQ_LEN 1000 + +#define TN40_FIFO_SIZE 4096 +#define TN40_FIFO_EXTRA_SPACE 1024 + +#define TN40_TXF_DESC_SZ 16 +#define TN40_MAX_TX_LEVEL (priv->txd_fifo0.m.memsz - 16) +#define TN40_MIN_TX_LEVEL 256 +#define TN40_NO_UPD_PACKETS 40 +#define TN40_MAX_MTU BIT(14) + +#define TN40_PCK_TH_MULT 128 +#define TN40_INT_COAL_MULT 2 + +#define TN40_INT_REG_VAL(coal, coal_rc, rxf_th, pck_th) ( \ + FIELD_PREP(GENMASK(14, 0), (coal)) | \ + FIELD_PREP(BIT(15), (coal_rc)) | \ + FIELD_PREP(GENMASK(19, 16), (rxf_th)) | \ + FIELD_PREP(GENMASK(31, 20), (pck_th)) \ + ) + +struct tn40_fifo { + dma_addr_t da; /* Physical address of fifo (used by HW) */ + char *va; /* Virtual address of fifo (used by SW) */ + u32 rptr, wptr; + /* Cached values of RPTR and WPTR registers, + * they're 32 bits on both 32 and 64 archs. + */ + u16 reg_cfg0; + u16 reg_cfg1; + u16 reg_rptr; + u16 reg_wptr; + u16 memsz; /* Memory size allocated for fifo */ + u16 size_mask; + u16 pktsz; /* Skb packet size to allocate */ + u16 rcvno; /* Number of buffers that come from this RXF */ +}; + +struct tn40_txf_fifo { + struct tn40_fifo m; /* The minimal set of variables used by all fifos */ +}; + +struct tn40_txd_fifo { + struct tn40_fifo m; /* The minimal set of variables used by all fifos */ +}; + +struct tn40_rxf_fifo { + struct tn40_fifo m; /* The minimal set of variables used by all fifos */ +}; + +struct tn40_rxd_fifo { + struct tn40_fifo m; /* The minimal set of variables used by all fifos */ +}; + +struct tn40_rx_map { + struct page *page; +}; + +struct tn40_rxdb { + unsigned int *stack; + struct tn40_rx_map *elems; + unsigned int nelem; + unsigned int top; +}; + +union tn40_tx_dma_addr { + dma_addr_t dma; + struct sk_buff *skb; +}; + +/* Entry in the db. + * if len == 0 addr is dma + * if len != 0 addr is skb + */ +struct tn40_tx_map { + union tn40_tx_dma_addr addr; + int len; +}; + +/* tx database - implemented as circular fifo buffer */ +struct tn40_txdb { + struct tn40_tx_map *start; /* Points to the first element */ + struct tn40_tx_map *end; /* Points just AFTER the last element */ + struct tn40_tx_map *rptr; /* Points to the next element to read */ + struct tn40_tx_map *wptr; /* Points to the next element to write */ + int size; /* Number of elements in the db */ +}; + +struct tn40_priv { + struct net_device *ndev; + struct pci_dev *pdev; + + struct napi_struct napi; + /* RX FIFOs: 1 for data (full) descs, and 2 for free descs */ + struct tn40_rxd_fifo rxd_fifo0; + struct tn40_rxf_fifo rxf_fifo0; + struct tn40_rxdb *rxdb0; /* Rx dbs to store skb pointers */ + struct page_pool *page_pool; + + /* Tx FIFOs: 1 for data desc, 1 for empty (acks) desc */ + struct tn40_txd_fifo txd_fifo0; + struct tn40_txf_fifo txf_fifo0; + struct tn40_txdb txdb; + int tx_level; + int tx_update_mark; + int tx_noupd; + + int stats_flag; + struct rtnl_link_stats64 stats; + struct u64_stats_sync syncp; + + u8 txd_size; + u8 txf_size; + u8 rxd_size; + u8 rxf_size; + u32 rdintcm; + u32 tdintcm; + + u32 isr_mask; + + void __iomem *regs; + + /* SHORT_PKT_FIX */ + u32 b0_len; + dma_addr_t b0_dma; /* Physical address of buffer */ + char *b0_va; /* Virtual address of buffer */ + + struct mii_bus *mdio; + struct phy_device *phydev; + struct phylink *phylink; + struct phylink_config phylink_config; +}; + +/* RX FREE descriptor - 64bit */ +struct tn40_rxf_desc { + __le32 info; /* Buffer Count + Info - described below */ + __le32 va_lo; /* VAdr[31:0] */ + __le32 va_hi; /* VAdr[63:32] */ + __le32 pa_lo; /* PAdr[31:0] */ + __le32 pa_hi; /* PAdr[63:32] */ + __le32 len; /* Buffer Length */ +}; + +#define TN40_GET_RXD_BC(x) FIELD_GET(GENMASK(4, 0), (x)) +#define TN40_GET_RXD_ERR(x) FIELD_GET(GENMASK(26, 21), (x)) +#define TN40_GET_RXD_PKT_ID(x) FIELD_GET(GENMASK(30, 28), (x)) +#define TN40_GET_RXD_VTAG(x) FIELD_GET(BIT(31), (x)) +#define TN40_GET_RXD_VLAN_TCI(x) FIELD_GET(GENMASK(15, 0), (x)) + +struct tn40_rxd_desc { + __le32 rxd_val1; + __le16 len; + __le16 rxd_vlan; + __le32 va_lo; + __le32 va_hi; + __le32 rss_lo; + __le32 rss_hash; +}; + +#define TN40_MAX_PBL (19) +/* PBL describes each virtual buffer to be transmitted from the host. */ +struct tn40_pbl { + __le32 pa_lo; + __le32 pa_hi; + __le32 len; +}; + +/* First word for TXD descriptor. It means: type = 3 for regular Tx packet, + * hw_csum = 7 for IP+UDP+TCP HW checksums. + */ +#define TN40_TXD_W1_VAL(bc, checksum, vtag, lgsnd, vlan_id) ( \ + GENMASK(17, 16) | \ + FIELD_PREP(GENMASK(4, 0), (bc)) | \ + FIELD_PREP(GENMASK(7, 5), (checksum)) | \ + FIELD_PREP(BIT(8), (vtag)) | \ + FIELD_PREP(GENMASK(12, 9), (lgsnd)) | \ + FIELD_PREP(GENMASK(15, 13), \ + FIELD_GET(GENMASK(15, 13), (vlan_id))) | \ + FIELD_PREP(GENMASK(31, 20), \ + FIELD_GET(GENMASK(11, 0), (vlan_id))) \ + ) + +struct tn40_txd_desc { + __le32 txd_val1; + __le16 mss; + __le16 length; + __le32 va_lo; + __le32 va_hi; + struct tn40_pbl pbl[]; /* Fragments */ +}; + +struct tn40_txf_desc { + u32 status; + u32 va_lo; /* VAdr[31:0] */ + u32 va_hi; /* VAdr[63:32] */ + u32 pad; +}; + +static inline u32 tn40_read_reg(struct tn40_priv *priv, u32 reg) +{ + return readl(priv->regs + reg); +} + +static inline void tn40_write_reg(struct tn40_priv *priv, u32 reg, u32 val) +{ + writel(val, priv->regs + reg); +} + +int tn40_set_link_speed(struct tn40_priv *priv, u32 speed); + +int tn40_mdiobus_init(struct tn40_priv *priv); + +int tn40_phy_register(struct tn40_priv *priv); +void tn40_phy_unregister(struct tn40_priv *priv); + +#endif /* _TN40XX_H */ diff --git a/drivers/net/ethernet/tehuti/tn40_mdio.c b/drivers/net/ethernet/tehuti/tn40_mdio.c new file mode 100644 index 000000000000..af18615d64a8 --- /dev/null +++ b/drivers/net/ethernet/tehuti/tn40_mdio.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Copyright (c) Tehuti Networks Ltd. */ + +#include <linux/netdevice.h> +#include <linux/pci.h> +#include <linux/phylink.h> + +#include "tn40.h" + +#define TN40_MDIO_DEVAD_MASK GENMASK(4, 0) +#define TN40_MDIO_PRTAD_MASK GENMASK(9, 5) +#define TN40_MDIO_CMD_VAL(device, port) \ + (FIELD_PREP(TN40_MDIO_DEVAD_MASK, (device)) | \ + (FIELD_PREP(TN40_MDIO_PRTAD_MASK, (port)))) +#define TN40_MDIO_CMD_READ BIT(15) + +static void tn40_mdio_set_speed(struct tn40_priv *priv, u32 speed) +{ + void __iomem *regs = priv->regs; + int mdio_cfg; + + if (speed == TN40_MDIO_SPEED_1MHZ) + mdio_cfg = (0x7d << 7) | 0x08; /* 1MHz */ + else + mdio_cfg = 0xA08; /* 6MHz */ + mdio_cfg |= (1 << 6); + writel(mdio_cfg, regs + TN40_REG_MDIO_CMD_STAT); + msleep(100); +} + +static u32 tn40_mdio_stat(struct tn40_priv *priv) +{ + void __iomem *regs = priv->regs; + + return readl(regs + TN40_REG_MDIO_CMD_STAT); +} + +static int tn40_mdio_wait_nobusy(struct tn40_priv *priv, u32 *val) +{ + u32 stat; + int ret; + + ret = readx_poll_timeout_atomic(tn40_mdio_stat, priv, stat, + TN40_GET_MDIO_BUSY(stat) == 0, 10, + 10000); + if (val) + *val = stat; + return ret; +} + +static int tn40_mdio_read(struct tn40_priv *priv, int port, int device, + u16 regnum) +{ + void __iomem *regs = priv->regs; + u32 i; + + /* wait until MDIO is not busy */ + if (tn40_mdio_wait_nobusy(priv, NULL)) + return -EIO; + + i = TN40_MDIO_CMD_VAL(device, port); + writel(i, regs + TN40_REG_MDIO_CMD); + writel((u32)regnum, regs + TN40_REG_MDIO_ADDR); + if (tn40_mdio_wait_nobusy(priv, NULL)) + return -EIO; + + writel(TN40_MDIO_CMD_READ | i, regs + TN40_REG_MDIO_CMD); + /* read CMD_STAT until not busy */ + if (tn40_mdio_wait_nobusy(priv, NULL)) + return -EIO; + + return lower_16_bits(readl(regs + TN40_REG_MDIO_DATA)); +} + +static int tn40_mdio_write(struct tn40_priv *priv, int port, int device, + u16 regnum, u16 data) +{ + void __iomem *regs = priv->regs; + u32 tmp_reg = 0; + int ret; + + /* wait until MDIO is not busy */ + if (tn40_mdio_wait_nobusy(priv, NULL)) + return -EIO; + writel(TN40_MDIO_CMD_VAL(device, port), regs + TN40_REG_MDIO_CMD); + writel((u32)regnum, regs + TN40_REG_MDIO_ADDR); + if (tn40_mdio_wait_nobusy(priv, NULL)) + return -EIO; + writel((u32)data, regs + TN40_REG_MDIO_DATA); + /* read CMD_STAT until not busy */ + ret = tn40_mdio_wait_nobusy(priv, &tmp_reg); + if (ret) + return -EIO; + + if (TN40_GET_MDIO_RD_ERR(tmp_reg)) { + dev_err(&priv->pdev->dev, "MDIO error after write command\n"); + return -EIO; + } + return 0; +} + +static int tn40_mdio_read_c45(struct mii_bus *mii_bus, int addr, int devnum, + int regnum) +{ + return tn40_mdio_read(mii_bus->priv, addr, devnum, regnum); +} + +static int tn40_mdio_write_c45(struct mii_bus *mii_bus, int addr, int devnum, + int regnum, u16 val) +{ + return tn40_mdio_write(mii_bus->priv, addr, devnum, regnum, val); +} + +int tn40_mdiobus_init(struct tn40_priv *priv) +{ + struct pci_dev *pdev = priv->pdev; + struct mii_bus *bus; + int ret; + + bus = devm_mdiobus_alloc(&pdev->dev); + if (!bus) + return -ENOMEM; + + bus->name = TN40_DRV_NAME; + bus->parent = &pdev->dev; + snprintf(bus->id, MII_BUS_ID_SIZE, "tn40xx-%x-%x", + pci_domain_nr(pdev->bus), pci_dev_id(pdev)); + bus->priv = priv; + + bus->read_c45 = tn40_mdio_read_c45; + bus->write_c45 = tn40_mdio_write_c45; + + ret = devm_mdiobus_register(&pdev->dev, bus); + if (ret) { + dev_err(&pdev->dev, "failed to register mdiobus %d %u %u\n", + ret, bus->state, MDIOBUS_UNREGISTERED); + return ret; + } + tn40_mdio_set_speed(priv, TN40_MDIO_SPEED_6MHZ); + priv->mdio = bus; + return 0; +} diff --git a/drivers/net/ethernet/tehuti/tn40_phy.c b/drivers/net/ethernet/tehuti/tn40_phy.c new file mode 100644 index 000000000000..39eef7ca7958 --- /dev/null +++ b/drivers/net/ethernet/tehuti/tn40_phy.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Copyright (c) Tehuti Networks Ltd. */ + +#include <linux/netdevice.h> +#include <linux/pci.h> +#include <linux/phylink.h> + +#include "tn40.h" + +static struct tn40_priv *tn40_config_to_priv(struct phylink_config *config) +{ + return container_of(config, struct tn40_priv, phylink_config); +} + +static void tn40_link_up(struct phylink_config *config, struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, bool tx_pause, bool rx_pause) +{ + struct tn40_priv *priv = tn40_config_to_priv(config); + + tn40_set_link_speed(priv, speed); + netif_wake_queue(priv->ndev); +} + +static void tn40_link_down(struct phylink_config *config, unsigned int mode, + phy_interface_t interface) +{ + struct tn40_priv *priv = tn40_config_to_priv(config); + + netif_stop_queue(priv->ndev); + tn40_set_link_speed(priv, 0); +} + +static void tn40_mac_config(struct phylink_config *config, unsigned int mode, + const struct phylink_link_state *state) +{ +} + +static const struct phylink_mac_ops tn40_mac_ops = { + .mac_config = tn40_mac_config, + .mac_link_up = tn40_link_up, + .mac_link_down = tn40_link_down, +}; + +int tn40_phy_register(struct tn40_priv *priv) +{ + struct phylink_config *config; + struct phy_device *phydev; + struct phylink *phylink; + + phydev = phy_find_first(priv->mdio); + if (!phydev) { + dev_err(&priv->pdev->dev, "PHY isn't found\n"); + return -ENODEV; + } + + config = &priv->phylink_config; + config->dev = &priv->ndev->dev; + config->type = PHYLINK_NETDEV; + config->mac_capabilities = MAC_10000FD; + __set_bit(PHY_INTERFACE_MODE_XAUI, config->supported_interfaces); + + phylink = phylink_create(config, NULL, PHY_INTERFACE_MODE_XAUI, + &tn40_mac_ops); + if (IS_ERR(phylink)) + return PTR_ERR(phylink); + + priv->phydev = phydev; + priv->phylink = phylink; + return 0; +} + +void tn40_phy_unregister(struct tn40_priv *priv) +{ + phylink_destroy(priv->phylink); +} diff --git a/drivers/net/ethernet/tehuti/tn40_regs.h b/drivers/net/ethernet/tehuti/tn40_regs.h new file mode 100644 index 000000000000..95171aa57a9e --- /dev/null +++ b/drivers/net/ethernet/tehuti/tn40_regs.h @@ -0,0 +1,245 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) Tehuti Networks Ltd. */ + +#ifndef _TN40_REGS_H_ +#define _TN40_REGS_H_ + +/* Register region size */ +#define TN40_REGS_SIZE 0x10000 + +/* Registers from 0x0000-0x00fc were remapped to 0x4000-0x40fc */ +#define TN40_REG_TXD_CFG1_0 0x4000 +#define TN40_REG_TXD_CFG1_1 0x4004 +#define TN40_REG_TXD_CFG1_2 0x4008 +#define TN40_REG_TXD_CFG1_3 0x400C + +#define TN40_REG_RXF_CFG1_0 0x4010 +#define TN40_REG_RXF_CFG1_1 0x4014 +#define TN40_REG_RXF_CFG1_2 0x4018 +#define TN40_REG_RXF_CFG1_3 0x401C + +#define TN40_REG_RXD_CFG1_0 0x4020 +#define TN40_REG_RXD_CFG1_1 0x4024 +#define TN40_REG_RXD_CFG1_2 0x4028 +#define TN40_REG_RXD_CFG1_3 0x402C + +#define TN40_REG_TXF_CFG1_0 0x4030 +#define TN40_REG_TXF_CFG1_1 0x4034 +#define TN40_REG_TXF_CFG1_2 0x4038 +#define TN40_REG_TXF_CFG1_3 0x403C + +#define TN40_REG_TXD_CFG0_0 0x4040 +#define TN40_REG_TXD_CFG0_1 0x4044 +#define TN40_REG_TXD_CFG0_2 0x4048 +#define TN40_REG_TXD_CFG0_3 0x404C + +#define TN40_REG_RXF_CFG0_0 0x4050 +#define TN40_REG_RXF_CFG0_1 0x4054 +#define TN40_REG_RXF_CFG0_2 0x4058 +#define TN40_REG_RXF_CFG0_3 0x405C + +#define TN40_REG_RXD_CFG0_0 0x4060 +#define TN40_REG_RXD_CFG0_1 0x4064 +#define TN40_REG_RXD_CFG0_2 0x4068 +#define TN40_REG_RXD_CFG0_3 0x406C + +#define TN40_REG_TXF_CFG0_0 0x4070 +#define TN40_REG_TXF_CFG0_1 0x4074 +#define TN40_REG_TXF_CFG0_2 0x4078 +#define TN40_REG_TXF_CFG0_3 0x407C + +#define TN40_REG_TXD_WPTR_0 0x4080 +#define TN40_REG_TXD_WPTR_1 0x4084 +#define TN40_REG_TXD_WPTR_2 0x4088 +#define TN40_REG_TXD_WPTR_3 0x408C + +#define TN40_REG_RXF_WPTR_0 0x4090 +#define TN40_REG_RXF_WPTR_1 0x4094 +#define TN40_REG_RXF_WPTR_2 0x4098 +#define TN40_REG_RXF_WPTR_3 0x409C + +#define TN40_REG_RXD_WPTR_0 0x40A0 +#define TN40_REG_RXD_WPTR_1 0x40A4 +#define TN40_REG_RXD_WPTR_2 0x40A8 +#define TN40_REG_RXD_WPTR_3 0x40AC + +#define TN40_REG_TXF_WPTR_0 0x40B0 +#define TN40_REG_TXF_WPTR_1 0x40B4 +#define TN40_REG_TXF_WPTR_2 0x40B8 +#define TN40_REG_TXF_WPTR_3 0x40BC + +#define TN40_REG_TXD_RPTR_0 0x40C0 +#define TN40_REG_TXD_RPTR_1 0x40C4 +#define TN40_REG_TXD_RPTR_2 0x40C8 +#define TN40_REG_TXD_RPTR_3 0x40CC + +#define TN40_REG_RXF_RPTR_0 0x40D0 +#define TN40_REG_RXF_RPTR_1 0x40D4 +#define TN40_REG_RXF_RPTR_2 0x40D8 +#define TN40_REG_RXF_RPTR_3 0x40DC + +#define TN40_REG_RXD_RPTR_0 0x40E0 +#define TN40_REG_RXD_RPTR_1 0x40E4 +#define TN40_REG_RXD_RPTR_2 0x40E8 +#define TN40_REG_RXD_RPTR_3 0x40EC + +#define TN40_REG_TXF_RPTR_0 0x40F0 +#define TN40_REG_TXF_RPTR_1 0x40F4 +#define TN40_REG_TXF_RPTR_2 0x40F8 +#define TN40_REG_TXF_RPTR_3 0x40FC + +/* Hardware versioning */ +#define TN40_FPGA_VER 0x5030 + +/* Registers from 0x0100-0x0150 were remapped to 0x5100-0x5150 */ +#define TN40_REG_ISR TN40_REG_ISR0 +#define TN40_REG_ISR0 0x5100 + +#define TN40_REG_IMR TN40_REG_IMR0 +#define TN40_REG_IMR0 0x5110 + +#define TN40_REG_RDINTCM0 0x5120 +#define TN40_REG_RDINTCM2 0x5128 + +#define TN40_REG_TDINTCM0 0x5130 + +#define TN40_REG_ISR_MSK0 0x5140 + +#define TN40_REG_INIT_SEMAPHORE 0x5170 +#define TN40_REG_INIT_STATUS 0x5180 + +#define TN40_REG_MAC_LNK_STAT 0x0200 +#define TN40_MAC_LINK_STAT 0x0004 /* Link state */ + +#define TN40_REG_BLNK_LED 0x0210 + +#define TN40_REG_GMAC_RXF_A 0x1240 + +#define TN40_REG_UNC_MAC0_A 0x1250 +#define TN40_REG_UNC_MAC1_A 0x1260 +#define TN40_REG_UNC_MAC2_A 0x1270 + +#define TN40_REG_VLAN_0 0x1800 + +#define TN40_REG_MAX_FRAME_A 0x12C0 + +#define TN40_REG_RX_MAC_MCST0 0x1A80 +#define TN40_REG_RX_MAC_MCST1 0x1A84 +#define TN40_MAC_MCST_NUM 15 +#define TN40_REG_RX_MCST_HASH0 0x1A00 +#define TN40_MAC_MCST_HASH_NUM 8 + +#define TN40_REG_VPC 0x2300 +#define TN40_REG_VIC 0x2320 +#define TN40_REG_VGLB 0x2340 + +#define TN40_REG_CLKPLL 0x5000 + +/* MDIO interface */ + +#define TN40_REG_MDIO_CMD_STAT 0x6030 +#define TN40_REG_MDIO_CMD 0x6034 +#define TN40_REG_MDIO_DATA 0x6038 +#define TN40_REG_MDIO_ADDR 0x603C +#define TN40_GET_MDIO_BUSY(x) FIELD_GET(GENMASK(0, 0), (x)) +#define TN40_GET_MDIO_RD_ERR(x) FIELD_GET(GENMASK(1, 1), (x)) + +#define TN40_REG_REVISION 0x6000 +#define TN40_REG_SCRATCH 0x6004 +#define TN40_REG_CTRLST 0x6008 +#define TN40_REG_MAC_ADDR_0 0x600C +#define TN40_REG_MAC_ADDR_1 0x6010 +#define TN40_REG_FRM_LENGTH 0x6014 +#define TN40_REG_PAUSE_QUANT 0x6054 +#define TN40_REG_RX_FIFO_SECTION 0x601C +#define TN40_REG_TX_FIFO_SECTION 0x6020 +#define TN40_REG_RX_FULLNESS 0x6024 +#define TN40_REG_TX_FULLNESS 0x6028 +#define TN40_REG_HASHTABLE 0x602C + +#define TN40_REG_RST_PORT 0x7000 +#define TN40_REG_DIS_PORT 0x7010 +#define TN40_REG_RST_QU 0x7020 +#define TN40_REG_DIS_QU 0x7030 + +#define TN40_REG_CTRLST_TX_ENA 0x0001 +#define TN40_REG_CTRLST_RX_ENA 0x0002 +#define TN40_REG_CTRLST_PRM_ENA 0x0010 +#define TN40_REG_CTRLST_PAD_ENA 0x0020 + +#define TN40_REG_CTRLST_BASE (TN40_REG_CTRLST_PAD_ENA | REG_CTRLST_PRM_ENA) + +/* TXD TXF RXF RXD CONFIG 0x0000 --- 0x007c */ +#define TN40_TX_RX_CFG1_BASE 0xffffffff /*0-31 */ +#define TN40_TX_RX_CFG0_BASE 0xfffff000 /*31:12 */ +#define TN40_TX_RX_CFG0_RSVD 0x00000ffc /*11:2 */ +#define TN40_TX_RX_CFG0_SIZE 0x00000003 /*1:0 */ + +/* TXD TXF RXF RXD WRITE 0x0080 --- 0x00BC */ +#define TN40_TXF_WPTR_WR_PTR 0x00007ff8 /*14:3 */ + +/* TXD TXF RXF RXD READ 0x00CO --- 0x00FC */ +#define TN40_TXF_RPTR_RD_PTR 0x00007ff8 /*14:3 */ + +/* The last 4 bits are dropped size is rounded to 16 */ +#define TN40_TXF_WPTR_MASK 0x7ff0 + +/* regISR 0x0100 */ +/* regIMR 0x0110 */ +#define TN40_IMR_INPROG 0x80000000 /*31 */ +#define TN40_IR_LNKCHG1 0x10000000 /*28 */ +#define TN40_IR_LNKCHG0 0x08000000 /*27 */ +#define TN40_IR_GPIO 0x04000000 /*26 */ +#define TN40_IR_RFRSH 0x02000000 /*25 */ +#define TN40_IR_RSVD 0x01000000 /*24 */ +#define TN40_IR_SWI 0x00800000 /*23 */ +#define TN40_IR_RX_FREE_3 0x00400000 /*22 */ +#define TN40_IR_RX_FREE_2 0x00200000 /*21 */ +#define TN40_IR_RX_FREE_1 0x00100000 /*20 */ +#define TN40_IR_RX_FREE_0 0x00080000 /*19 */ +#define TN40_IR_TX_FREE_3 0x00040000 /*18 */ +#define TN40_IR_TX_FREE_2 0x00020000 /*17 */ +#define TN40_IR_TX_FREE_1 0x00010000 /*16 */ +#define TN40_IR_TX_FREE_0 0x00008000 /*15 */ +#define TN40_IR_RX_DESC_3 0x00004000 /*14 */ +#define TN40_IR_RX_DESC_2 0x00002000 /*13 */ +#define TN40_IR_RX_DESC_1 0x00001000 /*12 */ +#define TN40_IR_RX_DESC_0 0x00000800 /*11 */ +#define TN40_IR_PSE 0x00000400 /*10 */ +#define TN40_IR_TMR3 0x00000200 /* 9 */ +#define TN40_IR_TMR2 0x00000100 /* 8 */ +#define TN40_IR_TMR1 0x00000080 /* 7 */ +#define TN40_IR_TMR0 0x00000040 /* 6 */ +#define TN40_IR_VNT 0x00000020 /* 5 */ +#define TN40_IR_RxFL 0x00000010 /* 4 */ +#define TN40_IR_SDPERR 0x00000008 /* 3 */ +#define TN40_IR_TR 0x00000004 /* 2 */ +#define TN40_IR_PCIE_LINK 0x00000002 /* 1 */ +#define TN40_IR_PCIE_TOUT 0x00000001 /* 0 */ + +#define TN40_IR_EXTRA \ + (TN40_IR_RX_FREE_0 | TN40_IR_LNKCHG0 | TN40_IR_LNKCHG1 |\ + TN40_IR_PSE | TN40_IR_TMR0 | TN40_IR_PCIE_LINK | \ + TN40_IR_PCIE_TOUT) + +#define TN40_GMAC_RX_FILTER_OSEN 0x1000 /* shared OS enable */ +#define TN40_GMAC_RX_FILTER_TXFC 0x0400 /* Tx flow control */ +#define TN40_GMAC_RX_FILTER_RSV0 0x0200 /* reserved */ +#define TN40_GMAC_RX_FILTER_FDA 0x0100 /* filter out direct address */ +#define TN40_GMAC_RX_FILTER_AOF 0x0080 /* accept over run */ +#define TN40_GMAC_RX_FILTER_ACF 0x0040 /* accept control frames */ +#define TN40_GMAC_RX_FILTER_ARUNT 0x0020 /* accept under run */ +#define TN40_GMAC_RX_FILTER_ACRC 0x0010 /* accept crc error */ +#define TN40_GMAC_RX_FILTER_AM 0x0008 /* accept multicast */ +#define TN40_GMAC_RX_FILTER_AB 0x0004 /* accept broadcast */ +#define TN40_GMAC_RX_FILTER_PRM 0x0001 /* [0:1] promiscuous mode */ + +#define TN40_MAX_FRAME_AB_VAL 0x3fff /* 13:0 */ + +#define TN40_CLKPLL_PLLLKD 0x0200 /* 9 */ +#define TN40_CLKPLL_RSTEND 0x0100 /* 8 */ +#define TN40_CLKPLL_SFTRST 0x0001 /* 0 */ + +#define TN40_CLKPLL_LKD (TN40_CLKPLL_PLLLKD | TN40_CLKPLL_RSTEND) + +#endif diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c index 3025e9c18970..003668dee738 100644 --- a/drivers/net/ethernet/ti/icssg/icss_iep.c +++ b/drivers/net/ethernet/ti/icssg/icss_iep.c @@ -17,6 +17,7 @@ #include <linux/timekeeping.h> #include <linux/interrupt.h> #include <linux/of_irq.h> +#include <linux/workqueue.h> #include "icss_iep.h" @@ -110,7 +111,6 @@ struct icss_iep { struct ptp_clock_info ptp_info; struct ptp_clock *ptp_clock; struct mutex ptp_clk_mutex; /* PHC access serializer */ - spinlock_t irq_lock; /* CMP IRQ vs icss_iep_ptp_enable access */ u32 def_inc; s16 slow_cmp_inc; u32 slow_cmp_count; @@ -122,6 +122,7 @@ struct icss_iep { int cap_cmp_irq; u64 period; u32 latch_enable; + struct work_struct work; }; /** @@ -192,14 +193,11 @@ static void icss_iep_update_to_next_boundary(struct icss_iep *iep, u64 start_ns) */ static void icss_iep_settime(struct icss_iep *iep, u64 ns) { - unsigned long flags; - if (iep->ops && iep->ops->settime) { iep->ops->settime(iep->clockops_data, ns); return; } - spin_lock_irqsave(&iep->irq_lock, flags); if (iep->pps_enabled || iep->perout_enabled) writel(0, iep->base + iep->plat_data->reg_offs[ICSS_IEP_SYNC_CTRL_REG]); @@ -210,7 +208,6 @@ static void icss_iep_settime(struct icss_iep *iep, u64 ns) writel(IEP_SYNC_CTRL_SYNC_N_EN(0) | IEP_SYNC_CTRL_SYNC_EN, iep->base + iep->plat_data->reg_offs[ICSS_IEP_SYNC_CTRL_REG]); } - spin_unlock_irqrestore(&iep->irq_lock, flags); } /** @@ -546,7 +543,6 @@ static int icss_iep_perout_enable_hw(struct icss_iep *iep, static int icss_iep_perout_enable(struct icss_iep *iep, struct ptp_perout_request *req, int on) { - unsigned long flags; int ret = 0; mutex_lock(&iep->ptp_clk_mutex); @@ -559,11 +555,9 @@ static int icss_iep_perout_enable(struct icss_iep *iep, if (iep->perout_enabled == !!on) goto exit; - spin_lock_irqsave(&iep->irq_lock, flags); ret = icss_iep_perout_enable_hw(iep, req, on); if (!ret) iep->perout_enabled = !!on; - spin_unlock_irqrestore(&iep->irq_lock, flags); exit: mutex_unlock(&iep->ptp_clk_mutex); @@ -571,11 +565,61 @@ exit: return ret; } +static void icss_iep_cap_cmp_work(struct work_struct *work) +{ + struct icss_iep *iep = container_of(work, struct icss_iep, work); + const u32 *reg_offs = iep->plat_data->reg_offs; + struct ptp_clock_event pevent; + unsigned int val; + u64 ns, ns_next; + + mutex_lock(&iep->ptp_clk_mutex); + + ns = readl(iep->base + reg_offs[ICSS_IEP_CMP1_REG0]); + if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT) { + val = readl(iep->base + reg_offs[ICSS_IEP_CMP1_REG1]); + ns |= (u64)val << 32; + } + /* set next event */ + ns_next = ns + iep->period; + writel(lower_32_bits(ns_next), + iep->base + reg_offs[ICSS_IEP_CMP1_REG0]); + if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT) + writel(upper_32_bits(ns_next), + iep->base + reg_offs[ICSS_IEP_CMP1_REG1]); + + pevent.pps_times.ts_real = ns_to_timespec64(ns); + pevent.type = PTP_CLOCK_PPSUSR; + pevent.index = 0; + ptp_clock_event(iep->ptp_clock, &pevent); + dev_dbg(iep->dev, "IEP:pps ts: %llu next:%llu:\n", ns, ns_next); + + mutex_unlock(&iep->ptp_clk_mutex); +} + +static irqreturn_t icss_iep_cap_cmp_irq(int irq, void *dev_id) +{ + struct icss_iep *iep = (struct icss_iep *)dev_id; + const u32 *reg_offs = iep->plat_data->reg_offs; + unsigned int val; + + val = readl(iep->base + reg_offs[ICSS_IEP_CMP_STAT_REG]); + /* The driver only enables CMP1 */ + if (val & BIT(1)) { + /* Clear the event */ + writel(BIT(1), iep->base + reg_offs[ICSS_IEP_CMP_STAT_REG]); + if (iep->pps_enabled || iep->perout_enabled) + schedule_work(&iep->work); + return IRQ_HANDLED; + } + + return IRQ_NONE; +} + static int icss_iep_pps_enable(struct icss_iep *iep, int on) { struct ptp_clock_request rq; struct timespec64 ts; - unsigned long flags; int ret = 0; u64 ns; @@ -589,8 +633,6 @@ static int icss_iep_pps_enable(struct icss_iep *iep, int on) if (iep->pps_enabled == !!on) goto exit; - spin_lock_irqsave(&iep->irq_lock, flags); - rq.perout.index = 0; if (on) { ns = icss_iep_gettime(iep, NULL); @@ -602,13 +644,13 @@ static int icss_iep_pps_enable(struct icss_iep *iep, int on) ret = icss_iep_perout_enable_hw(iep, &rq.perout, on); } else { ret = icss_iep_perout_enable_hw(iep, &rq.perout, on); + if (iep->cap_cmp_irq) + cancel_work_sync(&iep->work); } if (!ret) iep->pps_enabled = !!on; - spin_unlock_irqrestore(&iep->irq_lock, flags); - exit: mutex_unlock(&iep->ptp_clk_mutex); @@ -777,6 +819,8 @@ int icss_iep_init(struct icss_iep *iep, const struct icss_iep_clockops *clkops, if (iep->ops && iep->ops->perout_enable) { iep->ptp_info.n_per_out = 1; iep->ptp_info.pps = 1; + } else if (iep->cap_cmp_irq) { + iep->ptp_info.pps = 1; } if (iep->ops && iep->ops->extts_enable) @@ -817,6 +861,7 @@ static int icss_iep_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct icss_iep *iep; struct clk *iep_clk; + int ret, irq; iep = devm_kzalloc(dev, sizeof(*iep), GFP_KERNEL); if (!iep) @@ -827,6 +872,22 @@ static int icss_iep_probe(struct platform_device *pdev) if (IS_ERR(iep->base)) return -ENODEV; + irq = platform_get_irq_byname_optional(pdev, "iep_cap_cmp"); + if (irq == -EPROBE_DEFER) + return irq; + + if (irq > 0) { + ret = devm_request_irq(dev, irq, icss_iep_cap_cmp_irq, + IRQF_TRIGGER_HIGH, "iep_cap_cmp", iep); + if (ret) { + dev_info(iep->dev, "cap_cmp irq request failed: %x\n", + ret); + } else { + iep->cap_cmp_irq = irq; + INIT_WORK(&iep->work, icss_iep_cap_cmp_work); + } + } + iep_clk = devm_clk_get(dev, NULL); if (IS_ERR(iep_clk)) return PTR_ERR(iep_clk); @@ -853,7 +914,6 @@ static int icss_iep_probe(struct platform_device *pdev) iep->ptp_info = icss_iep_ptp_info; mutex_init(&iep->ptp_clk_mutex); - spin_lock_init(&iep->irq_lock); dev_set_drvdata(dev, iep); icss_iep_disable(iep); diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c index 7b3304bbd7fc..fa98bdb11ece 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c @@ -1011,16 +1011,44 @@ static int prueth_probe(struct platform_device *pdev) dev_dbg(dev, "sram: pa %llx va %p size %zx\n", prueth->msmcram.pa, prueth->msmcram.va, prueth->msmcram.size); + prueth->iep0 = icss_iep_get_idx(np, 0); + if (IS_ERR(prueth->iep0)) { + ret = dev_err_probe(dev, PTR_ERR(prueth->iep0), + "iep0 get failed\n"); + goto free_pool; + } + + prueth->iep1 = icss_iep_get_idx(np, 1); + if (IS_ERR(prueth->iep1)) { + ret = dev_err_probe(dev, PTR_ERR(prueth->iep1), + "iep1 get failed\n"); + goto put_iep0; + } + + ret = icss_iep_init(prueth->iep0, NULL, NULL, 0); + if (ret) { + dev_err_probe(dev, ret, "failed to init iep0\n"); + goto put_iep; + } + + ret = icss_iep_init(prueth->iep1, NULL, NULL, 0); + if (ret) { + dev_err_probe(dev, ret, "failed to init iep1\n"); + goto exit_iep0; + } + if (eth0_node) { ret = prueth_netdev_init(prueth, eth0_node); if (ret) { dev_err_probe(dev, ret, "netdev init %s failed\n", eth0_node->name); - goto free_pool; + goto exit_iep; } if (of_find_property(eth0_node, "ti,half-duplex-capable", NULL)) prueth->emac[PRUETH_MAC0]->half_duplex = 1; + + prueth->emac[PRUETH_MAC0]->iep = prueth->iep0; } if (eth1_node) { @@ -1033,6 +1061,8 @@ static int prueth_probe(struct platform_device *pdev) if (of_find_property(eth1_node, "ti,half-duplex-capable", NULL)) prueth->emac[PRUETH_MAC1]->half_duplex = 1; + + prueth->emac[PRUETH_MAC1]->iep = prueth->iep1; } /* register the network devices */ @@ -1091,6 +1121,19 @@ netdev_exit: prueth_netdev_exit(prueth, eth_node); } +exit_iep: + icss_iep_exit(prueth->iep1); +exit_iep0: + icss_iep_exit(prueth->iep0); + +put_iep: + icss_iep_put(prueth->iep1); + +put_iep0: + icss_iep_put(prueth->iep0); + prueth->iep0 = NULL; + prueth->iep1 = NULL; + free_pool: gen_pool_free(prueth->sram_pool, (unsigned long)prueth->msmcram.va, msmc_ram_size); @@ -1138,6 +1181,12 @@ static void prueth_remove(struct platform_device *pdev) prueth_netdev_exit(prueth, eth_node); } + icss_iep_exit(prueth->iep1); + icss_iep_exit(prueth->iep0); + + icss_iep_put(prueth->iep1); + icss_iep_put(prueth->iep0); + gen_pool_free(prueth->sram_pool, (unsigned long)prueth->msmcram.va, MSMC_RAM_SIZE_SR1); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c index cc3bec42ed8e..abe5921dde02 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c @@ -43,6 +43,11 @@ static const struct wx_stats wx_gstrings_stats[] = { WX_STAT("alloc_rx_buff_failed", alloc_rx_buff_failed), }; +static const struct wx_stats wx_gstrings_fdir_stats[] = { + WX_STAT("fdir_match", stats.fdirmatch), + WX_STAT("fdir_miss", stats.fdirmiss), +}; + /* drivers allocates num_tx_queues and num_rx_queues symmetrically so * we set the num_rx_queues to evaluate to num_tx_queues. This is * used because we do not have a good way to get the max number of @@ -55,13 +60,17 @@ static const struct wx_stats wx_gstrings_stats[] = { (WX_NUM_TX_QUEUES + WX_NUM_RX_QUEUES) * \ (sizeof(struct wx_queue_stats) / sizeof(u64))) #define WX_GLOBAL_STATS_LEN ARRAY_SIZE(wx_gstrings_stats) +#define WX_FDIR_STATS_LEN ARRAY_SIZE(wx_gstrings_fdir_stats) #define WX_STATS_LEN (WX_GLOBAL_STATS_LEN + WX_QUEUE_STATS_LEN) int wx_get_sset_count(struct net_device *netdev, int sset) { + struct wx *wx = netdev_priv(netdev); + switch (sset) { case ETH_SS_STATS: - return WX_STATS_LEN; + return (wx->mac.type == wx_mac_sp) ? + WX_STATS_LEN + WX_FDIR_STATS_LEN : WX_STATS_LEN; default: return -EOPNOTSUPP; } @@ -70,6 +79,7 @@ EXPORT_SYMBOL(wx_get_sset_count); void wx_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { + struct wx *wx = netdev_priv(netdev); u8 *p = data; int i; @@ -77,6 +87,10 @@ void wx_get_strings(struct net_device *netdev, u32 stringset, u8 *data) case ETH_SS_STATS: for (i = 0; i < WX_GLOBAL_STATS_LEN; i++) ethtool_puts(&p, wx_gstrings_stats[i].stat_string); + if (wx->mac.type == wx_mac_sp) { + for (i = 0; i < WX_FDIR_STATS_LEN; i++) + ethtool_puts(&p, wx_gstrings_fdir_stats[i].stat_string); + } for (i = 0; i < netdev->num_tx_queues; i++) { ethtool_sprintf(&p, "tx_queue_%u_packets", i); ethtool_sprintf(&p, "tx_queue_%u_bytes", i); @@ -96,7 +110,7 @@ void wx_get_ethtool_stats(struct net_device *netdev, struct wx *wx = netdev_priv(netdev); struct wx_ring *ring; unsigned int start; - int i, j; + int i, j, k; char *p; wx_update_stats(wx); @@ -107,6 +121,13 @@ void wx_get_ethtool_stats(struct net_device *netdev, sizeof(u64)) ? *(u64 *)p : *(u32 *)p; } + if (wx->mac.type == wx_mac_sp) { + for (k = 0; k < WX_FDIR_STATS_LEN; k++) { + p = (char *)wx + wx_gstrings_fdir_stats[k].stat_offset; + data[i++] = *(u64 *)p; + } + } + for (j = 0; j < netdev->num_tx_queues; j++) { ring = wx->tx_ring[j]; if (!ring) { @@ -172,17 +193,21 @@ EXPORT_SYMBOL(wx_get_pause_stats); void wx_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *info) { + unsigned int stats_len = WX_STATS_LEN; struct wx *wx = netdev_priv(netdev); + if (wx->mac.type == wx_mac_sp) + stats_len += WX_FDIR_STATS_LEN; + strscpy(info->driver, wx->driver_name, sizeof(info->driver)); strscpy(info->fw_version, wx->eeprom_id, sizeof(info->fw_version)); strscpy(info->bus_info, pci_name(wx->pdev), sizeof(info->bus_info)); if (wx->num_tx_queues <= WX_NUM_TX_QUEUES) { - info->n_stats = WX_STATS_LEN - + info->n_stats = stats_len - (WX_NUM_TX_QUEUES - wx->num_tx_queues) * (sizeof(struct wx_queue_stats) / sizeof(u64)) * 2; } else { - info->n_stats = WX_STATS_LEN; + info->n_stats = stats_len; } } EXPORT_SYMBOL(wx_get_drvinfo); @@ -383,6 +408,9 @@ void wx_get_channels(struct net_device *dev, /* record RSS queues */ ch->combined_count = wx->ring_feature[RING_F_RSS].indices; + + if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) + ch->combined_count = wx->ring_feature[RING_F_FDIR].indices; } EXPORT_SYMBOL(wx_get_channels); @@ -400,6 +428,9 @@ int wx_set_channels(struct net_device *dev, if (count > wx_max_channels(wx)) return -EINVAL; + if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) + wx->ring_feature[RING_F_FDIR].limit = count; + wx->ring_feature[RING_F_RSS].limit = count; return 0; diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index 7c4b6881a93f..44cd7a5866c1 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -1147,8 +1147,15 @@ static void wx_enable_rx(struct wx *wx) static void wx_set_rxpba(struct wx *wx) { u32 rxpktsize, txpktsize, txpbthresh; + u32 pbsize = wx->mac.rx_pb_size; - rxpktsize = wx->mac.rx_pb_size << WX_RDB_PB_SZ_SHIFT; + if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) { + if (test_bit(WX_FLAG_FDIR_HASH, wx->flags) || + test_bit(WX_FLAG_FDIR_PERFECT, wx->flags)) + pbsize -= 64; /* Default 64KB */ + } + + rxpktsize = pbsize << WX_RDB_PB_SZ_SHIFT; wr32(wx, WX_RDB_PB_SZ(0), rxpktsize); /* Only support an equally distributed Tx packet buffer strategy. */ @@ -1261,7 +1268,7 @@ static void wx_configure_port(struct wx *wx) * 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) +int wx_disable_sec_rx_path(struct wx *wx) { u32 secrx; @@ -1271,6 +1278,7 @@ static int wx_disable_sec_rx_path(struct wx *wx) return read_poll_timeout(rd32, secrx, secrx & WX_RSC_ST_RSEC_RDY, 1000, 40000, false, wx, WX_RSC_ST); } +EXPORT_SYMBOL(wx_disable_sec_rx_path); /** * wx_enable_sec_rx_path - Enables the receive data path @@ -1278,11 +1286,12 @@ static int wx_disable_sec_rx_path(struct wx *wx) * * Enables the receive data path. **/ -static void wx_enable_sec_rx_path(struct wx *wx) +void wx_enable_sec_rx_path(struct wx *wx) { wr32m(wx, WX_RSC_CTL, WX_RSC_CTL_RX_DIS, 0); WX_WRITE_FLUSH(wx); } +EXPORT_SYMBOL(wx_enable_sec_rx_path); static void wx_vlan_strip_control(struct wx *wx, bool enable) { @@ -1499,6 +1508,13 @@ static void wx_configure_tx_ring(struct wx *wx, txdctl |= ring->count / 128 << WX_PX_TR_CFG_TR_SIZE_SHIFT; txdctl |= 0x20 << WX_PX_TR_CFG_WTHRESH_SHIFT; + ring->atr_count = 0; + if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags) && + test_bit(WX_FLAG_FDIR_HASH, wx->flags)) + ring->atr_sample_rate = wx->atr_sample_rate; + else + ring->atr_sample_rate = 0; + /* reinitialize tx_buffer_info */ memset(ring->tx_buffer_info, 0, sizeof(struct wx_tx_buffer) * ring->count); @@ -1732,7 +1748,9 @@ void wx_configure(struct wx *wx) wx_set_rx_mode(wx->netdev); wx_restore_vlan(wx); - wx_enable_sec_rx_path(wx); + + if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) + wx->configure_fdir(wx); wx_configure_tx(wx); wx_configure_rx(wx); @@ -1959,6 +1977,7 @@ int wx_sw_init(struct wx *wx) } bitmap_zero(wx->state, WX_STATE_NBITS); + bitmap_zero(wx->flags, WX_PF_FLAGS_NBITS); return 0; } @@ -2333,6 +2352,11 @@ void wx_update_stats(struct wx *wx) hwstats->b2ogprc += rd32(wx, WX_RDM_BMC2OS_CNT); hwstats->rdmdrop += rd32(wx, WX_RDM_DRP_PKT); + if (wx->mac.type == wx_mac_sp) { + hwstats->fdirmatch += rd32(wx, WX_RDB_FDIR_MATCH); + hwstats->fdirmiss += rd32(wx, WX_RDB_FDIR_MISS); + } + for (i = 0; i < wx->mac.max_rx_queues; i++) hwstats->qmprc += rd32(wx, WX_PX_MPRC(i)); } diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.h b/drivers/net/ethernet/wangxun/libwx/wx_hw.h index 9e219fa717a2..11fb33349482 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.h @@ -28,6 +28,8 @@ 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); +int wx_disable_sec_rx_path(struct wx *wx); +void wx_enable_sec_rx_path(struct wx *wx); void wx_set_rx_mode(struct net_device *netdev); int wx_change_mtu(struct net_device *netdev, int new_mtu); void wx_disable_rx_queue(struct wx *wx, struct wx_ring *ring); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c index 68bde91b67a0..ac0e1d42fe55 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -148,10 +148,11 @@ static struct wx_dec_ptype wx_ptype_lookup[256] = { [0xFD] = WX_PTT(IP, IPV6, IGMV, IPV6, SCTP, PAY4), }; -static struct wx_dec_ptype wx_decode_ptype(const u8 ptype) +struct wx_dec_ptype wx_decode_ptype(const u8 ptype) { return wx_ptype_lookup[ptype]; } +EXPORT_SYMBOL(wx_decode_ptype); /* wx_test_staterr - tests bits in Rx descriptor status and error fields */ static __le32 wx_test_staterr(union wx_rx_desc *rx_desc, @@ -1453,6 +1454,7 @@ static void wx_tx_csum(struct wx_ring *tx_ring, struct wx_tx_buffer *first, static netdev_tx_t wx_xmit_frame_ring(struct sk_buff *skb, struct wx_ring *tx_ring) { + struct wx *wx = netdev_priv(tx_ring->netdev); u16 count = TXD_USE_COUNT(skb_headlen(skb)); struct wx_tx_buffer *first; u8 hdr_len = 0, ptype; @@ -1498,6 +1500,10 @@ static netdev_tx_t wx_xmit_frame_ring(struct sk_buff *skb, goto out_drop; else if (!tso) wx_tx_csum(tx_ring, first, ptype); + + if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags) && tx_ring->atr_sample_rate) + wx->atr(tx_ring, first, ptype); + wx_tx_map(tx_ring, first, hdr_len); return NETDEV_TX_OK; @@ -1574,8 +1580,27 @@ static void wx_set_rss_queues(struct wx *wx) f = &wx->ring_feature[RING_F_RSS]; f->indices = f->limit; - wx->num_rx_queues = f->limit; - wx->num_tx_queues = f->limit; + if (!(test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags))) + goto out; + + clear_bit(WX_FLAG_FDIR_HASH, wx->flags); + + /* Use Flow Director in addition to RSS to ensure the best + * distribution of flows across cores, even when an FDIR flow + * isn't matched. + */ + if (f->indices > 1) { + f = &wx->ring_feature[RING_F_FDIR]; + + f->indices = f->limit; + + if (!(test_bit(WX_FLAG_FDIR_PERFECT, wx->flags))) + set_bit(WX_FLAG_FDIR_HASH, wx->flags); + } + +out: + wx->num_rx_queues = f->indices; + wx->num_tx_queues = f->indices; } static void wx_set_num_queues(struct wx *wx) @@ -2680,6 +2705,7 @@ int wx_set_features(struct net_device *netdev, netdev_features_t features) { netdev_features_t changed = netdev->features ^ features; struct wx *wx = netdev_priv(netdev); + bool need_reset = false; if (features & NETIF_F_RXHASH) { wr32m(wx, WX_RDB_RA_CTL, WX_RDB_RA_CTL_RSS_EN, @@ -2697,6 +2723,36 @@ int wx_set_features(struct net_device *netdev, netdev_features_t features) else if (changed & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER)) wx_set_rx_mode(netdev); + if (!(test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags))) + return 0; + + /* Check if Flow Director n-tuple support was enabled or disabled. If + * the state changed, we need to reset. + */ + switch (features & NETIF_F_NTUPLE) { + case NETIF_F_NTUPLE: + /* turn off ATR, enable perfect filters and reset */ + if (!(test_and_set_bit(WX_FLAG_FDIR_PERFECT, wx->flags))) + need_reset = true; + + clear_bit(WX_FLAG_FDIR_HASH, wx->flags); + break; + default: + /* turn off perfect filters, enable ATR and reset */ + if (test_and_clear_bit(WX_FLAG_FDIR_PERFECT, wx->flags)) + need_reset = true; + + /* We cannot enable ATR if RSS is disabled */ + if (wx->ring_feature[RING_F_RSS].limit <= 1) + break; + + set_bit(WX_FLAG_FDIR_HASH, wx->flags); + break; + } + + if (need_reset) + wx->do_reset(netdev); + return 0; } EXPORT_SYMBOL(wx_set_features); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.h b/drivers/net/ethernet/wangxun/libwx/wx_lib.h index c41b29ea812f..fdeb0c315b75 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.h @@ -7,6 +7,7 @@ #ifndef _WX_LIB_H_ #define _WX_LIB_H_ +struct wx_dec_ptype wx_decode_ptype(const u8 ptype); 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, diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h index 5aaf7b1fa2db..e0b7866f96ec 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_type.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h @@ -157,6 +157,8 @@ #define WX_RDB_RA_CTL_RSS_IPV6_TCP BIT(21) #define WX_RDB_RA_CTL_RSS_IPV4_UDP BIT(22) #define WX_RDB_RA_CTL_RSS_IPV6_UDP BIT(23) +#define WX_RDB_FDIR_MATCH 0x19558 +#define WX_RDB_FDIR_MISS 0x1955C /******************************* PSR Registers *******************************/ /* psr control */ @@ -503,6 +505,34 @@ enum WX_MSCA_CMD_value { #define WX_PTYPE_TYP_TCP 0x04 #define WX_PTYPE_TYP_SCTP 0x05 +/* Packet type non-ip values */ +enum wx_l2_ptypes { + WX_PTYPE_L2_ABORTED = (WX_PTYPE_PKT_MAC), + WX_PTYPE_L2_MAC = (WX_PTYPE_PKT_MAC | WX_PTYPE_TYP_MAC), + + WX_PTYPE_L2_IPV4_FRAG = (WX_PTYPE_PKT_IP | WX_PTYPE_TYP_IPFRAG), + WX_PTYPE_L2_IPV4 = (WX_PTYPE_PKT_IP | WX_PTYPE_TYP_IP), + WX_PTYPE_L2_IPV4_UDP = (WX_PTYPE_PKT_IP | WX_PTYPE_TYP_UDP), + WX_PTYPE_L2_IPV4_TCP = (WX_PTYPE_PKT_IP | WX_PTYPE_TYP_TCP), + WX_PTYPE_L2_IPV4_SCTP = (WX_PTYPE_PKT_IP | WX_PTYPE_TYP_SCTP), + WX_PTYPE_L2_IPV6_FRAG = (WX_PTYPE_PKT_IP | WX_PTYPE_PKT_IPV6 | + WX_PTYPE_TYP_IPFRAG), + WX_PTYPE_L2_IPV6 = (WX_PTYPE_PKT_IP | WX_PTYPE_PKT_IPV6 | + WX_PTYPE_TYP_IP), + WX_PTYPE_L2_IPV6_UDP = (WX_PTYPE_PKT_IP | WX_PTYPE_PKT_IPV6 | + WX_PTYPE_TYP_UDP), + WX_PTYPE_L2_IPV6_TCP = (WX_PTYPE_PKT_IP | WX_PTYPE_PKT_IPV6 | + WX_PTYPE_TYP_TCP), + WX_PTYPE_L2_IPV6_SCTP = (WX_PTYPE_PKT_IP | WX_PTYPE_PKT_IPV6 | + WX_PTYPE_TYP_SCTP), + + WX_PTYPE_L2_TUN4_MAC = (WX_PTYPE_TUN_IPV4 | WX_PTYPE_PKT_IGM), + WX_PTYPE_L2_TUN6_MAC = (WX_PTYPE_TUN_IPV6 | WX_PTYPE_PKT_IGM), +}; + +#define WX_PTYPE_PKT(_pt) ((_pt) & 0x30) +#define WX_PTYPE_TYPL4(_pt) ((_pt) & 0x07) + #define WX_RXD_PKTTYPE(_rxd) \ ((le32_to_cpu((_rxd)->wb.lower.lo_dword.data) >> 9) & 0xFF) #define WX_RXD_IPV6EX(_rxd) \ @@ -552,6 +582,9 @@ enum wx_tx_flags { WX_TX_FLAGS_OUTER_IPV4 = 0x100, WX_TX_FLAGS_LINKSEC = 0x200, WX_TX_FLAGS_IPSEC = 0x400, + + /* software defined flags */ + WX_TX_FLAGS_SW_VLAN = 0x40, }; /* VLAN info */ @@ -900,7 +933,13 @@ struct wx_ring { */ u16 next_to_use; u16 next_to_clean; - u16 next_to_alloc; + union { + u16 next_to_alloc; + struct { + u8 atr_sample_rate; + u8 atr_count; + }; + }; struct wx_queue_stats stats; struct u64_stats_sync syncp; @@ -939,6 +978,7 @@ struct wx_ring_feature { enum wx_ring_f_enum { RING_F_NONE = 0, RING_F_RSS, + RING_F_FDIR, RING_F_ARRAY_SIZE /* must be last in enum set */ }; @@ -980,15 +1020,26 @@ struct wx_hw_stats { u64 crcerrs; u64 rlec; u64 qmprc; + u64 fdirmatch; + u64 fdirmiss; }; enum wx_state { WX_STATE_RESETTING, WX_STATE_NBITS, /* must be last */ }; + +enum wx_pf_flags { + WX_FLAG_FDIR_CAPABLE, + WX_FLAG_FDIR_HASH, + WX_FLAG_FDIR_PERFECT, + WX_PF_FLAGS_NBITS /* must be last */ +}; + struct wx { unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; DECLARE_BITMAP(state, WX_STATE_NBITS); + DECLARE_BITMAP(flags, WX_PF_FLAGS_NBITS); void *priv; u8 __iomem *hw_addr; @@ -1077,6 +1128,9 @@ struct wx { u64 hw_csum_rx_error; u64 alloc_rx_buff_failed; + u32 atr_sample_rate; + void (*atr)(struct wx_ring *ring, struct wx_tx_buffer *first, u8 ptype); + void (*configure_fdir)(struct wx *wx); void (*do_reset)(struct net_device *netdev); }; diff --git a/drivers/net/ethernet/wangxun/txgbe/Makefile b/drivers/net/ethernet/wangxun/txgbe/Makefile index 42718875277c..f74576fe7062 100644 --- a/drivers/net/ethernet/wangxun/txgbe/Makefile +++ b/drivers/net/ethernet/wangxun/txgbe/Makefile @@ -10,4 +10,5 @@ txgbe-objs := txgbe_main.o \ txgbe_hw.o \ txgbe_phy.o \ txgbe_irq.o \ + txgbe_fdir.o \ txgbe_ethtool.o diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c index 31fde3fa7c6b..d98314b26c19 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c @@ -9,6 +9,7 @@ #include "../libwx/wx_type.h" #include "../libwx/wx_lib.h" #include "txgbe_type.h" +#include "txgbe_fdir.h" #include "txgbe_ethtool.h" static int txgbe_set_ringparam(struct net_device *netdev, @@ -79,6 +80,430 @@ static int txgbe_set_channels(struct net_device *dev, return txgbe_setup_tc(dev, netdev_get_num_tc(dev)); } +static int txgbe_get_ethtool_fdir_entry(struct txgbe *txgbe, + struct ethtool_rxnfc *cmd) +{ + struct ethtool_rx_flow_spec *fsp = + (struct ethtool_rx_flow_spec *)&cmd->fs; + union txgbe_atr_input *mask = &txgbe->fdir_mask; + struct txgbe_fdir_filter *rule = NULL; + struct hlist_node *node; + + /* report total rule count */ + cmd->data = (1024 << TXGBE_FDIR_PBALLOC_64K) - 2; + + hlist_for_each_entry_safe(rule, node, &txgbe->fdir_filter_list, + fdir_node) { + if (fsp->location <= rule->sw_idx) + break; + } + + if (!rule || fsp->location != rule->sw_idx) + return -EINVAL; + + /* set flow type field */ + switch (rule->filter.formatted.flow_type) { + case TXGBE_ATR_FLOW_TYPE_TCPV4: + fsp->flow_type = TCP_V4_FLOW; + break; + case TXGBE_ATR_FLOW_TYPE_UDPV4: + fsp->flow_type = UDP_V4_FLOW; + break; + case TXGBE_ATR_FLOW_TYPE_SCTPV4: + fsp->flow_type = SCTP_V4_FLOW; + break; + case TXGBE_ATR_FLOW_TYPE_IPV4: + fsp->flow_type = IP_USER_FLOW; + fsp->h_u.usr_ip4_spec.ip_ver = ETH_RX_NFC_IP4; + fsp->h_u.usr_ip4_spec.proto = 0; + fsp->m_u.usr_ip4_spec.proto = 0; + break; + default: + return -EINVAL; + } + + fsp->h_u.tcp_ip4_spec.psrc = rule->filter.formatted.src_port; + fsp->m_u.tcp_ip4_spec.psrc = mask->formatted.src_port; + fsp->h_u.tcp_ip4_spec.pdst = rule->filter.formatted.dst_port; + fsp->m_u.tcp_ip4_spec.pdst = mask->formatted.dst_port; + fsp->h_u.tcp_ip4_spec.ip4src = rule->filter.formatted.src_ip[0]; + fsp->m_u.tcp_ip4_spec.ip4src = mask->formatted.src_ip[0]; + fsp->h_u.tcp_ip4_spec.ip4dst = rule->filter.formatted.dst_ip[0]; + fsp->m_u.tcp_ip4_spec.ip4dst = mask->formatted.dst_ip[0]; + fsp->h_ext.vlan_etype = rule->filter.formatted.flex_bytes; + fsp->m_ext.vlan_etype = mask->formatted.flex_bytes; + fsp->h_ext.data[1] = htonl(rule->filter.formatted.vm_pool); + fsp->m_ext.data[1] = htonl(mask->formatted.vm_pool); + fsp->flow_type |= FLOW_EXT; + + /* record action */ + if (rule->action == TXGBE_RDB_FDIR_DROP_QUEUE) + fsp->ring_cookie = RX_CLS_FLOW_DISC; + else + fsp->ring_cookie = rule->action; + + return 0; +} + +static int txgbe_get_ethtool_fdir_all(struct txgbe *txgbe, + struct ethtool_rxnfc *cmd, + u32 *rule_locs) +{ + struct txgbe_fdir_filter *rule; + struct hlist_node *node; + int cnt = 0; + + /* report total rule count */ + cmd->data = (1024 << TXGBE_FDIR_PBALLOC_64K) - 2; + + hlist_for_each_entry_safe(rule, node, &txgbe->fdir_filter_list, + fdir_node) { + if (cnt == cmd->rule_cnt) + return -EMSGSIZE; + rule_locs[cnt] = rule->sw_idx; + cnt++; + } + + cmd->rule_cnt = cnt; + + return 0; +} + +static int txgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, + u32 *rule_locs) +{ + struct wx *wx = netdev_priv(dev); + struct txgbe *txgbe = wx->priv; + int ret = -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_GRXRINGS: + cmd->data = wx->num_rx_queues; + ret = 0; + break; + case ETHTOOL_GRXCLSRLCNT: + cmd->rule_cnt = txgbe->fdir_filter_count; + ret = 0; + break; + case ETHTOOL_GRXCLSRULE: + ret = txgbe_get_ethtool_fdir_entry(txgbe, cmd); + break; + case ETHTOOL_GRXCLSRLALL: + ret = txgbe_get_ethtool_fdir_all(txgbe, cmd, (u32 *)rule_locs); + break; + default: + break; + } + + return ret; +} + +static int txgbe_flowspec_to_flow_type(struct ethtool_rx_flow_spec *fsp, + u8 *flow_type) +{ + switch (fsp->flow_type & ~FLOW_EXT) { + case TCP_V4_FLOW: + *flow_type = TXGBE_ATR_FLOW_TYPE_TCPV4; + break; + case UDP_V4_FLOW: + *flow_type = TXGBE_ATR_FLOW_TYPE_UDPV4; + break; + case SCTP_V4_FLOW: + *flow_type = TXGBE_ATR_FLOW_TYPE_SCTPV4; + break; + case IP_USER_FLOW: + switch (fsp->h_u.usr_ip4_spec.proto) { + case IPPROTO_TCP: + *flow_type = TXGBE_ATR_FLOW_TYPE_TCPV4; + break; + case IPPROTO_UDP: + *flow_type = TXGBE_ATR_FLOW_TYPE_UDPV4; + break; + case IPPROTO_SCTP: + *flow_type = TXGBE_ATR_FLOW_TYPE_SCTPV4; + break; + case 0: + if (!fsp->m_u.usr_ip4_spec.proto) { + *flow_type = TXGBE_ATR_FLOW_TYPE_IPV4; + break; + } + fallthrough; + default: + return -EINVAL; + } + break; + default: + return -EINVAL; + } + + return 0; +} + +static bool txgbe_match_ethtool_fdir_entry(struct txgbe *txgbe, + struct txgbe_fdir_filter *input) +{ + struct txgbe_fdir_filter *rule = NULL; + struct hlist_node *node2; + + hlist_for_each_entry_safe(rule, node2, &txgbe->fdir_filter_list, + fdir_node) { + if (rule->filter.formatted.bkt_hash == + input->filter.formatted.bkt_hash && + rule->action == input->action) { + wx_dbg(txgbe->wx, "FDIR entry already exist\n"); + return true; + } + } + return false; +} + +static int txgbe_update_ethtool_fdir_entry(struct txgbe *txgbe, + struct txgbe_fdir_filter *input, + u16 sw_idx) +{ + struct hlist_node *node = NULL, *parent = NULL; + struct txgbe_fdir_filter *rule; + struct wx *wx = txgbe->wx; + bool deleted = false; + int err; + + hlist_for_each_entry_safe(rule, node, &txgbe->fdir_filter_list, + fdir_node) { + /* hash found, or no matching entry */ + if (rule->sw_idx >= sw_idx) + break; + parent = node; + } + + /* if there is an old rule occupying our place remove it */ + if (rule && rule->sw_idx == sw_idx) { + /* hardware filters are only configured when interface is up, + * and we should not issue filter commands while the interface + * is down + */ + if (netif_running(wx->netdev) && + (!input || rule->filter.formatted.bkt_hash != + input->filter.formatted.bkt_hash)) { + err = txgbe_fdir_erase_perfect_filter(wx, + &rule->filter, + sw_idx); + if (err) + return -EINVAL; + } + + hlist_del(&rule->fdir_node); + kfree(rule); + txgbe->fdir_filter_count--; + deleted = true; + } + + /* If we weren't given an input, then this was a request to delete a + * filter. We should return -EINVAL if the filter wasn't found, but + * return 0 if the rule was successfully deleted. + */ + if (!input) + return deleted ? 0 : -EINVAL; + + /* initialize node and set software index */ + INIT_HLIST_NODE(&input->fdir_node); + + /* add filter to the list */ + if (parent) + hlist_add_behind(&input->fdir_node, parent); + else + hlist_add_head(&input->fdir_node, + &txgbe->fdir_filter_list); + + /* update counts */ + txgbe->fdir_filter_count++; + + return 0; +} + +static int txgbe_add_ethtool_fdir_entry(struct txgbe *txgbe, + struct ethtool_rxnfc *cmd) +{ + struct ethtool_rx_flow_spec *fsp = + (struct ethtool_rx_flow_spec *)&cmd->fs; + struct txgbe_fdir_filter *input; + union txgbe_atr_input mask; + struct wx *wx = txgbe->wx; + int err = -EINVAL; + u16 ptype = 0; + u8 queue; + + if (!(test_bit(WX_FLAG_FDIR_PERFECT, wx->flags))) + return -EOPNOTSUPP; + + /* ring_cookie is a masked into a set of queues and txgbe pools or + * we use drop index + */ + if (fsp->ring_cookie == RX_CLS_FLOW_DISC) { + queue = TXGBE_RDB_FDIR_DROP_QUEUE; + } else { + u32 ring = ethtool_get_flow_spec_ring(fsp->ring_cookie); + + if (ring >= wx->num_rx_queues) + return -EINVAL; + + /* Map the ring onto the absolute queue index */ + queue = wx->rx_ring[ring]->reg_idx; + } + + /* Don't allow indexes to exist outside of available space */ + if (fsp->location >= ((1024 << TXGBE_FDIR_PBALLOC_64K) - 2)) { + wx_err(wx, "Location out of range\n"); + return -EINVAL; + } + + input = kzalloc(sizeof(*input), GFP_ATOMIC); + if (!input) + return -ENOMEM; + + memset(&mask, 0, sizeof(union txgbe_atr_input)); + + /* set SW index */ + input->sw_idx = fsp->location; + + /* record flow type */ + if (txgbe_flowspec_to_flow_type(fsp, + &input->filter.formatted.flow_type)) { + wx_err(wx, "Unrecognized flow type\n"); + goto err_out; + } + + mask.formatted.flow_type = TXGBE_ATR_L4TYPE_IPV6_MASK | + TXGBE_ATR_L4TYPE_MASK; + + if (input->filter.formatted.flow_type == TXGBE_ATR_FLOW_TYPE_IPV4) + mask.formatted.flow_type &= TXGBE_ATR_L4TYPE_IPV6_MASK; + + /* Copy input into formatted structures */ + input->filter.formatted.src_ip[0] = fsp->h_u.tcp_ip4_spec.ip4src; + mask.formatted.src_ip[0] = fsp->m_u.tcp_ip4_spec.ip4src; + input->filter.formatted.dst_ip[0] = fsp->h_u.tcp_ip4_spec.ip4dst; + mask.formatted.dst_ip[0] = fsp->m_u.tcp_ip4_spec.ip4dst; + input->filter.formatted.src_port = fsp->h_u.tcp_ip4_spec.psrc; + mask.formatted.src_port = fsp->m_u.tcp_ip4_spec.psrc; + input->filter.formatted.dst_port = fsp->h_u.tcp_ip4_spec.pdst; + mask.formatted.dst_port = fsp->m_u.tcp_ip4_spec.pdst; + + if (fsp->flow_type & FLOW_EXT) { + input->filter.formatted.vm_pool = + (unsigned char)ntohl(fsp->h_ext.data[1]); + mask.formatted.vm_pool = + (unsigned char)ntohl(fsp->m_ext.data[1]); + input->filter.formatted.flex_bytes = + fsp->h_ext.vlan_etype; + mask.formatted.flex_bytes = fsp->m_ext.vlan_etype; + } + + switch (input->filter.formatted.flow_type) { + case TXGBE_ATR_FLOW_TYPE_TCPV4: + ptype = WX_PTYPE_L2_IPV4_TCP; + break; + case TXGBE_ATR_FLOW_TYPE_UDPV4: + ptype = WX_PTYPE_L2_IPV4_UDP; + break; + case TXGBE_ATR_FLOW_TYPE_SCTPV4: + ptype = WX_PTYPE_L2_IPV4_SCTP; + break; + case TXGBE_ATR_FLOW_TYPE_IPV4: + ptype = WX_PTYPE_L2_IPV4; + break; + default: + break; + } + + input->filter.formatted.vlan_id = htons(ptype); + if (mask.formatted.flow_type & TXGBE_ATR_L4TYPE_MASK) + mask.formatted.vlan_id = htons(0xFFFF); + else + mask.formatted.vlan_id = htons(0xFFF8); + + /* determine if we need to drop or route the packet */ + if (fsp->ring_cookie == RX_CLS_FLOW_DISC) + input->action = TXGBE_RDB_FDIR_DROP_QUEUE; + else + input->action = fsp->ring_cookie; + + spin_lock(&txgbe->fdir_perfect_lock); + + if (hlist_empty(&txgbe->fdir_filter_list)) { + /* save mask and program input mask into HW */ + memcpy(&txgbe->fdir_mask, &mask, sizeof(mask)); + err = txgbe_fdir_set_input_mask(wx, &mask); + if (err) + goto err_unlock; + } else if (memcmp(&txgbe->fdir_mask, &mask, sizeof(mask))) { + wx_err(wx, "Hardware only supports one mask per port. To change the mask you must first delete all the rules.\n"); + goto err_unlock; + } + + /* apply mask and compute/store hash */ + txgbe_atr_compute_perfect_hash(&input->filter, &mask); + + /* check if new entry does not exist on filter list */ + if (txgbe_match_ethtool_fdir_entry(txgbe, input)) + goto err_unlock; + + /* only program filters to hardware if the net device is running, as + * we store the filters in the Rx buffer which is not allocated when + * the device is down + */ + if (netif_running(wx->netdev)) { + err = txgbe_fdir_write_perfect_filter(wx, &input->filter, + input->sw_idx, queue); + if (err) + goto err_unlock; + } + + txgbe_update_ethtool_fdir_entry(txgbe, input, input->sw_idx); + + spin_unlock(&txgbe->fdir_perfect_lock); + + return 0; +err_unlock: + spin_unlock(&txgbe->fdir_perfect_lock); +err_out: + kfree(input); + return err; +} + +static int txgbe_del_ethtool_fdir_entry(struct txgbe *txgbe, + struct ethtool_rxnfc *cmd) +{ + struct ethtool_rx_flow_spec *fsp = + (struct ethtool_rx_flow_spec *)&cmd->fs; + int err = 0; + + spin_lock(&txgbe->fdir_perfect_lock); + err = txgbe_update_ethtool_fdir_entry(txgbe, NULL, fsp->location); + spin_unlock(&txgbe->fdir_perfect_lock); + + return err; +} + +static int txgbe_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) +{ + struct wx *wx = netdev_priv(dev); + struct txgbe *txgbe = wx->priv; + int ret = -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_SRXCLSRLINS: + ret = txgbe_add_ethtool_fdir_entry(txgbe, cmd); + break; + case ETHTOOL_SRXCLSRLDEL: + ret = txgbe_del_ethtool_fdir_entry(txgbe, cmd); + break; + default: + break; + } + + return ret; +} + static const struct ethtool_ops txgbe_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_TX_MAX_FRAMES_IRQ, @@ -100,6 +525,8 @@ static const struct ethtool_ops txgbe_ethtool_ops = { .set_coalesce = wx_set_coalesce, .get_channels = wx_get_channels, .set_channels = txgbe_set_channels, + .get_rxnfc = txgbe_get_rxnfc, + .set_rxnfc = txgbe_set_rxnfc, .get_msglevel = wx_get_msglevel, .set_msglevel = wx_set_msglevel, }; diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_fdir.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_fdir.c new file mode 100644 index 000000000000..ef50efbaec0f --- /dev/null +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_fdir.c @@ -0,0 +1,643 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2015 - 2024 Beijing WangXun Technology Co., Ltd. */ + +#include <linux/string.h> +#include <linux/types.h> +#include <linux/pci.h> + +#include "../libwx/wx_type.h" +#include "../libwx/wx_lib.h" +#include "../libwx/wx_hw.h" +#include "txgbe_type.h" +#include "txgbe_fdir.h" + +/* These defines allow us to quickly generate all of the necessary instructions + * in the function below by simply calling out TXGBE_COMPUTE_SIG_HASH_ITERATION + * for values 0 through 15 + */ +#define TXGBE_ATR_COMMON_HASH_KEY \ + (TXGBE_ATR_BUCKET_HASH_KEY & TXGBE_ATR_SIGNATURE_HASH_KEY) +#define TXGBE_COMPUTE_SIG_HASH_ITERATION(_n) \ +do { \ + u32 n = (_n); \ + if (TXGBE_ATR_COMMON_HASH_KEY & (0x01 << n)) \ + common_hash ^= lo_hash_dword >> n; \ + else if (TXGBE_ATR_BUCKET_HASH_KEY & (0x01 << n)) \ + bucket_hash ^= lo_hash_dword >> n; \ + else if (TXGBE_ATR_SIGNATURE_HASH_KEY & (0x01 << n)) \ + sig_hash ^= lo_hash_dword << (16 - n); \ + if (TXGBE_ATR_COMMON_HASH_KEY & (0x01 << (n + 16))) \ + common_hash ^= hi_hash_dword >> n; \ + else if (TXGBE_ATR_BUCKET_HASH_KEY & (0x01 << (n + 16))) \ + bucket_hash ^= hi_hash_dword >> n; \ + else if (TXGBE_ATR_SIGNATURE_HASH_KEY & (0x01 << (n + 16))) \ + sig_hash ^= hi_hash_dword << (16 - n); \ +} while (0) + +/** + * txgbe_atr_compute_sig_hash - Compute the signature hash + * @input: input bitstream to compute the hash on + * @common: compressed common input dword + * @hash: pointer to the computed hash + * + * This function is almost identical to the function above but contains + * several optimizations such as unwinding all of the loops, letting the + * compiler work out all of the conditional ifs since the keys are static + * defines, and computing two keys at once since the hashed dword stream + * will be the same for both keys. + **/ +static void txgbe_atr_compute_sig_hash(union txgbe_atr_hash_dword input, + union txgbe_atr_hash_dword common, + u32 *hash) +{ + u32 sig_hash = 0, bucket_hash = 0, common_hash = 0; + u32 hi_hash_dword, lo_hash_dword, flow_vm_vlan; + u32 i; + + /* record the flow_vm_vlan bits as they are a key part to the hash */ + flow_vm_vlan = ntohl(input.dword); + + /* generate common hash dword */ + hi_hash_dword = ntohl(common.dword); + + /* low dword is word swapped version of common */ + lo_hash_dword = (hi_hash_dword >> 16) | (hi_hash_dword << 16); + + /* apply flow ID/VM pool/VLAN ID bits to hash words */ + hi_hash_dword ^= flow_vm_vlan ^ (flow_vm_vlan >> 16); + + /* Process bits 0 and 16 */ + TXGBE_COMPUTE_SIG_HASH_ITERATION(0); + + /* apply flow ID/VM pool/VLAN ID bits to lo hash dword, we had to + * delay this because bit 0 of the stream should not be processed + * so we do not add the VLAN until after bit 0 was processed + */ + lo_hash_dword ^= flow_vm_vlan ^ (flow_vm_vlan << 16); + + /* Process remaining 30 bit of the key */ + for (i = 1; i <= 15; i++) + TXGBE_COMPUTE_SIG_HASH_ITERATION(i); + + /* combine common_hash result with signature and bucket hashes */ + bucket_hash ^= common_hash; + bucket_hash &= TXGBE_ATR_HASH_MASK; + + sig_hash ^= common_hash << 16; + sig_hash &= TXGBE_ATR_HASH_MASK << 16; + + /* return completed signature hash */ + *hash = sig_hash ^ bucket_hash; +} + +#define TXGBE_COMPUTE_BKT_HASH_ITERATION(_n) \ +do { \ + u32 n = (_n); \ + if (TXGBE_ATR_BUCKET_HASH_KEY & (0x01 << n)) \ + bucket_hash ^= lo_hash_dword >> n; \ + if (TXGBE_ATR_BUCKET_HASH_KEY & (0x01 << (n + 16))) \ + bucket_hash ^= hi_hash_dword >> n; \ +} while (0) + +/** + * txgbe_atr_compute_perfect_hash - Compute the perfect filter hash + * @input: input bitstream to compute the hash on + * @input_mask: mask for the input bitstream + * + * This function serves two main purposes. First it applies the input_mask + * to the atr_input resulting in a cleaned up atr_input data stream. + * Secondly it computes the hash and stores it in the bkt_hash field at + * the end of the input byte stream. This way it will be available for + * future use without needing to recompute the hash. + **/ +void txgbe_atr_compute_perfect_hash(union txgbe_atr_input *input, + union txgbe_atr_input *input_mask) +{ + u32 hi_hash_dword, lo_hash_dword, flow_vm_vlan; + u32 bucket_hash = 0; + __be32 hi_dword = 0; + u32 i = 0; + + /* Apply masks to input data */ + for (i = 0; i < 11; i++) + input->dword_stream[i] &= input_mask->dword_stream[i]; + + /* record the flow_vm_vlan bits as they are a key part to the hash */ + flow_vm_vlan = ntohl(input->dword_stream[0]); + + /* generate common hash dword */ + for (i = 1; i <= 10; i++) + hi_dword ^= input->dword_stream[i]; + hi_hash_dword = ntohl(hi_dword); + + /* low dword is word swapped version of common */ + lo_hash_dword = (hi_hash_dword >> 16) | (hi_hash_dword << 16); + + /* apply flow ID/VM pool/VLAN ID bits to hash words */ + hi_hash_dword ^= flow_vm_vlan ^ (flow_vm_vlan >> 16); + + /* Process bits 0 and 16 */ + TXGBE_COMPUTE_BKT_HASH_ITERATION(0); + + /* apply flow ID/VM pool/VLAN ID bits to lo hash dword, we had to + * delay this because bit 0 of the stream should not be processed + * so we do not add the VLAN until after bit 0 was processed + */ + lo_hash_dword ^= flow_vm_vlan ^ (flow_vm_vlan << 16); + + /* Process remaining 30 bit of the key */ + for (i = 1; i <= 15; i++) + TXGBE_COMPUTE_BKT_HASH_ITERATION(i); + + /* Limit hash to 13 bits since max bucket count is 8K. + * Store result at the end of the input stream. + */ + input->formatted.bkt_hash = (__force __be16)(bucket_hash & 0x1FFF); +} + +static int txgbe_fdir_check_cmd_complete(struct wx *wx) +{ + u32 val; + + return read_poll_timeout_atomic(rd32, val, + !(val & TXGBE_RDB_FDIR_CMD_CMD_MASK), + 10, 100, false, + wx, TXGBE_RDB_FDIR_CMD); +} + +/** + * txgbe_fdir_add_signature_filter - Adds a signature hash filter + * @wx: pointer to hardware structure + * @input: unique input dword + * @common: compressed common input dword + * @queue: queue index to direct traffic to + * + * @return: 0 on success and negative on failure + **/ +static int txgbe_fdir_add_signature_filter(struct wx *wx, + union txgbe_atr_hash_dword input, + union txgbe_atr_hash_dword common, + u8 queue) +{ + u32 fdirhashcmd, fdircmd; + u8 flow_type; + int err; + + /* Get the flow_type in order to program FDIRCMD properly + * lowest 2 bits are FDIRCMD.L4TYPE, third lowest bit is FDIRCMD.IPV6 + * fifth is FDIRCMD.TUNNEL_FILTER + */ + flow_type = input.formatted.flow_type; + switch (flow_type) { + case TXGBE_ATR_FLOW_TYPE_TCPV4: + case TXGBE_ATR_FLOW_TYPE_UDPV4: + case TXGBE_ATR_FLOW_TYPE_SCTPV4: + case TXGBE_ATR_FLOW_TYPE_TCPV6: + case TXGBE_ATR_FLOW_TYPE_UDPV6: + case TXGBE_ATR_FLOW_TYPE_SCTPV6: + break; + default: + wx_err(wx, "Error on flow type input\n"); + return -EINVAL; + } + + /* configure FDIRCMD register */ + fdircmd = TXGBE_RDB_FDIR_CMD_CMD_ADD_FLOW | + TXGBE_RDB_FDIR_CMD_FILTER_UPDATE | + TXGBE_RDB_FDIR_CMD_LAST | TXGBE_RDB_FDIR_CMD_QUEUE_EN; + fdircmd |= TXGBE_RDB_FDIR_CMD_FLOW_TYPE(flow_type); + fdircmd |= TXGBE_RDB_FDIR_CMD_RX_QUEUE(queue); + + txgbe_atr_compute_sig_hash(input, common, &fdirhashcmd); + fdirhashcmd |= TXGBE_RDB_FDIR_HASH_BUCKET_VALID; + wr32(wx, TXGBE_RDB_FDIR_HASH, fdirhashcmd); + wr32(wx, TXGBE_RDB_FDIR_CMD, fdircmd); + + wx_dbg(wx, "Tx Queue=%x hash=%x\n", queue, (u32)fdirhashcmd); + + err = txgbe_fdir_check_cmd_complete(wx); + if (err) + wx_err(wx, "Flow Director command did not complete!\n"); + + return err; +} + +void txgbe_atr(struct wx_ring *ring, struct wx_tx_buffer *first, u8 ptype) +{ + union txgbe_atr_hash_dword common = { .dword = 0 }; + union txgbe_atr_hash_dword input = { .dword = 0 }; + struct wx_q_vector *q_vector = ring->q_vector; + struct wx_dec_ptype dptype; + union network_header { + struct ipv6hdr *ipv6; + struct iphdr *ipv4; + void *raw; + } hdr; + struct tcphdr *th; + + /* if ring doesn't have a interrupt vector, cannot perform ATR */ + if (!q_vector) + return; + + ring->atr_count++; + dptype = wx_decode_ptype(ptype); + if (dptype.etype) { + if (WX_PTYPE_TYPL4(ptype) != WX_PTYPE_TYP_TCP) + return; + hdr.raw = (void *)skb_inner_network_header(first->skb); + th = inner_tcp_hdr(first->skb); + } else { + if (WX_PTYPE_PKT(ptype) != WX_PTYPE_PKT_IP || + WX_PTYPE_TYPL4(ptype) != WX_PTYPE_TYP_TCP) + return; + hdr.raw = (void *)skb_network_header(first->skb); + th = tcp_hdr(first->skb); + } + + /* skip this packet since it is invalid or the socket is closing */ + if (!th || th->fin) + return; + + /* sample on all syn packets or once every atr sample count */ + if (!th->syn && ring->atr_count < ring->atr_sample_rate) + return; + + /* reset sample count */ + ring->atr_count = 0; + + /* src and dst are inverted, think how the receiver sees them + * + * The input is broken into two sections, a non-compressed section + * containing vm_pool, vlan_id, and flow_type. The rest of the data + * is XORed together and stored in the compressed dword. + */ + input.formatted.vlan_id = htons((u16)ptype); + + /* since src port and flex bytes occupy the same word XOR them together + * and write the value to source port portion of compressed dword + */ + if (first->tx_flags & WX_TX_FLAGS_SW_VLAN) + common.port.src ^= th->dest ^ first->skb->protocol; + else if (first->tx_flags & WX_TX_FLAGS_HW_VLAN) + common.port.src ^= th->dest ^ first->skb->vlan_proto; + else + common.port.src ^= th->dest ^ first->protocol; + common.port.dst ^= th->source; + + if (WX_PTYPE_PKT_IPV6 & WX_PTYPE_PKT(ptype)) { + input.formatted.flow_type = TXGBE_ATR_FLOW_TYPE_TCPV6; + common.ip ^= hdr.ipv6->saddr.s6_addr32[0] ^ + hdr.ipv6->saddr.s6_addr32[1] ^ + hdr.ipv6->saddr.s6_addr32[2] ^ + hdr.ipv6->saddr.s6_addr32[3] ^ + hdr.ipv6->daddr.s6_addr32[0] ^ + hdr.ipv6->daddr.s6_addr32[1] ^ + hdr.ipv6->daddr.s6_addr32[2] ^ + hdr.ipv6->daddr.s6_addr32[3]; + } else { + input.formatted.flow_type = TXGBE_ATR_FLOW_TYPE_TCPV4; + common.ip ^= hdr.ipv4->saddr ^ hdr.ipv4->daddr; + } + + /* This assumes the Rx queue and Tx queue are bound to the same CPU */ + txgbe_fdir_add_signature_filter(q_vector->wx, input, common, + ring->queue_index); +} + +int txgbe_fdir_set_input_mask(struct wx *wx, union txgbe_atr_input *input_mask) +{ + u32 fdirm = 0, fdirtcpm = 0, flex = 0; + + /* Program the relevant mask registers. If src/dst_port or src/dst_addr + * are zero, then assume a full mask for that field. Also assume that + * a VLAN of 0 is unspecified, so mask that out as well. L4type + * cannot be masked out in this implementation. + * + * This also assumes IPv4 only. IPv6 masking isn't supported at this + * point in time. + */ + + /* verify bucket hash is cleared on hash generation */ + if (input_mask->formatted.bkt_hash) + wx_dbg(wx, "bucket hash should always be 0 in mask\n"); + + /* Program FDIRM and verify partial masks */ + switch (input_mask->formatted.vm_pool & 0x7F) { + case 0x0: + fdirm |= TXGBE_RDB_FDIR_OTHER_MSK_POOL; + break; + case 0x7F: + break; + default: + wx_err(wx, "Error on vm pool mask\n"); + return -EINVAL; + } + + switch (input_mask->formatted.flow_type & TXGBE_ATR_L4TYPE_MASK) { + case 0x0: + fdirm |= TXGBE_RDB_FDIR_OTHER_MSK_L4P; + if (input_mask->formatted.dst_port || + input_mask->formatted.src_port) { + wx_err(wx, "Error on src/dst port mask\n"); + return -EINVAL; + } + break; + case TXGBE_ATR_L4TYPE_MASK: + break; + default: + wx_err(wx, "Error on flow type mask\n"); + return -EINVAL; + } + + /* Now mask VM pool and destination IPv6 - bits 5 and 2 */ + wr32(wx, TXGBE_RDB_FDIR_OTHER_MSK, fdirm); + + flex = rd32(wx, TXGBE_RDB_FDIR_FLEX_CFG(0)); + flex &= ~TXGBE_RDB_FDIR_FLEX_CFG_FIELD0; + flex |= (TXGBE_RDB_FDIR_FLEX_CFG_BASE_MAC | + TXGBE_RDB_FDIR_FLEX_CFG_OFST(0x6)); + + switch ((__force u16)input_mask->formatted.flex_bytes & 0xFFFF) { + case 0x0000: + /* Mask Flex Bytes */ + flex |= TXGBE_RDB_FDIR_FLEX_CFG_MSK; + break; + case 0xFFFF: + break; + default: + wx_err(wx, "Error on flexible byte mask\n"); + return -EINVAL; + } + wr32(wx, TXGBE_RDB_FDIR_FLEX_CFG(0), flex); + + /* store the TCP/UDP port masks, bit reversed from port layout */ + fdirtcpm = ntohs(input_mask->formatted.dst_port); + fdirtcpm <<= TXGBE_RDB_FDIR_PORT_DESTINATION_SHIFT; + fdirtcpm |= ntohs(input_mask->formatted.src_port); + + /* write both the same so that UDP and TCP use the same mask */ + wr32(wx, TXGBE_RDB_FDIR_TCP_MSK, ~fdirtcpm); + wr32(wx, TXGBE_RDB_FDIR_UDP_MSK, ~fdirtcpm); + wr32(wx, TXGBE_RDB_FDIR_SCTP_MSK, ~fdirtcpm); + + /* store source and destination IP masks (little-enian) */ + wr32(wx, TXGBE_RDB_FDIR_SA4_MSK, + ntohl(~input_mask->formatted.src_ip[0])); + wr32(wx, TXGBE_RDB_FDIR_DA4_MSK, + ntohl(~input_mask->formatted.dst_ip[0])); + + return 0; +} + +int txgbe_fdir_write_perfect_filter(struct wx *wx, + union txgbe_atr_input *input, + u16 soft_id, u8 queue) +{ + u32 fdirport, fdirvlan, fdirhash, fdircmd; + int err = 0; + + /* currently IPv6 is not supported, must be programmed with 0 */ + wr32(wx, TXGBE_RDB_FDIR_IP6(2), ntohl(input->formatted.src_ip[0])); + wr32(wx, TXGBE_RDB_FDIR_IP6(1), ntohl(input->formatted.src_ip[1])); + wr32(wx, TXGBE_RDB_FDIR_IP6(0), ntohl(input->formatted.src_ip[2])); + + /* record the source address (little-endian) */ + wr32(wx, TXGBE_RDB_FDIR_SA, ntohl(input->formatted.src_ip[0])); + + /* record the first 32 bits of the destination address + * (little-endian) + */ + wr32(wx, TXGBE_RDB_FDIR_DA, ntohl(input->formatted.dst_ip[0])); + + /* record source and destination port (little-endian)*/ + fdirport = ntohs(input->formatted.dst_port); + fdirport <<= TXGBE_RDB_FDIR_PORT_DESTINATION_SHIFT; + fdirport |= ntohs(input->formatted.src_port); + wr32(wx, TXGBE_RDB_FDIR_PORT, fdirport); + + /* record packet type and flex_bytes (little-endian) */ + fdirvlan = ntohs(input->formatted.flex_bytes); + fdirvlan <<= TXGBE_RDB_FDIR_FLEX_FLEX_SHIFT; + fdirvlan |= ntohs(input->formatted.vlan_id); + wr32(wx, TXGBE_RDB_FDIR_FLEX, fdirvlan); + + /* configure FDIRHASH register */ + fdirhash = (__force u32)input->formatted.bkt_hash | + TXGBE_RDB_FDIR_HASH_BUCKET_VALID | + TXGBE_RDB_FDIR_HASH_SIG_SW_INDEX(soft_id); + wr32(wx, TXGBE_RDB_FDIR_HASH, fdirhash); + + /* flush all previous writes to make certain registers are + * programmed prior to issuing the command + */ + WX_WRITE_FLUSH(wx); + + /* configure FDIRCMD register */ + fdircmd = TXGBE_RDB_FDIR_CMD_CMD_ADD_FLOW | + TXGBE_RDB_FDIR_CMD_FILTER_UPDATE | + TXGBE_RDB_FDIR_CMD_LAST | TXGBE_RDB_FDIR_CMD_QUEUE_EN; + if (queue == TXGBE_RDB_FDIR_DROP_QUEUE) + fdircmd |= TXGBE_RDB_FDIR_CMD_DROP; + fdircmd |= TXGBE_RDB_FDIR_CMD_FLOW_TYPE(input->formatted.flow_type); + fdircmd |= TXGBE_RDB_FDIR_CMD_RX_QUEUE(queue); + fdircmd |= TXGBE_RDB_FDIR_CMD_VT_POOL(input->formatted.vm_pool); + + wr32(wx, TXGBE_RDB_FDIR_CMD, fdircmd); + err = txgbe_fdir_check_cmd_complete(wx); + if (err) + wx_err(wx, "Flow Director command did not complete!\n"); + + return err; +} + +int txgbe_fdir_erase_perfect_filter(struct wx *wx, + union txgbe_atr_input *input, + u16 soft_id) +{ + u32 fdirhash, fdircmd; + int err = 0; + + /* configure FDIRHASH register */ + fdirhash = (__force u32)input->formatted.bkt_hash; + fdirhash |= TXGBE_RDB_FDIR_HASH_SIG_SW_INDEX(soft_id); + wr32(wx, TXGBE_RDB_FDIR_HASH, fdirhash); + + /* flush hash to HW */ + WX_WRITE_FLUSH(wx); + + /* Query if filter is present */ + wr32(wx, TXGBE_RDB_FDIR_CMD, TXGBE_RDB_FDIR_CMD_CMD_QUERY_REM_FILT); + + err = txgbe_fdir_check_cmd_complete(wx); + if (err) { + wx_err(wx, "Flow Director command did not complete!\n"); + return err; + } + + fdircmd = rd32(wx, TXGBE_RDB_FDIR_CMD); + /* if filter exists in hardware then remove it */ + if (fdircmd & TXGBE_RDB_FDIR_CMD_FILTER_VALID) { + wr32(wx, TXGBE_RDB_FDIR_HASH, fdirhash); + WX_WRITE_FLUSH(wx); + wr32(wx, TXGBE_RDB_FDIR_CMD, + TXGBE_RDB_FDIR_CMD_CMD_REMOVE_FLOW); + } + + return 0; +} + +/** + * txgbe_fdir_enable - Initialize Flow Director control registers + * @wx: pointer to hardware structure + * @fdirctrl: value to write to flow director control register + **/ +static void txgbe_fdir_enable(struct wx *wx, u32 fdirctrl) +{ + u32 val; + int ret; + + /* Prime the keys for hashing */ + wr32(wx, TXGBE_RDB_FDIR_HKEY, TXGBE_ATR_BUCKET_HASH_KEY); + wr32(wx, TXGBE_RDB_FDIR_SKEY, TXGBE_ATR_SIGNATURE_HASH_KEY); + + wr32(wx, TXGBE_RDB_FDIR_CTL, fdirctrl); + WX_WRITE_FLUSH(wx); + ret = read_poll_timeout(rd32, val, val & TXGBE_RDB_FDIR_CTL_INIT_DONE, + 1000, 10000, false, wx, TXGBE_RDB_FDIR_CTL); + + if (ret < 0) + wx_dbg(wx, "Flow Director poll time exceeded!\n"); +} + +/** + * txgbe_init_fdir_signature -Initialize Flow Director sig filters + * @wx: pointer to hardware structure + **/ +static void txgbe_init_fdir_signature(struct wx *wx) +{ + u32 fdirctrl = TXGBE_FDIR_PBALLOC_64K; + u32 flex = 0; + + flex = rd32(wx, TXGBE_RDB_FDIR_FLEX_CFG(0)); + flex &= ~TXGBE_RDB_FDIR_FLEX_CFG_FIELD0; + + flex |= (TXGBE_RDB_FDIR_FLEX_CFG_BASE_MAC | + TXGBE_RDB_FDIR_FLEX_CFG_OFST(0x6)); + wr32(wx, TXGBE_RDB_FDIR_FLEX_CFG(0), flex); + + /* Continue setup of fdirctrl register bits: + * Move the flexible bytes to use the ethertype - shift 6 words + * Set the maximum length per hash bucket to 0xA filters + * Send interrupt when 64 filters are left + */ + fdirctrl |= TXGBE_RDB_FDIR_CTL_HASH_BITS(0xF) | + TXGBE_RDB_FDIR_CTL_MAX_LENGTH(0xA) | + TXGBE_RDB_FDIR_CTL_FULL_THRESH(4); + + /* write hashes and fdirctrl register, poll for completion */ + txgbe_fdir_enable(wx, fdirctrl); +} + +/** + * txgbe_init_fdir_perfect - Initialize Flow Director perfect filters + * @wx: pointer to hardware structure + **/ +static void txgbe_init_fdir_perfect(struct wx *wx) +{ + u32 fdirctrl = TXGBE_FDIR_PBALLOC_64K; + + /* Continue setup of fdirctrl register bits: + * Turn perfect match filtering on + * Report hash in RSS field of Rx wb descriptor + * Initialize the drop queue + * Move the flexible bytes to use the ethertype - shift 6 words + * Set the maximum length per hash bucket to 0xA filters + * Send interrupt when 64 (0x4 * 16) filters are left + */ + fdirctrl |= TXGBE_RDB_FDIR_CTL_PERFECT_MATCH | + TXGBE_RDB_FDIR_CTL_DROP_Q(TXGBE_RDB_FDIR_DROP_QUEUE) | + TXGBE_RDB_FDIR_CTL_HASH_BITS(0xF) | + TXGBE_RDB_FDIR_CTL_MAX_LENGTH(0xA) | + TXGBE_RDB_FDIR_CTL_FULL_THRESH(4); + + /* write hashes and fdirctrl register, poll for completion */ + txgbe_fdir_enable(wx, fdirctrl); +} + +static void txgbe_fdir_filter_restore(struct wx *wx) +{ + struct txgbe_fdir_filter *filter; + struct txgbe *txgbe = wx->priv; + struct hlist_node *node; + u8 queue = 0; + int ret = 0; + + spin_lock(&txgbe->fdir_perfect_lock); + + if (!hlist_empty(&txgbe->fdir_filter_list)) + ret = txgbe_fdir_set_input_mask(wx, &txgbe->fdir_mask); + + if (ret) + goto unlock; + + hlist_for_each_entry_safe(filter, node, + &txgbe->fdir_filter_list, fdir_node) { + if (filter->action == TXGBE_RDB_FDIR_DROP_QUEUE) { + queue = TXGBE_RDB_FDIR_DROP_QUEUE; + } else { + u32 ring = ethtool_get_flow_spec_ring(filter->action); + + if (ring >= wx->num_rx_queues) { + wx_err(wx, "FDIR restore failed, ring:%u\n", + ring); + continue; + } + + /* Map the ring onto the absolute queue index */ + queue = wx->rx_ring[ring]->reg_idx; + } + + ret = txgbe_fdir_write_perfect_filter(wx, + &filter->filter, + filter->sw_idx, + queue); + if (ret) + wx_err(wx, "FDIR restore failed, index:%u\n", + filter->sw_idx); + } + +unlock: + spin_unlock(&txgbe->fdir_perfect_lock); +} + +void txgbe_configure_fdir(struct wx *wx) +{ + wx_disable_sec_rx_path(wx); + + if (test_bit(WX_FLAG_FDIR_HASH, wx->flags)) { + txgbe_init_fdir_signature(wx); + } else if (test_bit(WX_FLAG_FDIR_PERFECT, wx->flags)) { + txgbe_init_fdir_perfect(wx); + txgbe_fdir_filter_restore(wx); + } + + wx_enable_sec_rx_path(wx); +} + +void txgbe_fdir_filter_exit(struct wx *wx) +{ + struct txgbe_fdir_filter *filter; + struct txgbe *txgbe = wx->priv; + struct hlist_node *node; + + spin_lock(&txgbe->fdir_perfect_lock); + + hlist_for_each_entry_safe(filter, node, + &txgbe->fdir_filter_list, fdir_node) { + hlist_del(&filter->fdir_node); + kfree(filter); + } + txgbe->fdir_filter_count = 0; + + spin_unlock(&txgbe->fdir_perfect_lock); +} diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_fdir.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_fdir.h new file mode 100644 index 000000000000..1f44ce60becb --- /dev/null +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_fdir.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2015 - 2024 Beijing WangXun Technology Co., Ltd. */ + +#ifndef _TXGBE_FDIR_H_ +#define _TXGBE_FDIR_H_ + +void txgbe_atr_compute_perfect_hash(union txgbe_atr_input *input, + union txgbe_atr_input *input_mask); +void txgbe_atr(struct wx_ring *ring, struct wx_tx_buffer *first, u8 ptype); +int txgbe_fdir_set_input_mask(struct wx *wx, union txgbe_atr_input *input_mask); +int txgbe_fdir_write_perfect_filter(struct wx *wx, + union txgbe_atr_input *input, + u16 soft_id, u8 queue); +int txgbe_fdir_erase_perfect_filter(struct wx *wx, + union txgbe_atr_input *input, + u16 soft_id); +void txgbe_configure_fdir(struct wx *wx); +void txgbe_fdir_filter_exit(struct wx *wx); + +#endif /* _TXGBE_FDIR_H_ */ diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c index 8c7a74981b90..41e9ebf11e41 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c @@ -18,6 +18,7 @@ #include "txgbe_hw.h" #include "txgbe_phy.h" #include "txgbe_irq.h" +#include "txgbe_fdir.h" #include "txgbe_ethtool.h" char txgbe_driver_name[] = "txgbe"; @@ -257,6 +258,14 @@ static int txgbe_sw_init(struct wx *wx) num_online_cpus()); wx->rss_enabled = true; + wx->ring_feature[RING_F_FDIR].limit = min_t(int, TXGBE_MAX_FDIR_INDICES, + num_online_cpus()); + set_bit(WX_FLAG_FDIR_CAPABLE, wx->flags); + set_bit(WX_FLAG_FDIR_HASH, wx->flags); + wx->atr_sample_rate = TXGBE_DEFAULT_ATR_SAMPLE_RATE; + wx->atr = txgbe_atr; + wx->configure_fdir = txgbe_configure_fdir; + /* enable itr by default in dynamic mode */ wx->rx_itr_setting = 1; wx->tx_itr_setting = 1; @@ -274,6 +283,12 @@ static int txgbe_sw_init(struct wx *wx) return 0; } +static void txgbe_init_fdir(struct txgbe *txgbe) +{ + txgbe->fdir_filter_count = 0; + spin_lock_init(&txgbe->fdir_perfect_lock); +} + /** * txgbe_open - Called when a network interface is made active * @netdev: network interface device structure @@ -352,6 +367,7 @@ static int txgbe_close(struct net_device *netdev) txgbe_down(wx); wx_free_irq(wx); wx_free_resources(wx); + txgbe_fdir_filter_exit(wx); wx_control_hw(wx, false); return 0; @@ -660,6 +676,8 @@ static int txgbe_probe(struct pci_dev *pdev, txgbe->wx = wx; wx->priv = txgbe; + txgbe_init_fdir(txgbe); + err = txgbe_setup_misc_irq(txgbe); if (err) goto err_release_hw; diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h index f434a7865cb7..959102c4c379 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h @@ -89,6 +89,55 @@ #define TXGBE_XPCS_IDA_ADDR 0x13000 #define TXGBE_XPCS_IDA_DATA 0x13004 +/********************************* Flow Director *****************************/ +#define TXGBE_RDB_FDIR_DROP_QUEUE 127 +#define TXGBE_RDB_FDIR_CTL 0x19500 +#define TXGBE_RDB_FDIR_CTL_INIT_DONE BIT(3) +#define TXGBE_RDB_FDIR_CTL_PERFECT_MATCH BIT(4) +#define TXGBE_RDB_FDIR_CTL_DROP_Q(v) FIELD_PREP(GENMASK(14, 8), v) +#define TXGBE_RDB_FDIR_CTL_HASH_BITS(v) FIELD_PREP(GENMASK(23, 20), v) +#define TXGBE_RDB_FDIR_CTL_MAX_LENGTH(v) FIELD_PREP(GENMASK(27, 24), v) +#define TXGBE_RDB_FDIR_CTL_FULL_THRESH(v) FIELD_PREP(GENMASK(31, 28), v) +#define TXGBE_RDB_FDIR_IP6(_i) (0x1950C + ((_i) * 4)) /* 0-2 */ +#define TXGBE_RDB_FDIR_SA 0x19518 +#define TXGBE_RDB_FDIR_DA 0x1951C +#define TXGBE_RDB_FDIR_PORT 0x19520 +#define TXGBE_RDB_FDIR_PORT_DESTINATION_SHIFT 16 +#define TXGBE_RDB_FDIR_FLEX 0x19524 +#define TXGBE_RDB_FDIR_FLEX_FLEX_SHIFT 16 +#define TXGBE_RDB_FDIR_HASH 0x19528 +#define TXGBE_RDB_FDIR_HASH_SIG_SW_INDEX(v) FIELD_PREP(GENMASK(31, 16), v) +#define TXGBE_RDB_FDIR_HASH_BUCKET_VALID BIT(15) +#define TXGBE_RDB_FDIR_CMD 0x1952C +#define TXGBE_RDB_FDIR_CMD_CMD_MASK GENMASK(1, 0) +#define TXGBE_RDB_FDIR_CMD_CMD(v) FIELD_PREP(GENMASK(1, 0), v) +#define TXGBE_RDB_FDIR_CMD_CMD_ADD_FLOW TXGBE_RDB_FDIR_CMD_CMD(1) +#define TXGBE_RDB_FDIR_CMD_CMD_REMOVE_FLOW TXGBE_RDB_FDIR_CMD_CMD(2) +#define TXGBE_RDB_FDIR_CMD_CMD_QUERY_REM_FILT TXGBE_RDB_FDIR_CMD_CMD(3) +#define TXGBE_RDB_FDIR_CMD_FILTER_VALID BIT(2) +#define TXGBE_RDB_FDIR_CMD_FILTER_UPDATE BIT(3) +#define TXGBE_RDB_FDIR_CMD_FLOW_TYPE(v) FIELD_PREP(GENMASK(6, 5), v) +#define TXGBE_RDB_FDIR_CMD_DROP BIT(9) +#define TXGBE_RDB_FDIR_CMD_LAST BIT(11) +#define TXGBE_RDB_FDIR_CMD_QUEUE_EN BIT(15) +#define TXGBE_RDB_FDIR_CMD_RX_QUEUE(v) FIELD_PREP(GENMASK(22, 16), v) +#define TXGBE_RDB_FDIR_CMD_VT_POOL(v) FIELD_PREP(GENMASK(29, 24), v) +#define TXGBE_RDB_FDIR_DA4_MSK 0x1953C +#define TXGBE_RDB_FDIR_SA4_MSK 0x19540 +#define TXGBE_RDB_FDIR_TCP_MSK 0x19544 +#define TXGBE_RDB_FDIR_UDP_MSK 0x19548 +#define TXGBE_RDB_FDIR_SCTP_MSK 0x19560 +#define TXGBE_RDB_FDIR_HKEY 0x19568 +#define TXGBE_RDB_FDIR_SKEY 0x1956C +#define TXGBE_RDB_FDIR_OTHER_MSK 0x19570 +#define TXGBE_RDB_FDIR_OTHER_MSK_POOL BIT(2) +#define TXGBE_RDB_FDIR_OTHER_MSK_L4P BIT(3) +#define TXGBE_RDB_FDIR_FLEX_CFG(_i) (0x19580 + ((_i) * 4)) +#define TXGBE_RDB_FDIR_FLEX_CFG_FIELD0 GENMASK(7, 0) +#define TXGBE_RDB_FDIR_FLEX_CFG_BASE_MAC FIELD_PREP(GENMASK(1, 0), 0) +#define TXGBE_RDB_FDIR_FLEX_CFG_MSK BIT(2) +#define TXGBE_RDB_FDIR_FLEX_CFG_OFST(v) FIELD_PREP(GENMASK(7, 3), v) + /* Checksum and EEPROM pointers */ #define TXGBE_EEPROM_LAST_WORD 0x800 #define TXGBE_EEPROM_CHECKSUM 0x2F @@ -112,6 +161,98 @@ #define TXGBE_SP_RX_PB_SIZE 512 #define TXGBE_SP_TDB_PB_SZ (160 * 1024) /* 160KB Packet Buffer */ +#define TXGBE_DEFAULT_ATR_SAMPLE_RATE 20 + +/* Software ATR hash keys */ +#define TXGBE_ATR_BUCKET_HASH_KEY 0x3DAD14E2 +#define TXGBE_ATR_SIGNATURE_HASH_KEY 0x174D3614 + +/* Software ATR input stream values and masks */ +#define TXGBE_ATR_HASH_MASK 0x7fff +#define TXGBE_ATR_L4TYPE_MASK 0x3 +#define TXGBE_ATR_L4TYPE_UDP 0x1 +#define TXGBE_ATR_L4TYPE_TCP 0x2 +#define TXGBE_ATR_L4TYPE_SCTP 0x3 +#define TXGBE_ATR_L4TYPE_IPV6_MASK 0x4 +#define TXGBE_ATR_L4TYPE_TUNNEL_MASK 0x10 + +enum txgbe_atr_flow_type { + TXGBE_ATR_FLOW_TYPE_IPV4 = 0x0, + TXGBE_ATR_FLOW_TYPE_UDPV4 = 0x1, + TXGBE_ATR_FLOW_TYPE_TCPV4 = 0x2, + TXGBE_ATR_FLOW_TYPE_SCTPV4 = 0x3, + TXGBE_ATR_FLOW_TYPE_IPV6 = 0x4, + TXGBE_ATR_FLOW_TYPE_UDPV6 = 0x5, + TXGBE_ATR_FLOW_TYPE_TCPV6 = 0x6, + TXGBE_ATR_FLOW_TYPE_SCTPV6 = 0x7, + TXGBE_ATR_FLOW_TYPE_TUNNELED_IPV4 = 0x10, + TXGBE_ATR_FLOW_TYPE_TUNNELED_UDPV4 = 0x11, + TXGBE_ATR_FLOW_TYPE_TUNNELED_TCPV4 = 0x12, + TXGBE_ATR_FLOW_TYPE_TUNNELED_SCTPV4 = 0x13, + TXGBE_ATR_FLOW_TYPE_TUNNELED_IPV6 = 0x14, + TXGBE_ATR_FLOW_TYPE_TUNNELED_UDPV6 = 0x15, + TXGBE_ATR_FLOW_TYPE_TUNNELED_TCPV6 = 0x16, + TXGBE_ATR_FLOW_TYPE_TUNNELED_SCTPV6 = 0x17, +}; + +/* Flow Director ATR input struct. */ +union txgbe_atr_input { + /* Byte layout in order, all values with MSB first: + * + * vm_pool - 1 byte + * flow_type - 1 byte + * vlan_id - 2 bytes + * dst_ip - 16 bytes + * src_ip - 16 bytes + * src_port - 2 bytes + * dst_port - 2 bytes + * flex_bytes - 2 bytes + * bkt_hash - 2 bytes + */ + struct { + u8 vm_pool; + u8 flow_type; + __be16 vlan_id; + __be32 dst_ip[4]; + __be32 src_ip[4]; + __be16 src_port; + __be16 dst_port; + __be16 flex_bytes; + __be16 bkt_hash; + } formatted; + __be32 dword_stream[11]; +}; + +/* Flow Director compressed ATR hash input struct */ +union txgbe_atr_hash_dword { + struct { + u8 vm_pool; + u8 flow_type; + __be16 vlan_id; + } formatted; + __be32 ip; + struct { + __be16 src; + __be16 dst; + } port; + __be16 flex_bytes; + __be32 dword; +}; + +enum txgbe_fdir_pballoc_type { + TXGBE_FDIR_PBALLOC_NONE = 0, + TXGBE_FDIR_PBALLOC_64K = 1, + TXGBE_FDIR_PBALLOC_128K = 2, + TXGBE_FDIR_PBALLOC_256K = 3, +}; + +struct txgbe_fdir_filter { + struct hlist_node fdir_node; + union txgbe_atr_input filter; + u16 sw_idx; + u16 action; +}; + /* TX/RX descriptor defines */ #define TXGBE_DEFAULT_TXD 512 #define TXGBE_DEFAULT_TX_WORK 256 @@ -196,6 +337,12 @@ struct txgbe { struct gpio_chip *gpio; unsigned int gpio_irq; unsigned int link_irq; + + /* flow director */ + struct hlist_head fdir_filter_list; + union txgbe_atr_input fdir_mask; + int fdir_filter_count; + spinlock_t fdir_perfect_lock; /* spinlock for FDIR */ }; #endif /* _TXGBE_TYPE_H_ */ diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index c29809cd9201..e342f387c3dd 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1945,9 +1945,9 @@ axienet_ethtools_set_coalesce(struct net_device *ndev, struct axienet_local *lp = netdev_priv(ndev); if (netif_running(ndev)) { - netdev_err(ndev, - "Please stop netif before applying configuration\n"); - return -EFAULT; + NL_SET_ERR_MSG(extack, + "Please stop netif before applying configuration"); + return -EBUSY; } if (ecoalesce->rx_max_coalesced_frames) @@ -2254,7 +2254,6 @@ static int axienet_probe(struct platform_device *pdev) platform_set_drvdata(pdev, ndev); SET_NETDEV_DEV(ndev, &pdev->dev); - ndev->flags &= ~IFF_MULTICAST; /* clear multicast */ ndev->features = NETIF_F_SG; ndev->ethtool_ops = &axienet_ethtool_ops; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 51495cb4b9be..838e85ddec67 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -815,6 +815,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct geneve_dev *geneve, const struct ip_tunnel_info *info) { + bool inner_proto_inherit = geneve->cfg.inner_proto_inherit; bool xnet = !net_eq(geneve->net, dev_net(geneve->dev)); struct geneve_sock *gs4 = rcu_dereference(geneve->sock4); const struct ip_tunnel_key *key = &info->key; @@ -826,7 +827,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, __be16 sport; int err; - if (!skb_vlan_inet_prepare(skb)) + if (!skb_vlan_inet_prepare(skb, inner_proto_inherit)) return -EINVAL; if (!gs4) @@ -908,7 +909,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, } err = geneve_build_skb(&rt->dst, skb, info, xnet, sizeof(struct iphdr), - geneve->cfg.inner_proto_inherit); + inner_proto_inherit); if (unlikely(err)) return err; @@ -925,6 +926,7 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct geneve_dev *geneve, const struct ip_tunnel_info *info) { + bool inner_proto_inherit = geneve->cfg.inner_proto_inherit; bool xnet = !net_eq(geneve->net, dev_net(geneve->dev)); struct geneve_sock *gs6 = rcu_dereference(geneve->sock6); const struct ip_tunnel_key *key = &info->key; @@ -935,7 +937,7 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, __be16 sport; int err; - if (!skb_vlan_inet_prepare(skb)) + if (!skb_vlan_inet_prepare(skb, inner_proto_inherit)) return -EINVAL; if (!gs6) @@ -997,7 +999,7 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, ttl = ttl ? : ip6_dst_hoplimit(dst); } err = geneve_build_skb(dst, skb, info, xnet, sizeof(struct ipv6hdr), - geneve->cfg.inner_proto_inherit); + inner_proto_inherit); if (unlikely(err)) return err; diff --git a/drivers/net/mctp/mctp-i2c.c b/drivers/net/mctp/mctp-i2c.c index b37a9e4bade4..f9afea25044f 100644 --- a/drivers/net/mctp/mctp-i2c.c +++ b/drivers/net/mctp/mctp-i2c.c @@ -1042,8 +1042,8 @@ static struct notifier_block mctp_i2c_notifier = { }; static const struct i2c_device_id mctp_i2c_id[] = { - { "mctp-i2c-interface", 0 }, - {}, + { "mctp-i2c-interface" }, + {} }; MODULE_DEVICE_TABLE(i2c, mctp_i2c_id); diff --git a/drivers/net/mdio/mdio-mscc-miim.c b/drivers/net/mdio/mdio-mscc-miim.c index c29377c85307..62c47e0dd142 100644 --- a/drivers/net/mdio/mdio-mscc-miim.c +++ b/drivers/net/mdio/mdio-mscc-miim.c @@ -19,6 +19,7 @@ #include <linux/platform_device.h> #include <linux/property.h> #include <linux/regmap.h> +#include <linux/reset.h> #define MSCC_MIIM_REG_STATUS 0x0 #define MSCC_MIIM_STATUS_STAT_PENDING BIT(2) @@ -271,10 +272,17 @@ static int mscc_miim_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; struct regmap *mii_regmap, *phy_regmap; struct device *dev = &pdev->dev; + struct reset_control *reset; struct mscc_miim_dev *miim; struct mii_bus *bus; int ret; + reset = devm_reset_control_get_optional_shared(dev, "switch"); + if (IS_ERR(reset)) + return dev_err_probe(dev, PTR_ERR(reset), "Failed to get reset\n"); + + reset_control_reset(reset); + mii_regmap = ocelot_regmap_from_resource(pdev, 0, &mscc_miim_regmap_config); if (IS_ERR(mii_regmap)) diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index c22897bf5509..017a6102be0a 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -324,7 +324,8 @@ static int nsim_get_iflink(const struct net_device *dev) rcu_read_lock(); peer = rcu_dereference(nsim->peer); - iflink = peer ? READ_ONCE(peer->netdev->ifindex) : 0; + iflink = peer ? READ_ONCE(peer->netdev->ifindex) : + READ_ONCE(dev->ifindex); rcu_read_unlock(); return iflink; diff --git a/drivers/net/phy/dp83tg720.c b/drivers/net/phy/dp83tg720.c index 326c9770a6dc..c706429b225a 100644 --- a/drivers/net/phy/dp83tg720.c +++ b/drivers/net/phy/dp83tg720.c @@ -17,6 +17,11 @@ #define DP83TG720S_PHY_RESET 0x1f #define DP83TG720S_HW_RESET BIT(15) +#define DP83TG720S_LPS_CFG3 0x18c +/* Power modes are documented as bit fields but used as values */ +/* Power Mode 0 is Normal mode */ +#define DP83TG720S_LPS_CFG3_PWR_MODE_0 BIT(0) + #define DP83TG720S_RGMII_DELAY_CTRL 0x602 /* In RGMII mode, Enable or disable the internal delay for RXD */ #define DP83TG720S_RGMII_RX_CLK_SEL BIT(1) @@ -31,11 +36,20 @@ static int dp83tg720_config_aneg(struct phy_device *phydev) { + int ret; + /* Autoneg is not supported and this PHY supports only one speed. * We need to care only about master/slave configuration if it was * changed by user. */ - return genphy_c45_pma_baset1_setup_master_slave(phydev); + ret = genphy_c45_pma_baset1_setup_master_slave(phydev); + if (ret) + return ret; + + /* Re-read role configuration to make changes visible even if + * the link is in administrative down state. + */ + return genphy_c45_pma_baset1_read_master_slave(phydev); } static int dp83tg720_read_status(struct phy_device *phydev) @@ -64,6 +78,8 @@ static int dp83tg720_read_status(struct phy_device *phydev) return ret; /* After HW reset we need to restore master/slave configuration. + * genphy_c45_pma_baset1_read_master_slave() call will be done + * by the dp83tg720_config_aneg() function. */ ret = dp83tg720_config_aneg(phydev); if (ret) @@ -154,10 +170,24 @@ static int dp83tg720_config_init(struct phy_device *phydev) */ usleep_range(1000, 2000); - if (phy_interface_is_rgmii(phydev)) - return dp83tg720_config_rgmii_delay(phydev); + if (phy_interface_is_rgmii(phydev)) { + ret = dp83tg720_config_rgmii_delay(phydev); + if (ret) + return ret; + } + + /* In case the PHY is bootstrapped in managed mode, we need to + * wake it. + */ + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_LPS_CFG3, + DP83TG720S_LPS_CFG3_PWR_MODE_0); + if (ret) + return ret; - return 0; + /* Make role configuration visible for ethtool on init and after + * rest. + */ + return genphy_c45_pma_baset1_read_master_slave(phydev); } static struct phy_driver dp83tg720_driver[] = { diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 5aada7cf3da7..ebafedde0ab7 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -5607,6 +5607,7 @@ static struct mdio_device_id __maybe_unused micrel_tbl[] = { { PHY_ID_KSZ8081, MICREL_PHY_ID_MASK }, { PHY_ID_KSZ8873MLL, MICREL_PHY_ID_MASK }, { PHY_ID_KSZ886X, MICREL_PHY_ID_MASK }, + { PHY_ID_KSZ9477, 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/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c index b2d36a3a96f1..e5f8ac4b4604 100644 --- a/drivers/net/phy/mxl-gpy.c +++ b/drivers/net/phy/mxl-gpy.c @@ -107,6 +107,7 @@ struct gpy_priv { u8 fw_major; u8 fw_minor; + u32 wolopts; /* It takes 3 seconds to fully switch out of loopback mode before * it can safely re-enter loopback mode. Record the time when @@ -221,6 +222,15 @@ static int gpy_hwmon_register(struct phy_device *phydev) } #endif +static int gpy_ack_interrupt(struct phy_device *phydev) +{ + int ret; + + /* Clear all pending interrupts */ + ret = phy_read(phydev, PHY_ISTAT); + return ret < 0 ? ret : 0; +} + static int gpy_mbox_read(struct phy_device *phydev, u32 addr) { struct gpy_priv *priv = phydev->priv; @@ -262,16 +272,8 @@ out: static int gpy_config_init(struct phy_device *phydev) { - int ret; - - /* Mask all interrupts */ - ret = phy_write(phydev, PHY_IMASK, 0); - if (ret) - return ret; - - /* Clear all pending interrupts */ - ret = phy_read(phydev, PHY_ISTAT); - return ret < 0 ? ret : 0; + /* Nothing to configure. Configuration Requirement Placeholder */ + return 0; } static int gpy21x_config_init(struct phy_device *phydev) @@ -627,11 +629,23 @@ static int gpy_read_status(struct phy_device *phydev) static int gpy_config_intr(struct phy_device *phydev) { + struct gpy_priv *priv = phydev->priv; u16 mask = 0; + int ret; + + ret = gpy_ack_interrupt(phydev); + if (ret) + return ret; if (phydev->interrupts == PHY_INTERRUPT_ENABLED) mask = PHY_IMASK_MASK; + if (priv->wolopts & WAKE_MAGIC) + mask |= PHY_IMASK_WOL; + + if (priv->wolopts & WAKE_PHY) + mask |= PHY_IMASK_LSTC; + return phy_write(phydev, PHY_IMASK, mask); } @@ -678,6 +692,7 @@ static int gpy_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol) { struct net_device *attach_dev = phydev->attached_dev; + struct gpy_priv *priv = phydev->priv; int ret; if (wol->wolopts & WAKE_MAGIC) { @@ -725,6 +740,8 @@ static int gpy_set_wol(struct phy_device *phydev, ret = phy_read(phydev, PHY_ISTAT); if (ret < 0) return ret; + + priv->wolopts |= WAKE_MAGIC; } else { /* Disable magic packet matching */ ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND2, @@ -732,6 +749,13 @@ static int gpy_set_wol(struct phy_device *phydev, WOL_EN); if (ret < 0) return ret; + + /* Disable the WOL interrupt */ + ret = phy_clear_bits(phydev, PHY_IMASK, PHY_IMASK_WOL); + if (ret < 0) + return ret; + + priv->wolopts &= ~WAKE_MAGIC; } if (wol->wolopts & WAKE_PHY) { @@ -748,9 +772,11 @@ static int gpy_set_wol(struct phy_device *phydev, if (ret & (PHY_IMASK_MASK & ~PHY_IMASK_LSTC)) phy_trigger_machine(phydev); + priv->wolopts |= WAKE_PHY; return 0; } + priv->wolopts &= ~WAKE_PHY; /* Disable the link state change interrupt */ return phy_clear_bits(phydev, PHY_IMASK, PHY_IMASK_LSTC); } @@ -758,18 +784,10 @@ static int gpy_set_wol(struct phy_device *phydev, static void gpy_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol) { - int ret; + struct gpy_priv *priv = phydev->priv; wol->supported = WAKE_MAGIC | WAKE_PHY; - wol->wolopts = 0; - - ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, VPSPEC2_WOL_CTL); - if (ret & WOL_EN) - wol->wolopts |= WAKE_MAGIC; - - ret = phy_read(phydev, PHY_IMASK); - if (ret & PHY_IMASK_LSTC) - wol->wolopts |= WAKE_PHY; + wol->wolopts = priv->wolopts; } static int gpy_loopback(struct phy_device *phydev, bool enable) diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 15f349e5995a..a235ea2264a7 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -141,6 +141,7 @@ int phy_interface_num_ports(phy_interface_t interface) return 1; case PHY_INTERFACE_MODE_QSGMII: case PHY_INTERFACE_MODE_QUSGMII: + case PHY_INTERFACE_MODE_10G_QXGMII: return 4; case PHY_INTERFACE_MODE_PSGMII: return 5; diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 02427378acfd..6c24c48dcf0f 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -231,6 +231,7 @@ static int phylink_interface_max_speed(phy_interface_t interface) return SPEED_1000; case PHY_INTERFACE_MODE_2500BASEX: + case PHY_INTERFACE_MODE_10G_QXGMII: return SPEED_2500; case PHY_INTERFACE_MODE_5GBASER: @@ -500,7 +501,11 @@ static unsigned long phylink_get_capabilities(phy_interface_t interface, switch (interface) { case PHY_INTERFACE_MODE_USXGMII: - caps |= MAC_10000FD | MAC_5000FD | MAC_2500FD; + caps |= MAC_10000FD | MAC_5000FD; + fallthrough; + + case PHY_INTERFACE_MODE_10G_QXGMII: + caps |= MAC_2500FD; fallthrough; case PHY_INTERFACE_MODE_RGMII_TXID: @@ -926,6 +931,7 @@ static int phylink_parse_mode(struct phylink *pl, case PHY_INTERFACE_MODE_5GBASER: case PHY_INTERFACE_MODE_25GBASER: case PHY_INTERFACE_MODE_USXGMII: + case PHY_INTERFACE_MODE_10G_QXGMII: case PHY_INTERFACE_MODE_10GKR: case PHY_INTERFACE_MODE_10GBASER: case PHY_INTERFACE_MODE_XLGMII: @@ -1124,6 +1130,7 @@ static unsigned int phylink_pcs_neg_mode(unsigned int mode, case PHY_INTERFACE_MODE_QSGMII: case PHY_INTERFACE_MODE_QUSGMII: case PHY_INTERFACE_MODE_USXGMII: + case PHY_INTERFACE_MODE_10G_QXGMII: /* These protocols are designed for use with a PHY which * communicates its negotiation result back to the MAC via * inband communication. Note: there exist PHYs that run diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 7ab41f95dae5..2174893c974f 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -1318,6 +1318,14 @@ static struct phy_driver realtek_drvs[] = { .read_page = rtl821x_read_page, .write_page = rtl821x_write_page, }, { + PHY_ID_MATCH_EXACT(0x001ccad0), + .name = "RTL8224 2.5Gbps PHY", + .get_features = rtl822x_c45_get_features, + .config_aneg = rtl822x_c45_config_aneg, + .read_status = rtl822x_c45_read_status, + .suspend = genphy_c45_pma_suspend, + .resume = rtlgen_c45_resume, + }, { PHY_ID_MATCH_EXACT(0x001cc961), .name = "RTL8366RB Gigabit Ethernet", .config_init = &rtl8366rb_config_init, diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 3f9cbd797fd6..a5684ef5884b 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -2429,8 +2429,7 @@ static void sfp_sm_module(struct sfp *sfp, unsigned int event) /* Handle remove event globally, it resets this state machine */ if (event == SFP_E_REMOVE) { - if (sfp->sm_mod_state > SFP_MOD_PROBE) - sfp_sm_mod_remove(sfp); + sfp_sm_mod_remove(sfp); sfp_sm_mod_next(sfp, SFP_MOD_EMPTY, 0); return; } diff --git a/drivers/net/pse-pd/Kconfig b/drivers/net/pse-pd/Kconfig index 577ea904b3d9..7fab916a7f46 100644 --- a/drivers/net/pse-pd/Kconfig +++ b/drivers/net/pse-pd/Kconfig @@ -23,6 +23,7 @@ config PSE_REGULATOR config PSE_PD692X0 tristate "PD692X0 PSE controller" depends on I2C + select FW_LOADER select FW_UPLOAD help This module provides support for PD692x0 regulator based Ethernet diff --git a/drivers/net/pse-pd/pd692x0.c b/drivers/net/pse-pd/pd692x0.c index 6488b941703c..820358b71f0f 100644 --- a/drivers/net/pse-pd/pd692x0.c +++ b/drivers/net/pse-pd/pd692x0.c @@ -1194,8 +1194,8 @@ static void pd692x0_i2c_remove(struct i2c_client *client) } static const struct i2c_device_id pd692x0_id[] = { - { PD692X0_PSE_NAME, 0 }, - { }, + { PD692X0_PSE_NAME }, + { } }; MODULE_DEVICE_TABLE(i2c, pd692x0_id); diff --git a/drivers/net/pse-pd/tps23881.c b/drivers/net/pse-pd/tps23881.c index 98ffbb1bbf13..61f6ad9c1934 100644 --- a/drivers/net/pse-pd/tps23881.c +++ b/drivers/net/pse-pd/tps23881.c @@ -794,8 +794,8 @@ static int tps23881_i2c_probe(struct i2c_client *client) } static const struct i2c_device_id tps23881_id[] = { - { "tps23881", 0 }, - { }, + { "tps23881" }, + { } }; MODULE_DEVICE_TABLE(i2c, tps23881_id); diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 51c295e1e823..b034ef8a73ea 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -174,7 +174,6 @@ struct ax88179_data { u32 wol_supported; u32 wolopts; u8 disconnecting; - u8 initialized; }; struct ax88179_int_data { @@ -327,7 +326,8 @@ static void ax88179_status(struct usbnet *dev, struct urb *urb) if (netif_carrier_ok(dev->net) != link) { usbnet_link_change(dev, link, 1); - netdev_info(dev->net, "ax88179 - Link status is: %d\n", link); + if (!link) + netdev_info(dev->net, "ax88179 - Link status is: 0\n"); } } @@ -1543,6 +1543,7 @@ static int ax88179_link_reset(struct usbnet *dev) GMII_PHY_PHYSR, 2, &tmp16); if (!(tmp16 & GMII_PHY_PHYSR_LINK)) { + netdev_info(dev->net, "ax88179 - Link status is: 0\n"); return 0; } else if (GMII_PHY_PHYSR_GIGA == (tmp16 & GMII_PHY_PHYSR_SMASK)) { mode |= AX_MEDIUM_GIGAMODE | AX_MEDIUM_EN_125MHZ; @@ -1580,6 +1581,8 @@ static int ax88179_link_reset(struct usbnet *dev) netif_carrier_on(dev->net); + netdev_info(dev->net, "ax88179 - Link status is: 1\n"); + return 0; } @@ -1678,12 +1681,21 @@ static int ax88179_reset(struct usbnet *dev) static int ax88179_net_reset(struct usbnet *dev) { - struct ax88179_data *ax179_data = dev->driver_priv; + u16 tmp16; - if (ax179_data->initialized) + ax88179_read_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, GMII_PHY_PHYSR, + 2, &tmp16); + if (tmp16) { + ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_MEDIUM_STATUS_MODE, + 2, 2, &tmp16); + if (!(tmp16 & AX_MEDIUM_RECEIVE_EN)) { + tmp16 |= AX_MEDIUM_RECEIVE_EN; + ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_MEDIUM_STATUS_MODE, + 2, 2, &tmp16); + } + } else { ax88179_reset(dev); - else - ax179_data->initialized = 1; + } return 0; } diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index bf76ecccc2e6..d5c47a2a62dc 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -933,7 +933,8 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ cdc_ncm_find_endpoints(dev, ctx->data); cdc_ncm_find_endpoints(dev, ctx->control); - if (!dev->in || !dev->out || !dev->status) { + if (!dev->in || !dev->out || + (!dev->status && dev->driver_info->flags & FLAG_LINK_INTR)) { dev_dbg(&intf->dev, "failed to collect endpoints\n"); goto error2; } @@ -1925,6 +1926,34 @@ static const struct driver_info cdc_ncm_zlp_info = { .set_rx_mode = usbnet_cdc_update_filter, }; +/* Same as cdc_ncm_info, but with FLAG_SEND_ZLP */ +static const struct driver_info apple_tethering_interface_info = { + .description = "CDC NCM (Apple Tethering)", + .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET + | FLAG_LINK_INTR | FLAG_ETHER | FLAG_SEND_ZLP, + .bind = cdc_ncm_bind, + .unbind = cdc_ncm_unbind, + .manage_power = usbnet_manage_power, + .status = cdc_ncm_status, + .rx_fixup = cdc_ncm_rx_fixup, + .tx_fixup = cdc_ncm_tx_fixup, + .set_rx_mode = usbnet_cdc_update_filter, +}; + +/* Same as apple_tethering_interface_info, but without FLAG_LINK_INTR */ +static const struct driver_info apple_private_interface_info = { + .description = "CDC NCM (Apple Private)", + .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET + | FLAG_ETHER | FLAG_SEND_ZLP, + .bind = cdc_ncm_bind, + .unbind = cdc_ncm_unbind, + .manage_power = usbnet_manage_power, + .status = cdc_ncm_status, + .rx_fixup = cdc_ncm_rx_fixup, + .tx_fixup = cdc_ncm_tx_fixup, + .set_rx_mode = usbnet_cdc_update_filter, +}; + /* Same as cdc_ncm_info, but with FLAG_WWAN */ static const struct driver_info wwan_info = { .description = "Mobile Broadband Network Device", @@ -1954,6 +1983,22 @@ static const struct driver_info wwan_noarp_info = { }; static const struct usb_device_id cdc_devs[] = { + /* iPhone */ + { USB_DEVICE_INTERFACE_NUMBER(0x05ac, 0x12a8, 2), + .driver_info = (unsigned long)&apple_tethering_interface_info, + }, + { USB_DEVICE_INTERFACE_NUMBER(0x05ac, 0x12a8, 4), + .driver_info = (unsigned long)&apple_private_interface_info, + }, + + /* iPad */ + { USB_DEVICE_INTERFACE_NUMBER(0x05ac, 0x12ab, 2), + .driver_info = (unsigned long)&apple_tethering_interface_info, + }, + { USB_DEVICE_INTERFACE_NUMBER(0x05ac, 0x12ab, 4), + .driver_info = (unsigned long)&apple_private_interface_info, + }, + /* Ericsson MBM devices like F5521gw */ { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_VENDOR, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 663e46348ce3..386d62769ded 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1372,6 +1372,8 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x1bc7, 0x1260, 2)}, /* Telit LE910Cx */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1261, 2)}, /* Telit LE910Cx */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1900, 1)}, /* Telit LN940 series */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x3000, 0)}, /* Telit FN912 series */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x3001, 0)}, /* Telit FN912 series */ {QMI_FIXED_INTF(0x1c9e, 0x9801, 3)}, /* Telewell TW-3G HSPA+ */ {QMI_FIXED_INTF(0x1c9e, 0x9803, 4)}, /* Telewell TW-3G HSPA+ */ {QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)}, /* XS Stick W100-2 from 4G Systems */ diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index 97afd7335d86..01a3b2417a54 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -778,7 +778,8 @@ static int rtl8150_get_link_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *ecmd) { rtl8150_t *dev = netdev_priv(netdev); - short lpa, bmcr; + short lpa = 0; + short bmcr = 0; u32 supported; supported = (SUPPORTED_10baseT_Half | diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 61a57d134544..0b4747e81464 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -47,7 +47,8 @@ module_param(napi_tx, bool, 0644); #define VIRTIO_XDP_TX BIT(0) #define VIRTIO_XDP_REDIR BIT(1) -#define VIRTIO_XDP_FLAG BIT(0) +#define VIRTIO_XDP_FLAG BIT(0) +#define VIRTIO_ORPHAN_FLAG BIT(1) /* RX packet size EWMA. The average packet size is used to determine the packet * buffer size when refilling RX rings. As the entire RX ring may be refilled @@ -85,6 +86,8 @@ struct virtnet_stat_desc { struct virtnet_sq_free_stats { u64 packets; u64 bytes; + u64 napi_packets; + u64 napi_bytes; }; struct virtnet_sq_stats { @@ -506,29 +509,50 @@ static struct xdp_frame *ptr_to_xdp(void *ptr) return (struct xdp_frame *)((unsigned long)ptr & ~VIRTIO_XDP_FLAG); } -static void __free_old_xmit(struct send_queue *sq, bool in_napi, - struct virtnet_sq_free_stats *stats) +static bool is_orphan_skb(void *ptr) +{ + return (unsigned long)ptr & VIRTIO_ORPHAN_FLAG; +} + +static void *skb_to_ptr(struct sk_buff *skb, bool orphan) +{ + return (void *)((unsigned long)skb | (orphan ? VIRTIO_ORPHAN_FLAG : 0)); +} + +static struct sk_buff *ptr_to_skb(void *ptr) +{ + return (struct sk_buff *)((unsigned long)ptr & ~VIRTIO_ORPHAN_FLAG); +} + +static void __free_old_xmit(struct send_queue *sq, struct netdev_queue *txq, + bool in_napi, struct virtnet_sq_free_stats *stats) { unsigned int len; void *ptr; while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) { - ++stats->packets; - if (!is_xdp_frame(ptr)) { - struct sk_buff *skb = ptr; + struct sk_buff *skb = ptr_to_skb(ptr); pr_debug("Sent skb %p\n", skb); - stats->bytes += skb->len; + if (is_orphan_skb(ptr)) { + stats->packets++; + stats->bytes += skb->len; + } else { + stats->napi_packets++; + stats->napi_bytes += skb->len; + } napi_consume_skb(skb, in_napi); } else { struct xdp_frame *frame = ptr_to_xdp(ptr); + stats->packets++; stats->bytes += xdp_get_frame_len(frame); xdp_return_frame(frame); } } + netdev_tx_completed_queue(txq, stats->napi_packets, stats->napi_bytes); } /* Converting between virtqueue no. and kernel tx/rx queue no. @@ -955,21 +979,22 @@ static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf) virtnet_rq_free_buf(vi, rq, buf); } -static void free_old_xmit(struct send_queue *sq, bool in_napi) +static void free_old_xmit(struct send_queue *sq, struct netdev_queue *txq, + bool in_napi) { struct virtnet_sq_free_stats stats = {0}; - __free_old_xmit(sq, in_napi, &stats); + __free_old_xmit(sq, txq, in_napi, &stats); /* Avoid overhead when no packets have been processed * happens when called speculatively from start_xmit. */ - if (!stats.packets) + if (!stats.packets && !stats.napi_packets) return; u64_stats_update_begin(&sq->stats.syncp); - u64_stats_add(&sq->stats.bytes, stats.bytes); - u64_stats_add(&sq->stats.packets, stats.packets); + u64_stats_add(&sq->stats.bytes, stats.bytes + stats.napi_bytes); + u64_stats_add(&sq->stats.packets, stats.packets + stats.napi_packets); u64_stats_update_end(&sq->stats.syncp); } @@ -1003,7 +1028,9 @@ static void check_sq_full_and_disable(struct virtnet_info *vi, * early means 16 slots are typically wasted. */ if (sq->vq->num_free < 2+MAX_SKB_FRAGS) { - netif_stop_subqueue(dev, qnum); + struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum); + + netif_tx_stop_queue(txq); u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.stop); u64_stats_update_end(&sq->stats.syncp); @@ -1012,7 +1039,7 @@ static void check_sq_full_and_disable(struct virtnet_info *vi, virtqueue_napi_schedule(&sq->napi, sq->vq); } else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) { /* More just got used, free them then recheck. */ - free_old_xmit(sq, false); + free_old_xmit(sq, txq, false); if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) { netif_start_subqueue(dev, qnum); u64_stats_update_begin(&sq->stats.syncp); @@ -1138,7 +1165,8 @@ static int virtnet_xdp_xmit(struct net_device *dev, } /* Free up any pending old buffers before queueing new ones. */ - __free_old_xmit(sq, false, &stats); + __free_old_xmit(sq, netdev_get_tx_queue(dev, sq - vi->sq), + false, &stats); for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; @@ -1360,6 +1388,10 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev, if (unlikely(hdr->hdr.gso_type)) goto err_xdp; + /* Partially checksummed packets must be dropped. */ + if (unlikely(hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM)) + goto err_xdp; + buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); @@ -1677,6 +1709,10 @@ static void *mergeable_xdp_get_buf(struct virtnet_info *vi, if (unlikely(hdr->hdr.gso_type)) return NULL; + /* Partially checksummed packets must be dropped. */ + if (unlikely(hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM)) + return NULL; + /* Now XDP core assumes frag size is PAGE_SIZE, but buffers * with headroom may add hole in truesize, which * make their length exceed PAGE_SIZE. So we disabled the @@ -1943,6 +1979,7 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, struct net_device *dev = vi->dev; struct sk_buff *skb; struct virtio_net_common_hdr *hdr; + u8 flags; if (unlikely(len < vi->hdr_len + ETH_HLEN)) { pr_debug("%s: short packet %i\n", dev->name, len); @@ -1951,6 +1988,15 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, return; } + /* 1. Save the flags early, as the XDP program might overwrite them. + * These flags ensure packets marked as VIRTIO_NET_HDR_F_DATA_VALID + * stay valid after XDP processing. + * 2. XDP doesn't work with partially checksummed packets (refer to + * virtnet_xdp_set()), so packets marked as + * VIRTIO_NET_HDR_F_NEEDS_CSUM get dropped during XDP processing. + */ + flags = ((struct virtio_net_common_hdr *)buf)->hdr.flags; + if (vi->mergeable_rx_bufs) skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit, stats); @@ -1966,7 +2012,7 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, if (dev->features & NETIF_F_RXHASH && vi->has_rss_hash_report) virtio_skb_set_hash(&hdr->hash_v1_hdr, skb); - if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID) + if (flags & VIRTIO_NET_HDR_F_DATA_VALID) skb->ip_summed = CHECKSUM_UNNECESSARY; if (virtio_net_hdr_to_skb(skb, &hdr->hdr, @@ -2313,7 +2359,7 @@ static void virtnet_poll_cleantx(struct receive_queue *rq) do { virtqueue_disable_cb(sq->vq); - free_old_xmit(sq, true); + free_old_xmit(sq, txq, true); } while (unlikely(!virtqueue_enable_cb_delayed(sq->vq))); if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) { @@ -2336,12 +2382,13 @@ static void virtnet_rx_dim_update(struct virtnet_info *vi, struct receive_queue if (!rq->packets_in_napi) return; - u64_stats_update_begin(&rq->stats.syncp); + /* Don't need protection when fetching stats, since fetcher and + * updater of the stats are in same context + */ dim_update_sample(rq->calls, u64_stats_read(&rq->stats.packets), u64_stats_read(&rq->stats.bytes), &cur_sample); - u64_stats_update_end(&rq->stats.syncp); net_dim(&rq->dim, cur_sample); rq->packets_in_napi = 0; @@ -2412,6 +2459,7 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index) goto err_xdp_reg_mem_model; virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi); + netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, qp_index)); virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi); return 0; @@ -2421,6 +2469,13 @@ err_xdp_reg_mem_model: return err; } +static void virtnet_cancel_dim(struct virtnet_info *vi, struct dim *dim) +{ + if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) + return; + net_dim_work_cancel(dim); +} + static int virtnet_open(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); @@ -2447,7 +2502,7 @@ err_enable_qp: for (i--; i >= 0; i--) { virtnet_disable_queue_pair(vi, i); - cancel_work_sync(&vi->rq[i].dim.work); + virtnet_cancel_dim(vi, &vi->rq[i].dim); } return err; @@ -2471,7 +2526,7 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget) txq = netdev_get_tx_queue(vi->dev, index); __netif_tx_lock(txq, raw_smp_processor_id()); virtqueue_disable_cb(sq->vq); - free_old_xmit(sq, true); + free_old_xmit(sq, txq, true); if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) { if (netif_tx_queue_stopped(txq)) { @@ -2505,7 +2560,7 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget) return 0; } -static int xmit_skb(struct send_queue *sq, struct sk_buff *skb) +static int xmit_skb(struct send_queue *sq, struct sk_buff *skb, bool orphan) { struct virtio_net_hdr_mrg_rxbuf *hdr; const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest; @@ -2549,7 +2604,8 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb) return num_sg; num_sg++; } - return virtqueue_add_outbuf(sq->vq, sq->sg, num_sg, skb, GFP_ATOMIC); + return virtqueue_add_outbuf(sq->vq, sq->sg, num_sg, + skb_to_ptr(skb, orphan), GFP_ATOMIC); } static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) @@ -2559,24 +2615,25 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) struct send_queue *sq = &vi->sq[qnum]; int err; struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum); - bool kick = !netdev_xmit_more(); + bool xmit_more = netdev_xmit_more(); bool use_napi = sq->napi.weight; + bool kick; /* Free up any pending old buffers before queueing new ones. */ do { if (use_napi) virtqueue_disable_cb(sq->vq); - free_old_xmit(sq, false); + free_old_xmit(sq, txq, false); - } while (use_napi && kick && + } while (use_napi && !xmit_more && unlikely(!virtqueue_enable_cb_delayed(sq->vq))); /* timestamp packet in software */ skb_tx_timestamp(skb); /* Try to transmit */ - err = xmit_skb(sq, skb); + err = xmit_skb(sq, skb, !use_napi); /* This should not happen! */ if (unlikely(err)) { @@ -2598,7 +2655,9 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) check_sq_full_and_disable(vi, dev, sq); - if (kick || netif_xmit_stopped(txq)) { + kick = use_napi ? __netdev_tx_sent_queue(txq, skb->len, xmit_more) : + !xmit_more || netif_xmit_stopped(txq); + if (kick) { if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) { u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.kicks); @@ -2619,7 +2678,7 @@ static int virtnet_rx_resize(struct virtnet_info *vi, if (running) { napi_disable(&rq->napi); - cancel_work_sync(&rq->dim.work); + virtnet_cancel_dim(vi, &rq->dim); } err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_unmap_free_buf); @@ -2880,7 +2939,7 @@ static int virtnet_close(struct net_device *dev) for (i = 0; i < vi->max_queue_pairs; i++) { virtnet_disable_queue_pair(vi, i); - cancel_work_sync(&vi->rq[i].dim.work); + virtnet_cancel_dim(vi, &vi->rq[i].dim); } return 0; @@ -4406,7 +4465,7 @@ static void virtnet_rx_dim_work(struct work_struct *work) if (!rq->dim_enabled) goto out; - update_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix); + update_moder = net_dim_get_rx_irq_moder(dev, dim); if (update_moder.usec != rq->intr_coal.max_usecs || update_moder.pkts != rq->intr_coal.max_packets) { err = virtnet_send_rx_ctrl_coal_vq_cmd(vi, qnum, @@ -5106,6 +5165,36 @@ static void virtnet_tx_timeout(struct net_device *dev, unsigned int txqueue) jiffies_to_usecs(jiffies - READ_ONCE(txq->trans_start))); } +static int virtnet_init_irq_moder(struct virtnet_info *vi) +{ + u8 profile_flags = 0, coal_flags = 0; + int ret, i; + + profile_flags |= DIM_PROFILE_RX; + coal_flags |= DIM_COALESCE_USEC | DIM_COALESCE_PKTS; + ret = net_dim_init_irq_moder(vi->dev, profile_flags, coal_flags, + DIM_CQ_PERIOD_MODE_START_FROM_EQE, + 0, virtnet_rx_dim_work, NULL); + + if (ret) + return ret; + + for (i = 0; i < vi->max_queue_pairs; i++) + net_dim_setting(vi->dev, &vi->rq[i].dim, false); + + return 0; +} + +static void virtnet_free_irq_moder(struct virtnet_info *vi) +{ + if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) + return; + + rtnl_lock(); + net_dim_free_irq_moder(vi->dev); + rtnl_unlock(); +} + static const struct net_device_ops virtnet_netdev = { .ndo_open = virtnet_open, .ndo_stop = virtnet_close, @@ -5385,9 +5474,6 @@ static int virtnet_alloc_queues(struct virtnet_info *vi) virtnet_poll_tx, napi_tx ? napi_weight : 0); - INIT_WORK(&vi->rq[i].dim.work, virtnet_rx_dim_work); - vi->rq[i].dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; - sg_init_table(vi->rq[i].sg, ARRAY_SIZE(vi->rq[i].sg)); ewma_pkt_len_init(&vi->rq[i].mrg_avg_pkt_len); sg_init_table(vi->sq[i].sg, ARRAY_SIZE(vi->sq[i].sg)); @@ -5666,8 +5752,16 @@ static int virtnet_probe(struct virtio_device *vdev) dev->features |= dev->hw_features & NETIF_F_ALL_TSO; /* (!csum && gso) case will be fixed by register_netdev() */ } - if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM)) - dev->features |= NETIF_F_RXCSUM; + + /* 1. With VIRTIO_NET_F_GUEST_CSUM negotiation, the driver doesn't + * need to calculate checksums for partially checksummed packets, + * as they're considered valid by the upper layer. + * 2. Without VIRTIO_NET_F_GUEST_CSUM negotiation, the driver only + * receives fully checksummed packets. The device may assist in + * validating these packets' checksums, so the driver won't have to. + */ + dev->features |= NETIF_F_RXCSUM; + if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) || virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6)) dev->features |= NETIF_F_GRO_HW; @@ -5808,6 +5902,10 @@ static int virtnet_probe(struct virtio_device *vdev) for (i = 0; i < vi->max_queue_pairs; i++) if (vi->sq[i].napi.weight) vi->sq[i].intr_coal.max_packets = 1; + + err = virtnet_init_irq_moder(vi); + if (err) + goto free; } #ifdef CONFIG_SYSFS @@ -5959,6 +6057,8 @@ static void virtnet_remove(struct virtio_device *vdev) disable_rx_mode_work(vi); flush_work(&vi->rx_mode_work); + virtnet_free_irq_moder(vi); + unregister_netdev(vi->dev); net_failover_destroy(vi->failover); diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 3a252ac5dd28..9af316cdd8b3 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -126,8 +126,8 @@ static void vrf_rx_stats(struct net_device *dev, int len) struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); u64_stats_update_begin(&dstats->syncp); - dstats->rx_packets++; - dstats->rx_bytes += len; + u64_stats_inc(&dstats->rx_packets); + u64_stats_add(&dstats->rx_bytes, len); u64_stats_update_end(&dstats->syncp); } @@ -137,33 +137,6 @@ static void vrf_tx_error(struct net_device *vrf_dev, struct sk_buff *skb) kfree_skb(skb); } -static void vrf_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *stats) -{ - int i; - - for_each_possible_cpu(i) { - const struct pcpu_dstats *dstats; - u64 tbytes, tpkts, tdrops, rbytes, rpkts; - unsigned int start; - - dstats = per_cpu_ptr(dev->dstats, i); - do { - start = u64_stats_fetch_begin(&dstats->syncp); - tbytes = dstats->tx_bytes; - tpkts = dstats->tx_packets; - tdrops = dstats->tx_drops; - rbytes = dstats->rx_bytes; - rpkts = dstats->rx_packets; - } while (u64_stats_fetch_retry(&dstats->syncp, start)); - stats->tx_bytes += tbytes; - stats->tx_packets += tpkts; - stats->tx_dropped += tdrops; - stats->rx_bytes += rbytes; - stats->rx_packets += rpkts; - } -} - static struct vrf_map *netns_vrf_map(struct net *net) { struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id); @@ -408,10 +381,15 @@ static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev, skb->protocol = eth_type_trans(skb, dev); - if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) + if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) { vrf_rx_stats(dev, len); - else - this_cpu_inc(dev->dstats->rx_drops); + } else { + struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); + + u64_stats_update_begin(&dstats->syncp); + u64_stats_inc(&dstats->rx_drops); + u64_stats_update_end(&dstats->syncp); + } return NETDEV_TX_OK; } @@ -599,19 +577,20 @@ static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev) static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) { + struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); + int len = skb->len; netdev_tx_t ret = is_ip_tx_frame(skb, dev); + u64_stats_update_begin(&dstats->syncp); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { - struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); - u64_stats_update_begin(&dstats->syncp); - dstats->tx_packets++; - dstats->tx_bytes += len; - u64_stats_update_end(&dstats->syncp); + u64_stats_inc(&dstats->tx_packets); + u64_stats_add(&dstats->tx_bytes, len); } else { - this_cpu_inc(dev->dstats->tx_drops); + u64_stats_inc(&dstats->tx_drops); } + u64_stats_update_end(&dstats->syncp); return ret; } @@ -1195,7 +1174,6 @@ static const struct net_device_ops vrf_netdev_ops = { .ndo_uninit = vrf_dev_uninit, .ndo_start_xmit = vrf_xmit, .ndo_set_mac_address = eth_mac_addr, - .ndo_get_stats64 = vrf_get_stats64, .ndo_add_slave = vrf_add_slave, .ndo_del_slave = vrf_del_slave, }; diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 567cb3faab70..ba59e92ab941 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -2339,7 +2339,7 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct ip_tunnel_key *pkey; struct ip_tunnel_key key; struct vxlan_dev *vxlan = netdev_priv(dev); - const struct iphdr *old_iph = ip_hdr(skb); + const struct iphdr *old_iph; struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; unsigned int pkt_len = skb->len; @@ -2353,8 +2353,15 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, bool use_cache; bool udp_sum = false; bool xnet = !net_eq(vxlan->net, dev_net(vxlan->dev)); + bool no_eth_encap; __be32 vni = 0; + no_eth_encap = flags & VXLAN_F_GPE && skb->protocol != htons(ETH_P_TEB); + if (!skb_vlan_inet_prepare(skb, no_eth_encap)) + goto drop; + + old_iph = ip_hdr(skb); + info = skb_tunnel_info(skb); use_cache = ip_tunnel_dst_cache_usable(skb, info); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index d29531d95353..90cf0ec69682 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -4791,7 +4791,7 @@ static int iwl_mvm_roc_station(struct iwl_mvm *mvm, if (fw_ver == IWL_FW_CMD_VER_UNKNOWN) { ret = iwl_mvm_send_aux_roc_cmd(mvm, channel, vif, duration); - } else if (fw_ver == 3) { + } else if (fw_ver >= 3) { ret = iwl_mvm_roc_add_cmd(mvm, channel, vif, duration, ROC_ACTIVITY_HOTSPOT); } else { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c index 23a860055354..8e0df31f1b3e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -1830,7 +1830,7 @@ iwl_mvm_umac_scan_cfg_channels_v7_6g(struct iwl_mvm *mvm, */ if (!iwl_mvm_is_scan_fragmented(params->type)) { if (!cfg80211_channel_is_psc(params->channels[i]) || - flags & IWL_UHB_CHAN_CFG_FLAG_PSC_CHAN_NO_LISTEN) { + psc_no_listen) { if (unsolicited_probe_on_chan) { max_s_ssids = 2; max_bssids = 6; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c index 98490866a7f5..2773dfa8baa9 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c @@ -1293,6 +1293,7 @@ void iwl_mvm_stop_roc(struct iwl_mvm *mvm, struct ieee80211_vif *vif) if (te_data->id >= SESSION_PROTECT_CONF_MAX_ID) { IWL_DEBUG_TE(mvm, "No remain on channel event\n"); + mutex_unlock(&mvm->mutex); return; } iwl_mvm_cancel_session_protection(mvm, vif, @@ -1308,6 +1309,7 @@ void iwl_mvm_stop_roc(struct iwl_mvm *mvm, struct ieee80211_vif *vif) te_data = iwl_mvm_get_roc_te(mvm); if (!te_data) { IWL_WARN(mvm, "No remain on channel event\n"); + mutex_unlock(&mvm->mutex); return; } diff --git a/drivers/net/wireless/mediatek/mt76/debugfs.c b/drivers/net/wireless/mediatek/mt76/debugfs.c index ae83be572b94..b6a2746c187d 100644 --- a/drivers/net/wireless/mediatek/mt76/debugfs.c +++ b/drivers/net/wireless/mediatek/mt76/debugfs.c @@ -33,8 +33,8 @@ mt76_napi_threaded_set(void *data, u64 val) if (!mt76_is_mmio(dev)) return -EOPNOTSUPP; - if (dev->napi_dev.threaded != val) - return dev_set_threaded(&dev->napi_dev, val); + if (dev->napi_dev->threaded != val) + return dev_set_threaded(dev->napi_dev, val); return 0; } @@ -44,7 +44,7 @@ mt76_napi_threaded_get(void *data, u64 *val) { struct mt76_dev *dev = data; - *val = dev->napi_dev.threaded; + *val = dev->napi_dev->threaded; return 0; } diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index f4f88c444e21..5f46d6daeaa7 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -916,7 +916,7 @@ int mt76_dma_rx_poll(struct napi_struct *napi, int budget) struct mt76_dev *dev; int qid, done = 0, cur; - dev = container_of(napi->dev, struct mt76_dev, napi_dev); + dev = mt76_priv(napi->dev); qid = napi - dev->napi; rcu_read_lock(); @@ -940,18 +940,35 @@ static int mt76_dma_init(struct mt76_dev *dev, int (*poll)(struct napi_struct *napi, int budget)) { + struct mt76_dev **priv; int i; - init_dummy_netdev(&dev->napi_dev); - init_dummy_netdev(&dev->tx_napi_dev); - snprintf(dev->napi_dev.name, sizeof(dev->napi_dev.name), "%s", + dev->napi_dev = alloc_netdev_dummy(sizeof(struct mt76_dev *)); + if (!dev->napi_dev) + return -ENOMEM; + + /* napi_dev private data points to mt76_dev parent, so, mt76_dev + * can be retrieved given napi_dev + */ + priv = netdev_priv(dev->napi_dev); + *priv = dev; + + dev->tx_napi_dev = alloc_netdev_dummy(sizeof(struct mt76_dev *)); + if (!dev->tx_napi_dev) { + free_netdev(dev->napi_dev); + return -ENOMEM; + } + priv = netdev_priv(dev->tx_napi_dev); + *priv = dev; + + snprintf(dev->napi_dev->name, sizeof(dev->napi_dev->name), "%s", wiphy_name(dev->hw->wiphy)); - dev->napi_dev.threaded = 1; + dev->napi_dev->threaded = 1; init_completion(&dev->mmio.wed_reset); init_completion(&dev->mmio.wed_reset_complete); mt76_for_each_q_rx(dev, i) { - netif_napi_add(&dev->napi_dev, &dev->napi[i], poll); + netif_napi_add(dev->napi_dev, &dev->napi[i], poll); mt76_dma_rx_fill(dev, &dev->q_rx[i], false); napi_enable(&dev->napi[i]); } @@ -1019,5 +1036,7 @@ void mt76_dma_cleanup(struct mt76_dev *dev) mt76_free_pending_txwi(dev); mt76_free_pending_rxwi(dev); + free_netdev(dev->napi_dev); + free_netdev(dev->tx_napi_dev); } EXPORT_SYMBOL_GPL(mt76_dma_cleanup); diff --git a/drivers/net/wireless/mediatek/mt76/dma.h b/drivers/net/wireless/mediatek/mt76/dma.h index 1de5a2b20f74..e3ddc7a83757 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.h +++ b/drivers/net/wireless/mediatek/mt76/dma.h @@ -116,4 +116,13 @@ mt76_dma_should_drop_buf(bool *drop, u32 ctrl, u32 buf1, u32 info) } } +static inline void *mt76_priv(struct net_device *dev) +{ + struct mt76_dev **priv; + + priv = netdev_priv(dev); + + return *priv; +} + #endif diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index 11b9f22ca7f3..15f83b5adac7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -831,8 +831,8 @@ struct mt76_dev { struct mt76_mcu mcu; - struct net_device napi_dev; - struct net_device tx_napi_dev; + struct net_device *napi_dev; + struct net_device *tx_napi_dev; spinlock_t rx_lock; struct napi_struct napi[__MT_RXQ_MAX]; struct sk_buff_head rx_skb[__MT_RXQ_MAX]; diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c index 14304b063715..ea017f22fff2 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c @@ -242,7 +242,7 @@ int mt7603_dma_init(struct mt7603_dev *dev) if (ret) return ret; - netif_napi_add_tx(&dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, + netif_napi_add_tx(dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, mt7603_poll_tx); napi_enable(&dev->mt76.tx_napi); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/dma.c b/drivers/net/wireless/mediatek/mt76/mt7615/dma.c index e7135b2f1742..bcf7864312d7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/dma.c @@ -67,7 +67,7 @@ static int mt7615_poll_tx(struct napi_struct *napi, int budget) { struct mt7615_dev *dev; - dev = container_of(napi, struct mt7615_dev, mt76.tx_napi); + dev = mt76_priv(napi->dev); if (!mt76_connac_pm_ref(&dev->mphy, &dev->pm)) { napi_complete(napi); queue_work(dev->mt76.wq, &dev->pm.wake_work); @@ -89,7 +89,7 @@ static int mt7615_poll_rx(struct napi_struct *napi, int budget) struct mt7615_dev *dev; int done; - dev = container_of(napi->dev, struct mt7615_dev, mt76.napi_dev); + dev = mt76_priv(napi->dev); if (!mt76_connac_pm_ref(&dev->mphy, &dev->pm)) { napi_complete(napi); @@ -282,7 +282,7 @@ int mt7615_dma_init(struct mt7615_dev *dev) if (ret < 0) return ret; - netif_napi_add_tx(&dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, + netif_napi_add_tx(dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, mt7615_poll_tx); napi_enable(&dev->mt76.tx_napi); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c index e5ad635d3c56..35b7ebc2c9c6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c @@ -239,7 +239,7 @@ int mt76x02_dma_init(struct mt76x02_dev *dev) if (ret) return ret; - netif_napi_add_tx(&dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, + netif_napi_add_tx(dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, mt76x02_poll_tx); napi_enable(&dev->mt76.tx_napi); diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/dma.c b/drivers/net/wireless/mediatek/mt76/mt7915/dma.c index 0baa82c8df5a..0c62272fe7d0 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/dma.c @@ -578,7 +578,7 @@ int mt7915_dma_init(struct mt7915_dev *dev, struct mt7915_phy *phy2) if (ret < 0) return ret; - netif_napi_add_tx(&dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, + netif_napi_add_tx(dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, mt7915_poll_tx); napi_enable(&dev->mt76.tx_napi); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c index f768e9389ac6..e75e7b6d3aaf 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c @@ -219,7 +219,7 @@ static int mt7921_dma_init(struct mt792x_dev *dev) if (ret < 0) return ret; - netif_napi_add_tx(&dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, + netif_napi_add_tx(dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, mt792x_poll_tx); napi_enable(&dev->mt76.tx_napi); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c index 07b74d492ce1..577574fb7a1e 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c @@ -254,7 +254,7 @@ static int mt7925_dma_init(struct mt792x_dev *dev) if (ret < 0) return ret; - netif_napi_add_tx(&dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, + netif_napi_add_tx(dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, mt792x_poll_tx); napi_enable(&dev->mt76.tx_napi); diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_dma.c b/drivers/net/wireless/mediatek/mt76/mt792x_dma.c index 5cc2d59b774a..6f9db782338e 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x_dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt792x_dma.c @@ -340,7 +340,7 @@ int mt792x_poll_rx(struct napi_struct *napi, int budget) struct mt792x_dev *dev; int done; - dev = container_of(napi->dev, struct mt792x_dev, mt76.napi_dev); + dev = mt76_priv(napi->dev); if (!mt76_connac_pm_ref(&dev->mphy, &dev->pm)) { napi_complete(napi); diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/dma.c b/drivers/net/wireless/mediatek/mt76/mt7996/dma.c index 73e633d0d700..69a7d9b2e38b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/dma.c @@ -641,7 +641,7 @@ int mt7996_dma_init(struct mt7996_dev *dev) if (ret < 0) return ret; - netif_napi_add_tx(&dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, + netif_napi_add_tx(dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, mt7996_poll_tx); napi_enable(&dev->mt76.tx_napi); diff --git a/drivers/net/wireless/ti/wlcore/cmd.c b/drivers/net/wireless/ti/wlcore/cmd.c index 0d1fcdca3869..cd8ad0fe59cc 100644 --- a/drivers/net/wireless/ti/wlcore/cmd.c +++ b/drivers/net/wireless/ti/wlcore/cmd.c @@ -1575,13 +1575,6 @@ int wl12xx_cmd_add_peer(struct wl1271 *wl, struct wl12xx_vif *wlvif, cpu_to_le32(wl1271_tx_enabled_rates_get(wl, sta_rates, wlvif->band)); - if (!cmd->supported_rates) { - wl1271_debug(DEBUG_CMD, - "peer has no supported rates yet, configuring basic rates: 0x%x", - wlvif->basic_rate_set); - cmd->supported_rates = cpu_to_le32(wlvif->basic_rate_set); - } - wl1271_debug(DEBUG_CMD, "new peer rates=0x%x queues=0x%x", cmd->supported_rates, sta->uapsd_queues); diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c index 7e1d30f89855..0c77b8524160 100644 --- a/drivers/net/wireless/ti/wlcore/main.c +++ b/drivers/net/wireless/ti/wlcore/main.c @@ -5222,19 +5222,23 @@ static int wl12xx_update_sta_state(struct wl1271 *wl, /* Add station (AP mode) */ if (is_ap && - old_state == IEEE80211_STA_NOTEXIST && - new_state == IEEE80211_STA_NONE) { + old_state == IEEE80211_STA_AUTH && + new_state == IEEE80211_STA_ASSOC) { ret = wl12xx_sta_add(wl, wlvif, sta); if (ret) return ret; + wl_sta->fw_added = true; + wlcore_update_inconn_sta(wl, wlvif, wl_sta, true); } /* Remove station (AP mode) */ if (is_ap && - old_state == IEEE80211_STA_NONE && - new_state == IEEE80211_STA_NOTEXIST) { + old_state == IEEE80211_STA_ASSOC && + new_state == IEEE80211_STA_AUTH) { + wl_sta->fw_added = false; + /* must not fail */ wl12xx_sta_remove(wl, wlvif, sta); @@ -5248,11 +5252,6 @@ static int wl12xx_update_sta_state(struct wl1271 *wl, if (ret < 0) return ret; - /* reconfigure rates */ - ret = wl12xx_cmd_add_peer(wl, wlvif, sta, wl_sta->hlid); - if (ret < 0) - return ret; - ret = wl1271_acx_set_ht_capabilities(wl, &sta->deflink.ht_cap, true, wl_sta->hlid); diff --git a/drivers/net/wireless/ti/wlcore/tx.c b/drivers/net/wireless/ti/wlcore/tx.c index 7bd3ce2f0804..464587d16ab2 100644 --- a/drivers/net/wireless/ti/wlcore/tx.c +++ b/drivers/net/wireless/ti/wlcore/tx.c @@ -140,11 +140,8 @@ EXPORT_SYMBOL(wl12xx_is_dummy_packet); static u8 wl12xx_tx_get_hlid_ap(struct wl1271 *wl, struct wl12xx_vif *wlvif, struct sk_buff *skb, struct ieee80211_sta *sta) { - if (sta) { - struct wl1271_station *wl_sta; - - wl_sta = (struct wl1271_station *)sta->drv_priv; - return wl_sta->hlid; + if (sta && wl1271_station(sta)->fw_added) { + return wl1271_station(sta)->hlid; } else { struct ieee80211_hdr *hdr; diff --git a/drivers/net/wireless/ti/wlcore/wlcore_i.h b/drivers/net/wireless/ti/wlcore/wlcore_i.h index 5fbed64302f1..5bdcb341629c 100644 --- a/drivers/net/wireless/ti/wlcore/wlcore_i.h +++ b/drivers/net/wireless/ti/wlcore/wlcore_i.h @@ -328,6 +328,7 @@ struct wl12xx_rx_filter { struct wl1271_station { u8 hlid; + bool fw_added; bool in_connection; /* @@ -339,6 +340,11 @@ struct wl1271_station { u64 total_freed_pkts; }; +static inline struct wl1271_station *wl1271_station(struct ieee80211_sta *sta) +{ + return (struct wl1271_station *)sta->drv_priv; +} + struct wl12xx_vif { struct wl1271 *wl; struct list_head list; diff --git a/drivers/nfc/microread/i2c.c b/drivers/nfc/microread/i2c.c index 642df4e0ce24..113b2e306e35 100644 --- a/drivers/nfc/microread/i2c.c +++ b/drivers/nfc/microread/i2c.c @@ -277,7 +277,7 @@ static void microread_i2c_remove(struct i2c_client *client) } static const struct i2c_device_id microread_i2c_id[] = { - { MICROREAD_I2C_DRIVER_NAME, 0}, + { MICROREAD_I2C_DRIVER_NAME }, { } }; MODULE_DEVICE_TABLE(i2c, microread_i2c_id); diff --git a/drivers/nfc/nfcmrvl/i2c.c b/drivers/nfc/nfcmrvl/i2c.c index 74553134c1b1..39ecf2aeda80 100644 --- a/drivers/nfc/nfcmrvl/i2c.c +++ b/drivers/nfc/nfcmrvl/i2c.c @@ -252,7 +252,7 @@ static const struct of_device_id of_nfcmrvl_i2c_match[] __maybe_unused = { MODULE_DEVICE_TABLE(of, of_nfcmrvl_i2c_match); static const struct i2c_device_id nfcmrvl_i2c_id_table[] = { - { "nfcmrvl_i2c", 0 }, + { "nfcmrvl_i2c" }, {} }; MODULE_DEVICE_TABLE(i2c, nfcmrvl_i2c_id_table); diff --git a/drivers/nfc/nxp-nci/i2c.c b/drivers/nfc/nxp-nci/i2c.c index 3ae4b41c59ac..a8aced0b8010 100644 --- a/drivers/nfc/nxp-nci/i2c.c +++ b/drivers/nfc/nxp-nci/i2c.c @@ -322,7 +322,7 @@ static void nxp_nci_i2c_remove(struct i2c_client *client) } static const struct i2c_device_id nxp_nci_i2c_id_table[] = { - {"nxp-nci_i2c", 0}, + { "nxp-nci_i2c" }, {} }; MODULE_DEVICE_TABLE(i2c, nxp_nci_i2c_id_table); diff --git a/drivers/nfc/pn533/i2c.c b/drivers/nfc/pn533/i2c.c index 438ab9553f7a..132c050a365d 100644 --- a/drivers/nfc/pn533/i2c.c +++ b/drivers/nfc/pn533/i2c.c @@ -249,7 +249,7 @@ static const struct of_device_id of_pn533_i2c_match[] __maybe_unused = { MODULE_DEVICE_TABLE(of, of_pn533_i2c_match); static const struct i2c_device_id pn533_i2c_id_table[] = { - { PN533_I2C_DRIVER_NAME, 0 }, + { PN533_I2C_DRIVER_NAME }, {} }; MODULE_DEVICE_TABLE(i2c, pn533_i2c_id_table); diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c index 3f6d74832bac..9fe664960b38 100644 --- a/drivers/nfc/pn544/i2c.c +++ b/drivers/nfc/pn544/i2c.c @@ -44,7 +44,7 @@ PN544_HCI_I2C_LLC_MAX_PAYLOAD) static const struct i2c_device_id pn544_hci_i2c_id_table[] = { - {"pn544", 0}, + { "pn544" }, {} }; diff --git a/drivers/nfc/s3fwrn5/i2c.c b/drivers/nfc/s3fwrn5/i2c.c index 720d4a72493c..536c566e3f59 100644 --- a/drivers/nfc/s3fwrn5/i2c.c +++ b/drivers/nfc/s3fwrn5/i2c.c @@ -245,7 +245,7 @@ static void s3fwrn5_i2c_remove(struct i2c_client *client) } static const struct i2c_device_id s3fwrn5_i2c_id_table[] = { - {S3FWRN5_I2C_DRIVER_NAME, 0}, + { S3FWRN5_I2C_DRIVER_NAME }, {} }; MODULE_DEVICE_TABLE(i2c, s3fwrn5_i2c_id_table); diff --git a/drivers/nfc/st-nci/i2c.c b/drivers/nfc/st-nci/i2c.c index d20a337e90b4..416770adbeba 100644 --- a/drivers/nfc/st-nci/i2c.c +++ b/drivers/nfc/st-nci/i2c.c @@ -257,7 +257,7 @@ static void st_nci_i2c_remove(struct i2c_client *client) } static const struct i2c_device_id st_nci_i2c_id_table[] = { - {ST_NCI_DRIVER_NAME, 0}, + { ST_NCI_DRIVER_NAME }, {} }; MODULE_DEVICE_TABLE(i2c, st_nci_i2c_id_table); diff --git a/drivers/nfc/st21nfca/i2c.c b/drivers/nfc/st21nfca/i2c.c index 064a63db288b..02c3d11a19c4 100644 --- a/drivers/nfc/st21nfca/i2c.c +++ b/drivers/nfc/st21nfca/i2c.c @@ -573,7 +573,7 @@ static void st21nfca_hci_i2c_remove(struct i2c_client *client) } static const struct i2c_device_id st21nfca_hci_i2c_id_table[] = { - {ST21NFCA_HCI_DRIVER_NAME, 0}, + { ST21NFCA_HCI_DRIVER_NAME }, {} }; MODULE_DEVICE_TABLE(i2c, st21nfca_hci_i2c_id_table); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index f5d150c62955..782090ce0bc1 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -998,6 +998,7 @@ void nvme_cleanup_cmd(struct request *req) clear_bit_unlock(0, &ctrl->discard_page_busy); else kfree(bvec_virt(&req->special_vec)); + req->rq_flags &= ~RQF_SPECIAL_PAYLOAD; } } EXPORT_SYMBOL_GPL(nvme_cleanup_cmd); @@ -3959,12 +3960,13 @@ static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, mutex_lock(&ctrl->namespaces_lock); list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) { - if (ns->head->ns_id > nsid) - list_splice_init_rcu(&ns->list, &rm_list, - synchronize_rcu); + if (ns->head->ns_id > nsid) { + list_del_rcu(&ns->list); + synchronize_srcu(&ctrl->srcu); + list_add_tail_rcu(&ns->list, &rm_list); + } } mutex_unlock(&ctrl->namespaces_lock); - synchronize_srcu(&ctrl->srcu); list_for_each_entry_safe(ns, next, &rm_list, list) nvme_ns_remove(ns); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index c6ad2148c2e0..ceb9c0ed3120 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -180,7 +180,7 @@ int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val) cmd.prop_get.offset = cpu_to_le32(off); ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0, - NVME_QID_ANY, 0); + NVME_QID_ANY, NVME_SUBMIT_RESERVED); if (ret >= 0) *val = le64_to_cpu(res.u64); @@ -226,7 +226,7 @@ int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val) cmd.prop_get.offset = cpu_to_le32(off); ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0, - NVME_QID_ANY, 0); + NVME_QID_ANY, NVME_SUBMIT_RESERVED); if (ret >= 0) *val = le64_to_cpu(res.u64); @@ -271,7 +271,7 @@ int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val) cmd.prop_set.value = cpu_to_le64(val); ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, NULL, NULL, 0, - NVME_QID_ANY, 0); + NVME_QID_ANY, NVME_SUBMIT_RESERVED); if (unlikely(ret)) dev_err(ctrl->device, "Property Set error: %d, offset %#x\n", diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 9d9d2a127c4e..8b69427a4476 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -111,6 +111,13 @@ static struct request *nvme_alloc_user_request(struct request_queue *q, return req; } +static void nvme_unmap_bio(struct bio *bio) +{ + if (bio_integrity(bio)) + bio_integrity_unmap_free_user(bio); + blk_rq_unmap_user(bio); +} + static int nvme_map_user_request(struct request *req, u64 ubuffer, unsigned bufflen, void __user *meta_buffer, unsigned meta_len, u32 meta_seed, struct io_uring_cmd *ioucmd, unsigned int flags) @@ -157,7 +164,7 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer, out_unmap: if (bio) - blk_rq_unmap_user(bio); + nvme_unmap_bio(bio); out: blk_mq_free_request(req); return ret; @@ -195,7 +202,7 @@ static int nvme_submit_user_cmd(struct request_queue *q, if (result) *result = le64_to_cpu(nvme_req(req)->result.u64); if (bio) - blk_rq_unmap_user(bio); + nvme_unmap_bio(bio); blk_mq_free_request(req); if (effects) @@ -406,7 +413,7 @@ static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd, struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); if (pdu->bio) - blk_rq_unmap_user(pdu->bio); + nvme_unmap_bio(pdu->bio); io_uring_cmd_done(ioucmd, pdu->status, pdu->result, issue_flags); } @@ -432,7 +439,7 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, */ if (blk_rq_is_poll(req)) { if (pdu->bio) - blk_rq_unmap_user(pdu->bio); + nvme_unmap_bio(pdu->bio); io_uring_cmd_iopoll_done(ioucmd, pdu->result, pdu->status); } else { io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb); diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c index e05571b2a1b0..8fa1ffcdaed4 100644 --- a/drivers/nvme/host/pr.c +++ b/drivers/nvme/host/pr.c @@ -77,7 +77,7 @@ static int nvme_sc_to_pr_err(int nvme_sc) if (nvme_is_path_error(nvme_sc)) return PR_STS_PATH_FAILED; - switch (nvme_sc) { + switch (nvme_sc & 0x7ff) { case NVME_SC_SUCCESS: return PR_STS_SUCCESS; case NVME_SC_RESERVATION_CONFLICT: diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 06f0c587f343..4ff460ba2826 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -957,6 +957,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, req->metadata_sg_cnt = 0; req->transfer_len = 0; req->metadata_len = 0; + req->cqe->result.u64 = 0; req->cqe->status = 0; req->cqe->sq_head = 0; req->ns = NULL; diff --git a/drivers/nvme/target/fabrics-cmd-auth.c b/drivers/nvme/target/fabrics-cmd-auth.c index d61b8c6ff3b2..cb34d644ed08 100644 --- a/drivers/nvme/target/fabrics-cmd-auth.c +++ b/drivers/nvme/target/fabrics-cmd-auth.c @@ -333,7 +333,6 @@ done: pr_debug("%s: ctrl %d qid %d nvme status %x error loc %d\n", __func__, ctrl->cntlid, req->sq->qid, status, req->error_loc); - req->cqe->result.u64 = 0; if (req->sq->dhchap_step != NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2 && req->sq->dhchap_step != NVME_AUTH_DHCHAP_MESSAGE_FAILURE2) { unsigned long auth_expire_secs = ctrl->kato ? ctrl->kato : 120; @@ -516,8 +515,6 @@ void nvmet_execute_auth_receive(struct nvmet_req *req) status = nvmet_copy_to_sgl(req, 0, d, al); kfree(d); done: - req->cqe->result.u64 = 0; - if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2) nvmet_auth_sq_free(req->sq); else if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_FAILURE1) { diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index 042b379cbb36..69d77d34bec1 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -226,9 +226,6 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) if (status) goto out; - /* zero out initial completion result, assign values as needed */ - req->cqe->result.u32 = 0; - if (c->recfmt != 0) { pr_warn("invalid connect version (%d).\n", le16_to_cpu(c->recfmt)); @@ -305,9 +302,6 @@ static void nvmet_execute_io_connect(struct nvmet_req *req) if (status) goto out; - /* zero out initial completion result, assign values as needed */ - req->cqe->result.u32 = 0; - if (c->recfmt != 0) { pr_warn("invalid connect version (%d).\n", le16_to_cpu(c->recfmt)); diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index bb4a69d538fd..f003782d4ecf 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -226,13 +226,13 @@ static void nvmet_passthru_execute_cmd_work(struct work_struct *w) req->cmd->common.opcode == nvme_admin_identify) { switch (req->cmd->identify.cns) { case NVME_ID_CNS_CTRL: - nvmet_passthru_override_id_ctrl(req); + status = nvmet_passthru_override_id_ctrl(req); break; case NVME_ID_CNS_NS: - nvmet_passthru_override_id_ns(req); + status = nvmet_passthru_override_id_ns(req); break; case NVME_ID_CNS_NS_DESC_LIST: - nvmet_passthru_override_id_descs(req); + status = nvmet_passthru_override_id_descs(req); break; } } else if (status < 0) diff --git a/drivers/parport/parport_amiga.c b/drivers/parport/parport_amiga.c index e6dc857aac3f..e06c7b2aac5c 100644 --- a/drivers/parport/parport_amiga.c +++ b/drivers/parport/parport_amiga.c @@ -229,7 +229,13 @@ static void __exit amiga_parallel_remove(struct platform_device *pdev) parport_put_port(port); } -static struct platform_driver amiga_parallel_driver = { +/* + * amiga_parallel_remove() lives in .exit.text. For drivers registered via + * module_platform_driver_probe() this is ok because they cannot get unbound at + * runtime. So mark the driver struct with __refdata to prevent modpost + * triggering a section mismatch warning. + */ +static struct platform_driver amiga_parallel_driver __refdata = { .remove_new = __exit_p(amiga_parallel_remove), .driver = { .name = "amiga-parallel", diff --git a/drivers/pci/access.c b/drivers/pci/access.c index 30f031de9cfe..b123da16b63b 100644 --- a/drivers/pci/access.c +++ b/drivers/pci/access.c @@ -289,8 +289,6 @@ void pci_cfg_access_lock(struct pci_dev *dev) { might_sleep(); - lock_map_acquire(&dev->cfg_access_lock); - raw_spin_lock_irq(&pci_lock); if (dev->block_cfg_access) pci_wait_cfg(dev); @@ -345,8 +343,6 @@ void pci_cfg_access_unlock(struct pci_dev *dev) raw_spin_unlock_irqrestore(&pci_lock, flags); wake_up_all(&pci_cfg_wait); - - lock_map_release(&dev->cfg_access_lock); } EXPORT_SYMBOL_GPL(pci_cfg_access_unlock); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 59e0949fb079..35fb1f17a589 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4883,7 +4883,6 @@ void __weak pcibios_reset_secondary_bus(struct pci_dev *dev) */ int pci_bridge_secondary_bus_reset(struct pci_dev *dev) { - lock_map_assert_held(&dev->cfg_access_lock); pcibios_reset_secondary_bus(dev); return pci_bridge_wait_for_secondary_bus(dev, "bus reset"); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 8e696e547565..5fbabb4e3425 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2546,9 +2546,6 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus) dev->dev.dma_mask = &dev->dma_mask; dev->dev.dma_parms = &dev->dma_parms; dev->dev.coherent_dma_mask = 0xffffffffull; - lockdep_register_key(&dev->cfg_access_key); - lockdep_init_map(&dev->cfg_access_lock, dev_name(&dev->dev), - &dev->cfg_access_key, 0); dma_set_max_seg_size(&dev->dev, 65536); dma_set_seg_boundary(&dev->dev, 0xffffffff); diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c index 7f999e8a433d..7b00945f7191 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c @@ -187,6 +187,31 @@ static const unsigned int qmp_v6_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { [QPHY_TX_TRANSCEIVER_BIAS_EN] = QSERDES_V6_TX_TRANSCEIVER_BIAS_EN, }; +static const unsigned int qmp_v6_n4_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { + [QPHY_SW_RESET] = QPHY_V6_N4_PCS_SW_RESET, + [QPHY_START_CTRL] = QPHY_V6_N4_PCS_START_CONTROL, + [QPHY_PCS_STATUS] = QPHY_V6_N4_PCS_PCS_STATUS1, + [QPHY_PCS_POWER_DOWN_CONTROL] = QPHY_V6_N4_PCS_POWER_DOWN_CONTROL, + + /* In PCS_USB */ + [QPHY_PCS_AUTONOMOUS_MODE_CTRL] = QPHY_V6_PCS_USB3_AUTONOMOUS_MODE_CTRL, + [QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR] = QPHY_V6_PCS_USB3_LFPS_RXTERM_IRQ_CLEAR, + + [QPHY_COM_RESETSM_CNTRL] = QSERDES_V6_COM_RESETSM_CNTRL, + [QPHY_COM_C_READY_STATUS] = QSERDES_V6_COM_C_READY_STATUS, + [QPHY_COM_CMN_STATUS] = QSERDES_V6_COM_CMN_STATUS, + [QPHY_COM_BIAS_EN_CLKBUFLR_EN] = QSERDES_V6_COM_PLL_BIAS_EN_CLK_BUFLR_EN, + + [QPHY_DP_PHY_STATUS] = QSERDES_V6_DP_PHY_STATUS, + [QPHY_DP_PHY_VCO_DIV] = QSERDES_V6_DP_PHY_VCO_DIV, + + [QPHY_TX_TX_POL_INV] = QSERDES_V6_N4_TX_TX_POL_INV, + [QPHY_TX_TX_DRV_LVL] = QSERDES_V6_N4_TX_TX_DRV_LVL, + [QPHY_TX_TX_EMP_POST1_LVL] = QSERDES_V6_N4_TX_TX_EMP_POST1_LVL, + [QPHY_TX_HIGHZ_DRVR_EN] = QSERDES_V6_N4_TX_HIGHZ_DRVR_EN, + [QPHY_TX_TRANSCEIVER_BIAS_EN] = QSERDES_V6_N4_TX_TRANSCEIVER_BIAS_EN, +}; + static const struct qmp_phy_init_tbl qmp_v3_usb3_serdes_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V3_COM_PLL_IVCO, 0x07), QMP_PHY_INIT_CFG(QSERDES_V3_COM_SYSCLK_EN_SEL, 0x14), @@ -997,6 +1022,31 @@ static const struct qmp_phy_init_tbl qmp_v6_dp_serdes_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0x0f), }; +static const struct qmp_phy_init_tbl qmp_v6_n4_dp_serdes_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SVS_MODE_CLK_SEL, 0x15), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0x3b), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYS_CLK_CTRL, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CLK_ENABLE1, 0x0c), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_BUF_ENABLE, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CLK_SELECT, 0x30), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_IVCO, 0x07), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x34), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE0, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE0, 0xc0), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x12), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN0_MODE0, 0x3f), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN1_MODE0, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BG_TIMER, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CORE_CLK_DIV_MODE0, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_CTRL, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_BIAS_EN_CLK_BUFLR_EN, 0x17), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0x0f), +}; + static const struct qmp_phy_init_tbl qmp_v6_dp_tx_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V6_TX_VMODE_CTRL1, 0x40), QMP_PHY_INIT_CFG(QSERDES_V6_TX_PRE_STALL_LDO_BOOST_EN, 0x30), @@ -1011,6 +1061,19 @@ static const struct qmp_phy_init_tbl qmp_v6_dp_tx_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V6_TX_TX_BAND, 0x4), }; +static const struct qmp_phy_init_tbl qmp_v6_n4_dp_tx_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_VMODE_CTRL1, 0x40), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_PRE_STALL_LDO_BOOST_EN, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_INTERFACE_SELECT, 0xff), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_CLKBUF_ENABLE, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_RESET_TSYNC_EN, 0x03), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_TRAN_DRVR_EMP_EN, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_PARRATE_REC_DETECT_IDLE_EN, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_RES_CODE_LANE_OFFSET_TX, 0x11), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_RES_CODE_LANE_OFFSET_RX, 0x11), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_TX_BAND, 0x1), +}; + static const struct qmp_phy_init_tbl qmp_v6_dp_serdes_tbl_rbr[] = { QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x05), QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x34), @@ -1059,6 +1122,74 @@ static const struct qmp_phy_init_tbl qmp_v6_dp_serdes_tbl_hbr3[] = { QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x0c), }; +static const struct qmp_phy_init_tbl qmp_v6_n4_dp_serdes_tbl_rbr[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x05), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x34), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x0b), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x37), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE0, 0x71), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x0c), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_ADJ_PER1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x6b), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0x92), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x01), +}; + +static const struct qmp_phy_init_tbl qmp_v6_n4_dp_serdes_tbl_hbr[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x03), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x34), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x08), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x0b), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x07), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x07), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE0, 0x71), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x0c), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_ADJ_PER1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x6b), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0x92), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x01), +}; + +static const struct qmp_phy_init_tbl qmp_v6_n4_dp_serdes_tbl_hbr2[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x46), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x08), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x05), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x0e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE0, 0x97), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x10), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_ADJ_PER1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x6b), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0x18), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x02), +}; + +static const struct qmp_phy_init_tbl qmp_v6_n4_dp_serdes_tbl_hbr3[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x34), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x08), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x0b), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x17), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x15), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE0, 0x71), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x0c), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_ADJ_PER1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x6b), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0x92), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x01), +}; + static const struct qmp_phy_init_tbl sc8280xp_usb43dp_serdes_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V5_COM_SSC_EN_CENTER, 0x01), QMP_PHY_INIT_CFG(QSERDES_V5_COM_SSC_PER1, 0x31), @@ -1273,20 +1404,20 @@ static const struct qmp_phy_init_tbl x1e80100_usb43dp_rx_tbl[] = { }; static const struct qmp_phy_init_tbl x1e80100_usb43dp_pcs_tbl[] = { - QMP_PHY_INIT_CFG(QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_L, 0xe7), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_H, 0x03), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG1, 0xc4), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG2, 0x89), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG3, 0x20), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG6, 0x13), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_REFGEN_REQ_CONFIG1, 0x21), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_RX_SIGDET_LVL, 0x55), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_CDR_RESET_TIME, 0x0a), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_ALIGN_DETECT_CONFIG1, 0xd4), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_ALIGN_DETECT_CONFIG2, 0x30), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_PCS_TX_RX_CONFIG, 0x0c), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_EQ_CONFIG1, 0x4b), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_EQ_CONFIG5, 0x10), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_RCVR_DTCT_DLY_P1U2_L, 0xe7), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_RCVR_DTCT_DLY_P1U2_H, 0x03), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_LOCK_DETECT_CONFIG1, 0xc4), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_LOCK_DETECT_CONFIG2, 0x89), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_LOCK_DETECT_CONFIG3, 0x20), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_LOCK_DETECT_CONFIG6, 0x13), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_REFGEN_REQ_CONFIG1, 0x21), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_RX_SIGDET_LVL, 0x55), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_RX_CONFIG, 0x0a), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_ALIGN_DETECT_CONFIG1, 0xd4), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_ALIGN_DETECT_CONFIG2, 0x30), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_PCS_TX_RX_CONFIG, 0x0c), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_EQ_CONFIG1, 0x4b), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_EQ_CONFIG5, 0x10), }; static const struct qmp_phy_init_tbl x1e80100_usb43dp_pcs_usb_tbl[] = { @@ -1794,22 +1925,22 @@ static const struct qmp_phy_cfg x1e80100_usb3dpphy_cfg = { .pcs_usb_tbl = x1e80100_usb43dp_pcs_usb_tbl, .pcs_usb_tbl_num = ARRAY_SIZE(x1e80100_usb43dp_pcs_usb_tbl), - .dp_serdes_tbl = qmp_v6_dp_serdes_tbl, - .dp_serdes_tbl_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl), - .dp_tx_tbl = qmp_v6_dp_tx_tbl, - .dp_tx_tbl_num = ARRAY_SIZE(qmp_v6_dp_tx_tbl), + .dp_serdes_tbl = qmp_v6_n4_dp_serdes_tbl, + .dp_serdes_tbl_num = ARRAY_SIZE(qmp_v6_n4_dp_serdes_tbl), + .dp_tx_tbl = qmp_v6_n4_dp_tx_tbl, + .dp_tx_tbl_num = ARRAY_SIZE(qmp_v6_n4_dp_tx_tbl), - .serdes_tbl_rbr = qmp_v6_dp_serdes_tbl_rbr, - .serdes_tbl_rbr_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_rbr), - .serdes_tbl_hbr = qmp_v6_dp_serdes_tbl_hbr, - .serdes_tbl_hbr_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr), - .serdes_tbl_hbr2 = qmp_v6_dp_serdes_tbl_hbr2, - .serdes_tbl_hbr2_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr2), - .serdes_tbl_hbr3 = qmp_v6_dp_serdes_tbl_hbr3, - .serdes_tbl_hbr3_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr3), + .serdes_tbl_rbr = qmp_v6_n4_dp_serdes_tbl_rbr, + .serdes_tbl_rbr_num = ARRAY_SIZE(qmp_v6_n4_dp_serdes_tbl_rbr), + .serdes_tbl_hbr = qmp_v6_n4_dp_serdes_tbl_hbr, + .serdes_tbl_hbr_num = ARRAY_SIZE(qmp_v6_n4_dp_serdes_tbl_hbr), + .serdes_tbl_hbr2 = qmp_v6_n4_dp_serdes_tbl_hbr2, + .serdes_tbl_hbr2_num = ARRAY_SIZE(qmp_v6_n4_dp_serdes_tbl_hbr2), + .serdes_tbl_hbr3 = qmp_v6_n4_dp_serdes_tbl_hbr3, + .serdes_tbl_hbr3_num = ARRAY_SIZE(qmp_v6_n4_dp_serdes_tbl_hbr3), - .swing_hbr_rbr = &qmp_dp_v5_voltage_swing_hbr_rbr, - .pre_emphasis_hbr_rbr = &qmp_dp_v5_pre_emphasis_hbr_rbr, + .swing_hbr_rbr = &qmp_dp_v6_voltage_swing_hbr_rbr, + .pre_emphasis_hbr_rbr = &qmp_dp_v6_pre_emphasis_hbr_rbr, .swing_hbr3_hbr2 = &qmp_dp_v5_voltage_swing_hbr3_hbr2, .pre_emphasis_hbr3_hbr2 = &qmp_dp_v5_pre_emphasis_hbr3_hbr2, @@ -1822,7 +1953,7 @@ static const struct qmp_phy_cfg x1e80100_usb3dpphy_cfg = { .num_resets = ARRAY_SIZE(msm8996_usb3phy_reset_l), .vreg_list = qmp_phy_vreg_l, .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), - .regs = qmp_v45_usb3phy_regs_layout, + .regs = qmp_v6_n4_usb3phy_regs_layout, }; static const struct qmp_phy_cfg sm6350_usb3dpphy_cfg = { diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6-n4.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6-n4.h new file mode 100644 index 000000000000..b3024714dab4 --- /dev/null +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6-n4.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023, Linaro Limited + */ + +#ifndef QCOM_PHY_QMP_PCS_V6_N4_H_ +#define QCOM_PHY_QMP_PCS_V6_N4_H_ + +/* Only for QMP V6 N4 PHY - USB/PCIe PCS registers */ +#define QPHY_V6_N4_PCS_SW_RESET 0x000 +#define QPHY_V6_N4_PCS_PCS_STATUS1 0x014 +#define QPHY_V6_N4_PCS_POWER_DOWN_CONTROL 0x040 +#define QPHY_V6_N4_PCS_START_CONTROL 0x044 +#define QPHY_V6_N4_PCS_POWER_STATE_CONFIG1 0x090 +#define QPHY_V6_N4_PCS_LOCK_DETECT_CONFIG1 0x0c4 +#define QPHY_V6_N4_PCS_LOCK_DETECT_CONFIG2 0x0c8 +#define QPHY_V6_N4_PCS_LOCK_DETECT_CONFIG3 0x0cc +#define QPHY_V6_N4_PCS_LOCK_DETECT_CONFIG6 0x0d8 +#define QPHY_V6_N4_PCS_REFGEN_REQ_CONFIG1 0x0dc +#define QPHY_V6_N4_PCS_RX_SIGDET_LVL 0x188 +#define QPHY_V6_N4_PCS_RCVR_DTCT_DLY_P1U2_L 0x190 +#define QPHY_V6_N4_PCS_RCVR_DTCT_DLY_P1U2_H 0x194 +#define QPHY_V6_N4_PCS_RATE_SLEW_CNTRL1 0x198 +#define QPHY_V6_N4_PCS_RX_CONFIG 0x1b0 +#define QPHY_V6_N4_PCS_ALIGN_DETECT_CONFIG1 0x1c0 +#define QPHY_V6_N4_PCS_ALIGN_DETECT_CONFIG2 0x1c4 +#define QPHY_V6_N4_PCS_PCS_TX_RX_CONFIG 0x1d0 +#define QPHY_V6_N4_PCS_EQ_CONFIG1 0x1dc +#define QPHY_V6_N4_PCS_EQ_CONFIG2 0x1e0 +#define QPHY_V6_N4_PCS_EQ_CONFIG5 0x1ec + +#endif diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_n4.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_n4.h index a814ad11af07..d37cc0d4fd36 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_n4.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_n4.h @@ -6,11 +6,24 @@ #ifndef QCOM_PHY_QMP_QSERDES_TXRX_V6_N4_H_ #define QCOM_PHY_QMP_QSERDES_TXRX_V6_N4_H_ +#define QSERDES_V6_N4_TX_CLKBUF_ENABLE 0x08 +#define QSERDES_V6_N4_TX_TX_EMP_POST1_LVL 0x0c +#define QSERDES_V6_N4_TX_TX_DRV_LVL 0x14 +#define QSERDES_V6_N4_TX_RESET_TSYNC_EN 0x1c +#define QSERDES_V6_N4_TX_PRE_STALL_LDO_BOOST_EN 0x20 #define QSERDES_V6_N4_TX_RES_CODE_LANE_OFFSET_TX 0x30 #define QSERDES_V6_N4_TX_RES_CODE_LANE_OFFSET_RX 0x34 +#define QSERDES_V6_N4_TX_TRANSCEIVER_BIAS_EN 0x48 +#define QSERDES_V6_N4_TX_HIGHZ_DRVR_EN 0x4c +#define QSERDES_V6_N4_TX_TX_POL_INV 0x50 +#define QSERDES_V6_N4_TX_PARRATE_REC_DETECT_IDLE_EN 0x54 #define QSERDES_V6_N4_TX_LANE_MODE_1 0x78 #define QSERDES_V6_N4_TX_LANE_MODE_2 0x7c #define QSERDES_V6_N4_TX_LANE_MODE_3 0x80 +#define QSERDES_V6_N4_TX_TRAN_DRVR_EMP_EN 0xac +#define QSERDES_V6_N4_TX_TX_BAND 0xd8 +#define QSERDES_V6_N4_TX_INTERFACE_SELECT 0xe4 +#define QSERDES_V6_N4_TX_VMODE_CTRL1 0xb0 #define QSERDES_V6_N4_RX_UCDR_FO_GAIN_RATE2 0x8 #define QSERDES_V6_N4_RX_UCDR_SO_GAIN_RATE2 0x18 diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.h b/drivers/phy/qualcomm/phy-qcom-qmp.h index d10b8f653c4b..d0f41e4aaa85 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp.h @@ -46,6 +46,8 @@ #include "phy-qcom-qmp-pcs-v6.h" +#include "phy-qcom-qmp-pcs-v6-n4.h" + #include "phy-qcom-qmp-pcs-v6_20.h" #include "phy-qcom-qmp-pcs-v7.h" diff --git a/drivers/pinctrl/bcm/pinctrl-bcm2835.c b/drivers/pinctrl/bcm/pinctrl-bcm2835.c index 7178a38475cc..27fd54795791 100644 --- a/drivers/pinctrl/bcm/pinctrl-bcm2835.c +++ b/drivers/pinctrl/bcm/pinctrl-bcm2835.c @@ -245,7 +245,7 @@ static const char * const irq_type_names[] = { }; static bool persist_gpio_outputs; -module_param(persist_gpio_outputs, bool, 0644); +module_param(persist_gpio_outputs, bool, 0444); MODULE_PARM_DESC(persist_gpio_outputs, "Enable GPIO_OUT persistence when pin is freed"); static inline u32 bcm2835_gpio_rd(struct bcm2835_pinctrl *pc, unsigned reg) diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c index cffeb869130d..f424a57f0013 100644 --- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -1106,8 +1106,8 @@ static struct pinctrl *create_pinctrl(struct device *dev, * an -EPROBE_DEFER later, as that is the worst case. */ if (ret == -EPROBE_DEFER) { - pinctrl_free(p, false); mutex_unlock(&pinctrl_maps_mutex); + pinctrl_free(p, false); return ERR_PTR(ret); } } diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index 3bedf36a0019..3f56991f5b89 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -634,23 +634,68 @@ static struct rockchip_mux_recalced_data rk3308_mux_recalced_data[] = { static struct rockchip_mux_recalced_data rk3328_mux_recalced_data[] = { { - .num = 2, - .pin = 12, - .reg = 0x24, - .bit = 8, - .mask = 0x3 - }, { + /* gpio2_b7_sel */ .num = 2, .pin = 15, .reg = 0x28, .bit = 0, .mask = 0x7 }, { + /* gpio2_c7_sel */ .num = 2, .pin = 23, .reg = 0x30, .bit = 14, .mask = 0x3 + }, { + /* gpio3_b1_sel */ + .num = 3, + .pin = 9, + .reg = 0x44, + .bit = 2, + .mask = 0x3 + }, { + /* gpio3_b2_sel */ + .num = 3, + .pin = 10, + .reg = 0x44, + .bit = 4, + .mask = 0x3 + }, { + /* gpio3_b3_sel */ + .num = 3, + .pin = 11, + .reg = 0x44, + .bit = 6, + .mask = 0x3 + }, { + /* gpio3_b4_sel */ + .num = 3, + .pin = 12, + .reg = 0x44, + .bit = 8, + .mask = 0x3 + }, { + /* gpio3_b5_sel */ + .num = 3, + .pin = 13, + .reg = 0x44, + .bit = 10, + .mask = 0x3 + }, { + /* gpio3_b6_sel */ + .num = 3, + .pin = 14, + .reg = 0x44, + .bit = 12, + .mask = 0x3 + }, { + /* gpio3_b7_sel */ + .num = 3, + .pin = 15, + .reg = 0x44, + .bit = 14, + .mask = 0x3 }, }; @@ -2433,6 +2478,7 @@ static int rockchip_get_pull(struct rockchip_pin_bank *bank, int pin_num) case RK3188: case RK3288: case RK3308: + case RK3328: case RK3368: case RK3399: case RK3568: @@ -2491,6 +2537,7 @@ static int rockchip_set_pull(struct rockchip_pin_bank *bank, case RK3188: case RK3288: case RK3308: + case RK3328: case RK3368: case RK3399: case RK3568: @@ -2704,8 +2751,10 @@ static int rockchip_pmx_set(struct pinctrl_dev *pctldev, unsigned selector, if (ret) { /* revert the already done pin settings */ - for (cnt--; cnt >= 0; cnt--) + for (cnt--; cnt >= 0; cnt--) { + bank = pin_to_bank(info, pins[cnt]); rockchip_set_mux(bank, pins[cnt] - bank->pin_base, 0); + } return ret; } @@ -2753,6 +2802,7 @@ static bool rockchip_pinconf_pull_valid(struct rockchip_pin_ctrl *ctrl, case RK3188: case RK3288: case RK3308: + case RK3328: case RK3368: case RK3399: case RK3568: @@ -3763,7 +3813,7 @@ static struct rockchip_pin_bank rk3328_pin_banks[] = { PIN_BANK_IOMUX_FLAGS(0, 32, "gpio0", 0, 0, 0, 0), PIN_BANK_IOMUX_FLAGS(1, 32, "gpio1", 0, 0, 0, 0), PIN_BANK_IOMUX_FLAGS(2, 32, "gpio2", 0, - IOMUX_WIDTH_3BIT, + 0, IOMUX_WIDTH_3BIT, 0), PIN_BANK_IOMUX_FLAGS(3, 32, "gpio3", @@ -3777,7 +3827,7 @@ static struct rockchip_pin_ctrl rk3328_pin_ctrl = { .pin_banks = rk3328_pin_banks, .nr_banks = ARRAY_SIZE(rk3328_pin_banks), .label = "RK3328-GPIO", - .type = RK3288, + .type = RK3328, .grf_mux_offset = 0x0, .iomux_recalced = rk3328_mux_recalced_data, .niomux_recalced = ARRAY_SIZE(rk3328_mux_recalced_data), diff --git a/drivers/pinctrl/pinctrl-rockchip.h b/drivers/pinctrl/pinctrl-rockchip.h index 4759f336941e..849266f8b191 100644 --- a/drivers/pinctrl/pinctrl-rockchip.h +++ b/drivers/pinctrl/pinctrl-rockchip.h @@ -193,6 +193,7 @@ enum rockchip_pinctrl_type { RK3188, RK3288, RK3308, + RK3328, RK3368, RK3399, RK3568, diff --git a/drivers/pinctrl/pinctrl-tps6594.c b/drivers/pinctrl/pinctrl-tps6594.c index 085047320853..5e7c7cf93445 100644 --- a/drivers/pinctrl/pinctrl-tps6594.c +++ b/drivers/pinctrl/pinctrl-tps6594.c @@ -486,6 +486,7 @@ static int tps6594_pinctrl_probe(struct platform_device *pdev) break; case TPS6593: case TPS6594: + case LP8764: pctrl_desc->pins = tps6594_pins; pctrl_desc->npins = ARRAY_SIZE(tps6594_pins); diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c index 4e80c7204e5f..4abd6f18bbef 100644 --- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c +++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c @@ -1207,7 +1207,6 @@ static const struct of_device_id pmic_gpio_of_match[] = { { .compatible = "qcom,pm7325-gpio", .data = (void *) 10 }, { .compatible = "qcom,pm7550ba-gpio", .data = (void *) 8}, { .compatible = "qcom,pm8005-gpio", .data = (void *) 4 }, - { .compatible = "qcom,pm8008-gpio", .data = (void *) 2 }, { .compatible = "qcom,pm8019-gpio", .data = (void *) 6 }, /* pm8150 has 10 GPIOs with holes on 2, 5, 7 and 8 */ { .compatible = "qcom,pm8150-gpio", .data = (void *) 10 }, diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c index c3256bfde502..60be78da9f52 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c +++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c @@ -2071,11 +2071,11 @@ static void rzg2l_gpio_irq_restore(struct rzg2l_pinctrl *pctrl) * This has to be atomically executed to protect against a concurrent * interrupt. */ - raw_spin_lock_irqsave(&pctrl->lock.rlock, flags); + spin_lock_irqsave(&pctrl->lock, flags); ret = rzg2l_gpio_irq_set_type(data, irqd_get_trigger_type(data)); if (!ret && !irqd_irq_disabled(data)) rzg2l_gpio_irq_enable(data); - raw_spin_unlock_irqrestore(&pctrl->lock.rlock, flags); + spin_unlock_irqrestore(&pctrl->lock, flags); if (ret) dev_crit(pctrl->dev, "Failed to set IRQ type for virq=%u\n", virq); diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 1953317541ea..665fa9524986 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -136,6 +136,7 @@ config YOGABOOK config YT2_1380 tristate "Lenovo Yoga Tablet 2 1380 fast charge driver" depends on SERIAL_DEV_BUS + depends on EXTCON depends on ACPI help Say Y here to enable support for the custom fast charging protocol diff --git a/drivers/platform/x86/amd/hsmp.c b/drivers/platform/x86/amd/hsmp.c index d84ea66eecc6..8fcf38eed7f0 100644 --- a/drivers/platform/x86/amd/hsmp.c +++ b/drivers/platform/x86/amd/hsmp.c @@ -907,16 +907,44 @@ static int hsmp_plat_dev_register(void) return ret; } +/* + * This check is only needed for backward compatibility of previous platforms. + * All new platforms are expected to support ACPI based probing. + */ +static bool legacy_hsmp_support(void) +{ + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) + return false; + + switch (boot_cpu_data.x86) { + case 0x19: + switch (boot_cpu_data.x86_model) { + case 0x00 ... 0x1F: + case 0x30 ... 0x3F: + case 0x90 ... 0x9F: + case 0xA0 ... 0xAF: + return true; + default: + return false; + } + case 0x1A: + switch (boot_cpu_data.x86_model) { + case 0x00 ... 0x1F: + return true; + default: + return false; + } + default: + return false; + } + + return false; +} + static int __init hsmp_plt_init(void) { int ret = -ENODEV; - if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD || boot_cpu_data.x86 < 0x19) { - pr_err("HSMP is not supported on Family:%x model:%x\n", - boot_cpu_data.x86, boot_cpu_data.x86_model); - return ret; - } - /* * amd_nb_num() returns number of SMN/DF interfaces present in the system * if we have N SMN/DF interfaces that ideally means N sockets @@ -930,7 +958,15 @@ static int __init hsmp_plt_init(void) return ret; if (!plat_dev.is_acpi_device) { - ret = hsmp_plat_dev_register(); + if (legacy_hsmp_support()) { + /* Not ACPI device, but supports HSMP, register a plat_dev */ + ret = hsmp_plat_dev_register(); + } else { + /* Not ACPI, Does not support HSMP */ + pr_info("HSMP is not supported on Family:%x model:%x\n", + boot_cpu_data.x86, boot_cpu_data.x86_model); + ret = -ENODEV; + } if (ret) platform_driver_unregister(&amd_hsmp_driver); } diff --git a/drivers/platform/x86/dell/dell-smbios-base.c b/drivers/platform/x86/dell/dell-smbios-base.c index e61bfaf8b5c4..b562ed99ec4e 100644 --- a/drivers/platform/x86/dell/dell-smbios-base.c +++ b/drivers/platform/x86/dell/dell-smbios-base.c @@ -11,6 +11,7 @@ */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/container_of.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/capability.h> @@ -25,11 +26,16 @@ static u32 da_supported_commands; static int da_num_tokens; static struct platform_device *platform_device; static struct calling_interface_token *da_tokens; -static struct device_attribute *token_location_attrs; -static struct device_attribute *token_value_attrs; +static struct token_sysfs_data *token_entries; static struct attribute **token_attrs; static DEFINE_MUTEX(smbios_mutex); +struct token_sysfs_data { + struct device_attribute location_attr; + struct device_attribute value_attr; + struct calling_interface_token *token; +}; + struct smbios_device { struct list_head list; struct device *device; @@ -416,47 +422,26 @@ static void __init find_tokens(const struct dmi_header *dm, void *dummy) } } -static int match_attribute(struct device *dev, - struct device_attribute *attr) -{ - int i; - - for (i = 0; i < da_num_tokens * 2; i++) { - if (!token_attrs[i]) - continue; - if (strcmp(token_attrs[i]->name, attr->attr.name) == 0) - return i/2; - } - dev_dbg(dev, "couldn't match: %s\n", attr->attr.name); - return -EINVAL; -} - static ssize_t location_show(struct device *dev, struct device_attribute *attr, char *buf) { - int i; + struct token_sysfs_data *data = container_of(attr, struct token_sysfs_data, location_attr); if (!capable(CAP_SYS_ADMIN)) return -EPERM; - i = match_attribute(dev, attr); - if (i > 0) - return sysfs_emit(buf, "%08x", da_tokens[i].location); - return 0; + return sysfs_emit(buf, "%08x", data->token->location); } static ssize_t value_show(struct device *dev, struct device_attribute *attr, char *buf) { - int i; + struct token_sysfs_data *data = container_of(attr, struct token_sysfs_data, value_attr); if (!capable(CAP_SYS_ADMIN)) return -EPERM; - i = match_attribute(dev, attr); - if (i > 0) - return sysfs_emit(buf, "%08x", da_tokens[i].value); - return 0; + return sysfs_emit(buf, "%08x", data->token->value); } static struct attribute_group smbios_attribute_group = { @@ -473,22 +458,15 @@ static int build_tokens_sysfs(struct platform_device *dev) { char *location_name; char *value_name; - size_t size; int ret; int i, j; - /* (number of tokens + 1 for null terminated */ - size = sizeof(struct device_attribute) * (da_num_tokens + 1); - token_location_attrs = kzalloc(size, GFP_KERNEL); - if (!token_location_attrs) + token_entries = kcalloc(da_num_tokens, sizeof(*token_entries), GFP_KERNEL); + if (!token_entries) return -ENOMEM; - token_value_attrs = kzalloc(size, GFP_KERNEL); - if (!token_value_attrs) - goto out_allocate_value; /* need to store both location and value + terminator*/ - size = sizeof(struct attribute *) * ((2 * da_num_tokens) + 1); - token_attrs = kzalloc(size, GFP_KERNEL); + token_attrs = kcalloc((2 * da_num_tokens) + 1, sizeof(*token_attrs), GFP_KERNEL); if (!token_attrs) goto out_allocate_attrs; @@ -496,32 +474,34 @@ static int build_tokens_sysfs(struct platform_device *dev) /* skip empty */ if (da_tokens[i].tokenID == 0) continue; + + token_entries[i].token = &da_tokens[i]; + /* add location */ location_name = kasprintf(GFP_KERNEL, "%04x_location", da_tokens[i].tokenID); if (location_name == NULL) goto out_unwind_strings; - sysfs_attr_init(&token_location_attrs[i].attr); - token_location_attrs[i].attr.name = location_name; - token_location_attrs[i].attr.mode = 0444; - token_location_attrs[i].show = location_show; - token_attrs[j++] = &token_location_attrs[i].attr; + + sysfs_attr_init(&token_entries[i].location_attr.attr); + token_entries[i].location_attr.attr.name = location_name; + token_entries[i].location_attr.attr.mode = 0444; + token_entries[i].location_attr.show = location_show; + token_attrs[j++] = &token_entries[i].location_attr.attr; /* add value */ value_name = kasprintf(GFP_KERNEL, "%04x_value", da_tokens[i].tokenID); - if (value_name == NULL) - goto loop_fail_create_value; - sysfs_attr_init(&token_value_attrs[i].attr); - token_value_attrs[i].attr.name = value_name; - token_value_attrs[i].attr.mode = 0444; - token_value_attrs[i].show = value_show; - token_attrs[j++] = &token_value_attrs[i].attr; - continue; - -loop_fail_create_value: - kfree(location_name); - goto out_unwind_strings; + if (!value_name) { + kfree(location_name); + goto out_unwind_strings; + } + + sysfs_attr_init(&token_entries[i].value_attr.attr); + token_entries[i].value_attr.attr.name = value_name; + token_entries[i].value_attr.attr.mode = 0444; + token_entries[i].value_attr.show = value_show; + token_attrs[j++] = &token_entries[i].value_attr.attr; } smbios_attribute_group.attrs = token_attrs; @@ -532,14 +512,12 @@ loop_fail_create_value: out_unwind_strings: while (i--) { - kfree(token_location_attrs[i].attr.name); - kfree(token_value_attrs[i].attr.name); + kfree(token_entries[i].location_attr.attr.name); + kfree(token_entries[i].value_attr.attr.name); } kfree(token_attrs); out_allocate_attrs: - kfree(token_value_attrs); -out_allocate_value: - kfree(token_location_attrs); + kfree(token_entries); return -ENOMEM; } @@ -551,12 +529,11 @@ static void free_group(struct platform_device *pdev) sysfs_remove_group(&pdev->dev.kobj, &smbios_attribute_group); for (i = 0; i < da_num_tokens; i++) { - kfree(token_location_attrs[i].attr.name); - kfree(token_value_attrs[i].attr.name); + kfree(token_entries[i].location_attr.attr.name); + kfree(token_entries[i].value_attr.attr.name); } kfree(token_attrs); - kfree(token_value_attrs); - kfree(token_location_attrs); + kfree(token_entries); } static int __init dell_smbios_init(void) diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 2d9ca2292ea1..f74af0a689f2 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -34,7 +34,6 @@ static const struct property_entry archos_101_cesium_educ_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1280), PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-archos-101-cesium-educ.fw"), { } @@ -49,7 +48,6 @@ static const struct property_entry bush_bush_windows_tablet_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1850), PROPERTY_ENTRY_U32("touchscreen-size-y", 1280), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-bush-bush-windows-tablet.fw"), { } @@ -79,7 +77,6 @@ static const struct property_entry chuwi_hi8_air_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1148), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3676-chuwi-hi8-air.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), { } }; @@ -95,7 +92,6 @@ static const struct property_entry chuwi_hi8_pro_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1148), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3680-chuwi-hi8-pro.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -123,7 +119,6 @@ static const struct property_entry chuwi_hi10_air_props[] = { PROPERTY_ENTRY_U32("touchscreen-fuzz-x", 5), PROPERTY_ENTRY_U32("touchscreen-fuzz-y", 4), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-chuwi-hi10-air.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -139,7 +134,6 @@ static const struct property_entry chuwi_hi10_plus_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1908), PROPERTY_ENTRY_U32("touchscreen-size-y", 1270), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-chuwi-hi10plus.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), PROPERTY_ENTRY_BOOL("silead,pen-supported"), PROPERTY_ENTRY_U32("silead,pen-resolution-x", 8), @@ -171,7 +165,6 @@ static const struct property_entry chuwi_hi10_pro_props[] = { PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-chuwi-hi10-pro.fw"), PROPERTY_ENTRY_U32_ARRAY("silead,efi-fw-min-max", chuwi_hi10_pro_efi_min_max), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), PROPERTY_ENTRY_BOOL("silead,pen-supported"), PROPERTY_ENTRY_U32("silead,pen-resolution-x", 8), @@ -201,7 +194,6 @@ static const struct property_entry chuwi_hibook_props[] = { PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-chuwi-hibook.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -227,7 +219,6 @@ static const struct property_entry chuwi_vi8_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1140), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3676-chuwi-vi8.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -255,7 +246,6 @@ static const struct property_entry chuwi_vi10_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1858), PROPERTY_ENTRY_U32("touchscreen-size-y", 1280), PROPERTY_ENTRY_STRING("firmware-name", "gsl3680-chuwi-vi10.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -271,7 +261,6 @@ static const struct property_entry chuwi_surbook_mini_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 2040), PROPERTY_ENTRY_U32("touchscreen-size-y", 1524), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-chuwi-surbook-mini.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), { } }; @@ -289,7 +278,6 @@ static const struct property_entry connect_tablet9_props[] = { PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-connect-tablet9.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), { } }; @@ -306,7 +294,6 @@ static const struct property_entry csl_panther_tab_hd_props[] = { PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-csl-panther-tab-hd.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), { } }; @@ -322,7 +309,6 @@ static const struct property_entry cube_iwork8_air_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 896), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3670-cube-iwork8-air.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), { } }; @@ -346,7 +332,6 @@ static const struct property_entry cube_knote_i1101_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1961), PROPERTY_ENTRY_U32("touchscreen-size-y", 1513), PROPERTY_ENTRY_STRING("firmware-name", "gsl3692-cube-knote-i1101.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -360,7 +345,6 @@ static const struct property_entry dexp_ursus_7w_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 890), PROPERTY_ENTRY_U32("touchscreen-size-y", 630), PROPERTY_ENTRY_STRING("firmware-name", "gsl1686-dexp-ursus-7w.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -376,7 +360,6 @@ static const struct property_entry dexp_ursus_kx210i_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1720), PROPERTY_ENTRY_U32("touchscreen-size-y", 1137), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-dexp-ursus-kx210i.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -391,7 +374,6 @@ static const struct property_entry digma_citi_e200_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1500), PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl1686-digma_citi_e200.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -450,7 +432,6 @@ static const struct property_entry irbis_tw90_props[] = { PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3680-irbis_tw90.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -466,7 +447,6 @@ static const struct property_entry irbis_tw118_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1960), PROPERTY_ENTRY_U32("touchscreen-size-y", 1510), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-irbis-tw118.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), { } }; @@ -483,7 +463,6 @@ static const struct property_entry itworks_tw891_props[] = { PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3670-itworks-tw891.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), { } }; @@ -496,7 +475,6 @@ static const struct property_entry jumper_ezpad_6_pro_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1980), PROPERTY_ENTRY_U32("touchscreen-size-y", 1500), PROPERTY_ENTRY_STRING("firmware-name", "gsl3692-jumper-ezpad-6-pro.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -511,7 +489,6 @@ static const struct property_entry jumper_ezpad_6_pro_b_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1500), PROPERTY_ENTRY_STRING("firmware-name", "gsl3692-jumper-ezpad-6-pro-b.fw"), PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -527,7 +504,6 @@ static const struct property_entry jumper_ezpad_6_m4_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1950), PROPERTY_ENTRY_U32("touchscreen-size-y", 1525), PROPERTY_ENTRY_STRING("firmware-name", "gsl3692-jumper-ezpad-6-m4.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -544,7 +520,6 @@ static const struct property_entry jumper_ezpad_7_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1526), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3680-jumper-ezpad-7.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,stuck-controller-bug"), { } }; @@ -561,7 +536,6 @@ static const struct property_entry jumper_ezpad_mini3_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1138), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3676-jumper-ezpad-mini3.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), { } }; @@ -578,7 +552,6 @@ static const struct property_entry mpman_converter9_props[] = { PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-mpman-converter9.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), { } }; @@ -594,7 +567,6 @@ static const struct property_entry mpman_mpwin895cl_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1150), PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3680-mpman-mpwin895cl.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -611,7 +583,6 @@ static const struct property_entry myria_my8307_props[] = { PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-myria-my8307.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -628,7 +599,6 @@ static const struct property_entry onda_obook_20_plus_props[] = { PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3676-onda-obook-20-plus.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -645,7 +615,6 @@ static const struct property_entry onda_v80_plus_v3_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1140), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3676-onda-v80-plus-v3.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -669,7 +638,6 @@ static const struct property_entry onda_v820w_32g_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1140), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-onda-v820w-32g.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -687,7 +655,6 @@ static const struct property_entry onda_v891_v5_props[] = { PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3676-onda-v891-v5.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -703,7 +670,6 @@ static const struct property_entry onda_v891w_v1_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1676), PROPERTY_ENTRY_U32("touchscreen-size-y", 1130), PROPERTY_ENTRY_STRING("firmware-name", "gsl3680-onda-v891w-v1.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -720,7 +686,6 @@ static const struct property_entry onda_v891w_v3_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1135), PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3676-onda-v891w-v3.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -759,7 +724,6 @@ static const struct property_entry pipo_w11_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1984), PROPERTY_ENTRY_U32("touchscreen-size-y", 1532), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-pipo-w11.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -775,7 +739,6 @@ static const struct property_entry positivo_c4128b_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1915), PROPERTY_ENTRY_U32("touchscreen-size-y", 1269), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-positivo-c4128b.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), { } }; @@ -791,7 +754,6 @@ static const struct property_entry pov_mobii_wintab_p800w_v20_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1146), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3680-pov-mobii-wintab-p800w-v20.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -808,7 +770,6 @@ static const struct property_entry pov_mobii_wintab_p800w_v21_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1148), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3692-pov-mobii-wintab-p800w.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -825,7 +786,6 @@ static const struct property_entry pov_mobii_wintab_p1006w_v10_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1520), PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3692-pov-mobii-wintab-p1006w-v10.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -842,7 +802,6 @@ static const struct property_entry predia_basic_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1144), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3680-predia-basic.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -859,7 +818,6 @@ static const struct property_entry rca_cambio_w101_v2_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 874), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-rca-cambio-w101-v2.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), { } }; @@ -874,7 +832,6 @@ static const struct property_entry rwc_nanote_p8_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1140), PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-rwc-nanote-p8.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), { } }; @@ -890,7 +847,6 @@ static const struct property_entry schneider_sct101ctm_props[] = { PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-schneider-sct101ctm.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -906,7 +862,6 @@ static const struct property_entry globalspace_solt_ivw116_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1723), PROPERTY_ENTRY_U32("touchscreen-size-y", 1077), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-globalspace-solt-ivw116.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -923,7 +878,6 @@ static const struct property_entry techbite_arc_11_6_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1270), PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-techbite-arc-11-6.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), { } }; @@ -939,7 +893,6 @@ static const struct property_entry teclast_tbook11_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1264), PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3692-teclast-tbook11.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -965,7 +918,6 @@ static const struct property_entry teclast_x16_plus_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1264), PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3692-teclast-x16-plus.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -988,7 +940,6 @@ static const struct property_entry teclast_x3_plus_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1980), PROPERTY_ENTRY_U32("touchscreen-size-y", 1500), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-teclast-x3-plus.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -1004,7 +955,6 @@ static const struct property_entry teclast_x98plus2_props[] = { PROPERTY_ENTRY_BOOL("touchscreen-inverted-x"), PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl1686-teclast_x98plus2.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), { } }; @@ -1018,7 +968,6 @@ static const struct property_entry trekstor_primebook_c11_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1530), PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-trekstor-primebook-c11.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -1032,7 +981,6 @@ static const struct property_entry trekstor_primebook_c13_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 2624), PROPERTY_ENTRY_U32("touchscreen-size-y", 1920), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-trekstor-primebook-c13.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -1046,7 +994,6 @@ static const struct property_entry trekstor_primetab_t13b_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 2500), PROPERTY_ENTRY_U32("touchscreen-size-y", 1900), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-trekstor-primetab-t13b.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), { } @@ -1074,7 +1021,6 @@ static const struct property_entry trekstor_surftab_twin_10_1_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-y", 1280), PROPERTY_ENTRY_U32("touchscreen-inverted-y", 1), PROPERTY_ENTRY_STRING("firmware-name", "gsl3670-surftab-twin-10-1-st10432-8.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -1090,7 +1036,6 @@ static const struct property_entry trekstor_surftab_wintron70_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 884), PROPERTY_ENTRY_U32("touchscreen-size-y", 632), PROPERTY_ENTRY_STRING("firmware-name", "gsl1686-surftab-wintron70-st70416-6.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -1107,7 +1052,6 @@ static const struct property_entry viglen_connect_10_props[] = { PROPERTY_ENTRY_U32("touchscreen-fuzz-y", 6), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3680-viglen-connect-10.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -1121,7 +1065,6 @@ static const struct property_entry vinga_twizzle_j116_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1920), PROPERTY_ENTRY_U32("touchscreen-size-y", 1280), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-vinga-twizzle_j116.fw"), - PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -1907,7 +1850,7 @@ static int __init ts_parse_props(char *str) u32 u32val; int i, ret; - strscpy(orig_str, str, sizeof(orig_str)); + strscpy(orig_str, str); /* * str is part of the static_command_line from init/main.c and poking diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c index a15460aaa03b..6b1b8f57cd95 100644 --- a/drivers/ptp/ptp_sysfs.c +++ b/drivers/ptp/ptp_sysfs.c @@ -296,8 +296,7 @@ static ssize_t max_vclocks_store(struct device *dev, if (max < ptp->n_vclocks) goto out; - size = sizeof(int) * max; - vclock_index = kzalloc(size, GFP_KERNEL); + vclock_index = kcalloc(max, sizeof(int), GFP_KERNEL); if (!vclock_index) { err = -ENOMEM; goto out; diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c index a2f231d13a9f..8bae3fd2b330 100644 --- a/drivers/pwm/pwm-stm32.c +++ b/drivers/pwm/pwm-stm32.c @@ -321,22 +321,30 @@ static int stm32_pwm_config(struct stm32_pwm *priv, unsigned int ch, * First we need to find the minimal value for prescaler such that * * period_ns * clkrate - * ------------------------------ + * ------------------------------ < max_arr + 1 * NSEC_PER_SEC * (prescaler + 1) * - * isn't bigger than max_arr. + * This equation is equivalent to + * + * period_ns * clkrate + * ---------------------------- < prescaler + 1 + * NSEC_PER_SEC * (max_arr + 1) + * + * Using integer division and knowing that the right hand side is + * integer, this is further equivalent to + * + * (period_ns * clkrate) // (NSEC_PER_SEC * (max_arr + 1)) ≤ prescaler */ prescaler = mul_u64_u64_div_u64(period_ns, clk_get_rate(priv->clk), - (u64)NSEC_PER_SEC * priv->max_arr); - if (prescaler > 0) - prescaler -= 1; - + (u64)NSEC_PER_SEC * ((u64)priv->max_arr + 1)); if (prescaler > MAX_TIM_PSC) return -EINVAL; prd = mul_u64_u64_div_u64(period_ns, clk_get_rate(priv->clk), (u64)NSEC_PER_SEC * (prescaler + 1)); + if (!prd) + return -EINVAL; /* * All channels share the same prescaler and counter so when two @@ -673,7 +681,8 @@ static int stm32_pwm_probe(struct platform_device *pdev) * .apply() won't overflow. */ if (clk_get_rate(priv->clk) > 1000000000) - return dev_err_probe(dev, -EINVAL, "Failed to lock clock\n"); + return dev_err_probe(dev, -EINVAL, "Clock freq too high (%lu)\n", + clk_get_rate(priv->clk)); chip->ops = &stm32pwm_ops; diff --git a/drivers/ras/amd/atl/internal.h b/drivers/ras/amd/atl/internal.h index 5de69e0bb0f9..196c1c8b578c 100644 --- a/drivers/ras/amd/atl/internal.h +++ b/drivers/ras/amd/atl/internal.h @@ -224,7 +224,7 @@ int df_indirect_read_broadcast(u16 node, u8 func, u16 reg, u32 *lo); int get_df_system_info(void); int determine_node_id(struct addr_ctx *ctx, u8 socket_num, u8 die_num); -int get_addr_hash_mi300(void); +int get_umc_info_mi300(void); int get_address_map(struct addr_ctx *ctx); diff --git a/drivers/ras/amd/atl/system.c b/drivers/ras/amd/atl/system.c index 701349e84942..6979fa3d4fe2 100644 --- a/drivers/ras/amd/atl/system.c +++ b/drivers/ras/amd/atl/system.c @@ -127,7 +127,7 @@ static int df4_determine_df_rev(u32 reg) if (reg == DF_FUNC0_ID_MI300) { df_cfg.flags.heterogeneous = 1; - if (get_addr_hash_mi300()) + if (get_umc_info_mi300()) return -EINVAL; } diff --git a/drivers/ras/amd/atl/umc.c b/drivers/ras/amd/atl/umc.c index 59b6169093f7..a1b4accf7b96 100644 --- a/drivers/ras/amd/atl/umc.c +++ b/drivers/ras/amd/atl/umc.c @@ -68,6 +68,8 @@ struct xor_bits { }; #define NUM_BANK_BITS 4 +#define NUM_COL_BITS 5 +#define NUM_SID_BITS 2 static struct { /* UMC::CH::AddrHashBank */ @@ -80,7 +82,22 @@ static struct { u8 bank_xor; } addr_hash; +static struct { + u8 bank[NUM_BANK_BITS]; + u8 col[NUM_COL_BITS]; + u8 sid[NUM_SID_BITS]; + u8 num_row_lo; + u8 num_row_hi; + u8 row_lo; + u8 row_hi; + u8 pc; +} bit_shifts; + #define MI300_UMC_CH_BASE 0x90000 +#define MI300_ADDR_CFG (MI300_UMC_CH_BASE + 0x30) +#define MI300_ADDR_SEL (MI300_UMC_CH_BASE + 0x40) +#define MI300_COL_SEL_LO (MI300_UMC_CH_BASE + 0x50) +#define MI300_ADDR_SEL_2 (MI300_UMC_CH_BASE + 0xA4) #define MI300_ADDR_HASH_BANK0 (MI300_UMC_CH_BASE + 0xC8) #define MI300_ADDR_HASH_PC (MI300_UMC_CH_BASE + 0xE0) #define MI300_ADDR_HASH_PC2 (MI300_UMC_CH_BASE + 0xE4) @@ -90,17 +107,42 @@ static struct { #define ADDR_HASH_ROW_XOR GENMASK(31, 14) #define ADDR_HASH_BANK_XOR GENMASK(5, 0) +#define ADDR_CFG_NUM_ROW_LO GENMASK(11, 8) +#define ADDR_CFG_NUM_ROW_HI GENMASK(15, 12) + +#define ADDR_SEL_BANK0 GENMASK(3, 0) +#define ADDR_SEL_BANK1 GENMASK(7, 4) +#define ADDR_SEL_BANK2 GENMASK(11, 8) +#define ADDR_SEL_BANK3 GENMASK(15, 12) +#define ADDR_SEL_BANK4 GENMASK(20, 16) +#define ADDR_SEL_ROW_LO GENMASK(27, 24) +#define ADDR_SEL_ROW_HI GENMASK(31, 28) + +#define COL_SEL_LO_COL0 GENMASK(3, 0) +#define COL_SEL_LO_COL1 GENMASK(7, 4) +#define COL_SEL_LO_COL2 GENMASK(11, 8) +#define COL_SEL_LO_COL3 GENMASK(15, 12) +#define COL_SEL_LO_COL4 GENMASK(19, 16) + +#define ADDR_SEL_2_BANK5 GENMASK(4, 0) +#define ADDR_SEL_2_CHAN GENMASK(15, 12) + /* * Read UMC::CH::AddrHash{Bank,PC,PC2} registers to get XOR bits used - * for hashing. Do this during module init, since the values will not - * change during run time. + * for hashing. + * + * Also, read UMC::CH::Addr{Cfg,Sel,Sel2} and UMC::CH:ColSelLo registers to + * get the values needed to reconstruct the normalized address. Apply additional + * offsets to the raw register values, as needed. + * + * Do this during module init, since the values will not change during run time. * * These registers are instantiated for each UMC across each AMD Node. * However, they should be identically programmed due to the fixed hardware * design of MI300 systems. So read the values from Node 0 UMC 0 and keep a * single global structure for simplicity. */ -int get_addr_hash_mi300(void) +int get_umc_info_mi300(void) { u32 temp; int ret; @@ -130,6 +172,44 @@ int get_addr_hash_mi300(void) addr_hash.bank_xor = FIELD_GET(ADDR_HASH_BANK_XOR, temp); + ret = amd_smn_read(0, MI300_ADDR_CFG, &temp); + if (ret) + return ret; + + bit_shifts.num_row_hi = FIELD_GET(ADDR_CFG_NUM_ROW_HI, temp); + bit_shifts.num_row_lo = 10 + FIELD_GET(ADDR_CFG_NUM_ROW_LO, temp); + + ret = amd_smn_read(0, MI300_ADDR_SEL, &temp); + if (ret) + return ret; + + bit_shifts.bank[0] = 5 + FIELD_GET(ADDR_SEL_BANK0, temp); + bit_shifts.bank[1] = 5 + FIELD_GET(ADDR_SEL_BANK1, temp); + bit_shifts.bank[2] = 5 + FIELD_GET(ADDR_SEL_BANK2, temp); + bit_shifts.bank[3] = 5 + FIELD_GET(ADDR_SEL_BANK3, temp); + /* Use BankBit4 for the SID0 position. */ + bit_shifts.sid[0] = 5 + FIELD_GET(ADDR_SEL_BANK4, temp); + bit_shifts.row_lo = 12 + FIELD_GET(ADDR_SEL_ROW_LO, temp); + bit_shifts.row_hi = 24 + FIELD_GET(ADDR_SEL_ROW_HI, temp); + + ret = amd_smn_read(0, MI300_COL_SEL_LO, &temp); + if (ret) + return ret; + + bit_shifts.col[0] = 2 + FIELD_GET(COL_SEL_LO_COL0, temp); + bit_shifts.col[1] = 2 + FIELD_GET(COL_SEL_LO_COL1, temp); + bit_shifts.col[2] = 2 + FIELD_GET(COL_SEL_LO_COL2, temp); + bit_shifts.col[3] = 2 + FIELD_GET(COL_SEL_LO_COL3, temp); + bit_shifts.col[4] = 2 + FIELD_GET(COL_SEL_LO_COL4, temp); + + ret = amd_smn_read(0, MI300_ADDR_SEL_2, &temp); + if (ret) + return ret; + + /* Use BankBit5 for the SID1 position. */ + bit_shifts.sid[1] = 5 + FIELD_GET(ADDR_SEL_2_BANK5, temp); + bit_shifts.pc = 5 + FIELD_GET(ADDR_SEL_2_CHAN, temp); + return 0; } @@ -146,9 +226,6 @@ int get_addr_hash_mi300(void) * The MCA address format is as follows: * MCA_ADDR[27:0] = {S[1:0], P[0], R[14:0], B[3:0], C[4:0], Z[0]} * - * The normalized address format is fixed in hardware and is as follows: - * NA[30:0] = {S[1:0], R[13:0], C4, B[1:0], B[3:2], C[3:2], P, C[1:0], Z[4:0]} - * * Additionally, the PC and Bank bits may be hashed. This must be accounted for before * reconstructing the normalized address. */ @@ -158,18 +235,10 @@ int get_addr_hash_mi300(void) #define MI300_UMC_MCA_PC BIT(25) #define MI300_UMC_MCA_SID GENMASK(27, 26) -#define MI300_NA_COL_1_0 GENMASK(6, 5) -#define MI300_NA_PC BIT(7) -#define MI300_NA_COL_3_2 GENMASK(9, 8) -#define MI300_NA_BANK_3_2 GENMASK(11, 10) -#define MI300_NA_BANK_1_0 GENMASK(13, 12) -#define MI300_NA_COL_4 BIT(14) -#define MI300_NA_ROW GENMASK(28, 15) -#define MI300_NA_SID GENMASK(30, 29) - static unsigned long convert_dram_to_norm_addr_mi300(unsigned long addr) { - u16 i, col, row, bank, pc, sid, temp; + u16 i, col, row, bank, pc, sid; + u32 temp; col = FIELD_GET(MI300_UMC_MCA_COL, addr); bank = FIELD_GET(MI300_UMC_MCA_BANK, addr); @@ -189,49 +258,48 @@ static unsigned long convert_dram_to_norm_addr_mi300(unsigned long addr) /* Calculate hash for PC bit. */ if (addr_hash.pc.xor_enable) { - /* Bits SID[1:0] act as Bank[6:5] for PC hash, so apply them here. */ - bank |= sid << 5; - temp = bitwise_xor_bits(col & addr_hash.pc.col_xor); temp ^= bitwise_xor_bits(row & addr_hash.pc.row_xor); - temp ^= bitwise_xor_bits(bank & addr_hash.bank_xor); + /* Bits SID[1:0] act as Bank[5:4] for PC hash, so apply them here. */ + temp ^= bitwise_xor_bits((bank | sid << NUM_BANK_BITS) & addr_hash.bank_xor); pc ^= temp; - - /* Drop SID bits for the sake of debug printing later. */ - bank &= 0x1F; } /* Reconstruct the normalized address starting with NA[4:0] = 0 */ addr = 0; - /* NA[6:5] = Column[1:0] */ - temp = col & 0x3; - addr |= FIELD_PREP(MI300_NA_COL_1_0, temp); - - /* NA[7] = PC */ - addr |= FIELD_PREP(MI300_NA_PC, pc); - - /* NA[9:8] = Column[3:2] */ - temp = (col >> 2) & 0x3; - addr |= FIELD_PREP(MI300_NA_COL_3_2, temp); + /* Column bits */ + for (i = 0; i < NUM_COL_BITS; i++) { + temp = (col >> i) & 0x1; + addr |= temp << bit_shifts.col[i]; + } - /* NA[11:10] = Bank[3:2] */ - temp = (bank >> 2) & 0x3; - addr |= FIELD_PREP(MI300_NA_BANK_3_2, temp); + /* Bank bits */ + for (i = 0; i < NUM_BANK_BITS; i++) { + temp = (bank >> i) & 0x1; + addr |= temp << bit_shifts.bank[i]; + } - /* NA[13:12] = Bank[1:0] */ - temp = bank & 0x3; - addr |= FIELD_PREP(MI300_NA_BANK_1_0, temp); + /* Row lo bits */ + for (i = 0; i < bit_shifts.num_row_lo; i++) { + temp = (row >> i) & 0x1; + addr |= temp << (i + bit_shifts.row_lo); + } - /* NA[14] = Column[4] */ - temp = (col >> 4) & 0x1; - addr |= FIELD_PREP(MI300_NA_COL_4, temp); + /* Row hi bits */ + for (i = 0; i < bit_shifts.num_row_hi; i++) { + temp = (row >> (i + bit_shifts.num_row_lo)) & 0x1; + addr |= temp << (i + bit_shifts.row_hi); + } - /* NA[28:15] = Row[13:0] */ - addr |= FIELD_PREP(MI300_NA_ROW, row); + /* PC bit */ + addr |= pc << bit_shifts.pc; - /* NA[30:29] = SID[1:0] */ - addr |= FIELD_PREP(MI300_NA_SID, sid); + /* SID bits */ + for (i = 0; i < NUM_SID_BITS; i++) { + temp = (sid >> i) & 0x1; + addr |= temp << bit_shifts.sid[i]; + } pr_debug("Addr=0x%016lx", addr); pr_debug("Bank=%u Row=%u Column=%u PC=%u SID=%u", bank, row, col, pc, sid); diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index 34fcdd82b2ea..f3c447ecdc3b 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -140,7 +140,7 @@ #define AXP717_DCDC1_NUM_VOLTAGES 88 #define AXP717_DCDC2_NUM_VOLTAGES 107 -#define AXP717_DCDC3_NUM_VOLTAGES 104 +#define AXP717_DCDC3_NUM_VOLTAGES 103 #define AXP717_DCDC_V_OUT_MASK GENMASK(6, 0) #define AXP717_LDO_V_OUT_MASK GENMASK(4, 0) @@ -763,10 +763,15 @@ static const struct linear_range axp717_dcdc1_ranges[] = { REGULATOR_LINEAR_RANGE(1220000, 71, 87, 20000), }; +/* + * The manual says that the last voltage is 3.4V, encoded as 0b1101011 (107), + * but every other method proves that this is wrong, so it's really 106 that + * programs the final 3.4V. + */ static const struct linear_range axp717_dcdc2_ranges[] = { REGULATOR_LINEAR_RANGE(500000, 0, 70, 10000), REGULATOR_LINEAR_RANGE(1220000, 71, 87, 20000), - REGULATOR_LINEAR_RANGE(1600000, 88, 107, 100000), + REGULATOR_LINEAR_RANGE(1600000, 88, 106, 100000), }; static const struct linear_range axp717_dcdc3_ranges[] = { @@ -790,40 +795,40 @@ static const struct regulator_desc axp717_regulators[] = { AXP_DESC(AXP717, DCDC4, "dcdc4", "vin4", 1000, 3700, 100, AXP717_DCDC4_CONTROL, AXP717_DCDC_V_OUT_MASK, AXP717_DCDC_OUTPUT_CONTROL, BIT(3)), - AXP_DESC(AXP717, ALDO1, "aldo1", "vin1", 500, 3500, 100, + AXP_DESC(AXP717, ALDO1, "aldo1", "aldoin", 500, 3500, 100, AXP717_ALDO1_CONTROL, AXP717_LDO_V_OUT_MASK, AXP717_LDO0_OUTPUT_CONTROL, BIT(0)), - AXP_DESC(AXP717, ALDO2, "aldo2", "vin1", 500, 3500, 100, + AXP_DESC(AXP717, ALDO2, "aldo2", "aldoin", 500, 3500, 100, AXP717_ALDO2_CONTROL, AXP717_LDO_V_OUT_MASK, AXP717_LDO0_OUTPUT_CONTROL, BIT(1)), - AXP_DESC(AXP717, ALDO3, "aldo3", "vin1", 500, 3500, 100, + AXP_DESC(AXP717, ALDO3, "aldo3", "aldoin", 500, 3500, 100, AXP717_ALDO3_CONTROL, AXP717_LDO_V_OUT_MASK, AXP717_LDO0_OUTPUT_CONTROL, BIT(2)), - AXP_DESC(AXP717, ALDO4, "aldo4", "vin1", 500, 3500, 100, + AXP_DESC(AXP717, ALDO4, "aldo4", "aldoin", 500, 3500, 100, AXP717_ALDO4_CONTROL, AXP717_LDO_V_OUT_MASK, AXP717_LDO0_OUTPUT_CONTROL, BIT(3)), - AXP_DESC(AXP717, BLDO1, "bldo1", "vin1", 500, 3500, 100, + AXP_DESC(AXP717, BLDO1, "bldo1", "bldoin", 500, 3500, 100, AXP717_BLDO1_CONTROL, AXP717_LDO_V_OUT_MASK, AXP717_LDO0_OUTPUT_CONTROL, BIT(4)), - AXP_DESC(AXP717, BLDO2, "bldo2", "vin1", 500, 3500, 100, + AXP_DESC(AXP717, BLDO2, "bldo2", "bldoin", 500, 3500, 100, AXP717_BLDO2_CONTROL, AXP717_LDO_V_OUT_MASK, AXP717_LDO0_OUTPUT_CONTROL, BIT(5)), - AXP_DESC(AXP717, BLDO3, "bldo3", "vin1", 500, 3500, 100, + AXP_DESC(AXP717, BLDO3, "bldo3", "bldoin", 500, 3500, 100, AXP717_BLDO3_CONTROL, AXP717_LDO_V_OUT_MASK, AXP717_LDO0_OUTPUT_CONTROL, BIT(6)), - AXP_DESC(AXP717, BLDO4, "bldo4", "vin1", 500, 3500, 100, + AXP_DESC(AXP717, BLDO4, "bldo4", "bldoin", 500, 3500, 100, AXP717_BLDO4_CONTROL, AXP717_LDO_V_OUT_MASK, AXP717_LDO0_OUTPUT_CONTROL, BIT(7)), - AXP_DESC(AXP717, CLDO1, "cldo1", "vin1", 500, 3500, 100, + AXP_DESC(AXP717, CLDO1, "cldo1", "cldoin", 500, 3500, 100, AXP717_CLDO1_CONTROL, AXP717_LDO_V_OUT_MASK, AXP717_LDO1_OUTPUT_CONTROL, BIT(0)), - AXP_DESC(AXP717, CLDO2, "cldo2", "vin1", 500, 3500, 100, + AXP_DESC(AXP717, CLDO2, "cldo2", "cldoin", 500, 3500, 100, AXP717_CLDO2_CONTROL, AXP717_LDO_V_OUT_MASK, AXP717_LDO1_OUTPUT_CONTROL, BIT(1)), - AXP_DESC(AXP717, CLDO3, "cldo3", "vin1", 500, 3500, 100, + AXP_DESC(AXP717, CLDO3, "cldo3", "cldoin", 500, 3500, 100, AXP717_CLDO3_CONTROL, AXP717_LDO_V_OUT_MASK, AXP717_LDO1_OUTPUT_CONTROL, BIT(2)), - AXP_DESC(AXP717, CLDO4, "cldo4", "vin1", 500, 3500, 100, + AXP_DESC(AXP717, CLDO4, "cldo4", "cldoin", 500, 3500, 100, AXP717_CLDO4_CONTROL, AXP717_LDO_V_OUT_MASK, AXP717_LDO1_OUTPUT_CONTROL, BIT(3)), AXP_DESC(AXP717, CPUSLDO, "cpusldo", "vin1", 500, 1400, 50, diff --git a/drivers/regulator/bd71815-regulator.c b/drivers/regulator/bd71815-regulator.c index 26192d55a685..79fbb45297f6 100644 --- a/drivers/regulator/bd71815-regulator.c +++ b/drivers/regulator/bd71815-regulator.c @@ -256,7 +256,7 @@ static int buck12_set_hw_dvs_levels(struct device_node *np, * 10: 2.50mV/usec 10mV 4uS * 11: 1.25mV/usec 10mV 8uS */ -static const unsigned int bd7181x_ramp_table[] = { 1250, 2500, 5000, 10000 }; +static const unsigned int bd7181x_ramp_table[] = { 10000, 5000, 2500, 1250 }; static int bd7181x_led_set_current_limit(struct regulator_dev *rdev, int min_uA, int max_uA) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 5794f4e9dd52..844e9587a880 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -3347,6 +3347,7 @@ struct regmap *regulator_get_regmap(struct regulator *regulator) return map ? map : ERR_PTR(-EOPNOTSUPP); } +EXPORT_SYMBOL_GPL(regulator_get_regmap); /** * regulator_get_hardware_vsel_register - get the HW voltage selector register diff --git a/drivers/regulator/tps6594-regulator.c b/drivers/regulator/tps6594-regulator.c index 4a859f4c0f83..ac53792e3fed 100644 --- a/drivers/regulator/tps6594-regulator.c +++ b/drivers/regulator/tps6594-regulator.c @@ -653,18 +653,14 @@ static int tps6594_regulator_probe(struct platform_device *pdev) } } - if (tps->chip_id == LP8764) { - nr_buck = ARRAY_SIZE(buck_regs); - nr_ldo = 0; - nr_types = REGS_INT_NB; - } else if (tps->chip_id == TPS65224) { + if (tps->chip_id == TPS65224) { nr_buck = ARRAY_SIZE(tps65224_buck_regs); nr_ldo = ARRAY_SIZE(tps65224_ldo_regs); - nr_types = REGS_INT_NB; + nr_types = TPS65224_REGS_INT_NB; } else { nr_buck = ARRAY_SIZE(buck_regs); - nr_ldo = ARRAY_SIZE(tps6594_ldo_regs); - nr_types = TPS65224_REGS_INT_NB; + nr_ldo = (tps->chip_id == LP8764) ? 0 : ARRAY_SIZE(tps6594_ldo_regs); + nr_types = REGS_INT_NB; } reg_irq_nb = nr_types * (nr_buck + nr_ldo); diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index a226dc1b65d7..4eb0837298d4 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -414,28 +414,40 @@ static char print_alua_state(unsigned char state) } } -static enum scsi_disposition alua_check_sense(struct scsi_device *sdev, - struct scsi_sense_hdr *sense_hdr) +static void alua_handle_state_transition(struct scsi_device *sdev) { struct alua_dh_data *h = sdev->handler_data; struct alua_port_group *pg; + rcu_read_lock(); + pg = rcu_dereference(h->pg); + if (pg) + pg->state = SCSI_ACCESS_STATE_TRANSITIONING; + rcu_read_unlock(); + alua_check(sdev, false); +} + +static enum scsi_disposition alua_check_sense(struct scsi_device *sdev, + struct scsi_sense_hdr *sense_hdr) +{ switch (sense_hdr->sense_key) { case NOT_READY: if (sense_hdr->asc == 0x04 && sense_hdr->ascq == 0x0a) { /* * LUN Not Accessible - ALUA state transition */ - rcu_read_lock(); - pg = rcu_dereference(h->pg); - if (pg) - pg->state = SCSI_ACCESS_STATE_TRANSITIONING; - rcu_read_unlock(); - alua_check(sdev, false); + alua_handle_state_transition(sdev); return NEEDS_RETRY; } break; case UNIT_ATTENTION: + if (sense_hdr->asc == 0x04 && sense_hdr->ascq == 0x0a) { + /* + * LUN Not Accessible - ALUA state transition + */ + alua_handle_state_transition(sdev); + return NEEDS_RETRY; + } if (sense_hdr->asc == 0x29 && sense_hdr->ascq == 0x00) { /* * Power On, Reset, or Bus Device Reset. @@ -502,7 +514,8 @@ static int alua_tur(struct scsi_device *sdev) retval = scsi_test_unit_ready(sdev, ALUA_FAILOVER_TIMEOUT * HZ, ALUA_FAILOVER_RETRIES, &sense_hdr); - if (sense_hdr.sense_key == NOT_READY && + if ((sense_hdr.sense_key == NOT_READY || + sense_hdr.sense_key == UNIT_ATTENTION) && sense_hdr.asc == 0x04 && sense_hdr.ascq == 0x0a) return SCSI_DH_RETRY; else if (retval) diff --git a/drivers/scsi/mpi3mr/mpi3mr_app.c b/drivers/scsi/mpi3mr/mpi3mr_app.c index 1638109a68a0..cd261b48eb46 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_app.c +++ b/drivers/scsi/mpi3mr/mpi3mr_app.c @@ -2163,10 +2163,72 @@ persistent_id_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(persistent_id); +/** + * sas_ncq_prio_supported_show - Indicate if device supports NCQ priority + * @dev: pointer to embedded device + * @attr: sas_ncq_prio_supported attribute descriptor + * @buf: the buffer returned + * + * A sysfs 'read-only' sdev attribute, only works with SATA devices + */ +static ssize_t +sas_ncq_prio_supported_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev = to_scsi_device(dev); + + return sysfs_emit(buf, "%d\n", sas_ata_ncq_prio_supported(sdev)); +} +static DEVICE_ATTR_RO(sas_ncq_prio_supported); + +/** + * sas_ncq_prio_enable_show - send prioritized io commands to device + * @dev: pointer to embedded device + * @attr: sas_ncq_prio_enable attribute descriptor + * @buf: the buffer returned + * + * A sysfs 'read/write' sdev attribute, only works with SATA devices + */ +static ssize_t +sas_ncq_prio_enable_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev = to_scsi_device(dev); + struct mpi3mr_sdev_priv_data *sdev_priv_data = sdev->hostdata; + + if (!sdev_priv_data) + return 0; + + return sysfs_emit(buf, "%d\n", sdev_priv_data->ncq_prio_enable); +} + +static ssize_t +sas_ncq_prio_enable_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct scsi_device *sdev = to_scsi_device(dev); + struct mpi3mr_sdev_priv_data *sdev_priv_data = sdev->hostdata; + bool ncq_prio_enable = 0; + + if (kstrtobool(buf, &ncq_prio_enable)) + return -EINVAL; + + if (!sas_ata_ncq_prio_supported(sdev)) + return -EINVAL; + + sdev_priv_data->ncq_prio_enable = ncq_prio_enable; + + return strlen(buf); +} +static DEVICE_ATTR_RW(sas_ncq_prio_enable); + static struct attribute *mpi3mr_dev_attrs[] = { &dev_attr_sas_address.attr, &dev_attr_device_handle.attr, &dev_attr_persistent_id.attr, + &dev_attr_sas_ncq_prio_supported.attr, + &dev_attr_sas_ncq_prio_enable.attr, NULL, }; diff --git a/drivers/scsi/mpi3mr/mpi3mr_transport.c b/drivers/scsi/mpi3mr/mpi3mr_transport.c index 329cc6ec3b58..82aa4e418c5a 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_transport.c +++ b/drivers/scsi/mpi3mr/mpi3mr_transport.c @@ -1364,7 +1364,7 @@ static struct mpi3mr_sas_port *mpi3mr_sas_port_add(struct mpi3mr_ioc *mrioc, continue; if (i > sizeof(mr_sas_port->phy_mask) * 8) { - ioc_warn(mrioc, "skipping port %u, max allowed value is %lu\n", + ioc_warn(mrioc, "skipping port %u, max allowed value is %zu\n", i, sizeof(mr_sas_port->phy_mask) * 8); goto out_fail; } diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 1320e06727df..b2bcf4a27ddc 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -8512,6 +8512,12 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc) ioc->pd_handles_sz = (ioc->facts.MaxDevHandle / 8); if (ioc->facts.MaxDevHandle % 8) ioc->pd_handles_sz++; + /* + * pd_handles_sz should have, at least, the minimal room for + * set_bit()/test_bit(), otherwise out-of-memory touch may occur. + */ + ioc->pd_handles_sz = ALIGN(ioc->pd_handles_sz, sizeof(unsigned long)); + ioc->pd_handles = kzalloc(ioc->pd_handles_sz, GFP_KERNEL); if (!ioc->pd_handles) { @@ -8529,6 +8535,13 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc) ioc->pend_os_device_add_sz = (ioc->facts.MaxDevHandle / 8); if (ioc->facts.MaxDevHandle % 8) ioc->pend_os_device_add_sz++; + + /* + * pend_os_device_add_sz should have, at least, the minimal room for + * set_bit()/test_bit(), otherwise out-of-memory may occur. + */ + ioc->pend_os_device_add_sz = ALIGN(ioc->pend_os_device_add_sz, + sizeof(unsigned long)); ioc->pend_os_device_add = kzalloc(ioc->pend_os_device_add_sz, GFP_KERNEL); if (!ioc->pend_os_device_add) { @@ -8820,6 +8833,12 @@ _base_check_ioc_facts_changes(struct MPT3SAS_ADAPTER *ioc) if (ioc->facts.MaxDevHandle % 8) pd_handles_sz++; + /* + * pd_handles should have, at least, the minimal room for + * set_bit()/test_bit(), otherwise out-of-memory touch may + * occur. + */ + pd_handles_sz = ALIGN(pd_handles_sz, sizeof(unsigned long)); pd_handles = krealloc(ioc->pd_handles, pd_handles_sz, GFP_KERNEL); if (!pd_handles) { diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h index bf100a4ebfc3..fe1e96fda284 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.h +++ b/drivers/scsi/mpt3sas/mpt3sas_base.h @@ -2048,9 +2048,6 @@ void mpt3sas_setup_direct_io(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd, struct _raid_device *raid_device, Mpi25SCSIIORequest_t *mpi_request); -/* NCQ Prio Handling Check */ -bool scsih_ncq_prio_supp(struct scsi_device *sdev); - void mpt3sas_setup_debugfs(struct MPT3SAS_ADAPTER *ioc); void mpt3sas_destroy_debugfs(struct MPT3SAS_ADAPTER *ioc); void mpt3sas_init_debugfs(void); diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c index 1c9fd26195b8..87784c96249a 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c +++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c @@ -4088,7 +4088,7 @@ sas_ncq_prio_supported_show(struct device *dev, { struct scsi_device *sdev = to_scsi_device(dev); - return sysfs_emit(buf, "%d\n", scsih_ncq_prio_supp(sdev)); + return sysfs_emit(buf, "%d\n", sas_ata_ncq_prio_supported(sdev)); } static DEVICE_ATTR_RO(sas_ncq_prio_supported); @@ -4123,7 +4123,7 @@ sas_ncq_prio_enable_store(struct device *dev, if (kstrtobool(buf, &ncq_prio_enable)) return -EINVAL; - if (!scsih_ncq_prio_supp(sdev)) + if (!sas_ata_ncq_prio_supported(sdev)) return -EINVAL; sas_device_priv_data->ncq_prio_enable = ncq_prio_enable; diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 89ef43a5ef86..870ec2cb4af4 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -302,8 +302,8 @@ struct _scsi_io_transfer { /** * _scsih_set_debug_level - global setting of ioc->logging_level. - * @val: ? - * @kp: ? + * @val: value of the parameter to be set + * @kp: pointer to kernel_param structure * * Note: The logging levels are defined in mpt3sas_debug.h. */ @@ -12571,29 +12571,6 @@ scsih_pci_mmio_enabled(struct pci_dev *pdev) return PCI_ERS_RESULT_RECOVERED; } -/** - * scsih_ncq_prio_supp - Check for NCQ command priority support - * @sdev: scsi device struct - * - * This is called when a user indicates they would like to enable - * ncq command priorities. This works only on SATA devices. - */ -bool scsih_ncq_prio_supp(struct scsi_device *sdev) -{ - struct scsi_vpd *vpd; - bool ncq_prio_supp = false; - - rcu_read_lock(); - vpd = rcu_dereference(sdev->vpd_pg89); - if (!vpd || vpd->len < 214) - goto out; - - ncq_prio_supp = (vpd->data[213] >> 4) & 1; -out: - rcu_read_unlock(); - - return ncq_prio_supp; -} /* * The pci device ids are defined in mpi/mpi2_cnfg.h. */ diff --git a/drivers/scsi/qedf/qedf.h b/drivers/scsi/qedf/qedf.h index 5058e01b65a2..98afdfe63600 100644 --- a/drivers/scsi/qedf/qedf.h +++ b/drivers/scsi/qedf/qedf.h @@ -363,6 +363,7 @@ struct qedf_ctx { #define QEDF_IN_RECOVERY 5 #define QEDF_DBG_STOP_IO 6 #define QEDF_PROBING 8 +#define QEDF_STAG_IN_PROGRESS 9 unsigned long flags; /* Miscellaneous state flags */ int fipvlan_retries; u8 num_queues; diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index fd12439cbaab..49adddf978cc 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -318,11 +318,18 @@ static struct fc_seq *qedf_elsct_send(struct fc_lport *lport, u32 did, */ if (resp == fc_lport_flogi_resp) { qedf->flogi_cnt++; + qedf->flogi_pending++; + + if (test_bit(QEDF_UNLOADING, &qedf->flags)) { + QEDF_ERR(&qedf->dbg_ctx, "Driver unloading\n"); + qedf->flogi_pending = 0; + } + if (qedf->flogi_pending >= QEDF_FLOGI_RETRY_CNT) { schedule_delayed_work(&qedf->stag_work, 2); return NULL; } - qedf->flogi_pending++; + return fc_elsct_send(lport, did, fp, op, qedf_flogi_resp, arg, timeout); } @@ -912,13 +919,14 @@ void qedf_ctx_soft_reset(struct fc_lport *lport) struct qedf_ctx *qedf; struct qed_link_output if_link; + qedf = lport_priv(lport); + if (lport->vport) { + clear_bit(QEDF_STAG_IN_PROGRESS, &qedf->flags); printk_ratelimited("Cannot issue host reset on NPIV port.\n"); return; } - qedf = lport_priv(lport); - qedf->flogi_pending = 0; /* For host reset, essentially do a soft link up/down */ atomic_set(&qedf->link_state, QEDF_LINK_DOWN); @@ -938,6 +946,7 @@ void qedf_ctx_soft_reset(struct fc_lport *lport) if (!if_link.link_up) { QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_DISC, "Physical link is not up.\n"); + clear_bit(QEDF_STAG_IN_PROGRESS, &qedf->flags); return; } /* Flush and wait to make sure link down is processed */ @@ -950,6 +959,7 @@ void qedf_ctx_soft_reset(struct fc_lport *lport) "Queue link up work.\n"); queue_delayed_work(qedf->link_update_wq, &qedf->link_update, 0); + clear_bit(QEDF_STAG_IN_PROGRESS, &qedf->flags); } /* Reset the host by gracefully logging out and then logging back in */ @@ -3463,6 +3473,7 @@ retry_probe: } /* Start the Slowpath-process */ + memset(&slowpath_params, 0, sizeof(struct qed_slowpath_params)); slowpath_params.int_mode = QED_INT_MODE_MSIX; slowpath_params.drv_major = QEDF_DRIVER_MAJOR_VER; slowpath_params.drv_minor = QEDF_DRIVER_MINOR_VER; @@ -3721,6 +3732,7 @@ static void __qedf_remove(struct pci_dev *pdev, int mode) { struct qedf_ctx *qedf; int rc; + int cnt = 0; if (!pdev) { QEDF_ERR(NULL, "pdev is NULL.\n"); @@ -3738,6 +3750,17 @@ static void __qedf_remove(struct pci_dev *pdev, int mode) return; } +stag_in_prog: + if (test_bit(QEDF_STAG_IN_PROGRESS, &qedf->flags)) { + QEDF_ERR(&qedf->dbg_ctx, "Stag in progress, cnt=%d.\n", cnt); + cnt++; + + if (cnt < 5) { + msleep(500); + goto stag_in_prog; + } + } + if (mode != QEDF_MODE_RECOVERY) set_bit(QEDF_UNLOADING, &qedf->flags); @@ -3997,6 +4020,24 @@ void qedf_stag_change_work(struct work_struct *work) struct qedf_ctx *qedf = container_of(work, struct qedf_ctx, stag_work.work); + if (!qedf) { + QEDF_ERR(&qedf->dbg_ctx, "qedf is NULL"); + return; + } + + if (test_bit(QEDF_IN_RECOVERY, &qedf->flags)) { + QEDF_ERR(&qedf->dbg_ctx, + "Already is in recovery, hence not calling software context reset.\n"); + return; + } + + if (test_bit(QEDF_UNLOADING, &qedf->flags)) { + QEDF_ERR(&qedf->dbg_ctx, "Driver unloading\n"); + return; + } + + set_bit(QEDF_STAG_IN_PROGRESS, &qedf->flags); + printk_ratelimited("[%s]:[%s:%d]:%d: Performing software context reset.", dev_name(&qedf->pdev->dev), __func__, __LINE__, qedf->dbg_ctx.host_no); diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 3e0c0381277a..ee69bd35889d 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -350,6 +350,13 @@ static int scsi_get_vpd_size(struct scsi_device *sdev, u8 page) if (result < SCSI_VPD_HEADER_SIZE) return 0; + if (result > sizeof(vpd)) { + dev_warn_once(&sdev->sdev_gendev, + "%s: long VPD page 0 length: %d bytes\n", + __func__, result); + result = sizeof(vpd); + } + result -= SCSI_VPD_HEADER_SIZE; if (!memchr(&vpd[SCSI_VPD_HEADER_SIZE], page, result)) return 0; @@ -666,6 +673,13 @@ void scsi_cdl_check(struct scsi_device *sdev) sdev->use_10_for_rw = 0; sdev->cdl_supported = 1; + + /* + * If the device supports CDL, make sure that the current drive + * feature status is consistent with the user controlled + * cdl_enable state. + */ + scsi_cdl_enable(sdev, sdev->cdl_enable); } else { sdev->cdl_supported = 0; } diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c index 424a89513814..4e33f1661e4c 100644 --- a/drivers/scsi/scsi_transport_sas.c +++ b/drivers/scsi/scsi_transport_sas.c @@ -416,6 +416,29 @@ unsigned int sas_is_tlr_enabled(struct scsi_device *sdev) } EXPORT_SYMBOL_GPL(sas_is_tlr_enabled); +/** + * sas_ata_ncq_prio_supported - Check for ATA NCQ command priority support + * @sdev: SCSI device + * + * Check if an ATA device supports NCQ priority using VPD page 89h (ATA + * Information). Since this VPD page is implemented only for ATA devices, + * this function always returns false for SCSI devices. + */ +bool sas_ata_ncq_prio_supported(struct scsi_device *sdev) +{ + struct scsi_vpd *vpd; + bool ncq_prio_supported = false; + + rcu_read_lock(); + vpd = rcu_dereference(sdev->vpd_pg89); + if (vpd && vpd->len >= 214) + ncq_prio_supported = (vpd->data[213] >> 4) & 1; + rcu_read_unlock(); + + return ncq_prio_supported; +} +EXPORT_SYMBOL_GPL(sas_ata_ncq_prio_supported); + /* * SAS Phy attributes */ diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index f6c822c9cbd2..6b64af7d4927 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -63,6 +63,7 @@ #include <scsi/scsi_cmnd.h> #include <scsi/scsi_dbg.h> #include <scsi/scsi_device.h> +#include <scsi/scsi_devinfo.h> #include <scsi/scsi_driver.h> #include <scsi/scsi_eh.h> #include <scsi/scsi_host.h> @@ -3118,6 +3119,9 @@ static void sd_read_io_hints(struct scsi_disk *sdkp, unsigned char *buffer) struct scsi_mode_data data; int res; + if (sdp->sdev_bflags & BLIST_SKIP_IO_HINTS) + return; + res = scsi_mode_sense(sdp, /*dbd=*/0x8, /*modepage=*/0x0a, /*subpage=*/0x05, buffer, SD_BUF_SIZE, SD_TIMEOUT, sdkp->max_retries, &data, &sshdr); @@ -3565,16 +3569,23 @@ static bool sd_validate_opt_xfer_size(struct scsi_disk *sdkp, static void sd_read_block_zero(struct scsi_disk *sdkp) { - unsigned int buf_len = sdkp->device->sector_size; - char *buffer, cmd[10] = { }; + struct scsi_device *sdev = sdkp->device; + unsigned int buf_len = sdev->sector_size; + u8 *buffer, cmd[16] = { }; buffer = kmalloc(buf_len, GFP_KERNEL); if (!buffer) return; - cmd[0] = READ_10; - put_unaligned_be32(0, &cmd[2]); /* Logical block address 0 */ - put_unaligned_be16(1, &cmd[7]); /* Transfer 1 logical block */ + if (sdev->use_16_for_rw) { + cmd[0] = READ_16; + put_unaligned_be64(0, &cmd[2]); /* Logical block address 0 */ + put_unaligned_be32(1, &cmd[10]);/* Transfer 1 logical block */ + } else { + cmd[0] = READ_10; + put_unaligned_be32(0, &cmd[2]); /* Logical block address 0 */ + put_unaligned_be16(1, &cmd[7]); /* Transfer 1 logical block */ + } scsi_execute_cmd(sdkp->device, cmd, REQ_OP_DRV_IN, buffer, buf_len, SD_TIMEOUT, sdkp->max_retries, NULL); diff --git a/drivers/scsi/sr.h b/drivers/scsi/sr.h index 1175f2e213b5..dc899277b3a4 100644 --- a/drivers/scsi/sr.h +++ b/drivers/scsi/sr.h @@ -65,7 +65,7 @@ int sr_disk_status(struct cdrom_device_info *); int sr_get_last_session(struct cdrom_device_info *, struct cdrom_multisession *); int sr_get_mcn(struct cdrom_device_info *, struct cdrom_mcn *); int sr_reset(struct cdrom_device_info *); -int sr_select_speed(struct cdrom_device_info *cdi, int speed); +int sr_select_speed(struct cdrom_device_info *cdi, unsigned long speed); int sr_audio_ioctl(struct cdrom_device_info *, unsigned int, void *); int sr_is_xa(Scsi_CD *); diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c index 5b0b35e60e61..a0d2556a27bb 100644 --- a/drivers/scsi/sr_ioctl.c +++ b/drivers/scsi/sr_ioctl.c @@ -425,11 +425,14 @@ int sr_reset(struct cdrom_device_info *cdi) return 0; } -int sr_select_speed(struct cdrom_device_info *cdi, int speed) +int sr_select_speed(struct cdrom_device_info *cdi, unsigned long speed) { Scsi_CD *cd = cdi->handle; struct packet_command cgc; + /* avoid exceeding the max speed or overflowing integer bounds */ + speed = clamp(0, speed, 0xffff / 177); + if (speed == 0) speed = 0xffff; /* set to max */ else diff --git a/drivers/soc/fsl/Kconfig b/drivers/soc/fsl/Kconfig index fcec6ed83d5e..a1e0bc8c1757 100644 --- a/drivers/soc/fsl/Kconfig +++ b/drivers/soc/fsl/Kconfig @@ -22,7 +22,7 @@ config FSL_GUTS config FSL_MC_DPIO tristate "QorIQ DPAA2 DPIO driver" - depends on FSL_MC_BUS + depends on FSL_MC_BUS && NET select SOC_BUS select FSL_GUTS select DIMLIB diff --git a/drivers/soc/tegra/fuse/fuse-tegra.c b/drivers/soc/tegra/fuse/fuse-tegra.c index b6bfd6729df3..d27667283846 100644 --- a/drivers/soc/tegra/fuse/fuse-tegra.c +++ b/drivers/soc/tegra/fuse/fuse-tegra.c @@ -127,8 +127,8 @@ static void tegra_fuse_print_sku_info(struct tegra_sku_info *tegra_sku_info) static int tegra_fuse_add_lookups(struct tegra_fuse *fuse) { - fuse->lookups = kmemdup_array(fuse->soc->lookups, sizeof(*fuse->lookups), - fuse->soc->num_lookups, GFP_KERNEL); + fuse->lookups = kmemdup_array(fuse->soc->lookups, fuse->soc->num_lookups, + sizeof(*fuse->lookups), GFP_KERNEL); if (!fuse->lookups) return -ENOMEM; diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c index 20d94bcfc9b4..795e223f7e5c 100644 --- a/drivers/soundwire/amd_manager.c +++ b/drivers/soundwire/amd_manager.c @@ -571,6 +571,9 @@ static int sdw_master_read_amd_prop(struct sdw_bus *bus) amd_manager->wake_en_mask = wake_en_mask; fwnode_property_read_u32(link, "amd-sdw-power-mode", &power_mode_mask); amd_manager->power_mode_mask = power_mode_mask; + + fwnode_handle_put(link); + return 0; } diff --git a/drivers/soundwire/intel_auxdevice.c b/drivers/soundwire/intel_auxdevice.c index 17cf27e6ea73..18517121cc89 100644 --- a/drivers/soundwire/intel_auxdevice.c +++ b/drivers/soundwire/intel_auxdevice.c @@ -155,8 +155,10 @@ static int sdw_master_read_intel_prop(struct sdw_bus *bus) SDW_MASTER_QUIRKS_CLEAR_INITIAL_PARITY; intel_prop = devm_kzalloc(bus->dev, sizeof(*intel_prop), GFP_KERNEL); - if (!intel_prop) + if (!intel_prop) { + fwnode_handle_put(link); return -ENOMEM; + } /* initialize with hardware defaults, in case the properties are not found */ intel_prop->doaise = 0x1; @@ -184,6 +186,8 @@ static int sdw_master_read_intel_prop(struct sdw_bus *bus) intel_prop->dodse, intel_prop->dods); + fwnode_handle_put(link); + return 0; } diff --git a/drivers/soundwire/mipi_disco.c b/drivers/soundwire/mipi_disco.c index 55a9c51c84c1..e5d9df26d4dc 100644 --- a/drivers/soundwire/mipi_disco.c +++ b/drivers/soundwire/mipi_disco.c @@ -66,8 +66,10 @@ int sdw_master_read_prop(struct sdw_bus *bus) prop->clk_freq = devm_kcalloc(bus->dev, prop->num_clk_freq, sizeof(*prop->clk_freq), GFP_KERNEL); - if (!prop->clk_freq) + if (!prop->clk_freq) { + fwnode_handle_put(link); return -ENOMEM; + } fwnode_property_read_u32_array(link, "mipi-sdw-clock-frequencies-supported", @@ -92,8 +94,10 @@ int sdw_master_read_prop(struct sdw_bus *bus) prop->clk_gears = devm_kcalloc(bus->dev, prop->num_clk_gears, sizeof(*prop->clk_gears), GFP_KERNEL); - if (!prop->clk_gears) + if (!prop->clk_gears) { + fwnode_handle_put(link); return -ENOMEM; + } fwnode_property_read_u32_array(link, "mipi-sdw-supported-clock-gears", @@ -116,6 +120,8 @@ int sdw_master_read_prop(struct sdw_bus *bus) fwnode_property_read_u32(link, "mipi-sdw-command-error-threshold", &prop->err_threshold); + fwnode_handle_put(link); + return 0; } EXPORT_SYMBOL(sdw_master_read_prop); @@ -197,8 +203,10 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave, dpn[i].num_words, sizeof(*dpn[i].words), GFP_KERNEL); - if (!dpn[i].words) + if (!dpn[i].words) { + fwnode_handle_put(node); return -ENOMEM; + } fwnode_property_read_u32_array(node, "mipi-sdw-port-wordlength-configs", @@ -236,8 +244,10 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave, dpn[i].num_channels, sizeof(*dpn[i].channels), GFP_KERNEL); - if (!dpn[i].channels) + if (!dpn[i].channels) { + fwnode_handle_put(node); return -ENOMEM; + } fwnode_property_read_u32_array(node, "mipi-sdw-channel-number-list", @@ -251,8 +261,10 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave, dpn[i].num_ch_combinations, sizeof(*dpn[i].ch_combinations), GFP_KERNEL); - if (!dpn[i].ch_combinations) + if (!dpn[i].ch_combinations) { + fwnode_handle_put(node); return -ENOMEM; + } fwnode_property_read_u32_array(node, "mipi-sdw-channel-combination-list", @@ -274,6 +286,8 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave, /* TODO: Read audio mode */ + fwnode_handle_put(node); + i++; } @@ -348,10 +362,14 @@ int sdw_slave_read_prop(struct sdw_slave *slave) prop->dp0_prop = devm_kzalloc(&slave->dev, sizeof(*prop->dp0_prop), GFP_KERNEL); - if (!prop->dp0_prop) + if (!prop->dp0_prop) { + fwnode_handle_put(port); return -ENOMEM; + } sdw_slave_read_dp0(slave, port, prop->dp0_prop); + + fwnode_handle_put(port); } /* diff --git a/drivers/spi/spi-cs42l43.c b/drivers/spi/spi-cs42l43.c index 9d747ea69926..8b618ef0f711 100644 --- a/drivers/spi/spi-cs42l43.c +++ b/drivers/spi/spi-cs42l43.c @@ -26,7 +26,7 @@ #include <linux/units.h> #define CS42L43_FIFO_SIZE 16 -#define CS42L43_SPI_ROOT_HZ (40 * HZ_PER_MHZ) +#define CS42L43_SPI_ROOT_HZ 49152000 #define CS42L43_SPI_MAX_LENGTH 65532 enum cs42l43_spi_cmd { @@ -54,7 +54,7 @@ static const struct software_node ampr = { static struct spi_board_info ampl_info = { .modalias = "cs35l56", - .max_speed_hz = 20 * HZ_PER_MHZ, + .max_speed_hz = 11 * HZ_PER_MHZ, .chip_select = 0, .mode = SPI_MODE_0, .swnode = &l, @@ -62,7 +62,7 @@ static struct spi_board_info ampl_info = { static struct spi_board_info ampr_info = { .modalias = "cs35l56", - .max_speed_hz = 20 * HZ_PER_MHZ, + .max_speed_hz = 11 * HZ_PER_MHZ, .chip_select = 1, .mode = SPI_MODE_0, .swnode = &r, diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index f4006c82f867..33164ebdb583 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -660,18 +660,8 @@ static int mx51_ecspi_prepare_transfer(struct spi_imx_data *spi_imx, ctrl |= (spi_imx->target_burst * 8 - 1) << MX51_ECSPI_CTRL_BL_OFFSET; else { - if (spi_imx->usedma) { - ctrl |= (spi_imx->bits_per_word - 1) - << MX51_ECSPI_CTRL_BL_OFFSET; - } else { - if (spi_imx->count >= MX51_ECSPI_CTRL_MAX_BURST) - ctrl |= (MX51_ECSPI_CTRL_MAX_BURST * BITS_PER_BYTE - 1) - << MX51_ECSPI_CTRL_BL_OFFSET; - else - ctrl |= (spi_imx->count / DIV_ROUND_UP(spi_imx->bits_per_word, - BITS_PER_BYTE) * spi_imx->bits_per_word - 1) - << MX51_ECSPI_CTRL_BL_OFFSET; - } + ctrl |= (spi_imx->bits_per_word - 1) + << MX51_ECSPI_CTRL_BL_OFFSET; } /* set clock speed */ diff --git a/drivers/spi/spi-stm32-qspi.c b/drivers/spi/spi-stm32-qspi.c index f1e922fd362a..955c920c4b63 100644 --- a/drivers/spi/spi-stm32-qspi.c +++ b/drivers/spi/spi-stm32-qspi.c @@ -349,7 +349,7 @@ static int stm32_qspi_wait_poll_status(struct stm32_qspi *qspi) static int stm32_qspi_get_mode(u8 buswidth) { - if (buswidth == 4) + if (buswidth >= 4) return CCR_BUSWIDTH_4; return buswidth; @@ -653,9 +653,7 @@ static int stm32_qspi_setup(struct spi_device *spi) return -EINVAL; mode = spi->mode & (SPI_TX_OCTAL | SPI_RX_OCTAL); - if ((mode == SPI_TX_OCTAL || mode == SPI_RX_OCTAL) || - ((mode == (SPI_TX_OCTAL | SPI_RX_OCTAL)) && - gpiod_count(qspi->dev, "cs") == -ENOENT)) { + if (mode && gpiod_count(qspi->dev, "cs") == -ENOENT) { dev_err(qspi->dev, "spi-rx-bus-width\\/spi-tx-bus-width\\/cs-gpios\n"); dev_err(qspi->dev, "configuration not supported\n"); @@ -676,10 +674,10 @@ static int stm32_qspi_setup(struct spi_device *spi) qspi->cr_reg = CR_APMS | 3 << CR_FTHRES_SHIFT | CR_SSHIFT | CR_EN; /* - * Dual flash mode is only enable in case SPI_TX_OCTAL and SPI_TX_OCTAL - * are both set in spi->mode and "cs-gpios" properties is found in DT + * Dual flash mode is only enable in case SPI_TX_OCTAL or SPI_RX_OCTAL + * is set in spi->mode and "cs-gpios" properties is found in DT */ - if (mode == (SPI_TX_OCTAL | SPI_RX_OCTAL)) { + if (mode) { qspi->cr_reg |= CR_DFM; dev_dbg(qspi->dev, "Dual flash mode enable"); } diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 9bc9fd10d538..fc13fa192189 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -689,10 +689,12 @@ static int __spi_add_device(struct spi_device *spi) * Make sure that multiple logical CS doesn't map to the same physical CS. * For example, spi->chip_select[0] != spi->chip_select[1] and so on. */ - for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) { - status = spi_dev_check_cs(dev, spi, idx, spi, idx + 1); - if (status) - return status; + if (!spi_controller_is_target(ctlr)) { + for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) { + status = spi_dev_check_cs(dev, spi, idx, spi, idx + 1); + if (status) + return status; + } } /* Set the bus ID string */ @@ -4156,7 +4158,8 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message) return -EINVAL; if (xfer->tx_nbits != SPI_NBITS_SINGLE && xfer->tx_nbits != SPI_NBITS_DUAL && - xfer->tx_nbits != SPI_NBITS_QUAD) + xfer->tx_nbits != SPI_NBITS_QUAD && + xfer->tx_nbits != SPI_NBITS_OCTAL) return -EINVAL; if ((xfer->tx_nbits == SPI_NBITS_DUAL) && !(spi->mode & (SPI_TX_DUAL | SPI_TX_QUAD))) @@ -4171,7 +4174,8 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message) return -EINVAL; if (xfer->rx_nbits != SPI_NBITS_SINGLE && xfer->rx_nbits != SPI_NBITS_DUAL && - xfer->rx_nbits != SPI_NBITS_QUAD) + xfer->rx_nbits != SPI_NBITS_QUAD && + xfer->rx_nbits != SPI_NBITS_OCTAL) return -EINVAL; if ((xfer->rx_nbits == SPI_NBITS_DUAL) && !(spi->mode & (SPI_RX_DUAL | SPI_RX_QUAD))) diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c index 297af1d80b12..69daeba974f2 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c @@ -1759,7 +1759,7 @@ static int vchiq_probe(struct platform_device *pdev) if (err) goto failed_platform_init; - vchiq_debugfs_init(); + vchiq_debugfs_init(&mgmt->state); dev_dbg(&pdev->dev, "arm: platform initialised - version %d (min %d)\n", VCHIQ_VERSION, VCHIQ_VERSION_MIN); diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.c index 54e7bf029d9a..1f74d0bb33ba 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.c @@ -42,9 +42,9 @@ static int debugfs_trace_show(struct seq_file *f, void *offset) static int vchiq_dump_show(struct seq_file *f, void *offset) { - struct vchiq_instance *instance = f->private; + struct vchiq_state *state = f->private; - vchiq_dump_state(f, instance->state); + vchiq_dump_state(f, state); return 0; } @@ -121,12 +121,12 @@ void vchiq_debugfs_remove_instance(struct vchiq_instance *instance) debugfs_remove_recursive(node->dentry); } -void vchiq_debugfs_init(void) +void vchiq_debugfs_init(struct vchiq_state *state) { vchiq_dbg_dir = debugfs_create_dir("vchiq", NULL); vchiq_dbg_clients = debugfs_create_dir("clients", vchiq_dbg_dir); - debugfs_create_file("state", S_IFREG | 0444, vchiq_dbg_dir, NULL, + debugfs_create_file("state", S_IFREG | 0444, vchiq_dbg_dir, state, &vchiq_dump_fops); } diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.h b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.h index e9bf055a4ca9..fabffd81b1ec 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.h +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.h @@ -10,7 +10,7 @@ struct vchiq_debugfs_node { struct dentry *dentry; }; -void vchiq_debugfs_init(void); +void vchiq_debugfs_init(struct vchiq_state *state); void vchiq_debugfs_deinit(void); diff --git a/drivers/thermal/gov_step_wise.c b/drivers/thermal/gov_step_wise.c index e0fdc497bfcc..65974fe8be0d 100644 --- a/drivers/thermal/gov_step_wise.c +++ b/drivers/thermal/gov_step_wise.c @@ -93,6 +93,23 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, if (instance->initialized && old_target == instance->target) continue; + if (trip->type == THERMAL_TRIP_PASSIVE) { + /* + * If the target state for this thermal instance + * changes from THERMAL_NO_TARGET to something else, + * ensure that the zone temperature will be updated + * (assuming enabled passive cooling) until it becomes + * THERMAL_NO_TARGET again, or the cooling device may + * not be reset to its initial state. + */ + if (old_target == THERMAL_NO_TARGET && + instance->target != THERMAL_NO_TARGET) + tz->passive++; + else if (old_target != THERMAL_NO_TARGET && + instance->target == THERMAL_NO_TARGET) + tz->passive--; + } + instance->initialized = true; mutex_lock(&instance->cdev->lock); diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c index 14e34eabc419..4a1bfebb1b8e 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c @@ -150,7 +150,7 @@ static irqreturn_t proc_thermal_irq_handler(int irq, void *devid) { struct proc_thermal_pci *pci_info = devid; struct proc_thermal_device *proc_priv; - int ret = IRQ_HANDLED; + int ret = IRQ_NONE; u32 status; proc_priv = pci_info->proc_priv; @@ -175,6 +175,7 @@ static irqreturn_t proc_thermal_irq_handler(int irq, void *devid) /* Disable enable interrupt flag */ proc_thermal_mmio_write(pci_info, PROC_THERMAL_MMIO_INT_ENABLE_0, 0); pkg_thermal_schedule_work(&pci_info->work); + ret = IRQ_HANDLED; } pci_write_config_byte(pci_info->pdev, 0xdc, 0x01); diff --git a/drivers/thermal/mediatek/lvts_thermal.c b/drivers/thermal/mediatek/lvts_thermal.c index 0bb3a495b56e..819ed0110f3e 100644 --- a/drivers/thermal/mediatek/lvts_thermal.c +++ b/drivers/thermal/mediatek/lvts_thermal.c @@ -769,7 +769,11 @@ static int lvts_golden_temp_init(struct device *dev, u8 *calib, */ gt = (((u32 *)calib)[0] >> lvts_data->gt_calib_bit_offset) & 0xff; - if (gt && gt < LVTS_GOLDEN_TEMP_MAX) + /* A zero value for gt means that device has invalid efuse data */ + if (!gt) + return -ENODATA; + + if (gt < LVTS_GOLDEN_TEMP_MAX) golden_temp = gt; golden_temp_offset = golden_temp * 500 + lvts_data->temp_offset; @@ -1458,7 +1462,6 @@ static const struct lvts_ctrl_data mt8188_lvts_mcu_data_ctrl[] = { }, VALID_SENSOR_MAP(1, 1, 1, 1), .offset = 0x0, - .mode = LVTS_MSR_FILTERED_MODE, }, { .lvts_sensor = { @@ -1469,7 +1472,6 @@ static const struct lvts_ctrl_data mt8188_lvts_mcu_data_ctrl[] = { }, VALID_SENSOR_MAP(1, 1, 0, 0), .offset = 0x100, - .mode = LVTS_MSR_FILTERED_MODE, } }; @@ -1483,7 +1485,6 @@ static const struct lvts_ctrl_data mt8188_lvts_ap_data_ctrl[] = { }, VALID_SENSOR_MAP(0, 1, 0, 0), .offset = 0x0, - .mode = LVTS_MSR_FILTERED_MODE, }, { .lvts_sensor = { @@ -1496,7 +1497,6 @@ static const struct lvts_ctrl_data mt8188_lvts_ap_data_ctrl[] = { }, VALID_SENSOR_MAP(1, 1, 1, 0), .offset = 0x100, - .mode = LVTS_MSR_FILTERED_MODE, }, { .lvts_sensor = { @@ -1507,7 +1507,6 @@ static const struct lvts_ctrl_data mt8188_lvts_ap_data_ctrl[] = { }, VALID_SENSOR_MAP(1, 1, 0, 0), .offset = 0x200, - .mode = LVTS_MSR_FILTERED_MODE, }, { .lvts_sensor = { @@ -1518,7 +1517,6 @@ static const struct lvts_ctrl_data mt8188_lvts_ap_data_ctrl[] = { }, VALID_SENSOR_MAP(1, 1, 0, 0), .offset = 0x300, - .mode = LVTS_MSR_FILTERED_MODE, } }; diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 30567b499455..1b0ab2790860 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -999,9 +999,17 @@ __thermal_cooling_device_register(struct device_node *np, if (ret) goto out_cdev_type; + /* + * The cooling device's current state is only needed for debug + * initialization below, so a failure to get it does not cause + * the entire cooling device initialization to fail. However, + * the debug will not work for the device if its initial state + * cannot be determined and drivers are responsible for ensuring + * that this will not happen. + */ ret = cdev->ops->get_cur_state(cdev, ¤t_state); if (ret) - goto out_cdev_type; + current_state = ULONG_MAX; thermal_cooling_device_setup_sysfs(cdev); @@ -1016,7 +1024,8 @@ __thermal_cooling_device_register(struct device_node *np, return ERR_PTR(ret); } - thermal_debug_cdev_add(cdev, current_state); + if (current_state <= cdev->max_state) + thermal_debug_cdev_add(cdev, current_state); /* Add 'this' new cdev to the global cdev list */ mutex_lock(&thermal_list_lock); @@ -1397,6 +1406,7 @@ thermal_zone_device_register_with_trips(const char *type, ida_init(&tz->ida); mutex_init(&tz->lock); init_completion(&tz->removal); + init_completion(&tz->resume); id = ida_alloc(&thermal_tz_ida, GFP_KERNEL); if (id < 0) { result = id; @@ -1642,6 +1652,9 @@ static void thermal_zone_device_resume(struct work_struct *work) thermal_zone_device_init(tz); __thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED); + complete(&tz->resume); + tz->resuming = false; + mutex_unlock(&tz->lock); } @@ -1659,6 +1672,20 @@ static int thermal_pm_notify(struct notifier_block *nb, list_for_each_entry(tz, &thermal_tz_list, node) { mutex_lock(&tz->lock); + if (tz->resuming) { + /* + * thermal_zone_device_resume() queued up for + * this zone has not acquired the lock yet, so + * release it to let the function run and wait + * util it has done the work. + */ + mutex_unlock(&tz->lock); + + wait_for_completion(&tz->resume); + + mutex_lock(&tz->lock); + } + tz->suspended = true; mutex_unlock(&tz->lock); @@ -1676,6 +1703,9 @@ static int thermal_pm_notify(struct notifier_block *nb, cancel_delayed_work(&tz->poll_queue); + reinit_completion(&tz->resume); + tz->resuming = true; + /* * Replace the work function with the resume one, which * will restore the original work function and schedule @@ -1700,6 +1730,12 @@ static int thermal_pm_notify(struct notifier_block *nb, static struct notifier_block thermal_pm_nb = { .notifier_call = thermal_pm_notify, + /* + * Run at the lowest priority to avoid interference between the thermal + * zone resume work items spawned by thermal_pm_notify() and the other + * PM notifiers. + */ + .priority = INT_MIN, }; static int __init thermal_init(void) diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h index 20e7b45673d6..66f67e54e0c8 100644 --- a/drivers/thermal/thermal_core.h +++ b/drivers/thermal/thermal_core.h @@ -55,6 +55,7 @@ struct thermal_governor { * @type: the thermal zone device type * @device: &struct device for this thermal zone * @removal: removal completion + * @resume: resume completion * @trip_temp_attrs: attributes for trip points for sysfs: trip temperature * @trip_type_attrs: attributes for trip points for sysfs: trip type * @trip_hyst_attrs: attributes for trip points for sysfs: trip hysteresis @@ -89,6 +90,7 @@ struct thermal_governor { * @poll_queue: delayed work for polling * @notify_event: Last notification event * @suspended: thermal zone suspend indicator + * @resuming: indicates whether or not thermal zone resume is in progress * @trips: array of struct thermal_trip objects */ struct thermal_zone_device { @@ -96,6 +98,7 @@ struct thermal_zone_device { char type[THERMAL_NAME_LENGTH]; struct device device; struct completion removal; + struct completion resume; struct attribute_group trips_attribute_group; struct thermal_attr *trip_temp_attrs; struct thermal_attr *trip_type_attrs; @@ -123,6 +126,7 @@ struct thermal_zone_device { struct delayed_work poll_queue; enum thermal_notify_event notify_event; bool suspended; + bool resuming; #ifdef CONFIG_THERMAL_DEBUGFS struct thermal_debugfs *debugfs; #endif diff --git a/drivers/thunderbolt/debugfs.c b/drivers/thunderbolt/debugfs.c index 193e9dfc983b..70b52aac3d97 100644 --- a/drivers/thunderbolt/debugfs.c +++ b/drivers/thunderbolt/debugfs.c @@ -943,8 +943,9 @@ static void margining_port_init(struct tb_port *port) debugfs_create_file("run", 0600, dir, port, &margining_run_fops); debugfs_create_file("results", 0600, dir, port, &margining_results_fops); debugfs_create_file("test", 0600, dir, port, &margining_test_fops); - if (independent_voltage_margins(usb4) || - (supports_time(usb4) && independent_time_margins(usb4))) + if (independent_voltage_margins(usb4) == USB4_MARGIN_CAP_0_VOLTAGE_HL || + (supports_time(usb4) && + independent_time_margins(usb4) == USB4_MARGIN_CAP_1_TIME_LR)) debugfs_create_file("margin", 0600, dir, port, &margining_margin_fops); } diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index f252d0b5a434..5e9ca4376d68 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -1619,15 +1619,25 @@ static void __receive_buf(struct tty_struct *tty, const u8 *cp, const u8 *fp, else if (ldata->raw || (L_EXTPROC(tty) && !preops)) n_tty_receive_buf_raw(tty, cp, fp, count); else if (tty->closing && !L_EXTPROC(tty)) { - if (la_count > 0) + if (la_count > 0) { n_tty_receive_buf_closing(tty, cp, fp, la_count, true); - if (count > la_count) - n_tty_receive_buf_closing(tty, cp, fp, count - la_count, false); + cp += la_count; + if (fp) + fp += la_count; + count -= la_count; + } + if (count > 0) + n_tty_receive_buf_closing(tty, cp, fp, count, false); } else { - if (la_count > 0) + if (la_count > 0) { n_tty_receive_buf_standard(tty, cp, fp, la_count, true); - if (count > la_count) - n_tty_receive_buf_standard(tty, cp, fp, count - la_count, false); + cp += la_count; + if (fp) + fp += la_count; + count -= la_count; + } + if (count > 0) + n_tty_receive_buf_standard(tty, cp, fp, count, false); flush_echoes(tty); if (tty->ops->flush_chars) diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c index ba9f4dc4e71d..fb809e32c6ae 100644 --- a/drivers/tty/serial/8250/8250_dw.c +++ b/drivers/tty/serial/8250/8250_dw.c @@ -55,6 +55,34 @@ #define DW_UART_QUIRK_SKIP_SET_RATE BIT(2) #define DW_UART_QUIRK_IS_DMA_FC BIT(3) #define DW_UART_QUIRK_APMC0D08 BIT(4) +#define DW_UART_QUIRK_CPR_VALUE BIT(5) + +struct dw8250_platform_data { + u8 usr_reg; + u32 cpr_value; + unsigned int quirks; +}; + +struct dw8250_data { + struct dw8250_port_data data; + const struct dw8250_platform_data *pdata; + + int msr_mask_on; + int msr_mask_off; + struct clk *clk; + struct clk *pclk; + struct notifier_block clk_notifier; + struct work_struct clk_work; + struct reset_control *rst; + + unsigned int skip_autocfg:1; + unsigned int uart_16550_compatible:1; +}; + +static inline struct dw8250_data *to_dw8250_data(struct dw8250_port_data *data) +{ + return container_of(data, struct dw8250_data, data); +} static inline struct dw8250_data *clk_to_dw8250_data(struct notifier_block *nb) { @@ -432,6 +460,10 @@ static void dw8250_prepare_rx_dma(struct uart_8250_port *p) static void dw8250_quirks(struct uart_port *p, struct dw8250_data *data) { unsigned int quirks = data->pdata ? data->pdata->quirks : 0; + u32 cpr_value = data->pdata ? data->pdata->cpr_value : 0; + + if (quirks & DW_UART_QUIRK_CPR_VALUE) + data->data.cpr_value = cpr_value; #ifdef CONFIG_64BIT if (quirks & DW_UART_QUIRK_OCTEON) { @@ -714,8 +746,8 @@ static const struct dw8250_platform_data dw8250_armada_38x_data = { static const struct dw8250_platform_data dw8250_renesas_rzn1_data = { .usr_reg = DW_UART_USR, - .cpr_val = 0x00012f32, - .quirks = DW_UART_QUIRK_IS_DMA_FC, + .cpr_value = 0x00012f32, + .quirks = DW_UART_QUIRK_CPR_VALUE | DW_UART_QUIRK_IS_DMA_FC, }; static const struct dw8250_platform_data dw8250_starfive_jh7100_data = { diff --git a/drivers/tty/serial/8250/8250_dwlib.c b/drivers/tty/serial/8250/8250_dwlib.c index 3e33ddf7bc80..5a2520943dfd 100644 --- a/drivers/tty/serial/8250/8250_dwlib.c +++ b/drivers/tty/serial/8250/8250_dwlib.c @@ -242,7 +242,6 @@ static const struct serial_rs485 dw8250_rs485_supported = { void dw8250_setup_port(struct uart_port *p) { struct dw8250_port_data *pd = p->private_data; - struct dw8250_data *data = to_dw8250_data(pd); struct uart_8250_port *up = up_to_u8250p(p); u32 reg, old_dlf; @@ -278,7 +277,7 @@ void dw8250_setup_port(struct uart_port *p) reg = dw8250_readl_ext(p, DW_UART_CPR); if (!reg) { - reg = data->pdata->cpr_val; + reg = pd->cpr_value; dev_dbg(p->dev, "CPR is not available, using 0x%08x instead\n", reg); } if (!reg) diff --git a/drivers/tty/serial/8250/8250_dwlib.h b/drivers/tty/serial/8250/8250_dwlib.h index f13e91f2cace..7dd2a8e7b780 100644 --- a/drivers/tty/serial/8250/8250_dwlib.h +++ b/drivers/tty/serial/8250/8250_dwlib.h @@ -2,15 +2,10 @@ /* Synopsys DesignWare 8250 library header file. */ #include <linux/io.h> -#include <linux/notifier.h> #include <linux/types.h> -#include <linux/workqueue.h> #include "8250.h" -struct clk; -struct reset_control; - struct dw8250_port_data { /* Port properties */ int line; @@ -19,42 +14,16 @@ struct dw8250_port_data { struct uart_8250_dma dma; /* Hardware configuration */ + u32 cpr_value; u8 dlf_size; /* RS485 variables */ bool hw_rs485_support; }; -struct dw8250_platform_data { - u8 usr_reg; - u32 cpr_val; - unsigned int quirks; -}; - -struct dw8250_data { - struct dw8250_port_data data; - const struct dw8250_platform_data *pdata; - - int msr_mask_on; - int msr_mask_off; - struct clk *clk; - struct clk *pclk; - struct notifier_block clk_notifier; - struct work_struct clk_work; - struct reset_control *rst; - - unsigned int skip_autocfg:1; - unsigned int uart_16550_compatible:1; -}; - void dw8250_do_set_termios(struct uart_port *p, struct ktermios *termios, const struct ktermios *old); void dw8250_setup_port(struct uart_port *p); -static inline struct dw8250_data *to_dw8250_data(struct dw8250_port_data *data) -{ - return container_of(data, struct dw8250_data, data); -} - static inline u32 dw8250_readl_ext(struct uart_port *p, int offset) { if (p->iotype == UPIO_MEM32BE) diff --git a/drivers/tty/serial/8250/8250_pxa.c b/drivers/tty/serial/8250/8250_pxa.c index f1a51b00b1b9..ba96fa913e7f 100644 --- a/drivers/tty/serial/8250/8250_pxa.c +++ b/drivers/tty/serial/8250/8250_pxa.c @@ -125,6 +125,7 @@ static int serial_pxa_probe(struct platform_device *pdev) uart.port.iotype = UPIO_MEM32; uart.port.regshift = 2; uart.port.fifosize = 64; + uart.tx_loadsz = 32; uart.dl_write = serial_pxa_dl_write; ret = serial8250_register_8250_port(&uart); diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 4fdd7857ef4d..28e4beeabf8f 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -1023,8 +1023,9 @@ config SERIAL_SCCNXP_CONSOLE help Support for console on SCCNXP serial ports. -config SERIAL_SC16IS7XX_CORE +config SERIAL_SC16IS7XX tristate "NXP SC16IS7xx UART support" + depends on SPI_MASTER || I2C select SERIAL_CORE select SERIAL_SC16IS7XX_SPI if SPI_MASTER select SERIAL_SC16IS7XX_I2C if I2C diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile index faa45f2b8bb0..6ff74f0a9530 100644 --- a/drivers/tty/serial/Makefile +++ b/drivers/tty/serial/Makefile @@ -75,7 +75,7 @@ obj-$(CONFIG_SERIAL_SA1100) += sa1100.o obj-$(CONFIG_SERIAL_SAMSUNG) += samsung_tty.o obj-$(CONFIG_SERIAL_SB1250_DUART) += sb1250-duart.o obj-$(CONFIG_SERIAL_SCCNXP) += sccnxp.o -obj-$(CONFIG_SERIAL_SC16IS7XX_CORE) += sc16is7xx.o +obj-$(CONFIG_SERIAL_SC16IS7XX) += sc16is7xx.o obj-$(CONFIG_SERIAL_SC16IS7XX_SPI) += sc16is7xx_spi.o obj-$(CONFIG_SERIAL_SC16IS7XX_I2C) += sc16is7xx_i2c.o obj-$(CONFIG_SERIAL_SH_SCI) += sh-sci.o diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 2c1a0254d3f4..0c4d60976663 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -622,7 +622,7 @@ static ssize_t uart_write(struct tty_struct *tty, const u8 *buf, size_t count) return -EL3HLT; port = uart_port_lock(state, flags); - if (WARN_ON_ONCE(!state->port.xmit_buf)) { + if (!state->port.xmit_buf) { uart_port_unlock(port, flags); return 0; } diff --git a/drivers/tty/serial/serial_port.c b/drivers/tty/serial/serial_port.c index 91a338d3cb34..d35f1d24156c 100644 --- a/drivers/tty/serial/serial_port.c +++ b/drivers/tty/serial/serial_port.c @@ -64,6 +64,13 @@ static int serial_port_runtime_suspend(struct device *dev) if (port->flags & UPF_DEAD) return 0; + /* + * Nothing to do on pm_runtime_force_suspend(), see + * DEFINE_RUNTIME_DEV_PM_OPS. + */ + if (!pm_runtime_enabled(dev)) + return 0; + uart_port_lock_irqsave(port, &flags); if (!port_dev->tx_enabled) { uart_port_unlock_irqrestore(port, flags); diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index 005d63ab1f44..8944548c30fa 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -634,20 +634,20 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd) struct ufshcd_lrb *lrbp = &hba->lrb[tag]; struct ufs_hw_queue *hwq; unsigned long flags; - int err = FAILED; + int err; if (!ufshcd_cmd_inflight(lrbp->cmd)) { dev_err(hba->dev, "%s: skip abort. cmd at tag %d already completed.\n", __func__, tag); - goto out; + return FAILED; } /* Skip task abort in case previous aborts failed and report failure */ if (lrbp->req_abort_skip) { dev_err(hba->dev, "%s: skip abort. tag %d failed earlier\n", __func__, tag); - goto out; + return FAILED; } hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd)); @@ -659,7 +659,7 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd) */ dev_err(hba->dev, "%s: cmd found in sq. hwq=%d, tag=%d\n", __func__, hwq->id, tag); - goto out; + return FAILED; } /* @@ -667,18 +667,17 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd) * in the completion queue either. Query the device to see if * the command is being processed in the device. */ - if (ufshcd_try_to_abort_task(hba, tag)) { + err = ufshcd_try_to_abort_task(hba, tag); + if (err) { dev_err(hba->dev, "%s: device abort failed %d\n", __func__, err); lrbp->req_abort_skip = true; - goto out; + return FAILED; } - err = SUCCESS; spin_lock_irqsave(&hwq->cq_lock, flags); if (ufshcd_cmd_inflight(lrbp->cmd)) ufshcd_release_scsi_cmd(hba, lrbp); spin_unlock_irqrestore(&hwq->cq_lock, flags); -out: - return err; + return SUCCESS; } diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 0cf07194bbe8..1b65e6ae4137 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -1366,7 +1366,7 @@ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba, u64 timeout_us) * make sure that there are no outstanding requests when * clock scaling is in progress */ - ufshcd_scsi_block_requests(hba); + blk_mq_quiesce_tagset(&hba->host->tag_set); mutex_lock(&hba->wb_mutex); down_write(&hba->clk_scaling_lock); @@ -1375,7 +1375,7 @@ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba, u64 timeout_us) ret = -EBUSY; up_write(&hba->clk_scaling_lock); mutex_unlock(&hba->wb_mutex); - ufshcd_scsi_unblock_requests(hba); + blk_mq_unquiesce_tagset(&hba->host->tag_set); goto out; } @@ -1396,7 +1396,7 @@ static void ufshcd_clock_scaling_unprepare(struct ufs_hba *hba, int err, bool sc mutex_unlock(&hba->wb_mutex); - ufshcd_scsi_unblock_requests(hba); + blk_mq_unquiesce_tagset(&hba->host->tag_set); ufshcd_release(hba); } @@ -8787,6 +8787,7 @@ static int ufshcd_probe_hba(struct ufs_hba *hba, bool init_dev_params) (hba->quirks & UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH)) { /* Reset the device and controller before doing reinit */ ufshcd_device_reset(hba); + ufs_put_device_desc(hba); ufshcd_hba_stop(hba); ufshcd_vops_reinit_notify(hba); ret = ufshcd_hba_enable(hba); diff --git a/drivers/usb/Makefile b/drivers/usb/Makefile index 3a9a0dd4be70..949eca0adebe 100644 --- a/drivers/usb/Makefile +++ b/drivers/usb/Makefile @@ -35,6 +35,7 @@ obj-$(CONFIG_USB_R8A66597_HCD) += host/ obj-$(CONFIG_USB_FSL_USB2) += host/ obj-$(CONFIG_USB_FOTG210_HCD) += host/ obj-$(CONFIG_USB_MAX3421_HCD) += host/ +obj-$(CONFIG_USB_XEN_HCD) += host/ obj-$(CONFIG_USB_C67X00_HCD) += c67x00/ diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c index bada13f704b6..835bf2428dc6 100644 --- a/drivers/usb/chipidea/core.c +++ b/drivers/usb/chipidea/core.c @@ -1084,6 +1084,10 @@ static int ci_hdrc_probe(struct platform_device *pdev) return -ENODEV; } + ret = ci_ulpi_init(ci); + if (ret) + return ret; + if (ci->platdata->phy) { ci->phy = ci->platdata->phy; } else if (ci->platdata->usb_phy) { @@ -1138,10 +1142,6 @@ static int ci_hdrc_probe(struct platform_device *pdev) goto ulpi_exit; } - ret = ci_ulpi_init(ci); - if (ret) - return ret; - ci->hw_bank.phys = res->start; ci->irq = platform_get_irq(pdev, 0); diff --git a/drivers/usb/chipidea/ulpi.c b/drivers/usb/chipidea/ulpi.c index 89fb51e2c3de..dfec07e8ae1d 100644 --- a/drivers/usb/chipidea/ulpi.c +++ b/drivers/usb/chipidea/ulpi.c @@ -68,6 +68,11 @@ int ci_ulpi_init(struct ci_hdrc *ci) if (ci->platdata->phy_mode != USBPHY_INTERFACE_MODE_ULPI) return 0; + /* + * Set PORTSC correctly so we can read/write ULPI registers for + * identification purposes + */ + hw_phymode_configure(ci); ci->ulpi_ops.read = ci_ulpi_read; ci->ulpi_ops.write = ci_ulpi_write; diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index c553decb5461..6830be4419e2 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -266,14 +266,14 @@ static void wdm_int_callback(struct urb *urb) dev_err(&desc->intf->dev, "Stall on int endpoint\n"); goto sw; /* halt is cleared in work */ default: - dev_err(&desc->intf->dev, + dev_err_ratelimited(&desc->intf->dev, "nonzero urb status received: %d\n", status); break; } } if (urb->actual_length < sizeof(struct usb_cdc_notification)) { - dev_err(&desc->intf->dev, "wdm_int_callback - %d bytes\n", + dev_err_ratelimited(&desc->intf->dev, "wdm_int_callback - %d bytes\n", urb->actual_length); goto exit; } diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index e3366f4d82b9..1ff7d901fede 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -1623,6 +1623,7 @@ static void __usb_hcd_giveback_urb(struct urb *urb) struct usb_hcd *hcd = bus_to_hcd(urb->dev->bus); struct usb_anchor *anchor = urb->anchor; int status = urb->unlinked; + unsigned long flags; urb->hcpriv = NULL; if (unlikely((urb->transfer_flags & URB_SHORT_NOT_OK) && @@ -1640,13 +1641,14 @@ static void __usb_hcd_giveback_urb(struct urb *urb) /* pass ownership to the completion handler */ urb->status = status; /* - * This function can be called in task context inside another remote - * coverage collection section, but kcov doesn't support that kind of - * recursion yet. Only collect coverage in softirq context for now. + * Only collect coverage in the softirq context and disable interrupts + * to avoid scenarios with nested remote coverage collection sections + * that KCOV does not support. + * See the comment next to kcov_remote_start_usb_softirq() for details. */ - kcov_remote_start_usb_softirq((u64)urb->dev->bus->busnum); + flags = kcov_remote_start_usb_softirq((u64)urb->dev->bus->busnum); urb->complete(urb); - kcov_remote_stop_softirq(); + kcov_remote_stop_softirq(flags); usb_anchor_resume_wakeups(anchor); atomic_dec(&urb->use_count); diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index c040d816e626..05881153883e 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -36,6 +36,7 @@ #define PCI_VENDOR_ID_ETRON 0x1b6f #define PCI_DEVICE_ID_EJ168 0x7023 +#define PCI_DEVICE_ID_EJ188 0x7052 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_XHCI 0x8c31 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI 0x9c31 @@ -395,6 +396,12 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) xhci->quirks |= XHCI_RESET_ON_RESUME; xhci->quirks |= XHCI_BROKEN_STREAMS; } + if (pdev->vendor == PCI_VENDOR_ID_ETRON && + pdev->device == PCI_DEVICE_ID_EJ188) { + xhci->quirks |= XHCI_RESET_ON_RESUME; + xhci->quirks |= XHCI_BROKEN_STREAMS; + } + if (pdev->vendor == PCI_VENDOR_ID_RENESAS && pdev->device == 0x0014) { xhci->quirks |= XHCI_ZERO_64B_REGS; diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 9e90d2952760..fd0cde3d1569 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1031,13 +1031,27 @@ static int xhci_invalidate_cancelled_tds(struct xhci_virt_ep *ep) break; case TD_DIRTY: /* TD is cached, clear it */ case TD_HALTED: + case TD_CLEARING_CACHE_DEFERRED: + if (cached_td) { + if (cached_td->urb->stream_id != td->urb->stream_id) { + /* Multiple streams case, defer move dq */ + xhci_dbg(xhci, + "Move dq deferred: stream %u URB %p\n", + td->urb->stream_id, td->urb); + td->cancel_status = TD_CLEARING_CACHE_DEFERRED; + break; + } + + /* Should never happen, but clear the TD if it does */ + xhci_warn(xhci, + "Found multiple active URBs %p and %p in stream %u?\n", + td->urb, cached_td->urb, + td->urb->stream_id); + td_to_noop(xhci, ring, cached_td, false); + cached_td->cancel_status = TD_CLEARED; + } + td->cancel_status = TD_CLEARING_CACHE; - if (cached_td) - /* FIXME stream case, several stopped rings */ - xhci_dbg(xhci, - "Move dq past stream %u URB %p instead of stream %u URB %p\n", - td->urb->stream_id, td->urb, - cached_td->urb->stream_id, cached_td->urb); cached_td = td; break; } @@ -1057,10 +1071,16 @@ static int xhci_invalidate_cancelled_tds(struct xhci_virt_ep *ep) if (err) { /* Failed to move past cached td, just set cached TDs to no-op */ list_for_each_entry_safe(td, tmp_td, &ep->cancelled_td_list, cancelled_td_list) { - if (td->cancel_status != TD_CLEARING_CACHE) + /* + * Deferred TDs need to have the deq pointer set after the above command + * completes, so if that failed we just give up on all of them (and + * complain loudly since this could cause issues due to caching). + */ + if (td->cancel_status != TD_CLEARING_CACHE && + td->cancel_status != TD_CLEARING_CACHE_DEFERRED) continue; - xhci_dbg(xhci, "Failed to clear cancelled cached URB %p, mark clear anyway\n", - td->urb); + xhci_warn(xhci, "Failed to clear cancelled cached URB %p, mark clear anyway\n", + td->urb); td_to_noop(xhci, ring, td, false); td->cancel_status = TD_CLEARED; } @@ -1346,6 +1366,7 @@ static void xhci_handle_cmd_set_deq(struct xhci_hcd *xhci, int slot_id, struct xhci_ep_ctx *ep_ctx; struct xhci_slot_ctx *slot_ctx; struct xhci_td *td, *tmp_td; + bool deferred = false; ep_index = TRB_TO_EP_INDEX(le32_to_cpu(trb->generic.field[3])); stream_id = TRB_TO_STREAM_ID(le32_to_cpu(trb->generic.field[2])); @@ -1432,6 +1453,8 @@ static void xhci_handle_cmd_set_deq(struct xhci_hcd *xhci, int slot_id, xhci_dbg(ep->xhci, "%s: Giveback cancelled URB %p TD\n", __func__, td->urb); xhci_td_cleanup(ep->xhci, td, ep_ring, td->status); + } else if (td->cancel_status == TD_CLEARING_CACHE_DEFERRED) { + deferred = true; } else { xhci_dbg(ep->xhci, "%s: Keep cancelled URB %p TD as cancel_status is %d\n", __func__, td->urb, td->cancel_status); @@ -1441,8 +1464,17 @@ cleanup: ep->ep_state &= ~SET_DEQ_PENDING; ep->queued_deq_seg = NULL; ep->queued_deq_ptr = NULL; - /* Restart any rings with pending URBs */ - ring_doorbell_for_active_rings(xhci, slot_id, ep_index); + + if (deferred) { + /* We have more streams to clear */ + xhci_dbg(ep->xhci, "%s: Pending TDs to clear, continuing with invalidation\n", + __func__); + xhci_invalidate_cancelled_tds(ep); + } else { + /* Restart any rings with pending URBs */ + xhci_dbg(ep->xhci, "%s: All TDs cleared, ring doorbell\n", __func__); + ring_doorbell_for_active_rings(xhci, slot_id, ep_index); + } } static void xhci_handle_cmd_reset_ep(struct xhci_hcd *xhci, int slot_id, @@ -2524,9 +2556,8 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, goto finish_td; case COMP_STOPPED_LENGTH_INVALID: /* stopped on ep trb with invalid length, exclude it */ - ep_trb_len = 0; - remaining = 0; - break; + td->urb->actual_length = sum_trb_lengths(xhci, ep_ring, ep_trb); + goto finish_td; case COMP_USB_TRANSACTION_ERROR: if (xhci->quirks & XHCI_NO_SOFT_RETRY || (ep->err_count++ > MAX_SOFT_RETRY) || diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 30415158ed3c..78d014c4d884 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1276,6 +1276,7 @@ enum xhci_cancelled_td_status { TD_DIRTY = 0, TD_HALTED, TD_CLEARING_CACHE, + TD_CLEARING_CACHE_DEFERRED, TD_CLEARED, }; diff --git a/drivers/usb/storage/alauda.c b/drivers/usb/storage/alauda.c index 115f05a6201a..40d34cc28344 100644 --- a/drivers/usb/storage/alauda.c +++ b/drivers/usb/storage/alauda.c @@ -105,6 +105,8 @@ struct alauda_info { unsigned char sense_key; unsigned long sense_asc; /* additional sense code */ unsigned long sense_ascq; /* additional sense code qualifier */ + + bool media_initialized; }; #define short_pack(lsb,msb) ( ((u16)(lsb)) | ( ((u16)(msb))<<8 ) ) @@ -476,11 +478,12 @@ static int alauda_check_media(struct us_data *us) } /* Check for media change */ - if (status[0] & 0x08) { + if (status[0] & 0x08 || !info->media_initialized) { usb_stor_dbg(us, "Media change detected\n"); alauda_free_maps(&MEDIA_INFO(us)); - alauda_init_media(us); - + rc = alauda_init_media(us); + if (rc == USB_STOR_TRANSPORT_GOOD) + info->media_initialized = true; info->sense_key = UNIT_ATTENTION; info->sense_asc = 0x28; info->sense_ascq = 0x00; diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index b31464740f6c..8c8b5e6041cc 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -79,6 +79,12 @@ static int slave_alloc (struct scsi_device *sdev) if (us->protocol == USB_PR_BULK && us->max_lun > 0) sdev->sdev_bflags |= BLIST_FORCELUN; + /* + * Some USB storage devices reset if the IO advice hints grouping mode + * page is queried. Hence skip that mode page. + */ + sdev->sdev_bflags |= BLIST_SKIP_IO_HINTS; + return 0; } diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index a48870a87a29..b610a2de4ae5 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -21,6 +21,7 @@ #include <scsi/scsi.h> #include <scsi/scsi_eh.h> #include <scsi/scsi_dbg.h> +#include <scsi/scsi_devinfo.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_device.h> #include <scsi/scsi_host.h> @@ -820,6 +821,12 @@ static int uas_slave_alloc(struct scsi_device *sdev) struct uas_dev_info *devinfo = (struct uas_dev_info *)sdev->host->hostdata; + /* + * Some USB storage devices reset if the IO advice hints grouping mode + * page is queried. Hence skip that mode page. + */ + sdev->sdev_bflags |= BLIST_SKIP_IO_HINTS; + sdev->hostdata = devinfo; return 0; } diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 8a1af08f71b6..5d4da962acc8 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -3014,8 +3014,10 @@ static int tcpm_register_source_caps(struct tcpm_port *port) memcpy(caps.pdo, port->source_caps, sizeof(u32) * port->nr_source_caps); caps.role = TYPEC_SOURCE; - if (cap) + if (cap) { usb_power_delivery_unregister_capabilities(cap); + port->partner_source_caps = NULL; + } cap = usb_power_delivery_register_capabilities(port->partner_pd, &caps); if (IS_ERR(cap)) @@ -6172,6 +6174,7 @@ static void _tcpm_pd_hard_reset(struct tcpm_port *port) port->tcpc->set_bist_data(port->tcpc, false); switch (port->state) { + case TOGGLING: case ERROR_RECOVERY: case PORT_RESET: case PORT_RESET_WAIT_OFF: diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index cb52e7b0a2c5..2cc7aedd490f 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -153,8 +153,13 @@ static int ucsi_exec_command(struct ucsi *ucsi, u64 cmd) } if (cci & UCSI_CCI_ERROR) { - if (cmd == UCSI_GET_ERROR_STATUS) + if (cmd == UCSI_GET_ERROR_STATUS) { + ret = ucsi_acknowledge(ucsi, false); + if (ret) + return ret; + return -EIO; + } return ucsi_read_error(ucsi); } diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c index f7546bb488c3..985a880e86da 100644 --- a/drivers/usb/typec/ucsi/ucsi_glink.c +++ b/drivers/usb/typec/ucsi/ucsi_glink.c @@ -14,7 +14,7 @@ #include <linux/soc/qcom/pmic_glink.h> #include "ucsi.h" -#define PMIC_GLINK_MAX_PORTS 2 +#define PMIC_GLINK_MAX_PORTS 3 #define UCSI_BUF_SIZE 48 diff --git a/drivers/vfio/device_cdev.c b/drivers/vfio/device_cdev.c index e75da0a70d1f..bb1817bd4ff3 100644 --- a/drivers/vfio/device_cdev.c +++ b/drivers/vfio/device_cdev.c @@ -39,6 +39,13 @@ int vfio_device_fops_cdev_open(struct inode *inode, struct file *filep) filep->private_data = df; + /* + * Use the pseudo fs inode on the device to link all mmaps + * to the same address space, allowing us to unmap all vmas + * associated to this device using unmap_mapping_range(). + */ + filep->f_mapping = device->inode->i_mapping; + return 0; err_put_registration: diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c index 610a429c6191..ded364588d29 100644 --- a/drivers/vfio/group.c +++ b/drivers/vfio/group.c @@ -286,6 +286,13 @@ static struct file *vfio_device_open_file(struct vfio_device *device) */ filep->f_mode |= (FMODE_PREAD | FMODE_PWRITE); + /* + * Use the pseudo fs inode on the device to link all mmaps + * to the same address space, allowing us to unmap all vmas + * associated to this device using unmap_mapping_range(). + */ + filep->f_mapping = device->inode->i_mapping; + if (device->group->type == VFIO_NO_IOMMU) dev_warn(device->dev, "vfio-noiommu device opened by user " "(%s:%d)\n", current->comm, task_pid_nr(current)); diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 80cae87fff36..987c7921affa 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -1610,100 +1610,20 @@ ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *bu } EXPORT_SYMBOL_GPL(vfio_pci_core_write); -/* Return 1 on zap and vma_lock acquired, 0 on contention (only with @try) */ -static int vfio_pci_zap_and_vma_lock(struct vfio_pci_core_device *vdev, bool try) +static void vfio_pci_zap_bars(struct vfio_pci_core_device *vdev) { - struct vfio_pci_mmap_vma *mmap_vma, *tmp; + struct vfio_device *core_vdev = &vdev->vdev; + loff_t start = VFIO_PCI_INDEX_TO_OFFSET(VFIO_PCI_BAR0_REGION_INDEX); + loff_t end = VFIO_PCI_INDEX_TO_OFFSET(VFIO_PCI_ROM_REGION_INDEX); + loff_t len = end - start; - /* - * Lock ordering: - * vma_lock is nested under mmap_lock for vm_ops callback paths. - * The memory_lock semaphore is used by both code paths calling - * into this function to zap vmas and the vm_ops.fault callback - * to protect the memory enable state of the device. - * - * When zapping vmas we need to maintain the mmap_lock => vma_lock - * ordering, which requires using vma_lock to walk vma_list to - * acquire an mm, then dropping vma_lock to get the mmap_lock and - * reacquiring vma_lock. This logic is derived from similar - * requirements in uverbs_user_mmap_disassociate(). - * - * mmap_lock must always be the top-level lock when it is taken. - * Therefore we can only hold the memory_lock write lock when - * vma_list is empty, as we'd need to take mmap_lock to clear - * entries. vma_list can only be guaranteed empty when holding - * vma_lock, thus memory_lock is nested under vma_lock. - * - * This enables the vm_ops.fault callback to acquire vma_lock, - * followed by memory_lock read lock, while already holding - * mmap_lock without risk of deadlock. - */ - while (1) { - struct mm_struct *mm = NULL; - - if (try) { - if (!mutex_trylock(&vdev->vma_lock)) - return 0; - } else { - mutex_lock(&vdev->vma_lock); - } - while (!list_empty(&vdev->vma_list)) { - mmap_vma = list_first_entry(&vdev->vma_list, - struct vfio_pci_mmap_vma, - vma_next); - mm = mmap_vma->vma->vm_mm; - if (mmget_not_zero(mm)) - break; - - list_del(&mmap_vma->vma_next); - kfree(mmap_vma); - mm = NULL; - } - if (!mm) - return 1; - mutex_unlock(&vdev->vma_lock); - - if (try) { - if (!mmap_read_trylock(mm)) { - mmput(mm); - return 0; - } - } else { - mmap_read_lock(mm); - } - if (try) { - if (!mutex_trylock(&vdev->vma_lock)) { - mmap_read_unlock(mm); - mmput(mm); - return 0; - } - } else { - mutex_lock(&vdev->vma_lock); - } - list_for_each_entry_safe(mmap_vma, tmp, - &vdev->vma_list, vma_next) { - struct vm_area_struct *vma = mmap_vma->vma; - - if (vma->vm_mm != mm) - continue; - - list_del(&mmap_vma->vma_next); - kfree(mmap_vma); - - zap_vma_ptes(vma, vma->vm_start, - vma->vm_end - vma->vm_start); - } - mutex_unlock(&vdev->vma_lock); - mmap_read_unlock(mm); - mmput(mm); - } + unmap_mapping_range(core_vdev->inode->i_mapping, start, len, true); } void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device *vdev) { - vfio_pci_zap_and_vma_lock(vdev, false); down_write(&vdev->memory_lock); - mutex_unlock(&vdev->vma_lock); + vfio_pci_zap_bars(vdev); } u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_core_device *vdev) @@ -1725,99 +1645,56 @@ void vfio_pci_memory_unlock_and_restore(struct vfio_pci_core_device *vdev, u16 c up_write(&vdev->memory_lock); } -/* Caller holds vma_lock */ -static int __vfio_pci_add_vma(struct vfio_pci_core_device *vdev, - struct vm_area_struct *vma) -{ - struct vfio_pci_mmap_vma *mmap_vma; - - mmap_vma = kmalloc(sizeof(*mmap_vma), GFP_KERNEL_ACCOUNT); - if (!mmap_vma) - return -ENOMEM; - - mmap_vma->vma = vma; - list_add(&mmap_vma->vma_next, &vdev->vma_list); - - return 0; -} - -/* - * Zap mmaps on open so that we can fault them in on access and therefore - * our vma_list only tracks mappings accessed since last zap. - */ -static void vfio_pci_mmap_open(struct vm_area_struct *vma) -{ - zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); -} - -static void vfio_pci_mmap_close(struct vm_area_struct *vma) +static unsigned long vma_to_pfn(struct vm_area_struct *vma) { struct vfio_pci_core_device *vdev = vma->vm_private_data; - struct vfio_pci_mmap_vma *mmap_vma; + int index = vma->vm_pgoff >> (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT); + u64 pgoff; - mutex_lock(&vdev->vma_lock); - list_for_each_entry(mmap_vma, &vdev->vma_list, vma_next) { - if (mmap_vma->vma == vma) { - list_del(&mmap_vma->vma_next); - kfree(mmap_vma); - break; - } - } - mutex_unlock(&vdev->vma_lock); + pgoff = vma->vm_pgoff & + ((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) - 1); + + return (pci_resource_start(vdev->pdev, index) >> PAGE_SHIFT) + pgoff; } static vm_fault_t vfio_pci_mmap_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct vfio_pci_core_device *vdev = vma->vm_private_data; - struct vfio_pci_mmap_vma *mmap_vma; - vm_fault_t ret = VM_FAULT_NOPAGE; + unsigned long pfn, pgoff = vmf->pgoff - vma->vm_pgoff; + unsigned long addr = vma->vm_start; + vm_fault_t ret = VM_FAULT_SIGBUS; + + pfn = vma_to_pfn(vma); - mutex_lock(&vdev->vma_lock); down_read(&vdev->memory_lock); - /* - * Memory region cannot be accessed if the low power feature is engaged - * or memory access is disabled. - */ - if (vdev->pm_runtime_engaged || !__vfio_pci_memory_enabled(vdev)) { - ret = VM_FAULT_SIGBUS; - goto up_out; - } + if (vdev->pm_runtime_engaged || !__vfio_pci_memory_enabled(vdev)) + goto out_unlock; + + ret = vmf_insert_pfn(vma, vmf->address, pfn + pgoff); + if (ret & VM_FAULT_ERROR) + goto out_unlock; /* - * We populate the whole vma on fault, so we need to test whether - * the vma has already been mapped, such as for concurrent faults - * to the same vma. io_remap_pfn_range() will trigger a BUG_ON if - * we ask it to fill the same range again. + * Pre-fault the remainder of the vma, abort further insertions and + * supress error if fault is encountered during pre-fault. */ - list_for_each_entry(mmap_vma, &vdev->vma_list, vma_next) { - if (mmap_vma->vma == vma) - goto up_out; - } - - if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, - vma->vm_end - vma->vm_start, - vma->vm_page_prot)) { - ret = VM_FAULT_SIGBUS; - zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); - goto up_out; - } + for (; addr < vma->vm_end; addr += PAGE_SIZE, pfn++) { + if (addr == vmf->address) + continue; - if (__vfio_pci_add_vma(vdev, vma)) { - ret = VM_FAULT_OOM; - zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); + if (vmf_insert_pfn(vma, addr, pfn) & VM_FAULT_ERROR) + break; } -up_out: +out_unlock: up_read(&vdev->memory_lock); - mutex_unlock(&vdev->vma_lock); + return ret; } static const struct vm_operations_struct vfio_pci_mmap_ops = { - .open = vfio_pci_mmap_open, - .close = vfio_pci_mmap_close, .fault = vfio_pci_mmap_fault, }; @@ -1880,11 +1757,12 @@ int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma vma->vm_private_data = vdev; vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - vma->vm_pgoff = (pci_resource_start(pdev, index) >> PAGE_SHIFT) + pgoff; + vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot); /* - * See remap_pfn_range(), called from vfio_pci_fault() but we can't - * change vm_flags within the fault handler. Set them now. + * Set vm_flags now, they should not be changed in the fault handler. + * We want the same flags and page protection (decrypted above) as + * io_remap_pfn_range() would set. * * VM_ALLOW_ANY_UNCACHED: The VMA flag is implemented for ARM64, * allowing KVM stage 2 device mapping attributes to use Normal-NC @@ -2202,8 +2080,6 @@ int vfio_pci_core_init_dev(struct vfio_device *core_vdev) mutex_init(&vdev->ioeventfds_lock); INIT_LIST_HEAD(&vdev->dummy_resources_list); INIT_LIST_HEAD(&vdev->ioeventfds_list); - mutex_init(&vdev->vma_lock); - INIT_LIST_HEAD(&vdev->vma_list); INIT_LIST_HEAD(&vdev->sriov_pfs_item); init_rwsem(&vdev->memory_lock); xa_init(&vdev->ctx); @@ -2219,7 +2095,6 @@ void vfio_pci_core_release_dev(struct vfio_device *core_vdev) mutex_destroy(&vdev->igate); mutex_destroy(&vdev->ioeventfds_lock); - mutex_destroy(&vdev->vma_lock); kfree(vdev->region); kfree(vdev->pm_save); } @@ -2497,26 +2372,15 @@ unwind: return ret; } -/* - * We need to get memory_lock for each device, but devices can share mmap_lock, - * therefore we need to zap and hold the vma_lock for each device, and only then - * get each memory_lock. - */ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, struct vfio_pci_group_info *groups, struct iommufd_ctx *iommufd_ctx) { - struct vfio_pci_core_device *cur_mem; - struct vfio_pci_core_device *cur_vma; - struct vfio_pci_core_device *cur; + struct vfio_pci_core_device *vdev; struct pci_dev *pdev; - bool is_mem = true; int ret; mutex_lock(&dev_set->lock); - cur_mem = list_first_entry(&dev_set->device_list, - struct vfio_pci_core_device, - vdev.dev_set_list); pdev = vfio_pci_dev_set_resettable(dev_set); if (!pdev) { @@ -2533,7 +2397,7 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, if (ret) goto err_unlock; - list_for_each_entry(cur_vma, &dev_set->device_list, vdev.dev_set_list) { + list_for_each_entry(vdev, &dev_set->device_list, vdev.dev_set_list) { bool owned; /* @@ -2557,38 +2421,38 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, * Otherwise, reset is not allowed. */ if (iommufd_ctx) { - int devid = vfio_iommufd_get_dev_id(&cur_vma->vdev, + int devid = vfio_iommufd_get_dev_id(&vdev->vdev, iommufd_ctx); owned = (devid > 0 || devid == -ENOENT); } else { - owned = vfio_dev_in_groups(&cur_vma->vdev, groups); + owned = vfio_dev_in_groups(&vdev->vdev, groups); } if (!owned) { ret = -EINVAL; - goto err_undo; + break; } /* - * Locking multiple devices is prone to deadlock, runaway and - * unwind if we hit contention. + * Take the memory write lock for each device and zap BAR + * mappings to prevent the user accessing the device while in + * reset. Locking multiple devices is prone to deadlock, + * runaway and unwind if we hit contention. */ - if (!vfio_pci_zap_and_vma_lock(cur_vma, true)) { + if (!down_write_trylock(&vdev->memory_lock)) { ret = -EBUSY; - goto err_undo; + break; } + + vfio_pci_zap_bars(vdev); } - cur_vma = NULL; - list_for_each_entry(cur_mem, &dev_set->device_list, vdev.dev_set_list) { - if (!down_write_trylock(&cur_mem->memory_lock)) { - ret = -EBUSY; - goto err_undo; - } - mutex_unlock(&cur_mem->vma_lock); + if (!list_entry_is_head(vdev, + &dev_set->device_list, vdev.dev_set_list)) { + vdev = list_prev_entry(vdev, vdev.dev_set_list); + goto err_undo; } - cur_mem = NULL; /* * The pci_reset_bus() will reset all the devices in the bus. @@ -2599,25 +2463,22 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, * cause the PCI config space reset without restoring the original * state (saved locally in 'vdev->pm_save'). */ - list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) - vfio_pci_set_power_state(cur, PCI_D0); + list_for_each_entry(vdev, &dev_set->device_list, vdev.dev_set_list) + vfio_pci_set_power_state(vdev, PCI_D0); ret = pci_reset_bus(pdev); + vdev = list_last_entry(&dev_set->device_list, + struct vfio_pci_core_device, vdev.dev_set_list); + err_undo: - list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) { - if (cur == cur_mem) - is_mem = false; - if (cur == cur_vma) - break; - if (is_mem) - up_write(&cur->memory_lock); - else - mutex_unlock(&cur->vma_lock); - } + list_for_each_entry_from_reverse(vdev, &dev_set->device_list, + vdev.dev_set_list) + up_write(&vdev->memory_lock); + + list_for_each_entry(vdev, &dev_set->device_list, vdev.dev_set_list) + pm_runtime_put(&vdev->pdev->dev); - list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) - pm_runtime_put(&cur->pdev->dev); err_unlock: mutex_unlock(&dev_set->lock); return ret; diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c index e97d796a54fb..a5a62d9d963f 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -22,8 +22,10 @@ #include <linux/list.h> #include <linux/miscdevice.h> #include <linux/module.h> +#include <linux/mount.h> #include <linux/mutex.h> #include <linux/pci.h> +#include <linux/pseudo_fs.h> #include <linux/rwsem.h> #include <linux/sched.h> #include <linux/slab.h> @@ -43,9 +45,13 @@ #define DRIVER_AUTHOR "Alex Williamson <[email protected]>" #define DRIVER_DESC "VFIO - User Level meta-driver" +#define VFIO_MAGIC 0x5646494f /* "VFIO" */ + static struct vfio { struct class *device_class; struct ida device_ida; + struct vfsmount *vfs_mount; + int fs_count; } vfio; #ifdef CONFIG_VFIO_NOIOMMU @@ -186,6 +192,8 @@ static void vfio_device_release(struct device *dev) if (device->ops->release) device->ops->release(device); + iput(device->inode); + simple_release_fs(&vfio.vfs_mount, &vfio.fs_count); kvfree(device); } @@ -228,6 +236,34 @@ out_free: } EXPORT_SYMBOL_GPL(_vfio_alloc_device); +static int vfio_fs_init_fs_context(struct fs_context *fc) +{ + return init_pseudo(fc, VFIO_MAGIC) ? 0 : -ENOMEM; +} + +static struct file_system_type vfio_fs_type = { + .name = "vfio", + .owner = THIS_MODULE, + .init_fs_context = vfio_fs_init_fs_context, + .kill_sb = kill_anon_super, +}; + +static struct inode *vfio_fs_inode_new(void) +{ + struct inode *inode; + int ret; + + ret = simple_pin_fs(&vfio_fs_type, &vfio.vfs_mount, &vfio.fs_count); + if (ret) + return ERR_PTR(ret); + + inode = alloc_anon_inode(vfio.vfs_mount->mnt_sb); + if (IS_ERR(inode)) + simple_release_fs(&vfio.vfs_mount, &vfio.fs_count); + + return inode; +} + /* * Initialize a vfio_device so it can be registered to vfio core. */ @@ -246,6 +282,11 @@ static int vfio_init_device(struct vfio_device *device, struct device *dev, init_completion(&device->comp); device->dev = dev; device->ops = ops; + device->inode = vfio_fs_inode_new(); + if (IS_ERR(device->inode)) { + ret = PTR_ERR(device->inode); + goto out_inode; + } if (ops->init) { ret = ops->init(device); @@ -260,6 +301,9 @@ static int vfio_init_device(struct vfio_device *device, struct device *dev, return 0; out_uninit: + iput(device->inode); + simple_release_fs(&vfio.vfs_mount, &vfio.fs_count); +out_inode: vfio_release_device_set(device); ida_free(&vfio.device_ida, device->index); return ret; diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c index 346cd91f91f9..8dec2c6cbb7e 100644 --- a/fs/bcachefs/alloc_background.c +++ b/fs/bcachefs/alloc_background.c @@ -259,6 +259,14 @@ int bch2_alloc_v4_invalid(struct bch_fs *c, struct bkey_s_c k, "invalid data type (got %u should be %u)", a.v->data_type, alloc_data_type(*a.v, a.v->data_type)); + for (unsigned i = 0; i < 2; i++) + bkey_fsck_err_on(a.v->io_time[i] > LRU_TIME_MAX, + c, err, + alloc_key_io_time_bad, + "invalid io_time[%s]: %llu, max %llu", + i == READ ? "read" : "write", + a.v->io_time[i], LRU_TIME_MAX); + switch (a.v->data_type) { case BCH_DATA_free: case BCH_DATA_need_gc_gens: @@ -741,6 +749,7 @@ int bch2_trigger_alloc(struct btree_trans *trans, enum btree_iter_update_trigger_flags flags) { struct bch_fs *c = trans->c; + struct printbuf buf = PRINTBUF; int ret = 0; struct bch_dev *ca = bch2_dev_bucket_tryget(c, new.k->p); @@ -756,8 +765,8 @@ int bch2_trigger_alloc(struct btree_trans *trans, alloc_data_type_set(new_a, new_a->data_type); if (bch2_bucket_sectors_total(*new_a) > bch2_bucket_sectors_total(*old_a)) { - new_a->io_time[READ] = max_t(u64, 1, atomic64_read(&c->io_clock[READ].now)); - new_a->io_time[WRITE]= max_t(u64, 1, atomic64_read(&c->io_clock[WRITE].now)); + new_a->io_time[READ] = bch2_current_io_time(c, READ); + new_a->io_time[WRITE]= bch2_current_io_time(c, WRITE); SET_BCH_ALLOC_V4_NEED_INC_GEN(new_a, true); SET_BCH_ALLOC_V4_NEED_DISCARD(new_a, true); } @@ -767,6 +776,7 @@ int bch2_trigger_alloc(struct btree_trans *trans, !bch2_bucket_is_open_safe(c, new.k->p.inode, new.k->p.offset)) { new_a->gen++; SET_BCH_ALLOC_V4_NEED_INC_GEN(new_a, false); + alloc_data_type_set(new_a, new_a->data_type); } if (old_a->data_type != new_a->data_type || @@ -780,7 +790,7 @@ int bch2_trigger_alloc(struct btree_trans *trans, if (new_a->data_type == BCH_DATA_cached && !new_a->io_time[READ]) - new_a->io_time[READ] = max_t(u64, 1, atomic64_read(&c->io_clock[READ].now)); + new_a->io_time[READ] = bch2_current_io_time(c, READ); u64 old_lru = alloc_lru_idx_read(*old_a); u64 new_lru = alloc_lru_idx_read(*new_a); @@ -860,8 +870,14 @@ int bch2_trigger_alloc(struct btree_trans *trans, } percpu_down_read(&c->mark_lock); - if (new_a->gen != old_a->gen) - *bucket_gen(ca, new.k->p.offset) = new_a->gen; + if (new_a->gen != old_a->gen) { + u8 *gen = bucket_gen(ca, new.k->p.offset); + if (unlikely(!gen)) { + percpu_up_read(&c->mark_lock); + goto invalid_bucket; + } + *gen = new_a->gen; + } bch2_dev_usage_update(c, ca, old_a, new_a, journal_seq, false); percpu_up_read(&c->mark_lock); @@ -875,7 +891,7 @@ int bch2_trigger_alloc(struct btree_trans *trans, closure_wake_up(&c->freelist_wait); if (statechange(a->data_type == BCH_DATA_need_discard) && - !bch2_bucket_is_open(c, new.k->p.inode, new.k->p.offset) && + !bch2_bucket_is_open_safe(c, new.k->p.inode, new.k->p.offset) && bucket_flushed(new_a)) bch2_discard_one_bucket_fast(c, new.k->p); @@ -895,6 +911,11 @@ int bch2_trigger_alloc(struct btree_trans *trans, percpu_down_read(&c->mark_lock); struct bucket *g = gc_bucket(ca, new.k->p.offset); + if (unlikely(!g)) { + percpu_up_read(&c->mark_lock); + goto invalid_bucket; + } + g->gen_valid = 1; bucket_lock(g); @@ -910,8 +931,14 @@ int bch2_trigger_alloc(struct btree_trans *trans, percpu_up_read(&c->mark_lock); } err: + printbuf_exit(&buf); bch2_dev_put(ca); return ret; +invalid_bucket: + bch2_fs_inconsistent(c, "reference to invalid bucket\n %s", + (bch2_bkey_val_to_text(&buf, c, new.s_c), buf.buf)); + ret = -EIO; + goto err; } /* @@ -1561,7 +1588,7 @@ static int bch2_check_alloc_to_lru_ref(struct btree_trans *trans, if (ret) goto err; - a_mut->v.io_time[READ] = atomic64_read(&c->io_clock[READ].now); + a_mut->v.io_time[READ] = bch2_current_io_time(c, READ); ret = bch2_trans_update(trans, alloc_iter, &a_mut->k_i, BTREE_TRIGGER_norun); if (ret) @@ -1616,7 +1643,7 @@ static int discard_in_flight_add(struct bch_fs *c, struct bpos bucket) mutex_lock(&c->discard_buckets_in_flight_lock); darray_for_each(c->discard_buckets_in_flight, i) if (bkey_eq(*i, bucket)) { - ret = -EEXIST; + ret = -BCH_ERR_EEXIST_discard_in_flight_add; goto out; } @@ -1770,8 +1797,9 @@ static int bch2_discard_one_bucket(struct btree_trans *trans, } SET_BCH_ALLOC_V4_NEED_DISCARD(&a->v, false); - alloc_data_type_set(&a->v, a->v.data_type); write: + alloc_data_type_set(&a->v, a->v.data_type); + ret = bch2_trans_update(trans, &iter, &a->k_i, 0) ?: bch2_trans_commit(trans, NULL, NULL, BCH_WATERMARK_btree| @@ -1957,8 +1985,8 @@ static int invalidate_one_bucket(struct btree_trans *trans, a->v.data_type = 0; a->v.dirty_sectors = 0; a->v.cached_sectors = 0; - a->v.io_time[READ] = atomic64_read(&c->io_clock[READ].now); - a->v.io_time[WRITE] = atomic64_read(&c->io_clock[WRITE].now); + a->v.io_time[READ] = bch2_current_io_time(c, READ); + a->v.io_time[WRITE] = bch2_current_io_time(c, WRITE); ret = bch2_trans_commit(trans, NULL, NULL, BCH_WATERMARK_btree| @@ -1993,6 +2021,21 @@ err: goto out; } +static struct bkey_s_c next_lru_key(struct btree_trans *trans, struct btree_iter *iter, + struct bch_dev *ca, bool *wrapped) +{ + struct bkey_s_c k; +again: + k = bch2_btree_iter_peek_upto(iter, lru_pos(ca->dev_idx, U64_MAX, LRU_TIME_MAX)); + if (!k.k && !*wrapped) { + bch2_btree_iter_set_pos(iter, lru_pos(ca->dev_idx, 0, 0)); + *wrapped = true; + goto again; + } + + return k; +} + static void bch2_do_invalidates_work(struct work_struct *work) { struct bch_fs *c = container_of(work, struct bch_fs, invalidate_work); @@ -2006,12 +2049,33 @@ static void bch2_do_invalidates_work(struct work_struct *work) for_each_member_device(c, ca) { s64 nr_to_invalidate = should_invalidate_buckets(ca, bch2_dev_usage_read(ca)); + struct btree_iter iter; + bool wrapped = false; - ret = for_each_btree_key_upto(trans, iter, BTREE_ID_lru, - lru_pos(ca->dev_idx, 0, 0), - lru_pos(ca->dev_idx, U64_MAX, LRU_TIME_MAX), - BTREE_ITER_intent, k, - invalidate_one_bucket(trans, &iter, k, &nr_to_invalidate)); + bch2_trans_iter_init(trans, &iter, BTREE_ID_lru, + lru_pos(ca->dev_idx, 0, + ((bch2_current_io_time(c, READ) + U32_MAX) & + LRU_TIME_MAX)), 0); + + while (true) { + bch2_trans_begin(trans); + + struct bkey_s_c k = next_lru_key(trans, &iter, ca, &wrapped); + ret = bkey_err(k); + if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) + continue; + if (ret) + break; + if (!k.k) + break; + + ret = invalidate_one_bucket(trans, &iter, k, &nr_to_invalidate); + if (ret) + break; + + bch2_btree_iter_advance(&iter); + } + bch2_trans_iter_exit(trans, &iter); if (ret < 0) { bch2_dev_put(ca); @@ -2186,7 +2250,7 @@ int bch2_bucket_io_time_reset(struct btree_trans *trans, unsigned dev, if (ret) return ret; - now = atomic64_read(&c->io_clock[rw].now); + now = bch2_current_io_time(c, rw); if (a->v.io_time[rw] == now) goto out; diff --git a/fs/bcachefs/alloc_background.h b/fs/bcachefs/alloc_background.h index ae31a94be6f9..c3cc3c5ba5b6 100644 --- a/fs/bcachefs/alloc_background.h +++ b/fs/bcachefs/alloc_background.h @@ -141,7 +141,13 @@ static inline u64 alloc_lru_idx_fragmentation(struct bch_alloc_v4 a, !bch2_bucket_sectors_fragmented(ca, a)) return 0; - u64 d = bch2_bucket_sectors_dirty(a); + /* + * avoid overflowing LRU_TIME_BITS on a corrupted fs, when + * bucket_sectors_dirty is (much) bigger than bucket_size + */ + u64 d = min(bch2_bucket_sectors_dirty(a), + ca->mi.bucket_size); + return div_u64(d * (1ULL << 31), ca->mi.bucket_size); } diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h index 2a538eb2af11..a6b83ecab7ce 100644 --- a/fs/bcachefs/bcachefs.h +++ b/fs/bcachefs/bcachefs.h @@ -790,7 +790,8 @@ struct bch_fs { /* BTREE CACHE */ struct bio_set btree_bio; - struct workqueue_struct *io_complete_wq; + struct workqueue_struct *btree_read_complete_wq; + struct workqueue_struct *btree_write_submit_wq; struct btree_root btree_roots_known[BTREE_ID_NR]; DARRAY(struct btree_root) btree_roots_extra; @@ -1213,6 +1214,11 @@ static inline s64 bch2_current_time(const struct bch_fs *c) return timespec_to_bch2_time(c, now); } +static inline u64 bch2_current_io_time(const struct bch_fs *c, int rw) +{ + return max(1ULL, (u64) atomic64_read(&c->io_clock[rw].now) & LRU_TIME_MAX); +} + static inline struct stdio_redirect *bch2_fs_stdio_redirect(struct bch_fs *c) { struct stdio_redirect *stdio = c->stdio; diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h index 90c12fe2a2cd..e3b1bde489c3 100644 --- a/fs/bcachefs/bcachefs_format.h +++ b/fs/bcachefs/bcachefs_format.h @@ -476,6 +476,9 @@ struct bch_lru { #define LRU_ID_STRIPES (1U << 16) +#define LRU_TIME_BITS 48 +#define LRU_TIME_MAX ((1ULL << LRU_TIME_BITS) - 1) + /* Optional/variable size superblock sections: */ struct bch_sb_field { @@ -987,8 +990,9 @@ enum bch_version_upgrade_opts { #define BCH_ERROR_ACTIONS() \ x(continue, 0) \ - x(ro, 1) \ - x(panic, 2) + x(fix_safe, 1) \ + x(panic, 2) \ + x(ro, 3) enum bch_error_actions { #define x(t, n) BCH_ON_ERROR_##t = n, @@ -1382,9 +1386,10 @@ enum btree_id { /* * Maximum number of btrees that we will _ever_ have under the current scheme, - * where we refer to them with bitfields + * where we refer to them with 64 bit bitfields - and we also need a bit for + * the interior btree node type: */ -#define BTREE_ID_NR_MAX 64 +#define BTREE_ID_NR_MAX 63 static inline bool btree_id_is_alloc(enum btree_id id) { diff --git a/fs/bcachefs/bkey.c b/fs/bcachefs/bkey.c index f46978e5cb7c..94a1d1982fa8 100644 --- a/fs/bcachefs/bkey.c +++ b/fs/bcachefs/bkey.c @@ -1064,7 +1064,7 @@ void bch2_bkey_swab_key(const struct bkey_format *_f, struct bkey_packed *k) { const struct bkey_format *f = bkey_packed(k) ? _f : &bch2_bkey_format_current; u8 *l = k->key_start; - u8 *h = (u8 *) (k->_data + f->key_u64s) - 1; + u8 *h = (u8 *) ((u64 *) k->_data + f->key_u64s) - 1; while (l < h) { swap(*l, *h); diff --git a/fs/bcachefs/bkey_methods.c b/fs/bcachefs/bkey_methods.c index c2c3dae52186..bd32aac05192 100644 --- a/fs/bcachefs/bkey_methods.c +++ b/fs/bcachefs/bkey_methods.c @@ -398,8 +398,12 @@ void __bch2_bkey_compat(unsigned level, enum btree_id btree_id, for (i = 0; i < nr_compat; i++) switch (!write ? i : nr_compat - 1 - i) { case 0: - if (big_endian != CPU_BIG_ENDIAN) + if (big_endian != CPU_BIG_ENDIAN) { + bch2_bkey_swab_key(f, k); + } else if (IS_ENABLED(CONFIG_BCACHEFS_DEBUG)) { bch2_bkey_swab_key(f, k); + bch2_bkey_swab_key(f, k); + } break; case 1: if (version < bcachefs_metadata_version_bkey_renumber) diff --git a/fs/bcachefs/bkey_methods.h b/fs/bcachefs/bkey_methods.h index 726ef7483763..baef0722f5fb 100644 --- a/fs/bcachefs/bkey_methods.h +++ b/fs/bcachefs/bkey_methods.h @@ -129,7 +129,8 @@ static inline void bch2_bkey_compat(unsigned level, enum btree_id btree_id, struct bkey_packed *k) { if (version < bcachefs_metadata_version_current || - big_endian != CPU_BIG_ENDIAN) + big_endian != CPU_BIG_ENDIAN || + IS_ENABLED(CONFIG_BCACHEFS_DEBUG)) __bch2_bkey_compat(level, btree_id, version, big_endian, write, f, k); diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c index 9e4ed75d3675..4f5e411771ba 100644 --- a/fs/bcachefs/btree_cache.c +++ b/fs/bcachefs/btree_cache.c @@ -91,10 +91,11 @@ static int bch2_btree_cache_cmp_fn(struct rhashtable_compare_arg *arg, } static const struct rhashtable_params bch_btree_cache_params = { - .head_offset = offsetof(struct btree, hash), - .key_offset = offsetof(struct btree, hash_val), - .key_len = sizeof(u64), - .obj_cmpfn = bch2_btree_cache_cmp_fn, + .head_offset = offsetof(struct btree, hash), + .key_offset = offsetof(struct btree, hash_val), + .key_len = sizeof(u64), + .obj_cmpfn = bch2_btree_cache_cmp_fn, + .automatic_shrinking = true, }; static int btree_node_data_alloc(struct bch_fs *c, struct btree *b, gfp_t gfp) diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c index dc97991bcd6a..0e477a926579 100644 --- a/fs/bcachefs/btree_gc.c +++ b/fs/bcachefs/btree_gc.c @@ -874,6 +874,9 @@ static int bch2_alloc_write_key(struct btree_trans *trans, const struct bch_alloc_v4 *old; int ret; + if (!bucket_valid(ca, k.k->p.offset)) + return 0; + old = bch2_alloc_to_v4(k, &old_convert); gc = new = *old; @@ -990,6 +993,8 @@ static int bch2_gc_alloc_start(struct bch_fs *c) buckets->first_bucket = ca->mi.first_bucket; buckets->nbuckets = ca->mi.nbuckets; + buckets->nbuckets_minus_first = + buckets->nbuckets - buckets->first_bucket; rcu_assign_pointer(ca->buckets_gc, buckets); } @@ -1003,12 +1008,14 @@ static int bch2_gc_alloc_start(struct bch_fs *c) continue; } - struct bch_alloc_v4 a_convert; - const struct bch_alloc_v4 *a = bch2_alloc_to_v4(k, &a_convert); + if (bucket_valid(ca, k.k->p.offset)) { + struct bch_alloc_v4 a_convert; + const struct bch_alloc_v4 *a = bch2_alloc_to_v4(k, &a_convert); - struct bucket *g = gc_bucket(ca, k.k->p.offset); - g->gen_valid = 1; - g->gen = a->gen; + struct bucket *g = gc_bucket(ca, k.k->p.offset); + g->gen_valid = 1; + g->gen = a->gen; + } 0; }))); bch2_dev_put(ca); diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index 829c1b91477d..7bca15c604f5 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -1389,7 +1389,7 @@ static void btree_node_read_endio(struct bio *bio) bch2_latency_acct(ca, rb->start_time, READ); } - queue_work(c->io_complete_wq, &rb->work); + queue_work(c->btree_read_complete_wq, &rb->work); } struct btree_node_read_all { @@ -1656,7 +1656,7 @@ static int btree_node_read_all_replicas(struct bch_fs *c, struct btree *b, bool btree_node_read_all_replicas_done(&ra->cl.work); } else { continue_at(&ra->cl, btree_node_read_all_replicas_done, - c->io_complete_wq); + c->btree_read_complete_wq); } return 0; @@ -1737,7 +1737,7 @@ void bch2_btree_node_read(struct btree_trans *trans, struct btree *b, if (sync) btree_node_read_work(&rb->work); else - queue_work(c->io_complete_wq, &rb->work); + queue_work(c->btree_read_complete_wq, &rb->work); } } @@ -2229,7 +2229,7 @@ do_write: atomic64_add(bytes_to_write, &c->btree_write_stats[type].bytes); INIT_WORK(&wbio->work, btree_write_submit); - queue_work(c->io_complete_wq, &wbio->work); + queue_work(c->btree_write_submit_wq, &wbio->work); return; err: set_btree_node_noevict(b); diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c index d3bcb4e4e230..3a1419d17888 100644 --- a/fs/bcachefs/btree_iter.c +++ b/fs/bcachefs/btree_iter.c @@ -221,11 +221,8 @@ static void bch2_btree_path_verify(struct btree_trans *trans, struct btree_path *path) { struct bch_fs *c = trans->c; - unsigned i; - - EBUG_ON(path->btree_id >= BTREE_ID_NR); - for (i = 0; i < (!path->cached ? BTREE_MAX_DEPTH : 1); i++) { + for (unsigned i = 0; i < (!path->cached ? BTREE_MAX_DEPTH : 1); i++) { if (!path->l[i].b) { BUG_ON(!path->cached && bch2_btree_id_root(c, path->btree_id)->b->c.level > i); @@ -251,8 +248,6 @@ static void bch2_btree_iter_verify(struct btree_iter *iter) { struct btree_trans *trans = iter->trans; - BUG_ON(iter->btree_id >= BTREE_ID_NR); - BUG_ON(!!(iter->flags & BTREE_ITER_cached) != btree_iter_path(trans, iter)->cached); BUG_ON((iter->flags & BTREE_ITER_is_extents) && @@ -3166,6 +3161,7 @@ struct btree_trans *__bch2_trans_get(struct bch_fs *c, unsigned fn_idx) list_add_done: seqmutex_unlock(&c->btree_trans_lock); got_trans: + trans->ref.closure_get_happened = false; trans->c = c; trans->last_begin_time = local_clock(); trans->fn_idx = fn_idx; @@ -3240,7 +3236,6 @@ void bch2_trans_put(struct btree_trans *trans) trans_for_each_update(trans, i) __btree_path_put(trans->paths + i->path, true); trans->nr_updates = 0; - trans->locking_wait.task = NULL; check_btree_paths_leaked(trans); @@ -3261,6 +3256,13 @@ void bch2_trans_put(struct btree_trans *trans) if (unlikely(trans->journal_replay_not_finished)) bch2_journal_keys_put(c); + /* + * trans->ref protects trans->locking_wait.task, btree_paths arary; used + * by cycle detector + */ + closure_sync(&trans->ref); + trans->locking_wait.task = NULL; + unsigned long *paths_allocated = trans->paths_allocated; trans->paths_allocated = NULL; trans->paths = NULL; @@ -3278,8 +3280,6 @@ void bch2_trans_put(struct btree_trans *trans) trans = this_cpu_xchg(c->btree_trans_bufs->trans, trans); if (trans) { - closure_sync(&trans->ref); - seqmutex_lock(&c->btree_trans_lock); list_del(&trans->list); seqmutex_unlock(&c->btree_trans_lock); @@ -3406,8 +3406,10 @@ void bch2_fs_btree_iter_exit(struct bch_fs *c) bch2_time_stats_exit(&s->lock_hold_times); } - if (c->btree_trans_barrier_initialized) + if (c->btree_trans_barrier_initialized) { + synchronize_srcu_expedited(&c->btree_trans_barrier); cleanup_srcu_struct(&c->btree_trans_barrier); + } mempool_exit(&c->btree_trans_mem_pool); mempool_exit(&c->btree_trans_pool); } diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c index 34056aaece00..2d3c0d45c37f 100644 --- a/fs/bcachefs/btree_key_cache.c +++ b/fs/bcachefs/btree_key_cache.c @@ -32,10 +32,11 @@ static int bch2_btree_key_cache_cmp_fn(struct rhashtable_compare_arg *arg, } static const struct rhashtable_params bch2_btree_key_cache_params = { - .head_offset = offsetof(struct bkey_cached, hash), - .key_offset = offsetof(struct bkey_cached, key), - .key_len = sizeof(struct bkey_cached_key), - .obj_cmpfn = bch2_btree_key_cache_cmp_fn, + .head_offset = offsetof(struct bkey_cached, hash), + .key_offset = offsetof(struct bkey_cached, key), + .key_len = sizeof(struct bkey_cached_key), + .obj_cmpfn = bch2_btree_key_cache_cmp_fn, + .automatic_shrinking = true, }; __flatten @@ -840,7 +841,6 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, six_lock_exit(&ck->c.lock); kmem_cache_free(bch2_key_cache, ck); atomic_long_dec(&bc->nr_freed); - freed++; bc->nr_freed_nonpcpu--; bc->freed++; } @@ -854,7 +854,6 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, six_lock_exit(&ck->c.lock); kmem_cache_free(bch2_key_cache, ck); atomic_long_dec(&bc->nr_freed); - freed++; bc->nr_freed_pcpu--; bc->freed++; } @@ -876,23 +875,22 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) { bc->skipped_dirty++; - goto next; } else if (test_bit(BKEY_CACHED_ACCESSED, &ck->flags)) { clear_bit(BKEY_CACHED_ACCESSED, &ck->flags); bc->skipped_accessed++; - goto next; - } else if (bkey_cached_lock_for_evict(ck)) { + } else if (!bkey_cached_lock_for_evict(ck)) { + bc->skipped_lock_fail++; + } else { bkey_cached_evict(bc, ck); bkey_cached_free(bc, ck); bc->moved_to_freelist++; - } else { - bc->skipped_lock_fail++; + freed++; } scanned++; if (scanned >= nr) break; -next: + pos = next; } @@ -917,6 +915,14 @@ static unsigned long bch2_btree_key_cache_count(struct shrinker *shrink, long nr = atomic_long_read(&bc->nr_keys) - atomic_long_read(&bc->nr_dirty); + /* + * Avoid hammering our shrinker too much if it's nearly empty - the + * shrinker code doesn't take into account how big our cache is, if it's + * mostly empty but the system is under memory pressure it causes nasty + * lock contention: + */ + nr -= 128; + return max(0L, nr); } @@ -1025,9 +1031,10 @@ int bch2_fs_btree_key_cache_init(struct btree_key_cache *bc) if (!shrink) return -BCH_ERR_ENOMEM_fs_btree_cache_init; bc->shrink = shrink; - shrink->seeks = 0; shrink->count_objects = bch2_btree_key_cache_count; shrink->scan_objects = bch2_btree_key_cache_scan; + shrink->batch = 1 << 14; + shrink->seeks = 0; shrink->private_data = c; shrinker_register(shrink); return 0; diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c index 45cb8149d374..2cb0442f6cc9 100644 --- a/fs/bcachefs/btree_node_scan.c +++ b/fs/bcachefs/btree_node_scan.c @@ -72,10 +72,11 @@ static bool found_btree_node_is_readable(struct btree_trans *trans, struct btree *b = bch2_btree_node_get_noiter(trans, &k.k, f->btree_id, f->level, false); bool ret = !IS_ERR_OR_NULL(b); - if (ret) { - f->sectors_written = b->written; - six_unlock_read(&b->c.lock); - } + if (!ret) + return ret; + + f->sectors_written = b->written; + six_unlock_read(&b->c.lock); /* * We might update this node's range; if that happens, we need the node diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h index d63db4fefe73..87f485e9c552 100644 --- a/fs/bcachefs/btree_types.h +++ b/fs/bcachefs/btree_types.h @@ -761,13 +761,13 @@ static inline bool btree_node_type_needs_gc(enum btree_node_type type) static inline bool btree_node_type_is_extents(enum btree_node_type type) { - const unsigned mask = 0 + const u64 mask = 0 #define x(name, nr, flags, ...) |((!!((flags) & BTREE_ID_EXTENTS)) << (nr + 1)) BCH_BTREE_IDS() #undef x ; - return (1U << type) & mask; + return BIT_ULL(type) & mask; } static inline bool btree_id_is_extents(enum btree_id btree) @@ -777,35 +777,35 @@ static inline bool btree_id_is_extents(enum btree_id btree) static inline bool btree_type_has_snapshots(enum btree_id id) { - const unsigned mask = 0 + const u64 mask = 0 #define x(name, nr, flags, ...) |((!!((flags) & BTREE_ID_SNAPSHOTS)) << nr) BCH_BTREE_IDS() #undef x ; - return (1U << id) & mask; + return BIT_ULL(id) & mask; } static inline bool btree_type_has_snapshot_field(enum btree_id id) { - const unsigned mask = 0 + const u64 mask = 0 #define x(name, nr, flags, ...) |((!!((flags) & (BTREE_ID_SNAPSHOT_FIELD|BTREE_ID_SNAPSHOTS))) << nr) BCH_BTREE_IDS() #undef x ; - return (1U << id) & mask; + return BIT_ULL(id) & mask; } static inline bool btree_type_has_ptrs(enum btree_id id) { - const unsigned mask = 0 + const u64 mask = 0 #define x(name, nr, flags, ...) |((!!((flags) & BTREE_ID_DATA)) << nr) BCH_BTREE_IDS() #undef x ; - return (1U << id) & mask; + return BIT_ULL(id) & mask; } struct btree_root { diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c index ed97712d0db1..743d57eba760 100644 --- a/fs/bcachefs/buckets.c +++ b/fs/bcachefs/buckets.c @@ -465,143 +465,172 @@ int bch2_update_cached_sectors_list(struct btree_trans *trans, unsigned dev, s64 return bch2_update_replicas_list(trans, &r.e, sectors); } -int bch2_check_fix_ptrs(struct btree_trans *trans, - enum btree_id btree, unsigned level, struct bkey_s_c k, - enum btree_iter_update_trigger_flags flags) +static int bch2_check_fix_ptr(struct btree_trans *trans, + struct bkey_s_c k, + struct extent_ptr_decoded p, + const union bch_extent_entry *entry, + bool *do_update) { struct bch_fs *c = trans->c; - struct bkey_ptrs_c ptrs_c = bch2_bkey_ptrs_c(k); - const union bch_extent_entry *entry_c; - struct extent_ptr_decoded p = { 0 }; - bool do_update = false; struct printbuf buf = PRINTBUF; int ret = 0; - percpu_down_read(&c->mark_lock); + struct bch_dev *ca = bch2_dev_tryget(c, p.ptr.dev); + if (!ca) { + if (fsck_err(c, ptr_to_invalid_device, + "pointer to missing device %u\n" + "while marking %s", + p.ptr.dev, + (printbuf_reset(&buf), + bch2_bkey_val_to_text(&buf, c, k), buf.buf))) + *do_update = true; + return 0; + } - bkey_for_each_ptr_decode(k.k, ptrs_c, p, entry_c) { - struct bch_dev *ca = bch2_dev_tryget(c, p.ptr.dev); - if (!ca) { - if (fsck_err(c, ptr_to_invalid_device, - "pointer to missing device %u\n" - "while marking %s", - p.ptr.dev, - (printbuf_reset(&buf), - bch2_bkey_val_to_text(&buf, c, k), buf.buf))) - do_update = true; - continue; - } + struct bucket *g = PTR_GC_BUCKET(ca, &p.ptr); + if (!g) { + if (fsck_err(c, ptr_to_invalid_device, + "pointer to invalid bucket on device %u\n" + "while marking %s", + p.ptr.dev, + (printbuf_reset(&buf), + bch2_bkey_val_to_text(&buf, c, k), buf.buf))) + *do_update = true; + goto out; + } - struct bucket *g = PTR_GC_BUCKET(ca, &p.ptr); - enum bch_data_type data_type = bch2_bkey_ptr_data_type(k, p, entry_c); + enum bch_data_type data_type = bch2_bkey_ptr_data_type(k, p, entry); - if (fsck_err_on(!g->gen_valid, - c, ptr_to_missing_alloc_key, - "bucket %u:%zu data type %s ptr gen %u missing in alloc btree\n" - "while marking %s", - p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr), - bch2_data_type_str(ptr_data_type(k.k, &p.ptr)), - p.ptr.gen, - (printbuf_reset(&buf), - bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { - if (!p.ptr.cached) { - g->gen_valid = true; - g->gen = p.ptr.gen; - } else { - do_update = true; - } + if (fsck_err_on(!g->gen_valid, + c, ptr_to_missing_alloc_key, + "bucket %u:%zu data type %s ptr gen %u missing in alloc btree\n" + "while marking %s", + p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr), + bch2_data_type_str(ptr_data_type(k.k, &p.ptr)), + p.ptr.gen, + (printbuf_reset(&buf), + bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { + if (!p.ptr.cached) { + g->gen_valid = true; + g->gen = p.ptr.gen; + } else { + *do_update = true; } + } - if (fsck_err_on(gen_cmp(p.ptr.gen, g->gen) > 0, - c, ptr_gen_newer_than_bucket_gen, - "bucket %u:%zu data type %s ptr gen in the future: %u > %u\n" - "while marking %s", - p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr), - bch2_data_type_str(ptr_data_type(k.k, &p.ptr)), - p.ptr.gen, g->gen, - (printbuf_reset(&buf), - bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { - if (!p.ptr.cached && - (g->data_type != BCH_DATA_btree || - data_type == BCH_DATA_btree)) { - g->gen_valid = true; - g->gen = p.ptr.gen; - g->data_type = 0; - g->dirty_sectors = 0; - g->cached_sectors = 0; - } else { - do_update = true; - } + if (fsck_err_on(gen_cmp(p.ptr.gen, g->gen) > 0, + c, ptr_gen_newer_than_bucket_gen, + "bucket %u:%zu data type %s ptr gen in the future: %u > %u\n" + "while marking %s", + p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr), + bch2_data_type_str(ptr_data_type(k.k, &p.ptr)), + p.ptr.gen, g->gen, + (printbuf_reset(&buf), + bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { + if (!p.ptr.cached && + (g->data_type != BCH_DATA_btree || + data_type == BCH_DATA_btree)) { + g->gen_valid = true; + g->gen = p.ptr.gen; + g->data_type = 0; + g->dirty_sectors = 0; + g->cached_sectors = 0; + } else { + *do_update = true; + } + } + + if (fsck_err_on(gen_cmp(g->gen, p.ptr.gen) > BUCKET_GC_GEN_MAX, + c, ptr_gen_newer_than_bucket_gen, + "bucket %u:%zu gen %u data type %s: ptr gen %u too stale\n" + "while marking %s", + p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr), g->gen, + bch2_data_type_str(ptr_data_type(k.k, &p.ptr)), + p.ptr.gen, + (printbuf_reset(&buf), + bch2_bkey_val_to_text(&buf, c, k), buf.buf))) + *do_update = true; + + if (fsck_err_on(!p.ptr.cached && gen_cmp(p.ptr.gen, g->gen) < 0, + c, stale_dirty_ptr, + "bucket %u:%zu data type %s stale dirty ptr: %u < %u\n" + "while marking %s", + p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr), + bch2_data_type_str(ptr_data_type(k.k, &p.ptr)), + p.ptr.gen, g->gen, + (printbuf_reset(&buf), + bch2_bkey_val_to_text(&buf, c, k), buf.buf))) + *do_update = true; + + if (data_type != BCH_DATA_btree && p.ptr.gen != g->gen) + goto out; + + if (fsck_err_on(bucket_data_type_mismatch(g->data_type, data_type), + c, ptr_bucket_data_type_mismatch, + "bucket %u:%zu gen %u different types of data in same bucket: %s, %s\n" + "while marking %s", + p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr), g->gen, + bch2_data_type_str(g->data_type), + bch2_data_type_str(data_type), + (printbuf_reset(&buf), + bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { + if (data_type == BCH_DATA_btree) { + g->gen_valid = true; + g->gen = p.ptr.gen; + g->data_type = data_type; + g->dirty_sectors = 0; + g->cached_sectors = 0; + } else { + *do_update = true; } + } + + if (p.has_ec) { + struct gc_stripe *m = genradix_ptr(&c->gc_stripes, p.ec.idx); - if (fsck_err_on(gen_cmp(g->gen, p.ptr.gen) > BUCKET_GC_GEN_MAX, - c, ptr_gen_newer_than_bucket_gen, - "bucket %u:%zu gen %u data type %s: ptr gen %u too stale\n" + if (fsck_err_on(!m || !m->alive, + c, ptr_to_missing_stripe, + "pointer to nonexistent stripe %llu\n" "while marking %s", - p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr), g->gen, - bch2_data_type_str(ptr_data_type(k.k, &p.ptr)), - p.ptr.gen, + (u64) p.ec.idx, (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf))) - do_update = true; + *do_update = true; - if (fsck_err_on(!p.ptr.cached && gen_cmp(p.ptr.gen, g->gen) < 0, - c, stale_dirty_ptr, - "bucket %u:%zu data type %s stale dirty ptr: %u < %u\n" + if (fsck_err_on(m && m->alive && !bch2_ptr_matches_stripe_m(m, p), + c, ptr_to_incorrect_stripe, + "pointer does not match stripe %llu\n" "while marking %s", - p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr), - bch2_data_type_str(ptr_data_type(k.k, &p.ptr)), - p.ptr.gen, g->gen, + (u64) p.ec.idx, (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf))) - do_update = true; + *do_update = true; + } +out: +fsck_err: + bch2_dev_put(ca); + printbuf_exit(&buf); + return ret; +} - if (data_type != BCH_DATA_btree && p.ptr.gen != g->gen) - goto next; +int bch2_check_fix_ptrs(struct btree_trans *trans, + enum btree_id btree, unsigned level, struct bkey_s_c k, + enum btree_iter_update_trigger_flags flags) +{ + struct bch_fs *c = trans->c; + struct bkey_ptrs_c ptrs_c = bch2_bkey_ptrs_c(k); + const union bch_extent_entry *entry_c; + struct extent_ptr_decoded p = { 0 }; + bool do_update = false; + struct printbuf buf = PRINTBUF; + int ret = 0; - if (fsck_err_on(bucket_data_type_mismatch(g->data_type, data_type), - c, ptr_bucket_data_type_mismatch, - "bucket %u:%zu gen %u different types of data in same bucket: %s, %s\n" - "while marking %s", - p.ptr.dev, PTR_BUCKET_NR(ca, &p.ptr), g->gen, - bch2_data_type_str(g->data_type), - bch2_data_type_str(data_type), - (printbuf_reset(&buf), - bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { - if (data_type == BCH_DATA_btree) { - g->gen_valid = true; - g->gen = p.ptr.gen; - g->data_type = data_type; - g->dirty_sectors = 0; - g->cached_sectors = 0; - } else { - do_update = true; - } - } + percpu_down_read(&c->mark_lock); - if (p.has_ec) { - struct gc_stripe *m = genradix_ptr(&c->gc_stripes, p.ec.idx); - - if (fsck_err_on(!m || !m->alive, c, - ptr_to_missing_stripe, - "pointer to nonexistent stripe %llu\n" - "while marking %s", - (u64) p.ec.idx, - (printbuf_reset(&buf), - bch2_bkey_val_to_text(&buf, c, k), buf.buf))) - do_update = true; - - if (fsck_err_on(m && m->alive && !bch2_ptr_matches_stripe_m(m, p), c, - ptr_to_incorrect_stripe, - "pointer does not match stripe %llu\n" - "while marking %s", - (u64) p.ec.idx, - (printbuf_reset(&buf), - bch2_bkey_val_to_text(&buf, c, k), buf.buf))) - do_update = true; - } -next: - bch2_dev_put(ca); + bkey_for_each_ptr_decode(k.k, ptrs_c, p, entry_c) { + ret = bch2_check_fix_ptr(trans, k, p, entry_c, &do_update); + if (ret) + goto err; } if (do_update) { @@ -716,7 +745,6 @@ found: bch2_btree_node_update_key_early(trans, btree, level - 1, k, new); } err: -fsck_err: percpu_up_read(&c->mark_lock); printbuf_exit(&buf); return ret; @@ -987,6 +1015,7 @@ static int bch2_trigger_pointer(struct btree_trans *trans, enum btree_iter_update_trigger_flags flags) { bool insert = !(flags & BTREE_TRIGGER_overwrite); + struct printbuf buf = PRINTBUF; int ret = 0; struct bch_fs *c = trans->c; @@ -1019,6 +1048,13 @@ static int bch2_trigger_pointer(struct btree_trans *trans, if (flags & BTREE_TRIGGER_gc) { percpu_down_read(&c->mark_lock); struct bucket *g = gc_bucket(ca, bucket.offset); + if (bch2_fs_inconsistent_on(!g, c, "reference to invalid bucket on device %u\n %s", + p.ptr.dev, + (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { + ret = -EIO; + goto err_unlock; + } + bucket_lock(g); struct bch_alloc_v4 old = bucket_m_to_alloc(*g), new = old; ret = __mark_pointer(trans, ca, k, &p.ptr, *sectors, bp.data_type, &new); @@ -1027,10 +1063,12 @@ static int bch2_trigger_pointer(struct btree_trans *trans, bch2_dev_usage_update(c, ca, &old, &new, 0, true); } bucket_unlock(g); +err_unlock: percpu_up_read(&c->mark_lock); } err: bch2_dev_put(ca); + printbuf_exit(&buf); return ret; } @@ -1318,10 +1356,11 @@ static int bch2_mark_metadata_bucket(struct bch_fs *c, struct bch_dev *ca, u64 b, enum bch_data_type data_type, unsigned sectors, enum btree_iter_update_trigger_flags flags) { - int ret = 0; - percpu_down_read(&c->mark_lock); struct bucket *g = gc_bucket(ca, b); + if (bch2_fs_inconsistent_on(!g, c, "reference to invalid bucket on device %u when marking metadata type %s", + ca->dev_idx, bch2_data_type_str(data_type))) + goto err_unlock; bucket_lock(g); struct bch_alloc_v4 old = bucket_m_to_alloc(*g); @@ -1330,29 +1369,27 @@ static int bch2_mark_metadata_bucket(struct bch_fs *c, struct bch_dev *ca, g->data_type != data_type, c, "different types of data in same bucket: %s, %s", bch2_data_type_str(g->data_type), - bch2_data_type_str(data_type))) { - ret = -EIO; + bch2_data_type_str(data_type))) goto err; - } if (bch2_fs_inconsistent_on((u64) g->dirty_sectors + sectors > ca->mi.bucket_size, c, "bucket %u:%llu gen %u data type %s sector count overflow: %u + %u > bucket size", ca->dev_idx, b, g->gen, bch2_data_type_str(g->data_type ?: data_type), - g->dirty_sectors, sectors)) { - ret = -EIO; + g->dirty_sectors, sectors)) goto err; - } g->data_type = data_type; g->dirty_sectors += sectors; struct bch_alloc_v4 new = bucket_m_to_alloc(*g); + bch2_dev_usage_update(c, ca, &old, &new, 0, true); + percpu_up_read(&c->mark_lock); + return 0; err: bucket_unlock(g); - if (!ret) - bch2_dev_usage_update(c, ca, &old, &new, 0, true); +err_unlock: percpu_up_read(&c->mark_lock); - return ret; + return -EIO; } int bch2_trans_mark_metadata_bucket(struct btree_trans *trans, @@ -1595,6 +1632,8 @@ int bch2_dev_buckets_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets) bucket_gens->first_bucket = ca->mi.first_bucket; bucket_gens->nbuckets = nbuckets; + bucket_gens->nbuckets_minus_first = + bucket_gens->nbuckets - bucket_gens->first_bucket; if (resize) { down_write(&c->gc_lock); diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h index 617ffde2fb7a..80ee0be9793e 100644 --- a/fs/bcachefs/buckets.h +++ b/fs/bcachefs/buckets.h @@ -93,7 +93,8 @@ static inline struct bucket *gc_bucket(struct bch_dev *ca, size_t b) { struct bucket_array *buckets = gc_bucket_array(ca); - BUG_ON(!bucket_valid(ca, b)); + if (b - buckets->first_bucket >= buckets->nbuckets_minus_first) + return NULL; return buckets->b + b; } @@ -110,7 +111,8 @@ static inline u8 *bucket_gen(struct bch_dev *ca, size_t b) { struct bucket_gens *gens = bucket_gens(ca); - BUG_ON(!bucket_valid(ca, b)); + if (b - gens->first_bucket >= gens->nbuckets_minus_first) + return NULL; return gens->b + b; } @@ -170,19 +172,22 @@ static inline int gen_after(u8 a, u8 b) return r > 0 ? r : 0; } -static inline u8 dev_ptr_stale_rcu(struct bch_dev *ca, const struct bch_extent_ptr *ptr) +static inline int dev_ptr_stale_rcu(struct bch_dev *ca, const struct bch_extent_ptr *ptr) { - return gen_after(*bucket_gen(ca, PTR_BUCKET_NR(ca, ptr)), ptr->gen); + u8 *gen = bucket_gen(ca, PTR_BUCKET_NR(ca, ptr)); + if (!gen) + return -1; + return gen_after(*gen, ptr->gen); } /** * dev_ptr_stale() - check if a pointer points into a bucket that has been * invalidated. */ -static inline u8 dev_ptr_stale(struct bch_dev *ca, const struct bch_extent_ptr *ptr) +static inline int dev_ptr_stale(struct bch_dev *ca, const struct bch_extent_ptr *ptr) { rcu_read_lock(); - u8 ret = dev_ptr_stale_rcu(ca, ptr); + int ret = dev_ptr_stale_rcu(ca, ptr); rcu_read_unlock(); return ret; diff --git a/fs/bcachefs/buckets_types.h b/fs/bcachefs/buckets_types.h index 6a31740222a7..f636e17c4caf 100644 --- a/fs/bcachefs/buckets_types.h +++ b/fs/bcachefs/buckets_types.h @@ -22,6 +22,7 @@ struct bucket_array { struct rcu_head rcu; u16 first_bucket; size_t nbuckets; + size_t nbuckets_minus_first; struct bucket b[]; }; @@ -29,6 +30,7 @@ struct bucket_gens { struct rcu_head rcu; u16 first_bucket; size_t nbuckets; + size_t nbuckets_minus_first; u8 b[]; }; diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c index 0d807c2ce9c6..1a0072eef109 100644 --- a/fs/bcachefs/data_update.c +++ b/fs/bcachefs/data_update.c @@ -202,9 +202,8 @@ restart_drop_conflicting_replicas: bch2_bkey_durability(c, bkey_i_to_s_c(&new->k_i)); /* Now, drop excess replicas: */ -restart_drop_extra_replicas: - rcu_read_lock(); +restart_drop_extra_replicas: bkey_for_each_ptr_decode(old.k, bch2_bkey_ptrs(bkey_i_to_s(insert)), p, entry) { unsigned ptr_durability = bch2_extent_ptr_durability(c, &p); diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c index d8b9beca3776..83e279d41829 100644 --- a/fs/bcachefs/ec.c +++ b/fs/bcachefs/ec.c @@ -268,6 +268,7 @@ static int mark_stripe_bucket(struct btree_trans *trans, { struct bch_fs *c = trans->c; const struct bch_extent_ptr *ptr = s.v->ptrs + ptr_idx; + struct printbuf buf = PRINTBUF; int ret = 0; struct bch_dev *ca = bch2_dev_tryget(c, ptr->dev); @@ -289,6 +290,13 @@ static int mark_stripe_bucket(struct btree_trans *trans, if (flags & BTREE_TRIGGER_gc) { percpu_down_read(&c->mark_lock); struct bucket *g = gc_bucket(ca, bucket.offset); + if (bch2_fs_inconsistent_on(!g, c, "reference to invalid bucket on device %u\n %s", + ptr->dev, + (bch2_bkey_val_to_text(&buf, c, s.s_c), buf.buf))) { + ret = -EIO; + goto err_unlock; + } + bucket_lock(g); struct bch_alloc_v4 old = bucket_m_to_alloc(*g), new = old; ret = __mark_stripe_bucket(trans, ca, s, ptr_idx, deleting, bucket, &new, flags); @@ -297,10 +305,12 @@ static int mark_stripe_bucket(struct btree_trans *trans, bch2_dev_usage_update(c, ca, &old, &new, 0, true); } bucket_unlock(g); +err_unlock: percpu_up_read(&c->mark_lock); } err: bch2_dev_put(ca); + printbuf_exit(&buf); return ret; } @@ -714,10 +724,12 @@ static void ec_block_endio(struct bio *bio) bch2_blk_status_to_str(bio->bi_status))) clear_bit(ec_bio->idx, ec_bio->buf->valid); - if (dev_ptr_stale(ca, ptr)) { + int stale = dev_ptr_stale(ca, ptr); + if (stale) { bch_err_ratelimited(ca->fs, - "error %s stripe: stale pointer after io", - bio_data_dir(bio) == READ ? "reading from" : "writing to"); + "error %s stripe: stale/invalid pointer (%i) after io", + bio_data_dir(bio) == READ ? "reading from" : "writing to", + stale); clear_bit(ec_bio->idx, ec_bio->buf->valid); } @@ -743,10 +755,12 @@ static void ec_block_io(struct bch_fs *c, struct ec_stripe_buf *buf, return; } - if (dev_ptr_stale(ca, ptr)) { + int stale = dev_ptr_stale(ca, ptr); + if (stale) { bch_err_ratelimited(c, - "error %s stripe: stale pointer", - rw == READ ? "reading from" : "writing to"); + "error %s stripe: stale pointer (%i)", + rw == READ ? "reading from" : "writing to", + stale); clear_bit(idx, buf->valid); return; } diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h index dbe35b80bc0b..58612abf7927 100644 --- a/fs/bcachefs/errcode.h +++ b/fs/bcachefs/errcode.h @@ -116,6 +116,9 @@ x(ENOENT, ENOENT_dev_idx_not_found) \ x(ENOTEMPTY, ENOTEMPTY_dir_not_empty) \ x(ENOTEMPTY, ENOTEMPTY_subvol_not_empty) \ + x(EEXIST, EEXIST_str_hash_set) \ + x(EEXIST, EEXIST_discard_in_flight_add) \ + x(EEXIST, EEXIST_subvolume_create) \ x(0, open_buckets_empty) \ x(0, freelist_empty) \ x(BCH_ERR_freelist_empty, no_buckets_found) \ diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c index c66eeffcd7f2..d95c40f1b6af 100644 --- a/fs/bcachefs/error.c +++ b/fs/bcachefs/error.c @@ -15,6 +15,7 @@ bool bch2_inconsistent_error(struct bch_fs *c) switch (c->opts.errors) { case BCH_ON_ERROR_continue: return false; + case BCH_ON_ERROR_fix_safe: case BCH_ON_ERROR_ro: if (bch2_fs_emergency_read_only(c)) bch_err(c, "inconsistency detected - emergency read only at journal seq %llu", @@ -191,6 +192,12 @@ static void prt_actioning(struct printbuf *out, const char *action) prt_str(out, "ing"); } +static const u8 fsck_flags_extra[] = { +#define x(t, n, flags) [BCH_FSCK_ERR_##t] = flags, + BCH_SB_ERRS() +#undef x +}; + int bch2_fsck_err(struct bch_fs *c, enum bch_fsck_flags flags, enum bch_sb_error_id err, @@ -203,6 +210,9 @@ int bch2_fsck_err(struct bch_fs *c, int ret = -BCH_ERR_fsck_ignore; const char *action_orig = "fix?", *action = action_orig; + if (!WARN_ON(err >= ARRAY_SIZE(fsck_flags_extra))) + flags |= fsck_flags_extra[err]; + if ((flags & FSCK_CAN_FIX) && test_bit(err, c->sb.errors_silent)) return -BCH_ERR_fsck_fix; @@ -265,7 +275,14 @@ int bch2_fsck_err(struct bch_fs *c, prt_printf(out, bch2_log_msg(c, "")); #endif - if (!test_bit(BCH_FS_fsck_running, &c->flags)) { + if ((flags & FSCK_CAN_FIX) && + (flags & FSCK_AUTOFIX) && + (c->opts.errors == BCH_ON_ERROR_continue || + c->opts.errors == BCH_ON_ERROR_fix_safe)) { + prt_str(out, ", "); + prt_actioning(out, action); + ret = -BCH_ERR_fsck_fix; + } else if (!test_bit(BCH_FS_fsck_running, &c->flags)) { if (c->opts.errors != BCH_ON_ERROR_continue || !(flags & (FSCK_CAN_FIX|FSCK_CAN_IGNORE))) { prt_str(out, ", shutting down"); diff --git a/fs/bcachefs/error.h b/fs/bcachefs/error.h index 36caedf72d89..777711504c35 100644 --- a/fs/bcachefs/error.h +++ b/fs/bcachefs/error.h @@ -108,13 +108,6 @@ struct fsck_err_state { char *last_msg; }; -enum bch_fsck_flags { - FSCK_CAN_FIX = 1 << 0, - FSCK_CAN_IGNORE = 1 << 1, - FSCK_NEED_FSCK = 1 << 2, - FSCK_NO_RATELIMIT = 1 << 3, -}; - #define fsck_err_count(_c, _err) bch2_sb_err_count(_c, BCH_FSCK_ERR_##_err) __printf(4, 5) __cold diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c index 469037929685..410b8bd81b5a 100644 --- a/fs/bcachefs/extents.c +++ b/fs/bcachefs/extents.c @@ -137,7 +137,7 @@ int bch2_bkey_pick_read_device(struct bch_fs *c, struct bkey_s_c k, struct bch_dev *ca = bch2_dev_rcu(c, p.ptr.dev); - if (p.ptr.cached && (!ca || dev_ptr_stale(ca, &p.ptr))) + if (p.ptr.cached && (!ca || dev_ptr_stale_rcu(ca, &p.ptr))) continue; f = failed ? dev_io_failures(failed, p.ptr.dev) : NULL; @@ -999,7 +999,7 @@ bool bch2_extent_normalize(struct bch_fs *c, struct bkey_s k) bch2_bkey_drop_ptrs(k, ptr, ptr->cached && (ca = bch2_dev_rcu(c, ptr->dev)) && - dev_ptr_stale_rcu(ca, ptr)); + dev_ptr_stale_rcu(ca, ptr) > 0); rcu_read_unlock(); return bkey_deleted(k.k); @@ -1024,8 +1024,11 @@ void bch2_extent_ptr_to_text(struct printbuf *out, struct bch_fs *c, const struc prt_str(out, " cached"); if (ptr->unwritten) prt_str(out, " unwritten"); - if (bucket_valid(ca, b) && dev_ptr_stale_rcu(ca, ptr)) + int stale = dev_ptr_stale_rcu(ca, ptr); + if (stale > 0) prt_printf(out, " stale"); + else if (stale) + prt_printf(out, " invalid"); } rcu_read_unlock(); --out->atomic; diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c index 205a323ffc6d..79a0c8732bce 100644 --- a/fs/bcachefs/fs-ioctl.c +++ b/fs/bcachefs/fs-ioctl.c @@ -308,8 +308,8 @@ static int bch2_ioc_goingdown(struct bch_fs *c, u32 __user *arg) return ret; } -static long __bch2_ioctl_subvolume_create(struct bch_fs *c, struct file *filp, - struct bch_ioctl_subvolume arg) +static long bch2_ioctl_subvolume_create(struct bch_fs *c, struct file *filp, + struct bch_ioctl_subvolume arg) { struct inode *dir; struct bch_inode_info *inode; @@ -373,7 +373,7 @@ retry: } if (dst_dentry->d_inode) { - error = -EEXIST; + error = -BCH_ERR_EEXIST_subvolume_create; goto err3; } @@ -406,9 +406,12 @@ retry: !arg.src_ptr) snapshot_src.subvol = inode_inum(to_bch_ei(dir)).subvol; + down_write(&c->snapshot_create_lock); inode = __bch2_create(file_mnt_idmap(filp), to_bch_ei(dir), dst_dentry, arg.mode|S_IFDIR, 0, snapshot_src, create_flags); + up_write(&c->snapshot_create_lock); + error = PTR_ERR_OR_ZERO(inode); if (error) goto err3; @@ -429,16 +432,6 @@ err1: return error; } -static long bch2_ioctl_subvolume_create(struct bch_fs *c, struct file *filp, - struct bch_ioctl_subvolume arg) -{ - down_write(&c->snapshot_create_lock); - long ret = __bch2_ioctl_subvolume_create(c, filp, arg); - up_write(&c->snapshot_create_lock); - - return ret; -} - static long bch2_ioctl_subvolume_destroy(struct bch_fs *c, struct file *filp, struct bch_ioctl_subvolume arg) { diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index cd388f1702dc..f9c9a95d7d4c 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -188,6 +188,12 @@ static struct bch_inode_info *bch2_inode_insert(struct bch_fs *c, struct bch_ino BUG_ON(!old); if (unlikely(old != inode)) { + /* + * bcachefs doesn't use I_NEW; we have no use for it since we + * only insert fully created inodes in the inode hash table. But + * discard_new_inode() expects it to be set... + */ + inode->v.i_flags |= I_NEW; discard_new_inode(&inode->v); inode = old; } else { @@ -195,8 +201,10 @@ static struct bch_inode_info *bch2_inode_insert(struct bch_fs *c, struct bch_ino list_add(&inode->ei_vfs_inode_list, &c->vfs_inodes_list); mutex_unlock(&c->vfs_inodes_lock); /* - * we really don't want insert_inode_locked2() to be setting - * I_NEW... + * Again, I_NEW makes no sense for bcachefs. This is only needed + * for clearing I_NEW, but since the inode was already fully + * created and initialized we didn't actually want + * inode_insert5() to set it for us. */ unlock_new_inode(&inode->v); } @@ -227,7 +235,9 @@ static struct bch_inode_info *__bch2_new_inode(struct bch_fs *c) mutex_init(&inode->ei_update_lock); two_state_lock_init(&inode->ei_pagecache_lock); INIT_LIST_HEAD(&inode->ei_vfs_inode_list); + inode->ei_flags = 0; mutex_init(&inode->ei_quota_lock); + memset(&inode->ei_devs_need_flush, 0, sizeof(inode->ei_devs_need_flush)); inode->v.i_state = 0; if (unlikely(inode_init_always(c->vfs_sb, &inode->v))) { @@ -1155,6 +1165,7 @@ static const struct file_operations bch_file_operations = { .read_iter = bch2_read_iter, .write_iter = bch2_write_iter, .mmap = bch2_mmap, + .get_unmapped_area = thp_get_unmapped_area, .fsync = bch2_fsync, .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, @@ -1486,11 +1497,6 @@ static void bch2_vfs_inode_init(struct btree_trans *trans, subvol_inum inum, bch2_iget5_set(&inode->v, &inum); bch2_inode_update_after_write(trans, inode, bi, ~0); - if (BCH_SUBVOLUME_SNAP(subvol)) - set_bit(EI_INODE_SNAPSHOT, &inode->ei_flags); - else - clear_bit(EI_INODE_SNAPSHOT, &inode->ei_flags); - inode->v.i_blocks = bi->bi_sectors; inode->v.i_ino = bi->bi_inum; inode->v.i_rdev = bi->bi_dev; @@ -1502,6 +1508,9 @@ static void bch2_vfs_inode_init(struct btree_trans *trans, subvol_inum inum, inode->ei_qid = bch_qid(bi); inode->ei_subvol = inum.subvol; + if (BCH_SUBVOLUME_SNAP(subvol)) + set_bit(EI_INODE_SNAPSHOT, &inode->ei_flags); + inode->v.i_mapping->a_ops = &bch_address_space_operations; switch (inode->v.i_mode & S_IFMT) { @@ -1967,6 +1976,7 @@ got_sb: sb->s_time_min = div_s64(S64_MIN, c->sb.time_units_per_sec) + 1; sb->s_time_max = div_s64(S64_MAX, c->sb.time_units_per_sec); sb->s_uuid = c->sb.user_uuid; + sb->s_shrink->seeks = 0; c->vfs_sb = sb; strscpy(sb->s_id, c->name, sizeof(sb->s_id)); diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index fd277bd58ed3..921bcdb3e5e4 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -1677,6 +1677,7 @@ static int check_subdir_count(struct btree_trans *trans, struct inode_walker *w) trans_was_restarted(trans, restart_count); } +noinline_for_stack static int check_dirent_inode_dirent(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c_dirent d, @@ -1773,6 +1774,7 @@ out_noiter: return ret; } +noinline_for_stack static int check_dirent_target(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c_dirent d, @@ -1847,6 +1849,7 @@ found: return ret; } +noinline_for_stack static int check_dirent_to_subvol(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c_dirent d) { diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c index f57486794484..c97fa7002b06 100644 --- a/fs/bcachefs/io_read.c +++ b/fs/bcachefs/io_read.c @@ -84,9 +84,10 @@ struct promote_op { }; static const struct rhashtable_params bch_promote_params = { - .head_offset = offsetof(struct promote_op, hash), - .key_offset = offsetof(struct promote_op, pos), - .key_len = sizeof(struct bpos), + .head_offset = offsetof(struct promote_op, hash), + .key_offset = offsetof(struct promote_op, pos), + .key_len = sizeof(struct bpos), + .automatic_shrinking = true, }; static inline int should_promote(struct bch_fs *c, struct bkey_s_c k, @@ -776,18 +777,32 @@ static noinline void read_from_stale_dirty_pointer(struct btree_trans *trans, PTR_BUCKET_POS(ca, &ptr), BTREE_ITER_cached); - prt_printf(&buf, "Attempting to read from stale dirty pointer:\n"); - printbuf_indent_add(&buf, 2); + u8 *gen = bucket_gen(ca, iter.pos.offset); + if (gen) { - bch2_bkey_val_to_text(&buf, c, k); - prt_newline(&buf); + prt_printf(&buf, "Attempting to read from stale dirty pointer:\n"); + printbuf_indent_add(&buf, 2); - prt_printf(&buf, "memory gen: %u", *bucket_gen(ca, iter.pos.offset)); - - ret = lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_slot(&iter))); - if (!ret) { + bch2_bkey_val_to_text(&buf, c, k); prt_newline(&buf); + + prt_printf(&buf, "memory gen: %u", *gen); + + ret = lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_slot(&iter))); + if (!ret) { + prt_newline(&buf); + bch2_bkey_val_to_text(&buf, c, k); + } + } else { + prt_printf(&buf, "Attempting to read from invalid bucket %llu:%llu:\n", + iter.pos.inode, iter.pos.offset); + printbuf_indent_add(&buf, 2); + + prt_printf(&buf, "first bucket %u nbuckets %llu\n", + ca->mi.first_bucket, ca->mi.nbuckets); + bch2_bkey_val_to_text(&buf, c, k); + prt_newline(&buf); } bch2_fs_inconsistent(c, "%s", buf.buf); diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c index 9401d13e31bb..05e0cbef420b 100644 --- a/fs/bcachefs/io_write.c +++ b/fs/bcachefs/io_write.c @@ -1220,7 +1220,7 @@ static void bch2_nocow_write(struct bch_write_op *op) DARRAY_PREALLOCATED(struct bucket_to_lock, 3) buckets; u32 snapshot; struct bucket_to_lock *stale_at; - int ret; + int stale, ret; if (op->flags & BCH_WRITE_MOVE) return; @@ -1299,7 +1299,8 @@ retry: BUCKET_NOCOW_LOCK_UPDATE); rcu_read_lock(); - bool stale = gen_after(*bucket_gen(ca, i->b.offset), i->gen); + u8 *gen = bucket_gen(ca, i->b.offset); + stale = !gen ? -1 : gen_after(*gen, i->gen); rcu_read_unlock(); if (unlikely(stale)) { @@ -1380,8 +1381,18 @@ err_bucket_stale: break; } - /* We can retry this: */ - ret = -BCH_ERR_transaction_restart; + struct printbuf buf = PRINTBUF; + if (bch2_fs_inconsistent_on(stale < 0, c, + "pointer to invalid bucket in nocow path on device %llu\n %s", + stale_at->b.inode, + (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { + ret = -EIO; + } else { + /* We can retry this: */ + ret = -BCH_ERR_transaction_restart; + } + printbuf_exit(&buf); + goto err_get_ioref; } diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c index adec8e1ea73e..dac2f498ae8b 100644 --- a/fs/bcachefs/journal.c +++ b/fs/bcachefs/journal.c @@ -1167,6 +1167,9 @@ void bch2_dev_journal_stop(struct journal *j, struct bch_dev *ca) void bch2_fs_journal_stop(struct journal *j) { + if (!test_bit(JOURNAL_running, &j->flags)) + return; + bch2_journal_reclaim_stop(j); bch2_journal_flush_all_pins(j); diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c index cdcb1ad49af4..492426c8d869 100644 --- a/fs/bcachefs/journal_io.c +++ b/fs/bcachefs/journal_io.c @@ -1967,7 +1967,6 @@ CLOSURE_CALLBACK(bch2_journal_write) struct journal *j = container_of(w, struct journal, buf[w->idx]); struct bch_fs *c = container_of(j, struct bch_fs, journal); struct bch_replicas_padded replicas; - struct printbuf journal_debug_buf = PRINTBUF; unsigned nr_rw_members = 0; int ret; @@ -2011,11 +2010,15 @@ CLOSURE_CALLBACK(bch2_journal_write) } if (ret) { - __bch2_journal_debug_to_text(&journal_debug_buf, j); + struct printbuf buf = PRINTBUF; + buf.atomic++; + + prt_printf(&buf, bch2_fmt(c, "Unable to allocate journal write: %s"), + bch2_err_str(ret)); + __bch2_journal_debug_to_text(&buf, j); spin_unlock(&j->lock); - bch_err(c, "Unable to allocate journal write:\n%s", - journal_debug_buf.buf); - printbuf_exit(&journal_debug_buf); + bch2_print_string_as_lines(KERN_ERR, buf.buf); + printbuf_exit(&buf); goto err; } diff --git a/fs/bcachefs/lru.h b/fs/bcachefs/lru.h index fb11ab0dd00e..bd71ba77de07 100644 --- a/fs/bcachefs/lru.h +++ b/fs/bcachefs/lru.h @@ -2,9 +2,6 @@ #ifndef _BCACHEFS_LRU_H #define _BCACHEFS_LRU_H -#define LRU_TIME_BITS 48 -#define LRU_TIME_MAX ((1ULL << LRU_TIME_BITS) - 1) - static inline u64 lru_pos_id(struct bpos pos) { return pos.inode >> LRU_TIME_BITS; diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c index 10bfb31c151b..eb49dd045eff 100644 --- a/fs/bcachefs/movinggc.c +++ b/fs/bcachefs/movinggc.c @@ -35,9 +35,10 @@ struct buckets_in_flight { }; static const struct rhashtable_params bch_move_bucket_params = { - .head_offset = offsetof(struct move_bucket_in_flight, hash), - .key_offset = offsetof(struct move_bucket_in_flight, bucket.k), - .key_len = sizeof(struct move_bucket_key), + .head_offset = offsetof(struct move_bucket_in_flight, hash), + .key_offset = offsetof(struct move_bucket_in_flight, bucket.k), + .key_len = sizeof(struct move_bucket_key), + .automatic_shrinking = true, }; static struct move_bucket_in_flight * diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h index 25530e0bb2f3..b197ec90d4cb 100644 --- a/fs/bcachefs/opts.h +++ b/fs/bcachefs/opts.h @@ -137,7 +137,7 @@ enum fsck_err_opts { x(errors, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_STR(bch2_error_actions), \ - BCH_SB_ERROR_ACTION, BCH_ON_ERROR_ro, \ + BCH_SB_ERROR_ACTION, BCH_ON_ERROR_fix_safe, \ NULL, "Action to take on filesystem error") \ x(metadata_replicas, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index cf513fc79ce4..1f9d044ed920 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -326,6 +326,12 @@ static int journal_replay_entry_early(struct bch_fs *c, case BCH_JSET_ENTRY_btree_root: { struct btree_root *r; + if (fsck_err_on(entry->btree_id >= BTREE_ID_NR_MAX, + c, invalid_btree_id, + "invalid btree id %u (max %u)", + entry->btree_id, BTREE_ID_NR_MAX)) + return 0; + while (entry->btree_id >= c->btree_roots_extra.nr + BTREE_ID_NR) { ret = darray_push(&c->btree_roots_extra, (struct btree_root) { NULL }); if (ret) @@ -415,7 +421,7 @@ static int journal_replay_entry_early(struct bch_fs *c, atomic64_set(&c->io_clock[clock->rw].now, le64_to_cpu(clock->time)); } } - +fsck_err: return ret; } @@ -658,10 +664,10 @@ int bch2_fs_recovery(struct bch_fs *c) if (check_version_upgrade(c)) write_sb = true; + c->recovery_passes_explicit |= bch2_recovery_passes_from_stable(le64_to_cpu(ext->recovery_passes_required[0])); + if (write_sb) bch2_write_super(c); - - c->recovery_passes_explicit |= bch2_recovery_passes_from_stable(le64_to_cpu(ext->recovery_passes_required[0])); mutex_unlock(&c->sb_lock); if (c->opts.fsck && IS_ENABLED(CONFIG_BCACHEFS_DEBUG)) diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c index 3fb23e399ffb..4710b61631f0 100644 --- a/fs/bcachefs/sb-downgrade.c +++ b/fs/bcachefs/sb-downgrade.c @@ -228,7 +228,7 @@ int bch2_sb_downgrade_update(struct bch_fs *c) dst = (void *) &darray_top(table); dst->version = cpu_to_le16(src->version); - dst->recovery_passes[0] = cpu_to_le64(src->recovery_passes); + dst->recovery_passes[0] = cpu_to_le64(bch2_recovery_passes_to_stable(src->recovery_passes)); dst->recovery_passes[1] = 0; dst->nr_errors = cpu_to_le16(src->nr_errors); for (unsigned i = 0; i < src->nr_errors; i++) diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h index 84d2763bd597..d6f35a99c429 100644 --- a/fs/bcachefs/sb-errors_format.h +++ b/fs/bcachefs/sb-errors_format.h @@ -2,281 +2,294 @@ #ifndef _BCACHEFS_SB_ERRORS_FORMAT_H #define _BCACHEFS_SB_ERRORS_FORMAT_H -#define BCH_SB_ERRS() \ - x(clean_but_journal_not_empty, 0) \ - x(dirty_but_no_journal_entries, 1) \ - x(dirty_but_no_journal_entries_post_drop_nonflushes, 2) \ - x(sb_clean_journal_seq_mismatch, 3) \ - x(sb_clean_btree_root_mismatch, 4) \ - x(sb_clean_missing, 5) \ - x(jset_unsupported_version, 6) \ - x(jset_unknown_csum, 7) \ - x(jset_last_seq_newer_than_seq, 8) \ - x(jset_past_bucket_end, 9) \ - x(jset_seq_blacklisted, 10) \ - x(journal_entries_missing, 11) \ - x(journal_entry_replicas_not_marked, 12) \ - x(journal_entry_past_jset_end, 13) \ - x(journal_entry_replicas_data_mismatch, 14) \ - x(journal_entry_bkey_u64s_0, 15) \ - x(journal_entry_bkey_past_end, 16) \ - x(journal_entry_bkey_bad_format, 17) \ - x(journal_entry_bkey_invalid, 18) \ - x(journal_entry_btree_root_bad_size, 19) \ - x(journal_entry_blacklist_bad_size, 20) \ - x(journal_entry_blacklist_v2_bad_size, 21) \ - x(journal_entry_blacklist_v2_start_past_end, 22) \ - x(journal_entry_usage_bad_size, 23) \ - x(journal_entry_data_usage_bad_size, 24) \ - x(journal_entry_clock_bad_size, 25) \ - x(journal_entry_clock_bad_rw, 26) \ - x(journal_entry_dev_usage_bad_size, 27) \ - x(journal_entry_dev_usage_bad_dev, 28) \ - x(journal_entry_dev_usage_bad_pad, 29) \ - x(btree_node_unreadable, 30) \ - x(btree_node_fault_injected, 31) \ - x(btree_node_bad_magic, 32) \ - x(btree_node_bad_seq, 33) \ - x(btree_node_unsupported_version, 34) \ - x(btree_node_bset_older_than_sb_min, 35) \ - x(btree_node_bset_newer_than_sb, 36) \ - x(btree_node_data_missing, 37) \ - x(btree_node_bset_after_end, 38) \ - x(btree_node_replicas_sectors_written_mismatch, 39) \ - x(btree_node_replicas_data_mismatch, 40) \ - x(bset_unknown_csum, 41) \ - x(bset_bad_csum, 42) \ - x(bset_past_end_of_btree_node, 43) \ - x(bset_wrong_sector_offset, 44) \ - x(bset_empty, 45) \ - x(bset_bad_seq, 46) \ - x(bset_blacklisted_journal_seq, 47) \ - x(first_bset_blacklisted_journal_seq, 48) \ - x(btree_node_bad_btree, 49) \ - x(btree_node_bad_level, 50) \ - x(btree_node_bad_min_key, 51) \ - x(btree_node_bad_max_key, 52) \ - x(btree_node_bad_format, 53) \ - x(btree_node_bkey_past_bset_end, 54) \ - x(btree_node_bkey_bad_format, 55) \ - x(btree_node_bad_bkey, 56) \ - x(btree_node_bkey_out_of_order, 57) \ - x(btree_root_bkey_invalid, 58) \ - x(btree_root_read_error, 59) \ - x(btree_root_bad_min_key, 60) \ - x(btree_root_bad_max_key, 61) \ - x(btree_node_read_error, 62) \ - x(btree_node_topology_bad_min_key, 63) \ - x(btree_node_topology_bad_max_key, 64) \ - x(btree_node_topology_overwritten_by_prev_node, 65) \ - x(btree_node_topology_overwritten_by_next_node, 66) \ - x(btree_node_topology_interior_node_empty, 67) \ - x(fs_usage_hidden_wrong, 68) \ - x(fs_usage_btree_wrong, 69) \ - x(fs_usage_data_wrong, 70) \ - x(fs_usage_cached_wrong, 71) \ - x(fs_usage_reserved_wrong, 72) \ - x(fs_usage_persistent_reserved_wrong, 73) \ - x(fs_usage_nr_inodes_wrong, 74) \ - x(fs_usage_replicas_wrong, 75) \ - x(dev_usage_buckets_wrong, 76) \ - x(dev_usage_sectors_wrong, 77) \ - x(dev_usage_fragmented_wrong, 78) \ - x(dev_usage_buckets_ec_wrong, 79) \ - x(bkey_version_in_future, 80) \ - x(bkey_u64s_too_small, 81) \ - x(bkey_invalid_type_for_btree, 82) \ - x(bkey_extent_size_zero, 83) \ - x(bkey_extent_size_greater_than_offset, 84) \ - x(bkey_size_nonzero, 85) \ - x(bkey_snapshot_nonzero, 86) \ - x(bkey_snapshot_zero, 87) \ - x(bkey_at_pos_max, 88) \ - x(bkey_before_start_of_btree_node, 89) \ - x(bkey_after_end_of_btree_node, 90) \ - x(bkey_val_size_nonzero, 91) \ - x(bkey_val_size_too_small, 92) \ - x(alloc_v1_val_size_bad, 93) \ - x(alloc_v2_unpack_error, 94) \ - x(alloc_v3_unpack_error, 95) \ - x(alloc_v4_val_size_bad, 96) \ - x(alloc_v4_backpointers_start_bad, 97) \ - x(alloc_key_data_type_bad, 98) \ - x(alloc_key_empty_but_have_data, 99) \ - x(alloc_key_dirty_sectors_0, 100) \ - x(alloc_key_data_type_inconsistency, 101) \ - x(alloc_key_to_missing_dev_bucket, 102) \ - x(alloc_key_cached_inconsistency, 103) \ - x(alloc_key_cached_but_read_time_zero, 104) \ - x(alloc_key_to_missing_lru_entry, 105) \ - x(alloc_key_data_type_wrong, 106) \ - x(alloc_key_gen_wrong, 107) \ - x(alloc_key_dirty_sectors_wrong, 108) \ - x(alloc_key_cached_sectors_wrong, 109) \ - x(alloc_key_stripe_wrong, 110) \ - x(alloc_key_stripe_redundancy_wrong, 111) \ - x(bucket_sector_count_overflow, 112) \ - x(bucket_metadata_type_mismatch, 113) \ - x(need_discard_key_wrong, 114) \ - x(freespace_key_wrong, 115) \ - x(freespace_hole_missing, 116) \ - x(bucket_gens_val_size_bad, 117) \ - x(bucket_gens_key_wrong, 118) \ - x(bucket_gens_hole_wrong, 119) \ - x(bucket_gens_to_invalid_dev, 120) \ - x(bucket_gens_to_invalid_buckets, 121) \ - x(bucket_gens_nonzero_for_invalid_buckets, 122) \ - x(need_discard_freespace_key_to_invalid_dev_bucket, 123) \ - x(need_discard_freespace_key_bad, 124) \ - x(backpointer_bucket_offset_wrong, 125) \ - x(backpointer_to_missing_device, 126) \ - x(backpointer_to_missing_alloc, 127) \ - x(backpointer_to_missing_ptr, 128) \ - x(lru_entry_at_time_0, 129) \ - x(lru_entry_to_invalid_bucket, 130) \ - x(lru_entry_bad, 131) \ - x(btree_ptr_val_too_big, 132) \ - x(btree_ptr_v2_val_too_big, 133) \ - x(btree_ptr_has_non_ptr, 134) \ - x(extent_ptrs_invalid_entry, 135) \ - x(extent_ptrs_no_ptrs, 136) \ - x(extent_ptrs_too_many_ptrs, 137) \ - x(extent_ptrs_redundant_crc, 138) \ - x(extent_ptrs_redundant_stripe, 139) \ - x(extent_ptrs_unwritten, 140) \ - x(extent_ptrs_written_and_unwritten, 141) \ - x(ptr_to_invalid_device, 142) \ - x(ptr_to_duplicate_device, 143) \ - x(ptr_after_last_bucket, 144) \ - x(ptr_before_first_bucket, 145) \ - x(ptr_spans_multiple_buckets, 146) \ - x(ptr_to_missing_backpointer, 147) \ - x(ptr_to_missing_alloc_key, 148) \ - x(ptr_to_missing_replicas_entry, 149) \ - x(ptr_to_missing_stripe, 150) \ - x(ptr_to_incorrect_stripe, 151) \ - x(ptr_gen_newer_than_bucket_gen, 152) \ - x(ptr_too_stale, 153) \ - x(stale_dirty_ptr, 154) \ - x(ptr_bucket_data_type_mismatch, 155) \ - x(ptr_cached_and_erasure_coded, 156) \ - x(ptr_crc_uncompressed_size_too_small, 157) \ - x(ptr_crc_csum_type_unknown, 158) \ - x(ptr_crc_compression_type_unknown, 159) \ - x(ptr_crc_redundant, 160) \ - x(ptr_crc_uncompressed_size_too_big, 161) \ - x(ptr_crc_nonce_mismatch, 162) \ - x(ptr_stripe_redundant, 163) \ - x(reservation_key_nr_replicas_invalid, 164) \ - x(reflink_v_refcount_wrong, 165) \ - x(reflink_p_to_missing_reflink_v, 166) \ - x(stripe_pos_bad, 167) \ - x(stripe_val_size_bad, 168) \ - x(stripe_sector_count_wrong, 169) \ - x(snapshot_tree_pos_bad, 170) \ - x(snapshot_tree_to_missing_snapshot, 171) \ - x(snapshot_tree_to_missing_subvol, 172) \ - x(snapshot_tree_to_wrong_subvol, 173) \ - x(snapshot_tree_to_snapshot_subvol, 174) \ - x(snapshot_pos_bad, 175) \ - x(snapshot_parent_bad, 176) \ - x(snapshot_children_not_normalized, 177) \ - x(snapshot_child_duplicate, 178) \ - x(snapshot_child_bad, 179) \ - x(snapshot_skiplist_not_normalized, 180) \ - x(snapshot_skiplist_bad, 181) \ - x(snapshot_should_not_have_subvol, 182) \ - x(snapshot_to_bad_snapshot_tree, 183) \ - x(snapshot_bad_depth, 184) \ - x(snapshot_bad_skiplist, 185) \ - x(subvol_pos_bad, 186) \ - x(subvol_not_master_and_not_snapshot, 187) \ - x(subvol_to_missing_root, 188) \ - x(subvol_root_wrong_bi_subvol, 189) \ - x(bkey_in_missing_snapshot, 190) \ - x(inode_pos_inode_nonzero, 191) \ - x(inode_pos_blockdev_range, 192) \ - x(inode_unpack_error, 193) \ - x(inode_str_hash_invalid, 194) \ - x(inode_v3_fields_start_bad, 195) \ - x(inode_snapshot_mismatch, 196) \ - x(inode_unlinked_but_clean, 197) \ - x(inode_unlinked_but_nlink_nonzero, 198) \ - x(inode_checksum_type_invalid, 199) \ - x(inode_compression_type_invalid, 200) \ - x(inode_subvol_root_but_not_dir, 201) \ - x(inode_i_size_dirty_but_clean, 202) \ - x(inode_i_sectors_dirty_but_clean, 203) \ - x(inode_i_sectors_wrong, 204) \ - x(inode_dir_wrong_nlink, 205) \ - x(inode_dir_multiple_links, 206) \ - x(inode_multiple_links_but_nlink_0, 207) \ - x(inode_wrong_backpointer, 208) \ - x(inode_wrong_nlink, 209) \ - x(inode_unreachable, 210) \ - x(deleted_inode_but_clean, 211) \ - x(deleted_inode_missing, 212) \ - x(deleted_inode_is_dir, 213) \ - x(deleted_inode_not_unlinked, 214) \ - x(extent_overlapping, 215) \ - x(extent_in_missing_inode, 216) \ - x(extent_in_non_reg_inode, 217) \ - x(extent_past_end_of_inode, 218) \ - x(dirent_empty_name, 219) \ - x(dirent_val_too_big, 220) \ - x(dirent_name_too_long, 221) \ - x(dirent_name_embedded_nul, 222) \ - x(dirent_name_dot_or_dotdot, 223) \ - x(dirent_name_has_slash, 224) \ - x(dirent_d_type_wrong, 225) \ - x(inode_bi_parent_wrong, 226) \ - x(dirent_in_missing_dir_inode, 227) \ - x(dirent_in_non_dir_inode, 228) \ - x(dirent_to_missing_inode, 229) \ - x(dirent_to_missing_subvol, 230) \ - x(dirent_to_itself, 231) \ - x(quota_type_invalid, 232) \ - x(xattr_val_size_too_small, 233) \ - x(xattr_val_size_too_big, 234) \ - x(xattr_invalid_type, 235) \ - x(xattr_name_invalid_chars, 236) \ - x(xattr_in_missing_inode, 237) \ - x(root_subvol_missing, 238) \ - x(root_dir_missing, 239) \ - x(root_inode_not_dir, 240) \ - x(dir_loop, 241) \ - x(hash_table_key_duplicate, 242) \ - x(hash_table_key_wrong_offset, 243) \ - x(unlinked_inode_not_on_deleted_list, 244) \ - x(reflink_p_front_pad_bad, 245) \ - x(journal_entry_dup_same_device, 246) \ - x(inode_bi_subvol_missing, 247) \ - x(inode_bi_subvol_wrong, 248) \ - x(inode_points_to_missing_dirent, 249) \ - x(inode_points_to_wrong_dirent, 250) \ - x(inode_bi_parent_nonzero, 251) \ - x(dirent_to_missing_parent_subvol, 252) \ - x(dirent_not_visible_in_parent_subvol, 253) \ - x(subvol_fs_path_parent_wrong, 254) \ - x(subvol_root_fs_path_parent_nonzero, 255) \ - x(subvol_children_not_set, 256) \ - x(subvol_children_bad, 257) \ - x(subvol_loop, 258) \ - x(subvol_unreachable, 259) \ - x(btree_node_bkey_bad_u64s, 260) \ - x(btree_node_topology_empty_interior_node, 261) \ - x(btree_ptr_v2_min_key_bad, 262) \ - x(btree_root_unreadable_and_scan_found_nothing, 263) \ - x(snapshot_node_missing, 264) \ - x(dup_backpointer_to_bad_csum_extent, 265) \ - x(btree_bitmap_not_marked, 266) \ - x(sb_clean_entry_overrun, 267) \ - x(btree_ptr_v2_written_0, 268) \ - x(subvol_snapshot_bad, 269) \ - x(subvol_inode_bad, 270) +enum bch_fsck_flags { + FSCK_CAN_FIX = 1 << 0, + FSCK_CAN_IGNORE = 1 << 1, + FSCK_NEED_FSCK = 1 << 2, + FSCK_NO_RATELIMIT = 1 << 3, + FSCK_AUTOFIX = 1 << 4, +}; + +#define BCH_SB_ERRS() \ + x(clean_but_journal_not_empty, 0, 0) \ + x(dirty_but_no_journal_entries, 1, 0) \ + x(dirty_but_no_journal_entries_post_drop_nonflushes, 2, 0) \ + x(sb_clean_journal_seq_mismatch, 3, 0) \ + x(sb_clean_btree_root_mismatch, 4, 0) \ + x(sb_clean_missing, 5, 0) \ + x(jset_unsupported_version, 6, 0) \ + x(jset_unknown_csum, 7, 0) \ + x(jset_last_seq_newer_than_seq, 8, 0) \ + x(jset_past_bucket_end, 9, 0) \ + x(jset_seq_blacklisted, 10, 0) \ + x(journal_entries_missing, 11, 0) \ + x(journal_entry_replicas_not_marked, 12, 0) \ + x(journal_entry_past_jset_end, 13, 0) \ + x(journal_entry_replicas_data_mismatch, 14, 0) \ + x(journal_entry_bkey_u64s_0, 15, 0) \ + x(journal_entry_bkey_past_end, 16, 0) \ + x(journal_entry_bkey_bad_format, 17, 0) \ + x(journal_entry_bkey_invalid, 18, 0) \ + x(journal_entry_btree_root_bad_size, 19, 0) \ + x(journal_entry_blacklist_bad_size, 20, 0) \ + x(journal_entry_blacklist_v2_bad_size, 21, 0) \ + x(journal_entry_blacklist_v2_start_past_end, 22, 0) \ + x(journal_entry_usage_bad_size, 23, 0) \ + x(journal_entry_data_usage_bad_size, 24, 0) \ + x(journal_entry_clock_bad_size, 25, 0) \ + x(journal_entry_clock_bad_rw, 26, 0) \ + x(journal_entry_dev_usage_bad_size, 27, 0) \ + x(journal_entry_dev_usage_bad_dev, 28, 0) \ + x(journal_entry_dev_usage_bad_pad, 29, 0) \ + x(btree_node_unreadable, 30, 0) \ + x(btree_node_fault_injected, 31, 0) \ + x(btree_node_bad_magic, 32, 0) \ + x(btree_node_bad_seq, 33, 0) \ + x(btree_node_unsupported_version, 34, 0) \ + x(btree_node_bset_older_than_sb_min, 35, 0) \ + x(btree_node_bset_newer_than_sb, 36, 0) \ + x(btree_node_data_missing, 37, 0) \ + x(btree_node_bset_after_end, 38, 0) \ + x(btree_node_replicas_sectors_written_mismatch, 39, 0) \ + x(btree_node_replicas_data_mismatch, 40, 0) \ + x(bset_unknown_csum, 41, 0) \ + x(bset_bad_csum, 42, 0) \ + x(bset_past_end_of_btree_node, 43, 0) \ + x(bset_wrong_sector_offset, 44, 0) \ + x(bset_empty, 45, 0) \ + x(bset_bad_seq, 46, 0) \ + x(bset_blacklisted_journal_seq, 47, 0) \ + x(first_bset_blacklisted_journal_seq, 48, 0) \ + x(btree_node_bad_btree, 49, 0) \ + x(btree_node_bad_level, 50, 0) \ + x(btree_node_bad_min_key, 51, 0) \ + x(btree_node_bad_max_key, 52, 0) \ + x(btree_node_bad_format, 53, 0) \ + x(btree_node_bkey_past_bset_end, 54, 0) \ + x(btree_node_bkey_bad_format, 55, 0) \ + x(btree_node_bad_bkey, 56, 0) \ + x(btree_node_bkey_out_of_order, 57, 0) \ + x(btree_root_bkey_invalid, 58, 0) \ + x(btree_root_read_error, 59, 0) \ + x(btree_root_bad_min_key, 60, 0) \ + x(btree_root_bad_max_key, 61, 0) \ + x(btree_node_read_error, 62, 0) \ + x(btree_node_topology_bad_min_key, 63, 0) \ + x(btree_node_topology_bad_max_key, 64, 0) \ + x(btree_node_topology_overwritten_by_prev_node, 65, 0) \ + x(btree_node_topology_overwritten_by_next_node, 66, 0) \ + x(btree_node_topology_interior_node_empty, 67, 0) \ + x(fs_usage_hidden_wrong, 68, FSCK_AUTOFIX) \ + x(fs_usage_btree_wrong, 69, FSCK_AUTOFIX) \ + x(fs_usage_data_wrong, 70, FSCK_AUTOFIX) \ + x(fs_usage_cached_wrong, 71, FSCK_AUTOFIX) \ + x(fs_usage_reserved_wrong, 72, FSCK_AUTOFIX) \ + x(fs_usage_persistent_reserved_wrong, 73, FSCK_AUTOFIX) \ + x(fs_usage_nr_inodes_wrong, 74, FSCK_AUTOFIX) \ + x(fs_usage_replicas_wrong, 75, FSCK_AUTOFIX) \ + x(dev_usage_buckets_wrong, 76, FSCK_AUTOFIX) \ + x(dev_usage_sectors_wrong, 77, FSCK_AUTOFIX) \ + x(dev_usage_fragmented_wrong, 78, FSCK_AUTOFIX) \ + x(dev_usage_buckets_ec_wrong, 79, FSCK_AUTOFIX) \ + x(bkey_version_in_future, 80, 0) \ + x(bkey_u64s_too_small, 81, 0) \ + x(bkey_invalid_type_for_btree, 82, 0) \ + x(bkey_extent_size_zero, 83, 0) \ + x(bkey_extent_size_greater_than_offset, 84, 0) \ + x(bkey_size_nonzero, 85, 0) \ + x(bkey_snapshot_nonzero, 86, 0) \ + x(bkey_snapshot_zero, 87, 0) \ + x(bkey_at_pos_max, 88, 0) \ + x(bkey_before_start_of_btree_node, 89, 0) \ + x(bkey_after_end_of_btree_node, 90, 0) \ + x(bkey_val_size_nonzero, 91, 0) \ + x(bkey_val_size_too_small, 92, 0) \ + x(alloc_v1_val_size_bad, 93, 0) \ + x(alloc_v2_unpack_error, 94, 0) \ + x(alloc_v3_unpack_error, 95, 0) \ + x(alloc_v4_val_size_bad, 96, 0) \ + x(alloc_v4_backpointers_start_bad, 97, 0) \ + x(alloc_key_data_type_bad, 98, 0) \ + x(alloc_key_empty_but_have_data, 99, 0) \ + x(alloc_key_dirty_sectors_0, 100, 0) \ + x(alloc_key_data_type_inconsistency, 101, 0) \ + x(alloc_key_to_missing_dev_bucket, 102, 0) \ + x(alloc_key_cached_inconsistency, 103, 0) \ + x(alloc_key_cached_but_read_time_zero, 104, 0) \ + x(alloc_key_to_missing_lru_entry, 105, 0) \ + x(alloc_key_data_type_wrong, 106, FSCK_AUTOFIX) \ + x(alloc_key_gen_wrong, 107, FSCK_AUTOFIX) \ + x(alloc_key_dirty_sectors_wrong, 108, FSCK_AUTOFIX) \ + x(alloc_key_cached_sectors_wrong, 109, FSCK_AUTOFIX) \ + x(alloc_key_stripe_wrong, 110, FSCK_AUTOFIX) \ + x(alloc_key_stripe_redundancy_wrong, 111, FSCK_AUTOFIX) \ + x(bucket_sector_count_overflow, 112, 0) \ + x(bucket_metadata_type_mismatch, 113, 0) \ + x(need_discard_key_wrong, 114, 0) \ + x(freespace_key_wrong, 115, 0) \ + x(freespace_hole_missing, 116, 0) \ + x(bucket_gens_val_size_bad, 117, 0) \ + x(bucket_gens_key_wrong, 118, 0) \ + x(bucket_gens_hole_wrong, 119, 0) \ + x(bucket_gens_to_invalid_dev, 120, 0) \ + x(bucket_gens_to_invalid_buckets, 121, 0) \ + x(bucket_gens_nonzero_for_invalid_buckets, 122, 0) \ + x(need_discard_freespace_key_to_invalid_dev_bucket, 123, 0) \ + x(need_discard_freespace_key_bad, 124, 0) \ + x(backpointer_bucket_offset_wrong, 125, 0) \ + x(backpointer_to_missing_device, 126, 0) \ + x(backpointer_to_missing_alloc, 127, 0) \ + x(backpointer_to_missing_ptr, 128, 0) \ + x(lru_entry_at_time_0, 129, 0) \ + x(lru_entry_to_invalid_bucket, 130, 0) \ + x(lru_entry_bad, 131, 0) \ + x(btree_ptr_val_too_big, 132, 0) \ + x(btree_ptr_v2_val_too_big, 133, 0) \ + x(btree_ptr_has_non_ptr, 134, 0) \ + x(extent_ptrs_invalid_entry, 135, 0) \ + x(extent_ptrs_no_ptrs, 136, 0) \ + x(extent_ptrs_too_many_ptrs, 137, 0) \ + x(extent_ptrs_redundant_crc, 138, 0) \ + x(extent_ptrs_redundant_stripe, 139, 0) \ + x(extent_ptrs_unwritten, 140, 0) \ + x(extent_ptrs_written_and_unwritten, 141, 0) \ + x(ptr_to_invalid_device, 142, 0) \ + x(ptr_to_duplicate_device, 143, 0) \ + x(ptr_after_last_bucket, 144, 0) \ + x(ptr_before_first_bucket, 145, 0) \ + x(ptr_spans_multiple_buckets, 146, 0) \ + x(ptr_to_missing_backpointer, 147, 0) \ + x(ptr_to_missing_alloc_key, 148, 0) \ + x(ptr_to_missing_replicas_entry, 149, 0) \ + x(ptr_to_missing_stripe, 150, 0) \ + x(ptr_to_incorrect_stripe, 151, 0) \ + x(ptr_gen_newer_than_bucket_gen, 152, 0) \ + x(ptr_too_stale, 153, 0) \ + x(stale_dirty_ptr, 154, 0) \ + x(ptr_bucket_data_type_mismatch, 155, 0) \ + x(ptr_cached_and_erasure_coded, 156, 0) \ + x(ptr_crc_uncompressed_size_too_small, 157, 0) \ + x(ptr_crc_csum_type_unknown, 158, 0) \ + x(ptr_crc_compression_type_unknown, 159, 0) \ + x(ptr_crc_redundant, 160, 0) \ + x(ptr_crc_uncompressed_size_too_big, 161, 0) \ + x(ptr_crc_nonce_mismatch, 162, 0) \ + x(ptr_stripe_redundant, 163, 0) \ + x(reservation_key_nr_replicas_invalid, 164, 0) \ + x(reflink_v_refcount_wrong, 165, 0) \ + x(reflink_p_to_missing_reflink_v, 166, 0) \ + x(stripe_pos_bad, 167, 0) \ + x(stripe_val_size_bad, 168, 0) \ + x(stripe_sector_count_wrong, 169, 0) \ + x(snapshot_tree_pos_bad, 170, 0) \ + x(snapshot_tree_to_missing_snapshot, 171, 0) \ + x(snapshot_tree_to_missing_subvol, 172, 0) \ + x(snapshot_tree_to_wrong_subvol, 173, 0) \ + x(snapshot_tree_to_snapshot_subvol, 174, 0) \ + x(snapshot_pos_bad, 175, 0) \ + x(snapshot_parent_bad, 176, 0) \ + x(snapshot_children_not_normalized, 177, 0) \ + x(snapshot_child_duplicate, 178, 0) \ + x(snapshot_child_bad, 179, 0) \ + x(snapshot_skiplist_not_normalized, 180, 0) \ + x(snapshot_skiplist_bad, 181, 0) \ + x(snapshot_should_not_have_subvol, 182, 0) \ + x(snapshot_to_bad_snapshot_tree, 183, 0) \ + x(snapshot_bad_depth, 184, 0) \ + x(snapshot_bad_skiplist, 185, 0) \ + x(subvol_pos_bad, 186, 0) \ + x(subvol_not_master_and_not_snapshot, 187, 0) \ + x(subvol_to_missing_root, 188, 0) \ + x(subvol_root_wrong_bi_subvol, 189, 0) \ + x(bkey_in_missing_snapshot, 190, 0) \ + x(inode_pos_inode_nonzero, 191, 0) \ + x(inode_pos_blockdev_range, 192, 0) \ + x(inode_unpack_error, 193, 0) \ + x(inode_str_hash_invalid, 194, 0) \ + x(inode_v3_fields_start_bad, 195, 0) \ + x(inode_snapshot_mismatch, 196, 0) \ + x(inode_unlinked_but_clean, 197, 0) \ + x(inode_unlinked_but_nlink_nonzero, 198, 0) \ + x(inode_checksum_type_invalid, 199, 0) \ + x(inode_compression_type_invalid, 200, 0) \ + x(inode_subvol_root_but_not_dir, 201, 0) \ + x(inode_i_size_dirty_but_clean, 202, 0) \ + x(inode_i_sectors_dirty_but_clean, 203, 0) \ + x(inode_i_sectors_wrong, 204, 0) \ + x(inode_dir_wrong_nlink, 205, 0) \ + x(inode_dir_multiple_links, 206, 0) \ + x(inode_multiple_links_but_nlink_0, 207, 0) \ + x(inode_wrong_backpointer, 208, 0) \ + x(inode_wrong_nlink, 209, 0) \ + x(inode_unreachable, 210, 0) \ + x(deleted_inode_but_clean, 211, 0) \ + x(deleted_inode_missing, 212, 0) \ + x(deleted_inode_is_dir, 213, 0) \ + x(deleted_inode_not_unlinked, 214, 0) \ + x(extent_overlapping, 215, 0) \ + x(extent_in_missing_inode, 216, 0) \ + x(extent_in_non_reg_inode, 217, 0) \ + x(extent_past_end_of_inode, 218, 0) \ + x(dirent_empty_name, 219, 0) \ + x(dirent_val_too_big, 220, 0) \ + x(dirent_name_too_long, 221, 0) \ + x(dirent_name_embedded_nul, 222, 0) \ + x(dirent_name_dot_or_dotdot, 223, 0) \ + x(dirent_name_has_slash, 224, 0) \ + x(dirent_d_type_wrong, 225, 0) \ + x(inode_bi_parent_wrong, 226, 0) \ + x(dirent_in_missing_dir_inode, 227, 0) \ + x(dirent_in_non_dir_inode, 228, 0) \ + x(dirent_to_missing_inode, 229, 0) \ + x(dirent_to_missing_subvol, 230, 0) \ + x(dirent_to_itself, 231, 0) \ + x(quota_type_invalid, 232, 0) \ + x(xattr_val_size_too_small, 233, 0) \ + x(xattr_val_size_too_big, 234, 0) \ + x(xattr_invalid_type, 235, 0) \ + x(xattr_name_invalid_chars, 236, 0) \ + x(xattr_in_missing_inode, 237, 0) \ + x(root_subvol_missing, 238, 0) \ + x(root_dir_missing, 239, 0) \ + x(root_inode_not_dir, 240, 0) \ + x(dir_loop, 241, 0) \ + x(hash_table_key_duplicate, 242, 0) \ + x(hash_table_key_wrong_offset, 243, 0) \ + x(unlinked_inode_not_on_deleted_list, 244, 0) \ + x(reflink_p_front_pad_bad, 245, 0) \ + x(journal_entry_dup_same_device, 246, 0) \ + x(inode_bi_subvol_missing, 247, 0) \ + x(inode_bi_subvol_wrong, 248, 0) \ + x(inode_points_to_missing_dirent, 249, 0) \ + x(inode_points_to_wrong_dirent, 250, 0) \ + x(inode_bi_parent_nonzero, 251, 0) \ + x(dirent_to_missing_parent_subvol, 252, 0) \ + x(dirent_not_visible_in_parent_subvol, 253, 0) \ + x(subvol_fs_path_parent_wrong, 254, 0) \ + x(subvol_root_fs_path_parent_nonzero, 255, 0) \ + x(subvol_children_not_set, 256, 0) \ + x(subvol_children_bad, 257, 0) \ + x(subvol_loop, 258, 0) \ + x(subvol_unreachable, 259, 0) \ + x(btree_node_bkey_bad_u64s, 260, 0) \ + x(btree_node_topology_empty_interior_node, 261, 0) \ + x(btree_ptr_v2_min_key_bad, 262, 0) \ + x(btree_root_unreadable_and_scan_found_nothing, 263, 0) \ + x(snapshot_node_missing, 264, 0) \ + x(dup_backpointer_to_bad_csum_extent, 265, 0) \ + x(btree_bitmap_not_marked, 266, 0) \ + x(sb_clean_entry_overrun, 267, 0) \ + x(btree_ptr_v2_written_0, 268, 0) \ + x(subvol_snapshot_bad, 269, 0) \ + x(subvol_inode_bad, 270, 0) \ + x(alloc_key_stripe_sectors_wrong, 271, 0) \ + x(accounting_mismatch, 272, 0) \ + x(accounting_replicas_not_marked, 273, 0) \ + x(invalid_btree_id, 274, 0) \ + x(alloc_key_io_time_bad, 275, 0) enum bch_sb_error_id { -#define x(t, n) BCH_FSCK_ERR_##t = n, +#define x(t, n, ...) BCH_FSCK_ERR_##t = n, BCH_SB_ERRS() #undef x BCH_SB_ERR_MAX diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c index 51918acfd726..4ef98e696673 100644 --- a/fs/bcachefs/snapshot.c +++ b/fs/bcachefs/snapshot.c @@ -1565,13 +1565,6 @@ int bch2_delete_dead_snapshots(struct bch_fs *c) if (!test_and_clear_bit(BCH_FS_need_delete_dead_snapshots, &c->flags)) return 0; - if (!test_bit(BCH_FS_started, &c->flags)) { - ret = bch2_fs_read_write_early(c); - bch_err_msg(c, ret, "deleting dead snapshots: error going rw"); - if (ret) - return ret; - } - trans = bch2_trans_get(c); /* @@ -1687,6 +1680,8 @@ void bch2_delete_dead_snapshots_work(struct work_struct *work) { struct bch_fs *c = container_of(work, struct bch_fs, snapshot_delete_work); + set_worker_desc("bcachefs-delete-dead-snapshots/%s", c->name); + bch2_delete_dead_snapshots(c); bch2_write_ref_put(c, BCH_WRITE_REF_delete_dead_snapshots); } diff --git a/fs/bcachefs/str_hash.h b/fs/bcachefs/str_hash.h index cbad9b27874f..c8c266cb5797 100644 --- a/fs/bcachefs/str_hash.h +++ b/fs/bcachefs/str_hash.h @@ -300,7 +300,7 @@ not_found: if (!found && (flags & STR_HASH_must_replace)) { ret = -BCH_ERR_ENOENT_str_hash_set_must_replace; } else if (found && (flags & STR_HASH_must_create)) { - ret = -EEXIST; + ret = -BCH_ERR_EEXIST_str_hash_set; } else { if (!found && slot.path) swap(iter, slot); diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c index d73a0222f709..b156fc85b8a3 100644 --- a/fs/bcachefs/super-io.c +++ b/fs/bcachefs/super-io.c @@ -649,9 +649,10 @@ reread: bytes = vstruct_bytes(sb->sb); - if (bytes > 512ULL << min(BCH_SB_LAYOUT_SIZE_BITS_MAX, sb->sb->layout.sb_max_size_bits)) { - prt_printf(err, "Invalid superblock: too big (got %zu bytes, layout max %lu)", - bytes, 512UL << sb->sb->layout.sb_max_size_bits); + u64 sb_size = 512ULL << min(BCH_SB_LAYOUT_SIZE_BITS_MAX, sb->sb->layout.sb_max_size_bits); + if (bytes > sb_size) { + prt_printf(err, "Invalid superblock: too big (got %zu bytes, layout max %llu)", + bytes, sb_size); return -BCH_ERR_invalid_sb_too_big; } @@ -1310,15 +1311,15 @@ void bch2_sb_to_text(struct printbuf *out, struct bch_sb *sb, prt_printf(out, "Device index:\t%u\n", sb->dev_idx); - prt_str(out, "Label:\t"); + prt_printf(out, "Label:\t"); prt_printf(out, "%.*s", (int) sizeof(sb->label), sb->label); prt_newline(out); - prt_str(out, "Version:\t"); + prt_printf(out, "Version:\t"); bch2_version_to_text(out, le16_to_cpu(sb->version)); prt_newline(out); - prt_str(out, "Version upgrade complete:\t"); + prt_printf(out, "Version upgrade complete:\t"); bch2_version_to_text(out, BCH_SB_VERSION_UPGRADE_COMPLETE(sb)); prt_newline(out); diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c index df2bea38e83f..9083df82073a 100644 --- a/fs/bcachefs/super.c +++ b/fs/bcachefs/super.c @@ -582,8 +582,10 @@ static void __bch2_fs_free(struct bch_fs *c) if (c->write_ref_wq) destroy_workqueue(c->write_ref_wq); - if (c->io_complete_wq) - destroy_workqueue(c->io_complete_wq); + if (c->btree_write_submit_wq) + destroy_workqueue(c->btree_write_submit_wq); + if (c->btree_read_complete_wq) + destroy_workqueue(c->btree_read_complete_wq); if (c->copygc_wq) destroy_workqueue(c->copygc_wq); if (c->btree_io_complete_wq) @@ -878,8 +880,10 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts) WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM, 1)) || !(c->copygc_wq = alloc_workqueue("bcachefs_copygc", WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 1)) || - !(c->io_complete_wq = alloc_workqueue("bcachefs_io", + !(c->btree_read_complete_wq = alloc_workqueue("bcachefs_btree_read_complete", WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM, 512)) || + !(c->btree_write_submit_wq = alloc_workqueue("bcachefs_btree_write_sumit", + WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM, 1)) || !(c->write_ref_wq = alloc_workqueue("bcachefs_write_ref", WQ_FREEZABLE, 0)) || #ifndef BCH_WRITE_REF_DEBUG @@ -908,9 +912,9 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts) bch2_io_clock_init(&c->io_clock[WRITE]) ?: bch2_fs_journal_init(&c->journal) ?: bch2_fs_replicas_init(c) ?: + bch2_fs_btree_iter_init(c) ?: bch2_fs_btree_cache_init(c) ?: bch2_fs_btree_key_cache_init(&c->btree_key_cache) ?: - bch2_fs_btree_iter_init(c) ?: bch2_fs_btree_interior_update_init(c) ?: bch2_fs_buckets_waiting_for_journal_init(c) ?: bch2_fs_btree_write_buffer_init(c) ?: @@ -927,12 +931,13 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts) if (ret) goto err; - for (i = 0; i < c->sb.nr_devices; i++) - if (bch2_member_exists(c->disk_sb.sb, i) && - bch2_dev_alloc(c, i)) { - ret = -EEXIST; + for (i = 0; i < c->sb.nr_devices; i++) { + if (!bch2_member_exists(c->disk_sb.sb, i)) + continue; + ret = bch2_dev_alloc(c, i); + if (ret) goto err; - } + } bch2_journal_entry_res_resize(&c->journal, &c->btree_root_journal_res, diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index 477f350a8bd0..e3a57196b0ee 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -741,7 +741,9 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) ret = btrfs_bio_csum(bbio); if (ret) goto fail_put_bio; - } else if (use_append) { + } else if (use_append || + (btrfs_is_zoned(fs_info) && inode && + inode->flags & BTRFS_INODE_NODATASUM)) { ret = btrfs_alloc_dummy_sum(bbio); if (ret) goto fail_put_bio; diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 1e09aeea69c2..1a66be33bb04 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1785,6 +1785,7 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) container_of(work, struct btrfs_fs_info, reclaim_bgs_work); struct btrfs_block_group *bg; struct btrfs_space_info *space_info; + LIST_HEAD(retry_list); if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags)) return; @@ -1921,8 +1922,11 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) } next: - if (ret) - btrfs_mark_bg_to_reclaim(bg); + if (ret) { + /* Refcount held by the reclaim_bgs list after splice. */ + btrfs_get_block_group(bg); + list_add_tail(&bg->bg_list, &retry_list); + } btrfs_put_block_group(bg); mutex_unlock(&fs_info->reclaim_bgs_lock); @@ -1942,6 +1946,9 @@ next: spin_unlock(&fs_info->unused_bgs_lock); mutex_unlock(&fs_info->reclaim_bgs_lock); end: + spin_lock(&fs_info->unused_bgs_lock); + list_splice_tail(&retry_list, &fs_info->reclaim_bgs); + spin_unlock(&fs_info->unused_bgs_lock); btrfs_exclop_finish(fs_info); sb_end_write(fs_info->sb); } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 1b20b3e390df..38cdb8875e8e 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4538,18 +4538,10 @@ static void btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, struct btrfs_fs_info *fs_info) { struct rb_node *node; - struct btrfs_delayed_ref_root *delayed_refs; + struct btrfs_delayed_ref_root *delayed_refs = &trans->delayed_refs; struct btrfs_delayed_ref_node *ref; - delayed_refs = &trans->delayed_refs; - spin_lock(&delayed_refs->lock); - if (atomic_read(&delayed_refs->num_entries) == 0) { - spin_unlock(&delayed_refs->lock); - btrfs_debug(fs_info, "delayed_refs has NO entry"); - return; - } - while ((node = rb_first_cached(&delayed_refs->href_root)) != NULL) { struct btrfs_delayed_ref_head *head; struct rb_node *n; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 597387e9f040..f688fab55251 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3689,6 +3689,8 @@ static struct extent_buffer *grab_extent_buffer( struct folio *folio = page_folio(page); struct extent_buffer *exists; + lockdep_assert_held(&page->mapping->i_private_lock); + /* * For subpage case, we completely rely on radix tree to ensure we * don't try to insert two ebs for the same bytenr. So here we always @@ -3756,13 +3758,14 @@ static int check_eb_alignment(struct btrfs_fs_info *fs_info, u64 start) * The caller needs to free the existing folios and retry using the same order. */ static int attach_eb_folio_to_filemap(struct extent_buffer *eb, int i, + struct btrfs_subpage *prealloc, struct extent_buffer **found_eb_ret) { struct btrfs_fs_info *fs_info = eb->fs_info; struct address_space *mapping = fs_info->btree_inode->i_mapping; const unsigned long index = eb->start >> PAGE_SHIFT; - struct folio *existing_folio; + struct folio *existing_folio = NULL; int ret; ASSERT(found_eb_ret); @@ -3774,12 +3777,14 @@ retry: ret = filemap_add_folio(mapping, eb->folios[i], index + i, GFP_NOFS | __GFP_NOFAIL); if (!ret) - return 0; + goto finish; existing_folio = filemap_lock_folio(mapping, index + i); /* The page cache only exists for a very short time, just retry. */ - if (IS_ERR(existing_folio)) + if (IS_ERR(existing_folio)) { + existing_folio = NULL; goto retry; + } /* For now, we should only have single-page folios for btree inode. */ ASSERT(folio_nr_pages(existing_folio) == 1); @@ -3790,14 +3795,13 @@ retry: return -EAGAIN; } - if (fs_info->nodesize < PAGE_SIZE) { - /* - * We're going to reuse the existing page, can drop our page - * and subpage structure now. - */ +finish: + spin_lock(&mapping->i_private_lock); + if (existing_folio && fs_info->nodesize < PAGE_SIZE) { + /* We're going to reuse the existing page, can drop our folio now. */ __free_page(folio_page(eb->folios[i], 0)); eb->folios[i] = existing_folio; - } else { + } else if (existing_folio) { struct extent_buffer *existing_eb; existing_eb = grab_extent_buffer(fs_info, @@ -3805,6 +3809,7 @@ retry: if (existing_eb) { /* The extent buffer still exists, we can use it directly. */ *found_eb_ret = existing_eb; + spin_unlock(&mapping->i_private_lock); folio_unlock(existing_folio); folio_put(existing_folio); return 1; @@ -3813,6 +3818,22 @@ retry: __free_page(folio_page(eb->folios[i], 0)); eb->folios[i] = existing_folio; } + eb->folio_size = folio_size(eb->folios[i]); + eb->folio_shift = folio_shift(eb->folios[i]); + /* Should not fail, as we have preallocated the memory. */ + ret = attach_extent_buffer_folio(eb, eb->folios[i], prealloc); + ASSERT(!ret); + /* + * To inform we have an extra eb under allocation, so that + * detach_extent_buffer_page() won't release the folio private when the + * eb hasn't been inserted into radix tree yet. + * + * The ref will be decreased when the eb releases the page, in + * detach_extent_buffer_page(). Thus needs no special handling in the + * error path. + */ + btrfs_folio_inc_eb_refs(fs_info, eb->folios[i]); + spin_unlock(&mapping->i_private_lock); return 0; } @@ -3824,7 +3845,6 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, int attached = 0; struct extent_buffer *eb; struct extent_buffer *existing_eb = NULL; - struct address_space *mapping = fs_info->btree_inode->i_mapping; struct btrfs_subpage *prealloc = NULL; u64 lockdep_owner = owner_root; bool page_contig = true; @@ -3890,7 +3910,7 @@ reallocate: for (int i = 0; i < num_folios; i++) { struct folio *folio; - ret = attach_eb_folio_to_filemap(eb, i, &existing_eb); + ret = attach_eb_folio_to_filemap(eb, i, prealloc, &existing_eb); if (ret > 0) { ASSERT(existing_eb); goto out; @@ -3927,24 +3947,6 @@ reallocate: * and free the allocated page. */ folio = eb->folios[i]; - eb->folio_size = folio_size(folio); - eb->folio_shift = folio_shift(folio); - spin_lock(&mapping->i_private_lock); - /* Should not fail, as we have preallocated the memory */ - ret = attach_extent_buffer_folio(eb, folio, prealloc); - ASSERT(!ret); - /* - * To inform we have extra eb under allocation, so that - * detach_extent_buffer_page() won't release the folio private - * when the eb hasn't yet been inserted into radix tree. - * - * The ref will be decreased when the eb released the page, in - * detach_extent_buffer_page(). - * Thus needs no special handling in error path. - */ - btrfs_folio_inc_eb_refs(fs_info, folio); - spin_unlock(&mapping->i_private_lock); - WARN_ON(btrfs_folio_test_dirty(fs_info, folio, eb->start, eb->len)); /* diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 5146387b416b..26a2e5aa08e9 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4860,18 +4860,23 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans, path->slots[0]++; continue; } - if (!dropped_extents) { - /* - * Avoid logging extent items logged in past fsync calls - * and leading to duplicate keys in the log tree. - */ + /* + * Avoid overlapping items in the log tree. The first time we + * get here, get rid of everything from a past fsync. After + * that, if the current extent starts before the end of the last + * extent we copied, truncate the last one. This can happen if + * an ordered extent completion modifies the subvolume tree + * while btrfs_next_leaf() has the tree unlocked. + */ + if (!dropped_extents || key.offset < truncate_offset) { ret = truncate_inode_items(trans, root->log_root, inode, - truncate_offset, + min(key.offset, truncate_offset), BTRFS_EXTENT_DATA_KEY); if (ret) goto out; dropped_extents = true; } + truncate_offset = btrfs_file_extent_end(path); if (ins_nr == 0) start_slot = slot; ins_nr++; diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 6465e2574230..06cdf1a8a16f 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -133,7 +133,7 @@ static int cachefiles_daemon_open(struct inode *inode, struct file *file) return 0; } -static void cachefiles_flush_reqs(struct cachefiles_cache *cache) +void cachefiles_flush_reqs(struct cachefiles_cache *cache) { struct xarray *xa = &cache->reqs; struct cachefiles_req *req; @@ -159,6 +159,7 @@ static void cachefiles_flush_reqs(struct cachefiles_cache *cache) xa_for_each(xa, index, req) { req->error = -EIO; complete(&req->done); + __xa_erase(xa, index); } xa_unlock(xa); diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index d33169f0018b..6845a90cdfcc 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -55,6 +55,7 @@ struct cachefiles_ondemand_info { int ondemand_id; enum cachefiles_object_state state; struct cachefiles_object *object; + spinlock_t lock; }; /* @@ -138,6 +139,7 @@ static inline bool cachefiles_in_ondemand_mode(struct cachefiles_cache *cache) struct cachefiles_req { struct cachefiles_object *object; struct completion done; + refcount_t ref; int error; struct cachefiles_msg msg; }; @@ -186,6 +188,7 @@ extern int cachefiles_has_space(struct cachefiles_cache *cache, * daemon.c */ extern const struct file_operations cachefiles_daemon_fops; +extern void cachefiles_flush_reqs(struct cachefiles_cache *cache); extern void cachefiles_get_unbind_pincount(struct cachefiles_cache *cache); extern void cachefiles_put_unbind_pincount(struct cachefiles_cache *cache); @@ -424,6 +427,8 @@ do { \ pr_err("I/O Error: " FMT"\n", ##__VA_ARGS__); \ fscache_io_error((___cache)->cache); \ set_bit(CACHEFILES_DEAD, &(___cache)->flags); \ + if (cachefiles_in_ondemand_mode(___cache)) \ + cachefiles_flush_reqs(___cache); \ } while (0) #define cachefiles_io_error_obj(object, FMT, ...) \ diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c index 4ba42f1fa3b4..bce005f2b456 100644 --- a/fs/cachefiles/ondemand.c +++ b/fs/cachefiles/ondemand.c @@ -1,22 +1,42 @@ // SPDX-License-Identifier: GPL-2.0-or-later -#include <linux/fdtable.h> #include <linux/anon_inodes.h> #include <linux/uio.h> #include "internal.h" +struct ondemand_anon_file { + struct file *file; + int fd; +}; + +static inline void cachefiles_req_put(struct cachefiles_req *req) +{ + if (refcount_dec_and_test(&req->ref)) + kfree(req); +} + static int cachefiles_ondemand_fd_release(struct inode *inode, struct file *file) { struct cachefiles_object *object = file->private_data; - struct cachefiles_cache *cache = object->volume->cache; - struct cachefiles_ondemand_info *info = object->ondemand; - int object_id = info->ondemand_id; + struct cachefiles_cache *cache; + struct cachefiles_ondemand_info *info; + int object_id; struct cachefiles_req *req; - XA_STATE(xas, &cache->reqs, 0); + XA_STATE(xas, NULL, 0); + + if (!object) + return 0; + + info = object->ondemand; + cache = object->volume->cache; + xas.xa = &cache->reqs; xa_lock(&cache->reqs); + spin_lock(&info->lock); + object_id = info->ondemand_id; info->ondemand_id = CACHEFILES_ONDEMAND_ID_CLOSED; cachefiles_ondemand_set_object_close(object); + spin_unlock(&info->lock); /* Only flush CACHEFILES_REQ_NEW marked req to avoid race with daemon_read */ xas_for_each_marked(&xas, req, ULONG_MAX, CACHEFILES_REQ_NEW) { @@ -76,12 +96,12 @@ static loff_t cachefiles_ondemand_fd_llseek(struct file *filp, loff_t pos, } static long cachefiles_ondemand_fd_ioctl(struct file *filp, unsigned int ioctl, - unsigned long arg) + unsigned long id) { struct cachefiles_object *object = filp->private_data; struct cachefiles_cache *cache = object->volume->cache; struct cachefiles_req *req; - unsigned long id; + XA_STATE(xas, &cache->reqs, id); if (ioctl != CACHEFILES_IOC_READ_COMPLETE) return -EINVAL; @@ -89,10 +109,15 @@ static long cachefiles_ondemand_fd_ioctl(struct file *filp, unsigned int ioctl, if (!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags)) return -EOPNOTSUPP; - id = arg; - req = xa_erase(&cache->reqs, id); - if (!req) + xa_lock(&cache->reqs); + req = xas_load(&xas); + if (!req || req->msg.opcode != CACHEFILES_OP_READ || + req->object != object) { + xa_unlock(&cache->reqs); return -EINVAL; + } + xas_store(&xas, NULL); + xa_unlock(&cache->reqs); trace_cachefiles_ondemand_cread(object, id); complete(&req->done); @@ -116,10 +141,12 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args) { struct cachefiles_req *req; struct fscache_cookie *cookie; + struct cachefiles_ondemand_info *info; char *pid, *psize; unsigned long id; long size; int ret; + XA_STATE(xas, &cache->reqs, 0); if (!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags)) return -EOPNOTSUPP; @@ -143,10 +170,18 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args) if (ret) return ret; - req = xa_erase(&cache->reqs, id); - if (!req) + xa_lock(&cache->reqs); + xas.xa_index = id; + req = xas_load(&xas); + if (!req || req->msg.opcode != CACHEFILES_OP_OPEN || + !req->object->ondemand->ondemand_id) { + xa_unlock(&cache->reqs); return -EINVAL; + } + xas_store(&xas, NULL); + xa_unlock(&cache->reqs); + info = req->object->ondemand; /* fail OPEN request if copen format is invalid */ ret = kstrtol(psize, 0, &size); if (ret) { @@ -166,6 +201,32 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args) goto out; } + spin_lock(&info->lock); + /* + * The anonymous fd was closed before copen ? Fail the request. + * + * t1 | t2 + * --------------------------------------------------------- + * cachefiles_ondemand_copen + * req = xa_erase(&cache->reqs, id) + * // Anon fd is maliciously closed. + * cachefiles_ondemand_fd_release + * xa_lock(&cache->reqs) + * cachefiles_ondemand_set_object_close(object) + * xa_unlock(&cache->reqs) + * cachefiles_ondemand_set_object_open + * // No one will ever close it again. + * cachefiles_ondemand_daemon_read + * cachefiles_ondemand_select_req + * + * Get a read req but its fd is already closed. The daemon can't + * issue a cread ioctl with an closed fd, then hung. + */ + if (info->ondemand_id == CACHEFILES_ONDEMAND_ID_CLOSED) { + spin_unlock(&info->lock); + req->error = -EBADFD; + goto out; + } cookie = req->object->cookie; cookie->object_size = size; if (size) @@ -175,9 +236,15 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args) trace_cachefiles_ondemand_copen(req->object, id, size); cachefiles_ondemand_set_object_open(req->object); + spin_unlock(&info->lock); wake_up_all(&cache->daemon_pollwq); out: + spin_lock(&info->lock); + /* Need to set object close to avoid reopen status continuing */ + if (info->ondemand_id == CACHEFILES_ONDEMAND_ID_CLOSED) + cachefiles_ondemand_set_object_close(req->object); + spin_unlock(&info->lock); complete(&req->done); return ret; } @@ -205,14 +272,14 @@ int cachefiles_ondemand_restore(struct cachefiles_cache *cache, char *args) return 0; } -static int cachefiles_ondemand_get_fd(struct cachefiles_req *req) +static int cachefiles_ondemand_get_fd(struct cachefiles_req *req, + struct ondemand_anon_file *anon_file) { struct cachefiles_object *object; struct cachefiles_cache *cache; struct cachefiles_open *load; - struct file *file; u32 object_id; - int ret, fd; + int ret; object = cachefiles_grab_object(req->object, cachefiles_obj_get_ondemand_fd); @@ -224,35 +291,53 @@ static int cachefiles_ondemand_get_fd(struct cachefiles_req *req) if (ret < 0) goto err; - fd = get_unused_fd_flags(O_WRONLY); - if (fd < 0) { - ret = fd; + anon_file->fd = get_unused_fd_flags(O_WRONLY); + if (anon_file->fd < 0) { + ret = anon_file->fd; goto err_free_id; } - file = anon_inode_getfile("[cachefiles]", &cachefiles_ondemand_fd_fops, - object, O_WRONLY); - if (IS_ERR(file)) { - ret = PTR_ERR(file); + anon_file->file = anon_inode_getfile("[cachefiles]", + &cachefiles_ondemand_fd_fops, object, O_WRONLY); + if (IS_ERR(anon_file->file)) { + ret = PTR_ERR(anon_file->file); goto err_put_fd; } - file->f_mode |= FMODE_PWRITE | FMODE_LSEEK; - fd_install(fd, file); + spin_lock(&object->ondemand->lock); + if (object->ondemand->ondemand_id > 0) { + spin_unlock(&object->ondemand->lock); + /* Pair with check in cachefiles_ondemand_fd_release(). */ + anon_file->file->private_data = NULL; + ret = -EEXIST; + goto err_put_file; + } + + anon_file->file->f_mode |= FMODE_PWRITE | FMODE_LSEEK; load = (void *)req->msg.data; - load->fd = fd; + load->fd = anon_file->fd; object->ondemand->ondemand_id = object_id; + spin_unlock(&object->ondemand->lock); cachefiles_get_unbind_pincount(cache); trace_cachefiles_ondemand_open(object, &req->msg, load); return 0; +err_put_file: + fput(anon_file->file); + anon_file->file = NULL; err_put_fd: - put_unused_fd(fd); + put_unused_fd(anon_file->fd); + anon_file->fd = ret; err_free_id: xa_erase(&cache->ondemand_ids, object_id); err: + spin_lock(&object->ondemand->lock); + /* Avoid marking an opened object as closed. */ + if (object->ondemand->ondemand_id <= 0) + cachefiles_ondemand_set_object_close(object); + spin_unlock(&object->ondemand->lock); cachefiles_put_object(object, cachefiles_obj_put_ondemand_fd); return ret; } @@ -294,14 +379,28 @@ static struct cachefiles_req *cachefiles_ondemand_select_req(struct xa_state *xa return NULL; } +static inline bool cachefiles_ondemand_finish_req(struct cachefiles_req *req, + struct xa_state *xas, int err) +{ + if (unlikely(!xas || !req)) + return false; + + if (xa_cmpxchg(xas->xa, xas->xa_index, req, NULL, 0) != req) + return false; + + req->error = err; + complete(&req->done); + return true; +} + ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, char __user *_buffer, size_t buflen) { struct cachefiles_req *req; struct cachefiles_msg *msg; - unsigned long id = 0; size_t n; int ret = 0; + struct ondemand_anon_file anon_file; XA_STATE(xas, &cache->reqs, cache->req_id_next); xa_lock(&cache->reqs); @@ -330,42 +429,37 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, xas_clear_mark(&xas, CACHEFILES_REQ_NEW); cache->req_id_next = xas.xa_index + 1; + refcount_inc(&req->ref); + cachefiles_grab_object(req->object, cachefiles_obj_get_read_req); xa_unlock(&cache->reqs); - id = xas.xa_index; - if (msg->opcode == CACHEFILES_OP_OPEN) { - ret = cachefiles_ondemand_get_fd(req); - if (ret) { - cachefiles_ondemand_set_object_close(req->object); - goto error; - } + ret = cachefiles_ondemand_get_fd(req, &anon_file); + if (ret) + goto out; } - msg->msg_id = id; + msg->msg_id = xas.xa_index; msg->object_id = req->object->ondemand->ondemand_id; - if (copy_to_user(_buffer, msg, n) != 0) { + if (copy_to_user(_buffer, msg, n) != 0) ret = -EFAULT; - goto err_put_fd; - } - /* CLOSE request has no reply */ - if (msg->opcode == CACHEFILES_OP_CLOSE) { - xa_erase(&cache->reqs, id); - complete(&req->done); + if (msg->opcode == CACHEFILES_OP_OPEN) { + if (ret < 0) { + fput(anon_file.file); + put_unused_fd(anon_file.fd); + goto out; + } + fd_install(anon_file.fd, anon_file.file); } - - return n; - -err_put_fd: - if (msg->opcode == CACHEFILES_OP_OPEN) - close_fd(((struct cachefiles_open *)msg->data)->fd); -error: - xa_erase(&cache->reqs, id); - req->error = ret; - complete(&req->done); - return ret; +out: + cachefiles_put_object(req->object, cachefiles_obj_put_read_req); + /* Remove error request and CLOSE request has no reply */ + if (ret || msg->opcode == CACHEFILES_OP_CLOSE) + cachefiles_ondemand_finish_req(req, &xas, ret); + cachefiles_req_put(req); + return ret ? ret : n; } typedef int (*init_req_fn)(struct cachefiles_req *req, void *private); @@ -395,6 +489,7 @@ static int cachefiles_ondemand_send_req(struct cachefiles_object *object, goto out; } + refcount_set(&req->ref, 1); req->object = object; init_completion(&req->done); req->msg.opcode = opcode; @@ -454,9 +549,19 @@ static int cachefiles_ondemand_send_req(struct cachefiles_object *object, goto out; wake_up_all(&cache->daemon_pollwq); - wait_for_completion(&req->done); - ret = req->error; - kfree(req); +wait: + ret = wait_for_completion_killable(&req->done); + if (!ret) { + ret = req->error; + } else { + ret = -EINTR; + if (!cachefiles_ondemand_finish_req(req, &xas, ret)) { + /* Someone will complete it soon. */ + cpu_relax(); + goto wait; + } + } + cachefiles_req_put(req); return ret; out: /* Reset the object to close state in error handling path. @@ -578,6 +683,7 @@ int cachefiles_ondemand_init_obj_info(struct cachefiles_object *object, return -ENOMEM; object->ondemand->object = object; + spin_lock_init(&object->ondemand->lock); INIT_WORK(&object->ondemand->ondemand_work, ondemand_object_worker); return 0; } diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index dc51df0b118d..8fd928899a59 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -107,8 +107,16 @@ static int debugfs_parse_param(struct fs_context *fc, struct fs_parameter *param int opt; opt = fs_parse(fc, debugfs_param_specs, param, &result); - if (opt < 0) + if (opt < 0) { + /* + * We might like to report bad mount options here; but + * traditionally debugfs has ignored all mount options + */ + if (opt == -ENOPARAM) + return 0; + return opt; + } switch (opt) { case Opt_uid: diff --git a/fs/file.c b/fs/file.c index 8076aef9c210..a3b72aa64f11 100644 --- a/fs/file.c +++ b/fs/file.c @@ -486,12 +486,12 @@ struct files_struct init_files = { static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start) { - unsigned int maxfd = fdt->max_fds; + unsigned int maxfd = fdt->max_fds; /* always multiple of BITS_PER_LONG */ unsigned int maxbit = maxfd / BITS_PER_LONG; unsigned int bitbit = start / BITS_PER_LONG; bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG; - if (bitbit > maxfd) + if (bitbit >= maxfd) return maxfd; if (bitbit > start) start = bitbit; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index c5802a459334..d46558990279 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -241,6 +241,7 @@ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio, unsigned block_size = (1 << block_bits); size_t poff = offset_in_folio(folio, *pos); size_t plen = min_t(loff_t, folio_size(folio) - poff, length); + size_t orig_plen = plen; unsigned first = poff >> block_bits; unsigned last = (poff + plen - 1) >> block_bits; @@ -277,7 +278,7 @@ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio, * handle both halves separately so that we properly zero data in the * page cache for blocks that are entirely outside of i_size. */ - if (orig_pos <= isize && orig_pos + length > isize) { + if (orig_pos <= isize && orig_pos + orig_plen > isize) { unsigned end = offset_in_folio(folio, isize - 1) >> block_bits; if (first <= end && last > end) @@ -877,22 +878,37 @@ static bool iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len, size_t copied, struct folio *folio) { const struct iomap *srcmap = iomap_iter_srcmap(iter); + loff_t old_size = iter->inode->i_size; + size_t written; if (srcmap->type == IOMAP_INLINE) { iomap_write_end_inline(iter, folio, pos, copied); - return true; + written = copied; + } else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) { + written = block_write_end(NULL, iter->inode->i_mapping, pos, + len, copied, &folio->page, NULL); + WARN_ON_ONCE(written != copied && written != 0); + } else { + written = __iomap_write_end(iter->inode, pos, len, copied, + folio) ? copied : 0; } - if (srcmap->flags & IOMAP_F_BUFFER_HEAD) { - size_t bh_written; - - bh_written = block_write_end(NULL, iter->inode->i_mapping, pos, - len, copied, &folio->page, NULL); - WARN_ON_ONCE(bh_written != copied && bh_written != 0); - return bh_written == copied; + /* + * Update the in-memory inode size after copying the data into the page + * cache. It's up to the file system to write the updated size to disk, + * preferably after I/O completion so that no stale data is exposed. + * Only once that's done can we unlock and release the folio. + */ + if (pos + written > old_size) { + i_size_write(iter->inode, pos + written); + iter->iomap.flags |= IOMAP_F_SIZE_CHANGED; } + __iomap_put_folio(iter, pos, written, folio); - return __iomap_write_end(iter->inode, pos, len, copied, folio); + if (old_size < pos) + pagecache_isize_extended(iter->inode, old_size, pos); + + return written == copied; } static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) @@ -907,7 +923,6 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) do { struct folio *folio; - loff_t old_size; size_t offset; /* Offset into folio */ size_t bytes; /* Bytes to write to folio */ size_t copied; /* Bytes copied from user */ @@ -959,23 +974,6 @@ retry: written = iomap_write_end(iter, pos, bytes, copied, folio) ? copied : 0; - /* - * Update the in-memory inode size after copying the data into - * the page cache. It's up to the file system to write the - * updated size to disk, preferably after I/O completion so that - * no stale data is exposed. Only once that's done can we - * unlock and release the folio. - */ - old_size = iter->inode->i_size; - if (pos + written > old_size) { - i_size_write(iter->inode, pos + written); - iter->iomap.flags |= IOMAP_F_SIZE_CHANGED; - } - __iomap_put_folio(iter, pos, written, folio); - - if (old_size < pos) - pagecache_isize_extended(iter->inode, old_size, pos); - cond_resched(); if (unlikely(written == 0)) { /* @@ -1346,7 +1344,6 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter) bytes = folio_size(folio) - offset; ret = iomap_write_end(iter, pos, bytes, bytes, folio); - __iomap_put_folio(iter, pos, bytes, folio); if (WARN_ON_ONCE(!ret)) return -EIO; @@ -1412,7 +1409,6 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) folio_mark_accessed(folio); ret = iomap_write_end(iter, pos, bytes, bytes, folio); - __iomap_put_folio(iter, pos, bytes, folio); if (WARN_ON_ONCE(!ret)) return -EIO; diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index 0fb7afac298e..9987055293b3 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -557,9 +557,11 @@ static int ea_get(struct inode *inode, struct ea_buffer *ea_buf, int min_size) size_check: if (EALIST_SIZE(ea_buf->xattr) != ea_size) { + int size = min_t(int, EALIST_SIZE(ea_buf->xattr), ea_size); + printk(KERN_ERR "ea_get: invalid extended attribute\n"); print_hex_dump(KERN_ERR, "", DUMP_PREFIX_ADDRESS, 16, 1, - ea_buf->xattr, ea_size, 1); + ea_buf->xattr, size, 1); ea_release(inode, ea_buf); rc = -EIO; goto clean_up; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 342930996226..07a7be27182e 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1627,7 +1627,16 @@ nfs_lookup_revalidate_done(struct inode *dir, struct dentry *dentry, switch (error) { case 1: break; - case 0: + case -ETIMEDOUT: + if (inode && (IS_ROOT(dentry) || + NFS_SERVER(inode)->flags & NFS_MOUNT_SOFTREVAL)) + error = 1; + break; + case -ESTALE: + case -ENOENT: + error = 0; + fallthrough; + default: /* * We can't d_drop the root of a disconnected tree: * its d_hash is on the s_anon list and d_drop() would hide @@ -1682,18 +1691,8 @@ static int nfs_lookup_revalidate_dentry(struct inode *dir, dir_verifier = nfs_save_change_attribute(dir); ret = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr); - if (ret < 0) { - switch (ret) { - case -ESTALE: - case -ENOENT: - ret = 0; - break; - case -ETIMEDOUT: - if (NFS_SERVER(inode)->flags & NFS_MOUNT_SOFTREVAL) - ret = 1; - } + if (ret < 0) goto out; - } /* Request help from readdirplus */ nfs_lookup_advise_force_readdirplus(dir, flags); @@ -1737,7 +1736,7 @@ nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode; - int error; + int error = 0; nfs_inc_stats(dir, NFSIOS_DENTRYREVALIDATE); inode = d_inode(dentry); @@ -1782,7 +1781,7 @@ out_valid: out_bad: if (flags & LOOKUP_RCU) return -ECHILD; - return nfs_lookup_revalidate_done(dir, dentry, inode, 0); + return nfs_lookup_revalidate_done(dir, dentry, inode, error); } static int @@ -1804,9 +1803,10 @@ __nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags, if (parent != READ_ONCE(dentry->d_parent)) return -ECHILD; } else { - /* Wait for unlink to complete */ + /* Wait for unlink to complete - see unblock_revalidate() */ wait_var_event(&dentry->d_fsdata, - dentry->d_fsdata != NFS_FSDATA_BLOCKED); + smp_load_acquire(&dentry->d_fsdata) + != NFS_FSDATA_BLOCKED); parent = dget_parent(dentry); ret = reval(d_inode(parent), dentry, flags); dput(parent); @@ -1819,6 +1819,29 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) return __nfs_lookup_revalidate(dentry, flags, nfs_do_lookup_revalidate); } +static void block_revalidate(struct dentry *dentry) +{ + /* old devname - just in case */ + kfree(dentry->d_fsdata); + + /* Any new reference that could lead to an open + * will take ->d_lock in lookup_open() -> d_lookup(). + * Holding this lock ensures we cannot race with + * __nfs_lookup_revalidate() and removes and need + * for further barriers. + */ + lockdep_assert_held(&dentry->d_lock); + + dentry->d_fsdata = NFS_FSDATA_BLOCKED; +} + +static void unblock_revalidate(struct dentry *dentry) +{ + /* store_release ensures wait_var_event() sees the update */ + smp_store_release(&dentry->d_fsdata, NULL); + wake_up_var(&dentry->d_fsdata); +} + /* * A weaker form of d_revalidate for revalidating just the d_inode(dentry) * when we don't really care about the dentry name. This is called when a @@ -2255,6 +2278,9 @@ int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry, */ int error = 0; + if (dentry->d_name.len > NFS_SERVER(dir)->namelen) + return -ENAMETOOLONG; + if (open_flags & O_CREAT) { file->f_mode |= FMODE_CREATED; error = nfs_do_create(dir, dentry, mode, open_flags); @@ -2549,15 +2575,12 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry) spin_unlock(&dentry->d_lock); goto out; } - /* old devname */ - kfree(dentry->d_fsdata); - dentry->d_fsdata = NFS_FSDATA_BLOCKED; + block_revalidate(dentry); spin_unlock(&dentry->d_lock); error = nfs_safe_remove(dentry); nfs_dentry_remove_handle_error(dir, dentry, error); - dentry->d_fsdata = NULL; - wake_up_var(&dentry->d_fsdata); + unblock_revalidate(dentry); out: trace_nfs_unlink_exit(dir, dentry, error); return error; @@ -2664,8 +2687,7 @@ nfs_unblock_rename(struct rpc_task *task, struct nfs_renamedata *data) { struct dentry *new_dentry = data->new_dentry; - new_dentry->d_fsdata = NULL; - wake_up_var(&new_dentry->d_fsdata); + unblock_revalidate(new_dentry); } /* @@ -2727,11 +2749,6 @@ int nfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, if (WARN_ON(new_dentry->d_flags & DCACHE_NFSFS_RENAMED) || WARN_ON(new_dentry->d_fsdata == NFS_FSDATA_BLOCKED)) goto out; - if (new_dentry->d_fsdata) { - /* old devname */ - kfree(new_dentry->d_fsdata); - new_dentry->d_fsdata = NULL; - } spin_lock(&new_dentry->d_lock); if (d_count(new_dentry) > 2) { @@ -2753,7 +2770,7 @@ int nfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, new_dentry = dentry; new_inode = NULL; } else { - new_dentry->d_fsdata = NFS_FSDATA_BLOCKED; + block_revalidate(new_dentry); must_unblock = true; spin_unlock(&new_dentry->d_lock); } @@ -2765,6 +2782,8 @@ int nfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, must_unblock ? nfs_unblock_rename : NULL); if (IS_ERR(task)) { + if (must_unblock) + unblock_revalidate(new_dentry); error = PTR_ERR(task); goto out; } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index bb2f583eb28b..90079ca134dd 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -141,8 +141,6 @@ int nfs_swap_rw(struct kiocb *iocb, struct iov_iter *iter) { ssize_t ret; - VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE); - if (iov_iter_rw(iter) == READ) ret = nfs_file_direct_read(iocb, iter, true); else diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index c93c12063b3a..a691fa10b3e9 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -4023,6 +4023,23 @@ static void test_fs_location_for_trunking(struct nfs4_fs_location *location, } } +static bool _is_same_nfs4_pathname(struct nfs4_pathname *path1, + struct nfs4_pathname *path2) +{ + int i; + + if (path1->ncomponents != path2->ncomponents) + return false; + for (i = 0; i < path1->ncomponents; i++) { + if (path1->components[i].len != path2->components[i].len) + return false; + if (memcmp(path1->components[i].data, path2->components[i].data, + path1->components[i].len)) + return false; + } + return true; +} + static int _nfs4_discover_trunking(struct nfs_server *server, struct nfs_fh *fhandle) { @@ -4056,9 +4073,13 @@ static int _nfs4_discover_trunking(struct nfs_server *server, if (status) goto out_free_3; - for (i = 0; i < locations->nlocations; i++) + for (i = 0; i < locations->nlocations; i++) { + if (!_is_same_nfs4_pathname(&locations->fs_path, + &locations->locations[i].rootpath)) + continue; test_fs_location_for_trunking(&locations->locations[i], clp, server); + } out_free_3: kfree(locations->fattr); out_free_2: @@ -6268,6 +6289,7 @@ nfs4_set_security_label(struct inode *inode, const void *buf, size_t buflen) if (status == 0) nfs_setsecurity(inode, fattr); + nfs_free_fattr(fattr); return status; } #endif /* CONFIG_NFS_V4_SECURITY_LABEL */ diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 6efb5068c116..040b6b79c75e 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -1545,6 +1545,11 @@ void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index) continue; } else if (index == prev->wb_index + 1) continue; + /* + * We will submit more requests after these. Indicate + * this to the underlying layers. + */ + desc->pg_moreio = 1; nfs_pageio_complete(desc); break; } diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c index 0e27a2e4e68b..13818129d268 100644 --- a/fs/nfs/symlink.c +++ b/fs/nfs/symlink.c @@ -41,7 +41,7 @@ static int nfs_symlink_filler(struct file *file, struct folio *folio) error: folio_set_error(folio); folio_unlock(folio); - return -EIO; + return error; } static const char *nfs_get_link(struct dentry *dentry, diff --git a/fs/nfsd/netlink.c b/fs/nfsd/netlink.c index 62d2586d9902..529a75ecf22e 100644 --- a/fs/nfsd/netlink.c +++ b/fs/nfsd/netlink.c @@ -44,9 +44,7 @@ static const struct nla_policy nfsd_listener_set_nl_policy[NFSD_A_SERVER_SOCK_AD static const struct genl_split_ops nfsd_nl_ops[] = { { .cmd = NFSD_CMD_RPC_STATUS_GET, - .start = nfsd_nl_rpc_status_get_start, .dumpit = nfsd_nl_rpc_status_get_dumpit, - .done = nfsd_nl_rpc_status_get_done, .flags = GENL_CMD_CAP_DUMP, }, { diff --git a/fs/nfsd/netlink.h b/fs/nfsd/netlink.h index e3724637d64d..2e132ef328f8 100644 --- a/fs/nfsd/netlink.h +++ b/fs/nfsd/netlink.h @@ -15,9 +15,6 @@ extern const struct nla_policy nfsd_sock_nl_policy[NFSD_A_SOCK_TRANSPORT_NAME + 1]; extern const struct nla_policy nfsd_version_nl_policy[NFSD_A_VERSION_ENABLED + 1]; -int nfsd_nl_rpc_status_get_start(struct netlink_callback *cb); -int nfsd_nl_rpc_status_get_done(struct netlink_callback *cb); - int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info); diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 202140df8f82..533b65057e18 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1460,28 +1460,6 @@ static int create_proc_exports_entry(void) unsigned int nfsd_net_id; -/** - * nfsd_nl_rpc_status_get_start - Prepare rpc_status_get dumpit - * @cb: netlink metadata and command arguments - * - * Return values: - * %0: The rpc_status_get command may proceed - * %-ENODEV: There is no NFSD running in this namespace - */ -int nfsd_nl_rpc_status_get_start(struct netlink_callback *cb) -{ - struct nfsd_net *nn = net_generic(sock_net(cb->skb->sk), nfsd_net_id); - int ret = -ENODEV; - - mutex_lock(&nfsd_mutex); - if (nn->nfsd_serv) - ret = 0; - else - mutex_unlock(&nfsd_mutex); - - return ret; -} - static int nfsd_genl_rpc_status_compose_msg(struct sk_buff *skb, struct netlink_callback *cb, struct nfsd_genl_rqstp *rqstp) @@ -1558,8 +1536,16 @@ static int nfsd_genl_rpc_status_compose_msg(struct sk_buff *skb, int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { - struct nfsd_net *nn = net_generic(sock_net(skb->sk), nfsd_net_id); int i, ret, rqstp_index = 0; + struct nfsd_net *nn; + + mutex_lock(&nfsd_mutex); + + nn = net_generic(sock_net(skb->sk), nfsd_net_id); + if (!nn->nfsd_serv) { + ret = -ENODEV; + goto out_unlock; + } rcu_read_lock(); @@ -1636,22 +1622,10 @@ int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb, ret = skb->len; out: rcu_read_unlock(); - - return ret; -} - -/** - * nfsd_nl_rpc_status_get_done - rpc_status_get dumpit post-processing - * @cb: netlink metadata and command arguments - * - * Return values: - * %0: Success - */ -int nfsd_nl_rpc_status_get_done(struct netlink_callback *cb) -{ +out_unlock: mutex_unlock(&nfsd_mutex); - return 0; + return ret; } /** diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index a002a44ff161..52e50b1b7f22 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -607,7 +607,7 @@ int nilfs_empty_dir(struct inode *inode) kaddr = nilfs_get_folio(inode, i, &folio); if (IS_ERR(kaddr)) - continue; + return 0; de = (struct nilfs_dir_entry *)kaddr; kaddr += nilfs_last_byte(inode, i) - NILFS_DIR_REC_LEN(1); diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 60d4f59f7665..6ea81f1d5094 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1652,6 +1652,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) if (bh->b_folio != bd_folio) { if (bd_folio) { folio_lock(bd_folio); + folio_wait_writeback(bd_folio); folio_clear_dirty_for_io(bd_folio); folio_start_writeback(bd_folio); folio_unlock(bd_folio); @@ -1665,6 +1666,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) if (bh == segbuf->sb_super_root) { if (bh->b_folio != bd_folio) { folio_lock(bd_folio); + folio_wait_writeback(bd_folio); folio_clear_dirty_for_io(bd_folio); folio_start_writeback(bd_folio); folio_unlock(bd_folio); @@ -1681,6 +1683,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) } if (bd_folio) { folio_lock(bd_folio); + folio_wait_writeback(bd_folio); folio_clear_dirty_for_io(bd_folio); folio_start_writeback(bd_folio); folio_unlock(bd_folio); diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index f0467d3b3c88..6be175a1ab3c 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2366,6 +2366,11 @@ static int ocfs2_dio_end_io_write(struct inode *inode, } list_for_each_entry(ue, &dwc->dw_zero_list, ue_node) { + ret = ocfs2_assure_trans_credits(handle, credits); + if (ret < 0) { + mlog_errno(ret); + break; + } ret = ocfs2_mark_extent_written(inode, &et, handle, ue->ue_cpos, 1, ue->ue_phys, diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 604fea3a26ff..530fba34f6d3 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -446,6 +446,23 @@ bail: } /* + * Make sure handle has at least 'nblocks' credits available. If it does not + * have that many credits available, we will try to extend the handle to have + * enough credits. If that fails, we will restart transaction to have enough + * credits. Similar notes regarding data consistency and locking implications + * as for ocfs2_extend_trans() apply here. + */ +int ocfs2_assure_trans_credits(handle_t *handle, int nblocks) +{ + int old_nblks = jbd2_handle_buffer_credits(handle); + + trace_ocfs2_assure_trans_credits(old_nblks); + if (old_nblks >= nblocks) + return 0; + return ocfs2_extend_trans(handle, nblocks - old_nblks); +} + +/* * If we have fewer than thresh credits, extend by OCFS2_MAX_TRANS_DATA. * If that fails, restart the transaction & regain write access for the * buffer head which is used for metadata modifications. @@ -479,12 +496,6 @@ bail: return status; } - -struct ocfs2_triggers { - struct jbd2_buffer_trigger_type ot_triggers; - int ot_offset; -}; - static inline struct ocfs2_triggers *to_ocfs2_trigger(struct jbd2_buffer_trigger_type *triggers) { return container_of(triggers, struct ocfs2_triggers, ot_triggers); @@ -548,85 +559,76 @@ static void ocfs2_db_frozen_trigger(struct jbd2_buffer_trigger_type *triggers, static void ocfs2_abort_trigger(struct jbd2_buffer_trigger_type *triggers, struct buffer_head *bh) { + struct ocfs2_triggers *ot = to_ocfs2_trigger(triggers); + mlog(ML_ERROR, "ocfs2_abort_trigger called by JBD2. bh = 0x%lx, " "bh->b_blocknr = %llu\n", (unsigned long)bh, (unsigned long long)bh->b_blocknr); - ocfs2_error(bh->b_assoc_map->host->i_sb, + ocfs2_error(ot->sb, "JBD2 has aborted our journal, ocfs2 cannot continue\n"); } -static struct ocfs2_triggers di_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_dinode, i_check), -}; - -static struct ocfs2_triggers eb_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_extent_block, h_check), -}; - -static struct ocfs2_triggers rb_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_refcount_block, rf_check), -}; - -static struct ocfs2_triggers gd_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_group_desc, bg_check), -}; - -static struct ocfs2_triggers db_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_db_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, -}; +static void ocfs2_setup_csum_triggers(struct super_block *sb, + enum ocfs2_journal_trigger_type type, + struct ocfs2_triggers *ot) +{ + BUG_ON(type >= OCFS2_JOURNAL_TRIGGER_COUNT); -static struct ocfs2_triggers xb_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_xattr_block, xb_check), -}; + switch (type) { + case OCFS2_JTR_DI: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_dinode, i_check); + break; + case OCFS2_JTR_EB: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_extent_block, h_check); + break; + case OCFS2_JTR_RB: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_refcount_block, rf_check); + break; + case OCFS2_JTR_GD: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_group_desc, bg_check); + break; + case OCFS2_JTR_DB: + ot->ot_triggers.t_frozen = ocfs2_db_frozen_trigger; + break; + case OCFS2_JTR_XB: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_xattr_block, xb_check); + break; + case OCFS2_JTR_DQ: + ot->ot_triggers.t_frozen = ocfs2_dq_frozen_trigger; + break; + case OCFS2_JTR_DR: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_dx_root_block, dr_check); + break; + case OCFS2_JTR_DL: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_dx_leaf, dl_check); + break; + case OCFS2_JTR_NONE: + /* To make compiler happy... */ + return; + } -static struct ocfs2_triggers dq_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_dq_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, -}; + ot->ot_triggers.t_abort = ocfs2_abort_trigger; + ot->sb = sb; +} -static struct ocfs2_triggers dr_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_dx_root_block, dr_check), -}; +void ocfs2_initialize_journal_triggers(struct super_block *sb, + struct ocfs2_triggers triggers[]) +{ + enum ocfs2_journal_trigger_type type; -static struct ocfs2_triggers dl_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_dx_leaf, dl_check), -}; + for (type = OCFS2_JTR_DI; type < OCFS2_JOURNAL_TRIGGER_COUNT; type++) + ocfs2_setup_csum_triggers(sb, type, &triggers[type]); +} static int __ocfs2_journal_access(handle_t *handle, struct ocfs2_caching_info *ci, @@ -708,56 +710,91 @@ static int __ocfs2_journal_access(handle_t *handle, int ocfs2_journal_access_di(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &di_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_DI], + type); } int ocfs2_journal_access_eb(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &eb_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_EB], + type); } int ocfs2_journal_access_rb(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &rb_triggers, + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_RB], type); } int ocfs2_journal_access_gd(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &gd_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_GD], + type); } int ocfs2_journal_access_db(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &db_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_DB], + type); } int ocfs2_journal_access_xb(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &xb_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_XB], + type); } int ocfs2_journal_access_dq(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &dq_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_DQ], + type); } int ocfs2_journal_access_dr(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &dr_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_DR], + type); } int ocfs2_journal_access_dl(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &dl_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_DL], + type); } int ocfs2_journal_access(handle_t *handle, struct ocfs2_caching_info *ci, @@ -778,13 +815,15 @@ void ocfs2_journal_dirty(handle_t *handle, struct buffer_head *bh) if (!is_handle_aborted(handle)) { journal_t *journal = handle->h_transaction->t_journal; - mlog(ML_ERROR, "jbd2_journal_dirty_metadata failed. " - "Aborting transaction and journal.\n"); + mlog(ML_ERROR, "jbd2_journal_dirty_metadata failed: " + "handle type %u started at line %u, credits %u/%u " + "errcode %d. Aborting transaction and journal.\n", + handle->h_type, handle->h_line_no, + handle->h_requested_credits, + jbd2_handle_buffer_credits(handle), status); handle->h_err = status; jbd2_journal_abort_handle(handle); jbd2_journal_abort(journal, status); - ocfs2_abort(bh->b_assoc_map->host->i_sb, - "Journal already aborted.\n"); } } } diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index 41c9fe7e62f9..e3c3a35dc5e0 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -243,6 +243,8 @@ handle_t *ocfs2_start_trans(struct ocfs2_super *osb, int ocfs2_commit_trans(struct ocfs2_super *osb, handle_t *handle); int ocfs2_extend_trans(handle_t *handle, int nblocks); +int ocfs2_assure_trans_credits(handle_t *handle, + int nblocks); int ocfs2_allocate_extend_trans(handle_t *handle, int thresh); diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index a503c553bab2..8fe826143d7b 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -284,6 +284,30 @@ enum ocfs2_mount_options #define OCFS2_OSB_ERROR_FS 0x0004 #define OCFS2_DEFAULT_ATIME_QUANTUM 60 +struct ocfs2_triggers { + struct jbd2_buffer_trigger_type ot_triggers; + int ot_offset; + struct super_block *sb; +}; + +enum ocfs2_journal_trigger_type { + OCFS2_JTR_DI, + OCFS2_JTR_EB, + OCFS2_JTR_RB, + OCFS2_JTR_GD, + OCFS2_JTR_DB, + OCFS2_JTR_XB, + OCFS2_JTR_DQ, + OCFS2_JTR_DR, + OCFS2_JTR_DL, + OCFS2_JTR_NONE /* This must be the last entry */ +}; + +#define OCFS2_JOURNAL_TRIGGER_COUNT OCFS2_JTR_NONE + +void ocfs2_initialize_journal_triggers(struct super_block *sb, + struct ocfs2_triggers triggers[]); + struct ocfs2_journal; struct ocfs2_slot_info; struct ocfs2_recovery_map; @@ -351,6 +375,9 @@ struct ocfs2_super struct ocfs2_journal *journal; unsigned long osb_commit_interval; + /* Journal triggers for checksum */ + struct ocfs2_triggers s_journal_triggers[OCFS2_JOURNAL_TRIGGER_COUNT]; + struct delayed_work la_enable_wq; /* diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h index 60e208b01c8d..0511c69c9fde 100644 --- a/fs/ocfs2/ocfs2_trace.h +++ b/fs/ocfs2/ocfs2_trace.h @@ -2577,6 +2577,8 @@ DEFINE_OCFS2_ULL_UINT_EVENT(ocfs2_commit_cache_end); DEFINE_OCFS2_INT_INT_EVENT(ocfs2_extend_trans); +DEFINE_OCFS2_INT_EVENT(ocfs2_assure_trans_credits); + DEFINE_OCFS2_INT_EVENT(ocfs2_extend_trans_restart); DEFINE_OCFS2_INT_INT_EVENT(ocfs2_allocate_extend_trans); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 8aabaed2c1cb..afee70125ae3 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1075,9 +1075,11 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) debugfs_create_file("fs_state", S_IFREG|S_IRUSR, osb->osb_debug_root, osb, &ocfs2_osb_debug_fops); - if (ocfs2_meta_ecc(osb)) + if (ocfs2_meta_ecc(osb)) { + ocfs2_initialize_journal_triggers(sb, osb->s_journal_triggers); ocfs2_blockcheck_stats_debugfs_install( &osb->osb_ecc_stats, osb->osb_debug_root); + } status = ocfs2_mount_volume(sb); if (status < 0) diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 116f542442dd..ab65e98a1def 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -1314,10 +1314,6 @@ static int ovl_create_tmpfile(struct file *file, struct dentry *dentry, int flags = file->f_flags | OVL_OPEN_FLAGS; int err; - err = ovl_copy_up(dentry->d_parent); - if (err) - return err; - old_cred = ovl_override_creds(dentry->d_sb); err = ovl_setup_cred_for_create(dentry, inode, mode, old_cred); if (err) @@ -1360,6 +1356,10 @@ static int ovl_tmpfile(struct mnt_idmap *idmap, struct inode *dir, if (!OVL_FS(dentry->d_sb)->tmpfile) return -EOPNOTSUPP; + err = ovl_copy_up(dentry->d_parent); + if (err) + return err; + err = ovl_want_write(dentry); if (err) return err; diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index 063409069f56..5868cb222955 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -181,6 +181,10 @@ static int ovl_check_encode_origin(struct dentry *dentry) struct ovl_fs *ofs = OVL_FS(dentry->d_sb); bool decodable = ofs->config.nfs_export; + /* No upper layer? */ + if (!ovl_upper_mnt(ofs)) + return 1; + /* Lower file handle for non-upper non-decodable */ if (!ovl_dentry_upper(dentry) && !decodable) return 1; @@ -209,7 +213,7 @@ static int ovl_check_encode_origin(struct dentry *dentry) * ovl_connect_layer() will try to make origin's layer "connected" by * copying up a "connectable" ancestor. */ - if (d_is_dir(dentry) && ovl_upper_mnt(ofs) && decodable) + if (d_is_dir(dentry) && decodable) return ovl_connect_layer(dentry); /* Lower file handle for indexed and non-upper dir/non-dir */ diff --git a/fs/proc/base.c b/fs/proc/base.c index 18550c071d71..72a1acd03675 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3214,7 +3214,7 @@ static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns, mm = get_task_mm(task); if (mm) { seq_printf(m, "ksm_rmap_items %lu\n", mm->ksm_rmap_items); - seq_printf(m, "ksm_zero_pages %lu\n", mm->ksm_zero_pages); + seq_printf(m, "ksm_zero_pages %ld\n", mm_ksm_zero_pages(mm)); seq_printf(m, "ksm_merging_pages %lu\n", mm->ksm_merging_pages); seq_printf(m, "ksm_process_profit %ld\n", ksm_process_profit(mm)); mmput(mm); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f8d35f993fe5..71e5039d940d 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -707,6 +707,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) #ifdef CONFIG_X86_USER_SHADOW_STACK [ilog2(VM_SHADOW_STACK)] = "ss", #endif +#ifdef CONFIG_64BIT + [ilog2(VM_SEALED)] = "sl", +#endif }; size_t i; diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index bb86fc0641d8..6397fdefd876 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -134,7 +134,7 @@ module_param(enable_oplocks, bool, 0644); MODULE_PARM_DESC(enable_oplocks, "Enable or disable oplocks. Default: y/Y/1"); module_param(enable_gcm_256, bool, 0644); -MODULE_PARM_DESC(enable_gcm_256, "Enable requesting strongest (256 bit) GCM encryption. Default: n/N/0"); +MODULE_PARM_DESC(enable_gcm_256, "Enable requesting strongest (256 bit) GCM encryption. Default: y/Y/0"); module_param(require_gcm_256, bool, 0644); MODULE_PARM_DESC(require_gcm_256, "Require strongest (256 bit) GCM encryption. Default: n/N/0"); diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 73482734a8d8..557b68e99d0a 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -1494,6 +1494,8 @@ struct cifs_aio_ctx { struct cifs_io_request { struct netfs_io_request rreq; struct cifsFileInfo *cfile; + struct TCP_Server_Info *server; + pid_t pid; }; /* asynchronous read support */ @@ -1504,7 +1506,6 @@ struct cifs_io_subrequest { struct cifs_io_request *req; }; ssize_t got_bytes; - pid_t pid; unsigned int xid; int result; bool have_xid; diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 25e9ab947c17..595c4b673707 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1345,8 +1345,8 @@ cifs_async_readv(struct cifs_io_subrequest *rdata) if (rc) return rc; - smb->hdr.Pid = cpu_to_le16((__u16)rdata->pid); - smb->hdr.PidHigh = cpu_to_le16((__u16)(rdata->pid >> 16)); + smb->hdr.Pid = cpu_to_le16((__u16)rdata->req->pid); + smb->hdr.PidHigh = cpu_to_le16((__u16)(rdata->req->pid >> 16)); smb->AndXCommand = 0xFF; /* none */ smb->Fid = rdata->req->cfile->fid.netfid; @@ -1689,8 +1689,8 @@ cifs_async_writev(struct cifs_io_subrequest *wdata) if (rc) goto async_writev_out; - smb->hdr.Pid = cpu_to_le16((__u16)wdata->pid); - smb->hdr.PidHigh = cpu_to_le16((__u16)(wdata->pid >> 16)); + smb->hdr.Pid = cpu_to_le16((__u16)wdata->req->pid); + smb->hdr.PidHigh = cpu_to_le16((__u16)(wdata->req->pid >> 16)); smb->AndXCommand = 0xFF; /* none */ smb->Fid = wdata->req->cfile->fid.netfid; diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 9d5c2440abfc..f1f2573bb18d 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -134,17 +134,15 @@ fail: static bool cifs_clamp_length(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; - struct TCP_Server_Info *server; struct cifs_io_subrequest *rdata = container_of(subreq, struct cifs_io_subrequest, subreq); struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq); + struct TCP_Server_Info *server = req->server; struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb); size_t rsize = 0; int rc; rdata->xid = get_xid(); rdata->have_xid = true; - - server = cifs_pick_channel(tlink_tcon(req->cfile->tlink)->ses); rdata->server = server; if (cifs_sb->ctx->rsize == 0) @@ -179,15 +177,8 @@ static void cifs_req_issue_read(struct netfs_io_subrequest *subreq) struct netfs_io_request *rreq = subreq->rreq; struct cifs_io_subrequest *rdata = container_of(subreq, struct cifs_io_subrequest, subreq); struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq); - struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb); - pid_t pid; int rc = 0; - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) - pid = req->cfile->pid; - else - pid = current->tgid; // Ummm... This may be a workqueue - cifs_dbg(FYI, "%s: op=%08x[%x] mapping=%p len=%zu/%zu\n", __func__, rreq->debug_id, subreq->debug_index, rreq->mapping, subreq->transferred, subreq->len); @@ -201,16 +192,8 @@ static void cifs_req_issue_read(struct netfs_io_subrequest *subreq) } __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); - rdata->pid = pid; - - rc = adjust_credits(rdata->server, &rdata->credits, rdata->subreq.len); - if (!rc) { - if (rdata->req->cfile->invalidHandle) - rc = -EAGAIN; - else - rc = rdata->server->ops->async_readv(rdata); - } + rc = rdata->server->ops->async_readv(rdata); out: if (rc) netfs_subreq_terminated(subreq, rc, false); @@ -245,11 +228,15 @@ static int cifs_init_request(struct netfs_io_request *rreq, struct file *file) rreq->rsize = cifs_sb->ctx->rsize; rreq->wsize = cifs_sb->ctx->wsize; + req->pid = current->tgid; // Ummm... This may be a workqueue if (file) { open_file = file->private_data; rreq->netfs_priv = file->private_data; req->cfile = cifsFileInfo_get(open_file); + req->server = cifs_pick_channel(tlink_tcon(req->cfile->tlink)->ses); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) + req->pid = req->cfile->pid; } else if (rreq->origin != NETFS_WRITEBACK) { WARN_ON_ONCE(1); return -EIO; @@ -3200,8 +3187,6 @@ static int cifs_swap_rw(struct kiocb *iocb, struct iov_iter *iter) { ssize_t ret; - WARN_ON_ONCE(iov_iter_count(iter) != PAGE_SIZE); - if (iov_iter_rw(iter) == READ) ret = netfs_unbuffered_read_iter_locked(iocb, iter); else diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 993ac36c3d58..2ae2dbb6202b 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4484,6 +4484,16 @@ smb2_new_read_req(void **buf, unsigned int *total_len, return rc; } +static void smb2_readv_worker(struct work_struct *work) +{ + struct cifs_io_subrequest *rdata = + container_of(work, struct cifs_io_subrequest, subreq.work); + + netfs_subreq_terminated(&rdata->subreq, + (rdata->result == 0 || rdata->result == -EAGAIN) ? + rdata->got_bytes : rdata->result, true); +} + static void smb2_readv_callback(struct mid_q_entry *mid) { @@ -4577,12 +4587,9 @@ smb2_readv_callback(struct mid_q_entry *mid) if (rdata->subreq.start < rdata->subreq.rreq->i_size) rdata->result = 0; } - if (rdata->result == 0 || rdata->result == -EAGAIN) - iov_iter_advance(&rdata->subreq.io_iter, rdata->got_bytes); rdata->credits.value = 0; - netfs_subreq_terminated(&rdata->subreq, - (rdata->result == 0 || rdata->result == -EAGAIN) ? - rdata->got_bytes : rdata->result, true); + INIT_WORK(&rdata->subreq.work, smb2_readv_worker); + queue_work(cifsiod_wq, &rdata->subreq.work); release_mid(mid); add_credits(server, &credits, 0); } @@ -4614,7 +4621,7 @@ smb2_async_readv(struct cifs_io_subrequest *rdata) io_parms.length = rdata->subreq.len; io_parms.persistent_fid = rdata->req->cfile->fid.persistent_fid; io_parms.volatile_fid = rdata->req->cfile->fid.volatile_fid; - io_parms.pid = rdata->pid; + io_parms.pid = rdata->req->pid; rc = smb2_new_read_req( (void **) &buf, &total_len, &io_parms, rdata, 0, 0); @@ -4789,7 +4796,6 @@ smb2_writev_callback(struct mid_q_entry *mid) wdata->result = -ENOSPC; else wdata->subreq.len = written; - iov_iter_advance(&wdata->subreq.io_iter, written); break; case MID_REQUEST_SUBMITTED: case MID_RETRY_NEEDED: @@ -4867,7 +4873,7 @@ smb2_async_writev(struct cifs_io_subrequest *wdata) .length = wdata->subreq.len, .persistent_fid = wdata->req->cfile->fid.persistent_fid, .volatile_fid = wdata->req->cfile->fid.volatile_fid, - .pid = wdata->pid, + .pid = wdata->req->pid, }; io_parms = &_io_parms; diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index 02135a605305..1476c445cadc 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -216,8 +216,8 @@ smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid) } tcon = smb2_find_smb_sess_tcon_unlocked(ses, tid); if (!tcon) { - cifs_put_smb_ses(ses); spin_unlock(&cifs_tcp_ses_lock); + cifs_put_smb_ses(ses); return NULL; } spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index b6c5a8ea3887..e7e07891781b 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -630,6 +630,12 @@ smb2_get_name(const char *src, const int maxlen, struct nls_table *local_nls) return name; } + if (*name == '\\') { + pr_err("not allow directory name included leading slash\n"); + kfree(name); + return ERR_PTR(-EINVAL); + } + ksmbd_conv_path_to_unix(name); ksmbd_strip_last_slash(name); return name; @@ -2361,7 +2367,8 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, if (rc > 0) { rc = ksmbd_vfs_remove_xattr(idmap, path, - attr_name); + attr_name, + get_write); if (rc < 0) { ksmbd_debug(SMB, @@ -2376,7 +2383,7 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, } else { rc = ksmbd_vfs_setxattr(idmap, path, attr_name, value, le16_to_cpu(eabuf->EaValueLength), - 0, true); + 0, get_write); if (rc < 0) { ksmbd_debug(SMB, "ksmbd_vfs_setxattr is failed(%d)\n", @@ -2468,7 +2475,7 @@ static int smb2_remove_smb_xattrs(const struct path *path) !strncmp(&name[XATTR_USER_PREFIX_LEN], STREAM_PREFIX, STREAM_PREFIX_LEN)) { err = ksmbd_vfs_remove_xattr(idmap, path, - name); + name, true); if (err) ksmbd_debug(SMB, "remove xattr failed : %s\n", name); @@ -2842,20 +2849,11 @@ int smb2_open(struct ksmbd_work *work) } if (req->NameLength) { - if ((req->CreateOptions & FILE_DIRECTORY_FILE_LE) && - *(char *)req->Buffer == '\\') { - pr_err("not allow directory name included leading slash\n"); - rc = -EINVAL; - goto err_out2; - } - name = smb2_get_name((char *)req + le16_to_cpu(req->NameOffset), le16_to_cpu(req->NameLength), work->conn->local_nls); if (IS_ERR(name)) { rc = PTR_ERR(name); - if (rc != -ENOMEM) - rc = -ENOENT; name = NULL; goto err_out2; } diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 51b1b0bed616..9e859ba010cf 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -1058,16 +1058,21 @@ int ksmbd_vfs_fqar_lseek(struct ksmbd_file *fp, loff_t start, loff_t length, } int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap, - const struct path *path, char *attr_name) + const struct path *path, char *attr_name, + bool get_write) { int err; - err = mnt_want_write(path->mnt); - if (err) - return err; + if (get_write == true) { + err = mnt_want_write(path->mnt); + if (err) + return err; + } err = vfs_removexattr(idmap, path->dentry, attr_name); - mnt_drop_write(path->mnt); + + if (get_write == true) + mnt_drop_write(path->mnt); return err; } @@ -1380,7 +1385,7 @@ int ksmbd_vfs_remove_sd_xattrs(struct mnt_idmap *idmap, const struct path *path) ksmbd_debug(SMB, "%s, len %zd\n", name, strlen(name)); if (!strncmp(name, XATTR_NAME_SD, XATTR_NAME_SD_LEN)) { - err = ksmbd_vfs_remove_xattr(idmap, path, name); + err = ksmbd_vfs_remove_xattr(idmap, path, name, true); if (err) ksmbd_debug(SMB, "remove xattr failed : %s\n", name); } diff --git a/fs/smb/server/vfs.h b/fs/smb/server/vfs.h index cfe1c8092f23..cb76f4b5bafe 100644 --- a/fs/smb/server/vfs.h +++ b/fs/smb/server/vfs.h @@ -114,7 +114,8 @@ int ksmbd_vfs_setxattr(struct mnt_idmap *idmap, int ksmbd_vfs_xattr_stream_name(char *stream_name, char **xattr_stream_name, size_t *xattr_stream_name_size, int s_type); int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap, - const struct path *path, char *attr_name); + const struct path *path, char *attr_name, + bool get_write); int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, unsigned int flags, struct path *parent_path, struct path *path, bool caseless); diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 6cb599cd287e..8b2e37c8716e 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -254,7 +254,8 @@ static void __ksmbd_inode_close(struct ksmbd_file *fp) ci->m_flags &= ~S_DEL_ON_CLS_STREAM; err = ksmbd_vfs_remove_xattr(file_mnt_idmap(filp), &filp->f_path, - fp->stream.name); + fp->stream.name, + true); if (err) pr_err("remove xattr failed : %s\n", fp->stream.name); diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 09e4bf949bf8..6b56f0f6d4c1 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -1038,11 +1038,12 @@ xfs_log_sb( * and hence we don't need have to update it here. */ if (xfs_has_lazysbcount(mp)) { - mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount); + mp->m_sb.sb_icount = percpu_counter_sum_positive(&mp->m_icount); mp->m_sb.sb_ifree = min_t(uint64_t, - percpu_counter_sum(&mp->m_ifree), + percpu_counter_sum_positive(&mp->m_ifree), mp->m_sb.sb_icount); - mp->m_sb.sb_fdblocks = percpu_counter_sum(&mp->m_fdblocks); + mp->m_sb.sb_fdblocks = + percpu_counter_sum_positive(&mp->m_fdblocks); } xfs_sb_to_disk(bp->b_addr, &mp->m_sb); diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 58fb7a5062e1..f36091e1e7f5 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2548,11 +2548,26 @@ xfs_ifree_cluster( * This buffer may not have been correctly initialised as we * didn't read it from disk. That's not important because we are * only using to mark the buffer as stale in the log, and to - * attach stale cached inodes on it. That means it will never be - * dispatched for IO. If it is, we want to know about it, and we - * want it to fail. We can acheive this by adding a write - * verifier to the buffer. + * attach stale cached inodes on it. + * + * For the inode that triggered the cluster freeing, this + * attachment may occur in xfs_inode_item_precommit() after we + * have marked this buffer stale. If this buffer was not in + * memory before xfs_ifree_cluster() started, it will not be + * marked XBF_DONE and this will cause problems later in + * xfs_inode_item_precommit() when we trip over a (stale, !done) + * buffer to attached to the transaction. + * + * Hence we have to mark the buffer as XFS_DONE here. This is + * safe because we are also marking the buffer as XBF_STALE and + * XFS_BLI_STALE. That means it will never be dispatched for + * IO and it won't be unlocked until the cluster freeing has + * been committed to the journal and the buffer unpinned. If it + * is written, we want to know about it, and we want it to + * fail. We can acheive this by adding a write verifier to the + * buffer. */ + bp->b_flags |= XBF_DONE; bp->b_ops = &xfs_inode_buf_ops; /* diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 94d0fc3bd412..80dc36f9d527 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -663,6 +663,10 @@ ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_adr_space_type space_id)) ACPI_EXTERNAL_RETURN_STATUS(acpi_status + acpi_execute_orphan_reg_method(acpi_handle device, + acpi_adr_space_type + space_id)) +ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_remove_address_space_handler(acpi_handle device, acpi_adr_space_type diff --git a/include/dt-bindings/net/ti-dp83867.h b/include/dt-bindings/net/ti-dp83867.h index 6fc4b445d3a1..b8a4f3ff4a3b 100644 --- a/include/dt-bindings/net/ti-dp83867.h +++ b/include/dt-bindings/net/ti-dp83867.h @@ -1,10 +1,10 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0-only OR MIT */ /* * Device Tree constants for the Texas Instruments DP83867 PHY * * Author: Dan Murphy <[email protected]> * - * Copyright: (C) 2015 Texas Instruments, Inc. + * Copyright (C) 2015-2024 Texas Instruments Incorporated - https://www.ti.com/ */ #ifndef _DT_BINDINGS_TI_DP83867_H diff --git a/include/dt-bindings/net/ti-dp83869.h b/include/dt-bindings/net/ti-dp83869.h index 218b1a64e975..917114aad7d0 100644 --- a/include/dt-bindings/net/ti-dp83869.h +++ b/include/dt-bindings/net/ti-dp83869.h @@ -1,10 +1,10 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0-only OR MIT */ /* * Device Tree constants for the Texas Instruments DP83869 PHY * * Author: Dan Murphy <[email protected]> * - * Copyright: (C) 2019 Texas Instruments, Inc. + * Copyright (C) 2015-2024 Texas Instruments Incorporated - https://www.ti.com/ */ #ifndef _DT_BINDINGS_TI_DP83869_H diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index 956bcba5dbf2..2f9d36b72bd8 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -2242,7 +2242,7 @@ raw_atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) /** * raw_atomic_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: int value to add + * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -4368,7 +4368,7 @@ raw_atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) /** * raw_atomic64_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: s64 value to add + * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -4690,4 +4690,4 @@ raw_atomic64_dec_if_positive(atomic64_t *v) } #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// 14850c0b0db20c62fdc78ccd1d42b98b88d76331 +// b565db590afeeff0d7c9485ccbca5bb6e155749f diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index debd487fe971..9409a6ddf3e0 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -1349,7 +1349,7 @@ atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) /** * atomic_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: int value to add + * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -2927,7 +2927,7 @@ atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) /** * atomic64_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: s64 value to add + * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -4505,7 +4505,7 @@ atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) /** * atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: long value to add + * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -5050,4 +5050,4 @@ atomic_long_dec_if_positive(atomic_long_t *v) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// ce5b65e0f1f8a276268b667194581d24bed219d4 +// 8829b337928e9508259079d32581775ececd415b diff --git a/include/linux/atomic/atomic-long.h b/include/linux/atomic/atomic-long.h index 3ef844b3ab8a..f86b29d90877 100644 --- a/include/linux/atomic/atomic-long.h +++ b/include/linux/atomic/atomic-long.h @@ -1535,7 +1535,7 @@ raw_atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) /** * raw_atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: long value to add + * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -1809,4 +1809,4 @@ raw_atomic_long_dec_if_positive(atomic_long_t *v) } #endif /* _LINUX_ATOMIC_LONG_H */ -// 1c4a26fc77f345342953770ebe3c4d08e7ce2f9a +// eadf183c3600b8b92b91839dd3be6bcc560c752d diff --git a/include/linux/bio.h b/include/linux/bio.h index d5379548d684..818e93612947 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -731,6 +731,7 @@ static inline bool bioset_initialized(struct bio_set *bs) bip_for_each_vec(_bvl, _bio->bi_integrity, _iter) int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t len, u32 seed); +void bio_integrity_unmap_free_user(struct bio *bio); extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int); extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int); extern bool bio_integrity_prep(struct bio *); @@ -807,6 +808,9 @@ static inline int bio_integrity_map_user(struct bio *bio, void __user *ubuf, { return -EINVAL; } +static inline void bio_integrity_unmap_free_user(struct bio *bio) +{ +} #endif /* CONFIG_BLK_DEV_INTEGRITY */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 50aa87f8d77f..e4070fb02b11 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -746,6 +746,8 @@ struct bpf_verifier_env { /* Same as scratched_regs but for stack slots */ u64 scratched_stack_slots; u64 prev_log_pos, prev_insn_print_pos; + /* buffer used to temporary hold constants as scalar registers */ + struct bpf_reg_state fake_reg[2]; /* buffer used to generate temporary string representations, * e.g., in reg_type_str() to generate reg_type string */ diff --git a/include/linux/btf.h b/include/linux/btf.h index f9e56fd12a9f..7c3e40c3295e 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -82,7 +82,7 @@ * as to avoid issues such as the compiler inlining or eliding either a static * kfunc, or a global kfunc in an LTO build. */ -#define __bpf_kfunc __used noinline +#define __bpf_kfunc __used __retain noinline #define __bpf_kfunc_start_defs() \ __diag_push(); \ diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 98c6fd0b39b6..fdfb61ccf55a 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -77,7 +77,7 @@ struct cdrom_device_ops { unsigned int clearing, int slot); int (*tray_move) (struct cdrom_device_info *, int); int (*lock_door) (struct cdrom_device_info *, int); - int (*select_speed) (struct cdrom_device_info *, int); + int (*select_speed) (struct cdrom_device_info *, unsigned long); int (*get_last_session) (struct cdrom_device_info *, struct cdrom_multisession *); int (*get_mcn) (struct cdrom_device_info *, diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 93600de3800b..f14c275950b5 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -143,6 +143,29 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } # define __preserve_most #endif +/* + * Annotating a function/variable with __retain tells the compiler to place + * the object in its own section and set the flag SHF_GNU_RETAIN. This flag + * instructs the linker to retain the object during garbage-cleanup or LTO + * phases. + * + * Note that the __used macro is also used to prevent functions or data + * being optimized out, but operates at the compiler/IR-level and may still + * allow unintended removal of objects during linking. + * + * Optional: only supported since gcc >= 11, clang >= 13 + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-retain-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#retain + */ +#if __has_attribute(__retain__) && \ + (defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || \ + defined(CONFIG_LTO_CLANG)) +# define __retain __attribute__((__retain__)) +#else +# define __retain +#endif + /* Compiler specific macros. */ #ifdef __clang__ #include <linux/compiler-clang.h> diff --git a/include/linux/device.h b/include/linux/device.h index fc3bd7116ab9..ace039151cb8 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1220,8 +1220,6 @@ static inline void device_remove_group(struct device *dev, return device_remove_groups(dev, groups); } -int __must_check devm_device_add_groups(struct device *dev, - const struct attribute_group **groups); int __must_check devm_device_add_group(struct device *dev, const struct attribute_group *grp); diff --git a/include/linux/dim.h b/include/linux/dim.h index f343bc9aa2ec..1b581ff25a15 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -10,6 +10,15 @@ #include <linux/types.h> #include <linux/workqueue.h> +struct net_device; + +/* Number of DIM profiles and period mode. */ +#define NET_DIM_PARAMS_NUM_PROFILES 5 +#define NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE 256 +#define NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE 128 +#define NET_DIM_DEF_PROFILE_CQE 1 +#define NET_DIM_DEF_PROFILE_EQE 1 + /* * Number of events between DIM iterations. * Causes a moderation of the algorithm run. @@ -38,12 +47,45 @@ * @pkts: CQ packet counter suggestion (by DIM) * @comps: Completion counter * @cq_period_mode: CQ period count mode (from CQE/EQE) + * @rcu: for asynchronous kfree_rcu */ struct dim_cq_moder { u16 usec; u16 pkts; u16 comps; u8 cq_period_mode; + struct rcu_head rcu; +}; + +#define DIM_PROFILE_RX BIT(0) /* support rx profile modification */ +#define DIM_PROFILE_TX BIT(1) /* support tx profile modification */ + +#define DIM_COALESCE_USEC BIT(0) /* support usec field modification */ +#define DIM_COALESCE_PKTS BIT(1) /* support pkts field modification */ +#define DIM_COALESCE_COMPS BIT(2) /* support comps field modification */ + +/** + * struct dim_irq_moder - Structure for irq moderation information. + * Used to collect irq moderation related information. + * + * @profile_flags: DIM_PROFILE_* + * @coal_flags: DIM_COALESCE_* for Rx and Tx + * @dim_rx_mode: Rx DIM period count mode: CQE or EQE + * @dim_tx_mode: Tx DIM period count mode: CQE or EQE + * @rx_profile: DIM profile list for Rx + * @tx_profile: DIM profile list for Tx + * @rx_dim_work: Rx DIM worker scheduled by net_dim() + * @tx_dim_work: Tx DIM worker scheduled by net_dim() + */ +struct dim_irq_moder { + u8 profile_flags; + u8 coal_flags; + u8 dim_rx_mode; + u8 dim_tx_mode; + struct dim_cq_moder __rcu *rx_profile; + struct dim_cq_moder __rcu *tx_profile; + void (*rx_dim_work)(struct work_struct *work); + void (*tx_dim_work)(struct work_struct *work); }; /** @@ -192,6 +234,77 @@ enum dim_step_result { }; /** + * net_dim_init_irq_moder - collect information to initialize irq moderation + * @dev: target network device + * @profile_flags: Rx or Tx profile modification capability + * @coal_flags: irq moderation params flags + * @rx_mode: CQ period mode for Rx + * @tx_mode: CQ period mode for Tx + * @rx_dim_work: Rx worker called after dim decision + * @tx_dim_work: Tx worker called after dim decision + * + * Return: 0 on success or a negative error code. + */ +int net_dim_init_irq_moder(struct net_device *dev, u8 profile_flags, + u8 coal_flags, u8 rx_mode, u8 tx_mode, + void (*rx_dim_work)(struct work_struct *work), + void (*tx_dim_work)(struct work_struct *work)); + +/** + * net_dim_free_irq_moder - free fields for irq moderation + * @dev: target network device + */ +void net_dim_free_irq_moder(struct net_device *dev); + +/** + * net_dim_setting - initialize DIM's cq mode and schedule worker + * @dev: target network device + * @dim: DIM context + * @is_tx: true indicates the tx direction, false indicates the rx direction + */ +void net_dim_setting(struct net_device *dev, struct dim *dim, bool is_tx); + +/** + * net_dim_work_cancel - synchronously cancel dim's worker + * @dim: DIM context + */ +void net_dim_work_cancel(struct dim *dim); + +/** + * net_dim_get_rx_irq_moder - get DIM rx results based on profile_ix + * @dev: target network device + * @dim: DIM context + * + * Return: DIM irq moderation + */ +struct dim_cq_moder +net_dim_get_rx_irq_moder(struct net_device *dev, struct dim *dim); + +/** + * net_dim_get_tx_irq_moder - get DIM tx results based on profile_ix + * @dev: target network device + * @dim: DIM context + * + * Return: DIM irq moderation + */ +struct dim_cq_moder +net_dim_get_tx_irq_moder(struct net_device *dev, struct dim *dim); + +/** + * net_dim_set_rx_mode - set DIM rx cq mode + * @dev: target network device + * @rx_mode: target rx cq mode + */ +void net_dim_set_rx_mode(struct net_device *dev, u8 rx_mode); + +/** + * net_dim_set_tx_mode - set DIM tx cq mode + * @dev: target network device + * @tx_mode: target tx cq mode + */ +void net_dim_set_tx_mode(struct net_device *dev, u8 tx_mode); + +/** * dim_on_top - check if current state is a good place to stop (top location) * @dim: DIM context * diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 6fd9107d3cc0..959196af7f5a 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -284,7 +284,9 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, #define ETHTOOL_COALESCE_TX_AGGR_MAX_BYTES BIT(24) #define ETHTOOL_COALESCE_TX_AGGR_MAX_FRAMES BIT(25) #define ETHTOOL_COALESCE_TX_AGGR_TIME_USECS BIT(26) -#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(26, 0) +#define ETHTOOL_COALESCE_RX_PROFILE BIT(27) +#define ETHTOOL_COALESCE_TX_PROFILE BIT(28) +#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(28, 0) #define ETHTOOL_COALESCE_USECS \ (ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_TX_USECS) diff --git a/include/linux/filter.h b/include/linux/filter.h index b02aea291b7e..c0349522de8f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -733,21 +733,101 @@ struct bpf_nh_params { }; }; +/* flags for bpf_redirect_info kern_flags */ +#define BPF_RI_F_RF_NO_DIRECT BIT(0) /* no napi_direct on return_frame */ +#define BPF_RI_F_RI_INIT BIT(1) +#define BPF_RI_F_CPU_MAP_INIT BIT(2) +#define BPF_RI_F_DEV_MAP_INIT BIT(3) +#define BPF_RI_F_XSK_MAP_INIT BIT(4) + struct bpf_redirect_info { u64 tgt_index; void *tgt_value; struct bpf_map *map; u32 flags; - u32 kern_flags; u32 map_id; enum bpf_map_type map_type; struct bpf_nh_params nh; + u32 kern_flags; }; -DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); +struct bpf_net_context { + struct bpf_redirect_info ri; + struct list_head cpu_map_flush_list; + struct list_head dev_map_flush_list; + struct list_head xskmap_map_flush_list; +}; -/* flags for bpf_redirect_info kern_flags */ -#define BPF_RI_F_RF_NO_DIRECT BIT(0) /* no napi_direct on return_frame */ +static inline struct bpf_net_context *bpf_net_ctx_set(struct bpf_net_context *bpf_net_ctx) +{ + struct task_struct *tsk = current; + + if (tsk->bpf_net_context != NULL) + return NULL; + bpf_net_ctx->ri.kern_flags = 0; + + tsk->bpf_net_context = bpf_net_ctx; + return bpf_net_ctx; +} + +static inline void bpf_net_ctx_clear(struct bpf_net_context *bpf_net_ctx) +{ + if (bpf_net_ctx) + current->bpf_net_context = NULL; +} + +static inline struct bpf_net_context *bpf_net_ctx_get(void) +{ + return current->bpf_net_context; +} + +static inline struct bpf_redirect_info *bpf_net_ctx_get_ri(void) +{ + struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); + + if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_RI_INIT)) { + memset(&bpf_net_ctx->ri, 0, offsetof(struct bpf_net_context, ri.nh)); + bpf_net_ctx->ri.kern_flags |= BPF_RI_F_RI_INIT; + } + + return &bpf_net_ctx->ri; +} + +static inline struct list_head *bpf_net_ctx_get_cpu_map_flush_list(void) +{ + struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); + + if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_CPU_MAP_INIT)) { + INIT_LIST_HEAD(&bpf_net_ctx->cpu_map_flush_list); + bpf_net_ctx->ri.kern_flags |= BPF_RI_F_CPU_MAP_INIT; + } + + return &bpf_net_ctx->cpu_map_flush_list; +} + +static inline struct list_head *bpf_net_ctx_get_dev_flush_list(void) +{ + struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); + + if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_DEV_MAP_INIT)) { + INIT_LIST_HEAD(&bpf_net_ctx->dev_map_flush_list); + bpf_net_ctx->ri.kern_flags |= BPF_RI_F_DEV_MAP_INIT; + } + + return &bpf_net_ctx->dev_map_flush_list; +} + +static inline struct list_head *bpf_net_ctx_get_xskmap_flush_list(void) +{ + struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); + + if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_XSK_MAP_INIT)) { + INIT_LIST_HEAD(&bpf_net_ctx->xskmap_map_flush_list); + bpf_net_ctx->ri.kern_flags |= BPF_RI_F_XSK_MAP_INIT; + } + + return &bpf_net_ctx->xskmap_map_flush_list; +} /* Compute the linear packet data range [data, data_end) which * will be accessed by various program types (cls_bpf, act_bpf, @@ -1018,25 +1098,23 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt); -void bpf_clear_redirect_map(struct bpf_map *map); - static inline bool xdp_return_frame_no_direct(void) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); return ri->kern_flags & BPF_RI_F_RF_NO_DIRECT; } static inline void xdp_set_return_frame_no_direct(void) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); ri->kern_flags |= BPF_RI_F_RF_NO_DIRECT; } static inline void xdp_clear_return_frame_no_direct(void) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); ri->kern_flags &= ~BPF_RI_F_RF_NO_DIRECT; } @@ -1592,7 +1670,7 @@ static __always_inline long __bpf_xdp_redirect_map(struct bpf_map *map, u64 inde u64 flags, const u64 flag_mask, void *lookup_elem(struct bpf_map *map, u32 key)) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); const u64 action_mask = XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX; /* Lower bits of the flags are used as return code on lookup failure */ diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index c8d3ec116e29..2aa986a5cd1b 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -269,8 +269,8 @@ enum mthp_stat_item { MTHP_STAT_ANON_FAULT_ALLOC, MTHP_STAT_ANON_FAULT_FALLBACK, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE, - MTHP_STAT_ANON_SWPOUT, - MTHP_STAT_ANON_SWPOUT_FALLBACK, + MTHP_STAT_SWPOUT, + MTHP_STAT_SWPOUT_FALLBACK, __MTHP_STAT_COUNT }; @@ -278,6 +278,7 @@ struct mthp_stat { unsigned long stats[ilog2(MAX_PTRS_PER_PTE) + 1][__MTHP_STAT_COUNT]; }; +#ifdef CONFIG_SYSFS DECLARE_PER_CPU(struct mthp_stat, mthp_stats); static inline void count_mthp_stat(int order, enum mthp_stat_item item) @@ -287,6 +288,11 @@ static inline void count_mthp_stat(int order, enum mthp_stat_item item) this_cpu_inc(mthp_stats.stats[order][item]); } +#else +static inline void count_mthp_stat(int order, enum mthp_stat_item item) +{ +} +#endif #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 9709537370ee..424acb98c7c2 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -960,8 +960,6 @@ int i2c_handle_smbus_host_notify(struct i2c_adapter *adap, unsigned short addr); #define builtin_i2c_driver(__i2c_driver) \ builtin_driver(__i2c_driver, i2c_add_driver) -#endif /* I2C */ - /* must call put_device() when done with returned i2c_client device */ struct i2c_client *i2c_find_device_by_fwnode(struct fwnode_handle *fwnode); @@ -971,6 +969,28 @@ struct i2c_adapter *i2c_find_adapter_by_fwnode(struct fwnode_handle *fwnode); /* must call i2c_put_adapter() when done with returned i2c_adapter device */ struct i2c_adapter *i2c_get_adapter_by_fwnode(struct fwnode_handle *fwnode); +#else /* I2C */ + +static inline struct i2c_client * +i2c_find_device_by_fwnode(struct fwnode_handle *fwnode) +{ + return NULL; +} + +static inline struct i2c_adapter * +i2c_find_adapter_by_fwnode(struct fwnode_handle *fwnode) +{ + return NULL; +} + +static inline struct i2c_adapter * +i2c_get_adapter_by_fwnode(struct fwnode_handle *fwnode) +{ + return NULL; +} + +#endif /* !I2C */ + #if IS_ENABLED(CONFIG_OF) /* must call put_device() when done with returned i2c_client device */ static inline struct i2c_client *of_find_i2c_device_by_node(struct device_node *node) diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 7a6b190c7da7..b48570eaa449 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -648,7 +648,7 @@ struct io_kiocb { struct io_rsrc_node *rsrc_node; atomic_t refs; - atomic_t poll_refs; + bool cancel_seq_set; struct io_task_work io_task_work; /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */ struct hlist_node hash_node; @@ -657,6 +657,7 @@ struct io_kiocb { /* opcode allocated if it needs to store data for async defer */ void *async_data; /* linked requests, IFF REQ_F_HARDLINK or REQ_F_LINK are set */ + atomic_t poll_refs; struct io_kiocb *link; /* custom credentials, valid IFF REQ_F_CREDS is set */ const struct cred *creds; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 7bc8dff7cf6d..17b3f36ad843 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -1533,7 +1533,7 @@ struct iommu_domain *iommu_sva_domain_alloc(struct device *dev, static inline struct iommu_sva * iommu_sva_bind_device(struct device *dev, struct mm_struct *mm) { - return NULL; + return ERR_PTR(-ENODEV); } static inline void iommu_sva_unbind_device(struct iommu_sva *handle) diff --git a/include/linux/kcov.h b/include/linux/kcov.h index b851ba415e03..75a2fb8b16c3 100644 --- a/include/linux/kcov.h +++ b/include/linux/kcov.h @@ -21,6 +21,8 @@ enum kcov_mode { KCOV_MODE_TRACE_PC = 2, /* Collecting comparison operands mode. */ KCOV_MODE_TRACE_CMP = 3, + /* The process owns a KCOV remote reference. */ + KCOV_MODE_REMOTE = 4, }; #define KCOV_IN_CTXSW (1 << 30) @@ -55,21 +57,47 @@ static inline void kcov_remote_start_usb(u64 id) /* * The softirq flavor of kcov_remote_*() functions is introduced as a temporary - * work around for kcov's lack of nested remote coverage sections support in - * task context. Adding support for nested sections is tracked in: - * https://bugzilla.kernel.org/show_bug.cgi?id=210337 + * workaround for KCOV's lack of nested remote coverage sections support. + * + * Adding support is tracked in https://bugzilla.kernel.org/show_bug.cgi?id=210337. + * + * kcov_remote_start_usb_softirq(): + * + * 1. Only collects coverage when called in the softirq context. This allows + * avoiding nested remote coverage collection sections in the task context. + * For example, USB/IP calls usb_hcd_giveback_urb() in the task context + * within an existing remote coverage collection section. Thus, KCOV should + * not attempt to start collecting coverage within the coverage collection + * section in __usb_hcd_giveback_urb() in this case. + * + * 2. Disables interrupts for the duration of the coverage collection section. + * This allows avoiding nested remote coverage collection sections in the + * softirq context (a softirq might occur during the execution of a work in + * the BH workqueue, which runs with in_serving_softirq() > 0). + * For example, usb_giveback_urb_bh() runs in the BH workqueue with + * interrupts enabled, so __usb_hcd_giveback_urb() might be interrupted in + * the middle of its remote coverage collection section, and the interrupt + * handler might invoke __usb_hcd_giveback_urb() again. */ -static inline void kcov_remote_start_usb_softirq(u64 id) +static inline unsigned long kcov_remote_start_usb_softirq(u64 id) { - if (in_serving_softirq()) + unsigned long flags = 0; + + if (in_serving_softirq()) { + local_irq_save(flags); kcov_remote_start_usb(id); + } + + return flags; } -static inline void kcov_remote_stop_softirq(void) +static inline void kcov_remote_stop_softirq(unsigned long flags) { - if (in_serving_softirq()) + if (in_serving_softirq()) { kcov_remote_stop(); + local_irq_restore(flags); + } } #ifdef CONFIG_64BIT @@ -103,8 +131,11 @@ static inline u64 kcov_common_handle(void) } static inline void kcov_remote_start_common(u64 id) {} static inline void kcov_remote_start_usb(u64 id) {} -static inline void kcov_remote_start_usb_softirq(u64 id) {} -static inline void kcov_remote_stop_softirq(void) {} +static inline unsigned long kcov_remote_start_usb_softirq(u64 id) +{ + return 0; +} +static inline void kcov_remote_stop_softirq(unsigned long flags) {} #endif /* CONFIG_KCOV */ #endif /* _LINUX_KCOV_H */ diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 52c63a9c5a9c..11690dacd986 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -33,16 +33,27 @@ void __ksm_exit(struct mm_struct *mm); */ #define is_ksm_zero_pte(pte) (is_zero_pfn(pte_pfn(pte)) && pte_dirty(pte)) -extern unsigned long ksm_zero_pages; +extern atomic_long_t ksm_zero_pages; + +static inline void ksm_map_zero_page(struct mm_struct *mm) +{ + atomic_long_inc(&ksm_zero_pages); + atomic_long_inc(&mm->ksm_zero_pages); +} static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { if (is_ksm_zero_pte(pte)) { - ksm_zero_pages--; - mm->ksm_zero_pages--; + atomic_long_dec(&ksm_zero_pages); + atomic_long_dec(&mm->ksm_zero_pages); } } +static inline long mm_ksm_zero_pages(struct mm_struct *mm) +{ + return atomic_long_read(&mm->ksm_zero_pages); +} + static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) diff --git a/include/linux/local_lock.h b/include/linux/local_lock.h index e55010fa7329..091dc0b6bdfb 100644 --- a/include/linux/local_lock.h +++ b/include/linux/local_lock.h @@ -51,4 +51,25 @@ #define local_unlock_irqrestore(lock, flags) \ __local_unlock_irqrestore(lock, flags) +DEFINE_GUARD(local_lock, local_lock_t __percpu*, + local_lock(_T), + local_unlock(_T)) +DEFINE_GUARD(local_lock_irq, local_lock_t __percpu*, + local_lock_irq(_T), + local_unlock_irq(_T)) +DEFINE_LOCK_GUARD_1(local_lock_irqsave, local_lock_t __percpu, + local_lock_irqsave(_T->lock, _T->flags), + local_unlock_irqrestore(_T->lock, _T->flags), + unsigned long flags) + +#define local_lock_nested_bh(_lock) \ + __local_lock_nested_bh(_lock) + +#define local_unlock_nested_bh(_lock) \ + __local_unlock_nested_bh(_lock) + +DEFINE_GUARD(local_lock_nested_bh, local_lock_t __percpu*, + local_lock_nested_bh(_T), + local_unlock_nested_bh(_T)) + #endif diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index 975e33b793a7..8dd71fbbb6d2 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -62,6 +62,17 @@ do { \ local_lock_debug_init(lock); \ } while (0) +#define __spinlock_nested_bh_init(lock) \ +do { \ + static struct lock_class_key __key; \ + \ + debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ + lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, \ + 0, LD_WAIT_CONFIG, LD_WAIT_INV, \ + LD_LOCK_NORMAL); \ + local_lock_debug_init(lock); \ +} while (0) + #define __local_lock(lock) \ do { \ preempt_disable(); \ @@ -98,6 +109,15 @@ do { \ local_irq_restore(flags); \ } while (0) +#define __local_lock_nested_bh(lock) \ + do { \ + lockdep_assert_in_softirq(); \ + local_lock_acquire(this_cpu_ptr(lock)); \ + } while (0) + +#define __local_unlock_nested_bh(lock) \ + local_lock_release(this_cpu_ptr(lock)) + #else /* !CONFIG_PREEMPT_RT */ /* @@ -138,4 +158,15 @@ typedef spinlock_t local_lock_t; #define __local_unlock_irqrestore(lock, flags) __local_unlock(lock) +#define __local_lock_nested_bh(lock) \ +do { \ + lockdep_assert_in_softirq_func(); \ + spin_lock(this_cpu_ptr(lock)); \ +} while (0) + +#define __local_unlock_nested_bh(lock) \ +do { \ + spin_unlock(this_cpu_ptr((lock))); \ +} while (0) + #endif /* CONFIG_PREEMPT_RT */ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 5e51b0de4c4b..3f5a551579cc 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -297,9 +297,6 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); .wait_type_inner = _wait_type, \ .lock_type = LD_LOCK_WAIT_OVERRIDE, } -#define lock_map_assert_held(l) \ - lockdep_assert(lock_is_held(l) != LOCK_STATE_NOT_HELD) - #else /* !CONFIG_LOCKDEP */ static inline void lockdep_init_task(struct task_struct *task) @@ -391,8 +388,6 @@ extern int lockdep_is_held(const void *); #define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type) \ struct lockdep_map __maybe_unused _name = {} -#define lock_map_assert_held(l) do { (void)(l); } while (0) - #endif /* !LOCKDEP */ #ifdef CONFIG_PROVE_LOCKING @@ -605,6 +600,8 @@ do { \ (!in_softirq() || in_irq() || in_nmi())); \ } while (0) +extern void lockdep_assert_in_softirq_func(void); + #else # define might_lock(lock) do { } while (0) # define might_lock_read(lock) do { } while (0) @@ -618,6 +615,7 @@ do { \ # define lockdep_assert_preemption_enabled() do { } while (0) # define lockdep_assert_preemption_disabled() do { } while (0) # define lockdep_assert_in_softirq() do { } while (0) +# define lockdep_assert_in_softirq_func() do { } while (0) #endif #ifdef CONFIG_PROVE_RAW_LOCK_NESTING diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index f804b76cde44..44488b1ab9a9 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -413,7 +413,7 @@ LSM_HOOK(void, LSM_RET_VOID, key_post_create_or_update, struct key *keyring, #ifdef CONFIG_AUDIT LSM_HOOK(int, 0, audit_rule_init, u32 field, u32 op, char *rulestr, - void **lsmrule) + void **lsmrule, gfp_t gfp) LSM_HOOK(int, 0, audit_rule_known, struct audit_krule *krule) LSM_HOOK(int, 0, audit_rule_match, u32 secid, u32 field, u32 op, void *lsmrule) LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 17acd0f3ca8e..66b921c81c0f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1093,7 +1093,8 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 tunnel_stateless_ip_over_ip_tx[0x1]; u8 reserved_at_2e[0x2]; u8 max_vxlan_udp_ports[0x8]; - u8 reserved_at_38[0x6]; + u8 swp_csum_l4_partial[0x1]; + u8 reserved_at_39[0x5]; u8 max_geneve_opt_len[0x1]; u8 tunnel_stateless_geneve_rx[0x1]; @@ -3914,7 +3915,7 @@ enum { }; enum { - ELEMENT_TYPE_CAP_MASK_TASR = 1 << 0, + ELEMENT_TYPE_CAP_MASK_TSAR = 1 << 0, ELEMENT_TYPE_CAP_MASK_VPORT = 1 << 1, ELEMENT_TYPE_CAP_MASK_VPORT_TC = 1 << 2, ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC = 1 << 3, diff --git a/include/linux/mm.h b/include/linux/mm.h index 9849dfda44d4..eb7c96d24ac0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -406,6 +406,11 @@ extern unsigned int kobjsize(const void *objp); #define VM_ALLOW_ANY_UNCACHED VM_NONE #endif +#ifdef CONFIG_64BIT +/* VM is sealed, in vm_flags */ +#define VM_SEALED _BITUL(63) +#endif + /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY) @@ -3776,14 +3781,7 @@ DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free); static inline bool want_init_on_free(void) { return static_branch_maybe(CONFIG_INIT_ON_FREE_DEFAULT_ON, - &init_on_free); -} - -DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON, init_mlocked_on_free); -static inline bool want_init_mlocked_on_free(void) -{ - return static_branch_maybe(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON, - &init_mlocked_on_free); + &init_on_free); } extern bool _debug_pagealloc_enabled_early; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 24323c7d0bd4..af3a0256fa93 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -985,7 +985,7 @@ struct mm_struct { * Represent how many empty pages are merged with kernel zero * pages when enabling KSM use_zero_pages. */ - unsigned long ksm_zero_pages; + atomic_long_t ksm_zero_pages; #endif /* CONFIG_KSM */ #ifdef CONFIG_LRU_GEN_WALKS_MMU struct { diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 8f9c9590a42c..586a8f0104d7 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -654,13 +654,12 @@ enum zone_watermarks { }; /* - * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. One additional list - * for THP which will usually be GFP_MOVABLE. Even if it is another type, - * it should not contribute to serious fragmentation causing THP allocation - * failures. + * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. Two additional lists + * are added for THP. One PCP list is used by GPF_MOVABLE, and the other PCP list + * is used by GFP_UNMOVABLE and GFP_RECLAIMABLE. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define NR_PCP_THP 1 +#define NR_PCP_THP 2 #else #define NR_PCP_THP 0 #endif diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d20c6c99eb88..cc18acd3c58b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -43,6 +43,7 @@ #include <linux/netdev_features.h> #include <linux/neighbour.h> +#include <linux/netdevice_xmit.h> #include <uapi/linux/netdevice.h> #include <uapi/linux/if_bonding.h> #include <uapi/linux/pkt_cls.h> @@ -2401,6 +2402,9 @@ struct net_device { /** @page_pools: page pools created for this netdevice */ struct hlist_head page_pools; #endif + + /** @irq_moder: dim parameters used if IS_ENABLED(CONFIG_DIMLIB). */ + struct dim_irq_moder *irq_moder; }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -2731,12 +2735,12 @@ struct pcpu_sw_netstats { } __aligned(4 * sizeof(u64)); struct pcpu_dstats { - u64 rx_packets; - u64 rx_bytes; - u64 rx_drops; - u64 tx_packets; - u64 tx_bytes; - u64 tx_drops; + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t rx_drops; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; + u64_stats_t tx_drops; struct u64_stats_sync syncp; } __aligned(8 * sizeof(u64)); @@ -3021,7 +3025,8 @@ int call_netdevice_notifiers_info(unsigned long val, #define net_device_entry(lh) list_entry(lh, struct net_device, dev_list) #define for_each_netdev_dump(net, d, ifindex) \ - xa_for_each_start(&(net)->dev_by_index, (ifindex), (d), (ifindex)) + for (; (d = xa_find(&(net)->dev_by_index, &ifindex, \ + ULONG_MAX, XA_PRESENT)); ifindex++) static inline struct net_device *next_net_device(struct net_device *dev) { @@ -3200,6 +3205,7 @@ static inline bool dev_has_header(const struct net_device *dev) struct softnet_data { struct list_head poll_list; struct sk_buff_head process_queue; + local_lock_t process_queue_bh_lock; /* stats */ unsigned int processed; @@ -3222,13 +3228,7 @@ struct softnet_data { struct sk_buff_head xfrm_backlog; #endif /* written and read only by owning cpu: */ - struct { - u16 recursion; - u8 more; -#ifdef CONFIG_NET_EGRESS - u8 skip_txqueue; -#endif - } xmit; + struct netdev_xmit xmit; #ifdef CONFIG_RPS /* input_queue_head should be written by cpu owning this struct, * and only read by other cpus. Worth using a cache line. @@ -3256,10 +3256,18 @@ struct softnet_data { DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); +#ifndef CONFIG_PREEMPT_RT static inline int dev_recursion_level(void) { return this_cpu_read(softnet_data.xmit.recursion); } +#else +static inline int dev_recursion_level(void) +{ + return current->net_xmit.recursion; +} + +#endif void __netif_schedule(struct Qdisc *q); void netif_schedule_queue(struct netdev_queue *txq); @@ -3903,9 +3911,6 @@ int generic_hwtstamp_get_lower(struct net_device *dev, int generic_hwtstamp_set_lower(struct net_device *dev, struct kernel_hwtstamp_config *kernel_cfg, struct netlink_ext_ack *extack); -int dev_set_hwtstamp_phylib(struct net_device *dev, - struct kernel_hwtstamp_config *cfg, - struct netlink_ext_ack *extack); int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata); unsigned int dev_get_flags(const struct net_device *); int __dev_change_flags(struct net_device *dev, unsigned int flags, @@ -4874,18 +4879,35 @@ static inline ktime_t netdev_get_tstamp(struct net_device *dev, return hwtstamps->hwtstamp; } -static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, - struct sk_buff *skb, struct net_device *dev, - bool more) +#ifndef CONFIG_PREEMPT_RT +static inline void netdev_xmit_set_more(bool more) { __this_cpu_write(softnet_data.xmit.more, more); - return ops->ndo_start_xmit(skb, dev); } static inline bool netdev_xmit_more(void) { return __this_cpu_read(softnet_data.xmit.more); } +#else +static inline void netdev_xmit_set_more(bool more) +{ + current->net_xmit.more = more; +} + +static inline bool netdev_xmit_more(void) +{ + return current->net_xmit.more; +} +#endif + +static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, + struct sk_buff *skb, struct net_device *dev, + bool more) +{ + netdev_xmit_set_more(more); + return ops->ndo_start_xmit(skb, dev); +} static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, bool more) diff --git a/include/linux/netdevice_xmit.h b/include/linux/netdevice_xmit.h new file mode 100644 index 000000000000..38325e070296 --- /dev/null +++ b/include/linux/netdevice_xmit.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_NETDEVICE_XMIT_H +#define _LINUX_NETDEVICE_XMIT_H + +struct netdev_xmit { + u16 recursion; + u8 more; +#ifdef CONFIG_NET_EGRESS + u8 skip_txqueue; +#endif +}; + +#endif diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 3ca3906bb8da..5d0288938cc2 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -521,7 +521,7 @@ static inline struct fscache_cookie *netfs_i_cookie(struct netfs_inode *ctx) /** * netfs_wait_for_outstanding_io - Wait for outstanding I/O to complete - * @ctx: The netfs inode to wait on + * @inode: The netfs inode to wait on * * Wait for outstanding I/O requests of any type to complete. This is intended * to be called from inode eviction routines. This makes sure that any diff --git a/include/linux/numa.h b/include/linux/numa.h index 1d43371fafd2..eb19503604fe 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -15,6 +15,11 @@ #define NUMA_NO_NODE (-1) #define NUMA_NO_MEMBLK (-1) +static inline bool numa_valid_node(int nid) +{ + return nid >= 0 && nid < MAX_NUMNODES; +} + /* optionally keep NUMA memory info available post init */ #ifdef CONFIG_NUMA_KEEP_MEMINFO #define __initdata_or_meminfo diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 104078afe0b1..b9e914e1face 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -944,15 +944,18 @@ PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) * mistaken for a page type value. */ -#define PAGE_TYPE_BASE 0xf0000000 -/* Reserve 0x0000007f to catch underflows of _mapcount */ -#define PAGE_MAPCOUNT_RESERVE -128 -#define PG_buddy 0x00000080 -#define PG_offline 0x00000100 -#define PG_table 0x00000200 -#define PG_guard 0x00000400 -#define PG_hugetlb 0x00000800 -#define PG_slab 0x00001000 +enum pagetype { + PG_buddy = 0x00000080, + PG_offline = 0x00000100, + PG_table = 0x00000200, + PG_guard = 0x00000400, + PG_hugetlb = 0x00000800, + PG_slab = 0x00001000, + + PAGE_TYPE_BASE = 0xf0000000, + /* Reserve 0x0000007f to catch underflows of _mapcount */ + PAGE_MAPCOUNT_RESERVE = -128, +}; #define PageType(page, flag) \ ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ee633712bba0..59f1df0cde5a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -381,6 +381,10 @@ static inline void mapping_set_large_folios(struct address_space *mapping) */ static inline bool mapping_large_folio_support(struct address_space *mapping) { + /* AS_LARGE_FOLIO_SUPPORT is only reasonable for pagecache folios */ + VM_WARN_ONCE((unsigned long)mapping & PAGE_MAPPING_ANON, + "Anonymous mapping always supports large folio"); + return IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } diff --git a/include/linux/pci.h b/include/linux/pci.h index fb004fd4e889..cafc5ab1cbcb 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -413,8 +413,6 @@ struct pci_dev { struct resource driver_exclusive_resource; /* driver exclusive resource ranges */ bool match_driver; /* Skip attaching driver */ - struct lock_class_key cfg_access_key; - struct lockdep_map cfg_access_lock; unsigned int transparent:1; /* Subtractive decode bridge */ unsigned int io_window:1; /* Bridge has I/O window */ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 942a587bb97e..677aea20d3e1 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2126,6 +2126,8 @@ #define PCI_VENDOR_ID_CHELSIO 0x1425 +#define PCI_VENDOR_ID_EDIMAX 0x1432 + #define PCI_VENDOR_ID_ADLINK 0x144a #define PCI_VENDOR_ID_SAMSUNG 0x144d diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h index 86ba5d33e43b..9cacadbd61f8 100644 --- a/include/linux/pgalloc_tag.h +++ b/include/linux/pgalloc_tag.h @@ -37,6 +37,9 @@ static inline union codetag_ref *get_page_tag_ref(struct page *page) static inline void put_page_tag_ref(union codetag_ref *ref) { + if (WARN_ON(!ref)) + return; + page_ext_put(page_ext_from_codetag_ref(ref)); } @@ -102,9 +105,11 @@ static inline struct alloc_tag *pgalloc_tag_get(struct page *page) union codetag_ref *ref = get_page_tag_ref(page); alloc_tag_sub_check(ref); - if (ref && ref->ct) - tag = ct_to_alloc_tag(ref->ct); - put_page_tag_ref(ref); + if (ref) { + if (ref->ct) + tag = ct_to_alloc_tag(ref->ct); + put_page_tag_ref(ref); + } } return tag; diff --git a/include/linux/phy.h b/include/linux/phy.h index e6e83304558e..205fccfc0f60 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -128,6 +128,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_10GKR: 10GBASE-KR - with Clause 73 AN * @PHY_INTERFACE_MODE_QUSGMII: Quad Universal SGMII * @PHY_INTERFACE_MODE_1000BASEKX: 1000Base-KX - with Clause 73 AN + * @PHY_INTERFACE_MODE_10G_QXGMII: 10G-QXGMII - 4 ports over 10G USXGMII * @PHY_INTERFACE_MODE_MAX: Book keeping * * Describes the interface between the MAC and PHY. @@ -168,6 +169,7 @@ typedef enum { PHY_INTERFACE_MODE_10GKR, PHY_INTERFACE_MODE_QUSGMII, PHY_INTERFACE_MODE_1000BASEKX, + PHY_INTERFACE_MODE_10G_QXGMII, PHY_INTERFACE_MODE_MAX, } phy_interface_t; @@ -289,6 +291,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "100base-x"; case PHY_INTERFACE_MODE_QUSGMII: return "qusgmii"; + case PHY_INTERFACE_MODE_10G_QXGMII: + return "10g-qxgmii"; default: return "unknown"; } diff --git a/include/linux/phylink.h b/include/linux/phylink.h index a30a692acc32..2381e07429a2 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -654,6 +654,7 @@ static inline int phylink_get_link_timer_ns(phy_interface_t interface) case PHY_INTERFACE_MODE_SGMII: case PHY_INTERFACE_MODE_QSGMII: case PHY_INTERFACE_MODE_USXGMII: + case PHY_INTERFACE_MODE_10G_QXGMII: return 1600000; case PHY_INTERFACE_MODE_1000BASEX: diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h index 6d07c95dabb9..6eec24ffa866 100644 --- a/include/linux/pse-pd/pse.h +++ b/include/linux/pse-pd/pse.h @@ -167,14 +167,14 @@ static inline int pse_ethtool_get_status(struct pse_control *psec, struct netlink_ext_ack *extack, struct pse_control_status *status) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int pse_ethtool_set_config(struct pse_control *psec, struct netlink_ext_ack *extack, const struct pse_control_config *config) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline bool pse_has_podl(struct pse_control *psec) diff --git a/include/linux/sched.h b/include/linux/sched.h index 61591ac6eab6..5ff5e65a4627 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -36,6 +36,7 @@ #include <linux/signal_types.h> #include <linux/syscall_user_dispatch_types.h> #include <linux/mm_types_task.h> +#include <linux/netdevice_xmit.h> #include <linux/task_io_accounting.h> #include <linux/posix-timers_types.h> #include <linux/restart_block.h> @@ -53,6 +54,7 @@ struct bio_list; struct blk_plug; struct bpf_local_storage; struct bpf_run_ctx; +struct bpf_net_context; struct capture_control; struct cfs_rq; struct fs_struct; @@ -975,7 +977,9 @@ struct task_struct { /* delay due to memory thrashing */ unsigned in_thrashing:1; #endif - +#ifdef CONFIG_PREEMPT_RT + struct netdev_xmit net_xmit; +#endif unsigned long atomic_flags; /* Flags requiring atomic access. */ struct restart_block restart_block; @@ -1506,6 +1510,8 @@ struct task_struct { /* Used for BPF run context */ struct bpf_run_ctx *bpf_ctx; #endif + /* Used by BPF for per-TASK xdp storage */ + struct bpf_net_context *bpf_net_context; #ifdef CONFIG_GCC_PLUGIN_STACKLEAK unsigned long lowest_stack; diff --git a/include/linux/security.h b/include/linux/security.h index 21cf70346b33..de3af33e6ff5 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2048,7 +2048,8 @@ static inline void security_key_post_create_or_update(struct key *keyring, #ifdef CONFIG_AUDIT #ifdef CONFIG_SECURITY -int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule); +int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule, + gfp_t gfp); int security_audit_rule_known(struct audit_krule *krule); int security_audit_rule_match(u32 secid, u32 field, u32 op, void *lsmrule); void security_audit_rule_free(void *lsmrule); @@ -2056,7 +2057,7 @@ void security_audit_rule_free(void *lsmrule); #else static inline int security_audit_rule_init(u32 field, u32 op, char *rulestr, - void **lsmrule) + void **lsmrule, gfp_t gfp) { return 0; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index fe7d8dbef77e..f4cda3fbdb75 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1251,8 +1251,14 @@ static inline bool skb_data_unref(const struct sk_buff *skb, return true; } -void __fix_address -kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason); +void __fix_address sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb, + enum skb_drop_reason reason); + +static inline void +kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) +{ + sk_skb_reason_drop(NULL, skb, reason); +} /** * kfree_skb - free an sk_buff with 'NOT_SPECIFIED' reason @@ -1498,8 +1504,14 @@ __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4) __skb_set_hash(skb, hash, true, is_l4); } -void __skb_get_hash(struct sk_buff *skb); -u32 __skb_get_hash_symmetric(const struct sk_buff *skb); +u32 __skb_get_hash_symmetric_net(const struct net *net, const struct sk_buff *skb); + +static inline u32 __skb_get_hash_symmetric(const struct sk_buff *skb) +{ + return __skb_get_hash_symmetric_net(NULL, skb); +} + +void __skb_get_hash_net(const struct net *net, struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, const void *data, const struct flow_keys_basic *keys, int hlen); @@ -1578,10 +1590,18 @@ void skb_flow_dissect_hash(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); +static inline __u32 skb_get_hash_net(const struct net *net, struct sk_buff *skb) +{ + if (!skb->l4_hash && !skb->sw_hash) + __skb_get_hash_net(net, skb); + + return skb->hash; +} + static inline __u32 skb_get_hash(struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) - __skb_get_hash(skb); + __skb_get_hash_net(NULL, skb); return skb->hash; } diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index e8e1e798924f..98fdef6e28f2 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -1085,12 +1085,13 @@ struct spi_transfer { unsigned dummy_data:1; unsigned cs_off:1; unsigned cs_change:1; - unsigned tx_nbits:3; - unsigned rx_nbits:3; + unsigned tx_nbits:4; + unsigned rx_nbits:4; unsigned timestamped:1; #define SPI_NBITS_SINGLE 0x01 /* 1-bit transfer */ #define SPI_NBITS_DUAL 0x02 /* 2-bit transfer */ #define SPI_NBITS_QUAD 0x04 /* 4-bit transfer */ +#define SPI_NBITS_OCTAL 0x08 /* 8-bit transfer */ u8 bits_per_word; struct spi_delay delay; struct spi_delay cs_change_delay; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 8f0f156d50d3..9c54f82901a1 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -13,7 +13,7 @@ #define __STMMAC_PLATFORM_DATA #include <linux/platform_device.h> -#include <linux/phy.h> +#include <linux/phylink.h> #define MTL_MAX_RX_QUEUES 8 #define MTL_MAX_TX_QUEUES 8 @@ -271,6 +271,8 @@ struct plat_stmmacenet_data { void (*dump_debug_regs)(void *priv); int (*pcs_init)(struct stmmac_priv *priv); void (*pcs_exit)(struct stmmac_priv *priv); + struct phylink_pcs *(*select_pcs)(struct stmmac_priv *priv, + phy_interface_t interface); void *bsp_priv; struct clk *stmmac_clk; struct clk *pclk; diff --git a/include/linux/string.h b/include/linux/string.h index 60168aa2af07..9edace076ddb 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -289,7 +289,7 @@ extern void *kmemdup_noprof(const void *src, size_t len, gfp_t gfp) __realloc_si extern void *kvmemdup(const void *src, size_t len, gfp_t gfp) __realloc_size(2); extern char *kmemdup_nul(const char *s, size_t len, gfp_t gfp); -extern void *kmemdup_array(const void *src, size_t element_size, size_t count, gfp_t gfp) +extern void *kmemdup_array(const void *src, size_t count, size_t element_size, gfp_t gfp) __realloc_size(2, 3); /* lib/argv_split.c */ diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index a7d725fbf739..c4e64dc11206 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -750,6 +750,15 @@ static inline int sysfs_emit_at(char *buf, int at, const char *fmt, ...) { return 0; } + +static inline ssize_t sysfs_bin_attr_simple_read(struct file *file, + struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t off, + size_t count) +{ + return 0; +} #endif /* CONFIG_SYSFS */ static inline int __must_check sysfs_create_file(struct kobject *kobj, diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 8b1a29820409..000a6cab2d31 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -64,6 +64,7 @@ struct vfio_device { struct completion comp; struct iommufd_access *iommufd_access; void (*put_kvm)(struct kvm *kvm); + struct inode *inode; #if IS_ENABLED(CONFIG_IOMMUFD) struct iommufd_device *iommufd_device; u8 iommufd_attached:1; diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index a2c8b8bba711..f87067438ed4 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -93,8 +93,6 @@ struct vfio_pci_core_device { struct list_head sriov_pfs_item; struct vfio_pci_core_device *sriov_pf_core_dev; struct notifier_block nb; - struct mutex vma_lock; - struct list_head vma_list; struct rw_semaphore memory_lock; }; diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index fb3993894536..d9968bfc8eac 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -95,7 +95,7 @@ enum wq_misc_consts { WORK_BUSY_RUNNING = 1 << 1, /* maximum string length for set_worker_desc() */ - WORKER_DESC_LEN = 24, + WORKER_DESC_LEN = 32, }; /* Convenience constants - of type 'unsigned long', not 'enum'! */ diff --git a/include/net/af_unix.h b/include/net/af_unix.h index b6eedf7650da..63129c79b8cb 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -96,20 +96,6 @@ struct unix_sock { #define unix_state_lock(s) spin_lock(&unix_sk(s)->lock) #define unix_state_unlock(s) spin_unlock(&unix_sk(s)->lock) -enum unix_socket_lock_class { - U_LOCK_NORMAL, - U_LOCK_SECOND, /* for double locking, see unix_state_double_lock(). */ - U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */ - U_LOCK_GC_LISTENER, /* used for listening socket while determining gc - * candidates to close a small race window. - */ -}; - -static inline void unix_state_lock_nested(struct sock *sk, - enum unix_socket_lock_class subclass) -{ - spin_lock_nested(&unix_sk(sk)->lock, subclass); -} #define peer_wait peer_wq.wait diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 9231396fe96f..c43716edf205 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -2113,18 +2113,46 @@ static inline int hci_check_conn_params(u16 min, u16 max, u16 latency, { u16 max_latency; - if (min > max || min < 6 || max > 3200) + if (min > max) { + BT_WARN("min %d > max %d", min, max); return -EINVAL; + } + + if (min < 6) { + BT_WARN("min %d < 6", min); + return -EINVAL; + } + + if (max > 3200) { + BT_WARN("max %d > 3200", max); + return -EINVAL; + } + + if (to_multiplier < 10) { + BT_WARN("to_multiplier %d < 10", to_multiplier); + return -EINVAL; + } - if (to_multiplier < 10 || to_multiplier > 3200) + if (to_multiplier > 3200) { + BT_WARN("to_multiplier %d > 3200", to_multiplier); return -EINVAL; + } - if (max >= to_multiplier * 8) + if (max >= to_multiplier * 8) { + BT_WARN("max %d >= to_multiplier %d * 8", max, to_multiplier); return -EINVAL; + } max_latency = (to_multiplier * 4 / max) - 1; - if (latency > 499 || latency > max_latency) + if (latency > 499) { + BT_WARN("latency %d > 499", latency); return -EINVAL; + } + + if (latency > max_latency) { + BT_WARN("latency %d > max_latency %d", latency, max_latency); + return -EINVAL; + } return 0; } diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 99626475c3f4..3e47e123934d 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -442,6 +442,8 @@ static inline bool flow_keys_have_l4(const struct flow_keys *keys) } u32 flow_hash_from_keys(struct flow_keys *keys); +u32 flow_hash_from_keys_seed(struct flow_keys *keys, + const siphash_key_t *keyval); void skb_flow_get_icmp_tci(const struct sk_buff *skb, struct flow_dissector_key_icmp *key_icmp, const void *data, int thoff, int hlen); diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index ec9f80509f60..292cd8f4b762 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -472,6 +472,28 @@ static inline bool flow_rule_is_supp_control_flags(const u32 supp_flags, } /** + * flow_rule_is_supp_enc_control_flags() - check for supported control flags + * @supp_enc_flags: encapsulation control flags supported by driver + * @enc_ctrl_flags: encapsulation control flags present in rule + * @extack: The netlink extended ACK for reporting errors. + * + * Return: true if only supported control flags are set, false otherwise. + */ +static inline bool flow_rule_is_supp_enc_control_flags(const u32 supp_enc_flags, + const u32 enc_ctrl_flags, + struct netlink_ext_ack *extack) +{ + if (likely((enc_ctrl_flags & ~supp_enc_flags) == 0)) + return true; + + NL_SET_ERR_MSG_FMT_MOD(extack, + "Unsupported match on enc_control.flags %#x", + enc_ctrl_flags); + + return false; +} + +/** * flow_rule_has_control_flags() - check for presence of any control flags * @ctrl_flags: control flags present in rule * @extack: The netlink extended ACK for reporting errors. @@ -485,6 +507,19 @@ static inline bool flow_rule_has_control_flags(const u32 ctrl_flags, } /** + * flow_rule_has_enc_control_flags() - check for presence of any control flags + * @enc_ctrl_flags: encapsulation control flags present in rule + * @extack: The netlink extended ACK for reporting errors. + * + * Return: true if control flags are set, false otherwise. + */ +static inline bool flow_rule_has_enc_control_flags(const u32 enc_ctrl_flags, + struct netlink_ext_ack *extack) +{ + return !flow_rule_is_supp_enc_control_flags(0, enc_ctrl_flags, extack); +} + +/** * flow_rule_match_has_control_flags() - match and check for any control flags * @rule: The flow_rule under evaluation. * @extack: The netlink extended ACK for reporting errors. diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 7d6b1254c92d..c0deaafebfdc 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -263,7 +263,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct sock *inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, struct sock *child); -void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, +bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout); struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, struct request_sock *req, diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 9b2f69ba5e49..6e7984bfb986 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -520,7 +520,35 @@ void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig); #ifdef CONFIG_IP_ROUTE_MULTIPATH int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, const struct sk_buff *skb, struct flow_keys *flkeys); + +static void +fib_multipath_hash_construct_key(siphash_key_t *key, u32 mp_seed) +{ + u64 mp_seed_64 = mp_seed; + + key->key[0] = (mp_seed_64 << 32) | mp_seed_64; + key->key[1] = key->key[0]; +} + +static inline u32 fib_multipath_hash_from_keys(const struct net *net, + struct flow_keys *keys) +{ + siphash_aligned_key_t hash_key; + u32 mp_seed; + + mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).mp_seed; + fib_multipath_hash_construct_key(&hash_key, mp_seed); + + return flow_hash_from_keys_seed(keys, &hash_key); +} +#else +static inline u32 fib_multipath_hash_from_keys(const struct net *net, + struct flow_keys *keys) +{ + return flow_hash_from_keys(keys); +} #endif + int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope, struct netlink_ext_ack *extack); void fib_select_multipath(struct fib_result *res, int hash); diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 5a530d4fb02c..3877315cf8b8 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -473,9 +473,10 @@ static inline bool pskb_inet_may_pull(struct sk_buff *skb) /* Variant of pskb_inet_may_pull(). */ -static inline bool skb_vlan_inet_prepare(struct sk_buff *skb) +static inline bool skb_vlan_inet_prepare(struct sk_buff *skb, + bool inner_proto_inherit) { - int nhlen = 0, maclen = ETH_HLEN; + int nhlen = 0, maclen = inner_proto_inherit ? 0 : ETH_HLEN; __be16 type = skb->protocol; /* Essentially this is skb_protocol(skb, true) diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 27684135bb4d..83963d9e804d 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -224,7 +224,15 @@ struct gdma_dev { struct auxiliary_device *adev; }; -#define MINIMUM_SUPPORTED_PAGE_SIZE PAGE_SIZE +/* MANA_PAGE_SIZE is the DMA unit */ +#define MANA_PAGE_SHIFT 12 +#define MANA_PAGE_SIZE BIT(MANA_PAGE_SHIFT) +#define MANA_PAGE_ALIGN(x) ALIGN((x), MANA_PAGE_SIZE) +#define MANA_PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), MANA_PAGE_SIZE) +#define MANA_PFN(a) ((a) >> MANA_PAGE_SHIFT) + +/* Required by HW */ +#define MANA_MIN_QSIZE MANA_PAGE_SIZE #define GDMA_CQE_SIZE 64 #define GDMA_EQE_SIZE 16 @@ -543,11 +551,13 @@ enum { */ #define GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX BIT(2) #define GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG BIT(3) +#define GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT BIT(5) #define GDMA_DRV_CAP_FLAGS1 \ (GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \ GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \ - GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG) + GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG | \ + GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT) #define GDMA_DRV_CAP_FLAGS2 0 diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 561f6719fb4e..e39b8676fe54 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -30,8 +30,8 @@ enum TRI_STATE { }; /* Number of entries for hardware indirection table must be in power of 2 */ -#define MANA_INDIRECT_TABLE_SIZE 64 -#define MANA_INDIRECT_TABLE_MASK (MANA_INDIRECT_TABLE_SIZE - 1) +#define MANA_INDIRECT_TABLE_MAX_SIZE 512 +#define MANA_INDIRECT_TABLE_DEF_SIZE 64 /* The Toeplitz hash key's length in bytes: should be multiple of 8 */ #define MANA_HASH_KEY_SIZE 40 @@ -42,7 +42,8 @@ enum TRI_STATE { #define MAX_SEND_BUFFERS_PER_QUEUE 256 -#define EQ_SIZE (8 * PAGE_SIZE) +#define EQ_SIZE (8 * MANA_PAGE_SIZE) + #define LOG2_EQ_THROTTLE 3 #define MAX_PORTS_IN_MANA_DEV 256 @@ -410,10 +411,11 @@ struct mana_port_context { struct mana_tx_qp *tx_qp; /* Indirection Table for RX & TX. The values are queue indexes */ - u32 indir_table[MANA_INDIRECT_TABLE_SIZE]; + u32 *indir_table; + u32 indir_table_sz; /* Indirection table containing RxObject Handles */ - mana_handle_t rxobj_table[MANA_INDIRECT_TABLE_SIZE]; + mana_handle_t *rxobj_table; /* Hash key used by the NIC */ u8 hashkey[MANA_HASH_KEY_SIZE]; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 2796153b03da..188d41da1a40 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -619,6 +619,11 @@ static inline void *nft_set_priv(const struct nft_set *set) return (void *)set->data; } +static inline enum nft_data_types nft_set_datatype(const struct nft_set *set) +{ + return set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE; +} + static inline bool nft_set_gc_is_pending(const struct nft_set *s) { return refcount_read(&s->refs) != 1; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index a91bb971f901..5fcd61ada622 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -40,6 +40,13 @@ struct inet_timewait_death_row { struct tcp_fastopen_context; +#ifdef CONFIG_IP_ROUTE_MULTIPATH +struct sysctl_fib_multipath_hash_seed { + u32 user_seed; + u32 mp_seed; +}; +#endif + struct netns_ipv4 { /* Cacheline organization can be found documented in * Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst. @@ -246,6 +253,7 @@ struct netns_ipv4 { #endif #endif #ifdef CONFIG_IP_ROUTE_MULTIPATH + struct sysctl_fib_multipath_hash_seed sysctl_fib_multipath_hash_seed; u32 sysctl_fib_multipath_hash_fields; u8 sysctl_fib_multipath_use_neigh; u8 sysctl_fib_multipath_hash_policy; diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h index 02bbdc577f8e..a6a0bf4a247e 100644 --- a/include/net/netns/netfilter.h +++ b/include/net/netns/netfilter.h @@ -15,6 +15,9 @@ struct netns_nf { const struct nf_logger __rcu *nf_loggers[NFPROTO_NUMPROTO]; #ifdef CONFIG_SYSCTL struct ctl_table_header *nf_log_dir_header; +#ifdef CONFIG_LWTUNNEL + struct ctl_table_header *nf_lwtnl_dir_header; +#endif #endif struct nf_hook_entries __rcu *hooks_ipv4[NF_INET_NUMHOOKS]; struct nf_hook_entries __rcu *hooks_ipv6[NF_INET_NUMHOOKS]; diff --git a/include/net/seg6_local.h b/include/net/seg6_local.h index 3fab9dec2ec4..888c1ce6f527 100644 --- a/include/net/seg6_local.h +++ b/include/net/seg6_local.h @@ -19,6 +19,7 @@ extern int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, extern bool seg6_bpf_has_valid_srh(struct sk_buff *skb); struct seg6_bpf_srh_state { + local_lock_t bh_lock; struct ipv6_sr_hdr *srh; u16 hdrlen; bool valid; diff --git a/include/net/sock.h b/include/net/sock.h index b30ea0c342a6..cce23ac4d514 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -544,6 +544,11 @@ struct sock { netns_tracker ns_tracker; }; +struct sock_bh_locked { + struct sock *sock; + local_lock_t bh_lock; +}; + enum sk_pacing { SK_PACING_NONE = 0, SK_PACING_NEEDED = 1, diff --git a/include/net/tcp.h b/include/net/tcp.h index a70fc39090fe..2aac11e7e1cc 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1863,12 +1863,6 @@ tcp_md5_do_lookup_any_l3index(const struct sock *sk, return __tcp_md5_do_lookup(sk, 0, addr, family, true); } -enum skb_drop_reason -tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, - const void *saddr, const void *daddr, - int family, int l3index, const __u8 *hash_location); - - #define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_key) #else static inline struct tcp_md5sig_key * @@ -1885,13 +1879,6 @@ tcp_md5_do_lookup_any_l3index(const struct sock *sk, return NULL; } -static inline enum skb_drop_reason -tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, - const void *saddr, const void *daddr, - int family, int l3index, const __u8 *hash_location) -{ - return SKB_NOT_DROPPED_YET; -} #define tcp_twsk_md5_key(twsk) NULL #endif @@ -2386,21 +2373,15 @@ static inline void tcp_get_current_key(const struct sock *sk, static inline bool tcp_key_is_md5(const struct tcp_key *key) { -#ifdef CONFIG_TCP_MD5SIG - if (static_branch_unlikely(&tcp_md5_needed.key) && - key->type == TCP_KEY_MD5) - return true; -#endif + if (static_branch_tcp_md5()) + return key->type == TCP_KEY_MD5; return false; } static inline bool tcp_key_is_ao(const struct tcp_key *key) { -#ifdef CONFIG_TCP_AO - if (static_branch_unlikely(&tcp_ao_needed.key) && - key->type == TCP_KEY_AO) - return true; -#endif + if (static_branch_tcp_ao()) + return key->type == TCP_KEY_AO; return false; } @@ -2812,66 +2793,9 @@ static inline bool tcp_ao_required(struct sock *sk, const void *saddr, return false; } -/* Called with rcu_read_lock() */ -static inline enum skb_drop_reason -tcp_inbound_hash(struct sock *sk, const struct request_sock *req, - const struct sk_buff *skb, - const void *saddr, const void *daddr, - int family, int dif, int sdif) -{ - const struct tcphdr *th = tcp_hdr(skb); - const struct tcp_ao_hdr *aoh; - const __u8 *md5_location; - int l3index; - - /* Invalid option or two times meet any of auth options */ - if (tcp_parse_auth_options(th, &md5_location, &aoh)) { - tcp_hash_fail("TCP segment has incorrect auth options set", - family, skb, ""); - return SKB_DROP_REASON_TCP_AUTH_HDR; - } - - if (req) { - if (tcp_rsk_used_ao(req) != !!aoh) { - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); - tcp_hash_fail("TCP connection can't start/end using TCP-AO", - family, skb, "%s", - !aoh ? "missing AO" : "AO signed"); - return SKB_DROP_REASON_TCP_AOFAILURE; - } - } - - /* sdif set, means packet ingressed via a device - * in an L3 domain and dif is set to the l3mdev - */ - l3index = sdif ? dif : 0; - - /* Fast path: unsigned segments */ - if (likely(!md5_location && !aoh)) { - /* Drop if there's TCP-MD5 or TCP-AO key with any rcvid/sndid - * for the remote peer. On TCP-AO established connection - * the last key is impossible to remove, so there's - * always at least one current_key. - */ - if (tcp_ao_required(sk, saddr, family, l3index, true)) { - tcp_hash_fail("AO hash is required, but not found", - family, skb, "L3 index %d", l3index); - return SKB_DROP_REASON_TCP_AONOTFOUND; - } - if (unlikely(tcp_md5_do_lookup(sk, l3index, saddr, family))) { - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); - tcp_hash_fail("MD5 Hash not found", - family, skb, "L3 index %d", l3index); - return SKB_DROP_REASON_TCP_MD5NOTFOUND; - } - return SKB_NOT_DROPPED_YET; - } - - if (aoh) - return tcp_inbound_ao_hash(sk, skb, family, req, l3index, aoh); - - return tcp_inbound_md5_hash(sk, skb, saddr, daddr, family, - l3index, md5_location); -} +enum skb_drop_reason tcp_inbound_hash(struct sock *sk, + const struct request_sock *req, const struct sk_buff *skb, + const void *saddr, const void *daddr, + int family, int dif, int sdif); #endif /* _TCP_H */ diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h index 5d8e9ed2c005..1d46460d0fef 100644 --- a/include/net/tcp_ao.h +++ b/include/net/tcp_ao.h @@ -19,6 +19,11 @@ struct tcp_ao_hdr { u8 rnext_keyid; }; +static inline u8 tcp_ao_hdr_maclen(const struct tcp_ao_hdr *aoh) +{ + return aoh->length - sizeof(struct tcp_ao_hdr); +} + struct tcp_ao_counters { atomic64_t pkt_good; atomic64_t pkt_bad; @@ -144,43 +149,6 @@ extern struct static_key_false_deferred tcp_ao_needed; #define static_branch_tcp_ao() false #endif -static inline bool tcp_hash_should_produce_warnings(void) -{ - return static_branch_tcp_md5() || static_branch_tcp_ao(); -} - -#define tcp_hash_fail(msg, family, skb, fmt, ...) \ -do { \ - const struct tcphdr *th = tcp_hdr(skb); \ - char hdr_flags[6]; \ - char *f = hdr_flags; \ - \ - if (!tcp_hash_should_produce_warnings()) \ - break; \ - if (th->fin) \ - *f++ = 'F'; \ - if (th->syn) \ - *f++ = 'S'; \ - if (th->rst) \ - *f++ = 'R'; \ - if (th->psh) \ - *f++ = 'P'; \ - if (th->ack) \ - *f++ = '.'; \ - *f = 0; \ - if ((family) == AF_INET) { \ - net_info_ratelimited("%s for %pI4.%d->%pI4.%d [%s] " fmt "\n", \ - msg, &ip_hdr(skb)->saddr, ntohs(th->source), \ - &ip_hdr(skb)->daddr, ntohs(th->dest), \ - hdr_flags, ##__VA_ARGS__); \ - } else { \ - net_info_ratelimited("%s for [%pI6c].%d->[%pI6c].%d [%s]" fmt "\n", \ - msg, &ipv6_hdr(skb)->saddr, ntohs(th->source), \ - &ipv6_hdr(skb)->daddr, ntohs(th->dest), \ - hdr_flags, ##__VA_ARGS__); \ - } \ -} while (0) - #ifdef CONFIG_TCP_AO /* TCP-AO structures and functions */ struct tcp4_ao_context { diff --git a/include/scsi/scsi_devinfo.h b/include/scsi/scsi_devinfo.h index 6b548dc2c496..1d79a3b536ce 100644 --- a/include/scsi/scsi_devinfo.h +++ b/include/scsi/scsi_devinfo.h @@ -69,8 +69,10 @@ #define BLIST_RETRY_ITF ((__force blist_flags_t)(1ULL << 32)) /* Always retry ABORTED_COMMAND with ASC 0xc1 */ #define BLIST_RETRY_ASC_C1 ((__force blist_flags_t)(1ULL << 33)) +/* Do not query the IO Advice Hints Grouping mode page */ +#define BLIST_SKIP_IO_HINTS ((__force blist_flags_t)(1ULL << 34)) -#define __BLIST_LAST_USED BLIST_RETRY_ASC_C1 +#define __BLIST_LAST_USED BLIST_SKIP_IO_HINTS #define __BLIST_HIGH_UNUSED (~(__BLIST_LAST_USED | \ (__force blist_flags_t) \ diff --git a/include/scsi/scsi_transport_sas.h b/include/scsi/scsi_transport_sas.h index 0e75b9277c8c..e3b6ce3cbf88 100644 --- a/include/scsi/scsi_transport_sas.h +++ b/include/scsi/scsi_transport_sas.h @@ -200,6 +200,8 @@ unsigned int sas_is_tlr_enabled(struct scsi_device *); void sas_disable_tlr(struct scsi_device *); void sas_enable_tlr(struct scsi_device *); +bool sas_ata_ncq_prio_supported(struct scsi_device *sdev); + extern struct sas_rphy *sas_end_device_alloc(struct sas_port *); extern struct sas_rphy *sas_expander_alloc(struct sas_port *, enum sas_device_type); void sas_rphy_free(struct sas_rphy *); diff --git a/include/sound/dmaengine_pcm.h b/include/sound/dmaengine_pcm.h index c11aaf8079fb..f6baa9a01868 100644 --- a/include/sound/dmaengine_pcm.h +++ b/include/sound/dmaengine_pcm.h @@ -36,6 +36,7 @@ snd_pcm_uframes_t snd_dmaengine_pcm_pointer_no_residue(struct snd_pcm_substream int snd_dmaengine_pcm_open(struct snd_pcm_substream *substream, struct dma_chan *chan); int snd_dmaengine_pcm_close(struct snd_pcm_substream *substream); +int snd_dmaengine_pcm_sync_stop(struct snd_pcm_substream *substream); int snd_dmaengine_pcm_open_request_chan(struct snd_pcm_substream *substream, dma_filter_fn filter_fn, void *filter_data); diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index cf4b98b9a9ed..7d931db02b93 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -33,6 +33,8 @@ enum cachefiles_obj_ref_trace { cachefiles_obj_see_withdrawal, cachefiles_obj_get_ondemand_fd, cachefiles_obj_put_ondemand_fd, + cachefiles_obj_get_read_req, + cachefiles_obj_put_read_req, }; enum fscache_why_object_killed { @@ -127,7 +129,11 @@ enum cachefiles_error_trace { EM(cachefiles_obj_see_lookup_cookie, "SEE lookup_cookie") \ EM(cachefiles_obj_see_lookup_failed, "SEE lookup_failed") \ EM(cachefiles_obj_see_withdraw_cookie, "SEE withdraw_cookie") \ - E_(cachefiles_obj_see_withdrawal, "SEE withdrawal") + EM(cachefiles_obj_see_withdrawal, "SEE withdrawal") \ + EM(cachefiles_obj_get_ondemand_fd, "GET ondemand_fd") \ + EM(cachefiles_obj_put_ondemand_fd, "PUT ondemand_fd") \ + EM(cachefiles_obj_get_read_req, "GET read_req") \ + E_(cachefiles_obj_put_read_req, "PUT read_req") #define cachefiles_coherency_traces \ EM(cachefiles_coherency_check_aux, "BAD aux ") \ diff --git a/include/trace/events/firewire.h b/include/trace/events/firewire.h index d695a560673f..5ccc0d91b220 100644 --- a/include/trace/events/firewire.h +++ b/include/trace/events/firewire.h @@ -36,10 +36,11 @@ #define QUADLET_SIZE 4 DECLARE_EVENT_CLASS(async_outbound_initiate_template, - TP_PROTO(u64 transaction, unsigned int generation, unsigned int scode, const u32 *header, const u32 *data, unsigned int data_count), - TP_ARGS(transaction, generation, scode, header, data, data_count), + TP_PROTO(u64 transaction, unsigned int card_index, unsigned int generation, unsigned int scode, const u32 *header, const u32 *data, unsigned int data_count), + TP_ARGS(transaction, card_index, generation, scode, header, data, data_count), TP_STRUCT__entry( __field(u64, transaction) + __field(u8, card_index) __field(u8, generation) __field(u8, scode) __array(u32, header, ASYNC_HEADER_QUADLET_COUNT) @@ -47,6 +48,7 @@ DECLARE_EVENT_CLASS(async_outbound_initiate_template, ), TP_fast_assign( __entry->transaction = transaction; + __entry->card_index = card_index; __entry->generation = generation; __entry->scode = scode; memcpy(__entry->header, header, QUADLET_SIZE * ASYNC_HEADER_QUADLET_COUNT); @@ -54,8 +56,9 @@ DECLARE_EVENT_CLASS(async_outbound_initiate_template, ), // This format is for the request subaction. TP_printk( - "transaction=0x%llx generation=%u scode=%u dst_id=0x%04x tlabel=%u tcode=%u src_id=0x%04x offset=0x%012llx header=%s data=%s", + "transaction=0x%llx card_index=%u generation=%u scode=%u dst_id=0x%04x tlabel=%u tcode=%u src_id=0x%04x offset=0x%012llx header=%s data=%s", __entry->transaction, + __entry->card_index, __entry->generation, __entry->scode, ASYNC_HEADER_GET_DESTINATION(__entry->header), @@ -71,10 +74,11 @@ DECLARE_EVENT_CLASS(async_outbound_initiate_template, // The value of status is one of ack codes and rcodes specific to Linux FireWire subsystem. DECLARE_EVENT_CLASS(async_outbound_complete_template, - TP_PROTO(u64 transaction, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp), - TP_ARGS(transaction, generation, scode, status, timestamp), + TP_PROTO(u64 transaction, unsigned int card_index, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp), + TP_ARGS(transaction, card_index, generation, scode, status, timestamp), TP_STRUCT__entry( __field(u64, transaction) + __field(u8, card_index) __field(u8, generation) __field(u8, scode) __field(u8, status) @@ -82,14 +86,16 @@ DECLARE_EVENT_CLASS(async_outbound_complete_template, ), TP_fast_assign( __entry->transaction = transaction; + __entry->card_index = card_index; __entry->generation = generation; __entry->scode = scode; __entry->status = status; __entry->timestamp = timestamp; ), TP_printk( - "transaction=0x%llx generation=%u scode=%u status=%u timestamp=0x%04x", + "transaction=0x%llx card_index=%u generation=%u scode=%u status=%u timestamp=0x%04x", __entry->transaction, + __entry->card_index, __entry->generation, __entry->scode, __entry->status, @@ -99,10 +105,11 @@ DECLARE_EVENT_CLASS(async_outbound_complete_template, // The value of status is one of ack codes and rcodes specific to Linux FireWire subsystem. DECLARE_EVENT_CLASS(async_inbound_template, - TP_PROTO(u64 transaction, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp, const u32 *header, const u32 *data, unsigned int data_count), - TP_ARGS(transaction, generation, scode, status, timestamp, header, data, data_count), + TP_PROTO(u64 transaction, unsigned int card_index, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp, const u32 *header, const u32 *data, unsigned int data_count), + TP_ARGS(transaction, card_index, generation, scode, status, timestamp, header, data, data_count), TP_STRUCT__entry( __field(u64, transaction) + __field(u8, card_index) __field(u8, generation) __field(u8, scode) __field(u8, status) @@ -112,6 +119,7 @@ DECLARE_EVENT_CLASS(async_inbound_template, ), TP_fast_assign( __entry->transaction = transaction; + __entry->card_index = card_index; __entry->generation = generation; __entry->scode = scode; __entry->status = status; @@ -121,8 +129,9 @@ DECLARE_EVENT_CLASS(async_inbound_template, ), // This format is for the response subaction. TP_printk( - "transaction=0x%llx generation=%u scode=%u status=%u timestamp=0x%04x dst_id=0x%04x tlabel=%u tcode=%u src_id=0x%04x rcode=%u header=%s data=%s", + "transaction=0x%llx card_index=%u generation=%u scode=%u status=%u timestamp=0x%04x dst_id=0x%04x tlabel=%u tcode=%u src_id=0x%04x rcode=%u header=%s data=%s", __entry->transaction, + __entry->card_index, __entry->generation, __entry->scode, __entry->status, @@ -139,26 +148,27 @@ DECLARE_EVENT_CLASS(async_inbound_template, ); DEFINE_EVENT(async_outbound_initiate_template, async_request_outbound_initiate, - TP_PROTO(u64 transaction, unsigned int generation, unsigned int scode, const u32 *header, const u32 *data, unsigned int data_count), - TP_ARGS(transaction, generation, scode, header, data, data_count) + TP_PROTO(u64 transaction, unsigned int card_index, unsigned int generation, unsigned int scode, const u32 *header, const u32 *data, unsigned int data_count), + TP_ARGS(transaction, card_index, generation, scode, header, data, data_count) ); DEFINE_EVENT(async_outbound_complete_template, async_request_outbound_complete, - TP_PROTO(u64 transaction, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp), - TP_ARGS(transaction, generation, scode, status, timestamp) + TP_PROTO(u64 transaction, unsigned int card_index, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp), + TP_ARGS(transaction, card_index, generation, scode, status, timestamp) ); DEFINE_EVENT(async_inbound_template, async_response_inbound, - TP_PROTO(u64 transaction, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp, const u32 *header, const u32 *data, unsigned int data_count), - TP_ARGS(transaction, generation, scode, status, timestamp, header, data, data_count) + TP_PROTO(u64 transaction, unsigned int card_index, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp, const u32 *header, const u32 *data, unsigned int data_count), + TP_ARGS(transaction, card_index, generation, scode, status, timestamp, header, data, data_count) ); DEFINE_EVENT_PRINT(async_inbound_template, async_request_inbound, - TP_PROTO(u64 transaction, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp, const u32 *header, const u32 *data, unsigned int data_count), - TP_ARGS(transaction, generation, scode, status, timestamp, header, data, data_count), + TP_PROTO(u64 transaction, unsigned int card_index, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp, const u32 *header, const u32 *data, unsigned int data_count), + TP_ARGS(transaction, card_index, generation, scode, status, timestamp, header, data, data_count), TP_printk( - "transaction=0x%llx generation=%u scode=%u status=%u timestamp=0x%04x dst_id=0x%04x tlabel=%u tcode=%u src_id=0x%04x offset=0x%012llx header=%s data=%s", + "transaction=0x%llx card_index=%u generation=%u scode=%u status=%u timestamp=0x%04x dst_id=0x%04x tlabel=%u tcode=%u src_id=0x%04x offset=0x%012llx header=%s data=%s", __entry->transaction, + __entry->card_index, __entry->generation, __entry->scode, __entry->status, @@ -175,11 +185,12 @@ DEFINE_EVENT_PRINT(async_inbound_template, async_request_inbound, ); DEFINE_EVENT_PRINT(async_outbound_initiate_template, async_response_outbound_initiate, - TP_PROTO(u64 transaction, unsigned int generation, unsigned int scode, const u32 *header, const u32 *data, unsigned int data_count), - TP_ARGS(transaction, generation, scode, header, data, data_count), + TP_PROTO(u64 transaction, unsigned int card_index, unsigned int generation, unsigned int scode, const u32 *header, const u32 *data, unsigned int data_count), + TP_ARGS(transaction, card_index, generation, scode, header, data, data_count), TP_printk( - "transaction=0x%llx generation=%u scode=%u dst_id=0x%04x tlabel=%u tcode=%u src_id=0x%04x rcode=%u header=%s data=%s", + "transaction=0x%llx card_index=%u generation=%u scode=%u dst_id=0x%04x tlabel=%u tcode=%u src_id=0x%04x rcode=%u header=%s data=%s", __entry->transaction, + __entry->card_index, __entry->generation, __entry->scode, ASYNC_HEADER_GET_DESTINATION(__entry->header), @@ -194,8 +205,8 @@ DEFINE_EVENT_PRINT(async_outbound_initiate_template, async_response_outbound_ini ); DEFINE_EVENT(async_outbound_complete_template, async_response_outbound_complete, - TP_PROTO(u64 transaction, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp), - TP_ARGS(transaction, generation, scode, status, timestamp) + TP_PROTO(u64 transaction, unsigned int card_index, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp), + TP_ARGS(transaction, card_index, generation, scode, status, timestamp) ); #undef ASYNC_HEADER_GET_DESTINATION @@ -206,23 +217,26 @@ DEFINE_EVENT(async_outbound_complete_template, async_response_outbound_complete, #undef ASYNC_HEADER_GET_RCODE TRACE_EVENT(async_phy_outbound_initiate, - TP_PROTO(u64 packet, unsigned int generation, u32 first_quadlet, u32 second_quadlet), - TP_ARGS(packet, generation, first_quadlet, second_quadlet), + TP_PROTO(u64 packet, unsigned int card_index, unsigned int generation, u32 first_quadlet, u32 second_quadlet), + TP_ARGS(packet, card_index, generation, first_quadlet, second_quadlet), TP_STRUCT__entry( __field(u64, packet) + __field(u8, card_index) __field(u8, generation) __field(u32, first_quadlet) __field(u32, second_quadlet) ), TP_fast_assign( __entry->packet = packet; + __entry->card_index = card_index; __entry->generation = generation; __entry->first_quadlet = first_quadlet; __entry->second_quadlet = second_quadlet ), TP_printk( - "packet=0x%llx generation=%u first_quadlet=0x%08x second_quadlet=0x%08x", + "packet=0x%llx card_index=%u generation=%u first_quadlet=0x%08x second_quadlet=0x%08x", __entry->packet, + __entry->card_index, __entry->generation, __entry->first_quadlet, __entry->second_quadlet @@ -230,23 +244,26 @@ TRACE_EVENT(async_phy_outbound_initiate, ); TRACE_EVENT(async_phy_outbound_complete, - TP_PROTO(u64 packet, unsigned int generation, unsigned int status, unsigned int timestamp), - TP_ARGS(packet, generation, status, timestamp), + TP_PROTO(u64 packet, unsigned int card_index, unsigned int generation, unsigned int status, unsigned int timestamp), + TP_ARGS(packet, card_index, generation, status, timestamp), TP_STRUCT__entry( __field(u64, packet) + __field(u8, card_index) __field(u8, generation) __field(u8, status) __field(u16, timestamp) ), TP_fast_assign( __entry->packet = packet; + __entry->card_index = card_index; __entry->generation = generation; __entry->status = status; __entry->timestamp = timestamp; ), TP_printk( - "packet=0x%llx generation=%u status=%u timestamp=0x%04x", + "packet=0x%llx card_index=%u generation=%u status=%u timestamp=0x%04x", __entry->packet, + __entry->card_index, __entry->generation, __entry->status, __entry->timestamp @@ -254,10 +271,11 @@ TRACE_EVENT(async_phy_outbound_complete, ); TRACE_EVENT(async_phy_inbound, - TP_PROTO(u64 packet, unsigned int generation, unsigned int status, unsigned int timestamp, u32 first_quadlet, u32 second_quadlet), - TP_ARGS(packet, generation, status, timestamp, first_quadlet, second_quadlet), + TP_PROTO(u64 packet, unsigned int card_index, unsigned int generation, unsigned int status, unsigned int timestamp, u32 first_quadlet, u32 second_quadlet), + TP_ARGS(packet, card_index, generation, status, timestamp, first_quadlet, second_quadlet), TP_STRUCT__entry( __field(u64, packet) + __field(u8, card_index) __field(u8, generation) __field(u8, status) __field(u16, timestamp) @@ -273,8 +291,9 @@ TRACE_EVENT(async_phy_inbound, __entry->second_quadlet = second_quadlet ), TP_printk( - "packet=0x%llx generation=%u status=%u timestamp=0x%04x first_quadlet=0x%08x second_quadlet=0x%08x", + "packet=0x%llx card_index=%u generation=%u status=%u timestamp=0x%04x first_quadlet=0x%08x second_quadlet=0x%08x", __entry->packet, + __entry->card_index, __entry->generation, __entry->status, __entry->timestamp, @@ -284,55 +303,61 @@ TRACE_EVENT(async_phy_inbound, ); DECLARE_EVENT_CLASS(bus_reset_arrange_template, - TP_PROTO(unsigned int generation, bool short_reset), - TP_ARGS(generation, short_reset), + TP_PROTO(unsigned int card_index, unsigned int generation, bool short_reset), + TP_ARGS(card_index, generation, short_reset), TP_STRUCT__entry( + __field(u8, card_index) __field(u8, generation) __field(bool, short_reset) ), TP_fast_assign( + __entry->card_index = card_index; __entry->generation = generation; __entry->short_reset = short_reset; ), TP_printk( - "generation=%u short_reset=%s", + "card_index=%u generation=%u short_reset=%s", + __entry->card_index, __entry->generation, __entry->short_reset ? "true" : "false" ) ); DEFINE_EVENT(bus_reset_arrange_template, bus_reset_initiate, - TP_PROTO(unsigned int generation, bool short_reset), - TP_ARGS(generation, short_reset) + TP_PROTO(unsigned int card_index, unsigned int generation, bool short_reset), + TP_ARGS(card_index, generation, short_reset) ); DEFINE_EVENT(bus_reset_arrange_template, bus_reset_schedule, - TP_PROTO(unsigned int generation, bool short_reset), - TP_ARGS(generation, short_reset) + TP_PROTO(unsigned int card_index, unsigned int generation, bool short_reset), + TP_ARGS(card_index, generation, short_reset) ); DEFINE_EVENT(bus_reset_arrange_template, bus_reset_postpone, - TP_PROTO(unsigned int generation, bool short_reset), - TP_ARGS(generation, short_reset) + TP_PROTO(unsigned int card_index, unsigned int generation, bool short_reset), + TP_ARGS(card_index, generation, short_reset) ); TRACE_EVENT(bus_reset_handle, - TP_PROTO(unsigned int generation, unsigned int node_id, bool bm_abdicate, u32 *self_ids, unsigned int self_id_count), - TP_ARGS(generation, node_id, bm_abdicate, self_ids, self_id_count), + TP_PROTO(unsigned int card_index, unsigned int generation, unsigned int node_id, bool bm_abdicate, u32 *self_ids, unsigned int self_id_count), + TP_ARGS(card_index, generation, node_id, bm_abdicate, self_ids, self_id_count), TP_STRUCT__entry( + __field(u8, card_index) __field(u8, generation) __field(u8, node_id) __field(bool, bm_abdicate) __dynamic_array(u32, self_ids, self_id_count) ), TP_fast_assign( + __entry->card_index = card_index; __entry->generation = generation; __entry->node_id = node_id; __entry->bm_abdicate = bm_abdicate; memcpy(__get_dynamic_array(self_ids), self_ids, __get_dynamic_array_len(self_ids)); ), TP_printk( - "generation=%u node_id=0x%04x bm_abdicate=%s self_ids=%s", + "card_index=%u generation=%u node_id=0x%04x bm_abdicate=%s self_ids=%s", + __entry->card_index, __entry->generation, __entry->node_id, __entry->bm_abdicate ? "true" : "false", diff --git a/include/trace/events/qdisc.h b/include/trace/events/qdisc.h index f1b5e816e7e5..ff33f41a9db7 100644 --- a/include/trace/events/qdisc.h +++ b/include/trace/events/qdisc.h @@ -81,7 +81,7 @@ TRACE_EVENT(qdisc_reset, TP_ARGS(q), TP_STRUCT__entry( - __string( dev, qdisc_dev(q)->name ) + __string( dev, qdisc_dev(q) ? qdisc_dev(q)->name : "(null)" ) __string( kind, q->ops->id ) __field( u32, parent ) __field( u32, handle ) diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 07e0715628ec..b877133cd93a 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -24,13 +24,14 @@ DEFINE_DROP_REASON(FN, FN) TRACE_EVENT(kfree_skb, TP_PROTO(struct sk_buff *skb, void *location, - enum skb_drop_reason reason), + enum skb_drop_reason reason, struct sock *rx_sk), - TP_ARGS(skb, location, reason), + TP_ARGS(skb, location, reason, rx_sk), TP_STRUCT__entry( __field(void *, skbaddr) __field(void *, location) + __field(void *, rx_sk) __field(unsigned short, protocol) __field(enum skb_drop_reason, reason) ), @@ -38,12 +39,14 @@ TRACE_EVENT(kfree_skb, TP_fast_assign( __entry->skbaddr = skb; __entry->location = location; + __entry->rx_sk = rx_sk; __entry->protocol = ntohs(skb->protocol); __entry->reason = reason; ), - TP_printk("skbaddr=%p protocol=%u location=%pS reason: %s", - __entry->skbaddr, __entry->protocol, __entry->location, + TP_printk("skbaddr=%p rx_sk=%p protocol=%u location=%pS reason: %s", + __entry->skbaddr, __entry->rx_sk, __entry->protocol, + __entry->location, __print_symbolic(__entry->reason, DEFINE_DROP_REASON(FN, FNe))) ); diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 49b5ee091cf6..1c8bd8e186b8 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -411,6 +411,323 @@ TRACE_EVENT(tcp_cong_state_set, __entry->cong_state) ); +DECLARE_EVENT_CLASS(tcp_hash_event, + + TP_PROTO(const struct sock *sk, const struct sk_buff *skb), + + TP_ARGS(sk, skb), + + TP_STRUCT__entry( + __field(__u64, net_cookie) + __field(const void *, skbaddr) + __field(const void *, skaddr) + __field(int, state) + + /* sockaddr_in6 is always bigger than sockaddr_in */ + __array(__u8, saddr, sizeof(struct sockaddr_in6)) + __array(__u8, daddr, sizeof(struct sockaddr_in6)) + __field(int, l3index) + + __field(__u16, sport) + __field(__u16, dport) + __field(__u16, family) + + __field(bool, fin) + __field(bool, syn) + __field(bool, rst) + __field(bool, psh) + __field(bool, ack) + ), + + TP_fast_assign( + const struct tcphdr *th = (const struct tcphdr *)skb->data; + + __entry->net_cookie = sock_net(sk)->net_cookie; + __entry->skbaddr = skb; + __entry->skaddr = sk; + __entry->state = sk->sk_state; + + memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); + memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); + TP_STORE_ADDR_PORTS_SKB(skb, th, __entry->saddr, __entry->daddr); + __entry->l3index = inet_sdif(skb) ? inet_iif(skb) : 0; + + /* For filtering use */ + __entry->sport = ntohs(th->source); + __entry->dport = ntohs(th->dest); + __entry->family = sk->sk_family; + + __entry->fin = th->fin; + __entry->syn = th->syn; + __entry->rst = th->rst; + __entry->psh = th->psh; + __entry->ack = th->ack; + ), + + TP_printk("net=%llu state=%s family=%s src=%pISpc dest=%pISpc L3index=%d [%c%c%c%c%c]", + __entry->net_cookie, + show_tcp_state_name(__entry->state), + show_family_name(__entry->family), + __entry->saddr, __entry->daddr, + __entry->l3index, + __entry->fin ? 'F' : ' ', + __entry->syn ? 'S' : ' ', + __entry->rst ? 'R' : ' ', + __entry->psh ? 'P' : ' ', + __entry->ack ? '.' : ' ') +); + +DEFINE_EVENT(tcp_hash_event, tcp_hash_bad_header, + + TP_PROTO(const struct sock *sk, const struct sk_buff *skb), + TP_ARGS(sk, skb) +); + +DEFINE_EVENT(tcp_hash_event, tcp_hash_md5_required, + + TP_PROTO(const struct sock *sk, const struct sk_buff *skb), + TP_ARGS(sk, skb) +); + +DEFINE_EVENT(tcp_hash_event, tcp_hash_md5_unexpected, + + TP_PROTO(const struct sock *sk, const struct sk_buff *skb), + TP_ARGS(sk, skb) +); + +DEFINE_EVENT(tcp_hash_event, tcp_hash_md5_mismatch, + + TP_PROTO(const struct sock *sk, const struct sk_buff *skb), + TP_ARGS(sk, skb) +); + +DEFINE_EVENT(tcp_hash_event, tcp_hash_ao_required, + + TP_PROTO(const struct sock *sk, const struct sk_buff *skb), + TP_ARGS(sk, skb) +); + +DECLARE_EVENT_CLASS(tcp_ao_event, + + TP_PROTO(const struct sock *sk, const struct sk_buff *skb, + const __u8 keyid, const __u8 rnext, const __u8 maclen), + + TP_ARGS(sk, skb, keyid, rnext, maclen), + + TP_STRUCT__entry( + __field(__u64, net_cookie) + __field(const void *, skbaddr) + __field(const void *, skaddr) + __field(int, state) + + /* sockaddr_in6 is always bigger than sockaddr_in */ + __array(__u8, saddr, sizeof(struct sockaddr_in6)) + __array(__u8, daddr, sizeof(struct sockaddr_in6)) + __field(int, l3index) + + __field(__u16, sport) + __field(__u16, dport) + __field(__u16, family) + + __field(bool, fin) + __field(bool, syn) + __field(bool, rst) + __field(bool, psh) + __field(bool, ack) + + __field(__u8, keyid) + __field(__u8, rnext) + __field(__u8, maclen) + ), + + TP_fast_assign( + const struct tcphdr *th = (const struct tcphdr *)skb->data; + + __entry->net_cookie = sock_net(sk)->net_cookie; + __entry->skbaddr = skb; + __entry->skaddr = sk; + __entry->state = sk->sk_state; + + memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); + memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); + TP_STORE_ADDR_PORTS_SKB(skb, th, __entry->saddr, __entry->daddr); + __entry->l3index = inet_sdif(skb) ? inet_iif(skb) : 0; + + /* For filtering use */ + __entry->sport = ntohs(th->source); + __entry->dport = ntohs(th->dest); + __entry->family = sk->sk_family; + + __entry->fin = th->fin; + __entry->syn = th->syn; + __entry->rst = th->rst; + __entry->psh = th->psh; + __entry->ack = th->ack; + + __entry->keyid = keyid; + __entry->rnext = rnext; + __entry->maclen = maclen; + ), + + TP_printk("net=%llu state=%s family=%s src=%pISpc dest=%pISpc L3index=%d [%c%c%c%c%c] keyid=%u rnext=%u maclen=%u", + __entry->net_cookie, + show_tcp_state_name(__entry->state), + show_family_name(__entry->family), + __entry->saddr, __entry->daddr, + __entry->l3index, + __entry->fin ? 'F' : ' ', + __entry->syn ? 'S' : ' ', + __entry->rst ? 'R' : ' ', + __entry->psh ? 'P' : ' ', + __entry->ack ? '.' : ' ', + __entry->keyid, __entry->rnext, __entry->maclen) +); + +DEFINE_EVENT(tcp_ao_event, tcp_ao_handshake_failure, + TP_PROTO(const struct sock *sk, const struct sk_buff *skb, + const __u8 keyid, const __u8 rnext, const __u8 maclen), + TP_ARGS(sk, skb, keyid, rnext, maclen) +); + +DEFINE_EVENT(tcp_ao_event, tcp_ao_wrong_maclen, + TP_PROTO(const struct sock *sk, const struct sk_buff *skb, + const __u8 keyid, const __u8 rnext, const __u8 maclen), + TP_ARGS(sk, skb, keyid, rnext, maclen) +); + +DEFINE_EVENT(tcp_ao_event, tcp_ao_mismatch, + TP_PROTO(const struct sock *sk, const struct sk_buff *skb, + const __u8 keyid, const __u8 rnext, const __u8 maclen), + TP_ARGS(sk, skb, keyid, rnext, maclen) +); + +DEFINE_EVENT(tcp_ao_event, tcp_ao_key_not_found, + TP_PROTO(const struct sock *sk, const struct sk_buff *skb, + const __u8 keyid, const __u8 rnext, const __u8 maclen), + TP_ARGS(sk, skb, keyid, rnext, maclen) +); + +DEFINE_EVENT(tcp_ao_event, tcp_ao_rnext_request, + TP_PROTO(const struct sock *sk, const struct sk_buff *skb, + const __u8 keyid, const __u8 rnext, const __u8 maclen), + TP_ARGS(sk, skb, keyid, rnext, maclen) +); + +DECLARE_EVENT_CLASS(tcp_ao_event_sk, + + TP_PROTO(const struct sock *sk, const __u8 keyid, const __u8 rnext), + + TP_ARGS(sk, keyid, rnext), + + TP_STRUCT__entry( + __field(__u64, net_cookie) + __field(const void *, skaddr) + __field(int, state) + + /* sockaddr_in6 is always bigger than sockaddr_in */ + __array(__u8, saddr, sizeof(struct sockaddr_in6)) + __array(__u8, daddr, sizeof(struct sockaddr_in6)) + + __field(__u16, sport) + __field(__u16, dport) + __field(__u16, family) + + __field(__u8, keyid) + __field(__u8, rnext) + ), + + TP_fast_assign( + const struct inet_sock *inet = inet_sk(sk); + + __entry->net_cookie = sock_net(sk)->net_cookie; + __entry->skaddr = sk; + __entry->state = sk->sk_state; + + memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); + memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); + TP_STORE_ADDR_PORTS(__entry, inet, sk); + + /* For filtering use */ + __entry->sport = ntohs(inet->inet_sport); + __entry->dport = ntohs(inet->inet_dport); + __entry->family = sk->sk_family; + + __entry->keyid = keyid; + __entry->rnext = rnext; + ), + + TP_printk("net=%llu state=%s family=%s src=%pISpc dest=%pISpc keyid=%u rnext=%u", + __entry->net_cookie, + show_tcp_state_name(__entry->state), + show_family_name(__entry->family), + __entry->saddr, __entry->daddr, + __entry->keyid, __entry->rnext) +); + +DEFINE_EVENT(tcp_ao_event_sk, tcp_ao_synack_no_key, + TP_PROTO(const struct sock *sk, const __u8 keyid, const __u8 rnext), + TP_ARGS(sk, keyid, rnext) +); + +DECLARE_EVENT_CLASS(tcp_ao_event_sne, + + TP_PROTO(const struct sock *sk, __u32 new_sne), + + TP_ARGS(sk, new_sne), + + TP_STRUCT__entry( + __field(__u64, net_cookie) + __field(const void *, skaddr) + __field(int, state) + + /* sockaddr_in6 is always bigger than sockaddr_in */ + __array(__u8, saddr, sizeof(struct sockaddr_in6)) + __array(__u8, daddr, sizeof(struct sockaddr_in6)) + + __field(__u16, sport) + __field(__u16, dport) + __field(__u16, family) + + __field(__u32, new_sne) + ), + + TP_fast_assign( + const struct inet_sock *inet = inet_sk(sk); + + __entry->net_cookie = sock_net(sk)->net_cookie; + __entry->skaddr = sk; + __entry->state = sk->sk_state; + + memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); + memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); + TP_STORE_ADDR_PORTS(__entry, inet, sk); + + /* For filtering use */ + __entry->sport = ntohs(inet->inet_sport); + __entry->dport = ntohs(inet->inet_dport); + __entry->family = sk->sk_family; + + __entry->new_sne = new_sne; + ), + + TP_printk("net=%llu state=%s family=%s src=%pISpc dest=%pISpc sne=%u", + __entry->net_cookie, + show_tcp_state_name(__entry->state), + show_family_name(__entry->family), + __entry->saddr, __entry->daddr, + __entry->new_sne) +); + +DEFINE_EVENT(tcp_ao_event_sne, tcp_ao_snd_sne_update, + TP_PROTO(const struct sock *sk, __u32 new_sne), + TP_ARGS(sk, new_sne) +); + +DEFINE_EVENT(tcp_ao_event_sne, tcp_ao_rcv_sne_update, + TP_PROTO(const struct sock *sk, __u32 new_sne), + TP_ARGS(sk, new_sne) +); + #endif /* _TRACE_TCP_H */ /* This part must be outside protection */ diff --git a/include/uapi/linux/can/isotp.h b/include/uapi/linux/can/isotp.h index 6cde62371b6f..bd990917f7c4 100644 --- a/include/uapi/linux/can/isotp.h +++ b/include/uapi/linux/can/isotp.h @@ -2,7 +2,7 @@ /* * linux/can/isotp.h * - * Definitions for isotp CAN sockets (ISO 15765-2:2016) + * Definitions for ISO 15765-2 CAN transport protocol sockets * * Copyright (c) 2020 Volkswagen Group Electronic Research * All rights reserved. diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index b49b804b9495..d15856c7e001 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -415,12 +415,34 @@ enum { ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES, /* u32 */ ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES, /* u32 */ ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS, /* u32 */ + /* nest - _A_PROFILE_IRQ_MODERATION */ + ETHTOOL_A_COALESCE_RX_PROFILE, + /* nest - _A_PROFILE_IRQ_MODERATION */ + ETHTOOL_A_COALESCE_TX_PROFILE, /* add new constants above here */ __ETHTOOL_A_COALESCE_CNT, ETHTOOL_A_COALESCE_MAX = (__ETHTOOL_A_COALESCE_CNT - 1) }; +enum { + ETHTOOL_A_PROFILE_UNSPEC, + /* nest, _A_IRQ_MODERATION_* */ + ETHTOOL_A_PROFILE_IRQ_MODERATION, + __ETHTOOL_A_PROFILE_CNT, + ETHTOOL_A_PROFILE_MAX = (__ETHTOOL_A_PROFILE_CNT - 1) +}; + +enum { + ETHTOOL_A_IRQ_MODERATION_UNSPEC, + ETHTOOL_A_IRQ_MODERATION_USEC, /* u32 */ + ETHTOOL_A_IRQ_MODERATION_PKTS, /* u32 */ + ETHTOOL_A_IRQ_MODERATION_COMPS, /* u32 */ + + __ETHTOOL_A_IRQ_MODERATION_CNT, + ETHTOOL_A_IRQ_MODERATION_MAX = (__ETHTOOL_A_IRQ_MODERATION_CNT - 1) +}; + /* PAUSE */ enum { diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index e682ab628dfa..d358add1611c 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -81,6 +81,8 @@ enum { #define IPPROTO_ETHERNET IPPROTO_ETHERNET IPPROTO_RAW = 255, /* Raw IP packets */ #define IPPROTO_RAW IPPROTO_RAW + IPPROTO_SMC = 256, /* Shared Memory Communications */ +#define IPPROTO_SMC IPPROTO_SMC IPPROTO_MPTCP = 262, /* Multipath TCP connection */ #define IPPROTO_MPTCP IPPROTO_MPTCP IPPROTO_MAX diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 03edf2ccdf6c..a4206723f503 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -618,6 +618,8 @@ #define KEY_CAMERA_ACCESS_ENABLE 0x24b /* Enables programmatic access to camera devices. (HUTRR72) */ #define KEY_CAMERA_ACCESS_DISABLE 0x24c /* Disables programmatic access to camera devices. (HUTRR72) */ #define KEY_CAMERA_ACCESS_TOGGLE 0x24d /* Toggles the current state of the camera access control. (HUTRR72) */ +#define KEY_ACCESSIBILITY 0x24e /* Toggles the system bound accessibility UI/command (HUTRR116) */ +#define KEY_DO_NOT_DISTURB 0x24f /* Toggles the system-wide "Do Not Disturb" control (HUTRR94)*/ #define KEY_BRIGHTNESS_MIN 0x250 /* Set Brightness to Minimum */ #define KEY_BRIGHTNESS_MAX 0x251 /* Set Brightness to Maximum */ diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 67626d535316..95770941ee2c 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -126,8 +126,8 @@ struct statx { __u64 stx_mnt_id; __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ - __u64 stx_subvol; /* Subvolume identifier */ /* 0xa0 */ + __u64 stx_subvol; /* Subvolume identifier */ __u64 __spare3[11]; /* Spare space for future expansion */ /* 0x100 */ }; diff --git a/init/Kconfig b/init/Kconfig index 72404c1f2157..febdea2afc3b 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -883,7 +883,7 @@ config GCC10_NO_ARRAY_BOUNDS config CC_NO_ARRAY_BOUNDS bool - default y if CC_IS_GCC && GCC_VERSION >= 100000 && GCC10_NO_ARRAY_BOUNDS + default y if CC_IS_GCC && GCC_VERSION >= 90000 && GCC10_NO_ARRAY_BOUNDS # Currently, disable -Wstringop-overflow for GCC globally. config GCC_NO_STRINGOP_OVERFLOW diff --git a/io_uring/cancel.h b/io_uring/cancel.h index 76b32e65c03c..b33995e00ba9 100644 --- a/io_uring/cancel.h +++ b/io_uring/cancel.h @@ -27,10 +27,10 @@ bool io_cancel_req_match(struct io_kiocb *req, struct io_cancel_data *cd); static inline bool io_cancel_match_sequence(struct io_kiocb *req, int sequence) { - if ((req->flags & REQ_F_CANCEL_SEQ) && sequence == req->work.cancel_seq) + if (req->cancel_seq_set && sequence == req->work.cancel_seq) return true; - req->flags |= REQ_F_CANCEL_SEQ; + req->cancel_seq_set = true; req->work.cancel_seq = sequence; return false; } diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index d1c47a9d9215..7d3316fe9bfc 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -927,7 +927,11 @@ void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work) { struct io_wq_acct *acct = io_work_get_acct(wq, work); unsigned long work_flags = work->flags; - struct io_cb_cancel_data match; + struct io_cb_cancel_data match = { + .fn = io_wq_work_match_item, + .data = work, + .cancel_all = false, + }; bool do_create; /* @@ -965,10 +969,6 @@ void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work) raw_spin_unlock(&wq->lock); /* fatal condition, failed to create the first worker */ - match.fn = io_wq_work_match_item, - match.data = work, - match.cancel_all = false, - io_acct_cancel_pending_work(wq, acct, &match); } } diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 816e93e7f949..154b25b8a613 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2058,6 +2058,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, req->file = NULL; req->rsrc_node = NULL; req->task = current; + req->cancel_seq_set = false; if (unlikely(opcode >= IORING_OP_LAST)) { req->opcode = 0; diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 624ca9076a50..726e6367af4d 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -433,7 +433,7 @@ static inline bool io_file_can_poll(struct io_kiocb *req) { if (req->flags & REQ_F_CAN_POLL) return true; - if (file_can_poll(req->file)) { + if (req->file && file_can_poll(req->file)) { req->flags |= REQ_F_CAN_POLL; return true; } diff --git a/io_uring/napi.c b/io_uring/napi.c index 883a1a665907..8c18ede595c4 100644 --- a/io_uring/napi.c +++ b/io_uring/napi.c @@ -261,12 +261,14 @@ int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg) } /* - * __io_napi_adjust_timeout() - Add napi id to the busy poll list + * __io_napi_adjust_timeout() - adjust busy loop timeout * @ctx: pointer to io-uring context structure * @iowq: pointer to io wait queue * @ts: pointer to timespec or NULL * * Adjust the busy loop timeout according to timespec and busy poll timeout. + * If the specified NAPI timeout is bigger than the wait timeout, then adjust + * the NAPI timeout accordingly. */ void __io_napi_adjust_timeout(struct io_ring_ctx *ctx, struct io_wait_queue *iowq, struct timespec64 *ts) @@ -274,16 +276,16 @@ void __io_napi_adjust_timeout(struct io_ring_ctx *ctx, struct io_wait_queue *iow unsigned int poll_to = READ_ONCE(ctx->napi_busy_poll_to); if (ts) { - struct timespec64 poll_to_ts = ns_to_timespec64(1000 * (s64)poll_to); - - if (timespec64_compare(ts, &poll_to_ts) > 0) { - *ts = timespec64_sub(*ts, poll_to_ts); - } else { - u64 to = timespec64_to_ns(ts); - - do_div(to, 1000); - ts->tv_sec = 0; - ts->tv_nsec = 0; + struct timespec64 poll_to_ts; + + poll_to_ts = ns_to_timespec64(1000 * (s64)poll_to); + if (timespec64_compare(ts, &poll_to_ts) < 0) { + s64 poll_to_ns = timespec64_to_ns(ts); + if (poll_to_ns > 0) { + u64 val = poll_to_ns + 999; + do_div(val, (s64) 1000); + poll_to = val; + } } } diff --git a/io_uring/register.c b/io_uring/register.c index ef8c908346a4..c0010a66a6f2 100644 --- a/io_uring/register.c +++ b/io_uring/register.c @@ -355,8 +355,10 @@ static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx, } if (sqd) { + mutex_unlock(&ctx->uring_lock); mutex_unlock(&sqd->lock); io_put_sq_data(sqd); + mutex_lock(&ctx->uring_lock); } if (copy_to_user(arg, new_count, sizeof(new_count))) @@ -380,8 +382,10 @@ static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx, return 0; err: if (sqd) { + mutex_unlock(&ctx->uring_lock); mutex_unlock(&sqd->lock); io_put_sq_data(sqd); + mutex_lock(&ctx->uring_lock); } return ret; } diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index 65417c9553b1..570bfa6a31aa 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -249,6 +249,7 @@ __cold static int io_rsrc_ref_quiesce(struct io_rsrc_data *data, ret = io_run_task_work_sig(ctx); if (ret < 0) { + __set_current_state(TASK_RUNNING); mutex_lock(&ctx->uring_lock); if (list_empty(&ctx->rsrc_ref_list)) ret = 0; @@ -1067,7 +1068,6 @@ int io_import_fixed(int ddir, struct iov_iter *iter, * branch doesn't expect non PAGE_SIZE'd chunks. */ iter->bvec = bvec; - iter->nr_segs = bvec->bv_len; iter->count -= offset; iter->iov_offset = offset; } else { diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index be8c680121e4..d6ef4f4f9cba 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -529,7 +529,8 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, entry->rule.buflen += f_val; f->lsm_str = str; err = security_audit_rule_init(f->type, f->op, str, - (void **)&f->lsm_rule); + (void **)&f->lsm_rule, + GFP_KERNEL); /* Keep currently invalid fields around in case they * become valid after a policy reload. */ if (err == -EINVAL) { @@ -799,7 +800,7 @@ static inline int audit_dupe_lsm_field(struct audit_field *df, /* our own (refreshed) copy of lsm_rule */ ret = security_audit_rule_init(df->type, df->op, df->lsm_str, - (void **)&df->lsm_rule); + (void **)&df->lsm_rule, GFP_KERNEL); /* Keep currently invalid fields around in case they * become valid after a policy reload. */ if (ret == -EINVAL) { diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c index 583ee4fe48ef..e52b3ad231b9 100644 --- a/kernel/bpf/arena.c +++ b/kernel/bpf/arena.c @@ -212,6 +212,7 @@ static u64 arena_map_mem_usage(const struct bpf_map *map) struct vma_list { struct vm_area_struct *vma; struct list_head head; + atomic_t mmap_count; }; static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma) @@ -221,20 +222,30 @@ static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma) vml = kmalloc(sizeof(*vml), GFP_KERNEL); if (!vml) return -ENOMEM; + atomic_set(&vml->mmap_count, 1); vma->vm_private_data = vml; vml->vma = vma; list_add(&vml->head, &arena->vma_list); return 0; } +static void arena_vm_open(struct vm_area_struct *vma) +{ + struct vma_list *vml = vma->vm_private_data; + + atomic_inc(&vml->mmap_count); +} + static void arena_vm_close(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; struct bpf_arena *arena = container_of(map, struct bpf_arena, map); - struct vma_list *vml; + struct vma_list *vml = vma->vm_private_data; + if (!atomic_dec_and_test(&vml->mmap_count)) + return; guard(mutex)(&arena->lock); - vml = vma->vm_private_data; + /* update link list under lock */ list_del(&vml->head); vma->vm_private_data = NULL; kfree(vml); @@ -287,6 +298,7 @@ out: } static const struct vm_operations_struct arena_vm_ops = { + .open = arena_vm_open, .close = arena_vm_close, .fault = arena_vm_fault, }; diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index a8e34416e960..068e994ed781 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -79,8 +79,6 @@ struct bpf_cpu_map { struct bpf_cpu_map_entry __rcu **cpu_map; }; -static DEFINE_PER_CPU(struct list_head, cpu_map_flush_list); - static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) { u32 value_size = attr->value_size; @@ -240,12 +238,14 @@ static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames, int xdp_n, struct xdp_cpumap_stats *stats, struct list_head *list) { + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; int nframes; if (!rcpu->prog) return xdp_n; rcu_read_lock_bh(); + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); nframes = cpu_map_bpf_prog_run_xdp(rcpu, frames, xdp_n, stats); @@ -255,6 +255,7 @@ static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames, if (unlikely(!list_empty(list))) cpu_map_bpf_prog_run_skb(rcpu, list, stats); + bpf_net_ctx_clear(bpf_net_ctx); rcu_read_unlock_bh(); /* resched point, may call do_softirq() */ return nframes; @@ -706,7 +707,7 @@ static void bq_flush_to_queue(struct xdp_bulk_queue *bq) */ static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) { - struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list); + struct list_head *flush_list = bpf_net_ctx_get_cpu_map_flush_list(); struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq); if (unlikely(bq->count == CPU_MAP_BULK_SIZE)) @@ -758,7 +759,7 @@ trace: void __cpu_map_flush(void) { - struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list); + struct list_head *flush_list = bpf_net_ctx_get_cpu_map_flush_list(); struct xdp_bulk_queue *bq, *tmp; list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { @@ -772,20 +773,9 @@ void __cpu_map_flush(void) #ifdef CONFIG_DEBUG_NET bool cpu_map_check_flush(void) { - if (list_empty(this_cpu_ptr(&cpu_map_flush_list))) + if (list_empty(bpf_net_ctx_get_cpu_map_flush_list())) return false; __cpu_map_flush(); return true; } #endif - -static int __init cpu_map_init(void) -{ - int cpu; - - for_each_possible_cpu(cpu) - INIT_LIST_HEAD(&per_cpu(cpu_map_flush_list, cpu)); - return 0; -} - -subsys_initcall(cpu_map_init); diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 7f3b34452243..317ac2d66ebd 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -83,7 +83,6 @@ struct bpf_dtab { u32 n_buckets; }; -static DEFINE_PER_CPU(struct list_head, dev_flush_list); static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); @@ -196,7 +195,14 @@ static void dev_map_free(struct bpf_map *map) list_del_rcu(&dtab->list); spin_unlock(&dev_map_lock); - bpf_clear_redirect_map(map); + /* bpf_redirect_info->map is assigned in __bpf_xdp_redirect_map() + * during NAPI callback and cleared after the XDP redirect. There is no + * explicit RCU read section which protects bpf_redirect_info->map but + * local_bh_disable() also marks the beginning an RCU section. This + * makes the complete softirq callback RCU protected. Thus after + * following synchronize_rcu() there no bpf_redirect_info->map == map + * assignment. + */ synchronize_rcu(); /* Make sure prior __dev_map_entry_free() have completed. */ @@ -408,7 +414,7 @@ out: */ void __dev_flush(void) { - struct list_head *flush_list = this_cpu_ptr(&dev_flush_list); + struct list_head *flush_list = bpf_net_ctx_get_dev_flush_list(); struct xdp_dev_bulk_queue *bq, *tmp; list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { @@ -422,7 +428,7 @@ void __dev_flush(void) #ifdef CONFIG_DEBUG_NET bool dev_check_flush(void) { - if (list_empty(this_cpu_ptr(&dev_flush_list))) + if (list_empty(bpf_net_ctx_get_dev_flush_list())) return false; __dev_flush(); return true; @@ -453,7 +459,7 @@ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key) static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { - struct list_head *flush_list = this_cpu_ptr(&dev_flush_list); + struct list_head *flush_list = bpf_net_ctx_get_dev_flush_list(); struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq); if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) @@ -1153,15 +1159,11 @@ static struct notifier_block dev_map_notifier = { static int __init dev_map_init(void) { - int cpu; - /* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */ BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) != offsetof(struct _bpf_dtab_netdev, dev)); register_netdevice_notifier(&dev_map_notifier); - for_each_possible_cpu(cpu) - INIT_LIST_HEAD(&per_cpu(dev_flush_list, cpu)); return 0; } diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 0ee653a936ea..e20b90c36131 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -51,7 +51,8 @@ struct bpf_ringbuf { * This prevents a user-space application from modifying the * position and ruining in-kernel tracking. The permissions of the * pages depend on who is producing samples: user-space or the - * kernel. + * kernel. Note that the pending counter is placed in the same + * page as the producer, so that it shares the same cache line. * * Kernel-producer * --------------- @@ -70,6 +71,7 @@ struct bpf_ringbuf { */ unsigned long consumer_pos __aligned(PAGE_SIZE); unsigned long producer_pos __aligned(PAGE_SIZE); + unsigned long pending_pos; char data[] __aligned(PAGE_SIZE); }; @@ -179,6 +181,7 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node) rb->mask = data_sz - 1; rb->consumer_pos = 0; rb->producer_pos = 0; + rb->pending_pos = 0; return rb; } @@ -404,9 +407,9 @@ bpf_ringbuf_restore_from_rec(struct bpf_ringbuf_hdr *hdr) static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) { - unsigned long cons_pos, prod_pos, new_prod_pos, flags; - u32 len, pg_off; + unsigned long cons_pos, prod_pos, new_prod_pos, pend_pos, flags; struct bpf_ringbuf_hdr *hdr; + u32 len, pg_off, tmp_size, hdr_len; if (unlikely(size > RINGBUF_MAX_RECORD_SZ)) return NULL; @@ -424,13 +427,29 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) spin_lock_irqsave(&rb->spinlock, flags); } + pend_pos = rb->pending_pos; prod_pos = rb->producer_pos; new_prod_pos = prod_pos + len; - /* check for out of ringbuf space by ensuring producer position - * doesn't advance more than (ringbuf_size - 1) ahead + while (pend_pos < prod_pos) { + hdr = (void *)rb->data + (pend_pos & rb->mask); + hdr_len = READ_ONCE(hdr->len); + if (hdr_len & BPF_RINGBUF_BUSY_BIT) + break; + tmp_size = hdr_len & ~BPF_RINGBUF_DISCARD_BIT; + tmp_size = round_up(tmp_size + BPF_RINGBUF_HDR_SZ, 8); + pend_pos += tmp_size; + } + rb->pending_pos = pend_pos; + + /* check for out of ringbuf space: + * - by ensuring producer position doesn't advance more than + * (ringbuf_size - 1) ahead + * - by ensuring oldest not yet committed record until newest + * record does not span more than (ringbuf_size - 1) */ - if (new_prod_pos - cons_pos > rb->mask) { + if (new_prod_pos - cons_pos > rb->mask || + new_prod_pos - pend_pos > rb->mask) { spin_unlock_irqrestore(&rb->spinlock, flags); return NULL; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 20ac9cfd54dd..fcecaba8668d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4549,11 +4549,12 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, state->stack[spi].spilled_ptr.id = 0; } else if (!reg && !(off % BPF_REG_SIZE) && is_bpf_st_mem(insn) && env->bpf_capable) { - struct bpf_reg_state fake_reg = {}; + struct bpf_reg_state *tmp_reg = &env->fake_reg[0]; - __mark_reg_known(&fake_reg, insn->imm); - fake_reg.type = SCALAR_VALUE; - save_register_state(env, state, spi, &fake_reg, size); + memset(tmp_reg, 0, sizeof(*tmp_reg)); + __mark_reg_known(tmp_reg, insn->imm); + tmp_reg->type = SCALAR_VALUE; + save_register_state(env, state, spi, tmp_reg, size); } else if (reg && is_spillable_regtype(reg->type)) { /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { @@ -6235,6 +6236,7 @@ static void set_sext32_default_val(struct bpf_reg_state *reg, int size) } reg->u32_min_value = 0; reg->u32_max_value = U32_MAX; + reg->var_off = tnum_subreg(tnum_unknown); } static void coerce_subreg_to_size_sx(struct bpf_reg_state *reg, int size) @@ -6279,6 +6281,7 @@ static void coerce_subreg_to_size_sx(struct bpf_reg_state *reg, int size) reg->s32_max_value = s32_max; reg->u32_min_value = (u32)s32_min; reg->u32_max_value = (u32)s32_max; + reg->var_off = tnum_subreg(tnum_range(s32_min, s32_max)); return; } @@ -12718,6 +12721,16 @@ static bool signed_add32_overflows(s32 a, s32 b) return res < a; } +static bool signed_add16_overflows(s16 a, s16 b) +{ + /* Do the add in u16, where overflow is well-defined */ + s16 res = (s16)((u16)a + (u16)b); + + if (b < 0) + return res > a; + return res < a; +} + static bool signed_sub_overflows(s64 a, s64 b) { /* Do the sub in u64, where overflow is well-defined */ @@ -15113,7 +15126,6 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs; struct bpf_reg_state *dst_reg, *other_branch_regs, *src_reg = NULL; struct bpf_reg_state *eq_branch_regs; - struct bpf_reg_state fake_reg = {}; u8 opcode = BPF_OP(insn->code); bool is_jmp32; int pred = -1; @@ -15179,7 +15191,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, verbose(env, "BPF_JMP/JMP32 uses reserved fields\n"); return -EINVAL; } - src_reg = &fake_reg; + src_reg = &env->fake_reg[0]; + memset(src_reg, 0, sizeof(*src_reg)); src_reg->type = SCALAR_VALUE; __mark_reg_known(src_reg, insn->imm); } @@ -15239,10 +15252,16 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, &other_branch_regs[insn->src_reg], dst_reg, src_reg, opcode, is_jmp32); } else /* BPF_SRC(insn->code) == BPF_K */ { + /* reg_set_min_max() can mangle the fake_reg. Make a copy + * so that these are two different memory locations. The + * src_reg is not used beyond here in context of K. + */ + memcpy(&env->fake_reg[1], &env->fake_reg[0], + sizeof(env->fake_reg[0])); err = reg_set_min_max(env, &other_branch_regs[insn->dst_reg], - src_reg /* fake one */, - dst_reg, src_reg /* same fake one */, + &env->fake_reg[0], + dst_reg, &env->fake_reg[1], opcode, is_jmp32); } if (err) @@ -17441,11 +17460,11 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) goto skip_inf_loop_check; } if (is_may_goto_insn_at(env, insn_idx)) { - if (states_equal(env, &sl->state, cur, RANGE_WITHIN)) { + if (sl->state.may_goto_depth != cur->may_goto_depth && + states_equal(env, &sl->state, cur, RANGE_WITHIN)) { update_loop_entry(cur, &sl->state); goto hit; } - goto skip_inf_loop_check; } if (calls_callback(env, insn_idx)) { if (states_equal(env, &sl->state, cur, RANGE_WITHIN)) @@ -18723,6 +18742,39 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of return new_prog; } +/* + * For all jmp insns in a given 'prog' that point to 'tgt_idx' insn adjust the + * jump offset by 'delta'. + */ +static int adjust_jmp_off(struct bpf_prog *prog, u32 tgt_idx, u32 delta) +{ + struct bpf_insn *insn = prog->insnsi; + u32 insn_cnt = prog->len, i; + + for (i = 0; i < insn_cnt; i++, insn++) { + u8 code = insn->code; + + if ((BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) || + BPF_OP(code) == BPF_CALL || BPF_OP(code) == BPF_EXIT) + continue; + + if (insn->code == (BPF_JMP32 | BPF_JA)) { + if (i + 1 + insn->imm != tgt_idx) + continue; + if (signed_add32_overflows(insn->imm, delta)) + return -ERANGE; + insn->imm += delta; + } else { + if (i + 1 + insn->off != tgt_idx) + continue; + if (signed_add16_overflows(insn->imm, delta)) + return -ERANGE; + insn->off += delta; + } + } + return 0; +} + static int adjust_subprog_starts_after_remove(struct bpf_verifier_env *env, u32 off, u32 cnt) { @@ -19997,7 +20049,10 @@ static int do_misc_fixups(struct bpf_verifier_env *env) stack_depth_extra = 8; insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_AX, BPF_REG_10, stack_off); - insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off + 2); + if (insn->off >= 0) + insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off + 2); + else + insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off - 1); insn_buf[2] = BPF_ALU64_IMM(BPF_SUB, BPF_REG_AX, 1); insn_buf[3] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_AX, stack_off); cnt = 4; @@ -20313,7 +20368,7 @@ patch_map_ops_generic: goto next_insn; } -#ifdef CONFIG_X86_64 +#if defined(CONFIG_X86_64) && !defined(CONFIG_UML) /* Implement bpf_get_smp_processor_id() inline. */ if (insn->imm == BPF_FUNC_get_smp_processor_id && prog->jit_requested && bpf_jit_supports_percpu_insn()) { @@ -20539,6 +20594,13 @@ next_insn: if (!new_prog) return -ENOMEM; env->prog = prog = new_prog; + /* + * If may_goto is a first insn of a prog there could be a jmp + * insn that points to it, hence adjust all such jmps to point + * to insn after BPF_ST that inits may_goto count. + * Adjustment will succeed because bpf_patch_insn_data() didn't fail. + */ + WARN_ON(adjust_jmp_off(env->prog, subprog_start, 1)); } /* Since poke tab is now finalized, publish aux to tracker. */ diff --git a/kernel/events/core.c b/kernel/events/core.c index f0128c5ff278..8f908f077935 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5384,6 +5384,7 @@ int perf_event_release_kernel(struct perf_event *event) again: mutex_lock(&event->child_mutex); list_for_each_entry(child, &event->child_list, child_list) { + void *var = NULL; /* * Cannot change, child events are not migrated, see the @@ -5424,11 +5425,23 @@ again: * this can't be the last reference. */ put_event(event); + } else { + var = &ctx->refcount; } mutex_unlock(&event->child_mutex); mutex_unlock(&ctx->mutex); put_ctx(ctx); + + if (var) { + /* + * If perf_event_free_task() has deleted all events from the + * ctx while the child_mutex got released above, make sure to + * notify about the preceding put_ctx(). + */ + smp_mb(); /* pairs with wait_var_event() */ + wake_up_var(var); + } goto again; } mutex_unlock(&event->child_mutex); diff --git a/kernel/fork.c b/kernel/fork.c index 99076dbe27d8..f314bdd7e610 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2355,6 +2355,7 @@ __latent_entropy struct task_struct *copy_process( RCU_INIT_POINTER(p->bpf_storage, NULL); p->bpf_ctx = NULL; #endif + p->bpf_net_context = NULL; /* Perform scheduler related setup. Assign this task to a CPU. */ retval = sched_fork(clone_flags, p); diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c index 74a4ef1da9ad..fd75b4a484d7 100644 --- a/kernel/gcov/gcc_4_7.c +++ b/kernel/gcov/gcc_4_7.c @@ -18,7 +18,9 @@ #include <linux/mm.h> #include "gcov.h" -#if (__GNUC__ >= 10) +#if (__GNUC__ >= 14) +#define GCOV_COUNTERS 9 +#elif (__GNUC__ >= 10) #define GCOV_COUNTERS 8 #elif (__GNUC__ >= 7) #define GCOV_COUNTERS 9 diff --git a/kernel/kcov.c b/kernel/kcov.c index c3124f6d5536..f0a69d402066 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -632,6 +632,7 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, return -EINVAL; kcov->mode = mode; t->kcov = kcov; + t->kcov_mode = KCOV_MODE_REMOTE; kcov->t = t; kcov->remote = true; kcov->remote_size = remote_arg->area_size; diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c index 8475a0794f8c..438c6086d540 100644 --- a/kernel/locking/spinlock.c +++ b/kernel/locking/spinlock.c @@ -413,3 +413,11 @@ notrace int in_lock_functions(unsigned long addr) && addr < (unsigned long)__lock_text_end; } EXPORT_SYMBOL(in_lock_functions); + +#if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_PREEMPT_RT) +void notrace lockdep_assert_in_softirq_func(void) +{ + lockdep_assert_in_softirq(); +} +EXPORT_SYMBOL(lockdep_assert_in_softirq_func); +#endif diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index dc48fecfa1dc..25f3cf679b35 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -218,6 +218,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) */ do { clear_thread_flag(TIF_SIGPENDING); + clear_thread_flag(TIF_NOTIFY_SIGNAL); rc = kernel_wait4(-1, NULL, __WALL, NULL); } while (rc != -ECHILD); diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index d88b13076b79..a47bcf71defc 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -178,26 +178,6 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) } } -#ifdef CONFIG_NO_HZ_FULL -static void giveup_do_timer(void *info) -{ - int cpu = *(unsigned int *)info; - - WARN_ON(tick_do_timer_cpu != smp_processor_id()); - - tick_do_timer_cpu = cpu; -} - -static void tick_take_do_timer_from_boot(void) -{ - int cpu = smp_processor_id(); - int from = tick_do_timer_boot_cpu; - - if (from >= 0 && from != cpu) - smp_call_function_single(from, giveup_do_timer, &cpu, 1); -} -#endif - /* * Setup the tick device */ @@ -221,19 +201,25 @@ static void tick_setup_device(struct tick_device *td, tick_next_period = ktime_get(); #ifdef CONFIG_NO_HZ_FULL /* - * The boot CPU may be nohz_full, in which case set - * tick_do_timer_boot_cpu so the first housekeeping - * secondary that comes up will take do_timer from - * us. + * The boot CPU may be nohz_full, in which case the + * first housekeeping secondary will take do_timer() + * from it. */ if (tick_nohz_full_cpu(cpu)) tick_do_timer_boot_cpu = cpu; - } else if (tick_do_timer_boot_cpu != -1 && - !tick_nohz_full_cpu(cpu)) { - tick_take_do_timer_from_boot(); + } else if (tick_do_timer_boot_cpu != -1 && !tick_nohz_full_cpu(cpu)) { tick_do_timer_boot_cpu = -1; - WARN_ON(READ_ONCE(tick_do_timer_cpu) != cpu); + /* + * The boot CPU will stay in periodic (NOHZ disabled) + * mode until clocksource_done_booting() called after + * smp_init() selects a high resolution clocksource and + * timekeeping_notify() kicks the NOHZ stuff alive. + * + * So this WRITE_ONCE can only race with the READ_ONCE + * check in tick_periodic() but this race is harmless. + */ + WRITE_ONCE(tick_do_timer_cpu, cpu); #endif } diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 166ad5444eea..721c3b221048 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -1136,7 +1136,7 @@ config PREEMPTIRQ_DELAY_TEST config SYNTH_EVENT_GEN_TEST tristate "Test module for in-kernel synthetic event generation" - depends on SYNTH_EVENTS + depends on SYNTH_EVENTS && m help This option creates a test module to check the base functionality of in-kernel synthetic event definition and @@ -1149,7 +1149,7 @@ config SYNTH_EVENT_GEN_TEST config KPROBE_EVENT_GEN_TEST tristate "Test module for in-kernel kprobe event generation" - depends on KPROBE_EVENTS + depends on KPROBE_EVENTS && m help This option creates a test module to check the base functionality of in-kernel kprobe event definition. diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 003474c9a77d..3fbaecfc88c2 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -125,6 +125,7 @@ enum wq_internal_consts { HIGHPRI_NICE_LEVEL = MIN_NICE, WQ_NAME_LEN = 32, + WORKER_ID_LEN = 10 + WQ_NAME_LEN, /* "kworker/R-" + WQ_NAME_LEN */ }; /* @@ -2742,6 +2743,26 @@ static void worker_detach_from_pool(struct worker *worker) complete(detach_completion); } +static int format_worker_id(char *buf, size_t size, struct worker *worker, + struct worker_pool *pool) +{ + if (worker->rescue_wq) + return scnprintf(buf, size, "kworker/R-%s", + worker->rescue_wq->name); + + if (pool) { + if (pool->cpu >= 0) + return scnprintf(buf, size, "kworker/%d:%d%s", + pool->cpu, worker->id, + pool->attrs->nice < 0 ? "H" : ""); + else + return scnprintf(buf, size, "kworker/u%d:%d", + pool->id, worker->id); + } else { + return scnprintf(buf, size, "kworker/dying"); + } +} + /** * create_worker - create a new workqueue worker * @pool: pool the new worker will belong to @@ -2758,7 +2779,6 @@ static struct worker *create_worker(struct worker_pool *pool) { struct worker *worker; int id; - char id_buf[23]; /* ID is needed to determine kthread name */ id = ida_alloc(&pool->worker_ida, GFP_KERNEL); @@ -2777,17 +2797,14 @@ static struct worker *create_worker(struct worker_pool *pool) worker->id = id; if (!(pool->flags & POOL_BH)) { - if (pool->cpu >= 0) - snprintf(id_buf, sizeof(id_buf), "%d:%d%s", pool->cpu, id, - pool->attrs->nice < 0 ? "H" : ""); - else - snprintf(id_buf, sizeof(id_buf), "u%d:%d", pool->id, id); + char id_buf[WORKER_ID_LEN]; + format_worker_id(id_buf, sizeof(id_buf), worker, pool); worker->task = kthread_create_on_node(worker_thread, worker, - pool->node, "kworker/%s", id_buf); + pool->node, "%s", id_buf); if (IS_ERR(worker->task)) { if (PTR_ERR(worker->task) == -EINTR) { - pr_err("workqueue: Interrupted when creating a worker thread \"kworker/%s\"\n", + pr_err("workqueue: Interrupted when creating a worker thread \"%s\"\n", id_buf); } else { pr_err_once("workqueue: Failed to create a worker thread: %pe", @@ -3350,7 +3367,6 @@ woke_up: raw_spin_unlock_irq(&pool->lock); set_pf_worker(false); - set_task_comm(worker->task, "kworker/dying"); ida_free(&pool->worker_ida, worker->id); worker_detach_from_pool(worker); WARN_ON_ONCE(!list_empty(&worker->entry)); @@ -5542,6 +5558,7 @@ static int wq_clamp_max_active(int max_active, unsigned int flags, static int init_rescuer(struct workqueue_struct *wq) { struct worker *rescuer; + char id_buf[WORKER_ID_LEN]; int ret; if (!(wq->flags & WQ_MEM_RECLAIM)) @@ -5555,7 +5572,9 @@ static int init_rescuer(struct workqueue_struct *wq) } rescuer->rescue_wq = wq; - rescuer->task = kthread_create(rescuer_thread, rescuer, "kworker/R-%s", wq->name); + format_worker_id(id_buf, sizeof(id_buf), rescuer, NULL); + + rescuer->task = kthread_create(rescuer_thread, rescuer, "%s", id_buf); if (IS_ERR(rescuer->task)) { ret = PTR_ERR(rescuer->task); pr_err("workqueue: Failed to create a rescuer kthread for wq \"%s\": %pe", @@ -6384,19 +6403,15 @@ void show_freezable_workqueues(void) /* used to show worker information through /proc/PID/{comm,stat,status} */ void wq_worker_comm(char *buf, size_t size, struct task_struct *task) { - int off; - - /* always show the actual comm */ - off = strscpy(buf, task->comm, size); - if (off < 0) - return; - /* stabilize PF_WQ_WORKER and worker pool association */ mutex_lock(&wq_pool_attach_mutex); if (task->flags & PF_WQ_WORKER) { struct worker *worker = kthread_data(task); struct worker_pool *pool = worker->pool; + int off; + + off = format_worker_id(buf, size, worker, pool); if (pool) { raw_spin_lock_irq(&pool->lock); @@ -6415,6 +6430,8 @@ void wq_worker_comm(char *buf, size_t size, struct task_struct *task) } raw_spin_unlock_irq(&pool->lock); } + } else { + strscpy(buf, task->comm, size); } mutex_unlock(&wq_pool_attach_mutex); diff --git a/lib/Kconfig b/lib/Kconfig index d33a268bc256..b38849af6f13 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -539,13 +539,7 @@ config CPUMASK_OFFSTACK stack overflow. config FORCE_NR_CPUS - bool "Set number of CPUs at compile time" - depends on SMP && EXPERT && !COMPILE_TEST - help - Say Yes if you have NR_CPUS set to an actual number of possible - CPUs in your system, not to a default value. This forces the core - code to rely on compile-time value and optimize kernel routines - better. + def_bool !SMP config CPU_RMAP bool @@ -629,6 +623,7 @@ config SIGNATURE config DIMLIB tristate + depends on NET help Dynamic Interrupt Moderation library. Implements an algorithm for dynamically changing CQ moderation values diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 11ed973ac359..c347b8b72d78 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -227,6 +227,7 @@ struct page_ext_operations page_alloc_tagging_ops = { }; EXPORT_SYMBOL(page_alloc_tagging_ops); +#ifdef CONFIG_SYSCTL static struct ctl_table memory_allocation_profiling_sysctls[] = { { .procname = "mem_profiling", @@ -241,6 +242,17 @@ static struct ctl_table memory_allocation_profiling_sysctls[] = { { } }; +static void __init sysctl_init(void) +{ + if (!mem_profiling_support) + memory_allocation_profiling_sysctls[0].mode = 0444; + + register_sysctl_init("vm", memory_allocation_profiling_sysctls); +} +#else /* CONFIG_SYSCTL */ +static inline void sysctl_init(void) {} +#endif /* CONFIG_SYSCTL */ + static int __init alloc_tag_init(void) { const struct codetag_type_desc desc = { @@ -253,9 +265,7 @@ static int __init alloc_tag_init(void) if (IS_ERR(alloc_tag_cttype)) return PTR_ERR(alloc_tag_cttype); - if (!mem_profiling_support) - memory_allocation_profiling_sysctls[0].mode = 0444; - register_sysctl_init("vm", memory_allocation_profiling_sysctls); + sysctl_init(); procfs_init(); return 0; diff --git a/lib/closure.c b/lib/closure.c index 07409e9e35a5..2e1ee9fdec08 100644 --- a/lib/closure.c +++ b/lib/closure.c @@ -17,12 +17,18 @@ static inline void closure_put_after_sub(struct closure *cl, int flags) { int r = flags & CLOSURE_REMAINING_MASK; - BUG_ON(flags & CLOSURE_GUARD_MASK); - BUG_ON(!r && (flags & ~CLOSURE_DESTRUCTOR)); + if (WARN(flags & CLOSURE_GUARD_MASK, + "closure has guard bits set: %x (%u)", + flags & CLOSURE_GUARD_MASK, (unsigned) __fls(r))) + r &= ~CLOSURE_GUARD_MASK; if (!r) { smp_acquire__after_ctrl_dep(); + WARN(flags & ~CLOSURE_DESTRUCTOR, + "closure ref hit 0 with incorrect flags set: %x (%u)", + flags & ~CLOSURE_DESTRUCTOR, (unsigned) __fls(flags)); + cl->closure_get_happened = false; if (cl->fn && !(flags & CLOSURE_DESTRUCTOR)) { diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c index 4e32f7aaac86..d7e7028e9b19 100644 --- a/lib/dim/net_dim.c +++ b/lib/dim/net_dim.c @@ -4,6 +4,7 @@ */ #include <linux/dim.h> +#include <linux/rtnetlink.h> /* * Net DIM profiles: @@ -11,12 +12,6 @@ * There are different set of profiles for RX/TX CQs. * Each profile size must be of NET_DIM_PARAMS_NUM_PROFILES */ -#define NET_DIM_PARAMS_NUM_PROFILES 5 -#define NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE 256 -#define NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE 128 -#define NET_DIM_DEF_PROFILE_CQE 1 -#define NET_DIM_DEF_PROFILE_EQE 1 - #define NET_DIM_RX_EQE_PROFILES { \ {.usec = 1, .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \ {.usec = 8, .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \ @@ -101,6 +96,143 @@ net_dim_get_def_tx_moderation(u8 cq_period_mode) } EXPORT_SYMBOL(net_dim_get_def_tx_moderation); +int net_dim_init_irq_moder(struct net_device *dev, u8 profile_flags, + u8 coal_flags, u8 rx_mode, u8 tx_mode, + void (*rx_dim_work)(struct work_struct *work), + void (*tx_dim_work)(struct work_struct *work)) +{ + struct dim_cq_moder *rxp = NULL, *txp; + struct dim_irq_moder *moder; + int len; + + dev->irq_moder = kzalloc(sizeof(*dev->irq_moder), GFP_KERNEL); + if (!dev->irq_moder) + return -ENOMEM; + + moder = dev->irq_moder; + len = NET_DIM_PARAMS_NUM_PROFILES * sizeof(*moder->rx_profile); + + moder->coal_flags = coal_flags; + moder->profile_flags = profile_flags; + + if (profile_flags & DIM_PROFILE_RX) { + moder->rx_dim_work = rx_dim_work; + moder->dim_rx_mode = rx_mode; + rxp = kmemdup(rx_profile[rx_mode], len, GFP_KERNEL); + if (!rxp) + goto free_moder; + + rcu_assign_pointer(moder->rx_profile, rxp); + } + + if (profile_flags & DIM_PROFILE_TX) { + moder->tx_dim_work = tx_dim_work; + moder->dim_tx_mode = tx_mode; + txp = kmemdup(tx_profile[tx_mode], len, GFP_KERNEL); + if (!txp) + goto free_rxp; + + rcu_assign_pointer(moder->tx_profile, txp); + } + + return 0; + +free_rxp: + kfree(rxp); +free_moder: + kfree(moder); + return -ENOMEM; +} +EXPORT_SYMBOL(net_dim_init_irq_moder); + +/* RTNL lock is held. */ +void net_dim_free_irq_moder(struct net_device *dev) +{ + struct dim_cq_moder *rxp, *txp; + + if (!dev->irq_moder) + return; + + rxp = rtnl_dereference(dev->irq_moder->rx_profile); + txp = rtnl_dereference(dev->irq_moder->tx_profile); + + rcu_assign_pointer(dev->irq_moder->rx_profile, NULL); + rcu_assign_pointer(dev->irq_moder->tx_profile, NULL); + + kfree_rcu(rxp, rcu); + kfree_rcu(txp, rcu); + kfree(dev->irq_moder); +} +EXPORT_SYMBOL(net_dim_free_irq_moder); + +void net_dim_setting(struct net_device *dev, struct dim *dim, bool is_tx) +{ + struct dim_irq_moder *irq_moder = dev->irq_moder; + + if (!irq_moder) + return; + + if (is_tx) { + INIT_WORK(&dim->work, irq_moder->tx_dim_work); + dim->mode = READ_ONCE(irq_moder->dim_tx_mode); + return; + } + + INIT_WORK(&dim->work, irq_moder->rx_dim_work); + dim->mode = READ_ONCE(irq_moder->dim_rx_mode); +} +EXPORT_SYMBOL(net_dim_setting); + +void net_dim_work_cancel(struct dim *dim) +{ + cancel_work_sync(&dim->work); +} +EXPORT_SYMBOL(net_dim_work_cancel); + +struct dim_cq_moder net_dim_get_rx_irq_moder(struct net_device *dev, + struct dim *dim) +{ + struct dim_cq_moder res, *profile; + + rcu_read_lock(); + profile = rcu_dereference(dev->irq_moder->rx_profile); + res = profile[dim->profile_ix]; + rcu_read_unlock(); + + res.cq_period_mode = dim->mode; + + return res; +} +EXPORT_SYMBOL(net_dim_get_rx_irq_moder); + +struct dim_cq_moder net_dim_get_tx_irq_moder(struct net_device *dev, + struct dim *dim) +{ + struct dim_cq_moder res, *profile; + + rcu_read_lock(); + profile = rcu_dereference(dev->irq_moder->tx_profile); + res = profile[dim->profile_ix]; + rcu_read_unlock(); + + res.cq_period_mode = dim->mode; + + return res; +} +EXPORT_SYMBOL(net_dim_get_tx_irq_moder); + +void net_dim_set_rx_mode(struct net_device *dev, u8 rx_mode) +{ + WRITE_ONCE(dev->irq_moder->dim_rx_mode, rx_mode); +} +EXPORT_SYMBOL(net_dim_set_rx_mode); + +void net_dim_set_tx_mode(struct net_device *dev, u8 tx_mode) +{ + WRITE_ONCE(dev->irq_moder->dim_tx_mode, tx_mode); +} +EXPORT_SYMBOL(net_dim_set_tx_mode); + static int net_dim_step(struct dim *dim) { if (dim->tired == (NET_DIM_PARAMS_NUM_PROFILES * 2)) diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c index f9cc467334ce..e17d520f532c 100644 --- a/lib/fortify_kunit.c +++ b/lib/fortify_kunit.c @@ -374,7 +374,7 @@ static const char * const test_strs[] = { for (i = 0; i < ARRAY_SIZE(test_strs); i++) { \ len = strlen(test_strs[i]); \ KUNIT_EXPECT_EQ(test, __builtin_constant_p(len), 0); \ - checker(len, kmemdup_array(test_strs[i], len, 1, gfp), \ + checker(len, kmemdup_array(test_strs[i], 1, len, gfp), \ kfree(p)); \ checker(len, kmemdup(test_strs[i], len, gfp), \ kfree(p)); \ diff --git a/lib/overflow_kunit.c b/lib/overflow_kunit.c index 4ef31b0bb74d..d305b0c054bb 100644 --- a/lib/overflow_kunit.c +++ b/lib/overflow_kunit.c @@ -1178,14 +1178,28 @@ struct foo { s16 array[] __counted_by(counter); }; +struct bar { + int a; + u32 counter; + s16 array[]; +}; + static void DEFINE_FLEX_test(struct kunit *test) { - DEFINE_RAW_FLEX(struct foo, two, array, 2); + /* Using _RAW_ on a __counted_by struct will initialize "counter" to zero */ + DEFINE_RAW_FLEX(struct foo, two_but_zero, array, 2); +#if __has_attribute(__counted_by__) + int expected_raw_size = sizeof(struct foo); +#else + int expected_raw_size = sizeof(struct foo) + 2 * sizeof(s16); +#endif + /* Without annotation, it will always be on-stack size. */ + DEFINE_RAW_FLEX(struct bar, two, array, 2); DEFINE_FLEX(struct foo, eight, array, counter, 8); DEFINE_FLEX(struct foo, empty, array, counter, 0); - KUNIT_EXPECT_EQ(test, __struct_size(two), - sizeof(struct foo) + sizeof(s16) + sizeof(s16)); + KUNIT_EXPECT_EQ(test, __struct_size(two_but_zero), expected_raw_size); + KUNIT_EXPECT_EQ(test, __struct_size(two), sizeof(struct bar) + 2 * sizeof(s16)); KUNIT_EXPECT_EQ(test, __struct_size(eight), 24); KUNIT_EXPECT_EQ(test, __struct_size(empty), sizeof(struct foo)); } diff --git a/mm/compaction.c b/mm/compaction.c index e731d45befc7..739b1bf3d637 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -79,6 +79,13 @@ static inline bool is_via_compact_memory(int order) { return false; } #define COMPACTION_HPAGE_ORDER (PMD_SHIFT - PAGE_SHIFT) #endif +static struct page *mark_allocated_noprof(struct page *page, unsigned int order, gfp_t gfp_flags) +{ + post_alloc_hook(page, order, __GFP_MOVABLE); + return page; +} +#define mark_allocated(...) alloc_hooks(mark_allocated_noprof(__VA_ARGS__)) + static void split_map_pages(struct list_head *freepages) { unsigned int i, order; @@ -93,7 +100,7 @@ static void split_map_pages(struct list_head *freepages) nr_pages = 1 << order; - post_alloc_hook(page, order, __GFP_MOVABLE); + mark_allocated(page, order, __GFP_MOVABLE); if (order) split_page(page, order); @@ -122,7 +129,7 @@ static unsigned long release_free_list(struct list_head *freepages) * Convert free pages into post allocation pages, so * that we can free them via __free_page. */ - post_alloc_hook(page, order, __GFP_MOVABLE); + mark_allocated(page, order, __GFP_MOVABLE); __free_pages(page, order); if (pfn > high_pfn) high_pfn = pfn; diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index b104a353b532..e4969fb54da3 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -40,22 +40,7 @@ * Please refer Documentation/mm/arch_pgtable_helpers.rst for the semantics * expectations that are being validated here. All future changes in here * or the documentation need to be in sync. - * - * On s390 platform, the lower 4 bits are used to identify given page table - * entry type. But these bits might affect the ability to clear entries with - * pxx_clear() because of how dynamic page table folding works on s390. So - * while loading up the entries do not change the lower 4 bits. It does not - * have affect any other platform. Also avoid the 62nd bit on ppc64 that is - * used to mark a pte entry. */ -#define S390_SKIP_MASK GENMASK(3, 0) -#if __BITS_PER_LONG == 64 -#define PPC64_SKIP_MASK GENMASK(62, 62) -#else -#define PPC64_SKIP_MASK 0x0 -#endif -#define ARCH_SKIP_MASK (S390_SKIP_MASK | PPC64_SKIP_MASK) -#define RANDOM_ORVALUE (GENMASK(BITS_PER_LONG - 1, 0) & ~ARCH_SKIP_MASK) #define RANDOM_NZVALUE GENMASK(7, 0) struct pgtable_debug_args { @@ -511,8 +496,7 @@ static void __init pud_clear_tests(struct pgtable_debug_args *args) return; pr_debug("Validating PUD clear\n"); - pud = __pud(pud_val(pud) | RANDOM_ORVALUE); - WRITE_ONCE(*args->pudp, pud); + WARN_ON(pud_none(pud)); pud_clear(args->pudp); pud = READ_ONCE(*args->pudp); WARN_ON(!pud_none(pud)); @@ -548,8 +532,7 @@ static void __init p4d_clear_tests(struct pgtable_debug_args *args) return; pr_debug("Validating P4D clear\n"); - p4d = __p4d(p4d_val(p4d) | RANDOM_ORVALUE); - WRITE_ONCE(*args->p4dp, p4d); + WARN_ON(p4d_none(p4d)); p4d_clear(args->p4dp); p4d = READ_ONCE(*args->p4dp); WARN_ON(!p4d_none(p4d)); @@ -582,8 +565,7 @@ static void __init pgd_clear_tests(struct pgtable_debug_args *args) return; pr_debug("Validating PGD clear\n"); - pgd = __pgd(pgd_val(pgd) | RANDOM_ORVALUE); - WRITE_ONCE(*args->pgdp, pgd); + WARN_ON(pgd_none(pgd)); pgd_clear(args->pgdp); pgd = READ_ONCE(*args->pgdp); WARN_ON(!pgd_none(pgd)); @@ -634,10 +616,8 @@ static void __init pte_clear_tests(struct pgtable_debug_args *args) if (WARN_ON(!args->ptep)) return; -#ifndef CONFIG_RISCV - pte = __pte(pte_val(pte) | RANDOM_ORVALUE); -#endif set_pte_at(args->mm, args->vaddr, args->ptep, pte); + WARN_ON(pte_none(pte)); flush_dcache_page(page); barrier(); ptep_clear(args->mm, args->vaddr, args->ptep); @@ -650,8 +630,7 @@ static void __init pmd_clear_tests(struct pgtable_debug_args *args) pmd_t pmd = READ_ONCE(*args->pmdp); pr_debug("Validating PMD clear\n"); - pmd = __pmd(pmd_val(pmd) | RANDOM_ORVALUE); - WRITE_ONCE(*args->pmdp, pmd); + WARN_ON(pmd_none(pmd)); pmd_clear(args->pmdp); pmd = READ_ONCE(*args->pmdp); WARN_ON(!pmd_none(pmd)); diff --git a/mm/filemap.c b/mm/filemap.c index 382c3d06bfb1..876cc64aadd7 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1000,7 +1000,7 @@ struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order) do { cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); - folio = __folio_alloc_node(gfp, order, n); + folio = __folio_alloc_node_noprof(gfp, order, n); } while (!folio && read_mems_allowed_retry(cpuset_mems_cookie)); return folio; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 317de2afd371..db7946a0a28c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -558,15 +558,15 @@ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) DEFINE_MTHP_STAT_ATTR(anon_fault_alloc, MTHP_STAT_ANON_FAULT_ALLOC); DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK); DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); -DEFINE_MTHP_STAT_ATTR(anon_swpout, MTHP_STAT_ANON_SWPOUT); -DEFINE_MTHP_STAT_ATTR(anon_swpout_fallback, MTHP_STAT_ANON_SWPOUT_FALLBACK); +DEFINE_MTHP_STAT_ATTR(swpout, MTHP_STAT_SWPOUT); +DEFINE_MTHP_STAT_ATTR(swpout_fallback, MTHP_STAT_SWPOUT_FALLBACK); static struct attribute *stats_attrs[] = { &anon_fault_alloc_attr.attr, &anon_fault_fallback_attr.attr, &anon_fault_fallback_charge_attr.attr, - &anon_swpout_attr.attr, - &anon_swpout_fallback_attr.attr, + &swpout_attr.attr, + &swpout_fallback_attr.attr, NULL, }; @@ -3009,30 +3009,36 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, if (new_order >= folio_order(folio)) return -EINVAL; - /* Cannot split anonymous THP to order-1 */ - if (new_order == 1 && folio_test_anon(folio)) { - VM_WARN_ONCE(1, "Cannot split to order-1 folio"); - return -EINVAL; - } - - if (new_order) { - /* Only swapping a whole PMD-mapped folio is supported */ - if (folio_test_swapcache(folio)) + if (folio_test_anon(folio)) { + /* order-1 is not supported for anonymous THP. */ + if (new_order == 1) { + VM_WARN_ONCE(1, "Cannot split to order-1 folio"); return -EINVAL; + } + } else if (new_order) { /* Split shmem folio to non-zero order not supported */ if (shmem_mapping(folio->mapping)) { VM_WARN_ONCE(1, "Cannot split shmem folio to non-0 order"); return -EINVAL; } - /* No split if the file system does not support large folio */ - if (!mapping_large_folio_support(folio->mapping)) { + /* + * No split if the file system does not support large folio. + * Note that we might still have THPs in such mappings due to + * CONFIG_READ_ONLY_THP_FOR_FS. But in that case, the mapping + * does not actually support large folios properly. + */ + if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && + !mapping_large_folio_support(folio->mapping)) { VM_WARN_ONCE(1, "Cannot split file folio to non-0 order"); return -EINVAL; } } + /* Only swapping a whole PMD-mapped folio is supported */ + if (folio_test_swapcache(folio) && new_order) + return -EINVAL; is_hzp = is_huge_zero_folio(folio); if (is_hzp) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6be78e7d4f6e..f35abff8be60 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5768,8 +5768,20 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, * do_exit() will not see it, and will keep the reservation * forever. */ - if (adjust_reservation && vma_needs_reservation(h, vma, address)) - vma_add_reservation(h, vma, address); + if (adjust_reservation) { + int rc = vma_needs_reservation(h, vma, address); + + if (rc < 0) + /* Pressumably allocate_file_region_entries failed + * to allocate a file_region struct. Clear + * hugetlb_restore_reserve so that global reserve + * count will not be incremented by free_huge_folio. + * Act as if we consumed the reservation. + */ + folio_clear_hugetlb_restore_reserve(page_folio(page)); + else if (rc) + vma_add_reservation(h, vma, address); + } tlb_remove_page_size(tlb, page, huge_page_size(h)); /* diff --git a/mm/internal.h b/mm/internal.h index b2c75b12014e..6902b7dd8509 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -588,7 +588,6 @@ extern void __putback_isolated_page(struct page *page, unsigned int order, extern void memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order); extern void __free_pages_core(struct page *page, unsigned int order); -extern void kernel_init_pages(struct page *page, int numpages); /* * This will have no effect, other than possibly generating a warning, if the @@ -1436,11 +1435,6 @@ unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority); #ifdef CONFIG_64BIT -/* VM is sealed, in vm_flags */ -#define VM_SEALED _BITUL(63) -#endif - -#ifdef CONFIG_64BIT static inline int can_do_mseal(unsigned long flags) { if (flags) diff --git a/mm/kasan/common.c b/mm/kasan/common.c index e7c9a4dc89f8..85e7c6b4575c 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -532,7 +532,7 @@ void __kasan_mempool_unpoison_object(void *ptr, size_t size, unsigned long ip) return; /* Unpoison the object and save alloc info for non-kmalloc() allocations. */ - unpoison_slab_object(slab->slab_cache, ptr, size, flags); + unpoison_slab_object(slab->slab_cache, ptr, flags, false); /* Poison the redzone and save alloc info for kmalloc() allocations. */ if (is_kmalloc_cache(slab->slab_cache)) diff --git a/mm/kmsan/core.c b/mm/kmsan/core.c index cf2d70e9c9a5..95f859e38c53 100644 --- a/mm/kmsan/core.c +++ b/mm/kmsan/core.c @@ -196,8 +196,7 @@ void kmsan_internal_set_shadow_origin(void *addr, size_t size, int b, u32 origin, bool checked) { u64 address = (u64)addr; - void *shadow_start; - u32 *origin_start; + u32 *shadow_start, *origin_start; size_t pad = 0; KMSAN_WARN_ON(!kmsan_metadata_is_contiguous(addr, size)); @@ -225,8 +224,16 @@ void kmsan_internal_set_shadow_origin(void *addr, size_t size, int b, origin_start = (u32 *)kmsan_get_metadata((void *)address, KMSAN_META_ORIGIN); - for (int i = 0; i < size / KMSAN_ORIGIN_SIZE; i++) - origin_start[i] = origin; + /* + * If the new origin is non-zero, assume that the shadow byte is also non-zero, + * and unconditionally overwrite the old origin slot. + * If the new origin is zero, overwrite the old origin slot iff the + * corresponding shadow slot is zero. + */ + for (int i = 0; i < size / KMSAN_ORIGIN_SIZE; i++) { + if (origin || !shadow_start[i]) + origin_start[i] = origin; + } } struct page *kmsan_vmalloc_to_page_or_null(void *vaddr) @@ -296,7 +296,7 @@ static bool ksm_use_zero_pages __read_mostly; static bool ksm_smart_scan = true; /* The number of zero pages which is placed by KSM */ -unsigned long ksm_zero_pages; +atomic_long_t ksm_zero_pages = ATOMIC_LONG_INIT(0); /* The number of pages that have been skipped due to "smart scanning" */ static unsigned long ksm_pages_skipped; @@ -1429,8 +1429,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, * the dirty bit in zero page's PTE is set. */ newpte = pte_mkdirty(pte_mkspecial(pfn_pte(page_to_pfn(kpage), vma->vm_page_prot))); - ksm_zero_pages++; - mm->ksm_zero_pages++; + ksm_map_zero_page(mm); /* * We're replacing an anonymous page with a zero page, which is * not anonymous. We need to do proper accounting otherwise we @@ -2754,18 +2753,16 @@ static void ksm_do_scan(unsigned int scan_npages) { struct ksm_rmap_item *rmap_item; struct page *page; - unsigned int npages = scan_npages; - while (npages-- && likely(!freezing(current))) { + while (scan_npages-- && likely(!freezing(current))) { cond_resched(); rmap_item = scan_get_next_rmap_item(&page); if (!rmap_item) return; cmp_and_merge_page(page, rmap_item); put_page(page); + ksm_pages_scanned++; } - - ksm_pages_scanned += scan_npages - npages; } static int ksmd_should_run(void) @@ -3376,7 +3373,7 @@ static void wait_while_offlining(void) #ifdef CONFIG_PROC_FS long ksm_process_profit(struct mm_struct *mm) { - return (long)(mm->ksm_merging_pages + mm->ksm_zero_pages) * PAGE_SIZE - + return (long)(mm->ksm_merging_pages + mm_ksm_zero_pages(mm)) * PAGE_SIZE - mm->ksm_rmap_items * sizeof(struct ksm_rmap_item); } #endif /* CONFIG_PROC_FS */ @@ -3665,7 +3662,7 @@ KSM_ATTR_RO(pages_skipped); static ssize_t ksm_zero_pages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sysfs_emit(buf, "%ld\n", ksm_zero_pages); + return sysfs_emit(buf, "%ld\n", atomic_long_read(&ksm_zero_pages)); } KSM_ATTR_RO(ksm_zero_pages); @@ -3674,7 +3671,7 @@ static ssize_t general_profit_show(struct kobject *kobj, { long general_profit; - general_profit = (ksm_pages_sharing + ksm_zero_pages) * PAGE_SIZE - + general_profit = (ksm_pages_sharing + atomic_long_read(&ksm_zero_pages)) * PAGE_SIZE - ksm_rmap_items * sizeof(struct ksm_rmap_item); return sysfs_emit(buf, "%ld\n", general_profit); diff --git a/mm/memblock.c b/mm/memblock.c index d09136e040d3..e81fb68f7f88 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -754,7 +754,7 @@ bool __init_memblock memblock_validate_numa_coverage(unsigned long threshold_byt /* calculate lose page */ for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { - if (nid == NUMA_NO_NODE) + if (!numa_valid_node(nid)) nr_pages += end_pfn - start_pfn; } @@ -1061,7 +1061,7 @@ static bool should_skip_region(struct memblock_type *type, return false; /* only memory regions are associated with nodes, check it */ - if (nid != NUMA_NO_NODE && nid != m_nid) + if (numa_valid_node(nid) && nid != m_nid) return true; /* skip hotpluggable memory regions if needed */ @@ -1118,10 +1118,6 @@ void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags, int idx_a = *idx & 0xffffffff; int idx_b = *idx >> 32; - if (WARN_ONCE(nid == MAX_NUMNODES, - "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n")) - nid = NUMA_NO_NODE; - for (; idx_a < type_a->cnt; idx_a++) { struct memblock_region *m = &type_a->regions[idx_a]; @@ -1215,9 +1211,6 @@ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, int idx_a = *idx & 0xffffffff; int idx_b = *idx >> 32; - if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n")) - nid = NUMA_NO_NODE; - if (*idx == (u64)ULLONG_MAX) { idx_a = type_a->cnt - 1; if (type_b != NULL) @@ -1303,7 +1296,7 @@ void __init_memblock __next_mem_pfn_range(int *idx, int nid, if (PFN_UP(r->base) >= PFN_DOWN(r->base + r->size)) continue; - if (nid == MAX_NUMNODES || nid == r_nid) + if (!numa_valid_node(nid) || nid == r_nid) break; } if (*idx >= type->cnt) { @@ -1448,9 +1441,6 @@ phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, enum memblock_flags flags = choose_memblock_flags(); phys_addr_t found; - if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n")) - nid = NUMA_NO_NODE; - if (!align) { /* Can't use WARNs this early in boot on powerpc */ dump_stack(); @@ -1463,7 +1453,7 @@ again: if (found && !memblock_reserve(found, size)) goto done; - if (nid != NUMA_NO_NODE && !exact_nid) { + if (numa_valid_node(nid) && !exact_nid) { found = memblock_find_in_range_node(size, align, start, end, NUMA_NO_NODE, flags); @@ -1983,7 +1973,7 @@ static void __init_memblock memblock_dump(struct memblock_type *type) end = base + size - 1; flags = rgn->flags; #ifdef CONFIG_NUMA - if (memblock_get_region_node(rgn) != MAX_NUMNODES) + if (numa_valid_node(memblock_get_region_node(rgn))) snprintf(nid_buf, sizeof(nid_buf), " on node %d", memblock_get_region_node(rgn)); #endif @@ -2177,7 +2167,7 @@ static void __init memmap_init_reserved_pages(void) start = region->base; end = start + region->size; - if (nid == NUMA_NO_NODE || nid >= MAX_NUMNODES) + if (!numa_valid_node(nid)) nid = early_pfn_to_nid(PFN_DOWN(start)); reserve_bootmem_region(start, end, nid); @@ -2268,7 +2258,7 @@ static int memblock_debug_show(struct seq_file *m, void *private) seq_printf(m, "%4d: ", i); seq_printf(m, "%pa..%pa ", ®->base, &end); - if (nid != MAX_NUMNODES) + if (numa_valid_node(nid)) seq_printf(m, "%4d ", nid); else seq_printf(m, "%4c ", 'x'); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7fad15b2290c..71fe2a95b8bd 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3147,8 +3147,6 @@ static inline void __mod_objcg_mlstate(struct obj_cgroup *objcg, struct mem_cgroup *memcg; struct lruvec *lruvec; - lockdep_assert_irqs_disabled(); - rcu_read_lock(); memcg = obj_cgroup_memcg(objcg); lruvec = mem_cgroup_lruvec(memcg, pgdat); @@ -7747,8 +7745,7 @@ void __mem_cgroup_uncharge_folios(struct folio_batch *folios) * @new: Replacement folio. * * Charge @new as a replacement folio for @old. @old will - * be uncharged upon free. This is only used by the page cache - * (in replace_page_cache_folio()). + * be uncharged upon free. * * Both folios must be locked, @new->mapping must be set up. */ diff --git a/mm/memory.c b/mm/memory.c index 0f47a533014e..d10e616d7389 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1507,12 +1507,6 @@ static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb, if (unlikely(folio_mapcount(folio) < 0)) print_bad_pte(vma, addr, ptent, page); } - - if (want_init_mlocked_on_free() && folio_test_mlocked(folio) && - !delay_rmap && folio_test_anon(folio)) { - kernel_init_pages(page, folio_nr_pages(folio)); - } - if (unlikely(__tlb_remove_folio_pages(tlb, page, nr, delay_rmap))) { *force_flush = true; *force_break = true; @@ -4614,8 +4608,9 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER)) return ret; - if (page != &folio->page || folio_order(folio) != HPAGE_PMD_ORDER) + if (folio_order(folio) != HPAGE_PMD_ORDER) return ret; + page = &folio->page; /* * Just backoff if any subpage of a THP is corrupted otherwise @@ -5106,10 +5101,16 @@ static void numa_rebuild_large_mapping(struct vm_fault *vmf, struct vm_area_stru bool ignore_writable, bool pte_write_upgrade) { int nr = pte_pfn(fault_pte) - folio_pfn(folio); - unsigned long start = max(vmf->address - nr * PAGE_SIZE, vma->vm_start); - unsigned long end = min(vmf->address + (folio_nr_pages(folio) - nr) * PAGE_SIZE, vma->vm_end); - pte_t *start_ptep = vmf->pte - (vmf->address - start) / PAGE_SIZE; - unsigned long addr; + unsigned long start, end, addr = vmf->address; + unsigned long addr_start = addr - (nr << PAGE_SHIFT); + unsigned long pt_start = ALIGN_DOWN(addr, PMD_SIZE); + pte_t *start_ptep; + + /* Stay within the VMA and within the page table. */ + start = max3(addr_start, pt_start, vma->vm_start); + end = min3(addr_start + folio_size(folio), pt_start + PMD_SIZE, + vma->vm_end); + start_ptep = vmf->pte - ((addr - start) >> PAGE_SHIFT); /* Restore all PTEs' mapping of the large folio */ for (addr = start; addr != end; start_ptep++, addr += PAGE_SIZE) { diff --git a/mm/mempool.c b/mm/mempool.c index 6ece63a00acf..3223337135d0 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -273,7 +273,7 @@ mempool_t *mempool_create_node_noprof(int min_nr, mempool_alloc_t *alloc_fn, { mempool_t *pool; - pool = kzalloc_node(sizeof(*pool), gfp_mask, node_id); + pool = kmalloc_node_noprof(sizeof(*pool), gfp_mask | __GFP_ZERO, node_id); if (!pool) return NULL; diff --git a/mm/migrate.c b/mm/migrate.c index dd04f578c19c..20cb9f5f7446 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1654,7 +1654,16 @@ static int migrate_pages_batch(struct list_head *from, /* * The rare folio on the deferred split list should - * be split now. It should not count as a failure. + * be split now. It should not count as a failure: + * but increment nr_failed because, without doing so, + * migrate_pages() may report success with (split but + * unmigrated) pages still on its fromlist; whereas it + * always reports success when its fromlist is empty. + * stats->nr_thp_failed should be increased too, + * otherwise stats inconsistency will happen when + * migrate_pages_batch is called via migrate_pages() + * with MIGRATE_SYNC and MIGRATE_ASYNC. + * * Only check it without removing it from the list. * Since the folio can be on deferred_split_scan() * local list and removing it can cause the local list @@ -1669,6 +1678,8 @@ static int migrate_pages_batch(struct list_head *from, if (nr_pages > 2 && !list_empty(&folio->_deferred_list)) { if (try_split_folio(folio, split_folios) == 0) { + nr_failed++; + stats->nr_thp_failed += is_thp; stats->nr_thp_split += is_thp; stats->nr_split++; continue; diff --git a/mm/mm_init.c b/mm/mm_init.c index f72b852bd5b8..3ec04933f7fd 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -2523,9 +2523,6 @@ EXPORT_SYMBOL(init_on_alloc); DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free); EXPORT_SYMBOL(init_on_free); -DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON, init_mlocked_on_free); -EXPORT_SYMBOL(init_mlocked_on_free); - static bool _init_on_alloc_enabled_early __read_mostly = IS_ENABLED(CONFIG_INIT_ON_ALLOC_DEFAULT_ON); static int __init early_init_on_alloc(char *buf) @@ -2543,14 +2540,6 @@ static int __init early_init_on_free(char *buf) } early_param("init_on_free", early_init_on_free); -static bool _init_mlocked_on_free_enabled_early __read_mostly - = IS_ENABLED(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON); -static int __init early_init_mlocked_on_free(char *buf) -{ - return kstrtobool(buf, &_init_mlocked_on_free_enabled_early); -} -early_param("init_mlocked_on_free", early_init_mlocked_on_free); - DEFINE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled); /* @@ -2578,21 +2567,12 @@ static void __init mem_debugging_and_hardening_init(void) } #endif - if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early || - _init_mlocked_on_free_enabled_early) && + if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early) && page_poisoning_requested) { pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, " - "will take precedence over init_on_alloc, init_on_free " - "and init_mlocked_on_free\n"); + "will take precedence over init_on_alloc and init_on_free\n"); _init_on_alloc_enabled_early = false; _init_on_free_enabled_early = false; - _init_mlocked_on_free_enabled_early = false; - } - - if (_init_mlocked_on_free_enabled_early && _init_on_free_enabled_early) { - pr_info("mem auto-init: init_on_free is on, " - "will take precedence over init_mlocked_on_free\n"); - _init_mlocked_on_free_enabled_early = false; } if (_init_on_alloc_enabled_early) { @@ -2609,17 +2589,9 @@ static void __init mem_debugging_and_hardening_init(void) static_branch_disable(&init_on_free); } - if (_init_mlocked_on_free_enabled_early) { - want_check_pages = true; - static_branch_enable(&init_mlocked_on_free); - } else { - static_branch_disable(&init_mlocked_on_free); - } - - if (IS_ENABLED(CONFIG_KMSAN) && (_init_on_alloc_enabled_early || - _init_on_free_enabled_early || _init_mlocked_on_free_enabled_early)) - pr_info("mem auto-init: please make sure init_on_alloc, init_on_free and " - "init_mlocked_on_free are disabled when running KMSAN\n"); + if (IS_ENABLED(CONFIG_KMSAN) && + (_init_on_alloc_enabled_early || _init_on_free_enabled_early)) + pr_info("mem auto-init: please make sure init_on_alloc and init_on_free are disabled when running KMSAN\n"); #ifdef CONFIG_DEBUG_PAGEALLOC if (debug_pagealloc_enabled()) { @@ -2658,10 +2630,9 @@ static void __init report_meminit(void) else stack = "off"; - pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s, mlocked free:%s\n", + pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s\n", stack, want_init_on_alloc(GFP_KERNEL) ? "on" : "off", - want_init_on_free() ? "on" : "off", - want_init_mlocked_on_free() ? "on" : "off"); + want_init_on_free() ? "on" : "off"); if (want_init_on_free()) pr_info("mem auto-init: clearing system memory may take some time...\n"); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2e22ce5675ca..9ecf99190ea2 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -504,10 +504,15 @@ out: static inline unsigned int order_to_pindex(int migratetype, int order) { + bool __maybe_unused movable; + #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (order > PAGE_ALLOC_COSTLY_ORDER) { VM_BUG_ON(order != HPAGE_PMD_ORDER); - return NR_LOWORDER_PCP_LISTS; + + movable = migratetype == MIGRATE_MOVABLE; + + return NR_LOWORDER_PCP_LISTS + movable; } #else VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); @@ -521,7 +526,7 @@ static inline int pindex_to_order(unsigned int pindex) int order = pindex / MIGRATE_PCPTYPES; #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (pindex == NR_LOWORDER_PCP_LISTS) + if (pindex >= NR_LOWORDER_PCP_LISTS) order = HPAGE_PMD_ORDER; #else VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); @@ -1016,7 +1021,7 @@ static inline bool should_skip_kasan_poison(struct page *page) return page_kasan_tag(page) == KASAN_TAG_KERNEL; } -void kernel_init_pages(struct page *page, int numpages) +static void kernel_init_pages(struct page *page, int numpages) { int i; @@ -1955,10 +1960,12 @@ int find_suitable_fallback(struct free_area *area, unsigned int order, } /* - * Reserve a pageblock for exclusive use of high-order atomic allocations if - * there are no empty page blocks that contain a page with a suitable order + * Reserve the pageblock(s) surrounding an allocation request for + * exclusive use of high-order atomic allocations if there are no + * empty page blocks that contain a page with a suitable order */ -static void reserve_highatomic_pageblock(struct page *page, struct zone *zone) +static void reserve_highatomic_pageblock(struct page *page, int order, + struct zone *zone) { int mt; unsigned long max_managed, flags; @@ -1984,10 +1991,17 @@ static void reserve_highatomic_pageblock(struct page *page, struct zone *zone) /* Yoink! */ mt = get_pageblock_migratetype(page); /* Only reserve normal pageblocks (i.e., they can merge with others) */ - if (migratetype_is_mergeable(mt)) - if (move_freepages_block(zone, page, mt, - MIGRATE_HIGHATOMIC) != -1) - zone->nr_reserved_highatomic += pageblock_nr_pages; + if (!migratetype_is_mergeable(mt)) + goto out_unlock; + + if (order < pageblock_order) { + if (move_freepages_block(zone, page, mt, MIGRATE_HIGHATOMIC) == -1) + goto out_unlock; + zone->nr_reserved_highatomic += pageblock_nr_pages; + } else { + change_pageblock_range(page, order, MIGRATE_HIGHATOMIC); + zone->nr_reserved_highatomic += 1 << order; + } out_unlock: spin_unlock_irqrestore(&zone->lock, flags); @@ -1999,7 +2013,7 @@ out_unlock: * intense memory pressure but failed atomic allocations should be easier * to recover from than an OOM. * - * If @force is true, try to unreserve a pageblock even though highatomic + * If @force is true, try to unreserve pageblocks even though highatomic * pageblock is exhausted. */ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, @@ -2041,6 +2055,7 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, * adjust the count once. */ if (is_migrate_highatomic(mt)) { + unsigned long size; /* * It should never happen but changes to * locking could inadvertently allow a per-cpu @@ -2048,9 +2063,9 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, * while unreserving so be safe and watch for * underflows. */ - zone->nr_reserved_highatomic -= min( - pageblock_nr_pages, - zone->nr_reserved_highatomic); + size = max(pageblock_nr_pages, 1UL << order); + size = min(size, zone->nr_reserved_highatomic); + zone->nr_reserved_highatomic -= size; } /* @@ -2062,11 +2077,19 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, * of pageblocks that cannot be completely freed * may increase. */ - ret = move_freepages_block(zone, page, mt, - ac->migratetype); + if (order < pageblock_order) + ret = move_freepages_block(zone, page, mt, + ac->migratetype); + else { + move_to_free_list(page, zone, order, mt, + ac->migratetype); + change_pageblock_range(page, order, + ac->migratetype); + ret = 1; + } /* - * Reserving this block already succeeded, so this should - * not fail on zone boundaries. + * Reserving the block(s) already succeeded, + * so this should not fail on zone boundaries. */ WARN_ON_ONCE(ret == -1); if (ret > 0) { @@ -3406,7 +3429,7 @@ try_this_zone: * if the pageblock should be reserved for the future */ if (unlikely(alloc_flags & ALLOC_HIGHATOMIC)) - reserve_highatomic_pageblock(page, zone); + reserve_highatomic_pageblock(page, order, zone); return page; } else { diff --git a/mm/page_io.c b/mm/page_io.c index 46c603dddf04..0a150c240bf4 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -217,7 +217,7 @@ static inline void count_swpout_vm_event(struct folio *folio) count_memcg_folio_events(folio, THP_SWPOUT, 1); count_vm_event(THP_SWPOUT); } - count_mthp_stat(folio_order(folio), MTHP_STAT_ANON_SWPOUT); + count_mthp_stat(folio_order(folio), MTHP_STAT_SWPOUT); #endif count_vm_events(PSWPOUT, folio_nr_pages(folio)); } diff --git a/mm/page_table_check.c b/mm/page_table_check.c index 4169576bed72..509c6ef8de40 100644 --- a/mm/page_table_check.c +++ b/mm/page_table_check.c @@ -73,6 +73,9 @@ static void page_table_check_clear(unsigned long pfn, unsigned long pgcnt) page = pfn_to_page(pfn); page_ext = page_ext_get(page); + if (!page_ext) + return; + BUG_ON(PageSlab(page)); anon = PageAnon(page); @@ -110,6 +113,9 @@ static void page_table_check_set(unsigned long pfn, unsigned long pgcnt, page = pfn_to_page(pfn); page_ext = page_ext_get(page); + if (!page_ext) + return; + BUG_ON(PageSlab(page)); anon = PageAnon(page); @@ -140,7 +146,10 @@ void __page_table_check_zero(struct page *page, unsigned int order) BUG_ON(PageSlab(page)); page_ext = page_ext_get(page); - BUG_ON(!page_ext); + + if (!page_ext) + return; + for (i = 0; i < (1ul << order); i++) { struct page_table_check *ptc = get_page_table_check(page_ext); diff --git a/mm/shmem.c b/mm/shmem.c index f5d60436b604..a8b181a63402 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1786,7 +1786,7 @@ static int shmem_replace_folio(struct folio **foliop, gfp_t gfp, xa_lock_irq(&swap_mapping->i_pages); error = shmem_replace_entry(swap_mapping, swap_index, old, new); if (!error) { - mem_cgroup_migrate(old, new); + mem_cgroup_replace_folio(old, new); __lruvec_stat_mod_folio(new, NR_FILE_PAGES, 1); __lruvec_stat_mod_folio(new, NR_SHMEM, 1); __lruvec_stat_mod_folio(old, NR_FILE_PAGES, -1); diff --git a/mm/slub.c b/mm/slub.c index 0809760cf789..4927edec6a8c 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1952,7 +1952,7 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, #ifdef CONFIG_MEMCG new_exts |= MEMCG_DATA_OBJEXTS; #endif - old_exts = slab->obj_exts; + old_exts = READ_ONCE(slab->obj_exts); handle_failed_objexts_alloc(old_exts, vec, objects); if (new_slab) { /* @@ -1961,7 +1961,8 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, * be simply assigned. */ slab->obj_exts = new_exts; - } else if (cmpxchg(&slab->obj_exts, old_exts, new_exts) != old_exts) { + } else if ((old_exts & ~OBJEXTS_FLAGS_MASK) || + cmpxchg(&slab->obj_exts, old_exts, new_exts) != old_exts) { /* * If the slab is already in use, somebody can allocate and * assign slabobj_exts in parallel. In this case the existing @@ -3901,7 +3902,6 @@ bool slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru, unsigned int orig_size) { unsigned int zero_size = s->object_size; - struct slabobj_ext *obj_exts; bool kasan_init = init; size_t i; gfp_t init_flags = flags & gfp_allowed_mask; @@ -3944,9 +3944,11 @@ bool slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru, kmemleak_alloc_recursive(p[i], s->object_size, 1, s->flags, init_flags); kmsan_slab_alloc(s, p[i], init_flags); +#ifdef CONFIG_MEM_ALLOC_PROFILING if (need_slab_obj_ext()) { + struct slabobj_ext *obj_exts; + obj_exts = prepare_slab_obj_exts_hook(s, flags, p[i]); -#ifdef CONFIG_MEM_ALLOC_PROFILING /* * Currently obj_exts is used only for allocation profiling. * If other users appear then mem_alloc_profiling_enabled() @@ -3954,8 +3956,8 @@ bool slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru, */ if (likely(obj_exts)) alloc_tag_add(&obj_exts->ref, current->alloc_tag, s->size); -#endif } +#endif } return memcg_slab_post_alloc_hook(s, lru, flags, size, p); diff --git a/mm/util.c b/mm/util.c index c9e519e6811f..fe723241b66f 100644 --- a/mm/util.c +++ b/mm/util.c @@ -139,14 +139,14 @@ EXPORT_SYMBOL(kmemdup_noprof); * kmemdup_array - duplicate a given array. * * @src: array to duplicate. - * @element_size: size of each element of array. * @count: number of elements to duplicate from array. + * @element_size: size of each element of array. * @gfp: GFP mask to use. * * Return: duplicated array of @src or %NULL in case of error, * result is physically contiguous. Use kfree() to free. */ -void *kmemdup_array(const void *src, size_t element_size, size_t count, gfp_t gfp) +void *kmemdup_array(const void *src, size_t count, size_t element_size, gfp_t gfp) { return kmemdup(src, size_mul(element_size, count), gfp); } @@ -705,7 +705,7 @@ void *kvrealloc_noprof(const void *p, size_t oldsize, size_t newsize, gfp_t flag if (oldsize >= newsize) return (void *)p; - newp = kvmalloc(newsize, flags); + newp = kvmalloc_noprof(newsize, flags); if (!newp) return NULL; memcpy(newp, p, oldsize); @@ -726,7 +726,7 @@ void *__vmalloc_array_noprof(size_t n, size_t size, gfp_t flags) if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; - return __vmalloc(bytes, flags); + return __vmalloc_noprof(bytes, flags); } EXPORT_SYMBOL(__vmalloc_array_noprof); @@ -737,7 +737,7 @@ EXPORT_SYMBOL(__vmalloc_array_noprof); */ void *vmalloc_array_noprof(size_t n, size_t size) { - return __vmalloc_array(n, size, GFP_KERNEL); + return __vmalloc_array_noprof(n, size, GFP_KERNEL); } EXPORT_SYMBOL(vmalloc_array_noprof); @@ -749,7 +749,7 @@ EXPORT_SYMBOL(vmalloc_array_noprof); */ void *__vcalloc_noprof(size_t n, size_t size, gfp_t flags) { - return __vmalloc_array(n, size, flags | __GFP_ZERO); + return __vmalloc_array_noprof(n, size, flags | __GFP_ZERO); } EXPORT_SYMBOL(__vcalloc_noprof); @@ -760,7 +760,7 @@ EXPORT_SYMBOL(__vcalloc_noprof); */ void *vcalloc_noprof(size_t n, size_t size) { - return __vmalloc_array(n, size, GFP_KERNEL | __GFP_ZERO); + return __vmalloc_array_noprof(n, size, GFP_KERNEL | __GFP_ZERO); } EXPORT_SYMBOL(vcalloc_noprof); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 5d3aa2dc88a8..d0cbdd7c1e5b 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -722,7 +722,7 @@ int is_vmalloc_or_module_addr(const void *x) * and fall back on vmalloc() if that fails. Others * just put it in the vmalloc space. */ -#if defined(CONFIG_MODULES) && defined(MODULES_VADDR) +#if defined(CONFIG_EXECMEM) && defined(MODULES_VADDR) unsigned long addr = (unsigned long)kasan_reset_tag(x); if (addr >= MODULES_VADDR && addr < MODULES_END) return 1; @@ -2498,6 +2498,7 @@ struct vmap_block { struct list_head free_list; struct rcu_head rcu_head; struct list_head purge; + unsigned int cpu; }; /* Queue of free and dirty vmap blocks, for allocation and flushing purposes */ @@ -2625,8 +2626,15 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) free_vmap_area(va); return ERR_PTR(err); } - - vbq = raw_cpu_ptr(&vmap_block_queue); + /* + * list_add_tail_rcu could happened in another core + * rather than vb->cpu due to task migration, which + * is safe as list_add_tail_rcu will ensure the list's + * integrity together with list_for_each_rcu from read + * side. + */ + vb->cpu = raw_smp_processor_id(); + vbq = per_cpu_ptr(&vmap_block_queue, vb->cpu); spin_lock(&vbq->lock); list_add_tail_rcu(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); @@ -2654,9 +2662,10 @@ static void free_vmap_block(struct vmap_block *vb) } static bool purge_fragmented_block(struct vmap_block *vb, - struct vmap_block_queue *vbq, struct list_head *purge_list, - bool force_purge) + struct list_head *purge_list, bool force_purge) { + struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, vb->cpu); + if (vb->free + vb->dirty != VMAP_BBMAP_BITS || vb->dirty == VMAP_BBMAP_BITS) return false; @@ -2704,7 +2713,7 @@ static void purge_fragmented_blocks(int cpu) continue; spin_lock(&vb->lock); - purge_fragmented_block(vb, vbq, &purge, true); + purge_fragmented_block(vb, &purge, true); spin_unlock(&vb->lock); } rcu_read_unlock(); @@ -2841,7 +2850,7 @@ static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush) * not purgeable, check whether there is dirty * space to be flushed. */ - if (!purge_fragmented_block(vb, vbq, &purge_list, false) && + if (!purge_fragmented_block(vb, &purge_list, false) && vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) { unsigned long va_start = vb->va->va_start; unsigned long s, e; diff --git a/mm/vmscan.c b/mm/vmscan.c index d55e8d07ffc4..2e34de9cd0d4 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1227,7 +1227,7 @@ retry: THP_SWPOUT_FALLBACK, 1); count_vm_event(THP_SWPOUT_FALLBACK); } - count_mthp_stat(order, MTHP_STAT_ANON_SWPOUT_FALLBACK); + count_mthp_stat(order, MTHP_STAT_SWPOUT_FALLBACK); #endif if (!add_to_swap(folio)) goto activate_locked_split; diff --git a/net/Kconfig b/net/Kconfig index 9fe65fa26e48..d27d0deac0bf 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -508,6 +508,7 @@ config FAILOVER config ETHTOOL_NETLINK bool "Netlink interface for ethtool" + select DIMLIB default y help An alternative userspace interface for ethtool based on generic diff --git a/net/atm/ioctl.c b/net/atm/ioctl.c index f81f8d56f5c0..0f7a39aeccc8 100644 --- a/net/atm/ioctl.c +++ b/net/atm/ioctl.c @@ -68,7 +68,7 @@ static int do_vcc_ioctl(struct socket *sock, unsigned int cmd, goto done; } error = put_user(sk->sk_sndbuf - sk_wmem_alloc_get(sk), - (int __user *)argp) ? -EFAULT : 0; + (int __user *)argp); goto done; case SIOCINQ: { @@ -83,7 +83,7 @@ static int do_vcc_ioctl(struct socket *sock, unsigned int cmd, skb = skb_peek(&sk->sk_receive_queue); amount = skb ? skb->len : 0; spin_unlock_irq(&sk->sk_receive_queue.lock); - error = put_user(amount, (int __user *)argp) ? -EFAULT : 0; + error = put_user(amount, (int __user *)argp); goto done; } case ATM_SETSC: diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index ac74f6ead62d..8f6dd2c6ee41 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -12,6 +12,7 @@ #include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/gfp.h> +#include <linux/if_vlan.h> #include <linux/jiffies.h> #include <linux/kref.h> #include <linux/list.h> @@ -132,6 +133,29 @@ batadv_orig_node_vlan_get(struct batadv_orig_node *orig_node, } /** + * batadv_vlan_id_valid() - check if vlan id is in valid batman-adv encoding + * @vid: the VLAN identifier + * + * Return: true when either no vlan is set or if VLAN is in correct range, + * false otherwise + */ +static bool batadv_vlan_id_valid(unsigned short vid) +{ + unsigned short non_vlan = vid & ~(BATADV_VLAN_HAS_TAG | VLAN_VID_MASK); + + if (vid == 0) + return true; + + if (!(vid & BATADV_VLAN_HAS_TAG)) + return false; + + if (non_vlan) + return false; + + return true; +} + +/** * batadv_orig_node_vlan_new() - search and possibly create an orig_node_vlan * object * @orig_node: the originator serving the VLAN @@ -149,6 +173,9 @@ batadv_orig_node_vlan_new(struct batadv_orig_node *orig_node, { struct batadv_orig_node_vlan *vlan; + if (!batadv_vlan_id_valid(vid)) + return NULL; + spin_lock_bh(&orig_node->vlan_list_lock); /* first look if an object for this vid already exists */ diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index b21ff3c36b07..2243cec18ecc 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -209,6 +209,20 @@ batadv_tt_global_hash_find(struct batadv_priv *bat_priv, const u8 *addr, } /** + * batadv_tt_local_entry_free_rcu() - free the tt_local_entry + * @rcu: rcu pointer of the tt_local_entry + */ +static void batadv_tt_local_entry_free_rcu(struct rcu_head *rcu) +{ + struct batadv_tt_local_entry *tt_local_entry; + + tt_local_entry = container_of(rcu, struct batadv_tt_local_entry, + common.rcu); + + kmem_cache_free(batadv_tl_cache, tt_local_entry); +} + +/** * batadv_tt_local_entry_release() - release tt_local_entry from lists and queue * for free after rcu grace period * @ref: kref pointer of the nc_node @@ -222,7 +236,7 @@ static void batadv_tt_local_entry_release(struct kref *ref) batadv_softif_vlan_put(tt_local_entry->vlan); - kfree_rcu(tt_local_entry, common.rcu); + call_rcu(&tt_local_entry->common.rcu, batadv_tt_local_entry_free_rcu); } /** @@ -241,6 +255,20 @@ batadv_tt_local_entry_put(struct batadv_tt_local_entry *tt_local_entry) } /** + * batadv_tt_global_entry_free_rcu() - free the tt_global_entry + * @rcu: rcu pointer of the tt_global_entry + */ +static void batadv_tt_global_entry_free_rcu(struct rcu_head *rcu) +{ + struct batadv_tt_global_entry *tt_global_entry; + + tt_global_entry = container_of(rcu, struct batadv_tt_global_entry, + common.rcu); + + kmem_cache_free(batadv_tg_cache, tt_global_entry); +} + +/** * batadv_tt_global_entry_release() - release tt_global_entry from lists and * queue for free after rcu grace period * @ref: kref pointer of the nc_node @@ -254,7 +282,7 @@ void batadv_tt_global_entry_release(struct kref *ref) batadv_tt_global_del_orig_list(tt_global_entry); - kfree_rcu(tt_global_entry, common.rcu); + call_rcu(&tt_global_entry->common.rcu, batadv_tt_global_entry_free_rcu); } /** @@ -380,6 +408,19 @@ static void batadv_tt_global_size_dec(struct batadv_orig_node *orig_node, } /** + * batadv_tt_orig_list_entry_free_rcu() - free the orig_entry + * @rcu: rcu pointer of the orig_entry + */ +static void batadv_tt_orig_list_entry_free_rcu(struct rcu_head *rcu) +{ + struct batadv_tt_orig_list_entry *orig_entry; + + orig_entry = container_of(rcu, struct batadv_tt_orig_list_entry, rcu); + + kmem_cache_free(batadv_tt_orig_cache, orig_entry); +} + +/** * batadv_tt_orig_list_entry_release() - release tt orig entry from lists and * queue for free after rcu grace period * @ref: kref pointer of the tt orig entry @@ -392,7 +433,7 @@ static void batadv_tt_orig_list_entry_release(struct kref *ref) refcount); batadv_orig_node_put(orig_entry->orig_node); - kfree_rcu(orig_entry, rcu); + call_rcu(&orig_entry->rcu, batadv_tt_orig_list_entry_free_rcu); } /** diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 16daa79b7981..a8a7d2b36870 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -1194,7 +1194,7 @@ int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance) cp.own_addr_type = own_addr_type; cp.channel_map = hdev->le_adv_channel_map; - cp.handle = instance; + cp.handle = adv ? adv->handle : instance; if (flags & MGMT_ADV_FLAG_SEC_2M) { cp.primary_phy = HCI_ADV_PHY_1M; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 5b509b767557..aed025734d04 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4011,8 +4011,8 @@ static void l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, status = L2CAP_CS_AUTHOR_PEND; chan->ops->defer(chan); } else { - l2cap_state_change(chan, BT_CONNECT2); - result = L2CAP_CR_PEND; + l2cap_state_change(chan, BT_CONFIG); + result = L2CAP_CR_SUCCESS; status = L2CAP_CS_NO_INFO; } } else { @@ -4647,13 +4647,7 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, memset(&rsp, 0, sizeof(rsp)); - if (max > hcon->le_conn_max_interval) { - BT_DBG("requested connection interval exceeds current bounds."); - err = -EINVAL; - } else { - err = hci_check_conn_params(min, max, latency, to_multiplier); - } - + err = hci_check_conn_params(min, max, latency, to_multiplier); if (err) rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_REJECTED); else diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 36ae54f57bf5..a6d7f790cdda 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -283,9 +283,10 @@ static int xdp_recv_frames(struct xdp_frame **frames, int nframes, static int xdp_test_run_batch(struct xdp_test_data *xdp, struct bpf_prog *prog, u32 repeat) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; int err = 0, act, ret, i, nframes = 0, batch_sz; struct xdp_frame **frames = xdp->frames; + struct bpf_redirect_info *ri; struct xdp_page_head *head; struct xdp_frame *frm; bool redirect = false; @@ -295,6 +296,8 @@ static int xdp_test_run_batch(struct xdp_test_data *xdp, struct bpf_prog *prog, batch_sz = min_t(u32, repeat, xdp->batch_size); local_bh_disable(); + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); + ri = bpf_net_ctx_get_ri(); xdp_set_return_frame_no_direct(); for (i = 0; i < batch_sz; i++) { @@ -359,6 +362,7 @@ out: } xdp_clear_return_frame_no_direct(); + bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); return err; } @@ -394,6 +398,7 @@ static int bpf_test_run_xdp_live(struct bpf_prog *prog, struct xdp_buff *ctx, static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *retval, u32 *time, bool xdp) { + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct bpf_prog_array_item item = {.prog = prog}; struct bpf_run_ctx *old_ctx; struct bpf_cg_run_ctx run_ctx; @@ -419,10 +424,14 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, do { run_ctx.prog_item = &item; local_bh_disable(); + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); + if (xdp) *retval = bpf_prog_run_xdp(prog, ctx); else *retval = bpf_prog_run(prog, ctx); + + bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); } while (bpf_test_timer_continue(&t, 1, repeat, &ret, time)); bpf_reset_run_ctx(old_ctx); diff --git a/net/bridge/br_mst.c b/net/bridge/br_mst.c index 3c66141d34d6..1820f09ff59c 100644 --- a/net/bridge/br_mst.c +++ b/net/bridge/br_mst.c @@ -73,11 +73,10 @@ int br_mst_get_state(const struct net_device *dev, u16 msti, u8 *state) } EXPORT_SYMBOL_GPL(br_mst_get_state); -static void br_mst_vlan_set_state(struct net_bridge_port *p, struct net_bridge_vlan *v, +static void br_mst_vlan_set_state(struct net_bridge_vlan_group *vg, + struct net_bridge_vlan *v, u8 state) { - struct net_bridge_vlan_group *vg = nbp_vlan_group(p); - if (br_vlan_get_state(v) == state) return; @@ -103,7 +102,7 @@ int br_mst_set_state(struct net_bridge_port *p, u16 msti, u8 state, int err = 0; rcu_read_lock(); - vg = nbp_vlan_group(p); + vg = nbp_vlan_group_rcu(p); if (!vg) goto out; @@ -121,7 +120,7 @@ int br_mst_set_state(struct net_bridge_port *p, u16 msti, u8 state, if (v->brvlan->msti != msti) continue; - br_mst_vlan_set_state(p, v, state); + br_mst_vlan_set_state(vg, v, state); } out: @@ -140,13 +139,13 @@ static void br_mst_vlan_sync_state(struct net_bridge_vlan *pv, u16 msti) * it. */ if (v != pv && v->brvlan->msti == msti) { - br_mst_vlan_set_state(pv->port, pv, v->state); + br_mst_vlan_set_state(vg, pv, v->state); return; } } /* Otherwise, start out in a new MSTI with all ports disabled. */ - return br_mst_vlan_set_state(pv->port, pv, BR_STATE_DISABLED); + return br_mst_vlan_set_state(vg, pv, BR_STATE_DISABLED); } int br_mst_vlan_set_msti(struct net_bridge_vlan *mv, u16 msti) diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index bf30c50b5689..3c9f6538990e 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -137,6 +137,7 @@ static inline bool is_pppoe_ipv6(const struct sk_buff *skb, #define NF_BRIDGE_MAX_MAC_HEADER_LENGTH (PPPOE_SES_HLEN + ETH_HLEN) struct brnf_frag_data { + local_lock_t bh_lock; char mac[NF_BRIDGE_MAX_MAC_HEADER_LENGTH]; u8 encap_size; u8 size; @@ -144,7 +145,9 @@ struct brnf_frag_data { __be16 vlan_proto; }; -static DEFINE_PER_CPU(struct brnf_frag_data, brnf_frag_data_storage); +static DEFINE_PER_CPU(struct brnf_frag_data, brnf_frag_data_storage) = { + .bh_lock = INIT_LOCAL_LOCK(bh_lock), +}; static void nf_bridge_info_free(struct sk_buff *skb) { @@ -850,6 +853,7 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); unsigned int mtu, mtu_reserved; + int ret; mtu_reserved = nf_bridge_mtu_reduction(skb); mtu = skb->dev->mtu; @@ -882,6 +886,7 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff IPCB(skb)->frag_max_size = nf_bridge->frag_max_size; + local_lock_nested_bh(&brnf_frag_data_storage.bh_lock); data = this_cpu_ptr(&brnf_frag_data_storage); if (skb_vlan_tag_present(skb)) { @@ -897,7 +902,9 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff skb_copy_from_linear_data_offset(skb, -data->size, data->mac, data->size); - return br_nf_ip_fragment(net, sk, skb, br_nf_push_frag_xmit); + ret = br_nf_ip_fragment(net, sk, skb, br_nf_push_frag_xmit); + local_unlock_nested_bh(&brnf_frag_data_storage.bh_lock); + return ret; } if (IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) && skb->protocol == htons(ETH_P_IPV6)) { @@ -909,6 +916,7 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size; + local_lock_nested_bh(&brnf_frag_data_storage.bh_lock); data = this_cpu_ptr(&brnf_frag_data_storage); data->encap_size = nf_bridge_encap_header_len(skb); data->size = ETH_HLEN + data->encap_size; @@ -916,8 +924,12 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff skb_copy_from_linear_data_offset(skb, -data->size, data->mac, data->size); - if (v6ops) - return v6ops->fragment(net, sk, skb, br_nf_push_frag_xmit); + if (v6ops) { + ret = v6ops->fragment(net, sk, skb, br_nf_push_frag_xmit); + local_unlock_nested_bh(&brnf_frag_data_storage.bh_lock); + return ret; + } + local_unlock_nested_bh(&brnf_frag_data_storage.bh_lock); kfree_skb(skb); return -EMSGSIZE; diff --git a/net/can/Kconfig b/net/can/Kconfig index cb56be8e3862..af64a6f76458 100644 --- a/net/can/Kconfig +++ b/net/can/Kconfig @@ -56,18 +56,17 @@ config CAN_GW source "net/can/j1939/Kconfig" config CAN_ISOTP - tristate "ISO 15765-2:2016 CAN transport protocol" + tristate "ISO 15765-2 CAN transport protocol" help CAN Transport Protocols offer support for segmented Point-to-Point communication between CAN nodes via two defined CAN Identifiers. + This protocol driver implements segmented data transfers for CAN CC + (aka Classical CAN, CAN 2.0B) and CAN FD frame types which were + introduced with ISO 15765-2:2016. As CAN frames can only transport a small amount of data bytes - (max. 8 bytes for 'classic' CAN and max. 64 bytes for CAN FD) this + (max. 8 bytes for CAN CC and max. 64 bytes for CAN FD) this segmentation is needed to transport longer Protocol Data Units (PDU) as needed e.g. for vehicle diagnosis (UDS, ISO 14229) or IP-over-CAN traffic. - This protocol driver implements data transfers according to - ISO 15765-2:2016 for 'classic' CAN and CAN FD frame types. - If you want to perform automotive vehicle diagnostic services (UDS), - say 'y'. endif diff --git a/net/can/isotp.c b/net/can/isotp.c index 25bac0fafc83..16046931542a 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -72,7 +72,7 @@ #include <net/sock.h> #include <net/net_namespace.h> -MODULE_DESCRIPTION("PF_CAN isotp 15765-2:2016 protocol"); +MODULE_DESCRIPTION("PF_CAN ISO 15765-2 transport protocol"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp <[email protected]>"); MODULE_ALIAS("can-proto-6"); @@ -83,10 +83,11 @@ MODULE_ALIAS("can-proto-6"); (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \ (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG)) -/* ISO 15765-2:2016 supports more than 4095 byte per ISO PDU as the FF_DL can - * take full 32 bit values (4 Gbyte). We would need some good concept to handle - * this between user space and kernel space. For now set the static buffer to - * something about 8 kbyte to be able to test this new functionality. +/* Since ISO 15765-2:2016 the CAN isotp protocol supports more than 4095 + * byte per ISO PDU as the FF_DL can take full 32 bit values (4 Gbyte). + * We would need some good concept to handle this between user space and + * kernel space. For now set the static buffer to something about 8 kbyte + * to be able to test this new functionality. */ #define DEFAULT_MAX_PDU_SIZE 8300 diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index a6fb89fa6278..7e8a20f2fc42 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -30,10 +30,6 @@ MODULE_ALIAS("can-proto-" __stringify(CAN_J1939)); /* CAN_HDR: #bytes before can_frame data part */ #define J1939_CAN_HDR (offsetof(struct can_frame, data)) -/* CAN_FTR: #bytes beyond data part */ -#define J1939_CAN_FTR (sizeof(struct can_frame) - J1939_CAN_HDR - \ - sizeof(((struct can_frame *)0)->data)) - /* lowest layer */ static void j1939_can_recv(struct sk_buff *iskb, void *data) { @@ -342,7 +338,7 @@ int j1939_send_one(struct j1939_priv *priv, struct sk_buff *skb) memset(cf, 0, J1939_CAN_HDR); /* make it a full can frame again */ - skb_put(skb, J1939_CAN_FTR + (8 - dlc)); + skb_put_zero(skb, 8 - dlc); canid = CAN_EFF_FLAG | (skcb->priority << 26) | diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index fe3df23a2595..4be73de5033c 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -1593,8 +1593,8 @@ j1939_session *j1939_xtp_rx_rts_session_new(struct j1939_priv *priv, struct j1939_sk_buff_cb skcb = *j1939_skb_to_cb(skb); struct j1939_session *session; const u8 *dat; + int len, ret; pgn_t pgn; - int len; netdev_dbg(priv->ndev, "%s\n", __func__); @@ -1653,7 +1653,22 @@ j1939_session *j1939_xtp_rx_rts_session_new(struct j1939_priv *priv, session->tskey = priv->rx_tskey++; j1939_sk_errqueue(session, J1939_ERRQUEUE_RX_RTS); - WARN_ON_ONCE(j1939_session_activate(session)); + ret = j1939_session_activate(session); + if (ret) { + /* Entering this scope indicates an issue with the J1939 bus. + * Possible scenarios include: + * - A time lapse occurred, and a new session was initiated + * due to another packet being sent correctly. This could + * have been caused by too long interrupt, debugger, or being + * out-scheduled by another task. + * - The bus is receiving numerous erroneous packets, either + * from a malfunctioning device or during a test scenario. + */ + netdev_alert(priv->ndev, "%s: 0x%p: concurrent session with same addr (%02x %02x) is already active.\n", + __func__, session, skcb.addr.sa, skcb.addr.da); + j1939_session_put(session); + return NULL; + } return session; } @@ -1681,6 +1696,8 @@ static int j1939_xtp_rx_rts_session_active(struct j1939_session *session, j1939_session_timers_cancel(session); j1939_session_cancel(session, J1939_XTP_ABORT_BUSY); + if (session->transmission) + j1939_session_deactivate_activate_next(session); return -EBUSY; } diff --git a/net/core/datagram.c b/net/core/datagram.c index e614cfd8e14a..95f242591fd2 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -417,14 +417,14 @@ static int __skb_datagram_iter(const struct sk_buff *skb, int offset, end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { struct page *page = skb_frag_page(frag); - u8 *vaddr = kmap(page); + u8 *vaddr = kmap_local_page(page); if (copy > len) copy = len; n = INDIRECT_CALL_1(cb, simple_copy_to_iter, vaddr + skb_frag_off(frag) + offset - start, copy, data, to); - kunmap(page); + kunmap_local(vaddr); offset += n; if (n != copy) goto short_copy; diff --git a/net/core/dev.c b/net/core/dev.c index e62698c7a0e6..0a23d7da7fbc 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -229,7 +229,7 @@ static inline void backlog_lock_irq_save(struct softnet_data *sd, { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_lock_irqsave(&sd->input_pkt_queue.lock, *flags); - else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + else local_irq_save(*flags); } @@ -237,7 +237,7 @@ static inline void backlog_lock_irq_disable(struct softnet_data *sd) { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_lock_irq(&sd->input_pkt_queue.lock); - else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + else local_irq_disable(); } @@ -246,7 +246,7 @@ static inline void backlog_unlock_irq_restore(struct softnet_data *sd, { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_unlock_irqrestore(&sd->input_pkt_queue.lock, *flags); - else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + else local_irq_restore(*flags); } @@ -254,7 +254,7 @@ static inline void backlog_unlock_irq_enable(struct softnet_data *sd) { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_unlock_irq(&sd->input_pkt_queue.lock); - else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + else local_irq_enable(); } @@ -449,7 +449,9 @@ static RAW_NOTIFIER_HEAD(netdev_chain); * queue in the local softnet handler. */ -DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); +DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data) = { + .process_queue_bh_lock = INIT_LOCAL_LOCK(process_queue_bh_lock), +}; EXPORT_PER_CPU_SYMBOL(softnet_data); /* Page_pool has a lockless array/stack to alloc/recycle pages. @@ -1226,9 +1228,9 @@ int dev_change_name(struct net_device *dev, const char *newname) memcpy(oldname, dev->name, IFNAMSIZ); - write_seqlock(&netdev_rename_lock); + write_seqlock_bh(&netdev_rename_lock); err = dev_get_valid_name(net, dev, newname); - write_sequnlock(&netdev_rename_lock); + write_sequnlock_bh(&netdev_rename_lock); if (err < 0) { up_write(&devnet_rename_sem); @@ -1269,9 +1271,9 @@ rollback: if (err >= 0) { err = ret; down_write(&devnet_rename_sem); - write_seqlock(&netdev_rename_lock); + write_seqlock_bh(&netdev_rename_lock); memcpy(dev->name, oldname, IFNAMSIZ); - write_sequnlock(&netdev_rename_lock); + write_sequnlock_bh(&netdev_rename_lock); memcpy(oldname, newname, IFNAMSIZ); WRITE_ONCE(dev->name_assign_type, old_assign_type); old_assign_type = NET_NAME_RENAMED; @@ -3940,6 +3942,7 @@ netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb) return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm)); } +#ifndef CONFIG_PREEMPT_RT static bool netdev_xmit_txqueue_skipped(void) { return __this_cpu_read(softnet_data.xmit.skip_txqueue); @@ -3950,6 +3953,19 @@ void netdev_xmit_skip_txqueue(bool skip) __this_cpu_write(softnet_data.xmit.skip_txqueue, skip); } EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue); + +#else +static bool netdev_xmit_txqueue_skipped(void) +{ + return current->net_xmit.skip_txqueue; +} + +void netdev_xmit_skip_txqueue(bool skip) +{ + current->net_xmit.skip_txqueue = skip; +} +EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue); +#endif #endif /* CONFIG_NET_EGRESS */ #ifdef CONFIG_NET_XGRESS @@ -4029,10 +4045,13 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, { struct bpf_mprog_entry *entry = rcu_dereference_bh(skb->dev->tcx_ingress); enum skb_drop_reason drop_reason = SKB_DROP_REASON_TC_INGRESS; + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; int sch_ret; if (!entry) return skb; + + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); if (*pt_prev) { *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; @@ -4061,10 +4080,12 @@ ingress_verdict: break; } *ret = NET_RX_SUCCESS; + bpf_net_ctx_clear(bpf_net_ctx); return NULL; case TC_ACT_SHOT: kfree_skb_reason(skb, drop_reason); *ret = NET_RX_DROP; + bpf_net_ctx_clear(bpf_net_ctx); return NULL; /* used by tc_run */ case TC_ACT_STOLEN: @@ -4074,8 +4095,10 @@ ingress_verdict: fallthrough; case TC_ACT_CONSUMED: *ret = NET_RX_SUCCESS; + bpf_net_ctx_clear(bpf_net_ctx); return NULL; } + bpf_net_ctx_clear(bpf_net_ctx); return skb; } @@ -4085,11 +4108,14 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) { struct bpf_mprog_entry *entry = rcu_dereference_bh(dev->tcx_egress); enum skb_drop_reason drop_reason = SKB_DROP_REASON_TC_EGRESS; + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; int sch_ret; if (!entry) return skb; + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); + /* qdisc_skb_cb(skb)->pkt_len & tcx_set_ingress() was * already set by the caller. */ @@ -4105,10 +4131,12 @@ egress_verdict: /* No need to push/pop skb's mac_header here on egress! */ skb_do_redirect(skb); *ret = NET_XMIT_SUCCESS; + bpf_net_ctx_clear(bpf_net_ctx); return NULL; case TC_ACT_SHOT: kfree_skb_reason(skb, drop_reason); *ret = NET_XMIT_DROP; + bpf_net_ctx_clear(bpf_net_ctx); return NULL; /* used by tc_run */ case TC_ACT_STOLEN: @@ -4118,8 +4146,10 @@ egress_verdict: fallthrough; case TC_ACT_CONSUMED: *ret = NET_XMIT_SUCCESS; + bpf_net_ctx_clear(bpf_net_ctx); return NULL; } + bpf_net_ctx_clear(bpf_net_ctx); return skb; } @@ -5234,7 +5264,7 @@ static __latent_entropy void net_tx_action(struct softirq_action *h) trace_consume_skb(skb, net_tx_action); else trace_kfree_skb(skb, net_tx_action, - get_kfree_skb_cb(skb)->reason); + get_kfree_skb_cb(skb)->reason, NULL); if (skb->fclone != SKB_FCLONE_UNAVAILABLE) __kfree_skb(skb); @@ -5935,6 +5965,7 @@ static void flush_backlog(struct work_struct *work) } backlog_unlock_irq_enable(sd); + local_lock_nested_bh(&softnet_data.process_queue_bh_lock); skb_queue_walk_safe(&sd->process_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->process_queue); @@ -5942,6 +5973,7 @@ static void flush_backlog(struct work_struct *work) rps_input_queue_head_incr(sd); } } + local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); local_bh_enable(); } @@ -6063,7 +6095,9 @@ static int process_backlog(struct napi_struct *napi, int quota) while (again) { struct sk_buff *skb; + local_lock_nested_bh(&softnet_data.process_queue_bh_lock); while ((skb = __skb_dequeue(&sd->process_queue))) { + local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); rcu_read_lock(); __netif_receive_skb(skb); rcu_read_unlock(); @@ -6072,7 +6106,9 @@ static int process_backlog(struct napi_struct *napi, int quota) return work; } + local_lock_nested_bh(&softnet_data.process_queue_bh_lock); } + local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); backlog_lock_irq_disable(sd); if (skb_queue_empty(&sd->input_pkt_queue)) { @@ -6087,8 +6123,10 @@ static int process_backlog(struct napi_struct *napi, int quota) napi->state &= NAPIF_STATE_THREADED; again = false; } else { + local_lock_nested_bh(&softnet_data.process_queue_bh_lock); skb_queue_splice_tail_init(&sd->input_pkt_queue, &sd->process_queue); + local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); } backlog_unlock_irq_enable(sd); } @@ -6301,6 +6339,7 @@ enum { static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, unsigned flags, u16 budget) { + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; bool skip_schedule = false; unsigned long timeout; int rc; @@ -6318,6 +6357,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, clear_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state); local_bh_disable(); + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); if (flags & NAPI_F_PREFER_BUSY_POLL) { napi->defer_hard_irqs_count = READ_ONCE(napi->dev->napi_defer_hard_irqs); @@ -6340,6 +6380,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, netpoll_poll_unlock(have_poll_lock); if (rc == budget) __busy_poll_stop(napi, skip_schedule); + bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); } @@ -6349,6 +6390,7 @@ static void __napi_busy_loop(unsigned int napi_id, { unsigned long start_time = loop_end ? busy_loop_current_time() : 0; int (*napi_poll)(struct napi_struct *napi, int budget); + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; void *have_poll_lock = NULL; struct napi_struct *napi; @@ -6367,6 +6409,7 @@ restart: int work = 0; local_bh_disable(); + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); if (!napi_poll) { unsigned long val = READ_ONCE(napi->state); @@ -6397,6 +6440,7 @@ count: __NET_ADD_STATS(dev_net(napi->dev), LINUX_MIB_BUSYPOLLRXPACKETS, work); skb_defer_free_flush(this_cpu_ptr(&softnet_data)); + bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); if (!loop_end || loop_end(loop_end_arg, start_time)) @@ -6824,6 +6868,7 @@ static int napi_thread_wait(struct napi_struct *napi) static void napi_threaded_poll_loop(struct napi_struct *napi) { + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct softnet_data *sd; unsigned long last_qs = jiffies; @@ -6832,6 +6877,8 @@ static void napi_threaded_poll_loop(struct napi_struct *napi) void *have; local_bh_disable(); + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); + sd = this_cpu_ptr(&softnet_data); sd->in_napi_threaded_poll = true; @@ -6847,6 +6894,7 @@ static void napi_threaded_poll_loop(struct napi_struct *napi) net_rps_action_and_irq_enable(sd); } skb_defer_free_flush(sd); + bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); if (!repoll) @@ -6872,10 +6920,12 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) struct softnet_data *sd = this_cpu_ptr(&softnet_data); unsigned long time_limit = jiffies + usecs_to_jiffies(READ_ONCE(net_hotdata.netdev_budget_usecs)); + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; int budget = READ_ONCE(net_hotdata.netdev_budget); LIST_HEAD(list); LIST_HEAD(repoll); + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); start: sd->in_net_rx_action = true; local_irq_disable(); @@ -6928,7 +6978,8 @@ start: sd->in_net_rx_action = false; net_rps_action_and_irq_enable(sd); -end:; +end: + bpf_net_ctx_clear(bpf_net_ctx); } struct netdev_adjacent { @@ -10703,6 +10754,54 @@ void netdev_run_todo(void) wake_up(&netdev_unregistering_wq); } +/* Collate per-cpu network dstats statistics + * + * Read per-cpu network statistics from dev->dstats and populate the related + * fields in @s. + */ +static void dev_fetch_dstats(struct rtnl_link_stats64 *s, + const struct pcpu_dstats __percpu *dstats) +{ + int cpu; + + for_each_possible_cpu(cpu) { + u64 rx_packets, rx_bytes, rx_drops; + u64 tx_packets, tx_bytes, tx_drops; + const struct pcpu_dstats *stats; + unsigned int start; + + stats = per_cpu_ptr(dstats, cpu); + do { + start = u64_stats_fetch_begin(&stats->syncp); + rx_packets = u64_stats_read(&stats->rx_packets); + rx_bytes = u64_stats_read(&stats->rx_bytes); + rx_drops = u64_stats_read(&stats->rx_drops); + tx_packets = u64_stats_read(&stats->tx_packets); + tx_bytes = u64_stats_read(&stats->tx_bytes); + tx_drops = u64_stats_read(&stats->tx_drops); + } while (u64_stats_fetch_retry(&stats->syncp, start)); + + s->rx_packets += rx_packets; + s->rx_bytes += rx_bytes; + s->rx_dropped += rx_drops; + s->tx_packets += tx_packets; + s->tx_bytes += tx_bytes; + s->tx_dropped += tx_drops; + } +} + +/* ndo_get_stats64 implementation for dtstats-based accounting. + * + * Populate @s from dev->stats and dev->dstats. This is used internally by the + * core for NETDEV_PCPU_STAT_DSTAT-type stats collection. + */ +static void dev_get_dstats64(const struct net_device *dev, + struct rtnl_link_stats64 *s) +{ + netdev_stats_to_stats64(s, &dev->stats); + dev_fetch_dstats(s, dev->dstats); +} + /* Convert net_device_stats to rtnl_link_stats64. rtnl_link_stats64 has * all the same fields in the same order as net_device_stats, with only * the type differing, but rtnl_link_stats64 may have additional fields @@ -10779,6 +10878,8 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev)); } else if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_TSTATS) { dev_get_tstats64(dev, storage); + } else if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_DSTATS) { + dev_get_dstats64(dev, storage); } else { netdev_stats_to_stats64(storage, &dev->stats); } @@ -11419,9 +11520,9 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, if (new_name[0]) { /* Rename the netdev to prepared name */ - write_seqlock(&netdev_rename_lock); + write_seqlock_bh(&netdev_rename_lock); strscpy(dev->name, new_name, IFNAMSIZ); - write_sequnlock(&netdev_rename_lock); + write_sequnlock_bh(&netdev_rename_lock); } /* Fixup kobjects */ diff --git a/net/core/dev.h b/net/core/dev.h index b7b518bc2be5..5654325c5b71 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -150,6 +150,8 @@ struct napi_struct *napi_by_id(unsigned int napi_id); void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu); #define XMIT_RECURSION_LIMIT 8 + +#ifndef CONFIG_PREEMPT_RT static inline bool dev_xmit_recursion(void) { return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > @@ -165,5 +167,25 @@ static inline void dev_xmit_recursion_dec(void) { __this_cpu_dec(softnet_data.xmit.recursion); } +#else +static inline bool dev_xmit_recursion(void) +{ + return unlikely(current->net_xmit.recursion > XMIT_RECURSION_LIMIT); +} + +static inline void dev_xmit_recursion_inc(void) +{ + current->net_xmit.recursion++; +} + +static inline void dev_xmit_recursion_dec(void) +{ + current->net_xmit.recursion--; +} +#endif + +int dev_set_hwtstamp_phylib(struct net_device *dev, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack); #endif diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 9a66cf5015f2..b9719ed3c3fd 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -363,7 +363,6 @@ int dev_set_hwtstamp_phylib(struct net_device *dev, return 0; } -EXPORT_SYMBOL_GPL(dev_set_hwtstamp_phylib); static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr) { diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 430ed18f8584..2e0ae3328232 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -109,7 +109,8 @@ static u32 net_dm_queue_len = 1000; struct net_dm_alert_ops { void (*kfree_skb_probe)(void *ignore, struct sk_buff *skb, void *location, - enum skb_drop_reason reason); + enum skb_drop_reason reason, + struct sock *rx_sk); void (*napi_poll_probe)(void *ignore, struct napi_struct *napi, int work, int budget); void (*work_item_func)(struct work_struct *work); @@ -264,7 +265,8 @@ out: static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location, - enum skb_drop_reason reason) + enum skb_drop_reason reason, + struct sock *rx_sk) { trace_drop_common(skb, location); } @@ -491,7 +493,8 @@ static const struct net_dm_alert_ops net_dm_alert_summary_ops = { static void net_dm_packet_trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location, - enum skb_drop_reason reason) + enum skb_drop_reason reason, + struct sock *rx_sk) { ktime_t tstamp = ktime_get_real(); struct per_cpu_dm_data *data; diff --git a/net/core/filter.c b/net/core/filter.c index 7c46ecba3b01..eb1c4425c06f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1658,13 +1658,21 @@ struct bpf_scratchpad { __be32 diff[MAX_BPF_STACK / sizeof(__be32)]; u8 buff[MAX_BPF_STACK]; }; + local_lock_t bh_lock; }; -static DEFINE_PER_CPU(struct bpf_scratchpad, bpf_sp); +static DEFINE_PER_CPU(struct bpf_scratchpad, bpf_sp) = { + .bh_lock = INIT_LOCAL_LOCK(bh_lock), +}; static inline int __bpf_try_make_writable(struct sk_buff *skb, unsigned int write_len) { +#ifdef CONFIG_DEBUG_NET + /* Avoid a splat in pskb_may_pull_reason() */ + if (write_len > INT_MAX) + return -EINVAL; +#endif return skb_ensure_writable(skb, write_len); } @@ -2016,6 +2024,7 @@ BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size, struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp); u32 diff_size = from_size + to_size; int i, j = 0; + __wsum ret; /* This is quite flexible, some examples: * @@ -2029,12 +2038,15 @@ BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size, diff_size > sizeof(sp->diff))) return -EINVAL; + local_lock_nested_bh(&bpf_sp.bh_lock); for (i = 0; i < from_size / sizeof(__be32); i++, j++) sp->diff[j] = ~from[i]; for (i = 0; i < to_size / sizeof(__be32); i++, j++) sp->diff[j] = to[i]; - return csum_partial(sp->diff, diff_size, seed); + ret = csum_partial(sp->diff, diff_size, seed); + local_unlock_nested_bh(&bpf_sp.bh_lock); + return ret; } static const struct bpf_func_proto bpf_csum_diff_proto = { @@ -2471,9 +2483,6 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = { .arg3_type = ARG_ANYTHING, }; -DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); -EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info); - static struct net_device *skb_get_peer_dev(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; @@ -2486,7 +2495,7 @@ static struct net_device *skb_get_peer_dev(struct net_device *dev) int skb_do_redirect(struct sk_buff *skb) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); struct net *net = dev_net(skb->dev); struct net_device *dev; u32 flags = ri->flags; @@ -2519,7 +2528,7 @@ out_drop: BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return TC_ACT_SHOT; @@ -2540,7 +2549,7 @@ static const struct bpf_func_proto bpf_redirect_proto = { BPF_CALL_2(bpf_redirect_peer, u32, ifindex, u64, flags) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely(flags)) return TC_ACT_SHOT; @@ -2562,7 +2571,7 @@ static const struct bpf_func_proto bpf_redirect_peer_proto = { BPF_CALL_4(bpf_redirect_neigh, u32, ifindex, struct bpf_redir_neigh *, params, int, plen, u64, flags) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely((plen && plen < sizeof(*params)) || flags)) return TC_ACT_SHOT; @@ -4288,30 +4297,13 @@ void xdp_do_check_flushed(struct napi_struct *napi) } #endif -void bpf_clear_redirect_map(struct bpf_map *map) -{ - struct bpf_redirect_info *ri; - int cpu; - - for_each_possible_cpu(cpu) { - ri = per_cpu_ptr(&bpf_redirect_info, cpu); - /* Avoid polluting remote cacheline due to writes if - * not needed. Once we pass this test, we need the - * cmpxchg() to make sure it hasn't been changed in - * the meantime by remote CPU. - */ - if (unlikely(READ_ONCE(ri->map) == map)) - cmpxchg(&ri->map, map, NULL); - } -} - DEFINE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key); EXPORT_SYMBOL_GPL(bpf_master_redirect_enabled_key); u32 xdp_master_redirect(struct xdp_buff *xdp) { + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); struct net_device *master, *slave; - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); master = netdev_master_upper_dev_get_rcu(xdp->rxq->dev); slave = master->netdev_ops->ndo_xdp_get_xmit_slave(master, xdp); @@ -4383,7 +4375,7 @@ static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, map = READ_ONCE(ri->map); /* The map pointer is cleared when the map is being torn - * down by bpf_clear_redirect_map() + * down by dev_map_free() */ if (unlikely(!map)) { err = -ENOENT; @@ -4428,7 +4420,7 @@ err: int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; if (map_type == BPF_MAP_TYPE_XSKMAP) @@ -4442,7 +4434,7 @@ EXPORT_SYMBOL_GPL(xdp_do_redirect); int xdp_do_redirect_frame(struct net_device *dev, struct xdp_buff *xdp, struct xdp_frame *xdpf, struct bpf_prog *xdp_prog) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; if (map_type == BPF_MAP_TYPE_XSKMAP) @@ -4459,7 +4451,7 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, enum bpf_map_type map_type, u32 map_id, u32 flags) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); struct bpf_map *map; int err; @@ -4471,7 +4463,7 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, map = READ_ONCE(ri->map); /* The map pointer is cleared when the map is being torn - * down by bpf_clear_redirect_map() + * down by dev_map_free() */ if (unlikely(!map)) { err = -ENOENT; @@ -4513,7 +4505,7 @@ err: int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; @@ -4549,7 +4541,7 @@ err: BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely(flags)) return XDP_ABORTED; @@ -6450,6 +6442,7 @@ BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset, void *srh_tlvs, *srh_end, *ptr; int srhoff = 0; + lockdep_assert_held(&srh_state->bh_lock); if (srh == NULL) return -EINVAL; @@ -6506,6 +6499,7 @@ BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb, int hdroff = 0; int err; + lockdep_assert_held(&srh_state->bh_lock); switch (action) { case SEG6_LOCAL_ACTION_END_X: if (!seg6_bpf_has_valid_srh(skb)) @@ -6582,6 +6576,7 @@ BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset, int srhoff = 0; int ret; + lockdep_assert_held(&srh_state->bh_lock); if (unlikely(srh == NULL)) return -EINVAL; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 59fe46077b3c..e64a26379807 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1806,6 +1806,13 @@ u32 flow_hash_from_keys(struct flow_keys *keys) } EXPORT_SYMBOL(flow_hash_from_keys); +u32 flow_hash_from_keys_seed(struct flow_keys *keys, + const siphash_key_t *keyval) +{ + return __flow_hash_from_keys(keys, keyval); +} +EXPORT_SYMBOL(flow_hash_from_keys_seed); + static inline u32 ___skb_get_hash(const struct sk_buff *skb, struct flow_keys *keys, const siphash_key_t *keyval) @@ -1845,22 +1852,23 @@ EXPORT_SYMBOL(make_flow_keys_digest); static struct flow_dissector flow_keys_dissector_symmetric __read_mostly; -u32 __skb_get_hash_symmetric(const struct sk_buff *skb) +u32 __skb_get_hash_symmetric_net(const struct net *net, const struct sk_buff *skb) { struct flow_keys keys; __flow_hash_secret_init(); memset(&keys, 0, sizeof(keys)); - __skb_flow_dissect(NULL, skb, &flow_keys_dissector_symmetric, + __skb_flow_dissect(net, skb, &flow_keys_dissector_symmetric, &keys, NULL, 0, 0, 0, 0); return __flow_hash_from_keys(&keys, &hashrnd); } -EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric); +EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric_net); /** - * __skb_get_hash: calculate a flow hash + * __skb_get_hash_net: calculate a flow hash + * @net: associated network namespace, derived from @skb if NULL * @skb: sk_buff to calculate flow hash from * * This function calculates a flow hash based on src/dst addresses @@ -1868,18 +1876,24 @@ EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric); * on success, zero indicates no valid hash. Also, sets l4_hash in skb * if hash is a canonical 4-tuple hash over transport ports. */ -void __skb_get_hash(struct sk_buff *skb) +void __skb_get_hash_net(const struct net *net, struct sk_buff *skb) { struct flow_keys keys; u32 hash; + memset(&keys, 0, sizeof(keys)); + + __skb_flow_dissect(net, skb, &flow_keys_dissector, + &keys, NULL, 0, 0, 0, + FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); + __flow_hash_secret_init(); - hash = ___skb_get_hash(skb, &keys, &hashrnd); + hash = __flow_hash_from_keys(&keys, &hashrnd); __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } -EXPORT_SYMBOL(__skb_get_hash); +EXPORT_SYMBOL(__skb_get_hash_net); __u32 skb_get_hash_perturb(const struct sk_buff *skb, const siphash_key_t *perturb) diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 4a0797f0a154..afb05f58b64c 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -38,13 +38,14 @@ static inline struct bpf_lwt *bpf_lwt_lwtunnel(struct lwtunnel_state *lwt) static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, struct dst_entry *dst, bool can_redirect) { + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; int ret; - /* Migration disable and BH disable are needed to protect per-cpu - * redirect_info between BPF prog and skb_do_redirect(). + /* Disabling BH is needed to protect per-CPU bpf_redirect_info between + * BPF prog and skb_do_redirect(). */ - migrate_disable(); local_bh_disable(); + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); bpf_compute_data_pointers(skb); ret = bpf_prog_run_save_cb(lwt->prog, skb); @@ -77,8 +78,8 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, break; } + bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); - migrate_enable(); return ret; } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 4f7a61688d18..6a823ba906c6 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -693,11 +693,16 @@ EXPORT_SYMBOL_GPL(__put_net); * get_net_ns - increment the refcount of the network namespace * @ns: common namespace (net) * - * Returns the net's common namespace. + * Returns the net's common namespace or ERR_PTR() if ref is zero. */ struct ns_common *get_net_ns(struct ns_common *ns) { - return &get_net(container_of(ns, struct net, ns))->ns; + struct net *net; + + net = maybe_get_net(container_of(ns, struct net, ns)); + if (net) + return &net->ns; + return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(get_net_ns); diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 1f6ae6379e0f..05f9515d2c05 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -59,22 +59,22 @@ XDP_METADATA_KFUNC_xxx nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_RX_METADATA_FEATURES, xdp_rx_meta, NETDEV_A_DEV_PAD) || nla_put_u64_64bit(rsp, NETDEV_A_DEV_XSK_FEATURES, - xsk_features, NETDEV_A_DEV_PAD)) { - genlmsg_cancel(rsp, hdr); - return -EINVAL; - } + xsk_features, NETDEV_A_DEV_PAD)) + goto err_cancel_msg; if (netdev->xdp_features & NETDEV_XDP_ACT_XSK_ZEROCOPY) { if (nla_put_u32(rsp, NETDEV_A_DEV_XDP_ZC_MAX_SEGS, - netdev->xdp_zc_max_segs)) { - genlmsg_cancel(rsp, hdr); - return -EINVAL; - } + netdev->xdp_zc_max_segs)) + goto err_cancel_msg; } genlmsg_end(rsp, hdr); return 0; + +err_cancel_msg: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; } static void diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c8ac79851cd6..eb9a7e65b5c8 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -277,6 +277,7 @@ static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp_mask) #endif struct napi_alloc_cache { + local_lock_t bh_lock; struct page_frag_cache page; struct page_frag_1k page_small; unsigned int skb_count; @@ -284,7 +285,9 @@ struct napi_alloc_cache { }; static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); -static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache); +static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache) = { + .bh_lock = INIT_LOCAL_LOCK(bh_lock), +}; /* Double check that napi_get_frags() allocates skbs with * skb->head being backed by slab, not a page fragment. @@ -306,11 +309,16 @@ void napi_get_frags_check(struct napi_struct *napi) void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); + void *data; fragsz = SKB_DATA_ALIGN(fragsz); - return __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, + local_lock_nested_bh(&napi_alloc_cache.bh_lock); + data = __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask); + local_unlock_nested_bh(&napi_alloc_cache.bh_lock); + return data; + } EXPORT_SYMBOL(__napi_alloc_frag_align); @@ -318,19 +326,15 @@ void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { void *data; - fragsz = SKB_DATA_ALIGN(fragsz); if (in_hardirq() || irqs_disabled()) { struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache); + fragsz = SKB_DATA_ALIGN(fragsz); data = __page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, align_mask); } else { - struct napi_alloc_cache *nc; - local_bh_disable(); - nc = this_cpu_ptr(&napi_alloc_cache); - data = __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, - align_mask); + data = __napi_alloc_frag_align(fragsz, align_mask); local_bh_enable(); } return data; @@ -342,16 +346,20 @@ static struct sk_buff *napi_skb_cache_get(void) struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); struct sk_buff *skb; + local_lock_nested_bh(&napi_alloc_cache.bh_lock); if (unlikely(!nc->skb_count)) { nc->skb_count = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, GFP_ATOMIC, NAPI_SKB_CACHE_BULK, nc->skb_cache); - if (unlikely(!nc->skb_count)) + if (unlikely(!nc->skb_count)) { + local_unlock_nested_bh(&napi_alloc_cache.bh_lock); return NULL; + } } skb = nc->skb_cache[--nc->skb_count]; + local_unlock_nested_bh(&napi_alloc_cache.bh_lock); kasan_mempool_unpoison_object(skb, kmem_cache_size(net_hotdata.skbuff_cache)); return skb; @@ -744,9 +752,13 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, pfmemalloc = nc->pfmemalloc; } else { local_bh_disable(); + local_lock_nested_bh(&napi_alloc_cache.bh_lock); + nc = this_cpu_ptr(&napi_alloc_cache.page); data = page_frag_alloc(nc, len, gfp_mask); pfmemalloc = nc->pfmemalloc; + + local_unlock_nested_bh(&napi_alloc_cache.bh_lock); local_bh_enable(); } @@ -810,11 +822,11 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) goto skb_success; } - nc = this_cpu_ptr(&napi_alloc_cache); - if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; + local_lock_nested_bh(&napi_alloc_cache.bh_lock); + nc = this_cpu_ptr(&napi_alloc_cache); if (NAPI_HAS_SMALL_PAGE_FRAG && len <= SKB_WITH_OVERHEAD(1024)) { /* we are artificially inflating the allocation size, but * that is not as bad as it may look like, as: @@ -836,6 +848,7 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) data = page_frag_alloc(&nc->page, len, gfp_mask); pfmemalloc = nc->page.pfmemalloc; } + local_unlock_nested_bh(&napi_alloc_cache.bh_lock); if (unlikely(!data)) return NULL; @@ -1190,7 +1203,8 @@ void __kfree_skb(struct sk_buff *skb) EXPORT_SYMBOL(__kfree_skb); static __always_inline -bool __kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) +bool __sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb, + enum skb_drop_reason reason) { if (unlikely(!skb_unref(skb))) return false; @@ -1203,26 +1217,27 @@ bool __kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) if (reason == SKB_CONSUMED) trace_consume_skb(skb, __builtin_return_address(0)); else - trace_kfree_skb(skb, __builtin_return_address(0), reason); + trace_kfree_skb(skb, __builtin_return_address(0), reason, sk); return true; } /** - * kfree_skb_reason - free an sk_buff with special reason + * sk_skb_reason_drop - free an sk_buff with special reason + * @sk: the socket to receive @skb, or NULL if not applicable * @skb: buffer to free * @reason: reason why this skb is dropped * - * Drop a reference to the buffer and free it if the usage count has - * hit zero. Meanwhile, pass the drop reason to 'kfree_skb' - * tracepoint. + * Drop a reference to the buffer and free it if the usage count has hit + * zero. Meanwhile, pass the receiving socket and drop reason to + * 'kfree_skb' tracepoint. */ void __fix_address -kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) +sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason) { - if (__kfree_skb_reason(skb, reason)) + if (__sk_skb_reason_drop(sk, skb, reason)) __kfree_skb(skb); } -EXPORT_SYMBOL(kfree_skb_reason); +EXPORT_SYMBOL(sk_skb_reason_drop); #define KFREE_SKB_BULK_SIZE 16 @@ -1261,7 +1276,7 @@ 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 (__sk_skb_reason_drop(NULL, segs, reason)) { skb_poison_list(segs); kfree_skb_add_bulk(segs, &sa, reason); } @@ -1433,6 +1448,7 @@ static void napi_skb_cache_put(struct sk_buff *skb) if (!kasan_mempool_poison_object(skb)) return; + local_lock_nested_bh(&napi_alloc_cache.bh_lock); nc->skb_cache[nc->skb_count++] = skb; if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { @@ -1444,6 +1460,7 @@ static void napi_skb_cache_put(struct sk_buff *skb) nc->skb_cache + NAPI_SKB_CACHE_HALF); nc->skb_count = NAPI_SKB_CACHE_HALF; } + local_unlock_nested_bh(&napi_alloc_cache.bh_lock); } void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason) diff --git a/net/core/sock.c b/net/core/sock.c index 69baddcfbd8c..9abc4fe25953 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3751,6 +3751,9 @@ void sk_common_release(struct sock *sk) sk->sk_prot->unhash(sk); + if (sk->sk_socket) + sk->sk_socket->sk = NULL; + /* * In this point socket cannot receive new packets, but it is possible * that some packets are in flight because some CPU runs receiver and diff --git a/net/core/xdp.c b/net/core/xdp.c index 41693154e426..022c12059cf2 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -295,10 +295,8 @@ static struct xdp_mem_allocator *__xdp_reg_mem_model(struct xdp_mem_info *mem, mutex_lock(&mem_id_lock); ret = __mem_id_init_hash_table(); mutex_unlock(&mem_id_lock); - if (ret < 0) { - WARN_ON(1); + if (ret < 0) return ERR_PTR(ret); - } } xdp_alloc = kzalloc(sizeof(*xdp_alloc), gfp); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index ff41bd6f99c3..5926159a6f20 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -657,8 +657,11 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (dccp_v4_send_response(sk, req)) goto drop_and_free; - inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); - reqsk_put(req); + if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT))) + reqsk_free(req); + else + reqsk_put(req); + return 0; drop_and_free: diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 85f4b8fdbe5e..da5dba120bc9 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -400,8 +400,11 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (dccp_v6_send_response(sk, req)) goto drop_and_free; - inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); - reqsk_put(req); + if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT))) + reqsk_free(req); + else + reqsk_put(req); + return 0; drop_and_free: diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 8e698bea99a3..8d5bf869eb14 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -129,7 +129,7 @@ config NET_DSA_TAG_RTL4_A tristate "Tag driver for Realtek 4 byte protocol A tags" help Say Y or M if you want to enable support for tagging frames for the - Realtek switches with 4 byte protocol A tags, sich as found in + Realtek switches with 4 byte protocol A tags, such as found in the Realtek RTL8366RB. config NET_DSA_TAG_RTL8_4 diff --git a/net/ethtool/coalesce.c b/net/ethtool/coalesce.c index 83112c1a71ae..759b16e3d134 100644 --- a/net/ethtool/coalesce.c +++ b/net/ethtool/coalesce.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only +#include <linux/dim.h> #include "netlink.h" #include "common.h" @@ -82,6 +83,14 @@ static int coalesce_prepare_data(const struct ethnl_req_info *req_base, static int coalesce_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { + int modersz = nla_total_size(0) + /* _PROFILE_IRQ_MODERATION, nest */ + nla_total_size(sizeof(u32)) + /* _IRQ_MODERATION_USEC */ + nla_total_size(sizeof(u32)) + /* _IRQ_MODERATION_PKTS */ + nla_total_size(sizeof(u32)); /* _IRQ_MODERATION_COMPS */ + + int total_modersz = nla_total_size(0) + /* _{R,T}X_PROFILE, nest */ + modersz * NET_DIM_PARAMS_NUM_PROFILES; + return nla_total_size(sizeof(u32)) + /* _RX_USECS */ nla_total_size(sizeof(u32)) + /* _RX_MAX_FRAMES */ nla_total_size(sizeof(u32)) + /* _RX_USECS_IRQ */ @@ -108,7 +117,8 @@ static int coalesce_reply_size(const struct ethnl_req_info *req_base, nla_total_size(sizeof(u8)) + /* _USE_CQE_MODE_RX */ nla_total_size(sizeof(u32)) + /* _TX_AGGR_MAX_BYTES */ nla_total_size(sizeof(u32)) + /* _TX_AGGR_MAX_FRAMES */ - nla_total_size(sizeof(u32)); /* _TX_AGGR_TIME_USECS */ + nla_total_size(sizeof(u32)) + /* _TX_AGGR_TIME_USECS */ + total_modersz * 2; /* _{R,T}X_PROFILE */ } static bool coalesce_put_u32(struct sk_buff *skb, u16 attr_type, u32 val, @@ -127,14 +137,84 @@ static bool coalesce_put_bool(struct sk_buff *skb, u16 attr_type, u32 val, return nla_put_u8(skb, attr_type, !!val); } +/** + * coalesce_put_profile - fill reply with a nla nest with four child nla nests. + * @skb: socket buffer the message is stored in + * @attr_type: nest attr type ETHTOOL_A_COALESCE_*X_PROFILE + * @profile: data passed to userspace + * @coal_flags: modifiable parameters supported by the driver + * + * Put a dim profile nest attribute. Refer to ETHTOOL_A_PROFILE_IRQ_MODERATION. + * + * Return: 0 on success or a negative error code. + */ +static int coalesce_put_profile(struct sk_buff *skb, u16 attr_type, + const struct dim_cq_moder *profile, + u8 coal_flags) +{ + struct nlattr *profile_attr, *moder_attr; + int i, ret; + + if (!profile || !coal_flags) + return 0; + + profile_attr = nla_nest_start(skb, attr_type); + if (!profile_attr) + return -EMSGSIZE; + + for (i = 0; i < NET_DIM_PARAMS_NUM_PROFILES; i++) { + moder_attr = nla_nest_start(skb, + ETHTOOL_A_PROFILE_IRQ_MODERATION); + if (!moder_attr) { + ret = -EMSGSIZE; + goto cancel_profile; + } + + if (coal_flags & DIM_COALESCE_USEC) { + ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_USEC, + profile[i].usec); + if (ret) + goto cancel_moder; + } + + if (coal_flags & DIM_COALESCE_PKTS) { + ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_PKTS, + profile[i].pkts); + if (ret) + goto cancel_moder; + } + + if (coal_flags & DIM_COALESCE_COMPS) { + ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_COMPS, + profile[i].comps); + if (ret) + goto cancel_moder; + } + + nla_nest_end(skb, moder_attr); + } + + nla_nest_end(skb, profile_attr); + + return 0; + +cancel_moder: + nla_nest_cancel(skb, moder_attr); +cancel_profile: + nla_nest_cancel(skb, profile_attr); + return ret; +} + static int coalesce_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct coalesce_reply_data *data = COALESCE_REPDATA(reply_base); const struct kernel_ethtool_coalesce *kcoal = &data->kernel_coalesce; + struct dim_irq_moder *moder = req_base->dev->irq_moder; const struct ethtool_coalesce *coal = &data->coalesce; u32 supported = data->supported_params; + int ret = 0; if (coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_USECS, coal->rx_coalesce_usecs, supported) || @@ -192,11 +272,41 @@ static int coalesce_fill_reply(struct sk_buff *skb, kcoal->tx_aggr_time_usecs, supported)) return -EMSGSIZE; - return 0; + if (!moder) + return 0; + + rcu_read_lock(); + if (moder->profile_flags & DIM_PROFILE_RX) { + ret = coalesce_put_profile(skb, ETHTOOL_A_COALESCE_RX_PROFILE, + rcu_dereference(moder->rx_profile), + moder->coal_flags); + if (ret) + goto out; + } + + if (moder->profile_flags & DIM_PROFILE_TX) + ret = coalesce_put_profile(skb, ETHTOOL_A_COALESCE_TX_PROFILE, + rcu_dereference(moder->tx_profile), + moder->coal_flags); + +out: + rcu_read_unlock(); + return ret; } /* COALESCE_SET */ +static const struct nla_policy coalesce_irq_moderation_policy[] = { + [ETHTOOL_A_IRQ_MODERATION_USEC] = { .type = NLA_U32 }, + [ETHTOOL_A_IRQ_MODERATION_PKTS] = { .type = NLA_U32 }, + [ETHTOOL_A_IRQ_MODERATION_COMPS] = { .type = NLA_U32 }, +}; + +static const struct nla_policy coalesce_profile_policy[] = { + [ETHTOOL_A_PROFILE_IRQ_MODERATION] = + NLA_POLICY_NESTED(coalesce_irq_moderation_policy), +}; + const struct nla_policy ethnl_coalesce_set_policy[] = { [ETHTOOL_A_COALESCE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), @@ -227,6 +337,10 @@ const struct nla_policy ethnl_coalesce_set_policy[] = { [ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_RX_PROFILE] = + NLA_POLICY_NESTED(coalesce_profile_policy), + [ETHTOOL_A_COALESCE_TX_PROFILE] = + NLA_POLICY_NESTED(coalesce_profile_policy), }; static int @@ -234,6 +348,7 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; + struct dim_irq_moder *irq_moder = req_info->dev->irq_moder; struct nlattr **tb = info->attrs; u32 supported_params; u16 a; @@ -243,6 +358,12 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info, /* make sure that only supported parameters are present */ supported_params = ops->supported_coalesce_params; + if (irq_moder && irq_moder->profile_flags & DIM_PROFILE_RX) + supported_params |= ETHTOOL_COALESCE_RX_PROFILE; + + if (irq_moder && irq_moder->profile_flags & DIM_PROFILE_TX) + supported_params |= ETHTOOL_COALESCE_TX_PROFILE; + for (a = ETHTOOL_A_COALESCE_RX_USECS; a < __ETHTOOL_A_COALESCE_CNT; a++) if (tb[a] && !(supported_params & attr_to_mask(a))) { NL_SET_ERR_MSG_ATTR(info->extack, tb[a], @@ -253,6 +374,138 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info, return 1; } +/** + * ethnl_update_irq_moder - update a specific field in the given profile + * @irq_moder: place that collects dim related information + * @irq_field: field in profile to modify + * @attr_type: attr type ETHTOOL_A_IRQ_MODERATION_* + * @tb: netlink attribute with new values or null + * @coal_bit: DIM_COALESCE_* bit from coal_flags + * @mod: pointer to bool for modification tracking + * @extack: netlink extended ack + * + * Return: 0 on success or a negative error code. + */ +static int ethnl_update_irq_moder(struct dim_irq_moder *irq_moder, + u16 *irq_field, u16 attr_type, + struct nlattr **tb, + u8 coal_bit, bool *mod, + struct netlink_ext_ack *extack) +{ + int ret = 0; + u32 val; + + if (!tb[attr_type]) + return 0; + + if (irq_moder->coal_flags & coal_bit) { + val = nla_get_u32(tb[attr_type]); + if (*irq_field == val) + return 0; + + *irq_field = val; + *mod = true; + } else { + NL_SET_BAD_ATTR(extack, tb[attr_type]); + ret = -EOPNOTSUPP; + } + + return ret; +} + +/** + * ethnl_update_profile - get a profile nest with child nests from userspace. + * @dev: netdevice to update the profile + * @dst: profile get from the driver and modified by ethnl_update_profile. + * @nests: nest attr ETHTOOL_A_COALESCE_*X_PROFILE to set profile. + * @mod: pointer to bool for modification tracking + * @extack: Netlink extended ack + * + * Layout of nests: + * Nested ETHTOOL_A_COALESCE_*X_PROFILE attr + * Nested ETHTOOL_A_PROFILE_IRQ_MODERATION attr + * ETHTOOL_A_IRQ_MODERATION_USEC attr + * ETHTOOL_A_IRQ_MODERATION_PKTS attr + * ETHTOOL_A_IRQ_MODERATION_COMPS attr + * ... + * Nested ETHTOOL_A_PROFILE_IRQ_MODERATION attr + * ETHTOOL_A_IRQ_MODERATION_USEC attr + * ETHTOOL_A_IRQ_MODERATION_PKTS attr + * ETHTOOL_A_IRQ_MODERATION_COMPS attr + * + * Return: 0 on success or a negative error code. + */ +static int ethnl_update_profile(struct net_device *dev, + struct dim_cq_moder __rcu **dst, + const struct nlattr *nests, + bool *mod, + struct netlink_ext_ack *extack) +{ + int len_irq_moder = ARRAY_SIZE(coalesce_irq_moderation_policy); + struct nlattr *tb[ARRAY_SIZE(coalesce_irq_moderation_policy)]; + struct dim_irq_moder *irq_moder = dev->irq_moder; + struct dim_cq_moder *new_profile, *old_profile; + int ret, rem, i = 0, len; + struct nlattr *nest; + + if (!nests) + return 0; + + if (!*dst) + return -EOPNOTSUPP; + + old_profile = rtnl_dereference(*dst); + len = NET_DIM_PARAMS_NUM_PROFILES * sizeof(*old_profile); + new_profile = kmemdup(old_profile, len, GFP_KERNEL); + if (!new_profile) + return -ENOMEM; + + nla_for_each_nested_type(nest, ETHTOOL_A_PROFILE_IRQ_MODERATION, + nests, rem) { + ret = nla_parse_nested(tb, len_irq_moder - 1, nest, + coalesce_irq_moderation_policy, + extack); + if (ret) + goto err_out; + + ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].usec, + ETHTOOL_A_IRQ_MODERATION_USEC, + tb, DIM_COALESCE_USEC, + mod, extack); + if (ret) + goto err_out; + + ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].pkts, + ETHTOOL_A_IRQ_MODERATION_PKTS, + tb, DIM_COALESCE_PKTS, + mod, extack); + if (ret) + goto err_out; + + ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].comps, + ETHTOOL_A_IRQ_MODERATION_COMPS, + tb, DIM_COALESCE_COMPS, + mod, extack); + if (ret) + goto err_out; + + i++; + } + + /* After the profile is modified, dim itself is a dynamic + * mechanism and will quickly fit to the appropriate + * coalescing parameters according to the new profile. + */ + rcu_assign_pointer(*dst, new_profile); + kfree_rcu(old_profile, rcu); + + return 0; + +err_out: + kfree(new_profile); + return ret; +} + static int __ethnl_set_coalesce(struct ethnl_req_info *req_info, struct genl_info *info, bool *dual_change) @@ -317,6 +570,22 @@ __ethnl_set_coalesce(struct ethnl_req_info *req_info, struct genl_info *info, ethnl_update_u32(&kernel_coalesce.tx_aggr_time_usecs, tb[ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS], &mod); + if (dev->irq_moder && dev->irq_moder->profile_flags & DIM_PROFILE_RX) { + ret = ethnl_update_profile(dev, &dev->irq_moder->rx_profile, + tb[ETHTOOL_A_COALESCE_RX_PROFILE], + &mod, info->extack); + if (ret < 0) + return ret; + } + + if (dev->irq_moder && dev->irq_moder->profile_flags & DIM_PROFILE_TX) { + ret = ethnl_update_profile(dev, &dev->irq_moder->tx_profile, + tb[ETHTOOL_A_COALESCE_TX_PROFILE], + &mod, info->extack); + if (ret < 0) + return ret; + } + /* Update operation modes */ ethnl_update_bool32(&coalesce.use_adaptive_rx_coalesce, tb[ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX], &mod_mode); diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index e6904288d40d..e4cc6b78dcfc 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -73,9 +73,15 @@ static void hsr_check_announce(struct net_device *hsr_dev) mod_timer(&hsr->announce_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL)); } + + if (hsr->redbox && !timer_pending(&hsr->announce_proxy_timer)) + mod_timer(&hsr->announce_proxy_timer, jiffies + + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL) / 2); } else { /* Deactivate the announce timer */ timer_delete(&hsr->announce_timer); + if (hsr->redbox) + timer_delete(&hsr->announce_proxy_timer); } } @@ -279,10 +285,11 @@ out: return NULL; } -static void send_hsr_supervision_frame(struct hsr_port *master, - unsigned long *interval) +static void send_hsr_supervision_frame(struct hsr_port *port, + unsigned long *interval, + const unsigned char *addr) { - struct hsr_priv *hsr = master->hsr; + struct hsr_priv *hsr = port->hsr; __u8 type = HSR_TLV_LIFE_CHECK; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tlv *hsr_stlv; @@ -296,9 +303,9 @@ static void send_hsr_supervision_frame(struct hsr_port *master, hsr->announce_count++; } - skb = hsr_init_skb(master); + skb = hsr_init_skb(port); if (!skb) { - netdev_warn_once(master->dev, "HSR: Could not send supervision frame\n"); + netdev_warn_once(port->dev, "HSR: Could not send supervision frame\n"); return; } @@ -321,11 +328,12 @@ static void send_hsr_supervision_frame(struct hsr_port *master, hsr_stag->tlv.HSR_TLV_length = hsr->prot_version ? sizeof(struct hsr_sup_payload) : 12; - /* Payload: MacAddressA */ + /* Payload: MacAddressA / SAN MAC from ProxyNodeTable */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); - ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); + ether_addr_copy(hsr_sp->macaddress_A, addr); - if (hsr->redbox) { + if (hsr->redbox && + hsr_is_node_in_db(&hsr->proxy_node_db, addr)) { hsr_stlv = skb_put(skb, sizeof(struct hsr_sup_tlv)); hsr_stlv->HSR_TLV_type = PRP_TLV_REDBOX_MAC; hsr_stlv->HSR_TLV_length = sizeof(struct hsr_sup_payload); @@ -340,13 +348,14 @@ static void send_hsr_supervision_frame(struct hsr_port *master, return; } - hsr_forward_skb(skb, master); + hsr_forward_skb(skb, port); spin_unlock_bh(&hsr->seqnr_lock); return; } static void send_prp_supervision_frame(struct hsr_port *master, - unsigned long *interval) + unsigned long *interval, + const unsigned char *addr) { struct hsr_priv *hsr = master->hsr; struct hsr_sup_payload *hsr_sp; @@ -396,7 +405,7 @@ static void hsr_announce(struct timer_list *t) rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); - hsr->proto_ops->send_sv_frame(master, &interval); + hsr->proto_ops->send_sv_frame(master, &interval, master->dev->dev_addr); if (is_admin_up(master->dev)) mod_timer(&hsr->announce_timer, jiffies + interval); @@ -404,6 +413,37 @@ static void hsr_announce(struct timer_list *t) rcu_read_unlock(); } +/* Announce (supervision frame) timer function for RedBox + */ +static void hsr_proxy_announce(struct timer_list *t) +{ + struct hsr_priv *hsr = from_timer(hsr, t, announce_proxy_timer); + struct hsr_port *interlink; + unsigned long interval = 0; + struct hsr_node *node; + + rcu_read_lock(); + /* RedBOX sends supervisory frames to HSR network with MAC addresses + * of SAN nodes stored in ProxyNodeTable. + */ + interlink = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); + list_for_each_entry_rcu(node, &hsr->proxy_node_db, mac_list) { + if (hsr_addr_is_redbox(hsr, node->macaddress_A)) + continue; + hsr->proto_ops->send_sv_frame(interlink, &interval, + node->macaddress_A); + } + + if (is_admin_up(interlink->dev)) { + if (!interval) + interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); + + mod_timer(&hsr->announce_proxy_timer, jiffies + interval); + } + + rcu_read_unlock(); +} + void hsr_del_ports(struct hsr_priv *hsr) { struct hsr_port *port; @@ -590,6 +630,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], timer_setup(&hsr->announce_timer, hsr_announce, 0); timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0); timer_setup(&hsr->prune_proxy_timer, hsr_prune_proxy_nodes, 0); + timer_setup(&hsr->announce_proxy_timer, hsr_proxy_announce, 0); ether_addr_copy(hsr->sup_multicast_addr, def_multicast_addr); hsr->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec; diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 05a61b8286ec..b38060246e62 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -117,6 +117,35 @@ static bool is_supervision_frame(struct hsr_priv *hsr, struct sk_buff *skb) return true; } +static bool is_proxy_supervision_frame(struct hsr_priv *hsr, + struct sk_buff *skb) +{ + struct hsr_sup_payload *payload; + struct ethhdr *eth_hdr; + u16 total_length = 0; + + eth_hdr = (struct ethhdr *)skb_mac_header(skb); + + /* Get the HSR protocol revision. */ + if (eth_hdr->h_proto == htons(ETH_P_HSR)) + total_length = sizeof(struct hsrv1_ethhdr_sp); + else + total_length = sizeof(struct hsrv0_ethhdr_sp); + + if (!pskb_may_pull(skb, total_length + sizeof(struct hsr_sup_payload))) + return false; + + skb_pull(skb, total_length); + payload = (struct hsr_sup_payload *)skb->data; + skb_push(skb, total_length); + + /* For RedBox (HSR-SAN) check if we have received the supervision + * frame with MAC addresses from own ProxyNodeTable. + */ + return hsr_is_node_in_db(&hsr->proxy_node_db, + payload->macaddress_A); +} + static struct sk_buff *create_stripped_skb_hsr(struct sk_buff *skb_in, struct hsr_frame_info *frame) { @@ -392,9 +421,9 @@ static int hsr_xmit(struct sk_buff *skb, struct hsr_port *port, bool prp_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port) { return ((frame->port_rcv->type == HSR_PT_SLAVE_A && - port->type == HSR_PT_SLAVE_B) || + port->type == HSR_PT_SLAVE_B) || (frame->port_rcv->type == HSR_PT_SLAVE_B && - port->type == HSR_PT_SLAVE_A)); + port->type == HSR_PT_SLAVE_A)); } bool hsr_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port) @@ -499,7 +528,8 @@ static void hsr_forward_do(struct hsr_frame_info *frame) frame->sequence_nr)) continue; - if (frame->is_supervision && port->type == HSR_PT_MASTER) { + if (frame->is_supervision && port->type == HSR_PT_MASTER && + !frame->is_proxy_supervision) { hsr_handle_sup_frame(frame); continue; } @@ -637,6 +667,9 @@ static int fill_frame_info(struct hsr_frame_info *frame, memset(frame, 0, sizeof(*frame)); frame->is_supervision = is_supervision_frame(port->hsr, skb); + if (frame->is_supervision && hsr->redbox) + frame->is_proxy_supervision = + is_proxy_supervision_frame(port->hsr, skb); n_db = &hsr->node_db; if (port->type == HSR_PT_INTERLINK) @@ -688,7 +721,7 @@ void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port) /* Gets called for ingress frames as well as egress from master port. * So check and increment stats for master port only here. */ - if (port->type == HSR_PT_MASTER) { + if (port->type == HSR_PT_MASTER || port->type == HSR_PT_INTERLINK) { port->dev->stats.tx_packets++; port->dev->stats.tx_bytes += skb->len; } diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 614df9649794..73bc6f659812 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -36,6 +36,14 @@ static bool seq_nr_after(u16 a, u16 b) #define seq_nr_before(a, b) seq_nr_after((b), (a)) #define seq_nr_before_or_eq(a, b) (!seq_nr_after((a), (b))) +bool hsr_addr_is_redbox(struct hsr_priv *hsr, unsigned char *addr) +{ + if (!hsr->redbox || !is_valid_ether_addr(hsr->macaddress_redbox)) + return false; + + return ether_addr_equal(addr, hsr->macaddress_redbox); +} + bool hsr_addr_is_self(struct hsr_priv *hsr, unsigned char *addr) { struct hsr_self_node *sn; @@ -591,6 +599,10 @@ void hsr_prune_proxy_nodes(struct timer_list *t) spin_lock_bh(&hsr->list_lock); list_for_each_entry_safe(node, tmp, &hsr->proxy_node_db, mac_list) { + /* Don't prune RedBox node. */ + if (hsr_addr_is_redbox(hsr, node->macaddress_A)) + continue; + timestamp = node->time_in[HSR_PT_INTERLINK]; /* Prune old entries */ diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index 7619e31c1d2d..993fa950d814 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -22,6 +22,7 @@ struct hsr_frame_info { struct hsr_node *node_src; u16 sequence_nr; bool is_supervision; + bool is_proxy_supervision; bool is_vlan; bool is_local_dest; bool is_local_exclusive; @@ -35,6 +36,7 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db, enum hsr_port_type rx_port); void hsr_handle_sup_frame(struct hsr_frame_info *frame); bool hsr_addr_is_self(struct hsr_priv *hsr, unsigned char *addr); +bool hsr_addr_is_redbox(struct hsr_priv *hsr, unsigned char *addr); void hsr_addr_subst_source(struct hsr_node *node, struct sk_buff *skb); void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb, diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 23850b16d1ea..ab1f8d35d9dc 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -170,7 +170,8 @@ struct hsr_node; struct hsr_proto_ops { /* format and send supervision frame */ - void (*send_sv_frame)(struct hsr_port *port, unsigned long *interval); + void (*send_sv_frame)(struct hsr_port *port, unsigned long *interval, + const unsigned char addr[ETH_ALEN]); void (*handle_san_frame)(bool san, enum hsr_port_type port, struct hsr_node *node); bool (*drop_frame)(struct hsr_frame_info *frame, struct hsr_port *port); @@ -197,6 +198,7 @@ struct hsr_priv { struct list_head proxy_node_db; /* RedBox HSR proxy nodes */ struct hsr_self_node __rcu *self_node; /* MACs of slaves */ struct timer_list announce_timer; /* Supervision frame dispatch */ + struct timer_list announce_proxy_timer; struct timer_list prune_timer; struct timer_list prune_proxy_timer; int announce_count; diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 898f18c6da53..f6ff0b61e08a 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -131,6 +131,7 @@ static void hsr_dellink(struct net_device *dev, struct list_head *head) del_timer_sync(&hsr->prune_timer); del_timer_sync(&hsr->prune_proxy_timer); del_timer_sync(&hsr->announce_timer); + timer_delete_sync(&hsr->announce_proxy_timer); hsr_debugfs_term(hsr); hsr_del_ports(hsr); diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 3a95c0f13ce3..8cc0e2f4159d 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1810,6 +1810,29 @@ static int cipso_v4_genopt(unsigned char *buf, u32 buf_len, return CIPSO_V4_HDR_LEN + ret_val; } +static int cipso_v4_get_actual_opt_len(const unsigned char *data, int len) +{ + int iter = 0, optlen = 0; + + /* determining the new total option length is tricky because of + * the padding necessary, the only thing i can think to do at + * this point is walk the options one-by-one, skipping the + * padding at the end to determine the actual option size and + * from there we can determine the new total option length + */ + while (iter < len) { + if (data[iter] == IPOPT_END) { + break; + } else if (data[iter] == IPOPT_NOP) { + iter++; + } else { + iter += data[iter + 1]; + optlen = iter; + } + } + return optlen; +} + /** * cipso_v4_sock_setattr - Add a CIPSO option to a socket * @sk: the socket @@ -1986,7 +2009,6 @@ static int cipso_v4_delopt(struct ip_options_rcu __rcu **opt_ptr) u8 cipso_len; u8 cipso_off; unsigned char *cipso_ptr; - int iter; int optlen_new; cipso_off = opt->opt.cipso - sizeof(struct iphdr); @@ -2006,19 +2028,8 @@ static int cipso_v4_delopt(struct ip_options_rcu __rcu **opt_ptr) memmove(cipso_ptr, cipso_ptr + cipso_len, opt->opt.optlen - cipso_off - cipso_len); - /* determining the new total option length is tricky because of - * the padding necessary, the only thing i can think to do at - * this point is walk the options one-by-one, skipping the - * padding at the end to determine the actual option size and - * from there we can determine the new total option length */ - iter = 0; - optlen_new = 0; - while (iter < opt->opt.optlen) - if (opt->opt.__data[iter] != IPOPT_NOP) { - iter += opt->opt.__data[iter + 1]; - optlen_new = iter; - } else - iter++; + optlen_new = cipso_v4_get_actual_opt_len(opt->opt.__data, + opt->opt.optlen); hdr_delta = opt->opt.optlen; opt->opt.optlen = (optlen_new + 3) & ~3; hdr_delta -= opt->opt.optlen; @@ -2238,7 +2249,8 @@ int cipso_v4_skbuff_setattr(struct sk_buff *skb, */ int cipso_v4_skbuff_delattr(struct sk_buff *skb) { - int ret_val; + int ret_val, cipso_len, hdr_len_actual, new_hdr_len_actual, new_hdr_len, + hdr_len_delta; struct iphdr *iph; struct ip_options *opt = &IPCB(skb)->opt; unsigned char *cipso_ptr; @@ -2251,16 +2263,37 @@ int cipso_v4_skbuff_delattr(struct sk_buff *skb) if (ret_val < 0) return ret_val; - /* the easiest thing to do is just replace the cipso option with noop - * options since we don't change the size of the packet, although we - * still need to recalculate the checksum */ - iph = ip_hdr(skb); cipso_ptr = (unsigned char *)iph + opt->cipso; - memset(cipso_ptr, IPOPT_NOOP, cipso_ptr[1]); + cipso_len = cipso_ptr[1]; + + hdr_len_actual = sizeof(struct iphdr) + + cipso_v4_get_actual_opt_len((unsigned char *)(iph + 1), + opt->optlen); + new_hdr_len_actual = hdr_len_actual - cipso_len; + new_hdr_len = (new_hdr_len_actual + 3) & ~3; + hdr_len_delta = (iph->ihl << 2) - new_hdr_len; + + /* 1. shift any options after CIPSO to the left */ + memmove(cipso_ptr, cipso_ptr + cipso_len, + new_hdr_len_actual - opt->cipso); + /* 2. move the whole IP header to its new place */ + memmove((unsigned char *)iph + hdr_len_delta, iph, new_hdr_len_actual); + /* 3. adjust the skb layout */ + skb_pull(skb, hdr_len_delta); + skb_reset_network_header(skb); + iph = ip_hdr(skb); + /* 4. re-fill new padding with IPOPT_END (may now be longer) */ + memset((unsigned char *)iph + new_hdr_len_actual, IPOPT_END, + new_hdr_len - new_hdr_len_actual); + + opt->optlen -= hdr_len_delta; opt->cipso = 0; opt->is_changed = 1; - + if (hdr_len_delta != 0) { + iph->ihl = new_hdr_len >> 2; + iph_set_totlen(iph, skb->len); + } ip_send_check(iph); return 0; diff --git a/net/ipv4/fou_core.c b/net/ipv4/fou_core.c index a8494f796dca..0abbc413e0fe 100644 --- a/net/ipv4/fou_core.c +++ b/net/ipv4/fou_core.c @@ -433,7 +433,7 @@ next_proto: offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[proto]); - if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive)) + if (!ops || !ops->callbacks.gro_receive) goto out; pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 7ced569778ab..64d07b842e73 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1180,25 +1180,34 @@ drop: inet_csk_reqsk_queue_drop_and_put(oreq->rsk_listener, oreq); } -static void reqsk_queue_hash_req(struct request_sock *req, +static bool reqsk_queue_hash_req(struct request_sock *req, unsigned long timeout) { + bool found_dup_sk = false; + + if (!inet_ehash_insert(req_to_sk(req), NULL, &found_dup_sk)) + return false; + + /* The timer needs to be setup after a successful insertion. */ timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED); mod_timer(&req->rsk_timer, jiffies + timeout); - inet_ehash_insert(req_to_sk(req), NULL, NULL); /* before letting lookups find us, make sure all req fields * are committed to memory and refcnt initialized. */ smp_wmb(); refcount_set(&req->rsk_refcnt, 2 + 1); + return true; } -void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, +bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout) { - reqsk_queue_hash_req(req, timeout); + if (!reqsk_queue_hash_req(req, timeout)) + return false; + inet_csk_reqsk_queue_added(sk); + return true; } EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index bccef2fcf620..5cffad42fe8c 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -1099,7 +1099,6 @@ static void ip_tunnel_dev_free(struct net_device *dev) gro_cells_destroy(&tunnel->gro_cells); dst_cache_destroy(&tunnel->dst_cache); - free_percpu(dev->tstats); } void ip_tunnel_dellink(struct net_device *dev, struct list_head *head) @@ -1313,20 +1312,15 @@ int ip_tunnel_init(struct net_device *dev) dev->needs_free_netdev = true; dev->priv_destructor = ip_tunnel_dev_free; - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); - if (err) { - free_percpu(dev->tstats); + if (err) return err; - } err = gro_cells_init(&tunnel->gro_cells, dev); if (err) { dst_cache_destroy(&tunnel->dst_cache); - free_percpu(dev->tstats); return err; } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 823306487a82..619ddc087957 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -946,7 +946,7 @@ static enum skb_drop_reason __ping_queue_rcv_skb(struct sock *sk, pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n", inet_sk(sk), inet_sk(sk)->inet_num, skb); if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) { - kfree_skb_reason(skb, reason); + sk_skb_reason_drop(sk, skb, reason); pr_debug("ping_queue_rcv_skb -> failed\n"); return reason; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 1a0953650356..474dfd263c8b 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -301,7 +301,7 @@ static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb) ipv4_pktinfo_prepare(sk, skb, true); if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) { - kfree_skb_reason(skb, reason); + sk_skb_reason_drop(sk, skb, reason); return NET_RX_DROP; } @@ -312,7 +312,7 @@ 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_reason(skb, SKB_DROP_REASON_XFRM_POLICY); + sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_XFRM_POLICY); return NET_RX_DROP; } nf_reset_ct(skb); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index cb0bdf34ed50..54512acbead7 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1923,7 +1923,7 @@ static u32 fib_multipath_custom_hash_outer(const struct net *net, hash_keys.ports.dst = keys.ports.dst; *p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION); - return flow_hash_from_keys(&hash_keys); + return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 fib_multipath_custom_hash_inner(const struct net *net, @@ -1972,7 +1972,7 @@ static u32 fib_multipath_custom_hash_inner(const struct net *net, if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) hash_keys.ports.dst = keys.ports.dst; - return flow_hash_from_keys(&hash_keys); + return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 fib_multipath_custom_hash_skb(const struct net *net, @@ -2009,7 +2009,7 @@ static u32 fib_multipath_custom_hash_fl4(const struct net *net, if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = fl4->fl4_dport; - return flow_hash_from_keys(&hash_keys); + return fib_multipath_hash_from_keys(net, &hash_keys); } /* if skb is set it will be used and fl4 can be NULL */ @@ -2030,7 +2030,7 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; } - mhash = flow_hash_from_keys(&hash_keys); + mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 1: /* skb is currently provided only when forwarding */ @@ -2064,7 +2064,7 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, hash_keys.ports.dst = fl4->fl4_dport; hash_keys.basic.ip_proto = fl4->flowi4_proto; } - mhash = flow_hash_from_keys(&hash_keys); + mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 2: memset(&hash_keys, 0, sizeof(hash_keys)); @@ -2095,7 +2095,7 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; } - mhash = flow_hash_from_keys(&hash_keys); + mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 3: if (skb) diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index b61d36810fe3..1948d15f1f28 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -496,6 +496,6 @@ out: out_free: reqsk_free(req); out_drop: - kfree_skb_reason(skb, reason); + sk_skb_reason_drop(sk, skb, reason); return NULL; } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index bb64c0ef092d..9140d20eb2d4 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -464,6 +464,61 @@ static int proc_fib_multipath_hash_fields(struct ctl_table *table, int write, return ret; } + +static u32 proc_fib_multipath_hash_rand_seed __ro_after_init; + +static void proc_fib_multipath_hash_init_rand_seed(void) +{ + get_random_bytes(&proc_fib_multipath_hash_rand_seed, + sizeof(proc_fib_multipath_hash_rand_seed)); +} + +static void proc_fib_multipath_hash_set_seed(struct net *net, u32 user_seed) +{ + struct sysctl_fib_multipath_hash_seed new = { + .user_seed = user_seed, + .mp_seed = (user_seed ? user_seed : + proc_fib_multipath_hash_rand_seed), + }; + + WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed, new); +} + +static int proc_fib_multipath_hash_seed(struct ctl_table *table, int write, + void *buffer, size_t *lenp, + loff_t *ppos) +{ + struct sysctl_fib_multipath_hash_seed *mphs; + struct net *net = table->data; + struct ctl_table tmp; + u32 user_seed; + int ret; + + mphs = &net->ipv4.sysctl_fib_multipath_hash_seed; + user_seed = mphs->user_seed; + + tmp = *table; + tmp.data = &user_seed; + + ret = proc_douintvec_minmax(&tmp, write, buffer, lenp, ppos); + + if (write && ret == 0) { + proc_fib_multipath_hash_set_seed(net, user_seed); + call_netevent_notifiers(NETEVENT_IPV4_MPATH_HASH_UPDATE, net); + } + + return ret; +} +#else + +static void proc_fib_multipath_hash_init_rand_seed(void) +{ +} + +static void proc_fib_multipath_hash_set_seed(struct net *net, u32 user_seed) +{ +} + #endif static struct ctl_table ipv4_table[] = { @@ -1072,6 +1127,13 @@ static struct ctl_table ipv4_net_table[] = { .extra1 = SYSCTL_ONE, .extra2 = &fib_multipath_hash_fields_all_mask, }, + { + .procname = "fib_multipath_hash_seed", + .data = &init_net, + .maxlen = sizeof(u32), + .mode = 0644, + .proc_handler = proc_fib_multipath_hash_seed, + }, #endif { .procname = "ip_unprivileged_port_start", @@ -1550,6 +1612,8 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) if (!net->ipv4.sysctl_local_reserved_ports) goto err_ports; + proc_fib_multipath_hash_set_seed(net, 0); + return 0; err_ports: @@ -1584,6 +1648,8 @@ static __init int sysctl_ipv4_init(void) if (!hdr) return -ENOMEM; + proc_fib_multipath_hash_init_rand_seed(); + if (register_pernet_subsys(&ipv4_sysctl_ops)) { unregister_net_sysctl_table(hdr); return -ENOMEM; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6553221694ec..e03a342c9162 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -282,6 +282,7 @@ #include <asm/ioctls.h> #include <net/busy_poll.h> #include <net/hotdata.h> +#include <trace/events/tcp.h> #include <net/rps.h> /* Track pending CMSGs. */ @@ -4463,7 +4464,7 @@ int tcp_md5_hash_key(struct tcp_sigpool *hp, EXPORT_SYMBOL(tcp_md5_hash_key); /* Called with rcu_read_lock() */ -enum skb_drop_reason +static enum skb_drop_reason tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, const void *saddr, const void *daddr, int family, int l3index, const __u8 *hash_location) @@ -4483,7 +4484,7 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, if (!key && hash_location) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); - tcp_hash_fail("Unexpected MD5 Hash found", family, skb, ""); + trace_tcp_hash_md5_unexpected(sk, skb); return SKB_DROP_REASON_TCP_MD5UNEXPECTED; } @@ -4498,29 +4499,90 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); - if (family == AF_INET) { - tcp_hash_fail("MD5 Hash failed", AF_INET, skb, "%s L3 index %d", - genhash ? "tcp_v4_calc_md5_hash failed" - : "", l3index); - } else { - if (genhash) { - tcp_hash_fail("MD5 Hash failed", - AF_INET6, skb, "L3 index %d", - l3index); - } else { - tcp_hash_fail("MD5 Hash mismatch", - AF_INET6, skb, "L3 index %d", - l3index); - } - } + trace_tcp_hash_md5_mismatch(sk, skb); return SKB_DROP_REASON_TCP_MD5FAILURE; } return SKB_NOT_DROPPED_YET; } -EXPORT_SYMBOL(tcp_inbound_md5_hash); +#else +static inline enum skb_drop_reason +tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, + const void *saddr, const void *daddr, + int family, int l3index, const __u8 *hash_location) +{ + return SKB_NOT_DROPPED_YET; +} #endif +/* Called with rcu_read_lock() */ +enum skb_drop_reason +tcp_inbound_hash(struct sock *sk, const struct request_sock *req, + const struct sk_buff *skb, + const void *saddr, const void *daddr, + int family, int dif, int sdif) +{ + const struct tcphdr *th = tcp_hdr(skb); + const struct tcp_ao_hdr *aoh; + const __u8 *md5_location; + int l3index; + + /* Invalid option or two times meet any of auth options */ + if (tcp_parse_auth_options(th, &md5_location, &aoh)) { + trace_tcp_hash_bad_header(sk, skb); + return SKB_DROP_REASON_TCP_AUTH_HDR; + } + + if (req) { + if (tcp_rsk_used_ao(req) != !!aoh) { + u8 keyid, rnext, maclen; + + if (aoh) { + keyid = aoh->keyid; + rnext = aoh->rnext_keyid; + maclen = tcp_ao_hdr_maclen(aoh); + } else { + keyid = rnext = maclen = 0; + } + + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); + trace_tcp_ao_handshake_failure(sk, skb, keyid, rnext, maclen); + return SKB_DROP_REASON_TCP_AOFAILURE; + } + } + + /* sdif set, means packet ingressed via a device + * in an L3 domain and dif is set to the l3mdev + */ + l3index = sdif ? dif : 0; + + /* Fast path: unsigned segments */ + if (likely(!md5_location && !aoh)) { + /* Drop if there's TCP-MD5 or TCP-AO key with any rcvid/sndid + * for the remote peer. On TCP-AO established connection + * the last key is impossible to remove, so there's + * always at least one current_key. + */ + if (tcp_ao_required(sk, saddr, family, l3index, true)) { + trace_tcp_hash_ao_required(sk, skb); + return SKB_DROP_REASON_TCP_AONOTFOUND; + } + if (unlikely(tcp_md5_do_lookup(sk, l3index, saddr, family))) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); + trace_tcp_hash_md5_required(sk, skb); + return SKB_DROP_REASON_TCP_MD5NOTFOUND; + } + return SKB_NOT_DROPPED_YET; + } + + if (aoh) + return tcp_inbound_ao_hash(sk, skb, family, req, l3index, aoh); + + return tcp_inbound_md5_hash(sk, skb, saddr, daddr, family, + l3index, md5_location); +} +EXPORT_SYMBOL_GPL(tcp_inbound_hash); + void tcp_done(struct sock *sk) { struct request_sock *req; diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 37c42b63ff99..85531437890c 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -16,6 +16,7 @@ #include <net/tcp.h> #include <net/ipv6.h> #include <net/icmp.h> +#include <trace/events/tcp.h> DEFINE_STATIC_KEY_DEFERRED_FALSE(tcp_ao_needed, HZ); @@ -884,17 +885,16 @@ tcp_ao_verify_hash(const struct sock *sk, const struct sk_buff *skb, const struct tcp_ao_hdr *aoh, struct tcp_ao_key *key, u8 *traffic_key, u8 *phash, u32 sne, int l3index) { - u8 maclen = aoh->length - sizeof(struct tcp_ao_hdr); const struct tcphdr *th = tcp_hdr(skb); + u8 maclen = tcp_ao_hdr_maclen(aoh); void *hash_buf = NULL; if (maclen != tcp_ao_maclen(key)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); atomic64_inc(&info->counters.pkt_bad); atomic64_inc(&key->pkt_bad); - tcp_hash_fail("AO hash wrong length", family, skb, - "%u != %d L3index: %d", maclen, - tcp_ao_maclen(key), l3index); + trace_tcp_ao_wrong_maclen(sk, skb, aoh->keyid, + aoh->rnext_keyid, maclen); return SKB_DROP_REASON_TCP_AOFAILURE; } @@ -909,8 +909,8 @@ tcp_ao_verify_hash(const struct sock *sk, const struct sk_buff *skb, NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); atomic64_inc(&info->counters.pkt_bad); atomic64_inc(&key->pkt_bad); - tcp_hash_fail("AO hash mismatch", family, skb, - "L3index: %d", l3index); + trace_tcp_ao_mismatch(sk, skb, aoh->keyid, + aoh->rnext_keyid, maclen); kfree(hash_buf); return SKB_DROP_REASON_TCP_AOFAILURE; } @@ -927,6 +927,7 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, int l3index, const struct tcp_ao_hdr *aoh) { const struct tcphdr *th = tcp_hdr(skb); + u8 maclen = tcp_ao_hdr_maclen(aoh); u8 *phash = (u8 *)(aoh + 1); /* hash goes just after the header */ struct tcp_ao_info *info; enum skb_drop_reason ret; @@ -939,8 +940,8 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, info = rcu_dereference(tcp_sk(sk)->ao_info); if (!info) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOKEYNOTFOUND); - tcp_hash_fail("AO key not found", family, skb, - "keyid: %u L3index: %d", aoh->keyid, l3index); + trace_tcp_ao_key_not_found(sk, skb, aoh->keyid, + aoh->rnext_keyid, maclen); return SKB_DROP_REASON_TCP_AOUNEXPECTED; } @@ -981,6 +982,9 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, current_key = READ_ONCE(info->current_key); /* Key rotation: the peer asks us to use new key (RNext) */ if (unlikely(aoh->rnext_keyid != current_key->sndid)) { + trace_tcp_ao_rnext_request(sk, skb, current_key->sndid, + aoh->rnext_keyid, + tcp_ao_hdr_maclen(aoh)); /* If the key is not found we do nothing. */ key = tcp_ao_established_key(info, aoh->rnext_keyid, -1); if (key) @@ -1046,8 +1050,8 @@ verify_hash: key_not_found: NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOKEYNOTFOUND); atomic64_inc(&info->counters.key_not_found); - tcp_hash_fail("Requested by the peer AO key id not found", - family, skb, "L3index: %d", l3index); + trace_tcp_ao_key_not_found(sk, skb, aoh->keyid, + aoh->rnext_keyid, maclen); return SKB_DROP_REASON_TCP_AOKEYNOTFOUND; } @@ -1968,8 +1972,10 @@ static int tcp_ao_info_cmd(struct sock *sk, unsigned short int family, first = true; } - if (cmd.ao_required && tcp_ao_required_verify(sk)) - return -EKEYREJECTED; + if (cmd.ao_required && tcp_ao_required_verify(sk)) { + err = -EKEYREJECTED; + goto out; + } /* For sockets in TCP_CLOSED it's possible set keys that aren't * matching the future peer (address/port/VRF/etc), diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index eb187450e4d7..ec2ed92dcad5 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2782,13 +2782,37 @@ static void tcp_mtup_probe_success(struct sock *sk) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMTUPSUCCESS); } +/* Sometimes we deduce that packets have been dropped due to reasons other than + * congestion, like path MTU reductions or failed client TFO attempts. In these + * cases we call this function to retransmit as many packets as cwnd allows, + * without reducing cwnd. Given that retransmits will set retrans_stamp to a + * non-zero value (and may do so in a later calling context due to TSQ), we + * also enter CA_Loss so that we track when all retransmitted packets are ACKed + * and clear retrans_stamp when that happens (to ensure later recurring RTOs + * are using the correct retrans_stamp and don't declare ETIMEDOUT + * prematurely). + */ +static void tcp_non_congestion_loss_retransmit(struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + + if (icsk->icsk_ca_state != TCP_CA_Loss) { + tp->high_seq = tp->snd_nxt; + tp->snd_ssthresh = tcp_current_ssthresh(sk); + tp->prior_ssthresh = 0; + tp->undo_marker = 0; + tcp_set_ca_state(sk, TCP_CA_Loss); + } + tcp_xmit_retransmit_queue(sk); +} + /* Do a simple retransmit without using the backoff mechanisms in * tcp_timer. This is used for path mtu discovery. * The socket is already locked here. */ void tcp_simple_retransmit(struct sock *sk) { - const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; int mss; @@ -2828,14 +2852,7 @@ void tcp_simple_retransmit(struct sock *sk) * in network, but units changed and effective * cwnd/ssthresh really reduced now. */ - if (icsk->icsk_ca_state != TCP_CA_Loss) { - tp->high_seq = tp->snd_nxt; - tp->snd_ssthresh = tcp_current_ssthresh(sk); - tp->prior_ssthresh = 0; - tp->undo_marker = 0; - tcp_set_ca_state(sk, TCP_CA_Loss); - } - tcp_xmit_retransmit_queue(sk); + tcp_non_congestion_loss_retransmit(sk); } EXPORT_SYMBOL(tcp_simple_retransmit); @@ -3578,8 +3595,10 @@ static void tcp_snd_sne_update(struct tcp_sock *tp, u32 ack) ao = rcu_dereference_protected(tp->ao_info, lockdep_sock_is_held((struct sock *)tp)); - if (ao && ack < tp->snd_una) + if (ao && ack < tp->snd_una) { ao->snd_sne++; + trace_tcp_ao_snd_sne_update((struct sock *)tp, ao->snd_sne); + } #endif } @@ -3604,8 +3623,10 @@ static void tcp_rcv_sne_update(struct tcp_sock *tp, u32 seq) ao = rcu_dereference_protected(tp->ao_info, lockdep_sock_is_held((struct sock *)tp)); - if (ao && seq < tp->rcv_nxt) + if (ao && seq < tp->rcv_nxt) { ao->rcv_sne++; + trace_tcp_ao_rcv_sne_update((struct sock *)tp, ao->rcv_sne); + } #endif } @@ -4856,7 +4877,7 @@ static void tcp_drop_reason(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason) { sk_drops_add(sk, skb); - kfree_skb_reason(skb, reason); + sk_skb_reason_drop(sk, skb, reason); } /* This one checks to see if we can put data from the @@ -6300,7 +6321,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, tp->fastopen_client_fail = TFO_DATA_NOT_ACKED; skb_rbtree_walk_from(data) tcp_mark_skb_lost(sk, data); - tcp_xmit_retransmit_queue(sk); + tcp_non_congestion_loss_retransmit(sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL); return true; @@ -7236,7 +7257,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_rsk(req)->tfo_listener = false; if (!want_cookie) { req->timeout = tcp_timeout_init((struct sock *)req); - inet_csk_reqsk_queue_hash_add(sk, req, req->timeout); + if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, + req->timeout))) { + reqsk_free(req); + return 0; + } + } af_ops->send_synack(sk, dst, &fl, req, &foc, !want_cookie ? TCP_SYNACK_NORMAL : diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index e61c7c974745..fd17f25ff288 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -93,7 +93,9 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, struct inet_hashinfo tcp_hashinfo; EXPORT_SYMBOL(tcp_hashinfo); -static DEFINE_PER_CPU(struct sock *, ipv4_tcp_sk); +static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = { + .bh_lock = INIT_LOCAL_LOCK(bh_lock), +}; static u32 tcp_v4_init_seq(const struct sk_buff *skb) { @@ -882,7 +884,9 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, arg.tos = ip_hdr(skb)->tos; arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); local_bh_disable(); - ctl_sk = this_cpu_read(ipv4_tcp_sk); + local_lock_nested_bh(&ipv4_tcp_sk.bh_lock); + ctl_sk = this_cpu_read(ipv4_tcp_sk.sock); + sock_net_set(ctl_sk, net); if (sk) { ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? @@ -907,6 +911,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); __TCP_INC_STATS(net, TCP_MIB_OUTRSTS); + local_unlock_nested_bh(&ipv4_tcp_sk.bh_lock); local_bh_enable(); #ifdef CONFIG_TCP_MD5SIG @@ -1002,7 +1007,8 @@ static void tcp_v4_send_ack(const struct sock *sk, arg.tos = tos; arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL); local_bh_disable(); - ctl_sk = this_cpu_read(ipv4_tcp_sk); + local_lock_nested_bh(&ipv4_tcp_sk.bh_lock); + ctl_sk = this_cpu_read(ipv4_tcp_sk.sock); sock_net_set(ctl_sk, net); ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark); @@ -1017,6 +1023,7 @@ static void tcp_v4_send_ack(const struct sock *sk, sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); + local_unlock_nested_bh(&ipv4_tcp_sk.bh_lock); local_bh_enable(); } @@ -1054,12 +1061,10 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) #else if (0) { #endif -#ifdef CONFIG_TCP_MD5SIG - } else if (static_branch_unlikely(&tcp_md5_needed.key)) { + } else if (static_branch_tcp_md5()) { key.md5_key = tcp_twsk_md5_key(tcptw); if (key.md5_key) key.type = TCP_KEY_MD5; -#endif } tcp_v4_send_ack(sk, skb, @@ -1128,8 +1133,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, #else if (0) { #endif -#ifdef CONFIG_TCP_MD5SIG - } else if (static_branch_unlikely(&tcp_md5_needed.key)) { + } else if (static_branch_tcp_md5()) { const union tcp_md5_addr *addr; int l3index; @@ -1138,7 +1142,6 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, key.md5_key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); if (key.md5_key) key.type = TCP_KEY_MD5; -#endif } tcp_v4_send_ack(sk, skb, seq, @@ -1936,7 +1939,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) reset: tcp_v4_send_reset(rsk, skb, sk_rst_convert_drop_reason(reason)); discard: - kfree_skb_reason(skb, reason); + sk_skb_reason_drop(sk, skb, reason); /* Be careful here. If this function gets more complicated and * gcc suffers from register pressure on the x86, sk (in %ebx) * might be destroyed here. This current version compiles correctly, @@ -2172,8 +2175,8 @@ int tcp_v4_rcv(struct sk_buff *skb) int dif = inet_iif(skb); const struct iphdr *iph; const struct tcphdr *th; + struct sock *sk = NULL; bool refcounted; - struct sock *sk; int ret; u32 isn; @@ -2372,7 +2375,7 @@ bad_packet: discard_it: SKB_DR_OR(drop_reason, NOT_SPECIFIED); /* Discard frame. */ - kfree_skb_reason(skb, drop_reason); + sk_skb_reason_drop(sk, skb, drop_reason); return 0; discard_and_relse: @@ -3619,7 +3622,7 @@ void __init tcp_v4_init(void) sk->sk_clockid = CLOCK_MONOTONIC; - per_cpu(ipv4_tcp_sk, cpu) = sk; + per_cpu(ipv4_tcp_sk.sock, cpu) = sk; } if (register_pernet_subsys(&tcp_sk_ops)) panic("Failed to create the TCP control socket.\n"); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 090fb0c24599..16c48df8df4c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3768,6 +3768,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, #ifdef CONFIG_TCP_AO struct tcp_ao_key *ao_key = NULL; u8 keyid = tcp_rsk(req)->ao_keyid; + u8 rnext = tcp_rsk(req)->ao_rcv_next; ao_key = tcp_sk(sk)->af_specific->ao_lookup(sk, req_to_sk(req), keyid, -1); @@ -3777,6 +3778,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, * ao_keyid (RFC5925 RNextKeyID), so let's keep it simple here. */ if (unlikely(!ao_key)) { + trace_tcp_ao_synack_no_key(sk, keyid, rnext); rcu_read_unlock(); kfree_skb(skb); net_warn_ratelimited("TCP-AO: the keyid %u from SYN packet is not present - not sending SYNACK\n", diff --git a/net/ipv4/tcp_sigpool.c b/net/ipv4/tcp_sigpool.c index 8512cb09ebc0..d8a4f192873a 100644 --- a/net/ipv4/tcp_sigpool.c +++ b/net/ipv4/tcp_sigpool.c @@ -10,7 +10,14 @@ #include <net/tcp.h> static size_t __scratch_size; -static DEFINE_PER_CPU(void __rcu *, sigpool_scratch); +struct sigpool_scratch { + local_lock_t bh_lock; + void __rcu *pad; +}; + +static DEFINE_PER_CPU(struct sigpool_scratch, sigpool_scratch) = { + .bh_lock = INIT_LOCAL_LOCK(bh_lock), +}; struct sigpool_entry { struct crypto_ahash *hash; @@ -72,7 +79,7 @@ static int sigpool_reserve_scratch(size_t size) break; } - old_scratch = rcu_replace_pointer(per_cpu(sigpool_scratch, cpu), + old_scratch = rcu_replace_pointer(per_cpu(sigpool_scratch.pad, cpu), scratch, lockdep_is_held(&cpool_mutex)); if (!cpu_online(cpu) || !old_scratch) { kfree(old_scratch); @@ -93,7 +100,7 @@ static void sigpool_scratch_free(void) int cpu; for_each_possible_cpu(cpu) - kfree(rcu_replace_pointer(per_cpu(sigpool_scratch, cpu), + kfree(rcu_replace_pointer(per_cpu(sigpool_scratch.pad, cpu), NULL, lockdep_is_held(&cpool_mutex))); __scratch_size = 0; } @@ -277,7 +284,8 @@ int tcp_sigpool_start(unsigned int id, struct tcp_sigpool *c) __cond_acquires(RC /* Pairs with tcp_sigpool_reserve_scratch(), scratch area is * valid (allocated) until tcp_sigpool_end(). */ - c->scratch = rcu_dereference_bh(*this_cpu_ptr(&sigpool_scratch)); + local_lock_nested_bh(&sigpool_scratch.bh_lock); + c->scratch = rcu_dereference_bh(*this_cpu_ptr(&sigpool_scratch.pad)); return 0; } EXPORT_SYMBOL_GPL(tcp_sigpool_start); @@ -286,6 +294,7 @@ void tcp_sigpool_end(struct tcp_sigpool *c) __releases(RCU_BH) { struct crypto_ahash *hash = crypto_ahash_reqtfm(c->req); + local_unlock_nested_bh(&sigpool_scratch.bh_lock); rcu_read_unlock_bh(); ahash_request_free(c->req); crypto_free_ahash(hash); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 3e8604ae7d06..ab4b6de0e069 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -481,8 +481,12 @@ static bool tcp_rtx_probe0_timed_out(const struct sock *sk, { const struct tcp_sock *tp = tcp_sk(sk); const int timeout = TCP_RTO_MAX * 2; - u32 rcv_delta; + s32 rcv_delta; + /* Note: timer interrupt might have been delayed by at least one jiffy, + * and tp->rcv_tstamp might very well have been written recently. + * rcv_delta can thus be negative. + */ rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp; if (rcv_delta <= timeout) return false; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index c9ca6d285347..d08bf16d476d 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2074,7 +2074,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); trace_udp_fail_queue_rcv_skb(rc, sk, skb); - kfree_skb_reason(skb, drop_reason); + sk_skb_reason_drop(sk, skb, drop_reason); return -1; } @@ -2196,7 +2196,7 @@ csum_error: drop: __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); atomic_inc(&sk->sk_drops); - kfree_skb_reason(skb, drop_reason); + sk_skb_reason_drop(sk, skb, drop_reason); return -1; } @@ -2383,7 +2383,7 @@ static int udp_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { - struct sock *sk; + struct sock *sk = NULL; struct udphdr *uh; unsigned short ulen; struct rtable *rt = skb_rtable(skb); @@ -2460,7 +2460,7 @@ no_sk: * Hmm. We got an UDP packet to a port to which we * don't wanna listen. Ignore it. */ - kfree_skb_reason(skb, drop_reason); + sk_skb_reason_drop(sk, skb, drop_reason); return 0; short_packet: @@ -2485,7 +2485,7 @@ csum_error: __UDP_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); drop: __UDP_INC_STATS(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); - kfree_skb_reason(skb, drop_reason); + sk_skb_reason_drop(sk, skb, drop_reason); return 0; } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index d9c9a542a414..eb111d20615c 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -2514,7 +2514,8 @@ int __init fib6_init(void) goto out_kmem_cache_create; ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETROUTE, NULL, - inet6_dump_fib, RTNL_FLAG_DUMP_UNLOCKED); + inet6_dump_fib, RTNL_FLAG_DUMP_UNLOCKED | + RTNL_FLAG_DUMP_SPLIT_NLM_DONE); if (ret) goto out_unregister_subsys; diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index e0c2347b4dc6..581ce055bf52 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -36,6 +36,7 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, .saddr = iph->saddr, + .flowlabel = ip6_flowinfo(iph), }; int err; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index f838366e8256..608fa9d05b55 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -362,14 +362,14 @@ static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb) if ((raw6_sk(sk)->checksum || rcu_access_pointer(sk->sk_filter)) && skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); - kfree_skb_reason(skb, SKB_DROP_REASON_SKB_CSUM); + sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_SKB_CSUM); return NET_RX_DROP; } /* Charge it to the socket. */ skb_dst_drop(skb); if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) { - kfree_skb_reason(skb, reason); + sk_skb_reason_drop(sk, skb, reason); return NET_RX_DROP; } @@ -390,7 +390,7 @@ 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_reason(skb, SKB_DROP_REASON_XFRM_POLICY); + sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_XFRM_POLICY); return NET_RX_DROP; } nf_reset_ct(skb); @@ -415,7 +415,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) if (inet_test_bit(HDRINCL, sk)) { if (skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); - kfree_skb_reason(skb, SKB_DROP_REASON_SKB_CSUM); + sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_SKB_CSUM); return NET_RX_DROP; } } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index ad5fff5a210c..5b107f241cdb 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -636,6 +636,8 @@ static void rt6_probe(struct fib6_nh *fib6_nh) rcu_read_lock(); last_probe = READ_ONCE(fib6_nh->last_probe); idev = __in6_dev_get(dev); + if (!idev) + goto out; neigh = __ipv6_neigh_lookup_noref(dev, nh_gw); if (neigh) { if (READ_ONCE(neigh->nud_state) & NUD_VALID) @@ -2372,7 +2374,7 @@ static u32 rt6_multipath_custom_hash_outer(const struct net *net, hash_keys.ports.dst = keys.ports.dst; *p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION); - return flow_hash_from_keys(&hash_keys); + return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 rt6_multipath_custom_hash_inner(const struct net *net, @@ -2421,7 +2423,7 @@ static u32 rt6_multipath_custom_hash_inner(const struct net *net, if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) hash_keys.ports.dst = keys.ports.dst; - return flow_hash_from_keys(&hash_keys); + return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 rt6_multipath_custom_hash_skb(const struct net *net, @@ -2460,7 +2462,7 @@ static u32 rt6_multipath_custom_hash_fl6(const struct net *net, if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = fl6->fl6_dport; - return flow_hash_from_keys(&hash_keys); + return fib_multipath_hash_from_keys(net, &hash_keys); } /* if skb is set it will be used and fl6 can be NULL */ @@ -2482,7 +2484,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); hash_keys.basic.ip_proto = fl6->flowi6_proto; } - mhash = flow_hash_from_keys(&hash_keys); + mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 1: if (skb) { @@ -2514,7 +2516,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, hash_keys.ports.dst = fl6->fl6_dport; hash_keys.basic.ip_proto = fl6->flowi6_proto; } - mhash = flow_hash_from_keys(&hash_keys); + mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 2: memset(&hash_keys, 0, sizeof(hash_keys)); @@ -2551,7 +2553,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); hash_keys.basic.ip_proto = fl6->flowi6_proto; } - mhash = flow_hash_from_keys(&hash_keys); + mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 3: if (skb) @@ -3601,7 +3603,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, if (!dev) goto out; - if (idev->cnf.disable_ipv6) { + if (!idev || idev->cnf.disable_ipv6) { NL_SET_ERR_MSG(extack, "IPv6 is disabled on nexthop device"); err = -EACCES; goto out; @@ -6341,12 +6343,12 @@ static int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write, if (!write) return -EINVAL; - net = (struct net *)ctl->extra1; - delay = net->ipv6.sysctl.flush_delay; ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (ret) return ret; + net = (struct net *)ctl->extra1; + delay = net->ipv6.sysctl.flush_delay; fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0); return 0; } diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 24e2b4b494cb..c74705ead984 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -941,8 +941,8 @@ static int input_action_end_dx6(struct sk_buff *skb, if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, - dev_net(skb->dev), NULL, skb, NULL, - skb_dst(skb)->dev, input_action_end_dx6_finish); + dev_net(skb->dev), NULL, skb, skb->dev, + NULL, input_action_end_dx6_finish); return input_action_end_dx6_finish(dev_net(skb->dev), NULL, skb); drop: @@ -991,8 +991,8 @@ static int input_action_end_dx4(struct sk_buff *skb, if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, - dev_net(skb->dev), NULL, skb, NULL, - skb_dst(skb)->dev, input_action_end_dx4_finish); + dev_net(skb->dev), NULL, skb, skb->dev, + NULL, input_action_end_dx4_finish); return input_action_end_dx4_finish(dev_net(skb->dev), NULL, skb); drop: @@ -1380,7 +1380,9 @@ drop: return err; } -DEFINE_PER_CPU(struct seg6_bpf_srh_state, seg6_bpf_srh_states); +DEFINE_PER_CPU(struct seg6_bpf_srh_state, seg6_bpf_srh_states) = { + .bh_lock = INIT_LOCAL_LOCK(bh_lock), +}; bool seg6_bpf_has_valid_srh(struct sk_buff *skb) { @@ -1388,6 +1390,7 @@ bool seg6_bpf_has_valid_srh(struct sk_buff *skb) this_cpu_ptr(&seg6_bpf_srh_states); struct ipv6_sr_hdr *srh = srh_state->srh; + lockdep_assert_held(&srh_state->bh_lock); if (unlikely(srh == NULL)) return false; @@ -1408,8 +1411,7 @@ bool seg6_bpf_has_valid_srh(struct sk_buff *skb) static int input_action_end_bpf(struct sk_buff *skb, struct seg6_local_lwt *slwt) { - struct seg6_bpf_srh_state *srh_state = - this_cpu_ptr(&seg6_bpf_srh_states); + struct seg6_bpf_srh_state *srh_state; struct ipv6_sr_hdr *srh; int ret; @@ -1420,10 +1422,14 @@ static int input_action_end_bpf(struct sk_buff *skb, } advance_nextseg(srh, &ipv6_hdr(skb)->daddr); - /* preempt_disable is needed to protect the per-CPU buffer srh_state, - * which is also accessed by the bpf_lwt_seg6_* helpers + /* The access to the per-CPU buffer srh_state is protected by running + * always in softirq context (with disabled BH). On PREEMPT_RT the + * required locking is provided by the following local_lock_nested_bh() + * statement. It is also accessed by the bpf_lwt_seg6_* helpers via + * bpf_prog_run_save_cb(). */ - preempt_disable(); + local_lock_nested_bh(&seg6_bpf_srh_states.bh_lock); + srh_state = this_cpu_ptr(&seg6_bpf_srh_states); srh_state->srh = srh; srh_state->hdrlen = srh->hdrlen << 3; srh_state->valid = true; @@ -1446,15 +1452,15 @@ static int input_action_end_bpf(struct sk_buff *skb, if (srh_state->srh && !seg6_bpf_has_valid_srh(skb)) goto drop; + local_unlock_nested_bh(&seg6_bpf_srh_states.bh_lock); - preempt_enable(); if (ret != BPF_REDIRECT) seg6_lookup_nexthop(skb, NULL, 0); return dst_input(skb); drop: - preempt_enable(); + local_unlock_nested_bh(&seg6_bpf_srh_states.bh_lock); kfree_skb(skb); return -EINVAL; } diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index bfad1e89b6a6..9d83eadd308b 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -275,6 +275,6 @@ out: out_free: reqsk_free(req); out_drop: - kfree_skb_reason(skb, reason); + sk_skb_reason_drop(sk, skb, reason); return NULL; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f4777c03cdd7..200fea92f12f 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1435,7 +1435,6 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * */ newsk->sk_gso_type = SKB_GSO_TCPV6; - ip6_dst_store(newsk, dst, NULL, NULL); inet6_sk_rx_dst_set(newsk, skb); inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk); @@ -1446,6 +1445,8 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * memcpy(newnp, np, sizeof(struct ipv6_pinfo)); + ip6_dst_store(newsk, dst, NULL, NULL); + newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr; newnp->saddr = ireq->ir_v6_loc_addr; newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr; @@ -1673,7 +1674,7 @@ reset: discard: if (opt_skb) __kfree_skb(opt_skb); - kfree_skb_reason(skb, reason); + sk_skb_reason_drop(sk, skb, reason); return 0; csum_err: reason = SKB_DROP_REASON_TCP_CSUM; @@ -1746,8 +1747,8 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) int dif = inet6_iif(skb); const struct tcphdr *th; const struct ipv6hdr *hdr; + struct sock *sk = NULL; bool refcounted; - struct sock *sk; int ret; u32 isn; struct net *net = dev_net(skb->dev); @@ -1939,7 +1940,7 @@ bad_packet: discard_it: SKB_DR_OR(drop_reason, NOT_SPECIFIED); - kfree_skb_reason(skb, drop_reason); + sk_skb_reason_drop(sk, skb, drop_reason); return 0; discard_and_relse: diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index c81a07ac0463..b56f0b9f4307 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -673,7 +673,7 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); trace_udp_fail_queue_rcv_skb(rc, sk, skb); - kfree_skb_reason(skb, drop_reason); + sk_skb_reason_drop(sk, skb, drop_reason); return -1; } @@ -776,7 +776,7 @@ csum_error: drop: __UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); atomic_inc(&sk->sk_drops); - kfree_skb_reason(skb, drop_reason); + sk_skb_reason_drop(sk, skb, drop_reason); return -1; } @@ -940,8 +940,8 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; const struct in6_addr *saddr, *daddr; struct net *net = dev_net(skb->dev); + struct sock *sk = NULL; struct udphdr *uh; - struct sock *sk; bool refcounted; u32 ulen = 0; @@ -1033,7 +1033,7 @@ no_sk: __UDP6_INC_STATS(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); - kfree_skb_reason(skb, reason); + sk_skb_reason_drop(sk, skb, reason); return 0; short_packet: @@ -1054,7 +1054,7 @@ csum_error: __UDP6_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); discard: __UDP6_INC_STATS(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); - kfree_skb_reason(skb, reason); + sk_skb_reason_drop(sk, skb, reason); return 0; } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index cc885d3aa9e5..2f1ea5f999a2 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -56,12 +56,18 @@ static int xfrm6_get_saddr(struct net *net, int oif, { struct dst_entry *dst; struct net_device *dev; + struct inet6_dev *idev; dst = xfrm6_dst_lookup(net, 0, oif, NULL, daddr, mark); if (IS_ERR(dst)) return -EHOSTUNREACH; - dev = ip6_dst_idev(dst)->dev; + idev = ip6_dst_idev(dst); + if (!idev) { + dst_release(dst); + return -EHOSTUNREACH; + } + dev = idev->dev; ipv6_dev_get_saddr(dev_net(dev), dev, &daddr->in6, 0, &saddr->in6); dst_release(dst); return 0; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 88a34db265d8..64f446f0930b 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -39,7 +39,6 @@ #include <linux/ip.h> #include <linux/udp.h> #include <linux/l2tp.h> -#include <linux/hash.h> #include <linux/sort.h> #include <linux/file.h> #include <linux/nsproxy.h> @@ -107,11 +106,23 @@ struct l2tp_net { /* Lock for write access to l2tp_tunnel_idr */ spinlock_t l2tp_tunnel_idr_lock; struct idr l2tp_tunnel_idr; - struct hlist_head l2tp_session_hlist[L2TP_HASH_SIZE_2]; - /* Lock for write access to l2tp_session_hlist */ - spinlock_t l2tp_session_hlist_lock; + /* Lock for write access to l2tp_v[23]_session_idr/htable */ + spinlock_t l2tp_session_idr_lock; + struct idr l2tp_v2_session_idr; + struct idr l2tp_v3_session_idr; + struct hlist_head l2tp_v3_session_htable[16]; }; +static inline u32 l2tp_v2_session_key(u16 tunnel_id, u16 session_id) +{ + return ((u32)tunnel_id) << 16 | session_id; +} + +static inline unsigned long l2tp_v3_session_hashkey(struct sock *sk, u32 session_id) +{ + return ((unsigned long)sk) + session_id; +} + #if IS_ENABLED(CONFIG_IPV6) static bool l2tp_sk_is_v6(struct sock *sk) { @@ -125,29 +136,6 @@ static inline struct l2tp_net *l2tp_pernet(const struct net *net) return net_generic(net, l2tp_net_id); } -/* Session hash global list for L2TPv3. - * The session_id SHOULD be random according to RFC3931, but several - * L2TP implementations use incrementing session_ids. So we do a real - * hash on the session_id, rather than a simple bitmask. - */ -static inline struct hlist_head * -l2tp_session_id_hash_2(struct l2tp_net *pn, u32 session_id) -{ - return &pn->l2tp_session_hlist[hash_32(session_id, L2TP_HASH_BITS_2)]; -} - -/* Session hash list. - * The session_id SHOULD be random according to RFC2661, but several - * L2TP implementations (Cisco and Microsoft) use incrementing - * session_ids. So we do a real hash on the session_id, rather than a - * simple bitmask. - */ -static inline struct hlist_head * -l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id) -{ - return &tunnel->session_hlist[hash_32(session_id, L2TP_HASH_BITS)]; -} - static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) { trace_free_tunnel(tunnel); @@ -240,66 +228,82 @@ struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth) } EXPORT_SYMBOL_GPL(l2tp_tunnel_get_nth); -struct l2tp_session *l2tp_tunnel_get_session(struct l2tp_tunnel *tunnel, - u32 session_id) +struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, u32 session_id) { - struct hlist_head *session_list; + const struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_session *session; - session_list = l2tp_session_id_hash(tunnel, session_id); - rcu_read_lock_bh(); - hlist_for_each_entry_rcu(session, session_list, hlist) - if (session->session_id == session_id) { - l2tp_session_inc_refcount(session); - rcu_read_unlock_bh(); + session = idr_find(&pn->l2tp_v3_session_idr, session_id); + if (session && !hash_hashed(&session->hlist) && + refcount_inc_not_zero(&session->ref_count)) { + rcu_read_unlock_bh(); + return session; + } - return session; + /* If we get here and session is non-NULL, the session_id + * collides with one in another tunnel. If sk is non-NULL, + * find the session matching sk. + */ + if (session && sk) { + unsigned long key = l2tp_v3_session_hashkey(sk, session->session_id); + + hash_for_each_possible_rcu(pn->l2tp_v3_session_htable, session, + hlist, key) { + if (session->tunnel->sock == sk && + refcount_inc_not_zero(&session->ref_count)) { + rcu_read_unlock_bh(); + return session; + } } + } rcu_read_unlock_bh(); return NULL; } -EXPORT_SYMBOL_GPL(l2tp_tunnel_get_session); +EXPORT_SYMBOL_GPL(l2tp_v3_session_get); -struct l2tp_session *l2tp_session_get(const struct net *net, u32 session_id) +struct l2tp_session *l2tp_v2_session_get(const struct net *net, u16 tunnel_id, u16 session_id) { - struct hlist_head *session_list; + u32 session_key = l2tp_v2_session_key(tunnel_id, session_id); + const struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_session *session; - session_list = l2tp_session_id_hash_2(l2tp_pernet(net), session_id); - rcu_read_lock_bh(); - hlist_for_each_entry_rcu(session, session_list, global_hlist) - if (session->session_id == session_id) { - l2tp_session_inc_refcount(session); - rcu_read_unlock_bh(); - - return session; - } + session = idr_find(&pn->l2tp_v2_session_idr, session_key); + if (session && refcount_inc_not_zero(&session->ref_count)) { + rcu_read_unlock_bh(); + return session; + } rcu_read_unlock_bh(); return NULL; } +EXPORT_SYMBOL_GPL(l2tp_v2_session_get); + +struct l2tp_session *l2tp_session_get(const struct net *net, struct sock *sk, int pver, + u32 tunnel_id, u32 session_id) +{ + if (pver == L2TP_HDR_VER_2) + return l2tp_v2_session_get(net, tunnel_id, session_id); + else + return l2tp_v3_session_get(net, sk, session_id); +} EXPORT_SYMBOL_GPL(l2tp_session_get); struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth) { - int hash; struct l2tp_session *session; int count = 0; rcu_read_lock_bh(); - for (hash = 0; hash < L2TP_HASH_SIZE; hash++) { - hlist_for_each_entry_rcu(session, &tunnel->session_hlist[hash], hlist) { - if (++count > nth) { - l2tp_session_inc_refcount(session); - rcu_read_unlock_bh(); - return session; - } + list_for_each_entry_rcu(session, &tunnel->session_list, list) { + if (++count > nth) { + l2tp_session_inc_refcount(session); + rcu_read_unlock_bh(); + return session; } } - rcu_read_unlock_bh(); return NULL; @@ -313,86 +317,186 @@ struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, const char *ifname) { struct l2tp_net *pn = l2tp_pernet(net); - int hash; + unsigned long tunnel_id, tmp; struct l2tp_session *session; + struct l2tp_tunnel *tunnel; rcu_read_lock_bh(); - for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) { - hlist_for_each_entry_rcu(session, &pn->l2tp_session_hlist[hash], global_hlist) { - if (!strcmp(session->ifname, ifname)) { - l2tp_session_inc_refcount(session); - rcu_read_unlock_bh(); - - return session; + idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { + if (tunnel) { + list_for_each_entry_rcu(session, &tunnel->session_list, list) { + if (!strcmp(session->ifname, ifname)) { + l2tp_session_inc_refcount(session); + rcu_read_unlock_bh(); + + return session; + } } } } - rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_session_get_by_ifname); +static void l2tp_session_coll_list_add(struct l2tp_session_coll_list *clist, + struct l2tp_session *session) +{ + l2tp_session_inc_refcount(session); + WARN_ON_ONCE(session->coll_list); + session->coll_list = clist; + spin_lock(&clist->lock); + list_add(&session->clist, &clist->list); + spin_unlock(&clist->lock); +} + +static int l2tp_session_collision_add(struct l2tp_net *pn, + struct l2tp_session *session1, + struct l2tp_session *session2) +{ + struct l2tp_session_coll_list *clist; + + lockdep_assert_held(&pn->l2tp_session_idr_lock); + + if (!session2) + return -EEXIST; + + /* If existing session is in IP-encap tunnel, refuse new session */ + if (session2->tunnel->encap == L2TP_ENCAPTYPE_IP) + return -EEXIST; + + clist = session2->coll_list; + if (!clist) { + /* First collision. Allocate list to manage the collided sessions + * and add the existing session to the list. + */ + clist = kmalloc(sizeof(*clist), GFP_ATOMIC); + if (!clist) + return -ENOMEM; + + spin_lock_init(&clist->lock); + INIT_LIST_HEAD(&clist->list); + refcount_set(&clist->ref_count, 1); + l2tp_session_coll_list_add(clist, session2); + } + + /* If existing session isn't already in the session hlist, add it. */ + if (!hash_hashed(&session2->hlist)) + hash_add(pn->l2tp_v3_session_htable, &session2->hlist, + session2->hlist_key); + + /* Add new session to the hlist and collision list */ + hash_add(pn->l2tp_v3_session_htable, &session1->hlist, + session1->hlist_key); + refcount_inc(&clist->ref_count); + l2tp_session_coll_list_add(clist, session1); + + return 0; +} + +static void l2tp_session_collision_del(struct l2tp_net *pn, + struct l2tp_session *session) +{ + struct l2tp_session_coll_list *clist = session->coll_list; + unsigned long session_key = session->session_id; + struct l2tp_session *session2; + + lockdep_assert_held(&pn->l2tp_session_idr_lock); + + hash_del(&session->hlist); + + if (clist) { + /* Remove session from its collision list. If there + * are other sessions with the same ID, replace this + * session's IDR entry with that session, otherwise + * remove the IDR entry. If this is the last session, + * the collision list data is freed. + */ + spin_lock(&clist->lock); + list_del_init(&session->clist); + session2 = list_first_entry_or_null(&clist->list, struct l2tp_session, clist); + if (session2) { + void *old = idr_replace(&pn->l2tp_v3_session_idr, session2, session_key); + + WARN_ON_ONCE(IS_ERR_VALUE(old)); + } else { + void *removed = idr_remove(&pn->l2tp_v3_session_idr, session_key); + + WARN_ON_ONCE(removed != session); + } + session->coll_list = NULL; + spin_unlock(&clist->lock); + if (refcount_dec_and_test(&clist->ref_count)) + kfree(clist); + l2tp_session_dec_refcount(session); + } +} + int l2tp_session_register(struct l2tp_session *session, struct l2tp_tunnel *tunnel) { - struct l2tp_session *session_walk; - struct hlist_head *g_head; - struct hlist_head *head; - struct l2tp_net *pn; + struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); + u32 session_key; int err; - head = l2tp_session_id_hash(tunnel, session->session_id); - - spin_lock_bh(&tunnel->hlist_lock); + spin_lock_bh(&tunnel->list_lock); if (!tunnel->acpt_newsess) { err = -ENODEV; goto err_tlock; } - hlist_for_each_entry(session_walk, head, hlist) - if (session_walk->session_id == session->session_id) { - err = -EEXIST; - goto err_tlock; - } - if (tunnel->version == L2TP_HDR_VER_3) { - pn = l2tp_pernet(tunnel->l2tp_net); - g_head = l2tp_session_id_hash_2(pn, session->session_id); - - spin_lock_bh(&pn->l2tp_session_hlist_lock); - + session_key = session->session_id; + spin_lock_bh(&pn->l2tp_session_idr_lock); + err = idr_alloc_u32(&pn->l2tp_v3_session_idr, NULL, + &session_key, session_key, GFP_ATOMIC); /* IP encap expects session IDs to be globally unique, while - * UDP encap doesn't. + * UDP encap doesn't. This isn't per the RFC, which says that + * sessions are identified only by the session ID, but is to + * support existing userspace which depends on it. */ - hlist_for_each_entry(session_walk, g_head, global_hlist) - if (session_walk->session_id == session->session_id && - (session_walk->tunnel->encap == L2TP_ENCAPTYPE_IP || - tunnel->encap == L2TP_ENCAPTYPE_IP)) { - err = -EEXIST; - goto err_tlock_pnlock; - } + if (err == -ENOSPC && tunnel->encap == L2TP_ENCAPTYPE_UDP) { + struct l2tp_session *session2; - l2tp_tunnel_inc_refcount(tunnel); - hlist_add_head_rcu(&session->global_hlist, g_head); - - spin_unlock_bh(&pn->l2tp_session_hlist_lock); + session2 = idr_find(&pn->l2tp_v3_session_idr, + session_key); + err = l2tp_session_collision_add(pn, session, session2); + } + spin_unlock_bh(&pn->l2tp_session_idr_lock); } else { - l2tp_tunnel_inc_refcount(tunnel); + session_key = l2tp_v2_session_key(tunnel->tunnel_id, + session->session_id); + spin_lock_bh(&pn->l2tp_session_idr_lock); + err = idr_alloc_u32(&pn->l2tp_v2_session_idr, NULL, + &session_key, session_key, GFP_ATOMIC); + spin_unlock_bh(&pn->l2tp_session_idr_lock); } - hlist_add_head_rcu(&session->hlist, head); - spin_unlock_bh(&tunnel->hlist_lock); + if (err) { + if (err == -ENOSPC) + err = -EEXIST; + goto err_tlock; + } + + l2tp_tunnel_inc_refcount(tunnel); + + list_add(&session->list, &tunnel->session_list); + spin_unlock_bh(&tunnel->list_lock); + + spin_lock_bh(&pn->l2tp_session_idr_lock); + if (tunnel->version == L2TP_HDR_VER_3) + idr_replace(&pn->l2tp_v3_session_idr, session, session_key); + else + idr_replace(&pn->l2tp_v2_session_idr, session, session_key); + spin_unlock_bh(&pn->l2tp_session_idr_lock); trace_register_session(session); return 0; -err_tlock_pnlock: - spin_unlock_bh(&pn->l2tp_session_hlist_lock); err_tlock: - spin_unlock_bh(&tunnel->hlist_lock); + spin_unlock_bh(&tunnel->list_lock); return err; } @@ -785,19 +889,14 @@ static void l2tp_session_queue_purge(struct l2tp_session *session) } } -/* Internal UDP receive frame. Do the real work of receiving an L2TP data frame - * here. The skb is not on a list when we get here. - * Returns 0 if the packet was a data packet and was successfully passed on. - * Returns 1 if the packet was not a good data packet and could not be - * forwarded. All such packets are passed up to userspace to deal with. - */ -static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) +/* UDP encapsulation receive handler. See net/ipv4/udp.c for details. */ +int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct l2tp_session *session = NULL; - struct l2tp_tunnel *orig_tunnel = tunnel; + struct l2tp_tunnel *tunnel = NULL; + struct net *net = sock_net(sk); unsigned char *ptr, *optr; u16 hdrflags; - u32 tunnel_id, session_id; u16 version; int length; @@ -807,11 +906,8 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) __skb_pull(skb, sizeof(struct udphdr)); /* Short packet? */ - if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) { - pr_debug_ratelimited("%s: recv short packet (len=%d)\n", - tunnel->name, skb->len); - goto invalid; - } + if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) + goto pass; /* Point to L2TP header */ optr = skb->data; @@ -834,6 +930,8 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) ptr += 2; if (version == L2TP_HDR_VER_2) { + u16 tunnel_id, session_id; + /* If length is present, skip it */ if (hdrflags & L2TP_HDRFLAG_L) ptr += 2; @@ -841,49 +939,35 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) /* Extract tunnel and session ID */ tunnel_id = ntohs(*(__be16 *)ptr); ptr += 2; - - if (tunnel_id != tunnel->tunnel_id) { - /* We are receiving trafic for another tunnel, probably - * because we have several tunnels between the same - * IP/port quadruple, look it up. - */ - struct l2tp_tunnel *alt_tunnel; - - alt_tunnel = l2tp_tunnel_get(tunnel->l2tp_net, tunnel_id); - if (!alt_tunnel) - goto pass; - tunnel = alt_tunnel; - } - session_id = ntohs(*(__be16 *)ptr); ptr += 2; + + session = l2tp_v2_session_get(net, tunnel_id, session_id); } else { + u32 session_id; + ptr += 2; /* skip reserved bits */ - tunnel_id = tunnel->tunnel_id; session_id = ntohl(*(__be32 *)ptr); ptr += 4; - } - /* Check protocol version */ - if (version != tunnel->version) { - pr_debug_ratelimited("%s: recv protocol version mismatch: got %d expected %d\n", - tunnel->name, version, tunnel->version); - goto invalid; + session = l2tp_v3_session_get(net, sk, session_id); } - /* Find the session context */ - session = l2tp_tunnel_get_session(tunnel, session_id); if (!session || !session->recv_skb) { if (session) l2tp_session_dec_refcount(session); /* Not found? Pass to userspace to deal with */ - pr_debug_ratelimited("%s: no session found (%u/%u). Passing up.\n", - tunnel->name, tunnel_id, session_id); goto pass; } - if (tunnel->version == L2TP_HDR_VER_3 && + tunnel = session->tunnel; + + /* Check protocol version */ + if (version != tunnel->version) + goto invalid; + + if (version == L2TP_HDR_VER_3 && l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) { l2tp_session_dec_refcount(session); goto invalid; @@ -892,9 +976,6 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); l2tp_session_dec_refcount(session); - if (tunnel != orig_tunnel) - l2tp_tunnel_dec_refcount(tunnel); - return 0; invalid: @@ -904,51 +985,14 @@ pass: /* Put UDP header back */ __skb_push(skb, sizeof(struct udphdr)); - if (tunnel != orig_tunnel) - l2tp_tunnel_dec_refcount(tunnel); - - return 1; -} - -/* UDP encapsulation receive and error receive handlers. - * See net/ipv4/udp.c for details. - * - * Note that these functions are called from inside an - * RCU-protected region, but without the socket being locked. - * - * Hence we use rcu_dereference_sk_user_data to access the - * tunnel data structure rather the usual l2tp_sk_to_tunnel - * accessor function. - */ -int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) -{ - struct l2tp_tunnel *tunnel; - - tunnel = rcu_dereference_sk_user_data(sk); - if (!tunnel) - goto pass_up; - if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC)) - goto pass_up; - - if (l2tp_udp_recv_core(tunnel, skb)) - goto pass_up; - - return 0; - -pass_up: return 1; } EXPORT_SYMBOL_GPL(l2tp_udp_encap_recv); +/* UDP encapsulation receive error handler. See net/ipv4/udp.c for details. */ static void l2tp_udp_encap_err_recv(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload) { - struct l2tp_tunnel *tunnel; - - tunnel = rcu_dereference_sk_user_data(sk); - if (!tunnel || tunnel->fd < 0) - return; - sk->sk_err = err; sk_error_report(sk); @@ -1206,26 +1250,36 @@ end: return; } -/* Remove an l2tp session from l2tp_core's hash lists. */ +/* Remove an l2tp session from l2tp_core's lists. */ static void l2tp_session_unhash(struct l2tp_session *session) { struct l2tp_tunnel *tunnel = session->tunnel; - /* Remove the session from core hashes */ if (tunnel) { - /* Remove from the per-tunnel hash */ - spin_lock_bh(&tunnel->hlist_lock); - hlist_del_init_rcu(&session->hlist); - spin_unlock_bh(&tunnel->hlist_lock); - - /* For L2TPv3 we have a per-net hash: remove from there, too */ - if (tunnel->version != L2TP_HDR_VER_2) { - struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); - - spin_lock_bh(&pn->l2tp_session_hlist_lock); - hlist_del_init_rcu(&session->global_hlist); - spin_unlock_bh(&pn->l2tp_session_hlist_lock); + struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); + struct l2tp_session *removed = session; + + /* Remove from the per-tunnel list */ + spin_lock_bh(&tunnel->list_lock); + list_del_init(&session->list); + spin_unlock_bh(&tunnel->list_lock); + + /* Remove from per-net IDR */ + spin_lock_bh(&pn->l2tp_session_idr_lock); + if (tunnel->version == L2TP_HDR_VER_3) { + if (hash_hashed(&session->hlist)) + l2tp_session_collision_del(pn, session); + else + removed = idr_remove(&pn->l2tp_v3_session_idr, + session->session_id); + } else { + u32 session_key = l2tp_v2_session_key(tunnel->tunnel_id, + session->session_id); + removed = idr_remove(&pn->l2tp_v2_session_idr, + session_key); } + WARN_ON_ONCE(removed && removed != session); + spin_unlock_bh(&pn->l2tp_session_idr_lock); synchronize_rcu(); } @@ -1236,28 +1290,19 @@ static void l2tp_session_unhash(struct l2tp_session *session) static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) { struct l2tp_session *session; - int hash; + struct list_head *pos; + struct list_head *tmp; - spin_lock_bh(&tunnel->hlist_lock); + spin_lock_bh(&tunnel->list_lock); tunnel->acpt_newsess = false; - for (hash = 0; hash < L2TP_HASH_SIZE; hash++) { -again: - hlist_for_each_entry_rcu(session, &tunnel->session_hlist[hash], hlist) { - hlist_del_init_rcu(&session->hlist); - - spin_unlock_bh(&tunnel->hlist_lock); - l2tp_session_delete(session); - spin_lock_bh(&tunnel->hlist_lock); - - /* Now restart from the beginning of this hash - * chain. We always remove a session from the - * list so we are guaranteed to make forward - * progress. - */ - goto again; - } + list_for_each_safe(pos, tmp, &tunnel->session_list) { + session = list_entry(pos, struct l2tp_session, list); + list_del_init(&session->list); + spin_unlock_bh(&tunnel->list_lock); + l2tp_session_delete(session); + spin_lock_bh(&tunnel->list_lock); } - spin_unlock_bh(&tunnel->hlist_lock); + spin_unlock_bh(&tunnel->list_lock); } /* Tunnel socket destroy hook for UDP encapsulation */ @@ -1451,8 +1496,9 @@ int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, tunnel->magic = L2TP_TUNNEL_MAGIC; sprintf(&tunnel->name[0], "tunl %u", tunnel_id); - spin_lock_init(&tunnel->hlist_lock); + spin_lock_init(&tunnel->list_lock); tunnel->acpt_newsess = true; + INIT_LIST_HEAD(&tunnel->session_list); tunnel->encap = encap; @@ -1462,8 +1508,6 @@ int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, /* Init delete workqueue struct */ INIT_WORK(&tunnel->del_work, l2tp_tunnel_del_work); - INIT_LIST_HEAD(&tunnel->list); - err = 0; err: if (tunnelp) @@ -1651,8 +1695,10 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn skb_queue_head_init(&session->reorder_q); + session->hlist_key = l2tp_v3_session_hashkey(tunnel->sock, session->session_id); INIT_HLIST_NODE(&session->hlist); - INIT_HLIST_NODE(&session->global_hlist); + INIT_LIST_HEAD(&session->clist); + INIT_LIST_HEAD(&session->list); if (cfg) { session->pwtype = cfg->pw_type; @@ -1685,15 +1731,13 @@ EXPORT_SYMBOL_GPL(l2tp_session_create); static __net_init int l2tp_init_net(struct net *net) { struct l2tp_net *pn = net_generic(net, l2tp_net_id); - int hash; idr_init(&pn->l2tp_tunnel_idr); spin_lock_init(&pn->l2tp_tunnel_idr_lock); - for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) - INIT_HLIST_HEAD(&pn->l2tp_session_hlist[hash]); - - spin_lock_init(&pn->l2tp_session_hlist_lock); + idr_init(&pn->l2tp_v2_session_idr); + idr_init(&pn->l2tp_v3_session_idr); + spin_lock_init(&pn->l2tp_session_idr_lock); return 0; } @@ -1703,7 +1747,6 @@ static __net_exit void l2tp_exit_net(struct net *net) struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_tunnel *tunnel = NULL; unsigned long tunnel_id, tmp; - int hash; rcu_read_lock_bh(); idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { @@ -1716,8 +1759,8 @@ static __net_exit void l2tp_exit_net(struct net *net) flush_workqueue(l2tp_wq); rcu_barrier(); - for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) - WARN_ON_ONCE(!hlist_empty(&pn->l2tp_session_hlist[hash])); + idr_destroy(&pn->l2tp_v2_session_idr); + idr_destroy(&pn->l2tp_v3_session_idr); idr_destroy(&pn->l2tp_tunnel_idr); } diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 91ebf0a3f499..8ac81bc1bc6f 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -19,14 +19,6 @@ #define L2TP_TUNNEL_MAGIC 0x42114DDA #define L2TP_SESSION_MAGIC 0x0C04EB7D -/* Per tunnel session hash table size */ -#define L2TP_HASH_BITS 4 -#define L2TP_HASH_SIZE BIT(L2TP_HASH_BITS) - -/* System-wide session hash table size */ -#define L2TP_HASH_BITS_2 8 -#define L2TP_HASH_SIZE_2 BIT(L2TP_HASH_BITS_2) - struct sk_buff; struct l2tp_stats { @@ -61,10 +53,15 @@ struct l2tp_session_cfg { char *ifname; }; +struct l2tp_session_coll_list { + spinlock_t lock; /* for access to list */ + struct list_head list; + refcount_t ref_count; +}; + /* Represents a session (pseudowire) instance. * Tracks runtime state including cookies, dataplane packet sequencing, and IO statistics. - * Is linked into a per-tunnel session hashlist; and in the case of an L2TPv3 session into - * an additional per-net ("global") hashlist. + * Is linked into a per-tunnel session list and a per-net ("global") IDR tree. */ #define L2TP_SESSION_NAME_MAX 32 struct l2tp_session { @@ -88,8 +85,12 @@ struct l2tp_session { u32 nr_oos; /* NR of last OOS packet */ int nr_oos_count; /* for OOS recovery */ int nr_oos_count_max; - struct hlist_node hlist; /* hash list node */ + struct list_head list; /* per-tunnel list node */ refcount_t ref_count; + struct hlist_node hlist; /* per-net session hlist */ + unsigned long hlist_key; /* key for session hlist */ + struct l2tp_session_coll_list *coll_list; /* session collision list */ + struct list_head clist; /* for coll_list */ char name[L2TP_SESSION_NAME_MAX]; /* for logging */ char ifname[IFNAMSIZ]; @@ -102,7 +103,6 @@ struct l2tp_session { int reorder_skip; /* set if skip to next nr */ enum l2tp_pwtype pwtype; struct l2tp_stats stats; - struct hlist_node global_hlist; /* global hash list node */ /* Session receive handler for data packets. * Each pseudowire implementation should implement this callback in order to @@ -114,7 +114,7 @@ struct l2tp_session { /* Session close handler. * Each pseudowire implementation may implement this callback in order to carry * out pseudowire-specific shutdown actions. - * The callback is called by core after unhashing the session and purging its + * The callback is called by core after unlisting the session and purging its * reorder queue. */ void (*session_close)(struct l2tp_session *session); @@ -150,7 +150,7 @@ struct l2tp_tunnel_cfg { /* Represents a tunnel instance. * Tracks runtime state including IO statistics. * Holds the tunnel socket (either passed from userspace or directly created by the kernel). - * Maintains a hashlist of sessions belonging to the tunnel instance. + * Maintains a list of sessions belonging to the tunnel instance. * Is linked into a per-net list of tunnels. */ #define L2TP_TUNNEL_NAME_MAX 20 @@ -160,12 +160,11 @@ struct l2tp_tunnel { unsigned long dead; struct rcu_head rcu; - spinlock_t hlist_lock; /* write-protection for session_hlist */ + spinlock_t list_lock; /* write-protection for session_list */ bool acpt_newsess; /* indicates whether this tunnel accepts - * new sessions. Protected by hlist_lock. + * new sessions. Protected by list_lock. */ - struct hlist_head session_hlist[L2TP_HASH_SIZE]; - /* hashed list of sessions, hashed by id */ + struct list_head session_list; /* list of sessions */ u32 tunnel_id; u32 peer_tunnel_id; int version; /* 2=>L2TPv2, 3=>L2TPv3 */ @@ -174,7 +173,6 @@ struct l2tp_tunnel { enum l2tp_encap_type encap; struct l2tp_stats stats; - struct list_head list; /* list node on per-namespace list of tunnels */ struct net *l2tp_net; /* the net we belong to */ refcount_t ref_count; @@ -224,10 +222,11 @@ void l2tp_session_dec_refcount(struct l2tp_session *session); */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id); struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth); -struct l2tp_session *l2tp_tunnel_get_session(struct l2tp_tunnel *tunnel, - u32 session_id); -struct l2tp_session *l2tp_session_get(const struct net *net, u32 session_id); +struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, u32 session_id); +struct l2tp_session *l2tp_v2_session_get(const struct net *net, u16 tunnel_id, u16 session_id); +struct l2tp_session *l2tp_session_get(const struct net *net, struct sock *sk, int pver, + u32 tunnel_id, u32 session_id); struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth); struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, const char *ifname); diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index 4595b56d175d..8755ae521154 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -123,17 +123,14 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v) struct l2tp_tunnel *tunnel = v; struct l2tp_session *session; int session_count = 0; - int hash; rcu_read_lock_bh(); - for (hash = 0; hash < L2TP_HASH_SIZE; hash++) { - hlist_for_each_entry_rcu(session, &tunnel->session_hlist[hash], hlist) { - /* Session ID of zero is a dummy/reserved value used by pppol2tp */ - if (session->session_id == 0) - continue; + list_for_each_entry_rcu(session, &tunnel->session_list, list) { + /* Session ID of zero is a dummy/reserved value used by pppol2tp */ + if (session->session_id == 0) + continue; - session_count++; - } + session_count++; } rcu_read_unlock_bh(); diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 19c8cc5289d5..e48aa177d74c 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -140,7 +140,7 @@ static int l2tp_ip_recv(struct sk_buff *skb) } /* Ok, this is a data packet. Lookup the session. */ - session = l2tp_session_get(net, session_id); + session = l2tp_v3_session_get(net, NULL, session_id); if (!session) goto discard; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 8780ec64f376..d217ff1f229e 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -150,7 +150,7 @@ static int l2tp_ip6_recv(struct sk_buff *skb) } /* Ok, this is a data packet. Lookup the session. */ - session = l2tp_session_get(net, session_id); + session = l2tp_v3_session_get(net, NULL, session_id); if (!session) goto discard; diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index a901fd14fe3b..d105030520f9 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -61,7 +61,8 @@ static struct l2tp_session *l2tp_nl_session_get(struct genl_info *info) session_id = nla_get_u32(info->attrs[L2TP_ATTR_SESSION_ID]); tunnel = l2tp_tunnel_get(net, tunnel_id); if (tunnel) { - session = l2tp_tunnel_get_session(tunnel, session_id); + session = l2tp_session_get(net, tunnel->sock, tunnel->version, + tunnel_id, session_id); l2tp_tunnel_dec_refcount(tunnel); } } @@ -635,7 +636,8 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf &cfg); if (ret >= 0) { - session = l2tp_tunnel_get_session(tunnel, session_id); + session = l2tp_session_get(net, tunnel->sock, tunnel->version, + tunnel_id, session_id); if (session) { ret = l2tp_session_notify(&l2tp_nl_family, info, session, L2TP_CMD_SESSION_CREATE); diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 6146e4e67bbb..3596290047b2 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -753,7 +753,8 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, if (tunnel->peer_tunnel_id == 0) tunnel->peer_tunnel_id = info.peer_tunnel_id; - session = l2tp_tunnel_get_session(tunnel, info.session_id); + session = l2tp_session_get(sock_net(sk), tunnel->sock, tunnel->version, + info.tunnel_id, info.session_id); if (session) { drop_refcnt = true; @@ -1045,7 +1046,8 @@ static int pppol2tp_tunnel_copy_stats(struct pppol2tp_ioc_stats *stats, /* If session_id is set, search the corresponding session in the * context of this tunnel and record the session's statistics. */ - session = l2tp_tunnel_get_session(tunnel, stats->session_id); + session = l2tp_session_get(tunnel->l2tp_net, tunnel->sock, tunnel->version, + tunnel->tunnel_id, stats->session_id); if (!session) return -EBADR; diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index bef43990f07a..fe868b521622 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -311,6 +311,18 @@ int drv_assign_vif_chanctx(struct ieee80211_local *local, might_sleep(); lockdep_assert_wiphy(local->hw.wiphy); + /* + * We should perhaps push emulate chanctx down and only + * make it call ->config() when the chanctx is actually + * assigned here (and unassigned below), but that's yet + * another change to all drivers to add assign/unassign + * emulation callbacks. Maybe later. + */ + if (sdata->vif.type == NL80211_IFTYPE_MONITOR && + local->emulate_chanctx && + !ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) + return 0; + if (!check_sdata_in_driver(sdata)) return -EIO; @@ -338,6 +350,11 @@ void drv_unassign_vif_chanctx(struct ieee80211_local *local, might_sleep(); lockdep_assert_wiphy(local->hw.wiphy); + if (sdata->vif.type == NL80211_IFTYPE_MONITOR && + local->emulate_chanctx && + !ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) + return; + if (!check_sdata_in_driver(sdata)) return; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 64106097949a..6d969d9f1ac9 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -682,6 +682,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do ieee80211_del_virtual_monitor(local); ieee80211_recalc_idle(local); + ieee80211_recalc_offload(local); if (!(sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE)) break; @@ -1108,9 +1109,6 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local) struct ieee80211_sub_if_data *sdata; int ret; - if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) - return 0; - ASSERT_RTNL(); lockdep_assert_wiphy(local->hw.wiphy); @@ -1132,11 +1130,13 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local) ieee80211_set_default_queues(sdata); - ret = drv_add_interface(local, sdata); - if (WARN_ON(ret)) { - /* ok .. stupid driver, it asked for this! */ - kfree(sdata); - return ret; + if (ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { + ret = drv_add_interface(local, sdata); + if (WARN_ON(ret)) { + /* ok .. stupid driver, it asked for this! */ + kfree(sdata); + return ret; + } } set_bit(SDATA_STATE_RUNNING, &sdata->state); @@ -1174,9 +1174,6 @@ void ieee80211_del_virtual_monitor(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata; - if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) - return; - ASSERT_RTNL(); lockdep_assert_wiphy(local->hw.wiphy); @@ -1196,7 +1193,8 @@ void ieee80211_del_virtual_monitor(struct ieee80211_local *local) ieee80211_link_release_channel(&sdata->deflink); - drv_remove_interface(local, sdata); + if (ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) + drv_remove_interface(local, sdata); kfree(sdata); } diff --git a/net/mac80211/main.c b/net/mac80211/main.c index c8cb091b5ea3..a9aefc83d30a 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -424,6 +424,7 @@ u64 ieee80211_reset_erp_info(struct ieee80211_sub_if_data *sdata) BSS_CHANGED_ERP_SLOT; } +/* context: requires softirqs disabled */ void ieee80211_handle_queued_frames(struct ieee80211_local *local) { struct sk_buff *skb; diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 8ecc4b710b0e..b5f2df61c7f6 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -358,7 +358,8 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_sub_if_data *sdata) struct cfg80211_scan_request *req; struct cfg80211_chan_def chandef; u8 bands_used = 0; - int i, ielen, n_chans; + int i, ielen; + u32 *n_chans; u32 flags = 0; req = rcu_dereference_protected(local->scan_req, @@ -368,34 +369,34 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_sub_if_data *sdata) return false; if (ieee80211_hw_check(&local->hw, SINGLE_SCAN_ON_ALL_BANDS)) { + local->hw_scan_req->req.n_channels = req->n_channels; + for (i = 0; i < req->n_channels; i++) { local->hw_scan_req->req.channels[i] = req->channels[i]; bands_used |= BIT(req->channels[i]->band); } - - n_chans = req->n_channels; } else { do { if (local->hw_scan_band == NUM_NL80211_BANDS) return false; - n_chans = 0; + n_chans = &local->hw_scan_req->req.n_channels; + *n_chans = 0; for (i = 0; i < req->n_channels; i++) { if (req->channels[i]->band != local->hw_scan_band) continue; - local->hw_scan_req->req.channels[n_chans] = + local->hw_scan_req->req.channels[(*n_chans)++] = req->channels[i]; - n_chans++; + bands_used |= BIT(req->channels[i]->band); } local->hw_scan_band++; - } while (!n_chans); + } while (!*n_chans); } - local->hw_scan_req->req.n_channels = n_chans; ieee80211_prepare_scan_chandef(&chandef); if (req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT) diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 610f0a94796c..c6d5f73119d8 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1567,7 +1567,9 @@ u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata, void ieee80211_stop_device(struct ieee80211_local *local, bool suspend) { + local_bh_disable(); ieee80211_handle_queued_frames(local); + local_bh_enable(); ieee80211_led_radio(local, false); ieee80211_mod_tpt_led_trig(local, 0, IEEE80211_TPT_LEDTRIG_FL_RADIO); @@ -1843,7 +1845,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) /* add interfaces */ sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); - if (sdata) { + if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { /* in HW restart it exists already */ WARN_ON(local->resuming); res = drv_add_interface(local, sdata); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 7f53e022e27e..ea9e5817b9e9 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -677,6 +677,7 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) unsigned int add_addr_accept_max; struct mptcp_addr_info remote; unsigned int subflows_max; + bool sf_created = false; int i, nr; add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk); @@ -704,15 +705,18 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) if (nr == 0) return; - msk->pm.add_addr_accepted++; - if (msk->pm.add_addr_accepted >= add_addr_accept_max || - msk->pm.subflows >= subflows_max) - WRITE_ONCE(msk->pm.accept_addr, false); - spin_unlock_bh(&msk->pm.lock); for (i = 0; i < nr; i++) - __mptcp_subflow_connect(sk, &addrs[i], &remote); + if (__mptcp_subflow_connect(sk, &addrs[i], &remote) == 0) + sf_created = true; spin_lock_bh(&msk->pm.lock); + + if (sf_created) { + msk->pm.add_addr_accepted++; + if (msk->pm.add_addr_accepted >= add_addr_accept_max || + msk->pm.subflows >= subflows_max) + WRITE_ONCE(msk->pm.accept_addr, false); + } } void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk) @@ -814,10 +818,13 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, spin_lock_bh(&msk->pm.lock); removed = true; - __MPTCP_INC_STATS(sock_net(sk), rm_type); + if (rm_type == MPTCP_MIB_RMSUBFLOW) + __MPTCP_INC_STATS(sock_net(sk), rm_type); } if (rm_type == MPTCP_MIB_RMSUBFLOW) __set_bit(rm_id ? rm_id : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap); + else if (rm_type == MPTCP_MIB_RMADDR) + __MPTCP_INC_STATS(sock_net(sk), rm_type); if (!removed) continue; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index cacad912747a..a26c2c840fd9 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3740,6 +3740,7 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) WRITE_ONCE(msk->write_seq, subflow->idsn); WRITE_ONCE(msk->snd_nxt, subflow->idsn); + WRITE_ONCE(msk->snd_una, subflow->idsn); if (likely(!__mptcp_check_fallback(msk))) MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVE); diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 3126911f5042..b00fc285b334 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -815,12 +815,21 @@ int __init netfilter_init(void) if (ret < 0) goto err; +#ifdef CONFIG_LWTUNNEL + ret = netfilter_lwtunnel_init(); + if (ret < 0) + goto err_lwtunnel_pernet; +#endif ret = netfilter_log_init(); if (ret < 0) - goto err_pernet; + goto err_log_pernet; return 0; -err_pernet: +err_log_pernet: +#ifdef CONFIG_LWTUNNEL + netfilter_lwtunnel_fini(); +err_lwtunnel_pernet: +#endif unregister_pernet_subsys(&netfilter_net_ops); err: return ret; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 3184cc6be4c9..61431690cbd5 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -53,12 +53,13 @@ MODULE_DESCRIPTION("core IP set support"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET); /* When the nfnl mutex or ip_set_ref_lock is held: */ -#define ip_set_dereference(p) \ - rcu_dereference_protected(p, \ +#define ip_set_dereference(inst) \ + rcu_dereference_protected((inst)->ip_set_list, \ lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \ - lockdep_is_held(&ip_set_ref_lock)) + lockdep_is_held(&ip_set_ref_lock) || \ + (inst)->is_deleted) #define ip_set(inst, id) \ - ip_set_dereference((inst)->ip_set_list)[id] + ip_set_dereference(inst)[id] #define ip_set_ref_netlink(inst,id) \ rcu_dereference_raw((inst)->ip_set_list)[id] #define ip_set_dereference_nfnl(p) \ @@ -1133,7 +1134,7 @@ static int ip_set_create(struct sk_buff *skb, const struct nfnl_info *info, if (!list) goto cleanup; /* nfnl mutex is held, both lists are valid */ - tmp = ip_set_dereference(inst->ip_set_list); + tmp = ip_set_dereference(inst); memcpy(list, tmp, sizeof(struct ip_set *) * inst->ip_set_max); rcu_assign_pointer(inst->ip_set_list, list); /* Make sure all current packets have passed through */ @@ -1172,23 +1173,50 @@ ip_set_setname_policy[IPSET_ATTR_CMD_MAX + 1] = { .len = IPSET_MAXNAMELEN - 1 }, }; +/* In order to return quickly when destroying a single set, it is split + * into two stages: + * - Cancel garbage collector + * - Destroy the set itself via call_rcu() + */ + static void -ip_set_destroy_set(struct ip_set *set) +ip_set_destroy_set_rcu(struct rcu_head *head) { - pr_debug("set: %s\n", set->name); + struct ip_set *set = container_of(head, struct ip_set, rcu); - /* Must call it without holding any lock */ set->variant->destroy(set); module_put(set->type->me); kfree(set); } static void -ip_set_destroy_set_rcu(struct rcu_head *head) +_destroy_all_sets(struct ip_set_net *inst) { - struct ip_set *set = container_of(head, struct ip_set, rcu); + struct ip_set *set; + ip_set_id_t i; + bool need_wait = false; - ip_set_destroy_set(set); + /* First cancel gc's: set:list sets are flushed as well */ + for (i = 0; i < inst->ip_set_max; i++) { + set = ip_set(inst, i); + if (set) { + set->variant->cancel_gc(set); + if (set->type->features & IPSET_TYPE_NAME) + need_wait = true; + } + } + /* Must wait for flush to be really finished */ + if (need_wait) + rcu_barrier(); + for (i = 0; i < inst->ip_set_max; i++) { + set = ip_set(inst, i); + if (set) { + ip_set(inst, i) = NULL; + set->variant->destroy(set); + module_put(set->type->me); + kfree(set); + } + } } static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, @@ -1202,11 +1230,10 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, if (unlikely(protocol_min_failed(attr))) return -IPSET_ERR_PROTOCOL; - /* Commands are serialized and references are * protected by the ip_set_ref_lock. * External systems (i.e. xt_set) must call - * ip_set_put|get_nfnl_* functions, that way we + * ip_set_nfnl_get_* functions, that way we * can safely check references here. * * list:set timer can only decrement the reference @@ -1214,8 +1241,6 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, * without holding the lock. */ if (!attr[IPSET_ATTR_SETNAME]) { - /* Must wait for flush to be really finished in list:set */ - rcu_barrier(); read_lock_bh(&ip_set_ref_lock); for (i = 0; i < inst->ip_set_max; i++) { s = ip_set(inst, i); @@ -1226,15 +1251,7 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, } inst->is_destroyed = true; read_unlock_bh(&ip_set_ref_lock); - for (i = 0; i < inst->ip_set_max; i++) { - s = ip_set(inst, i); - if (s) { - ip_set(inst, i) = NULL; - /* Must cancel garbage collectors */ - s->variant->cancel_gc(s); - ip_set_destroy_set(s); - } - } + _destroy_all_sets(inst); /* Modified by ip_set_destroy() only, which is serialized */ inst->is_destroyed = false; } else { @@ -1255,12 +1272,12 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, features = s->type->features; ip_set(inst, i) = NULL; read_unlock_bh(&ip_set_ref_lock); + /* Must cancel garbage collectors */ + s->variant->cancel_gc(s); if (features & IPSET_TYPE_NAME) { /* Must wait for flush to be really finished */ rcu_barrier(); } - /* Must cancel garbage collectors */ - s->variant->cancel_gc(s); call_rcu(&s->rcu, ip_set_destroy_set_rcu); } return 0; @@ -2365,30 +2382,25 @@ ip_set_net_init(struct net *net) } static void __net_exit -ip_set_net_exit(struct net *net) +ip_set_net_pre_exit(struct net *net) { struct ip_set_net *inst = ip_set_pernet(net); - struct ip_set *set = NULL; - ip_set_id_t i; - inst->is_deleted = true; /* flag for ip_set_nfnl_put */ +} - nfnl_lock(NFNL_SUBSYS_IPSET); - for (i = 0; i < inst->ip_set_max; i++) { - set = ip_set(inst, i); - if (set) { - ip_set(inst, i) = NULL; - set->variant->cancel_gc(set); - ip_set_destroy_set(set); - } - } - nfnl_unlock(NFNL_SUBSYS_IPSET); +static void __net_exit +ip_set_net_exit(struct net *net) +{ + struct ip_set_net *inst = ip_set_pernet(net); + + _destroy_all_sets(inst); kvfree(rcu_dereference_protected(inst->ip_set_list, 1)); } static struct pernet_operations ip_set_net_ops = { .init = ip_set_net_init, + .pre_exit = ip_set_net_pre_exit, .exit = ip_set_net_exit, .id = &ip_set_net_id, .size = sizeof(struct ip_set_net), diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 54e2a1dd7f5f..bfae7066936b 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -79,7 +79,7 @@ list_set_kadd(struct ip_set *set, const struct sk_buff *skb, struct set_elem *e; int ret; - list_for_each_entry(e, &map->members, list) { + list_for_each_entry_rcu(e, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; @@ -99,7 +99,7 @@ list_set_kdel(struct ip_set *set, const struct sk_buff *skb, struct set_elem *e; int ret; - list_for_each_entry(e, &map->members, list) { + list_for_each_entry_rcu(e, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; @@ -188,9 +188,10 @@ list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct list_set *map = set->data; struct set_adt_elem *d = value; struct set_elem *e, *next, *prev = NULL; - int ret; + int ret = 0; - list_for_each_entry(e, &map->members, list) { + rcu_read_lock(); + list_for_each_entry_rcu(e, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; @@ -201,6 +202,7 @@ list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext, if (d->before == 0) { ret = 1; + goto out; } else if (d->before > 0) { next = list_next_entry(e, list); ret = !list_is_last(&e->list, &map->members) && @@ -208,9 +210,11 @@ list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext, } else { ret = prev && prev->id == d->refid; } - return ret; + goto out; } - return 0; +out: + rcu_read_unlock(); + return ret; } static void @@ -239,7 +243,7 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext, /* Find where to add the new entry */ n = prev = next = NULL; - list_for_each_entry(e, &map->members, list) { + list_for_each_entry_rcu(e, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; @@ -316,9 +320,9 @@ list_set_udel(struct ip_set *set, void *value, const struct ip_set_ext *ext, { struct list_set *map = set->data; struct set_adt_elem *d = value; - struct set_elem *e, *next, *prev = NULL; + struct set_elem *e, *n, *next, *prev = NULL; - list_for_each_entry(e, &map->members, list) { + list_for_each_entry_safe(e, n, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; @@ -424,14 +428,8 @@ static void list_set_destroy(struct ip_set *set) { struct list_set *map = set->data; - struct set_elem *e, *n; - list_for_each_entry_safe(e, n, &map->members, list) { - list_del(&e->list); - ip_set_put_byindex(map->net, e->id); - ip_set_ext_destroy(set, e); - kfree(e); - } + WARN_ON_ONCE(!list_empty(&map->members)); kfree(map); set->data = NULL; diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 74112e9c5dab..6c40bdf8b05a 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -22,9 +22,6 @@ #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_timestamp.h> -#ifdef CONFIG_LWTUNNEL -#include <net/netfilter/nf_hooks_lwtunnel.h> -#endif #include <linux/rculist_nulls.h> static bool enable_hooks __read_mostly; @@ -612,9 +609,6 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_GRE, NF_SYSCTL_CT_PROTO_TIMEOUT_GRE_STREAM, #endif -#ifdef CONFIG_LWTUNNEL - NF_SYSCTL_CT_LWTUNNEL, -#endif NF_SYSCTL_CT_LAST_SYSCTL, }; @@ -946,15 +940,6 @@ static struct ctl_table nf_ct_sysctl_table[] = { .proc_handler = proc_dointvec_jiffies, }, #endif -#ifdef CONFIG_LWTUNNEL - [NF_SYSCTL_CT_LWTUNNEL] = { - .procname = "nf_hooks_lwtunnel", - .data = NULL, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = nf_hooks_lwtunnel_sysctl_handler, - }, -#endif }; static struct ctl_table nf_ct_netfilter_table[] = { diff --git a/net/netfilter/nf_hooks_lwtunnel.c b/net/netfilter/nf_hooks_lwtunnel.c index 00e89ffd78f6..d8ebebc9775d 100644 --- a/net/netfilter/nf_hooks_lwtunnel.c +++ b/net/netfilter/nf_hooks_lwtunnel.c @@ -3,6 +3,9 @@ #include <linux/sysctl.h> #include <net/lwtunnel.h> #include <net/netfilter/nf_hooks_lwtunnel.h> +#include <linux/netfilter.h> + +#include "nf_internals.h" static inline int nf_hooks_lwtunnel_get(void) { @@ -50,4 +53,71 @@ int nf_hooks_lwtunnel_sysctl_handler(struct ctl_table *table, int write, return ret; } EXPORT_SYMBOL_GPL(nf_hooks_lwtunnel_sysctl_handler); + +static struct ctl_table nf_lwtunnel_sysctl_table[] = { + { + .procname = "nf_hooks_lwtunnel", + .data = NULL, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = nf_hooks_lwtunnel_sysctl_handler, + }, +}; + +static int __net_init nf_lwtunnel_net_init(struct net *net) +{ + struct ctl_table_header *hdr; + struct ctl_table *table; + + table = nf_lwtunnel_sysctl_table; + if (!net_eq(net, &init_net)) { + table = kmemdup(nf_lwtunnel_sysctl_table, + sizeof(nf_lwtunnel_sysctl_table), + GFP_KERNEL); + if (!table) + goto err_alloc; + } + + hdr = register_net_sysctl_sz(net, "net/netfilter", table, + ARRAY_SIZE(nf_lwtunnel_sysctl_table)); + if (!hdr) + goto err_reg; + + net->nf.nf_lwtnl_dir_header = hdr; + + return 0; +err_reg: + if (!net_eq(net, &init_net)) + kfree(table); +err_alloc: + return -ENOMEM; +} + +static void __net_exit nf_lwtunnel_net_exit(struct net *net) +{ + const struct ctl_table *table; + + table = net->nf.nf_lwtnl_dir_header->ctl_table_arg; + unregister_net_sysctl_table(net->nf.nf_lwtnl_dir_header); + if (!net_eq(net, &init_net)) + kfree(table); +} + +static struct pernet_operations nf_lwtunnel_net_ops = { + .init = nf_lwtunnel_net_init, + .exit = nf_lwtunnel_net_exit, +}; + +int __init netfilter_lwtunnel_init(void) +{ + return register_pernet_subsys(&nf_lwtunnel_net_ops); +} + +void netfilter_lwtunnel_fini(void) +{ + unregister_pernet_subsys(&nf_lwtunnel_net_ops); +} +#else +int __init netfilter_lwtunnel_init(void) { return 0; } +void netfilter_lwtunnel_fini(void) {} #endif /* CONFIG_SYSCTL */ diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h index 832ae64179f0..25403023060b 100644 --- a/net/netfilter/nf_internals.h +++ b/net/netfilter/nf_internals.h @@ -29,6 +29,12 @@ void nf_queue_nf_hook_drop(struct net *net); /* nf_log.c */ int __init netfilter_log_init(void); +#ifdef CONFIG_LWTUNNEL +/* nf_hooks_lwtunnel.c */ +int __init netfilter_lwtunnel_init(void); +void netfilter_lwtunnel_fini(void); +#endif + /* core.c */ void nf_hook_entries_delete_raw(struct nf_hook_entries __rcu **pp, const struct nf_hook_ops *reg); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index be3b4c90d2ed..e8dcf41d360d 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5740,8 +5740,7 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && nft_data_dump(skb, NFTA_SET_ELEM_DATA, nft_set_ext_data(ext), - set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE, - set->dlen) < 0) + nft_set_datatype(set), set->dlen) < 0) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS) && @@ -11073,6 +11072,9 @@ static int nft_validate_register_store(const struct nft_ctx *ctx, return 0; default: + if (type != NFT_DATA_VALUE) + return -EINVAL; + if (reg < NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE) return -EINVAL; if (len == 0) @@ -11081,8 +11083,6 @@ static int nft_validate_register_store(const struct nft_ctx *ctx, sizeof_field(struct nft_regs, data)) return -ERANGE; - if (data != NULL && type != NFT_DATA_VALUE) - return -EINVAL; return 0; } } diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index a83637e3f455..580c55268f65 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -317,7 +317,7 @@ void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, net_get_random_once(&trace_key, sizeof(trace_key)); info->skbid = (u32)siphash_3u32(hash32_ptr(skb), - skb_get_hash(skb), + skb_get_hash_net(nft_net(pkt), skb), skb->skb_iif, &trace_key); } diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index 92d47e469204..868d68302d22 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -51,7 +51,8 @@ static void nft_symhash_eval(const struct nft_expr *expr, struct sk_buff *skb = pkt->skb; u32 h; - h = reciprocal_scale(__skb_get_hash_symmetric(skb), priv->modulus); + h = reciprocal_scale(__skb_get_hash_symmetric_net(nft_net(pkt), skb), + priv->modulus); regs->data[priv->dreg] = h + priv->offset; } diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index b314ca728a29..f3080fa1b226 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -132,7 +132,8 @@ static int nft_lookup_init(const struct nft_ctx *ctx, return -EINVAL; err = nft_parse_register_store(ctx, tb[NFTA_LOOKUP_DREG], - &priv->dreg, NULL, set->dtype, + &priv->dreg, NULL, + nft_set_datatype(set), set->dlen); if (err < 0) return err; diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index ba0d3683a45d..9139ce38ea7b 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -839,6 +839,9 @@ static int nft_meta_inner_init(const struct nft_ctx *ctx, struct nft_meta *priv = nft_expr_priv(expr); unsigned int len; + if (!tb[NFTA_META_KEY] || !tb[NFTA_META_DREG]) + return -EINVAL; + priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); switch (priv->key) { case NFT_META_PROTOCOL: diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 0c43d748e23a..50429cbd42da 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -650,6 +650,10 @@ static int nft_payload_inner_init(const struct nft_ctx *ctx, struct nft_payload *priv = nft_expr_priv(expr); u32 base; + if (!tb[NFTA_PAYLOAD_BASE] || !tb[NFTA_PAYLOAD_OFFSET] || + !tb[NFTA_PAYLOAD_LEN] || !tb[NFTA_PAYLOAD_DREG]) + return -EINVAL; + base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE])); switch (base) { case NFT_PAYLOAD_TUN_HEADER: diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c index 4e7c968cde2d..5e3ca068f04e 100644 --- a/net/netrom/nr_timer.c +++ b/net/netrom/nr_timer.c @@ -121,7 +121,8 @@ static void nr_heartbeat_expiry(struct timer_list *t) is accepted() it isn't 'dead' so doesn't get removed. */ if (sock_flag(sk, SOCK_DESTROY) || (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) { - sock_hold(sk); + if (sk->sk_state == TCP_LISTEN) + sock_hold(sk); bh_unlock_sock(sk); nr_destroy_socket(sk); goto out; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 2928c142a2dd..3b980bf2770b 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -168,8 +168,13 @@ static u32 ovs_ct_get_mark(const struct nf_conn *ct) static void ovs_ct_get_labels(const struct nf_conn *ct, struct ovs_key_ct_labels *labels) { - struct nf_conn_labels *cl = ct ? nf_ct_labels_find(ct) : NULL; + struct nf_conn_labels *cl = NULL; + if (ct) { + if (ct->master && !nf_ct_is_confirmed(ct)) + ct = ct->master; + cl = nf_ct_labels_find(ct); + } if (cl) memcpy(labels, cl->bits, OVS_CT_LABELS_LEN); else diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index fce390887591..42d29b8a84fc 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2121,7 +2121,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { enum skb_drop_reason drop_reason = SKB_CONSUMED; - struct sock *sk; + struct sock *sk = NULL; struct sockaddr_ll *sll; struct packet_sock *po; u8 *skb_head = skb->data; @@ -2226,7 +2226,7 @@ drop_n_restore: skb->len = skb_len; } drop: - kfree_skb_reason(skb, drop_reason); + sk_skb_reason_drop(sk, skb, drop_reason); return 0; } @@ -2234,7 +2234,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { enum skb_drop_reason drop_reason = SKB_CONSUMED; - struct sock *sk; + struct sock *sk = NULL; struct packet_sock *po; struct sockaddr_ll *sll; union tpacket_uhdr h; @@ -2494,7 +2494,7 @@ drop_n_restore: skb->len = skb_len; } drop: - kfree_skb_reason(skb, drop_reason); + sk_skb_reason_drop(sk, skb, drop_reason); return 0; drop_n_account: @@ -2503,7 +2503,7 @@ drop_n_account: drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; sk->sk_data_ready(sk); - kfree_skb_reason(copy_skb, drop_reason); + sk_skb_reason_drop(sk, copy_skb, drop_reason); goto drop_n_restore; } diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index 654a3cc0d347..3de9350cbf30 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -132,8 +132,8 @@ static int service_announce_new(struct sockaddr_qrtr *dest, return kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); } -static int service_announce_del(struct sockaddr_qrtr *dest, - struct qrtr_server *srv) +static void service_announce_del(struct sockaddr_qrtr *dest, + struct qrtr_server *srv) { struct qrtr_ctrl_pkt pkt; struct msghdr msg = { }; @@ -157,10 +157,10 @@ static int service_announce_del(struct sockaddr_qrtr *dest, msg.msg_namelen = sizeof(*dest); ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); - if (ret < 0) + if (ret < 0 && ret != -ENODEV) pr_err("failed to announce del service\n"); - return ret; + return; } static void lookup_notify(struct sockaddr_qrtr *to, struct qrtr_server *srv, @@ -188,7 +188,7 @@ static void lookup_notify(struct sockaddr_qrtr *to, struct qrtr_server *srv, msg.msg_namelen = sizeof(*to); ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); - if (ret < 0) + if (ret < 0 && ret != -ENODEV) pr_err("failed to send lookup notification\n"); } @@ -207,6 +207,9 @@ static int announce_servers(struct sockaddr_qrtr *sq) xa_for_each(&node->servers, index, srv) { ret = service_announce_new(sq, srv); if (ret < 0) { + if (ret == -ENODEV) + continue; + pr_err("failed to announce new service\n"); return ret; } @@ -369,7 +372,7 @@ static int ctrl_cmd_bye(struct sockaddr_qrtr *from) msg.msg_namelen = sizeof(sq); ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); - if (ret < 0) { + if (ret < 0 && ret != -ENODEV) { pr_err("failed to send bye cmd\n"); return ret; } @@ -443,7 +446,7 @@ static int ctrl_cmd_del_client(struct sockaddr_qrtr *from, msg.msg_namelen = sizeof(sq); ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); - if (ret < 0) { + if (ret < 0 && ret != -ENODEV) { pr_err("failed to send del client cmd\n"); return ret; } diff --git a/net/rds/tcp.c b/net/rds/tcp.c index d8111ac83bb6..3dc6956f66f8 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -719,9 +719,7 @@ static int __init rds_tcp_init(void) { int ret; - rds_tcp_conn_slab = kmem_cache_create("rds_tcp_connection", - sizeof(struct rds_tcp_connection), - 0, 0, NULL); + rds_tcp_conn_slab = KMEM_CACHE(rds_tcp_connection, 0); if (!rds_tcp_conn_slab) { ret = -ENOMEM; goto out; diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c index c00f04a1a534..7997a19d1da3 100644 --- a/net/rds/tcp_recv.c +++ b/net/rds/tcp_recv.c @@ -337,9 +337,7 @@ out: int rds_tcp_recv_init(void) { - rds_tcp_incoming_slab = kmem_cache_create("rds_tcp_incoming", - sizeof(struct rds_tcp_incoming), - 0, 0, NULL); + rds_tcp_incoming_slab = KMEM_CACHE(rds_tcp_incoming, 0); if (!rds_tcp_incoming_slab) return -ENOMEM; return 0; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 7458b3154426..2714c4ed928e 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -830,7 +830,6 @@ int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, u32 max; if (*index) { -again: rcu_read_lock(); p = idr_find(&idrinfo->action_idr, *index); @@ -839,7 +838,7 @@ again: * index but did not assign the pointer yet. */ rcu_read_unlock(); - goto again; + return -EAGAIN; } if (!p) { diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index baac083fd8f1..2a96d9c1db65 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -41,21 +41,26 @@ static struct workqueue_struct *act_ct_wq; static struct rhashtable zones_ht; static DEFINE_MUTEX(zones_mutex); +struct zones_ht_key { + struct net *net; + u16 zone; +}; + struct tcf_ct_flow_table { struct rhash_head node; /* In zones tables */ struct rcu_work rwork; struct nf_flowtable nf_ft; refcount_t ref; - u16 zone; + struct zones_ht_key key; bool dying; }; static const struct rhashtable_params zones_params = { .head_offset = offsetof(struct tcf_ct_flow_table, node), - .key_offset = offsetof(struct tcf_ct_flow_table, zone), - .key_len = sizeof_field(struct tcf_ct_flow_table, zone), + .key_offset = offsetof(struct tcf_ct_flow_table, key), + .key_len = sizeof_field(struct tcf_ct_flow_table, key), .automatic_shrinking = true, }; @@ -316,11 +321,12 @@ static struct nf_flowtable_type flowtable_ct = { static int tcf_ct_flow_table_get(struct net *net, struct tcf_ct_params *params) { + struct zones_ht_key key = { .net = net, .zone = params->zone }; struct tcf_ct_flow_table *ct_ft; int err = -ENOMEM; mutex_lock(&zones_mutex); - ct_ft = rhashtable_lookup_fast(&zones_ht, ¶ms->zone, zones_params); + ct_ft = rhashtable_lookup_fast(&zones_ht, &key, zones_params); if (ct_ft && refcount_inc_not_zero(&ct_ft->ref)) goto out_unlock; @@ -329,7 +335,7 @@ static int tcf_ct_flow_table_get(struct net *net, struct tcf_ct_params *params) goto err_alloc; refcount_set(&ct_ft->ref, 1); - ct_ft->zone = params->zone; + ct_ft->key = key; err = rhashtable_insert_fast(&zones_ht, &ct_ft->node, zones_params); if (err) goto err_insert; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 1417f1991452..2af24547a82c 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -677,6 +677,7 @@ struct Qdisc noop_qdisc = { .qlen = 0, .lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.skb_bad_txq.lock), }, + .owner = -1, }; EXPORT_SYMBOL(noop_qdisc); diff --git a/net/smc/Makefile b/net/smc/Makefile index 2c510d543058..60f1c87d5212 100644 --- a/net/smc/Makefile +++ b/net/smc/Makefile @@ -4,6 +4,6 @@ obj-$(CONFIG_SMC) += smc.o obj-$(CONFIG_SMC_DIAG) += smc_diag.o smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o smc_stats.o -smc-y += smc_tracepoint.o +smc-y += smc_tracepoint.o smc_inet.o smc-$(CONFIG_SYSCTL) += smc_sysctl.o smc-$(CONFIG_SMC_LO) += smc_loopback.o diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index c5f98c6b2561..73a875573e7a 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -54,6 +54,7 @@ #include "smc_tracepoint.h" #include "smc_sysctl.h" #include "smc_loopback.h" +#include "smc_inet.h" static DEFINE_MUTEX(smc_server_lgr_pending); /* serialize link group * creation on server @@ -170,15 +171,15 @@ static bool smc_hs_congested(const struct sock *sk) return false; } -static struct smc_hashinfo smc_v4_hashinfo = { +struct smc_hashinfo smc_v4_hashinfo = { .lock = __RW_LOCK_UNLOCKED(smc_v4_hashinfo.lock), }; -static struct smc_hashinfo smc_v6_hashinfo = { +struct smc_hashinfo smc_v6_hashinfo = { .lock = __RW_LOCK_UNLOCKED(smc_v6_hashinfo.lock), }; -static int smc_hash_sk(struct sock *sk) +int smc_hash_sk(struct sock *sk) { struct smc_hashinfo *h = sk->sk_prot->h.smc_hash; struct hlist_head *head; @@ -193,7 +194,7 @@ static int smc_hash_sk(struct sock *sk) return 0; } -static void smc_unhash_sk(struct sock *sk) +void smc_unhash_sk(struct sock *sk) { struct smc_hashinfo *h = sk->sk_prot->h.smc_hash; @@ -207,7 +208,7 @@ static void smc_unhash_sk(struct sock *sk) * work which we didn't do because of user hold the sock_lock in the * BH context */ -static void smc_release_cb(struct sock *sk) +void smc_release_cb(struct sock *sk) { struct smc_sock *smc = smc_sk(sk); @@ -307,7 +308,7 @@ static int __smc_release(struct smc_sock *smc) return rc; } -static int smc_release(struct socket *sock) +int smc_release(struct socket *sock) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -361,25 +362,15 @@ static void smc_destruct(struct sock *sk) return; } -static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, - int protocol) +void smc_sk_init(struct net *net, struct sock *sk, int protocol) { - struct smc_sock *smc; - struct proto *prot; - struct sock *sk; - - prot = (protocol == SMCPROTO_SMC6) ? &smc_proto6 : &smc_proto; - sk = sk_alloc(net, PF_SMC, GFP_KERNEL, prot, 0); - if (!sk) - return NULL; + struct smc_sock *smc = smc_sk(sk); - sock_init_data(sock, sk); /* sets sk_refcnt to 1 */ sk->sk_state = SMC_INIT; sk->sk_destruct = smc_destruct; sk->sk_protocol = protocol; WRITE_ONCE(sk->sk_sndbuf, 2 * READ_ONCE(net->smc.sysctl_wmem)); WRITE_ONCE(sk->sk_rcvbuf, 2 * READ_ONCE(net->smc.sysctl_rmem)); - smc = smc_sk(sk); INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work); INIT_WORK(&smc->connect_work, smc_connect_work); INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work); @@ -389,12 +380,30 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, sk->sk_prot->hash(sk); mutex_init(&smc->clcsock_release_lock); smc_init_saved_callbacks(smc); + smc->limit_smc_hs = net->smc.limit_smc_hs; + smc->use_fallback = false; /* assume rdma capability first */ + smc->fallback_rsn = 0; +} + +static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, + int protocol) +{ + struct proto *prot; + struct sock *sk; + + prot = (protocol == SMCPROTO_SMC6) ? &smc_proto6 : &smc_proto; + sk = sk_alloc(net, PF_SMC, GFP_KERNEL, prot, 0); + if (!sk) + return NULL; + + sock_init_data(sock, sk); /* sets sk_refcnt to 1 */ + smc_sk_init(net, sk, protocol); return sk; } -static int smc_bind(struct socket *sock, struct sockaddr *uaddr, - int addr_len) +int smc_bind(struct socket *sock, struct sockaddr *uaddr, + int addr_len) { struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; struct sock *sk = sock->sk; @@ -1623,8 +1632,8 @@ out: release_sock(&smc->sk); } -static int smc_connect(struct socket *sock, struct sockaddr *addr, - int alen, int flags) +int smc_connect(struct socket *sock, struct sockaddr *addr, + int alen, int flags) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -2605,7 +2614,7 @@ out: read_unlock_bh(&listen_clcsock->sk_callback_lock); } -static int smc_listen(struct socket *sock, int backlog) +int smc_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -2670,8 +2679,8 @@ out: return rc; } -static int smc_accept(struct socket *sock, struct socket *new_sock, - struct proto_accept_arg *arg) +int smc_accept(struct socket *sock, struct socket *new_sock, + struct proto_accept_arg *arg) { struct sock *sk = sock->sk, *nsk; DECLARE_WAITQUEUE(wait, current); @@ -2740,8 +2749,8 @@ out: return rc; } -static int smc_getname(struct socket *sock, struct sockaddr *addr, - int peer) +int smc_getname(struct socket *sock, struct sockaddr *addr, + int peer) { struct smc_sock *smc; @@ -2754,7 +2763,7 @@ static int smc_getname(struct socket *sock, struct sockaddr *addr, return smc->clcsock->ops->getname(smc->clcsock, addr, peer); } -static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) +int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -2792,8 +2801,8 @@ out: return rc; } -static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, - int flags) +int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -2842,8 +2851,8 @@ static __poll_t smc_accept_poll(struct sock *parent) return mask; } -static __poll_t smc_poll(struct file *file, struct socket *sock, - poll_table *wait) +__poll_t smc_poll(struct file *file, struct socket *sock, + poll_table *wait) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -2895,7 +2904,7 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, return mask; } -static int smc_shutdown(struct socket *sock, int how) +int smc_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; bool do_shutdown = true; @@ -3035,8 +3044,8 @@ static int __smc_setsockopt(struct socket *sock, int level, int optname, return rc; } -static int smc_setsockopt(struct socket *sock, int level, int optname, - sockptr_t optval, unsigned int optlen) +int smc_setsockopt(struct socket *sock, int level, int optname, + sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -3122,8 +3131,8 @@ out: return rc; } -static int smc_getsockopt(struct socket *sock, int level, int optname, - char __user *optval, int __user *optlen) +int smc_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) { struct smc_sock *smc; int rc; @@ -3148,8 +3157,8 @@ static int smc_getsockopt(struct socket *sock, int level, int optname, return rc; } -static int smc_ioctl(struct socket *sock, unsigned int cmd, - unsigned long arg) +int smc_ioctl(struct socket *sock, unsigned int cmd, + unsigned long arg) { union smc_host_cursor cons, urg; struct smc_connection *conn; @@ -3235,9 +3244,9 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd, * Note that subsequent recv() calls have to wait till all splice() processing * completed. */ -static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, - struct pipe_inode_info *pipe, size_t len, - unsigned int flags) +ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -3303,6 +3312,31 @@ static const struct proto_ops smc_sock_ops = { .splice_read = smc_splice_read, }; +int smc_create_clcsk(struct net *net, struct sock *sk, int family) +{ + struct smc_sock *smc = smc_sk(sk); + int rc; + + rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, + &smc->clcsock); + if (rc) { + sk_common_release(sk); + return rc; + } + + /* smc_clcsock_release() does not wait smc->clcsock->sk's + * destruction; its sk_state might not be TCP_CLOSE after + * smc->sk is close()d, and TCP timers can be fired later, + * which need net ref. + */ + sk = smc->clcsock->sk; + __netns_tracker_free(net, &sk->ns_tracker, false); + sk->sk_net_refcnt = 1; + get_net_track(net, &sk->ns_tracker, GFP_KERNEL); + sock_inuse_add(net, 1); + return 0; +} + static int __smc_create(struct net *net, struct socket *sock, int protocol, int kern, struct socket *clcsock) { @@ -3328,35 +3362,12 @@ static int __smc_create(struct net *net, struct socket *sock, int protocol, /* create internal TCP socket for CLC handshake and fallback */ smc = smc_sk(sk); - smc->use_fallback = false; /* assume rdma capability first */ - smc->fallback_rsn = 0; - - /* default behavior from limit_smc_hs in every net namespace */ - smc->limit_smc_hs = net->smc.limit_smc_hs; rc = 0; - if (!clcsock) { - rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, - &smc->clcsock); - if (rc) { - sk_common_release(sk); - goto out; - } - - /* smc_clcsock_release() does not wait smc->clcsock->sk's - * destruction; its sk_state might not be TCP_CLOSE after - * smc->sk is close()d, and TCP timers can be fired later, - * which need net ref. - */ - sk = smc->clcsock->sk; - __netns_tracker_free(net, &sk->ns_tracker, false); - sk->sk_net_refcnt = 1; - get_net_track(net, &sk->ns_tracker, GFP_KERNEL); - sock_inuse_add(net, 1); - } else { + if (clcsock) smc->clcsock = clcsock; - } - + else + rc = smc_create_clcsk(net, sk, family); out: return rc; } @@ -3565,10 +3576,15 @@ static int __init smc_init(void) pr_err("%s: tcp_ulp_register fails with %d\n", __func__, rc); goto out_lo; } - + rc = smc_inet_init(); + if (rc) { + pr_err("%s: smc_inet_init fails with %d\n", __func__, rc); + goto out_ulp; + } static_branch_enable(&tcp_have_smc); return 0; - +out_ulp: + tcp_unregister_ulp(&smc_ulp_ops); out_lo: smc_loopback_exit(); out_ib: @@ -3605,6 +3621,7 @@ out_pernet_subsys: static void __exit smc_exit(void) { static_branch_disable(&tcp_have_smc); + smc_inet_exit(); tcp_unregister_ulp(&smc_ulp_ops); sock_unregister(PF_SMC); smc_core_exit(); @@ -3632,4 +3649,9 @@ MODULE_DESCRIPTION("smc socket address family"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_SMC); MODULE_ALIAS_TCP_ULP("smc"); +/* 256 for IPPROTO_SMC and 1 for SOCK_STREAM */ +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 256, 1); +#if IS_ENABLED(CONFIG_IPV6) +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 256, 1); +#endif /* CONFIG_IPV6 */ MODULE_ALIAS_GENL_FAMILY(SMC_GENL_FAMILY_NAME); diff --git a/net/smc/smc.h b/net/smc/smc.h index 18c8b7870198..34b781e463c4 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -34,6 +34,44 @@ extern struct proto smc_proto; extern struct proto smc_proto6; +extern struct smc_hashinfo smc_v4_hashinfo; +extern struct smc_hashinfo smc_v6_hashinfo; + +int smc_hash_sk(struct sock *sk); +void smc_unhash_sk(struct sock *sk); +void smc_release_cb(struct sock *sk); + +int smc_release(struct socket *sock); +int smc_bind(struct socket *sock, struct sockaddr *uaddr, + int addr_len); +int smc_connect(struct socket *sock, struct sockaddr *addr, + int alen, int flags); +int smc_accept(struct socket *sock, struct socket *new_sock, + struct proto_accept_arg *arg); +int smc_getname(struct socket *sock, struct sockaddr *addr, + int peer); +__poll_t smc_poll(struct file *file, struct socket *sock, + poll_table *wait); +int smc_ioctl(struct socket *sock, unsigned int cmd, + unsigned long arg); +int smc_listen(struct socket *sock, int backlog); +int smc_shutdown(struct socket *sock, int how); +int smc_setsockopt(struct socket *sock, int level, int optname, + sockptr_t optval, unsigned int optlen); +int smc_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen); +int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len); +int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags); +ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags); + +/* smc sock initialization */ +void smc_sk_init(struct net *net, struct sock *sk, int protocol); +/* clcsock initialization */ +int smc_create_clcsk(struct net *net, struct sock *sk, int family); + #ifdef ATOMIC64_INIT #define KERNEL_HAS_ATOMIC64 #endif diff --git a/net/smc/smc_inet.c b/net/smc/smc_inet.c new file mode 100644 index 000000000000..bece346dd8e9 --- /dev/null +++ b/net/smc/smc_inet.c @@ -0,0 +1,159 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * Definitions for the IPPROTO_SMC (socket related) + * + * Copyright IBM Corp. 2016, 2018 + * Copyright (c) 2024, Alibaba Inc. + * + * Author: D. Wythe <[email protected]> + */ + +#include <net/protocol.h> +#include <net/sock.h> + +#include "smc_inet.h" +#include "smc.h" + +static int smc_inet_init_sock(struct sock *sk); + +static struct proto smc_inet_prot = { + .name = "INET_SMC", + .owner = THIS_MODULE, + .init = smc_inet_init_sock, + .hash = smc_hash_sk, + .unhash = smc_unhash_sk, + .release_cb = smc_release_cb, + .obj_size = sizeof(struct smc_sock), + .h.smc_hash = &smc_v4_hashinfo, + .slab_flags = SLAB_TYPESAFE_BY_RCU, +}; + +static const struct proto_ops smc_inet_stream_ops = { + .family = PF_INET, + .owner = THIS_MODULE, + .release = smc_release, + .bind = smc_bind, + .connect = smc_connect, + .socketpair = sock_no_socketpair, + .accept = smc_accept, + .getname = smc_getname, + .poll = smc_poll, + .ioctl = smc_ioctl, + .listen = smc_listen, + .shutdown = smc_shutdown, + .setsockopt = smc_setsockopt, + .getsockopt = smc_getsockopt, + .sendmsg = smc_sendmsg, + .recvmsg = smc_recvmsg, + .mmap = sock_no_mmap, + .splice_read = smc_splice_read, +}; + +static struct inet_protosw smc_inet_protosw = { + .type = SOCK_STREAM, + .protocol = IPPROTO_SMC, + .prot = &smc_inet_prot, + .ops = &smc_inet_stream_ops, + .flags = INET_PROTOSW_ICSK, +}; + +#if IS_ENABLED(CONFIG_IPV6) +static struct proto smc_inet6_prot = { + .name = "INET6_SMC", + .owner = THIS_MODULE, + .init = smc_inet_init_sock, + .hash = smc_hash_sk, + .unhash = smc_unhash_sk, + .release_cb = smc_release_cb, + .obj_size = sizeof(struct smc_sock), + .h.smc_hash = &smc_v6_hashinfo, + .slab_flags = SLAB_TYPESAFE_BY_RCU, +}; + +static const struct proto_ops smc_inet6_stream_ops = { + .family = PF_INET6, + .owner = THIS_MODULE, + .release = smc_release, + .bind = smc_bind, + .connect = smc_connect, + .socketpair = sock_no_socketpair, + .accept = smc_accept, + .getname = smc_getname, + .poll = smc_poll, + .ioctl = smc_ioctl, + .listen = smc_listen, + .shutdown = smc_shutdown, + .setsockopt = smc_setsockopt, + .getsockopt = smc_getsockopt, + .sendmsg = smc_sendmsg, + .recvmsg = smc_recvmsg, + .mmap = sock_no_mmap, + .splice_read = smc_splice_read, +}; + +static struct inet_protosw smc_inet6_protosw = { + .type = SOCK_STREAM, + .protocol = IPPROTO_SMC, + .prot = &smc_inet6_prot, + .ops = &smc_inet6_stream_ops, + .flags = INET_PROTOSW_ICSK, +}; +#endif /* CONFIG_IPV6 */ + +static int smc_inet_init_sock(struct sock *sk) +{ + struct net *net = sock_net(sk); + + /* init common smc sock */ + smc_sk_init(net, sk, IPPROTO_SMC); + /* create clcsock */ + return smc_create_clcsk(net, sk, sk->sk_family); +} + +int __init smc_inet_init(void) +{ + int rc; + + rc = proto_register(&smc_inet_prot, 1); + if (rc) { + pr_err("%s: proto_register smc_inet_prot fails with %d\n", + __func__, rc); + return rc; + } + /* no return value */ + inet_register_protosw(&smc_inet_protosw); + +#if IS_ENABLED(CONFIG_IPV6) + rc = proto_register(&smc_inet6_prot, 1); + if (rc) { + pr_err("%s: proto_register smc_inet6_prot fails with %d\n", + __func__, rc); + goto out_inet6_prot; + } + rc = inet6_register_protosw(&smc_inet6_protosw); + if (rc) { + pr_err("%s: inet6_register_protosw smc_inet6_protosw fails with %d\n", + __func__, rc); + goto out_inet6_protosw; + } + return rc; +out_inet6_protosw: + proto_unregister(&smc_inet6_prot); +out_inet6_prot: + inet_unregister_protosw(&smc_inet_protosw); + proto_unregister(&smc_inet_prot); +#endif /* CONFIG_IPV6 */ + return rc; +} + +void smc_inet_exit(void) +{ +#if IS_ENABLED(CONFIG_IPV6) + inet6_unregister_protosw(&smc_inet6_protosw); + proto_unregister(&smc_inet6_prot); +#endif /* CONFIG_IPV6 */ + inet_unregister_protosw(&smc_inet_protosw); + proto_unregister(&smc_inet_prot); +} diff --git a/net/smc/smc_inet.h b/net/smc/smc_inet.h new file mode 100644 index 000000000000..a489c8a2b8ef --- /dev/null +++ b/net/smc/smc_inet.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * Definitions for the IPPROTO_SMC (socket related) + + * Copyright IBM Corp. 2016 + * Copyright (c) 2024, Alibaba Inc. + * + * Author: D. Wythe <[email protected]> + */ +#ifndef __INET_SMC +#define __INET_SMC + +/* Initialize protocol registration on IPPROTO_SMC, + * @return 0 on success + */ +int smc_inet_init(void); + +void smc_inet_exit(void); + +#endif /* __INET_SMC */ diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index c7af0220f82f..369310909fc9 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1875,8 +1875,10 @@ gss_wrap_req_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, offset = (u8 *)p - (u8 *)snd_buf->head[0].iov_base; maj_stat = gss_wrap(ctx->gc_gss_ctx, offset, snd_buf, inpages); /* slack space should prevent this ever happening: */ - if (unlikely(snd_buf->len > snd_buf->buflen)) + if (unlikely(snd_buf->len > snd_buf->buflen)) { + status = -EIO; goto wrap_failed; + } /* We're assuming that when GSS_S_CONTEXT_EXPIRED, the encryption was * done anyway, so it's safe to put the request on the wire: */ if (maj_stat == GSS_S_CONTEXT_EXPIRED) diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 96ab50eda9c2..73a90ad873fb 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1069,7 +1069,7 @@ static int gss_read_proxy_verf(struct svc_rqst *rqstp, goto out_denied_free; pages = DIV_ROUND_UP(inlen, PAGE_SIZE); - in_token->pages = kcalloc(pages, sizeof(struct page *), GFP_KERNEL); + in_token->pages = kcalloc(pages + 1, sizeof(struct page *), GFP_KERNEL); if (!in_token->pages) goto out_denied_free; in_token->page_base = 0; diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index dd86d7f1e97e..49a3bea33f9d 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -1421,12 +1421,13 @@ static void *svc_pool_stats_start(struct seq_file *m, loff_t *pos) dprintk("svc_pool_stats_start, *pidx=%u\n", pidx); + if (!si->serv) + return NULL; + mutex_lock(si->mutex); if (!pidx) return SEQ_START_TOKEN; - if (!si->serv) - return NULL; return pidx > si->serv->sv_nrpools ? NULL : &si->serv->sv_pools[pidx - 1]; } @@ -1458,7 +1459,8 @@ static void svc_pool_stats_stop(struct seq_file *m, void *p) { struct svc_info *si = m->private; - mutex_unlock(si->mutex); + if (si->serv) + mutex_unlock(si->mutex); } static int svc_pool_stats_show(struct seq_file *m, void *p) diff --git a/net/tipc/node.c b/net/tipc/node.c index c1e890a82434..500320e5ca47 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -2105,6 +2105,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b) } else { n = tipc_node_find_by_id(net, ehdr->id); } + skb_dst_force(skb); tipc_crypto_rcv(net, (n) ? n->crypto_rx : NULL, &skb, b); if (!skb) return; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 3821f8945b1e..b0a4c6d08e0a 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -126,6 +126,81 @@ static spinlock_t bsd_socket_locks[UNIX_HASH_SIZE / 2]; * hash table is protected with spinlock. * each socket state is protected by separate spinlock. */ +#ifdef CONFIG_PROVE_LOCKING +#define cmp_ptr(l, r) (((l) > (r)) - ((l) < (r))) + +static int unix_table_lock_cmp_fn(const struct lockdep_map *a, + const struct lockdep_map *b) +{ + return cmp_ptr(a, b); +} + +static int unix_state_lock_cmp_fn(const struct lockdep_map *_a, + const struct lockdep_map *_b) +{ + const struct unix_sock *a, *b; + + a = container_of(_a, struct unix_sock, lock.dep_map); + b = container_of(_b, struct unix_sock, lock.dep_map); + + if (a->sk.sk_state == TCP_LISTEN) { + /* unix_stream_connect(): Before the 2nd unix_state_lock(), + * + * 1. a is TCP_LISTEN. + * 2. b is not a. + * 3. concurrent connect(b -> a) must fail. + * + * Except for 2. & 3., the b's state can be any possible + * value due to concurrent connect() or listen(). + * + * 2. is detected in debug_spin_lock_before(), and 3. cannot + * be expressed as lock_cmp_fn. + */ + switch (b->sk.sk_state) { + case TCP_CLOSE: + case TCP_ESTABLISHED: + case TCP_LISTEN: + return -1; + default: + /* Invalid case. */ + return 0; + } + } + + /* Should never happen. Just to be symmetric. */ + if (b->sk.sk_state == TCP_LISTEN) { + switch (b->sk.sk_state) { + case TCP_CLOSE: + case TCP_ESTABLISHED: + return 1; + default: + return 0; + } + } + + /* unix_state_double_lock(): ascending address order. */ + return cmp_ptr(a, b); +} + +static int unix_recvq_lock_cmp_fn(const struct lockdep_map *_a, + const struct lockdep_map *_b) +{ + const struct sock *a, *b; + + a = container_of(_a, struct sock, sk_receive_queue.lock.dep_map); + b = container_of(_b, struct sock, sk_receive_queue.lock.dep_map); + + /* unix_collect_skb(): listener -> embryo order. */ + if (a->sk_state == TCP_LISTEN && unix_sk(b)->listener == a) + return -1; + + /* Should never happen. Just to be symmetric. */ + if (b->sk_state == TCP_LISTEN && unix_sk(a)->listener == b) + return 1; + + return 0; +} +#endif static unsigned int unix_unbound_hash(struct sock *sk) { @@ -168,7 +243,7 @@ static void unix_table_double_lock(struct net *net, swap(hash1, hash2); spin_lock(&net->unx.table.locks[hash1]); - spin_lock_nested(&net->unx.table.locks[hash2], SINGLE_DEPTH_NESTING); + spin_lock(&net->unx.table.locks[hash2]); } static void unix_table_double_unlock(struct net *net, @@ -676,14 +751,19 @@ static void unix_release_sock(struct sock *sk, int embrion) static void init_peercred(struct sock *sk) { + sk->sk_peer_pid = get_pid(task_tgid(current)); + sk->sk_peer_cred = get_current_cred(); +} + +static void update_peercred(struct sock *sk) +{ const struct cred *old_cred; struct pid *old_pid; spin_lock(&sk->sk_peer_lock); old_pid = sk->sk_peer_pid; old_cred = sk->sk_peer_cred; - sk->sk_peer_pid = get_pid(task_tgid(current)); - sk->sk_peer_cred = get_current_cred(); + init_peercred(sk); spin_unlock(&sk->sk_peer_lock); put_pid(old_pid); @@ -692,26 +772,12 @@ static void init_peercred(struct sock *sk) static void copy_peercred(struct sock *sk, struct sock *peersk) { - const struct cred *old_cred; - struct pid *old_pid; + lockdep_assert_held(&unix_sk(peersk)->lock); - if (sk < peersk) { - spin_lock(&sk->sk_peer_lock); - spin_lock_nested(&peersk->sk_peer_lock, SINGLE_DEPTH_NESTING); - } else { - spin_lock(&peersk->sk_peer_lock); - spin_lock_nested(&sk->sk_peer_lock, SINGLE_DEPTH_NESTING); - } - old_pid = sk->sk_peer_pid; - old_cred = sk->sk_peer_cred; - sk->sk_peer_pid = get_pid(peersk->sk_peer_pid); + spin_lock(&sk->sk_peer_lock); + sk->sk_peer_pid = get_pid(peersk->sk_peer_pid); sk->sk_peer_cred = get_cred(peersk->sk_peer_cred); - spin_unlock(&sk->sk_peer_lock); - spin_unlock(&peersk->sk_peer_lock); - - put_pid(old_pid); - put_cred(old_cred); } static int unix_listen(struct socket *sock, int backlog) @@ -735,7 +801,7 @@ static int unix_listen(struct socket *sock, int backlog) WRITE_ONCE(sk->sk_state, TCP_LISTEN); /* set credentials so connect can copy them */ - init_peercred(sk); + update_peercred(sk); err = 0; out_unlock: @@ -972,12 +1038,15 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, sk->sk_write_space = unix_write_space; sk->sk_max_ack_backlog = READ_ONCE(net->unx.sysctl_max_dgram_qlen); sk->sk_destruct = unix_sock_destructor; + lock_set_cmp_fn(&sk->sk_receive_queue.lock, unix_recvq_lock_cmp_fn, NULL); + u = unix_sk(sk); u->listener = NULL; u->vertex = NULL; u->path.dentry = NULL; u->path.mnt = NULL; spin_lock_init(&u->lock); + lock_set_cmp_fn(&u->lock, unix_state_lock_cmp_fn, NULL); mutex_init(&u->iolock); /* single task reading lock */ mutex_init(&u->bindlock); /* single task binding lock */ init_waitqueue_head(&u->peer_wait); @@ -1326,11 +1395,12 @@ static void unix_state_double_lock(struct sock *sk1, struct sock *sk2) unix_state_lock(sk1); return; } + if (sk1 > sk2) swap(sk1, sk2); unix_state_lock(sk1); - unix_state_lock_nested(sk2, U_LOCK_SECOND); + unix_state_lock(sk2); } static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2) @@ -1473,6 +1543,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, struct unix_sock *u = unix_sk(sk), *newu, *otheru; struct net *net = sock_net(sk); struct sk_buff *skb = NULL; + unsigned char state; long timeo; int err; @@ -1523,7 +1594,6 @@ restart: goto out; } - /* Latch state of peer */ unix_state_lock(other); /* Apparently VFS overslept socket death. Retry. */ @@ -1553,37 +1623,21 @@ restart: goto restart; } - /* Latch our state. - - It is tricky place. We need to grab our state lock and cannot - drop lock on peer. It is dangerous because deadlock is - possible. Connect to self case and simultaneous - attempt to connect are eliminated by checking socket - state. other is TCP_LISTEN, if sk is TCP_LISTEN we - check this before attempt to grab lock. - - Well, and we have to recheck the state after socket locked. + /* self connect and simultaneous connect are eliminated + * by rejecting TCP_LISTEN socket to avoid deadlock. */ - switch (READ_ONCE(sk->sk_state)) { - case TCP_CLOSE: - /* This is ok... continue with connect */ - break; - case TCP_ESTABLISHED: - /* Socket is already connected */ - err = -EISCONN; - goto out_unlock; - default: - err = -EINVAL; + state = READ_ONCE(sk->sk_state); + if (unlikely(state != TCP_CLOSE)) { + err = state == TCP_ESTABLISHED ? -EISCONN : -EINVAL; goto out_unlock; } - unix_state_lock_nested(sk, U_LOCK_SECOND); + unix_state_lock(sk); - if (sk->sk_state != TCP_CLOSE) { + if (unlikely(sk->sk_state != TCP_CLOSE)) { + err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EINVAL; unix_state_unlock(sk); - unix_state_unlock(other); - sock_put(other); - goto restart; + goto out_unlock; } err = security_unix_stream_connect(sk, other, newsk); @@ -2613,10 +2667,24 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, { struct unix_sock *u = unix_sk(sk); - if (!unix_skb_len(skb) && !(flags & MSG_PEEK)) { - skb_unlink(skb, &sk->sk_receive_queue); - consume_skb(skb); - skb = NULL; + if (!unix_skb_len(skb)) { + struct sk_buff *unlinked_skb = NULL; + + spin_lock(&sk->sk_receive_queue.lock); + + if (copied && (!u->oob_skb || skb == u->oob_skb)) { + skb = NULL; + } else if (flags & MSG_PEEK) { + skb = skb_peek_next(skb, &sk->sk_receive_queue); + } else { + unlinked_skb = skb; + skb = skb_peek_next(skb, &sk->sk_receive_queue); + __skb_unlink(unlinked_skb, &sk->sk_receive_queue); + } + + spin_unlock(&sk->sk_receive_queue.lock); + + consume_skb(unlinked_skb); } else { struct sk_buff *unlinked_skb = NULL; @@ -2625,18 +2693,18 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, if (skb == u->oob_skb) { if (copied) { skb = NULL; - } else if (sock_flag(sk, SOCK_URGINLINE)) { - if (!(flags & MSG_PEEK)) { + } else if (!(flags & MSG_PEEK)) { + if (sock_flag(sk, SOCK_URGINLINE)) { WRITE_ONCE(u->oob_skb, NULL); consume_skb(skb); + } else { + __skb_unlink(skb, &sk->sk_receive_queue); + WRITE_ONCE(u->oob_skb, NULL); + unlinked_skb = skb; + skb = skb_peek(&sk->sk_receive_queue); } - } else if (flags & MSG_PEEK) { - skb = NULL; - } else { - __skb_unlink(skb, &sk->sk_receive_queue); - WRITE_ONCE(u->oob_skb, NULL); - unlinked_skb = skb; - skb = skb_peek(&sk->sk_receive_queue); + } else if (!sock_flag(sk, SOCK_URGINLINE)) { + skb = skb_peek_next(skb, &sk->sk_receive_queue); } } @@ -3076,12 +3144,23 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) #if IS_ENABLED(CONFIG_AF_UNIX_OOB) case SIOCATMARK: { + struct unix_sock *u = unix_sk(sk); struct sk_buff *skb; int answ = 0; + mutex_lock(&u->iolock); + skb = skb_peek(&sk->sk_receive_queue); - if (skb && skb == READ_ONCE(unix_sk(sk)->oob_skb)) - answ = 1; + if (skb) { + struct sk_buff *oob_skb = READ_ONCE(u->oob_skb); + + if (skb == oob_skb || + (!oob_skb && !unix_skb_len(skb))) + answ = 1; + } + + mutex_unlock(&u->iolock); + err = put_user(answ, (int __user *)arg); } break; @@ -3578,6 +3657,7 @@ static int __net_init unix_net_init(struct net *net) for (i = 0; i < UNIX_HASH_SIZE; i++) { spin_lock_init(&net->unx.table.locks[i]); + lock_set_cmp_fn(&net->unx.table.locks[i], unix_table_lock_cmp_fn, NULL); INIT_HLIST_HEAD(&net->unx.table.buckets[i]); } diff --git a/net/unix/diag.c b/net/unix/diag.c index 937edf4afed4..9138af8b465e 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -47,9 +47,7 @@ static int sk_diag_dump_peer(struct sock *sk, struct sk_buff *nlskb) peer = unix_peer_get(sk); if (peer) { - unix_state_lock(peer); ino = sock_i_ino(peer); - unix_state_unlock(peer); sock_put(peer); return nla_put_u32(nlskb, UNIX_DIAG_PEER, ino); @@ -75,20 +73,9 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb) buf = nla_data(attr); i = 0; - skb_queue_walk(&sk->sk_receive_queue, skb) { - struct sock *req, *peer; - - req = skb->sk; - /* - * The state lock is outer for the same sk's - * queue lock. With the other's queue locked it's - * OK to lock the state. - */ - unix_state_lock_nested(req, U_LOCK_DIAG); - peer = unix_sk(req)->peer; - buf[i++] = (peer ? sock_i_ino(peer) : 0); - unix_state_unlock(req); - } + skb_queue_walk(&sk->sk_receive_queue, skb) + buf[i++] = sock_i_ino(unix_peer(skb->sk)); + spin_unlock(&sk->sk_receive_queue.lock); } @@ -180,22 +167,6 @@ out_nlmsg_trim: return -EMSGSIZE; } -static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req, - struct user_namespace *user_ns, - u32 portid, u32 seq, u32 flags) -{ - int sk_ino; - - unix_state_lock(sk); - sk_ino = sock_i_ino(sk); - unix_state_unlock(sk); - - if (!sk_ino) - return 0; - - return sk_diag_fill(sk, skb, req, user_ns, portid, seq, flags, sk_ino); -} - static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); @@ -213,14 +184,22 @@ static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) num = 0; spin_lock(&net->unx.table.locks[slot]); sk_for_each(sk, &net->unx.table.buckets[slot]) { + int sk_ino; + if (num < s_num) goto next; + if (!(req->udiag_states & (1 << READ_ONCE(sk->sk_state)))) goto next; - if (sk_diag_dump(sk, skb, req, sk_user_ns(skb->sk), + + sk_ino = sock_i_ino(sk); + if (!sk_ino) + goto next; + + if (sk_diag_fill(sk, skb, req, sk_user_ns(skb->sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - NLM_F_MULTI) < 0) { + NLM_F_MULTI, sk_ino) < 0) { spin_unlock(&net->unx.table.locks[slot]); goto done; } diff --git a/net/unix/garbage.c b/net/unix/garbage.c index dfe94a90ece4..eb8aa5171a68 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -337,11 +337,6 @@ static bool unix_vertex_dead(struct unix_vertex *vertex) return true; } -enum unix_recv_queue_lock_class { - U_RECVQ_LOCK_NORMAL, - U_RECVQ_LOCK_EMBRYO, -}; - static void unix_collect_queue(struct unix_sock *u, struct sk_buff_head *hitlist) { skb_queue_splice_init(&u->sk.sk_receive_queue, hitlist); @@ -375,8 +370,7 @@ static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist skb_queue_walk(queue, skb) { struct sk_buff_head *embryo_queue = &skb->sk->sk_receive_queue; - /* listener -> embryo order, the inversion never happens. */ - spin_lock_nested(&embryo_queue->lock, U_RECVQ_LOCK_EMBRYO); + spin_lock(&embryo_queue->lock); unix_collect_queue(unix_sk(skb->sk), hitlist); spin_unlock(&embryo_queue->lock); } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index fcac7dedcd61..19d81200a2a2 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -467,6 +467,10 @@ static const struct netlink_range_validation nl80211_punct_bitmap_range = { .max = 0xffff, }; +static const struct netlink_range_validation q_range = { + .max = INT_MAX, +}; + static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [0] = { .strict_start_type = NL80211_ATTR_HE_OBSS_PD }, [NL80211_ATTR_WIPHY] = { .type = NLA_U32 }, @@ -753,7 +757,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_TXQ_LIMIT] = { .type = NLA_U32 }, [NL80211_ATTR_TXQ_MEMORY_LIMIT] = { .type = NLA_U32 }, - [NL80211_ATTR_TXQ_QUANTUM] = { .type = NLA_U32 }, + [NL80211_ATTR_TXQ_QUANTUM] = NLA_POLICY_FULL_RANGE(NLA_U32, &q_range), [NL80211_ATTR_HE_CAPABILITY] = NLA_POLICY_VALIDATE_FN(NLA_BINARY, validate_he_capa, NL80211_HE_MAX_CAPABILITY_LEN), diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 88ce365764f5..d99319d82205 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -3453,10 +3453,14 @@ int cfg80211_wext_siwscan(struct net_device *dev, wiphy = &rdev->wiphy; /* Determine number of channels, needed to allocate creq */ - if (wreq && wreq->num_channels) + if (wreq && wreq->num_channels) { + /* Passed from userspace so should be checked */ + if (unlikely(wreq->num_channels > IW_MAX_FREQUENCIES)) + return -EINVAL; n_channels = wreq->num_channels; - else + } else { n_channels = ieee80211_get_num_supported_channels(wiphy); + } creq = kzalloc(sizeof(*creq) + sizeof(struct cfg80211_ssid) + n_channels * sizeof(void *), @@ -3530,8 +3534,10 @@ int cfg80211_wext_siwscan(struct net_device *dev, memcpy(creq->ssids[0].ssid, wreq->essid, wreq->essid_len); creq->ssids[0].ssid_len = wreq->essid_len; } - if (wreq->scan_type == IW_SCAN_TYPE_PASSIVE) + if (wreq->scan_type == IW_SCAN_TYPE_PASSIVE) { + creq->ssids = NULL; creq->n_ssids = 0; + } } for (i = 0; i < NUM_NL80211_BANDS; i++) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 7d1c0986f9bb..ed062e038389 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -35,8 +35,6 @@ #define TX_BATCH_SIZE 32 #define MAX_PER_SOCKET_BUDGET (TX_BATCH_SIZE) -static DEFINE_PER_CPU(struct list_head, xskmap_flush_list); - void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool) { if (pool->cached_need_wakeup & XDP_WAKEUP_RX) @@ -372,7 +370,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp) { - struct list_head *flush_list = this_cpu_ptr(&xskmap_flush_list); + struct list_head *flush_list = bpf_net_ctx_get_xskmap_flush_list(); int err; err = xsk_rcv(xs, xdp); @@ -387,7 +385,7 @@ int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp) void __xsk_map_flush(void) { - struct list_head *flush_list = this_cpu_ptr(&xskmap_flush_list); + struct list_head *flush_list = bpf_net_ctx_get_xskmap_flush_list(); struct xdp_sock *xs, *tmp; list_for_each_entry_safe(xs, tmp, flush_list, flush_node) { @@ -399,7 +397,7 @@ void __xsk_map_flush(void) #ifdef CONFIG_DEBUG_NET bool xsk_map_check_flush(void) { - if (list_empty(this_cpu_ptr(&xskmap_flush_list))) + if (list_empty(bpf_net_ctx_get_xskmap_flush_list())) return false; __xsk_map_flush(); return true; @@ -1772,7 +1770,7 @@ static struct pernet_operations xsk_net_ops = { static int __init xsk_init(void) { - int err, cpu; + int err; err = proto_register(&xsk_proto, 0 /* no slab */); if (err) @@ -1790,8 +1788,6 @@ static int __init xsk_init(void) if (err) goto out_pernet; - for_each_possible_cpu(cpu) - INIT_LIST_HEAD(&per_cpu(xskmap_flush_list, cpu)); return 0; out_pernet: diff --git a/rust/kernel/alloc/vec_ext.rs b/rust/kernel/alloc/vec_ext.rs index e9a81052728a..1297a4be32e8 100644 --- a/rust/kernel/alloc/vec_ext.rs +++ b/rust/kernel/alloc/vec_ext.rs @@ -4,7 +4,6 @@ use super::{AllocError, Flags}; use alloc::vec::Vec; -use core::ptr; /// Extensions to [`Vec`]. pub trait VecExt<T>: Sized { @@ -141,7 +140,11 @@ impl<T> VecExt<T> for Vec<T> { // `krealloc_aligned`. A `Vec<T>`'s `ptr` value is not guaranteed to be NULL and might be // dangling after being created with `Vec::new`. Instead, we can rely on `Vec<T>`'s capacity // to be zero if no memory has been allocated yet. - let ptr = if cap == 0 { ptr::null_mut() } else { old_ptr }; + let ptr = if cap == 0 { + core::ptr::null_mut() + } else { + old_ptr + }; // SAFETY: `ptr` is valid because it's either NULL or comes from a previous call to // `krealloc_aligned`. We also verified that the type is not a ZST. diff --git a/scripts/atomic/kerneldoc/sub_and_test b/scripts/atomic/kerneldoc/sub_and_test index d3760f7749d4..96615e50836b 100644 --- a/scripts/atomic/kerneldoc/sub_and_test +++ b/scripts/atomic/kerneldoc/sub_and_test @@ -1,7 +1,7 @@ cat <<EOF /** * ${class}${atomicname}() - atomic subtract and test if zero with ${desc_order} ordering - * @i: ${int} value to add + * @i: ${int} value to subtract * @v: pointer to ${atomic}_t * * Atomically updates @v to (@v - @i) with ${desc_order} ordering. diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index 387503daf0f7..85b53069ba7a 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -533,19 +533,6 @@ int conf_read(const char *name) */ if (sym->visible == no && !conf_unsaved) sym->flags &= ~SYMBOL_DEF_USER; - switch (sym->type) { - case S_STRING: - case S_INT: - case S_HEX: - /* Reset a string value if it's out of range */ - if (sym_string_within_range(sym, sym->def[S_DEF_USER].val)) - break; - sym->flags &= ~SYMBOL_VALID; - conf_unsaved++; - break; - default: - break; - } } } diff --git a/scripts/kconfig/expr.c b/scripts/kconfig/expr.c index 4d95fce5f9a7..fcc190b67b6f 100644 --- a/scripts/kconfig/expr.c +++ b/scripts/kconfig/expr.c @@ -397,35 +397,6 @@ static struct expr *expr_eliminate_yn(struct expr *e) } /* - * bool FOO!=n => FOO - */ -struct expr *expr_trans_bool(struct expr *e) -{ - if (!e) - return NULL; - switch (e->type) { - case E_AND: - case E_OR: - case E_NOT: - e->left.expr = expr_trans_bool(e->left.expr); - e->right.expr = expr_trans_bool(e->right.expr); - break; - case E_UNEQUAL: - // FOO!=n -> FOO - if (e->left.sym->type == S_TRISTATE) { - if (e->right.sym == &symbol_no) { - e->type = E_SYMBOL; - e->right.sym = NULL; - } - } - break; - default: - ; - } - return e; -} - -/* * e1 || e2 -> ? */ static struct expr *expr_join_or(struct expr *e1, struct expr *e2) diff --git a/scripts/kconfig/expr.h b/scripts/kconfig/expr.h index fa50fc45622e..7c0c242318bc 100644 --- a/scripts/kconfig/expr.h +++ b/scripts/kconfig/expr.h @@ -284,7 +284,6 @@ void expr_free(struct expr *e); void expr_eliminate_eq(struct expr **ep1, struct expr **ep2); int expr_eq(struct expr *e1, struct expr *e2); tristate expr_calc_value(struct expr *e); -struct expr *expr_trans_bool(struct expr *e); struct expr *expr_eliminate_dups(struct expr *e); struct expr *expr_transform(struct expr *e); int expr_contains_symbol(struct expr *dep, struct symbol *sym); diff --git a/scripts/kconfig/gconf.c b/scripts/kconfig/gconf.c index cc400ffe6615..e04dbafd3add 100644 --- a/scripts/kconfig/gconf.c +++ b/scripts/kconfig/gconf.c @@ -1422,7 +1422,6 @@ int main(int ac, char *av[]) conf_parse(name); fixup_rootmenu(&rootmenu); - conf_read(NULL); /* Load the interface and connect signals */ init_main_window(glade_file); @@ -1430,6 +1429,8 @@ int main(int ac, char *av[]) init_left_tree(); init_right_tree(); + conf_read(NULL); + switch (view_mode) { case SINGLE_VIEW: display_tree_part(); diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c index 53151c5a6028..eef9b63cdf11 100644 --- a/scripts/kconfig/menu.c +++ b/scripts/kconfig/menu.c @@ -398,8 +398,6 @@ static void _menu_finalize(struct menu *parent, bool inside_choice) dep = expr_transform(dep); dep = expr_alloc_and(expr_copy(basedep), dep); dep = expr_eliminate_dups(dep); - if (menu->sym && menu->sym->type != S_TRISTATE) - dep = expr_trans_bool(dep); prop->visible.expr = dep; /* diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 46ce5d04dbeb..518c70b8db50 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -193,7 +193,7 @@ kallsyms_step() mksysmap() { info NM ${2} - ${NM} -n "${1}" | "${srctree}/scripts/mksysmap" > "${2}" + ${NM} -n "${1}" | sed -f "${srctree}/scripts/mksysmap" > "${2}" } sorttable() diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 937294ff164f..f48d72d22dc2 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1647,10 +1647,11 @@ static void read_symbols(const char *modname) namespace = get_next_modinfo(&info, "import_ns", namespace); } + + if (extra_warn && !get_modinfo(&info, "description")) + warn("missing MODULE_DESCRIPTION() in %s\n", modname); } - if (extra_warn && !get_modinfo(&info, "description")) - warn("missing MODULE_DESCRIPTION() in %s\n", modname); for (sym = info.symtab_start; sym < info.symtab_stop; sym++) { symname = remove_dot(info.strtab + sym->st_name); diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening index effbf5982be1..2cff851ebfd7 100644 --- a/security/Kconfig.hardening +++ b/security/Kconfig.hardening @@ -255,21 +255,6 @@ config INIT_ON_FREE_DEFAULT_ON touching "cold" memory areas. Most cases see 3-5% impact. Some synthetic workloads have measured as high as 8%. -config INIT_MLOCKED_ON_FREE_DEFAULT_ON - bool "Enable mlocked memory zeroing on free" - depends on !KMSAN - help - This config has the effect of setting "init_mlocked_on_free=1" - on the kernel command line. If it is enabled, all mlocked process - memory is zeroed when freed. This restriction to mlocked memory - improves performance over "init_on_free" but can still be used to - protect confidential data like key material from content exposures - to other processes, as well as live forensics and cold boot attacks. - Any non-mlocked memory is not cleared before it is reassigned. This - configuration can be overwritten by setting "init_mlocked_on_free=0" - on the command line. The "init_on_free" boot option takes - precedence over "init_mlocked_on_free". - config CC_HAS_ZERO_CALL_USED_REGS def_bool $(cc-option,-fzero-call-used-regs=used-gpr) # https://github.com/ClangBuiltLinux/linux/issues/1766 diff --git a/security/apparmor/audit.c b/security/apparmor/audit.c index 45beb1c5f747..6b5181c668b5 100644 --- a/security/apparmor/audit.c +++ b/security/apparmor/audit.c @@ -217,7 +217,7 @@ void aa_audit_rule_free(void *vrule) } } -int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule) +int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule, gfp_t gfp) { struct aa_audit_rule *rule; @@ -230,14 +230,14 @@ int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule) return -EINVAL; } - rule = kzalloc(sizeof(struct aa_audit_rule), GFP_KERNEL); + rule = kzalloc(sizeof(struct aa_audit_rule), gfp); if (!rule) return -ENOMEM; /* Currently rules are treated as coming from the root ns */ rule->label = aa_label_parse(&root_ns->unconfined->label, rulestr, - GFP_KERNEL, true, false); + gfp, true, false); if (IS_ERR(rule->label)) { int err = PTR_ERR(rule->label); aa_audit_rule_free(rule); diff --git a/security/apparmor/include/audit.h b/security/apparmor/include/audit.h index acbb03b9bd25..0c8cc86b417b 100644 --- a/security/apparmor/include/audit.h +++ b/security/apparmor/include/audit.h @@ -200,7 +200,7 @@ static inline int complain_error(int error) } void aa_audit_rule_free(void *vrule); -int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule); +int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule, gfp_t gfp); int aa_audit_rule_known(struct audit_krule *rule); int aa_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule); diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index 3e568126cd48..c51e24d24d1e 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -546,7 +546,7 @@ static inline void ima_free_modsig(struct modsig *modsig) #else static inline int ima_filter_rule_init(u32 field, u32 op, char *rulestr, - void **lsmrule) + void **lsmrule, gfp_t gfp) { return -EINVAL; } diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index c0556907c2e6..09da8e639239 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -401,7 +401,8 @@ static void ima_free_rule(struct ima_rule_entry *entry) kfree(entry); } -static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry) +static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry, + gfp_t gfp) { struct ima_rule_entry *nentry; int i; @@ -410,7 +411,7 @@ static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry) * Immutable elements are copied over as pointers and data; only * lsm rules can change */ - nentry = kmemdup(entry, sizeof(*nentry), GFP_KERNEL); + nentry = kmemdup(entry, sizeof(*nentry), gfp); if (!nentry) return NULL; @@ -425,7 +426,8 @@ static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry) ima_filter_rule_init(nentry->lsm[i].type, Audit_equal, nentry->lsm[i].args_p, - &nentry->lsm[i].rule); + &nentry->lsm[i].rule, + gfp); if (!nentry->lsm[i].rule) pr_warn("rule for LSM \'%s\' is undefined\n", nentry->lsm[i].args_p); @@ -438,7 +440,7 @@ static int ima_lsm_update_rule(struct ima_rule_entry *entry) int i; struct ima_rule_entry *nentry; - nentry = ima_lsm_copy_rule(entry); + nentry = ima_lsm_copy_rule(entry, GFP_KERNEL); if (!nentry) return -ENOMEM; @@ -664,7 +666,7 @@ retry: } if (rc == -ESTALE && !rule_reinitialized) { - lsm_rule = ima_lsm_copy_rule(rule); + lsm_rule = ima_lsm_copy_rule(rule, GFP_ATOMIC); if (lsm_rule) { rule_reinitialized = true; goto retry; @@ -1140,7 +1142,8 @@ static int ima_lsm_rule_init(struct ima_rule_entry *entry, entry->lsm[lsm_rule].type = audit_type; result = ima_filter_rule_init(entry->lsm[lsm_rule].type, Audit_equal, entry->lsm[lsm_rule].args_p, - &entry->lsm[lsm_rule].rule); + &entry->lsm[lsm_rule].rule, + GFP_KERNEL); if (!entry->lsm[lsm_rule].rule) { pr_warn("rule for LSM \'%s\' is undefined\n", entry->lsm[lsm_rule].args_p); diff --git a/security/security.c b/security/security.c index e5da848c50b9..e5ca08789f74 100644 --- a/security/security.c +++ b/security/security.c @@ -5332,15 +5332,17 @@ void security_key_post_create_or_update(struct key *keyring, struct key *key, * @op: rule operator * @rulestr: rule context * @lsmrule: receive buffer for audit rule struct + * @gfp: GFP flag used for kmalloc * * Allocate and initialize an LSM audit rule structure. * * Return: Return 0 if @lsmrule has been successfully set, -EINVAL in case of * an invalid rule. */ -int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule) +int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule, + gfp_t gfp) { - return call_int_hook(audit_rule_init, field, op, rulestr, lsmrule); + return call_int_hook(audit_rule_init, field, op, rulestr, lsmrule, gfp); } /** diff --git a/security/selinux/include/audit.h b/security/selinux/include/audit.h index 52aca71210b4..29c7d4c86f6d 100644 --- a/security/selinux/include/audit.h +++ b/security/selinux/include/audit.h @@ -21,12 +21,14 @@ * @op: the operator the rule uses * @rulestr: the text "target" of the rule * @rule: pointer to the new rule structure returned via this + * @gfp: GFP flag used for kmalloc * * Returns 0 if successful, -errno if not. On success, the rule structure * will be allocated internally. The caller must free this structure with * selinux_audit_rule_free() after use. */ -int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **rule); +int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **rule, + gfp_t gfp); /** * selinux_audit_rule_free - free an selinux audit rule structure. diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index f20e1968b7f7..e33e55384b75 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -3507,7 +3507,8 @@ void selinux_audit_rule_free(void *vrule) } } -int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule) +int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule, + gfp_t gfp) { struct selinux_state *state = &selinux_state; struct selinux_policy *policy; @@ -3548,7 +3549,7 @@ int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule) return -EINVAL; } - tmprule = kzalloc(sizeof(struct selinux_audit_rule), GFP_KERNEL); + tmprule = kzalloc(sizeof(struct selinux_audit_rule), gfp); if (!tmprule) return -ENOMEM; context_init(&tmprule->au_ctxt); diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 70ba2841e181..f5cbec1e6a92 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -4693,11 +4693,13 @@ static int smack_post_notification(const struct cred *w_cred, * @op: required testing operator (=, !=, >, <, ...) * @rulestr: smack label to be audited * @vrule: pointer to save our own audit rule representation + * @gfp: type of the memory for the allocation * * Prepare to audit cases where (@field @op @rulestr) is true. * The label to be audited is created if necessay. */ -static int smack_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule) +static int smack_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule, + gfp_t gfp) { struct smack_known *skp; char **rule = (char **)vrule; diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c index b6684a074a59..39944a859ff6 100644 --- a/security/yama/yama_lsm.c +++ b/security/yama/yama_lsm.c @@ -111,6 +111,7 @@ static void report_access(const char *access, struct task_struct *target, /** * yama_relation_cleanup - remove invalid entries from the relation list + * @work: unused * */ static void yama_relation_cleanup(struct work_struct *work) diff --git a/sound/core/pcm_dmaengine.c b/sound/core/pcm_dmaengine.c index 12aa1cef11a1..cc5db93b9132 100644 --- a/sound/core/pcm_dmaengine.c +++ b/sound/core/pcm_dmaengine.c @@ -349,6 +349,16 @@ int snd_dmaengine_pcm_open_request_chan(struct snd_pcm_substream *substream, } EXPORT_SYMBOL_GPL(snd_dmaengine_pcm_open_request_chan); +int snd_dmaengine_pcm_sync_stop(struct snd_pcm_substream *substream) +{ + struct dmaengine_pcm_runtime_data *prtd = substream_to_prtd(substream); + + dmaengine_synchronize(prtd->dma_chan); + + return 0; +} +EXPORT_SYMBOL_GPL(snd_dmaengine_pcm_sync_stop); + /** * snd_dmaengine_pcm_close - Close a dmaengine based PCM substream * @substream: PCM substream @@ -358,6 +368,12 @@ EXPORT_SYMBOL_GPL(snd_dmaengine_pcm_open_request_chan); int snd_dmaengine_pcm_close(struct snd_pcm_substream *substream) { struct dmaengine_pcm_runtime_data *prtd = substream_to_prtd(substream); + struct dma_tx_state state; + enum dma_status status; + + status = dmaengine_tx_status(prtd->dma_chan, prtd->cookie, &state); + if (status == DMA_PAUSED) + dmaengine_terminate_async(prtd->dma_chan); dmaengine_synchronize(prtd->dma_chan); kfree(prtd); @@ -378,6 +394,12 @@ EXPORT_SYMBOL_GPL(snd_dmaengine_pcm_close); int snd_dmaengine_pcm_close_release_chan(struct snd_pcm_substream *substream) { struct dmaengine_pcm_runtime_data *prtd = substream_to_prtd(substream); + struct dma_tx_state state; + enum dma_status status; + + status = dmaengine_tx_status(prtd->dma_chan, prtd->cookie, &state); + if (status == DMA_PAUSED) + dmaengine_terminate_async(prtd->dma_chan); dmaengine_synchronize(prtd->dma_chan); dma_release_channel(prtd->dma_chan); diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 521ba56392a0..c152ccf32214 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -1775,6 +1775,8 @@ static int snd_pcm_pre_resume(struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_runtime *runtime = substream->runtime; + if (runtime->state != SNDRV_PCM_STATE_SUSPENDED) + return -EBADFD; if (!(runtime->info & SNDRV_PCM_INFO_RESUME)) return -ENOSYS; runtime->trigger_master = substream; diff --git a/sound/core/seq/seq_ump_convert.c b/sound/core/seq/seq_ump_convert.c index 171fb75267af..e90b27a135e6 100644 --- a/sound/core/seq/seq_ump_convert.c +++ b/sound/core/seq/seq_ump_convert.c @@ -791,7 +791,8 @@ static int paf_ev_to_ump_midi2(const struct snd_seq_event *event, /* set up the MIDI2 RPN/NRPN packet data from the parsed info */ static void fill_rpn(struct snd_seq_ump_midi2_bank *cc, - union snd_ump_midi2_msg *data) + union snd_ump_midi2_msg *data, + unsigned char channel) { if (cc->rpn_set) { data->rpn.status = UMP_MSG_STATUS_RPN; @@ -808,6 +809,7 @@ static void fill_rpn(struct snd_seq_ump_midi2_bank *cc, } data->rpn.data = upscale_14_to_32bit((cc->cc_data_msb << 7) | cc->cc_data_lsb); + data->rpn.channel = channel; cc->cc_data_msb = cc->cc_data_lsb = 0; } @@ -855,7 +857,7 @@ static int cc_ev_to_ump_midi2(const struct snd_seq_event *event, cc->cc_data_lsb = val; if (!(cc->rpn_set || cc->nrpn_set)) return 0; // skip - fill_rpn(cc, data); + fill_rpn(cc, data, channel); return 1; } @@ -957,7 +959,7 @@ static int ctrl14_ev_to_ump_midi2(const struct snd_seq_event *event, cc->cc_data_lsb = lsb; if (!(cc->rpn_set || cc->nrpn_set)) return 0; // skip - fill_rpn(cc, data); + fill_rpn(cc, data, channel); return 1; } @@ -1018,7 +1020,7 @@ static int system_2p_ev_to_ump_midi2(const struct snd_seq_event *event, union snd_ump_midi2_msg *data, unsigned char status) { - return system_1p_ev_to_ump_midi1(event, dest_port, + return system_2p_ev_to_ump_midi1(event, dest_port, (union snd_ump_midi1_msg *)data, status); } @@ -1075,6 +1077,8 @@ static const struct seq_ev_to_ump seq_ev_ump_encoders[] = { system_ev_to_ump_midi1, system_ev_to_ump_midi2 }, { SNDRV_SEQ_EVENT_SENSING, UMP_SYSTEM_STATUS_ACTIVE_SENSING, system_ev_to_ump_midi1, system_ev_to_ump_midi2 }, + { SNDRV_SEQ_EVENT_RESET, UMP_SYSTEM_STATUS_RESET, + system_ev_to_ump_midi1, system_ev_to_ump_midi2 }, }; static const struct seq_ev_to_ump *find_ump_encoder(int type) diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index 537863447358..478d2b50c571 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -18,7 +18,7 @@ static int dsp_driver; module_param(dsp_driver, int, 0444); -MODULE_PARM_DESC(dsp_driver, "Force the DSP driver for Intel DSP (0=auto, 1=legacy, 2=SST, 3=SOF)"); +MODULE_PARM_DESC(dsp_driver, "Force the DSP driver for Intel DSP (0=auto, 1=legacy, 2=SST, 3=SOF, 4=AVS)"); #define FLAG_SST BIT(0) #define FLAG_SOF BIT(1) diff --git a/sound/oss/dmasound/dmasound_core.c b/sound/oss/dmasound/dmasound_core.c index 164335d3c200..4b1baf4dd50e 100644 --- a/sound/oss/dmasound/dmasound_core.c +++ b/sound/oss/dmasound/dmasound_core.c @@ -204,6 +204,7 @@ module_param(numWriteBufs, int, 0); static unsigned int writeBufSize = DEFAULT_BUFF_SIZE ; /* in bytes */ module_param(writeBufSize, int, 0); +MODULE_DESCRIPTION("Atari/Amiga/Q40 core DMA sound driver"); MODULE_LICENSE("GPL"); static int sq_unit = -1; diff --git a/sound/pci/hda/Kconfig b/sound/pci/hda/Kconfig index 0da625533afc..a3cf0725fc43 100644 --- a/sound/pci/hda/Kconfig +++ b/sound/pci/hda/Kconfig @@ -162,6 +162,7 @@ config SND_HDA_SCODEC_CS35L56_I2C depends on ACPI || COMPILE_TEST depends on SND_SOC select FW_CS_DSP + imply SERIAL_MULTI_INSTANTIATE select SND_HDA_GENERIC select SND_SOC_CS35L56_SHARED select SND_HDA_SCODEC_CS35L56 @@ -178,6 +179,7 @@ config SND_HDA_SCODEC_CS35L56_SPI depends on ACPI || COMPILE_TEST depends on SND_SOC select FW_CS_DSP + imply SERIAL_MULTI_INSTANTIATE select SND_HDA_GENERIC select SND_SOC_CS35L56_SHARED select SND_HDA_SCODEC_CS35L56 diff --git a/sound/pci/hda/cs35l41_hda.c b/sound/pci/hda/cs35l41_hda.c index 6c49e5c6cd20..031703f010be 100644 --- a/sound/pci/hda/cs35l41_hda.c +++ b/sound/pci/hda/cs35l41_hda.c @@ -1495,7 +1495,7 @@ static void cs35l41_hda_unbind(struct device *dev, struct device *master, void * if (comps[cs35l41->index].dev == dev) { memset(&comps[cs35l41->index], 0, sizeof(*comps)); sleep_flags = lock_system_sleep(); - device_link_remove(&comps->codec->core.dev, cs35l41->dev); + device_link_remove(&cs35l41->codec->core.dev, cs35l41->dev); unlock_system_sleep(sleep_flags); } } @@ -2019,6 +2019,8 @@ void cs35l41_hda_remove(struct device *dev) { struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev); + component_del(cs35l41->dev, &cs35l41_hda_comp_ops); + pm_runtime_get_sync(cs35l41->dev); pm_runtime_dont_use_autosuspend(cs35l41->dev); pm_runtime_disable(cs35l41->dev); @@ -2026,8 +2028,6 @@ void cs35l41_hda_remove(struct device *dev) if (cs35l41->halo_initialized) cs35l41_remove_dsp(cs35l41); - component_del(cs35l41->dev, &cs35l41_hda_comp_ops); - acpi_dev_put(cs35l41->dacpi); pm_runtime_put_noidle(cs35l41->dev); diff --git a/sound/pci/hda/cs35l41_hda_property.c b/sound/pci/hda/cs35l41_hda_property.c index 6a7a6d486916..51998d1c72ff 100644 --- a/sound/pci/hda/cs35l41_hda_property.c +++ b/sound/pci/hda/cs35l41_hda_property.c @@ -128,6 +128,10 @@ static const struct cs35l41_config cs35l41_config_table[] = { { "17AA38B5", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 }, { "17AA38B6", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 }, { "17AA38B7", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 }, + { "17AA38C7", 4, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, CS35L41_LEFT, CS35L41_RIGHT }, 0, 2, -1, 1000, 4500, 24 }, + { "17AA38C8", 4, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, CS35L41_LEFT, CS35L41_RIGHT }, 0, 2, -1, 1000, 4500, 24 }, + { "17AA38F9", 2, EXTERNAL, { CS35L41_RIGHT, CS35L41_LEFT, 0, 0 }, 0, 2, -1, 0, 0, 0 }, + { "17AA38FA", 2, EXTERNAL, { CS35L41_RIGHT, CS35L41_LEFT, 0, 0 }, 0, 2, -1, 0, 0, 0 }, {} }; @@ -529,6 +533,10 @@ static const struct cs35l41_prop_model cs35l41_prop_model_table[] = { { "CSC3551", "17AA38B5", generic_dsd_config }, { "CSC3551", "17AA38B6", generic_dsd_config }, { "CSC3551", "17AA38B7", generic_dsd_config }, + { "CSC3551", "17AA38C7", generic_dsd_config }, + { "CSC3551", "17AA38C8", generic_dsd_config }, + { "CSC3551", "17AA38F9", generic_dsd_config }, + { "CSC3551", "17AA38FA", generic_dsd_config }, {} }; diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c index 11b0570ff56d..e134ede6c5aa 100644 --- a/sound/pci/hda/cs35l56_hda.c +++ b/sound/pci/hda/cs35l56_hda.c @@ -735,6 +735,8 @@ static void cs35l56_hda_unbind(struct device *dev, struct device *master, void * if (comps[cs35l56->index].dev == dev) memset(&comps[cs35l56->index], 0, sizeof(*comps)); + cs35l56->codec = NULL; + dev_dbg(cs35l56->base.dev, "Unbound\n"); } @@ -840,6 +842,9 @@ static int cs35l56_hda_system_resume(struct device *dev) cs35l56->suspended = false; + if (!cs35l56->codec) + return 0; + ret = cs35l56_is_fw_reload_needed(&cs35l56->base); dev_dbg(cs35l56->base.dev, "fw_reload_needed: %d\n", ret); if (ret > 0) { @@ -1072,12 +1077,12 @@ void cs35l56_hda_remove(struct device *dev) { struct cs35l56_hda *cs35l56 = dev_get_drvdata(dev); + component_del(cs35l56->base.dev, &cs35l56_hda_comp_ops); + pm_runtime_dont_use_autosuspend(cs35l56->base.dev); pm_runtime_get_sync(cs35l56->base.dev); pm_runtime_disable(cs35l56->base.dev); - component_del(cs35l56->base.dev, &cs35l56_hda_comp_ops); - cs_dsp_remove(&cs35l56->cs_dsp); kfree(cs35l56->system_name); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index aa76d1c88589..811e82474200 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -583,10 +583,14 @@ static void alc_shutup_pins(struct hda_codec *codec) switch (codec->core.vendor_id) { case 0x10ec0236: case 0x10ec0256: + case 0x10ec0257: case 0x19e58326: case 0x10ec0283: + case 0x10ec0285: case 0x10ec0286: + case 0x10ec0287: case 0x10ec0288: + case 0x10ec0295: case 0x10ec0298: alc_headset_mic_no_shutup(codec); break; @@ -7520,6 +7524,8 @@ enum { ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1, ALC287_FIXUP_LENOVO_THKPAD_WH_ALC1318, ALC256_FIXUP_CHROME_BOOK, + ALC287_FIXUP_LENOVO_14ARP8_LEGION_IAH7, + ALC287_FIXUP_LENOVO_SSID_17AA3820, }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -7559,6 +7565,21 @@ static void alc287_fixup_lenovo_14irp8_duetitl(struct hda_codec *codec, __snd_hda_apply_fixup(codec, id, action, 0); } +/* Similar to above the Lenovo Yoga Pro 7 14ARP8 PCI SSID matches the codec SSID of the + Legion Y9000X 2022 IAH7.*/ +static void alc287_fixup_lenovo_14arp8_legion_iah7(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + int id; + + if (codec->core.subsystem_id == 0x17aa386e) + id = ALC287_FIXUP_CS35L41_I2C_2; /* Legion Y9000X 2022 IAH7 */ + else + id = ALC285_FIXUP_SPEAKER2_TO_DAC1; /* Yoga Pro 7 14ARP8 */ + __snd_hda_apply_fixup(codec, id, action, 0); +} + /* Another hilarious PCI SSID conflict with Lenovo Legion Pro 7 16ARX8H (with * TAS2781 codec) and Legion 7i 16IAX7 (with CS35L41 codec); * we apply a corresponding fixup depending on the codec SSID instead @@ -7576,6 +7597,20 @@ static void alc287_fixup_lenovo_legion_7(struct hda_codec *codec, __snd_hda_apply_fixup(codec, id, action, 0); } +/* Yet more conflicting PCI SSID (17aa:3820) on two Lenovo models */ +static void alc287_fixup_lenovo_ssid_17aa3820(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + int id; + + if (codec->core.subsystem_id == 0x17aa3820) + id = ALC269_FIXUP_ASPIRE_HEADSET_MIC; /* IdeaPad 330-17IKB 81DM */ + else /* 0x17aa3802 */ + id = ALC287_FIXUP_YOGA7_14ITL_SPEAKERS; /* "Yoga Duet 7 13ITL6 */ + __snd_hda_apply_fixup(codec, id, action, 0); +} + static const struct hda_fixup alc269_fixups[] = { [ALC269_FIXUP_GPIO2] = { .type = HDA_FIXUP_FUNC, @@ -9658,6 +9693,10 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK, }, + [ALC287_FIXUP_LENOVO_14ARP8_LEGION_IAH7] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc287_fixup_lenovo_14arp8_legion_iah7, + }, [ALC287_FIXUP_YOGA9_14IMH9_BASS_SPK_PIN] = { .type = HDA_FIXUP_FUNC, .v.func = alc287_fixup_yoga9_14iap7_bass_spk_pin, @@ -9808,6 +9847,10 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC225_FIXUP_HEADSET_JACK }, + [ALC287_FIXUP_LENOVO_SSID_17AA3820] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc287_fixup_lenovo_ssid_17aa3820, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -10045,6 +10088,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8788, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x87b7, "HP Laptop 14-fq0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x87d3, "HP Laptop 15-gw0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x87e5, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87e7, "HP ProBook 450 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87f1, "HP ProBook 630 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), @@ -10194,6 +10238,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8c70, "HP EliteBook 835 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c71, "HP EliteBook 845 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c7b, "HP ProBook 445 G11", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8c7c, "HP ProBook 445 G11", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8c7d, "HP ProBook 465 G11", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8c7e, "HP ProBook 465 G11", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8c7f, "HP EliteBook 645 G11", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8c80, "HP EliteBook 645 G11", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8c81, "HP EliteBook 665 G11", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8c89, "HP ProBook 460 G11", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c8a, "HP EliteBook 630", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c8c, "HP EliteBook 660", ALC236_FIXUP_HP_GPIO_LED), @@ -10502,7 +10553,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3813, "Legion 7i 15IMHG05", ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940 / Yoga Duet 7", ALC298_FIXUP_LENOVO_C940_DUET7), SND_PCI_QUIRK(0x17aa, 0x3819, "Lenovo 13s Gen2 ITL", ALC287_FIXUP_13S_GEN2_SPEAKERS), - SND_PCI_QUIRK(0x17aa, 0x3820, "Yoga Duet 7 13ITL6", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), + SND_PCI_QUIRK(0x17aa, 0x3820, "IdeaPad 330 / Yoga Duet 7", ALC287_FIXUP_LENOVO_SSID_17AA3820), SND_PCI_QUIRK(0x17aa, 0x3824, "Legion Y9000X 2020", ALC285_FIXUP_LEGION_Y9000X_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3827, "Ideapad S740", ALC285_FIXUP_IDEAPAD_S740_COEF), SND_PCI_QUIRK(0x17aa, 0x3834, "Lenovo IdeaPad Slim 9i 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), @@ -10516,7 +10567,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3865, "Lenovo 13X", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3866, "Lenovo 13X", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3869, "Lenovo Yoga7 14IAL7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), - SND_PCI_QUIRK(0x17aa, 0x386e, "Legion Y9000X 2022 IAH7", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x17aa, 0x386e, "Legion Y9000X 2022 IAH7 / Yoga Pro 7 14ARP8", ALC287_FIXUP_LENOVO_14ARP8_LEGION_IAH7), SND_PCI_QUIRK(0x17aa, 0x386f, "Legion Pro 7/7i", ALC287_FIXUP_LENOVO_LEGION_7), SND_PCI_QUIRK(0x17aa, 0x3870, "Lenovo Yoga 7 14ARB7", ALC287_FIXUP_YOGA7_14ARB7_I2C), SND_PCI_QUIRK(0x17aa, 0x3877, "Lenovo Legion 7 Slim 16ARHA7", ALC287_FIXUP_CS35L41_I2C_2), @@ -10527,6 +10578,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3882, "Lenovo Yoga Pro 7 14APH8", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x3884, "Y780 YG DUAL", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x3886, "Y780 VECO DUAL", ALC287_FIXUP_TAS2781_I2C), + SND_PCI_QUIRK(0x17aa, 0x3891, "Lenovo Yoga Pro 7 14AHP9", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x38a7, "Y780P AMD YG dual", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38a8, "Y780P AMD VECO dual", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38a9, "Thinkbook 16P", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), @@ -10540,10 +10592,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x38be, "Yoga S980-14.5 proX YC Dual", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38bf, "Yoga S980-14.5 proX LX Dual", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38c3, "Y980 DUAL", ALC287_FIXUP_TAS2781_I2C), + SND_PCI_QUIRK(0x17aa, 0x38c7, "Thinkbook 13x Gen 4", ALC287_FIXUP_CS35L41_I2C_4), + SND_PCI_QUIRK(0x17aa, 0x38c8, "Thinkbook 13x Gen 4", ALC287_FIXUP_CS35L41_I2C_4), SND_PCI_QUIRK(0x17aa, 0x38cb, "Y790 YG DUAL", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38cd, "Y790 VECO DUAL", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38d2, "Lenovo Yoga 9 14IMH9", ALC287_FIXUP_YOGA9_14IMH9_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x38d7, "Lenovo Yoga 9 14IMH9", ALC287_FIXUP_YOGA9_14IMH9_BASS_SPK_PIN), + SND_PCI_QUIRK(0x17aa, 0x38f9, "Thinkbook 16P Gen5", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x17aa, 0x38fa, "Thinkbook 16P Gen5", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo B50-70", ALC269_FIXUP_DMIC_THINKPAD_ACPI), @@ -10581,6 +10637,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */ SND_PCI_QUIRK(0x1c06, 0x2013, "Lemote A1802", ALC269_FIXUP_LEMOTE_A1802), SND_PCI_QUIRK(0x1c06, 0x2015, "Lemote A190X", ALC269_FIXUP_LEMOTE_A190X), + SND_PCI_QUIRK(0x1c6c, 0x122a, "Positivo N14AP7", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1c6c, 0x1251, "Positivo N14KP6-TG", ALC288_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1d05, 0x1132, "TongFang PHxTxX1", ALC256_FIXUP_SET_COEF_DEFAULTS), SND_PCI_QUIRK(0x1d05, 0x1096, "TongFang GMxMRxx", ALC269_FIXUP_NO_SHUTUP), @@ -10605,7 +10662,6 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10), SND_PCI_QUIRK(0x8086, 0x3038, "Intel NUC 13", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0xf111, 0x0001, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), - SND_PCI_QUIRK(0xf111, 0x0005, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x0006, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), #if 0 diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c index 75f7674c66ee..fdee6592c502 100644 --- a/sound/pci/hda/tas2781_hda_i2c.c +++ b/sound/pci/hda/tas2781_hda_i2c.c @@ -777,11 +777,11 @@ static void tas2781_hda_remove(struct device *dev) { struct tas2781_hda *tas_hda = dev_get_drvdata(dev); + component_del(tas_hda->dev, &tas2781_hda_comp_ops); + pm_runtime_get_sync(tas_hda->dev); pm_runtime_disable(tas_hda->dev); - component_del(tas_hda->dev, &tas2781_hda_comp_ops); - pm_runtime_put_noidle(tas_hda->dev); tasdevice_remove(tas_hda->priv); diff --git a/sound/soc/amd/acp/acp-i2s.c b/sound/soc/amd/acp/acp-i2s.c index 60cbc881be6e..ef12f97ddc69 100644 --- a/sound/soc/amd/acp/acp-i2s.c +++ b/sound/soc/amd/acp/acp-i2s.c @@ -588,20 +588,12 @@ static int acp_i2s_probe(struct snd_soc_dai *dai) { struct device *dev = dai->component->dev; struct acp_dev_data *adata = dev_get_drvdata(dev); - struct acp_resource *rsrc = adata->rsrc; - unsigned int val; if (!adata->acp_base) { dev_err(dev, "I2S base is NULL\n"); return -EINVAL; } - val = readl(adata->acp_base + rsrc->i2s_pin_cfg_offset); - if (val != rsrc->i2s_mode) { - dev_err(dev, "I2S Mode not supported val %x\n", val); - return -EINVAL; - } - return 0; } diff --git a/sound/soc/amd/acp/acp-pci.c b/sound/soc/amd/acp/acp-pci.c index ad320b29e87d..777b5a78d8a9 100644 --- a/sound/soc/amd/acp/acp-pci.c +++ b/sound/soc/amd/acp/acp-pci.c @@ -100,6 +100,7 @@ static int acp_pci_probe(struct pci_dev *pci, const struct pci_device_id *pci_id ret = -EINVAL; goto release_regions; } + chip->flag = flag; dmic_dev = platform_device_register_data(dev, "dmic-codec", PLATFORM_DEVID_NONE, NULL, 0); if (IS_ERR(dmic_dev)) { dev_err(dev, "failed to create DMIC device\n"); @@ -139,7 +140,6 @@ static int acp_pci_probe(struct pci_dev *pci, const struct pci_device_id *pci_id } } - chip->flag = flag; memset(&pdevinfo, 0, sizeof(pdevinfo)); pdevinfo.name = chip->name; @@ -199,10 +199,12 @@ static int __maybe_unused snd_acp_resume(struct device *dev) ret = acp_init(chip); if (ret) dev_err(dev, "ACP init failed\n"); - child = chip->chip_pdev->dev; - adata = dev_get_drvdata(&child); - if (adata) - acp_enable_interrupts(adata); + if (chip->chip_pdev) { + child = chip->chip_pdev->dev; + adata = dev_get_drvdata(&child); + if (adata) + acp_enable_interrupts(adata); + } return ret; } diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 1760b5d42460..4e3a8ce690a4 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -283,6 +283,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "M5402RA"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "M5602RA"), + } + }, { .driver_data = &acp6x_card, .matches = { diff --git a/sound/soc/atmel/atmel-classd.c b/sound/soc/atmel/atmel-classd.c index 6aed1ee443b4..ba314b279919 100644 --- a/sound/soc/atmel/atmel-classd.c +++ b/sound/soc/atmel/atmel-classd.c @@ -473,19 +473,22 @@ static int atmel_classd_asoc_card_init(struct device *dev, if (!dai_link) return -ENOMEM; - comp = devm_kzalloc(dev, sizeof(*comp), GFP_KERNEL); + comp = devm_kzalloc(dev, 2 * sizeof(*comp), GFP_KERNEL); if (!comp) return -ENOMEM; - dai_link->cpus = comp; + dai_link->cpus = &comp[0]; dai_link->codecs = &snd_soc_dummy_dlc; + dai_link->platforms = &comp[1]; dai_link->num_cpus = 1; dai_link->num_codecs = 1; + dai_link->num_platforms = 1; dai_link->name = "CLASSD"; dai_link->stream_name = "CLASSD PCM"; dai_link->cpus->dai_name = dev_name(dev); + dai_link->platforms->name = dev_name(dev); card->dai_link = dai_link; card->num_links = 1; diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c index 8af89a263594..30497152e02a 100644 --- a/sound/soc/codecs/cs35l56-shared.c +++ b/sound/soc/codecs/cs35l56-shared.c @@ -215,6 +215,10 @@ static const struct reg_sequence cs35l56_asp1_defaults[] = { REG_SEQ0(CS35L56_ASP1_FRAME_CONTROL5, 0x00020100), REG_SEQ0(CS35L56_ASP1_DATA_CONTROL1, 0x00000018), REG_SEQ0(CS35L56_ASP1_DATA_CONTROL5, 0x00000018), + REG_SEQ0(CS35L56_ASP1TX1_INPUT, 0x00000000), + REG_SEQ0(CS35L56_ASP1TX2_INPUT, 0x00000000), + REG_SEQ0(CS35L56_ASP1TX3_INPUT, 0x00000000), + REG_SEQ0(CS35L56_ASP1TX4_INPUT, 0x00000000), }; /* diff --git a/sound/soc/codecs/cs42l43-jack.c b/sound/soc/codecs/cs42l43-jack.c index 901b9dbcf585..d9ab003e166b 100644 --- a/sound/soc/codecs/cs42l43-jack.c +++ b/sound/soc/codecs/cs42l43-jack.c @@ -121,7 +121,7 @@ int cs42l43_set_jack(struct snd_soc_component *component, priv->buttons[3] = 735; } - ret = cs42l43_find_index(priv, "cirrus,detect-us", 1000, &priv->detect_us, + ret = cs42l43_find_index(priv, "cirrus,detect-us", 50000, &priv->detect_us, cs42l43_accdet_us, ARRAY_SIZE(cs42l43_accdet_us)); if (ret < 0) goto error; @@ -433,7 +433,7 @@ irqreturn_t cs42l43_button_press(int irq, void *data) // Wait for 2 full cycles of comb filter to ensure good reading queue_delayed_work(system_wq, &priv->button_press_work, - msecs_to_jiffies(10)); + msecs_to_jiffies(20)); return IRQ_HANDLED; } diff --git a/sound/soc/codecs/es8326.c b/sound/soc/codecs/es8326.c index 03b539ba540f..6a4e42e5e35b 100644 --- a/sound/soc/codecs/es8326.c +++ b/sound/soc/codecs/es8326.c @@ -857,12 +857,16 @@ static void es8326_jack_detect_handler(struct work_struct *work) * set auto-check mode, then restart jack_detect_work after 400ms. * Don't report jack status. */ - regmap_write(es8326->regmap, ES8326_INT_SOURCE, - (ES8326_INT_SRC_PIN9 | ES8326_INT_SRC_BUTTON)); + regmap_write(es8326->regmap, ES8326_INT_SOURCE, 0x00); regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x01); + regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x10, 0x00); es8326_enable_micbias(es8326->component); usleep_range(50000, 70000); regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x00); + regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x10, 0x10); + usleep_range(50000, 70000); + regmap_write(es8326->regmap, ES8326_INT_SOURCE, + (ES8326_INT_SRC_PIN9 | ES8326_INT_SRC_BUTTON)); regmap_write(es8326->regmap, ES8326_SYS_BIAS, 0x1f); regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x0f, 0x08); queue_delayed_work(system_wq, &es8326->jack_detect_work, diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index cdb7ff7020e9..51187b1e0ed2 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -81,7 +81,7 @@ static const struct reg_sequence init_list[] = { static const struct reg_sequence rt5650_init_list[] = { {0xf6, 0x0100}, {RT5645_PWR_ANLG1, 0x02}, - {RT5645_IL_CMD3, 0x0018}, + {RT5645_IL_CMD3, 0x6728}, }; static const struct reg_default rt5645_reg[] = { @@ -3130,20 +3130,32 @@ static void rt5645_enable_push_button_irq(struct snd_soc_component *component, bool enable) { struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(component); + int ret; if (enable) { snd_soc_dapm_force_enable_pin(dapm, "ADC L power"); snd_soc_dapm_force_enable_pin(dapm, "ADC R power"); snd_soc_dapm_sync(dapm); + snd_soc_component_update_bits(component, RT5650_4BTN_IL_CMD2, + RT5645_EN_4BTN_IL_MASK | RT5645_RST_4BTN_IL_MASK, + RT5645_EN_4BTN_IL_EN | RT5645_RST_4BTN_IL_RST); + usleep_range(10000, 15000); + snd_soc_component_update_bits(component, RT5650_4BTN_IL_CMD2, + RT5645_EN_4BTN_IL_MASK | RT5645_RST_4BTN_IL_MASK, + RT5645_EN_4BTN_IL_EN | RT5645_RST_4BTN_IL_NORM); + msleep(50); + ret = snd_soc_component_read(component, RT5645_INT_IRQ_ST); + pr_debug("%s read %x = %x\n", __func__, RT5645_INT_IRQ_ST, + snd_soc_component_read(component, RT5645_INT_IRQ_ST)); + snd_soc_component_write(component, RT5645_INT_IRQ_ST, ret); + ret = snd_soc_component_read(component, RT5650_4BTN_IL_CMD1); + pr_debug("%s read %x = %x\n", __func__, RT5650_4BTN_IL_CMD1, + snd_soc_component_read(component, RT5650_4BTN_IL_CMD1)); + snd_soc_component_write(component, RT5650_4BTN_IL_CMD1, ret); snd_soc_component_update_bits(component, RT5650_4BTN_IL_CMD1, 0x3, 0x3); snd_soc_component_update_bits(component, RT5645_INT_IRQ_ST, 0x8, 0x8); - snd_soc_component_update_bits(component, - RT5650_4BTN_IL_CMD2, 0x8000, 0x8000); - snd_soc_component_read(component, RT5650_4BTN_IL_CMD1); - pr_debug("%s read %x = %x\n", __func__, RT5650_4BTN_IL_CMD1, - snd_soc_component_read(component, RT5650_4BTN_IL_CMD1)); } else { snd_soc_component_update_bits(component, RT5650_4BTN_IL_CMD2, 0x8000, 0x0); snd_soc_component_update_bits(component, RT5645_INT_IRQ_ST, 0x8, 0x0); diff --git a/sound/soc/codecs/rt5645.h b/sound/soc/codecs/rt5645.h index 90816b2c5489..bef74b29fd54 100644 --- a/sound/soc/codecs/rt5645.h +++ b/sound/soc/codecs/rt5645.h @@ -2011,6 +2011,12 @@ #define RT5645_ZCD_HP_DIS (0x0 << 15) #define RT5645_ZCD_HP_EN (0x1 << 15) +/* Buttons Inline Command Function 2 (0xe0) */ +#define RT5645_EN_4BTN_IL_MASK (0x1 << 15) +#define RT5645_EN_4BTN_IL_EN (0x1 << 15) +#define RT5645_RST_4BTN_IL_MASK (0x1 << 14) +#define RT5645_RST_4BTN_IL_RST (0x0 << 14) +#define RT5645_RST_4BTN_IL_NORM (0x1 << 14) /* Codec Private Register definition */ /* DAC ADC Digital Volume (0x00) */ diff --git a/sound/soc/codecs/rt722-sdca-sdw.c b/sound/soc/codecs/rt722-sdca-sdw.c index b33da2215ade..87354bb1564e 100644 --- a/sound/soc/codecs/rt722-sdca-sdw.c +++ b/sound/soc/codecs/rt722-sdca-sdw.c @@ -68,6 +68,7 @@ static bool rt722_sdca_mbq_readable_register(struct device *dev, unsigned int re case 0x200007f: case 0x2000082 ... 0x200008e: case 0x2000090 ... 0x2000094: + case 0x3110000: case 0x5300000 ... 0x5300002: case 0x5400002: case 0x5600000 ... 0x5600007: @@ -125,6 +126,7 @@ static bool rt722_sdca_mbq_volatile_register(struct device *dev, unsigned int re case 0x2000067: case 0x2000084: case 0x2000086: + case 0x3110000: return true; default: return false; @@ -350,7 +352,7 @@ static int rt722_sdca_interrupt_callback(struct sdw_slave *slave, if (status->sdca_cascade && !rt722->disable_irq) mod_delayed_work(system_power_efficient_wq, - &rt722->jack_detect_work, msecs_to_jiffies(30)); + &rt722->jack_detect_work, msecs_to_jiffies(280)); mutex_unlock(&rt722->disable_irq_lock); diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c index 5ddc0c2fe53f..eb67689dcd6e 100644 --- a/sound/soc/fsl/fsl-asoc-card.c +++ b/sound/soc/fsl/fsl-asoc-card.c @@ -559,6 +559,8 @@ static int fsl_asoc_card_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; + priv->pdev = pdev; + cpu_np = of_parse_phandle(np, "audio-cpu", 0); /* Give a chance to old DT binding */ if (!cpu_np) @@ -787,7 +789,6 @@ static int fsl_asoc_card_probe(struct platform_device *pdev) } /* Initialize sound card */ - priv->pdev = pdev; priv->card.dev = &pdev->dev; priv->card.owner = THIS_MODULE; ret = snd_soc_of_parse_card_name(&priv->card, "model"); diff --git a/sound/soc/fsl/imx-pcm-dma.c b/sound/soc/fsl/imx-pcm-dma.c index 14e94270911c..4fa208d6a032 100644 --- a/sound/soc/fsl/imx-pcm-dma.c +++ b/sound/soc/fsl/imx-pcm-dma.c @@ -50,4 +50,5 @@ int imx_pcm_dma_init(struct platform_device *pdev) } EXPORT_SYMBOL_GPL(imx_pcm_dma_init); +MODULE_DESCRIPTION("Freescale i.MX PCM DMA interface"); MODULE_LICENSE("GPL"); diff --git a/sound/soc/intel/avs/topology.c b/sound/soc/intel/avs/topology.c index 02bae207f6ec..b6c5d94a1554 100644 --- a/sound/soc/intel/avs/topology.c +++ b/sound/soc/intel/avs/topology.c @@ -1545,8 +1545,8 @@ static int avs_route_load(struct snd_soc_component *comp, int index, { struct snd_soc_acpi_mach *mach = dev_get_platdata(comp->card->dev); size_t len = SNDRV_CTL_ELEM_ID_NAME_MAXLEN; - char buf[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; int ssp_port, tdm_slot; + char *buf; /* See parse_link_formatted_string() for dynamic naming when(s). */ if (!avs_mach_singular_ssp(mach)) @@ -1557,13 +1557,24 @@ static int avs_route_load(struct snd_soc_component *comp, int index, return 0; tdm_slot = avs_mach_ssp_tdm(mach, ssp_port); + buf = devm_kzalloc(comp->card->dev, len, GFP_KERNEL); + if (!buf) + return -ENOMEM; avs_ssp_sprint(buf, len, route->source, ssp_port, tdm_slot); - strscpy((char *)route->source, buf, len); + route->source = buf; + + buf = devm_kzalloc(comp->card->dev, len, GFP_KERNEL); + if (!buf) + return -ENOMEM; avs_ssp_sprint(buf, len, route->sink, ssp_port, tdm_slot); - strscpy((char *)route->sink, buf, len); + route->sink = buf; + if (route->control) { + buf = devm_kzalloc(comp->card->dev, len, GFP_KERNEL); + if (!buf) + return -ENOMEM; avs_ssp_sprint(buf, len, route->control, ssp_port, tdm_slot); - strscpy((char *)route->control, buf, len); + route->control = buf; } return 0; diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index b41a1147f1c3..a64d1989e28a 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -613,6 +613,17 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { { .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ARCHOS"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "ARCHOS 101 CESIUM"), + }, + .driver_data = (void *)(BYTCR_INPUT_DEFAULTS | + BYT_RT5640_JD_NOT_INV | + BYT_RT5640_DIFF_MIC | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), + }, + { + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ARCHOS"), DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "ARCHOS 140 CESIUM"), }, .driver_data = (void *)(BYT_RT5640_IN1_MAP | diff --git a/sound/soc/intel/common/soc-acpi-intel-mtl-match.c b/sound/soc/intel/common/soc-acpi-intel-mtl-match.c index 48252fa9e39e..8e0ae3635a35 100644 --- a/sound/soc/intel/common/soc-acpi-intel-mtl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-mtl-match.c @@ -293,7 +293,7 @@ static const struct snd_soc_acpi_adr_device rt1318_1_single_adr[] = { .adr = 0x000130025D131801, .num_endpoints = 1, .endpoints = &single_endpoint, - .name_prefix = "rt1318" + .name_prefix = "rt1318-1" } }; diff --git a/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c b/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c index acaf81fd6c9b..f848e14b091a 100644 --- a/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c +++ b/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c @@ -31,7 +31,7 @@ struct mt8183_da7219_max98357_priv { static struct snd_soc_jack_pin mt8183_da7219_max98357_jack_pins[] = { { - .pin = "Headphone", + .pin = "Headphones", .mask = SND_JACK_HEADPHONE, }, { @@ -626,7 +626,7 @@ static struct snd_soc_codec_conf mt6358_codec_conf[] = { }; static const struct snd_kcontrol_new mt8183_da7219_max98357_snd_controls[] = { - SOC_DAPM_PIN_SWITCH("Headphone"), + SOC_DAPM_PIN_SWITCH("Headphones"), SOC_DAPM_PIN_SWITCH("Headset Mic"), SOC_DAPM_PIN_SWITCH("Speakers"), SOC_DAPM_PIN_SWITCH("Line Out"), @@ -634,7 +634,7 @@ static const struct snd_kcontrol_new mt8183_da7219_max98357_snd_controls[] = { static const struct snd_soc_dapm_widget mt8183_da7219_max98357_dapm_widgets[] = { - SND_SOC_DAPM_HP("Headphone", NULL), + SND_SOC_DAPM_HP("Headphones", NULL), SND_SOC_DAPM_MIC("Headset Mic", NULL), SND_SOC_DAPM_SPK("Speakers", NULL), SND_SOC_DAPM_SPK("Line Out", NULL), @@ -680,7 +680,7 @@ static struct snd_soc_codec_conf mt8183_da7219_rt1015_codec_conf[] = { }; static const struct snd_kcontrol_new mt8183_da7219_rt1015_snd_controls[] = { - SOC_DAPM_PIN_SWITCH("Headphone"), + SOC_DAPM_PIN_SWITCH("Headphones"), SOC_DAPM_PIN_SWITCH("Headset Mic"), SOC_DAPM_PIN_SWITCH("Left Spk"), SOC_DAPM_PIN_SWITCH("Right Spk"), @@ -689,7 +689,7 @@ static const struct snd_kcontrol_new mt8183_da7219_rt1015_snd_controls[] = { static const struct snd_soc_dapm_widget mt8183_da7219_rt1015_dapm_widgets[] = { - SND_SOC_DAPM_HP("Headphone", NULL), + SND_SOC_DAPM_HP("Headphones", NULL), SND_SOC_DAPM_MIC("Headset Mic", NULL), SND_SOC_DAPM_SPK("Left Spk", NULL), SND_SOC_DAPM_SPK("Right Spk", NULL), diff --git a/sound/soc/mediatek/mt8195/mt8195-mt6359.c b/sound/soc/mediatek/mt8195/mt8195-mt6359.c index ca8751190520..2832ef78eaed 100644 --- a/sound/soc/mediatek/mt8195/mt8195-mt6359.c +++ b/sound/soc/mediatek/mt8195/mt8195-mt6359.c @@ -827,6 +827,7 @@ SND_SOC_DAILINK_DEFS(ETDM2_IN_BE, SND_SOC_DAILINK_DEFS(ETDM1_OUT_BE, DAILINK_COMP_ARRAY(COMP_CPU("ETDM1_OUT")), + DAILINK_COMP_ARRAY(COMP_EMPTY()), DAILINK_COMP_ARRAY(COMP_EMPTY())); SND_SOC_DAILINK_DEFS(ETDM2_OUT_BE, diff --git a/sound/soc/mxs/mxs-pcm.c b/sound/soc/mxs/mxs-pcm.c index df2e4be992d2..9bb08cadeb18 100644 --- a/sound/soc/mxs/mxs-pcm.c +++ b/sound/soc/mxs/mxs-pcm.c @@ -43,4 +43,5 @@ int mxs_pcm_platform_register(struct device *dev) } EXPORT_SYMBOL_GPL(mxs_pcm_platform_register); +MODULE_DESCRIPTION("MXS ASoC PCM driver"); MODULE_LICENSE("GPL"); diff --git a/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c b/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c index 68a38f63a2db..66b911b49e3f 100644 --- a/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c +++ b/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c @@ -141,14 +141,17 @@ static void q6apm_lpass_dai_shutdown(struct snd_pcm_substream *substream, struct struct q6apm_lpass_dai_data *dai_data = dev_get_drvdata(dai->dev); int rc; - if (!dai_data->is_port_started[dai->id]) - return; - rc = q6apm_graph_stop(dai_data->graph[dai->id]); - if (rc < 0) - dev_err(dai->dev, "fail to close APM port (%d)\n", rc); + if (dai_data->is_port_started[dai->id]) { + rc = q6apm_graph_stop(dai_data->graph[dai->id]); + dai_data->is_port_started[dai->id] = false; + if (rc < 0) + dev_err(dai->dev, "fail to close APM port (%d)\n", rc); + } - q6apm_graph_close(dai_data->graph[dai->id]); - dai_data->is_port_started[dai->id] = false; + if (dai_data->graph[dai->id]) { + q6apm_graph_close(dai_data->graph[dai->id]); + dai_data->graph[dai->id] = NULL; + } } static int q6apm_lpass_dai_prepare(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) @@ -163,8 +166,10 @@ static int q6apm_lpass_dai_prepare(struct snd_pcm_substream *substream, struct s q6apm_graph_stop(dai_data->graph[dai->id]); dai_data->is_port_started[dai->id] = false; - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { q6apm_graph_close(dai_data->graph[dai->id]); + dai_data->graph[dai->id] = NULL; + } } /** @@ -183,26 +188,29 @@ static int q6apm_lpass_dai_prepare(struct snd_pcm_substream *substream, struct s cfg->direction = substream->stream; rc = q6apm_graph_media_format_pcm(dai_data->graph[dai->id], cfg); - if (rc) { dev_err(dai->dev, "Failed to set media format %d\n", rc); - return rc; + goto err; } rc = q6apm_graph_prepare(dai_data->graph[dai->id]); if (rc) { dev_err(dai->dev, "Failed to prepare Graph %d\n", rc); - return rc; + goto err; } rc = q6apm_graph_start(dai_data->graph[dai->id]); if (rc < 0) { dev_err(dai->dev, "fail to start APM port %x\n", dai->id); - return rc; + goto err; } dai_data->is_port_started[dai->id] = true; return 0; +err: + q6apm_graph_close(dai_data->graph[dai->id]); + dai_data->graph[dai->id] = NULL; + return rc; } static int q6apm_lpass_dai_startup(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) diff --git a/sound/soc/qcom/sdw.c b/sound/soc/qcom/sdw.c index eaa8bb016e50..f2eda2ff46c0 100644 --- a/sound/soc/qcom/sdw.c +++ b/sound/soc/qcom/sdw.c @@ -160,4 +160,5 @@ int qcom_snd_sdw_hw_free(struct snd_pcm_substream *substream, return 0; } EXPORT_SYMBOL_GPL(qcom_snd_sdw_hw_free); +MODULE_DESCRIPTION("Qualcomm ASoC SoundWire helper functions"); MODULE_LICENSE("GPL"); diff --git a/sound/soc/rockchip/rockchip_i2s_tdm.c b/sound/soc/rockchip/rockchip_i2s_tdm.c index 9fa020ef7eab..ee517d7b5b7b 100644 --- a/sound/soc/rockchip/rockchip_i2s_tdm.c +++ b/sound/soc/rockchip/rockchip_i2s_tdm.c @@ -655,8 +655,17 @@ static int rockchip_i2s_tdm_hw_params(struct snd_pcm_substream *substream, int err; if (i2s_tdm->is_master_mode) { - struct clk *mclk = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) ? - i2s_tdm->mclk_tx : i2s_tdm->mclk_rx; + struct clk *mclk; + + if (i2s_tdm->clk_trcm == TRCM_TX) { + mclk = i2s_tdm->mclk_tx; + } else if (i2s_tdm->clk_trcm == TRCM_RX) { + mclk = i2s_tdm->mclk_rx; + } else if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { + mclk = i2s_tdm->mclk_tx; + } else { + mclk = i2s_tdm->mclk_rx; + } err = clk_set_rate(mclk, DEFAULT_MCLK_FS * params_rate(params)); if (err) diff --git a/sound/soc/soc-generic-dmaengine-pcm.c b/sound/soc/soc-generic-dmaengine-pcm.c index ea3bc9318412..a63e942fdc0b 100644 --- a/sound/soc/soc-generic-dmaengine-pcm.c +++ b/sound/soc/soc-generic-dmaengine-pcm.c @@ -318,6 +318,12 @@ static int dmaengine_copy(struct snd_soc_component *component, return 0; } +static int dmaengine_pcm_sync_stop(struct snd_soc_component *component, + struct snd_pcm_substream *substream) +{ + return snd_dmaengine_pcm_sync_stop(substream); +} + static const struct snd_soc_component_driver dmaengine_pcm_component = { .name = SND_DMAENGINE_PCM_DRV_NAME, .probe_order = SND_SOC_COMP_ORDER_LATE, @@ -327,6 +333,7 @@ static const struct snd_soc_component_driver dmaengine_pcm_component = { .trigger = dmaengine_pcm_trigger, .pointer = dmaengine_pcm_pointer, .pcm_construct = dmaengine_pcm_new, + .sync_stop = dmaengine_pcm_sync_stop, }; static const struct snd_soc_component_driver dmaengine_pcm_component_process = { @@ -339,6 +346,7 @@ static const struct snd_soc_component_driver dmaengine_pcm_component_process = { .pointer = dmaengine_pcm_pointer, .copy = dmaengine_copy, .pcm_construct = dmaengine_pcm_new, + .sync_stop = dmaengine_pcm_sync_stop, }; static const char * const dmaengine_pcm_dma_channel_names[] = { diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 90ca37e008b3..6951ff7bc61e 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -1021,6 +1021,7 @@ static int soc_tplg_dapm_graph_elems_load(struct soc_tplg *tplg, struct snd_soc_tplg_hdr *hdr) { struct snd_soc_dapm_context *dapm = &tplg->comp->dapm; + const size_t maxlen = SNDRV_CTL_ELEM_ID_NAME_MAXLEN; struct snd_soc_tplg_dapm_graph_elem *elem; struct snd_soc_dapm_route *route; int count, i; @@ -1044,31 +1045,27 @@ static int soc_tplg_dapm_graph_elems_load(struct soc_tplg *tplg, tplg->pos += sizeof(struct snd_soc_tplg_dapm_graph_elem); /* validate routes */ - if (strnlen(elem->source, SNDRV_CTL_ELEM_ID_NAME_MAXLEN) == - SNDRV_CTL_ELEM_ID_NAME_MAXLEN) { + if ((strnlen(elem->source, maxlen) == maxlen) || + (strnlen(elem->sink, maxlen) == maxlen) || + (strnlen(elem->control, maxlen) == maxlen)) { ret = -EINVAL; break; } - if (strnlen(elem->sink, SNDRV_CTL_ELEM_ID_NAME_MAXLEN) == - SNDRV_CTL_ELEM_ID_NAME_MAXLEN) { - ret = -EINVAL; - break; - } - if (strnlen(elem->control, SNDRV_CTL_ELEM_ID_NAME_MAXLEN) == - SNDRV_CTL_ELEM_ID_NAME_MAXLEN) { - ret = -EINVAL; + + route->source = devm_kstrdup(tplg->dev, elem->source, GFP_KERNEL); + route->sink = devm_kstrdup(tplg->dev, elem->sink, GFP_KERNEL); + if (!route->source || !route->sink) { + ret = -ENOMEM; break; } - route->source = elem->source; - route->sink = elem->sink; - - /* set to NULL atm for tplg users */ - route->connected = NULL; - if (strnlen(elem->control, SNDRV_CTL_ELEM_ID_NAME_MAXLEN) == 0) - route->control = NULL; - else - route->control = elem->control; + if (strnlen(elem->control, maxlen) != 0) { + route->control = devm_kstrdup(tplg->dev, elem->control, GFP_KERNEL); + if (!route->control) { + ret = -ENOMEM; + break; + } + } /* add route dobj to dobj_list */ route->dobj.type = SND_SOC_DOBJ_GRAPH; diff --git a/sound/soc/sof/intel/hda-dai.c b/sound/soc/sof/intel/hda-dai.c index ce675c22a5ab..c61d298ea6b3 100644 --- a/sound/soc/sof/intel/hda-dai.c +++ b/sound/soc/sof/intel/hda-dai.c @@ -379,7 +379,7 @@ static int non_hda_dai_hw_params_data(struct snd_pcm_substream *substream, sdev = widget_to_sdev(w); if (sdev->dspless_mode_selected) - goto skip_tlv; + return 0; /* get stream_id */ hext_stream = ops->get_hext_stream(sdev, cpu_dai, substream); @@ -423,7 +423,6 @@ static int non_hda_dai_hw_params_data(struct snd_pcm_substream *substream, dma_config->dma_stream_channel_map.device_count = 1; dma_config->dma_priv_config_size = 0; -skip_tlv: return 0; } @@ -525,6 +524,9 @@ int sdw_hda_dai_hw_params(struct snd_pcm_substream *substream, return ret; } + if (sdev->dspless_mode_selected) + return 0; + ipc4_copier = widget_to_copier(w); dma_config_tlv = &ipc4_copier->dma_config_tlv[cpu_dai_id]; dma_config = &dma_config_tlv->dma_config; diff --git a/sound/soc/sof/sof-audio.c b/sound/soc/sof/sof-audio.c index b3ac040811e7..ef9318947d74 100644 --- a/sound/soc/sof/sof-audio.c +++ b/sound/soc/sof/sof-audio.c @@ -485,7 +485,7 @@ sink_prepare: if (ret < 0) { /* unprepare the source widget */ if (widget_ops[widget->id].ipc_unprepare && - swidget && swidget->prepared) { + swidget && swidget->prepared && swidget->use_count == 0) { widget_ops[widget->id].ipc_unprepare(swidget); swidget->prepared = false; } diff --git a/sound/soc/ti/davinci-mcasp.c b/sound/soc/ti/davinci-mcasp.c index 1e760c315521..2b1ed91a736c 100644 --- a/sound/soc/ti/davinci-mcasp.c +++ b/sound/soc/ti/davinci-mcasp.c @@ -1472,10 +1472,11 @@ static int davinci_mcasp_hw_rule_min_periodsize( { struct snd_interval *period_size = hw_param_interval(params, SNDRV_PCM_HW_PARAM_PERIOD_SIZE); + u8 numevt = *((u8 *)rule->private); struct snd_interval frames; snd_interval_any(&frames); - frames.min = 64; + frames.min = numevt; frames.integer = 1; return snd_interval_refine(period_size, &frames); @@ -1490,6 +1491,7 @@ static int davinci_mcasp_startup(struct snd_pcm_substream *substream, u32 max_channels = 0; int i, dir, ret; int tdm_slots = mcasp->tdm_slots; + u8 *numevt; /* Do not allow more then one stream per direction */ if (mcasp->substreams[substream->stream]) @@ -1589,9 +1591,12 @@ static int davinci_mcasp_startup(struct snd_pcm_substream *substream, return ret; } + numevt = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) ? + &mcasp->txnumevt : + &mcasp->rxnumevt; snd_pcm_hw_rule_add(substream->runtime, 0, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, - davinci_mcasp_hw_rule_min_periodsize, NULL, + davinci_mcasp_hw_rule_min_periodsize, numevt, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, -1); return 0; diff --git a/sound/soc/ti/omap-hdmi.c b/sound/soc/ti/omap-hdmi.c index 639bc83f4263..cf43ac19c4a6 100644 --- a/sound/soc/ti/omap-hdmi.c +++ b/sound/soc/ti/omap-hdmi.c @@ -354,11 +354,7 @@ static int omap_hdmi_audio_probe(struct platform_device *pdev) if (!card) return -ENOMEM; - card->name = devm_kasprintf(dev, GFP_KERNEL, - "HDMI %s", dev_name(ad->dssdev)); - if (!card->name) - return -ENOMEM; - + card->name = "HDMI"; card->owner = THIS_MODULE; card->dai_link = devm_kzalloc(dev, sizeof(*(card->dai_link)), GFP_KERNEL); diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h index 52f076afeb96..7b32b99023a2 100644 --- a/tools/arch/arm64/include/asm/cputype.h +++ b/tools/arch/arm64/include/asm/cputype.h @@ -86,6 +86,9 @@ #define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define ARM_CPU_PART_CORTEX_A78C 0xD4B +#define ARM_CPU_PART_NEOVERSE_V2 0xD4F +#define ARM_CPU_PART_CORTEX_X4 0xD82 +#define ARM_CPU_PART_NEOVERSE_V3 0xD84 #define APM_CPU_PART_XGENE 0x000 #define APM_CPU_VAR_POTENZA 0x00 @@ -159,6 +162,9 @@ #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2) #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) +#define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) +#define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) +#define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index e72c2b872957..e022e6eb766c 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -170,6 +170,10 @@ * CPU is not affected by Branch * History Injection. */ +#define ARCH_CAP_XAPIC_DISABLE BIT(21) /* + * IA32_XAPIC_DISABLE_STATUS MSR + * supported + */ #define ARCH_CAP_PBRSB_NO BIT(24) /* * Not susceptible to Post-Barrier * Return Stack Buffer Predictions. @@ -192,11 +196,6 @@ * File. */ -#define ARCH_CAP_XAPIC_DISABLE BIT(21) /* - * IA32_XAPIC_DISABLE_STATUS MSR - * supported - */ - #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* * Writeback and invalidate the diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index ef11aa4cab42..9fae1b73b529 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -457,8 +457,13 @@ struct kvm_sync_regs { #define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001 -/* attributes for system fd (group 0) */ -#define KVM_X86_XCOMP_GUEST_SUPP 0 +/* vendor-independent attributes for system fd (group 0) */ +#define KVM_X86_GRP_SYSTEM 0 +# define KVM_X86_XCOMP_GUEST_SUPP 0 + +/* vendor-specific groups and attributes for system fd */ +#define KVM_X86_GRP_SEV 1 +# define KVM_X86_SEV_VMSA_FEATURES 0 struct kvm_vmx_nested_state_data { __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; @@ -689,6 +694,9 @@ enum sev_cmd_id { /* Guest Migration Extension */ KVM_SEV_SEND_CANCEL, + /* Second time is the charm; improved versions of the above ioctls. */ + KVM_SEV_INIT2, + KVM_SEV_NR_MAX, }; @@ -700,6 +708,14 @@ struct kvm_sev_cmd { __u32 sev_fd; }; +struct kvm_sev_init { + __u64 vmsa_features; + __u32 flags; + __u16 ghcb_version; + __u16 pad1; + __u32 pad2[8]; +}; + struct kvm_sev_launch_start { __u32 handle; __u32 policy; @@ -856,5 +872,7 @@ struct kvm_hyperv_eventfd { #define KVM_X86_DEFAULT_VM 0 #define KVM_X86_SW_PROTECTED_VM 1 +#define KVM_X86_SEV_VM 2 +#define KVM_X86_SEV_ES_VM 3 #endif /* _ASM_X86_KVM_H */ diff --git a/tools/hv/Makefile b/tools/hv/Makefile index bb52871da341..2e60e2c212cd 100644 --- a/tools/hv/Makefile +++ b/tools/hv/Makefile @@ -17,6 +17,7 @@ endif MAKEFLAGS += -r override CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include +override CFLAGS += -Wno-address-of-packed-member ALL_TARGETS := hv_kvp_daemon hv_vss_daemon ifneq ($(ARCH), aarch64) diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 75f00965ab15..d983c48a3b6a 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -842,8 +842,11 @@ __SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr) #define __NR_lsm_list_modules 461 __SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules) +#define __NR_mseal 462 +__SYSCALL(__NR_mseal, sys_mseal) + #undef __NR_syscalls -#define __NR_syscalls 462 +#define __NR_syscalls 463 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 2ee338860b7e..d4d86e566e07 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -806,6 +806,12 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_PXP_STATUS 58 +/* + * Query if kernel allows marking a context to send a Freq hint to SLPC. This + * will enable use of the strategies allowed by the SLPC algorithm. + */ +#define I915_PARAM_HAS_CONTEXT_FREQ_HINT 59 + /* Must be kept compact -- no holes and well documented */ /** @@ -2148,6 +2154,15 @@ struct drm_i915_gem_context_param { * -EIO: The firmware did not succeed in creating the protected context. */ #define I915_CONTEXT_PARAM_PROTECTED_CONTENT 0xd + +/* + * I915_CONTEXT_PARAM_LOW_LATENCY: + * + * Mark this context as a low latency workload which requires aggressive GT + * frequency scaling. Use I915_PARAM_HAS_CONTEXT_FREQ_HINT to check if the kernel + * supports this per context flag. + */ +#define I915_CONTEXT_PARAM_LOW_LATENCY 0xe /* Must be kept compact -- no holes and well documented */ /** @value: Context parameter value to be set or queried */ @@ -2623,19 +2638,29 @@ struct drm_i915_reg_read { * */ +/* + * struct drm_i915_reset_stats - Return global reset and other context stats + * + * Driver keeps few stats for each contexts and also global reset count. + * This struct can be used to query those stats. + */ struct drm_i915_reset_stats { + /** @ctx_id: ID of the requested context */ __u32 ctx_id; + + /** @flags: MBZ */ __u32 flags; - /* All resets since boot/module reload, for all contexts */ + /** @reset_count: All resets since boot/module reload, for all contexts */ __u32 reset_count; - /* Number of batches lost when active in GPU, for this context */ + /** @batch_active: Number of batches lost when active in GPU, for this context */ __u32 batch_active; - /* Number of batches lost pending for execution, for this context */ + /** @batch_pending: Number of batches lost pending for execution, for this context */ __u32 batch_pending; + /** @pad: MBZ */ __u32 pad; }; diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index ea32b101b999..d03842abae57 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1221,9 +1221,9 @@ struct kvm_vfio_spapr_tce { /* Available with KVM_CAP_SPAPR_RESIZE_HPT */ #define KVM_PPC_RESIZE_HPT_PREPARE _IOR(KVMIO, 0xad, struct kvm_ppc_resize_hpt) #define KVM_PPC_RESIZE_HPT_COMMIT _IOR(KVMIO, 0xae, struct kvm_ppc_resize_hpt) -/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_MMU_HASH_V3 */ +/* Available with KVM_CAP_PPC_MMU_RADIX or KVM_CAP_PPC_MMU_HASH_V3 */ #define KVM_PPC_CONFIGURE_V3_MMU _IOW(KVMIO, 0xaf, struct kvm_ppc_mmuv3_cfg) -/* Available with KVM_CAP_PPC_RADIX_MMU */ +/* Available with KVM_CAP_PPC_MMU_RADIX */ #define KVM_PPC_GET_RMMU_INFO _IOW(KVMIO, 0xb0, struct kvm_ppc_rmmu_info) /* Available with KVM_CAP_PPC_GET_CPU_CHAR */ #define KVM_PPC_GET_CPU_CHAR _IOR(KVMIO, 0xb1, struct kvm_ppc_cpu_char) diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h index 2f2ee82d5517..67626d535316 100644 --- a/tools/include/uapi/linux/stat.h +++ b/tools/include/uapi/linux/stat.h @@ -126,8 +126,9 @@ struct statx { __u64 stx_mnt_id; __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ + __u64 stx_subvol; /* Subvolume identifier */ /* 0xa0 */ - __u64 __spare3[12]; /* Spare space for future expansion */ + __u64 __spare3[11]; /* Spare space for future expansion */ /* 0x100 */ }; @@ -155,6 +156,7 @@ struct statx { #define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */ #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ +#define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 5c35c0d89306..e6d56b555369 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -214,6 +214,7 @@ NON_CONFIG_TARGETS := clean python-clean TAGS tags cscope help ifdef MAKECMDGOALS ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),) + VMLINUX_H=$(src-perf)/util/bpf_skel/vmlinux/vmlinux.h config := 0 endif endif diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl index 532b855df589..1464c6be6eb3 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -376,3 +376,4 @@ 459 n64 lsm_get_self_attr sys_lsm_get_self_attr 460 n64 lsm_set_self_attr sys_lsm_set_self_attr 461 n64 lsm_list_modules sys_lsm_list_modules +462 n64 mseal sys_mseal diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 17173b82ca21..3656f1ca7a21 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -548,3 +548,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 095bb86339a7..bd0fee24ad10 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -464,3 +464,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal sys_mseal diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 7e8d46f4147f..a396f6e6ab5b 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -374,7 +374,7 @@ 450 common set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat 452 common fchmodat2 sys_fchmodat2 -453 64 map_shadow_stack sys_map_shadow_stack +453 common map_shadow_stack sys_map_shadow_stack 454 common futex_wake sys_futex_wake 455 common futex_wait sys_futex_wait 456 common futex_requeue sys_futex_requeue @@ -383,6 +383,7 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal # # Due to a historical design error, certain syscalls are numbered differently diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 66a3de8ac661..0a8ba1323d64 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1956,8 +1956,7 @@ static void record__read_lost_samples(struct record *rec) if (count.lost) { if (!lost) { - lost = zalloc(sizeof(*lost) + - session->machines.host.id_hdr_size); + lost = zalloc(PERF_SAMPLE_MAX_SIZE); if (!lost) { pr_debug("Memory allocation failed\n"); return; @@ -1973,8 +1972,7 @@ static void record__read_lost_samples(struct record *rec) lost_count = perf_bpf_filter__lost_count(evsel); if (lost_count) { if (!lost) { - lost = zalloc(sizeof(*lost) + - session->machines.host.id_hdr_size); + lost = zalloc(PERF_SAMPLE_MAX_SIZE); if (!lost) { pr_debug("Memory allocation failed\n"); return; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 51eca671c797..08a3a6effac1 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -765,7 +765,7 @@ static const char *fcntl_cmds[] = { static DEFINE_STRARRAY(fcntl_cmds, "F_"); static const char *fcntl_linux_specific_cmds[] = { - "SETLEASE", "GETLEASE", "NOTIFY", [5] = "CANCELLK", "DUPFD_CLOEXEC", + "SETLEASE", "GETLEASE", "NOTIFY", "DUPFD_QUERY", [5] = "CANCELLK", "DUPFD_CLOEXEC", "SETPIPE_SZ", "GETPIPE_SZ", "ADD_SEALS", "GET_SEALS", "GET_RW_HINT", "SET_RW_HINT", "GET_FILE_RW_HINT", "SET_FILE_RW_HINT", }; diff --git a/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h b/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h index d18bfb238f66..13aea8fc3d45 100644 --- a/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h +++ b/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h @@ -97,10 +97,16 @@ #define LOCAL_TIMER_VECTOR 0xec +/* + * Posted interrupt notification vector for all device MSIs delivered to + * the host kernel. + */ +#define POSTED_MSI_NOTIFICATION_VECTOR 0xeb + #define NR_VECTORS 256 #ifdef CONFIG_X86_LOCAL_APIC -#define FIRST_SYSTEM_VECTOR LOCAL_TIMER_VECTOR +#define FIRST_SYSTEM_VECTOR POSTED_MSI_NOTIFICATION_VECTOR #else #define FIRST_SYSTEM_VECTOR NR_VECTORS #endif diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index 139c330ccf2c..89d16b90370b 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -16,6 +16,7 @@ struct cred; struct socket; struct sock; struct sk_buff; +struct proto_accept_arg; #define __sockaddr_check_size(size) \ BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage))) @@ -433,7 +434,7 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, extern int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr __user *addr, int addr_len); -extern struct file *do_accept(struct file *file, unsigned file_flags, +extern struct file *do_accept(struct file *file, struct proto_accept_arg *arg, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, diff --git a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h index 282e90aeb163..c0bcc185fa48 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h +++ b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h @@ -9,6 +9,14 @@ #define F_GETLEASE (F_LINUX_SPECIFIC_BASE + 1) /* + * Request nofications on a directory. + * See below for events that may be notified. + */ +#define F_NOTIFY (F_LINUX_SPECIFIC_BASE + 2) + +#define F_DUPFD_QUERY (F_LINUX_SPECIFIC_BASE + 3) + +/* * Cancel a blocking posix lock; internal use only until we expose an * asynchronous lock api to userspace: */ @@ -18,12 +26,6 @@ #define F_DUPFD_CLOEXEC (F_LINUX_SPECIFIC_BASE + 6) /* - * Request nofications on a directory. - * See below for events that may be notified. - */ -#define F_NOTIFY (F_LINUX_SPECIFIC_BASE+2) - -/* * Set and get of pipe page size array */ #define F_SETPIPE_SZ (F_LINUX_SPECIFIC_BASE + 7) diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h index 370ed14b1ae0..35791791a879 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h +++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h @@ -306,4 +306,26 @@ struct prctl_mm_map { # define PR_RISCV_V_VSTATE_CTRL_NEXT_MASK 0xc # define PR_RISCV_V_VSTATE_CTRL_MASK 0x1f +#define PR_RISCV_SET_ICACHE_FLUSH_CTX 71 +# define PR_RISCV_CTX_SW_FENCEI_ON 0 +# define PR_RISCV_CTX_SW_FENCEI_OFF 1 +# define PR_RISCV_SCOPE_PER_PROCESS 0 +# define PR_RISCV_SCOPE_PER_THREAD 1 + +/* PowerPC Dynamic Execution Control Register (DEXCR) controls */ +#define PR_PPC_GET_DEXCR 72 +#define PR_PPC_SET_DEXCR 73 +/* DEXCR aspect to act on */ +# define PR_PPC_DEXCR_SBHE 0 /* Speculative branch hint enable */ +# define PR_PPC_DEXCR_IBRTPD 1 /* Indirect branch recurrent target prediction disable */ +# define PR_PPC_DEXCR_SRAPD 2 /* Subroutine return address prediction disable */ +# define PR_PPC_DEXCR_NPHIE 3 /* Non-privileged hash instruction enable */ +/* Action to apply / return */ +# define PR_PPC_DEXCR_CTRL_EDITABLE 0x1 /* Aspect can be modified with PR_PPC_SET_DEXCR */ +# define PR_PPC_DEXCR_CTRL_SET 0x2 /* Set the aspect for this process */ +# define PR_PPC_DEXCR_CTRL_CLEAR 0x4 /* Clear the aspect for this process */ +# define PR_PPC_DEXCR_CTRL_SET_ONEXEC 0x8 /* Set the aspect on exec */ +# define PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC 0x10 /* Clear the aspect on exec */ +# define PR_PPC_DEXCR_CTRL_MASK 0x1f + #endif /* _LINUX_PRCTL_H */ diff --git a/tools/perf/trace/beauty/include/uapi/linux/stat.h b/tools/perf/trace/beauty/include/uapi/linux/stat.h index 2f2ee82d5517..67626d535316 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/stat.h +++ b/tools/perf/trace/beauty/include/uapi/linux/stat.h @@ -126,8 +126,9 @@ struct statx { __u64 stx_mnt_id; __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ + __u64 stx_subvol; /* Subvolume identifier */ /* 0xa0 */ - __u64 __spare3[12]; /* Spare space for future expansion */ + __u64 __spare3[11]; /* Spare space for future expansion */ /* 0x100 */ }; @@ -155,6 +156,7 @@ struct statx { #define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */ #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ +#define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index e0b3887b3d2d..dd49c1d23a60 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -457,7 +457,7 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \ LSKELS := fentry_test.c fexit_test.c fexit_sleep.c atomics.c \ trace_printk.c trace_vprintk.c map_ptr_kern.c \ core_kern.c core_kern_overflow.c test_ringbuf.c \ - test_ringbuf_n.c test_ringbuf_map_key.c + test_ringbuf_n.c test_ringbuf_map_key.c test_ringbuf_write.c # Generate both light skeleton and libbpf skeleton for these LSKELS_EXTRA := test_ksyms_module.c test_ksyms_weak.c kfunc_call_test.c \ diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c index 4c6f42dae409..da430df45aa4 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c @@ -12,9 +12,11 @@ #include <sys/sysinfo.h> #include <linux/perf_event.h> #include <linux/ring_buffer.h> + #include "test_ringbuf.lskel.h" #include "test_ringbuf_n.lskel.h" #include "test_ringbuf_map_key.lskel.h" +#include "test_ringbuf_write.lskel.h" #define EDONE 7777 @@ -84,6 +86,58 @@ static void *poll_thread(void *input) return (void *)(long)ring_buffer__poll(ringbuf, timeout); } +static void ringbuf_write_subtest(void) +{ + struct test_ringbuf_write_lskel *skel; + int page_size = getpagesize(); + size_t *mmap_ptr; + int err, rb_fd; + + skel = test_ringbuf_write_lskel__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + skel->maps.ringbuf.max_entries = 0x4000; + + err = test_ringbuf_write_lskel__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + rb_fd = skel->maps.ringbuf.map_fd; + + mmap_ptr = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, rb_fd, 0); + if (!ASSERT_OK_PTR(mmap_ptr, "rw_cons_pos")) + goto cleanup; + *mmap_ptr = 0x3000; + ASSERT_OK(munmap(mmap_ptr, page_size), "unmap_rw"); + + skel->bss->pid = getpid(); + + ringbuf = ring_buffer__new(rb_fd, process_sample, NULL, NULL); + if (!ASSERT_OK_PTR(ringbuf, "ringbuf_new")) + goto cleanup; + + err = test_ringbuf_write_lskel__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto cleanup_ringbuf; + + skel->bss->discarded = 0; + skel->bss->passed = 0; + + /* trigger exactly two samples */ + syscall(__NR_getpgid); + syscall(__NR_getpgid); + + ASSERT_EQ(skel->bss->discarded, 2, "discarded"); + ASSERT_EQ(skel->bss->passed, 0, "passed"); + + test_ringbuf_write_lskel__detach(skel); +cleanup_ringbuf: + ring_buffer__free(ringbuf); +cleanup: + test_ringbuf_write_lskel__destroy(skel); +} + static void ringbuf_subtest(void) { const size_t rec_sz = BPF_RINGBUF_HDR_SZ + sizeof(struct sample); @@ -451,4 +505,6 @@ void test_ringbuf(void) ringbuf_n_subtest(); if (test__start_subtest("ringbuf_map_key")) ringbuf_map_key_subtest(); + if (test__start_subtest("ringbuf_write")) + ringbuf_write_subtest(); } diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index 6816ff064516..9dc3687bc406 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -53,6 +53,7 @@ #include "verifier_movsx.skel.h" #include "verifier_netfilter_ctx.skel.h" #include "verifier_netfilter_retcode.skel.h" +#include "verifier_or_jmp32_k.skel.h" #include "verifier_precision.skel.h" #include "verifier_prevent_map_lookup.skel.h" #include "verifier_raw_stack.skel.h" @@ -171,6 +172,7 @@ void test_verifier_meta_access(void) { RUN(verifier_meta_access); } void test_verifier_movsx(void) { RUN(verifier_movsx); } void test_verifier_netfilter_ctx(void) { RUN(verifier_netfilter_ctx); } void test_verifier_netfilter_retcode(void) { RUN(verifier_netfilter_retcode); } +void test_verifier_or_jmp32_k(void) { RUN(verifier_or_jmp32_k); } void test_verifier_precision(void) { RUN(verifier_precision); } void test_verifier_prevent_map_lookup(void) { RUN(verifier_prevent_map_lookup); } void test_verifier_raw_stack(void) { RUN(verifier_raw_stack); } diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf_write.c b/tools/testing/selftests/bpf/progs/test_ringbuf_write.c new file mode 100644 index 000000000000..350513c0e4c9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ringbuf_write.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); +} ringbuf SEC(".maps"); + +/* inputs */ +int pid = 0; + +/* outputs */ +long passed = 0; +long discarded = 0; + +SEC("fentry/" SYS_PREFIX "sys_getpgid") +int test_ringbuf_write(void *ctx) +{ + int *foo, cur_pid = bpf_get_current_pid_tgid() >> 32; + void *sample1, *sample2; + + if (cur_pid != pid) + return 0; + + sample1 = bpf_ringbuf_reserve(&ringbuf, 0x3000, 0); + if (!sample1) + return 0; + /* first one can pass */ + sample2 = bpf_ringbuf_reserve(&ringbuf, 0x3000, 0); + if (!sample2) { + bpf_ringbuf_discard(sample1, 0); + __sync_fetch_and_add(&discarded, 1); + return 0; + } + /* second one must not */ + __sync_fetch_and_add(&passed, 1); + foo = sample2 + 4084; + *foo = 256; + bpf_ringbuf_discard(sample1, 0); + bpf_ringbuf_discard(sample2, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c index bd676d7e615f..80c737b6d340 100644 --- a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c +++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c @@ -274,6 +274,58 @@ static __naked void iter_limit_bug_cb(void) ); } +int tmp_var; +SEC("socket") +__failure __msg("infinite loop detected at insn 2") +__naked void jgt_imm64_and_may_goto(void) +{ + asm volatile (" \ + r0 = %[tmp_var] ll; \ +l0_%=: .byte 0xe5; /* may_goto */ \ + .byte 0; /* regs */ \ + .short -3; /* off -3 */ \ + .long 0; /* imm */ \ + if r0 > 10 goto l0_%=; \ + r0 = 0; \ + exit; \ +" :: __imm_addr(tmp_var) + : __clobber_all); +} + +SEC("socket") +__failure __msg("infinite loop detected at insn 1") +__naked void may_goto_self(void) +{ + asm volatile (" \ + r0 = *(u32 *)(r10 - 4); \ +l0_%=: .byte 0xe5; /* may_goto */ \ + .byte 0; /* regs */ \ + .short -1; /* off -1 */ \ + .long 0; /* imm */ \ + if r0 > 10 goto l0_%=; \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__success __retval(0) +__naked void may_goto_neg_off(void) +{ + asm volatile (" \ + r0 = *(u32 *)(r10 - 4); \ + goto l0_%=; \ + goto l1_%=; \ +l0_%=: .byte 0xe5; /* may_goto */ \ + .byte 0; /* regs */ \ + .short -2; /* off -2 */ \ + .long 0; /* imm */ \ + if r0 > 10 goto l0_%=; \ +l1_%=: r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + SEC("tc") __failure __flag(BPF_F_TEST_STATE_FREQ) @@ -307,6 +359,100 @@ int iter_limit_bug(struct __sk_buff *skb) return 0; } +SEC("socket") +__success __retval(0) +__naked void ja_and_may_goto(void) +{ + asm volatile (" \ +l0_%=: .byte 0xe5; /* may_goto */ \ + .byte 0; /* regs */ \ + .short 1; /* off 1 */ \ + .long 0; /* imm */ \ + goto l0_%=; \ + r0 = 0; \ + exit; \ +" ::: __clobber_common); +} + +SEC("socket") +__success __retval(0) +__naked void ja_and_may_goto2(void) +{ + asm volatile (" \ +l0_%=: r0 = 0; \ + .byte 0xe5; /* may_goto */ \ + .byte 0; /* regs */ \ + .short 1; /* off 1 */ \ + .long 0; /* imm */ \ + goto l0_%=; \ + r0 = 0; \ + exit; \ +" ::: __clobber_common); +} + +SEC("socket") +__success __retval(0) +__naked void jlt_and_may_goto(void) +{ + asm volatile (" \ +l0_%=: call %[bpf_jiffies64]; \ + .byte 0xe5; /* may_goto */ \ + .byte 0; /* regs */ \ + .short 1; /* off 1 */ \ + .long 0; /* imm */ \ + if r0 < 10 goto l0_%=; \ + r0 = 0; \ + exit; \ +" :: __imm(bpf_jiffies64) + : __clobber_all); +} + +#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ + (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \ + defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390) || \ + defined(__TARGET_ARCH_loongarch)) && \ + __clang_major__ >= 18 +SEC("socket") +__success __retval(0) +__naked void gotol_and_may_goto(void) +{ + asm volatile (" \ +l0_%=: r0 = 0; \ + .byte 0xe5; /* may_goto */ \ + .byte 0; /* regs */ \ + .short 1; /* off 1 */ \ + .long 0; /* imm */ \ + gotol l0_%=; \ + r0 = 0; \ + exit; \ +" ::: __clobber_common); +} +#endif + +SEC("socket") +__success __retval(0) +__naked void ja_and_may_goto_subprog(void) +{ + asm volatile (" \ + call subprog_with_may_goto; \ + exit; \ +" ::: __clobber_all); +} + +static __naked __noinline __used +void subprog_with_may_goto(void) +{ + asm volatile (" \ +l0_%=: .byte 0xe5; /* may_goto */ \ + .byte 0; /* regs */ \ + .short 1; /* off 1 */ \ + .long 0; /* imm */ \ + goto l0_%=; \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + #define ARR_SZ 1000000 int zero; char arr[ARR_SZ]; diff --git a/tools/testing/selftests/bpf/progs/verifier_movsx.c b/tools/testing/selftests/bpf/progs/verifier_movsx.c index cbb9d6714f53..028ec855587b 100644 --- a/tools/testing/selftests/bpf/progs/verifier_movsx.c +++ b/tools/testing/selftests/bpf/progs/verifier_movsx.c @@ -224,6 +224,69 @@ l0_%=: \ : __clobber_all); } +SEC("socket") +__description("MOV32SX, S8, var_off u32_max") +__failure __msg("infinite loop detected") +__failure_unpriv __msg_unpriv("back-edge from insn 2 to 0") +__naked void mov64sx_s32_varoff_1(void) +{ + asm volatile (" \ +l0_%=: \ + r3 = *(u8 *)(r10 -387); \ + w7 = (s8)w3; \ + if w7 >= 0x2533823b goto l0_%=; \ + w0 = 0; \ + exit; \ +" : + : + : __clobber_all); +} + +SEC("socket") +__description("MOV32SX, S8, var_off not u32_max, positive after s8 extension") +__success __retval(0) +__failure_unpriv __msg_unpriv("frame pointer is read only") +__naked void mov64sx_s32_varoff_2(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r3 = r0; \ + r3 &= 0xf; \ + w7 = (s8)w3; \ + if w7 s>= 16 goto l0_%=; \ + w0 = 0; \ + exit; \ +l0_%=: \ + r10 = 1; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("MOV32SX, S8, var_off not u32_max, negative after s8 extension") +__success __retval(0) +__failure_unpriv __msg_unpriv("frame pointer is read only") +__naked void mov64sx_s32_varoff_3(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r3 = r0; \ + r3 &= 0xf; \ + r3 |= 0x80; \ + w7 = (s8)w3; \ + if w7 s>= -5 goto l0_%=; \ + w0 = 0; \ + exit; \ +l0_%=: \ + r10 = 1; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + #else SEC("socket") diff --git a/tools/testing/selftests/bpf/progs/verifier_or_jmp32_k.c b/tools/testing/selftests/bpf/progs/verifier_or_jmp32_k.c new file mode 100644 index 000000000000..f37713a265ac --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_or_jmp32_k.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("socket") +__description("or_jmp32_k: bit ops + branch on unknown value") +__failure +__msg("R0 invalid mem access 'scalar'") +__naked void or_jmp32_k(void) +{ + asm volatile (" \ + r0 = 0xffffffff; \ + r0 /= 1; \ + r1 = 0; \ + w1 = -1; \ + w1 >>= 1; \ + w0 &= w1; \ + w0 |= 2; \ + if w0 != 0x7ffffffd goto l1; \ + r0 = 1; \ + exit; \ +l3: \ + r0 = 5; \ + *(u64*)(r0 - 8) = r0; \ + exit; \ +l2: \ + w0 -= 0xe; \ + if w0 == 1 goto l3; \ + r0 = 4; \ + exit; \ +l1: \ + w0 -= 0x7ffffff0; \ + if w0 s>= 0xe goto l2; \ + r0 = 3; \ + exit; \ +" ::: __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile index 4933d045ab66..c9f2f48fc30f 100644 --- a/tools/testing/selftests/drivers/net/hw/Makefile +++ b/tools/testing/selftests/drivers/net/hw/Makefile @@ -11,6 +11,7 @@ TEST_PROGS = \ hw_stats_l3_gre.sh \ loopback.sh \ pp_alloc_fail.py \ + rss_ctx.py \ # TEST_FILES := \ diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py new file mode 100755 index 000000000000..68c7d40214eb --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py @@ -0,0 +1,383 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +import datetime +import random +from lib.py import ksft_run, ksft_pr, ksft_exit, ksft_eq, ksft_ge, ksft_lt +from lib.py import NetDrvEpEnv +from lib.py import NetdevFamily +from lib.py import KsftSkipEx +from lib.py import rand_port +from lib.py import ethtool, ip, GenerateTraffic, CmdExitFailure + + +def _rss_key_str(key): + return ":".join(["{:02x}".format(x) for x in key]) + + +def _rss_key_rand(length): + return [random.randint(0, 255) for _ in range(length)] + + +def get_rss(cfg, context=0): + return ethtool(f"-x {cfg.ifname} context {context}", json=True)[0] + + +def get_drop_err_sum(cfg): + stats = ip("-s -s link show dev " + cfg.ifname, json=True)[0] + cnt = 0 + for key in ['errors', 'dropped', 'over_errors', 'fifo_errors', + 'length_errors', 'crc_errors', 'missed_errors', + 'frame_errors']: + cnt += stats["stats64"]["rx"][key] + return cnt, stats["stats64"]["tx"]["carrier_changes"] + + +def ethtool_create(cfg, act, opts): + output = ethtool(f"{act} {cfg.ifname} {opts}").stdout + # Output will be something like: "New RSS context is 1" or + # "Added rule with ID 7", we want the integer from the end + return int(output.split()[-1]) + + +def require_ntuple(cfg): + features = ethtool(f"-k {cfg.ifname}", json=True)[0] + if not features["ntuple-filters"]["active"]: + # ntuple is more of a capability than a config knob, don't bother + # trying to enable it (until some driver actually needs it). + raise KsftSkipEx("Ntuple filters not enabled on the device: " + str(features["ntuple-filters"])) + + +# Get Rx packet counts for all queues, as a simple list of integers +# if @prev is specified the prev counts will be subtracted +def _get_rx_cnts(cfg, prev=None): + cfg.wait_hw_stats_settle() + data = cfg.netdevnl.qstats_get({"ifindex": cfg.ifindex, "scope": ["queue"]}, dump=True) + data = [x for x in data if x['queue-type'] == "rx"] + max_q = max([x["queue-id"] for x in data]) + queue_stats = [0] * (max_q + 1) + for q in data: + queue_stats[q["queue-id"]] = q["rx-packets"] + if prev and q["queue-id"] < len(prev): + queue_stats[q["queue-id"]] -= prev[q["queue-id"]] + return queue_stats + + +def test_rss_key_indir(cfg): + """ + Test basics like updating the main RSS key and indirection table. + """ + if len(_get_rx_cnts(cfg)) < 2: + KsftSkipEx("Device has only one queue (or doesn't support queue stats)") + + data = get_rss(cfg) + want_keys = ['rss-hash-key', 'rss-hash-function', 'rss-indirection-table'] + for k in want_keys: + if k not in data: + raise KsftFailEx("ethtool results missing key: " + k) + if not data[k]: + raise KsftFailEx(f"ethtool results empty for '{k}': {data[k]}") + + key_len = len(data['rss-hash-key']) + + # Set the key + key = _rss_key_rand(key_len) + ethtool(f"-X {cfg.ifname} hkey " + _rss_key_str(key)) + + data = get_rss(cfg) + ksft_eq(key, data['rss-hash-key']) + + # Set the indirection table + ethtool(f"-X {cfg.ifname} equal 2") + data = get_rss(cfg) + ksft_eq(0, min(data['rss-indirection-table'])) + ksft_eq(1, max(data['rss-indirection-table'])) + + # Check we only get traffic on the first 2 queues + cnts = _get_rx_cnts(cfg) + GenerateTraffic(cfg).wait_pkts_and_stop(20000) + cnts = _get_rx_cnts(cfg, prev=cnts) + # 2 queues, 20k packets, must be at least 5k per queue + ksft_ge(cnts[0], 5000, "traffic on main context (1/2): " + str(cnts)) + ksft_ge(cnts[1], 5000, "traffic on main context (2/2): " + str(cnts)) + # The other queues should be unused + ksft_eq(sum(cnts[2:]), 0, "traffic on unused queues: " + str(cnts)) + + # Restore, and check traffic gets spread again + ethtool(f"-X {cfg.ifname} default") + + cnts = _get_rx_cnts(cfg) + GenerateTraffic(cfg).wait_pkts_and_stop(20000) + cnts = _get_rx_cnts(cfg, prev=cnts) + # First two queues get less traffic than all the rest + ksft_lt(sum(cnts[:2]), sum(cnts[2:]), "traffic distributed: " + str(cnts)) + + +def test_rss_context(cfg, ctx_cnt=1, create_with_cfg=None): + """ + Test separating traffic into RSS contexts. + The queues will be allocated 2 for each context: + ctx0 ctx1 ctx2 ctx3 + [0 1] [2 3] [4 5] [6 7] ... + """ + + require_ntuple(cfg) + + requested_ctx_cnt = ctx_cnt + + # Try to allocate more queues when necessary + qcnt = len(_get_rx_cnts(cfg)) + if qcnt >= 2 + 2 * ctx_cnt: + qcnt = None + else: + try: + ksft_pr(f"Increasing queue count {qcnt} -> {2 + 2 * ctx_cnt}") + ethtool(f"-L {cfg.ifname} combined {2 + 2 * ctx_cnt}") + except: + raise KsftSkipEx("Not enough queues for the test") + + ntuple = [] + ctx_id = [] + ports = [] + try: + # Use queues 0 and 1 for normal traffic + ethtool(f"-X {cfg.ifname} equal 2") + + for i in range(ctx_cnt): + want_cfg = f"start {2 + i * 2} equal 2" + create_cfg = want_cfg if create_with_cfg else "" + + try: + ctx_id.append(ethtool_create(cfg, "-X", f"context new {create_cfg}")) + except CmdExitFailure: + # try to carry on and skip at the end + if i == 0: + raise + ksft_pr(f"Failed to create context {i + 1}, trying to test what we got") + ctx_cnt = i + break + + if not create_with_cfg: + ethtool(f"-X {cfg.ifname} context {ctx_id[i]} {want_cfg}") + + # Sanity check the context we just created + data = get_rss(cfg, ctx_id[i]) + ksft_eq(min(data['rss-indirection-table']), 2 + i * 2, "Unexpected context cfg: " + str(data)) + ksft_eq(max(data['rss-indirection-table']), 2 + i * 2 + 1, "Unexpected context cfg: " + str(data)) + + ports.append(rand_port()) + flow = f"flow-type tcp{cfg.addr_ipver} dst-port {ports[i]} context {ctx_id[i]}" + ntuple.append(ethtool_create(cfg, "-N", flow)) + + for i in range(ctx_cnt): + cnts = _get_rx_cnts(cfg) + GenerateTraffic(cfg, port=ports[i]).wait_pkts_and_stop(20000) + cnts = _get_rx_cnts(cfg, prev=cnts) + + ksft_lt(sum(cnts[ :2]), 10000, "traffic on main context:" + str(cnts)) + ksft_ge(sum(cnts[2+i*2:4+i*2]), 20000, f"traffic on context {i}: " + str(cnts)) + ksft_eq(sum(cnts[2:2+i*2] + cnts[4+i*2:]), 0, "traffic on other contexts: " + str(cnts)) + finally: + for nid in ntuple: + ethtool(f"-N {cfg.ifname} delete {nid}") + for cid in ctx_id: + ethtool(f"-X {cfg.ifname} context {cid} delete") + ethtool(f"-X {cfg.ifname} default") + if qcnt: + ethtool(f"-L {cfg.ifname} combined {qcnt}") + + if requested_ctx_cnt != ctx_cnt: + raise KsftSkipEx(f"Tested only {ctx_cnt} contexts, wanted {requested_ctx_cnt}") + + +def test_rss_context4(cfg): + test_rss_context(cfg, 4) + + +def test_rss_context32(cfg): + test_rss_context(cfg, 32) + + +def test_rss_context4_create_with_cfg(cfg): + test_rss_context(cfg, 4, create_with_cfg=True) + + +def test_rss_context_out_of_order(cfg, ctx_cnt=4): + """ + Test separating traffic into RSS contexts. + Contexts are removed in semi-random order, and steering re-tested + to make sure removal doesn't break steering to surviving contexts. + Test requires 3 contexts to work. + """ + + require_ntuple(cfg) + + requested_ctx_cnt = ctx_cnt + + # Try to allocate more queues when necessary + qcnt = len(_get_rx_cnts(cfg)) + if qcnt >= 2 + 2 * ctx_cnt: + qcnt = None + else: + try: + ksft_pr(f"Increasing queue count {qcnt} -> {2 + 2 * ctx_cnt}") + ethtool(f"-L {cfg.ifname} combined {2 + 2 * ctx_cnt}") + except: + raise KsftSkipEx("Not enough queues for the test") + + ntuple = [] + ctx_id = [] + ports = [] + + def remove_ctx(idx): + ethtool(f"-N {cfg.ifname} delete {ntuple[idx]}") + ntuple[idx] = None + ethtool(f"-X {cfg.ifname} context {ctx_id[idx]} delete") + ctx_id[idx] = None + + def check_traffic(): + for i in range(ctx_cnt): + cnts = _get_rx_cnts(cfg) + GenerateTraffic(cfg, port=ports[i]).wait_pkts_and_stop(20000) + cnts = _get_rx_cnts(cfg, prev=cnts) + + if ctx_id[i] is None: + ksft_lt(sum(cnts[ :2]), 10000, "traffic on main context:" + str(cnts)) + ksft_ge(sum(cnts[2+i*2:4+i*2]), 20000, f"traffic on context {i}: " + str(cnts)) + ksft_eq(sum(cnts[2:2+i*2] + cnts[4+i*2:]), 0, "traffic on other contexts: " + str(cnts)) + else: + ksft_ge(sum(cnts[ :2]), 20000, "traffic on main context:" + str(cnts)) + ksft_eq(sum(cnts[2: ]), 0, "traffic on other contexts: " + str(cnts)) + + try: + # Use queues 0 and 1 for normal traffic + ethtool(f"-X {cfg.ifname} equal 2") + + for i in range(ctx_cnt): + ctx_id.append(ethtool_create(cfg, "-X", f"context new start {2 + i * 2} equal 2")) + + ports.append(rand_port()) + flow = f"flow-type tcp{cfg.addr_ipver} dst-port {ports[i]} context {ctx_id[i]}" + ntuple.append(ethtool_create(cfg, "-N", flow)) + + check_traffic() + + # Remove middle context + remove_ctx(ctx_cnt // 2) + check_traffic() + + # Remove first context + remove_ctx(0) + check_traffic() + + # Remove last context + remove_ctx(-1) + check_traffic() + + finally: + for nid in ntuple: + if nid is not None: + ethtool(f"-N {cfg.ifname} delete {nid}") + for cid in ctx_id: + if cid is not None: + ethtool(f"-X {cfg.ifname} context {cid} delete") + ethtool(f"-X {cfg.ifname} default") + if qcnt: + ethtool(f"-L {cfg.ifname} combined {qcnt}") + + if requested_ctx_cnt != ctx_cnt: + raise KsftSkipEx(f"Tested only {ctx_cnt} contexts, wanted {requested_ctx_cnt}") + + +def test_rss_context_overlap(cfg, other_ctx=0): + """ + Test contexts overlapping with each other. + Use 4 queues for the main context, but only queues 2 and 3 for context 1. + """ + + require_ntuple(cfg) + + queue_cnt = len(_get_rx_cnts(cfg)) + if queue_cnt >= 4: + queue_cnt = None + else: + try: + ksft_pr(f"Increasing queue count {queue_cnt} -> 4") + ethtool(f"-L {cfg.ifname} combined 4") + except: + raise KsftSkipEx("Not enough queues for the test") + + ctx_id = None + ntuple = None + if other_ctx == 0: + ethtool(f"-X {cfg.ifname} equal 4") + else: + other_ctx = ethtool_create(cfg, "-X", "context new") + ethtool(f"-X {cfg.ifname} context {other_ctx} equal 4") + + try: + ctx_id = ethtool_create(cfg, "-X", "context new") + ethtool(f"-X {cfg.ifname} context {ctx_id} start 2 equal 2") + + port = rand_port() + if other_ctx: + flow = f"flow-type tcp{cfg.addr_ipver} dst-port {port} context {other_ctx}" + ntuple = ethtool_create(cfg, "-N", flow) + + # Test the main context + cnts = _get_rx_cnts(cfg) + GenerateTraffic(cfg, port=port).wait_pkts_and_stop(20000) + cnts = _get_rx_cnts(cfg, prev=cnts) + + ksft_ge(sum(cnts[ :4]), 20000, "traffic on main context: " + str(cnts)) + ksft_ge(sum(cnts[ :2]), 7000, "traffic on main context (1/2): " + str(cnts)) + ksft_ge(sum(cnts[2:4]), 7000, "traffic on main context (2/2): " + str(cnts)) + if other_ctx == 0: + ksft_eq(sum(cnts[4: ]), 0, "traffic on other queues: " + str(cnts)) + + # Now create a rule for context 1 and make sure traffic goes to a subset + if other_ctx: + ethtool(f"-N {cfg.ifname} delete {ntuple}") + ntuple = None + flow = f"flow-type tcp{cfg.addr_ipver} dst-port {port} context {ctx_id}" + ntuple = ethtool_create(cfg, "-N", flow) + + cnts = _get_rx_cnts(cfg) + GenerateTraffic(cfg, port=port).wait_pkts_and_stop(20000) + cnts = _get_rx_cnts(cfg, prev=cnts) + + ksft_lt(sum(cnts[ :2]), 7000, "traffic on main context: " + str(cnts)) + ksft_ge(sum(cnts[2:4]), 20000, "traffic on extra context: " + str(cnts)) + if other_ctx == 0: + ksft_eq(sum(cnts[4: ]), 0, "traffic on other queues: " + str(cnts)) + finally: + if ntuple is not None: + ethtool(f"-N {cfg.ifname} delete {ntuple}") + if ctx_id: + ethtool(f"-X {cfg.ifname} context {ctx_id} delete") + if other_ctx == 0: + ethtool(f"-X {cfg.ifname} default") + else: + ethtool(f"-X {cfg.ifname} context {other_ctx} delete") + if queue_cnt: + ethtool(f"-L {cfg.ifname} combined {queue_cnt}") + + +def test_rss_context_overlap2(cfg): + test_rss_context_overlap(cfg, True) + + +def main() -> None: + with NetDrvEpEnv(__file__, nsim_test=False) as cfg: + cfg.netdevnl = NetdevFamily() + + ksft_run([test_rss_key_indir, + test_rss_context, test_rss_context4, test_rss_context32, + test_rss_context_overlap, test_rss_context_overlap2, + test_rss_context_out_of_order, test_rss_context4_create_with_cfg], + args=(cfg, )) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py index edcedd7bffab..a5e800b8f103 100644 --- a/tools/testing/selftests/drivers/net/lib/py/env.py +++ b/tools/testing/selftests/drivers/net/lib/py/env.py @@ -1,9 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 import os +import time from pathlib import Path from lib.py import KsftSkipEx, KsftXfailEx -from lib.py import cmd, ip +from lib.py import cmd, ethtool, ip from lib.py import NetNS, NetdevSimDev from .remote import Remote @@ -82,6 +83,8 @@ class NetDrvEpEnv: self.env = _load_env_file(src_path) + self._stats_settle_time = None + # Things we try to destroy self.remote = None # These are for local testing state @@ -222,3 +225,17 @@ class NetDrvEpEnv: if remote: if not self._require_cmd(comm, "remote"): raise KsftSkipEx("Test requires (remote) command: " + comm) + + def wait_hw_stats_settle(self): + """ + Wait for HW stats to become consistent, some devices DMA HW stats + periodically so events won't be reflected until next sync. + Good drivers will tell us via ethtool what their sync period is. + """ + if self._stats_settle_time is None: + data = ethtool("-c " + self.ifname, json=True)[0] + + self._stats_settle_time = 0.025 + \ + data.get('stats-block-usecs', 0) / 1000 / 1000 + + time.sleep(self._stats_settle_time) diff --git a/tools/testing/selftests/drivers/net/lib/py/load.py b/tools/testing/selftests/drivers/net/lib/py/load.py index abdb677bdb1c..d9c10613ae67 100644 --- a/tools/testing/selftests/drivers/net/lib/py/load.py +++ b/tools/testing/selftests/drivers/net/lib/py/load.py @@ -5,28 +5,45 @@ import time from lib.py import ksft_pr, cmd, ip, rand_port, wait_port_listen class GenerateTraffic: - def __init__(self, env): + def __init__(self, env, port=None): env.require_cmd("iperf3", remote=True) self.env = env - port = rand_port() - self._iperf_server = cmd(f"iperf3 -s -p {port}", background=True) + if port is None: + port = rand_port() + self._iperf_server = cmd(f"iperf3 -s -1 -p {port}", background=True) wait_port_listen(port) time.sleep(0.1) self._iperf_client = cmd(f"iperf3 -c {env.addr} -P 16 -p {port} -t 86400", background=True, host=env.remote) # Wait for traffic to ramp up - pkt = ip("-s link show dev " + env.ifname, json=True)[0]["stats64"]["rx"]["packets"] + if not self._wait_pkts(pps=1000): + self.stop(verbose=True) + raise Exception("iperf3 traffic did not ramp up") + + def _wait_pkts(self, pkt_cnt=None, pps=None): + """ + Wait until we've seen pkt_cnt or until traffic ramps up to pps. + Only one of pkt_cnt or pss can be specified. + """ + pkt_start = ip("-s link show dev " + self.env.ifname, json=True)[0]["stats64"]["rx"]["packets"] for _ in range(50): time.sleep(0.1) - now = ip("-s link show dev " + env.ifname, json=True)[0]["stats64"]["rx"]["packets"] - if now - pkt > 1000: - return - pkt = now - self.stop(verbose=True) - raise Exception("iperf3 traffic did not ramp up") + pkt_now = ip("-s link show dev " + self.env.ifname, json=True)[0]["stats64"]["rx"]["packets"] + if pps: + if pkt_now - pkt_start > pps / 10: + return True + pkt_start = pkt_now + elif pkt_cnt: + if pkt_now - pkt_start > pkt_cnt: + return True + return False + + def wait_pkts_and_stop(self, pkt_cnt): + failed = not self._wait_pkts(pkt_cnt=pkt_cnt) + self.stop(verbose=failed) def stop(self, verbose=None): self._iperf_client.process(terminate=True) diff --git a/tools/testing/selftests/drivers/net/virtio_net/config b/tools/testing/selftests/drivers/net/virtio_net/config index f35de0542b60..bcf7555eaffe 100644 --- a/tools/testing/selftests/drivers/net/virtio_net/config +++ b/tools/testing/selftests/drivers/net/virtio_net/config @@ -1,2 +1,8 @@ -CONFIG_VIRTIO_NET=y +CONFIG_BPF_SYSCALL=y +CONFIG_CGROUP_BPF=y +CONFIG_IPV6=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_NET_L3_MASTER_DEV=y +CONFIG_NET_VRF=m CONFIG_VIRTIO_DEBUG=y +CONFIG_VIRTIO_NET=y diff --git a/tools/testing/selftests/fchmodat2/Makefile b/tools/testing/selftests/fchmodat2/Makefile index 71ec34bf1501..4373cea79b79 100644 --- a/tools/testing/selftests/fchmodat2/Makefile +++ b/tools/testing/selftests/fchmodat2/Makefile @@ -1,6 +1,15 @@ # SPDX-License-Identifier: GPL-2.0-or-later -CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined -static-libasan $(KHDR_INCLUDES) +CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined $(KHDR_INCLUDES) + +# gcc requires -static-libasan in order to ensure that Address Sanitizer's +# library is the first one loaded. However, clang already statically links the +# Address Sanitizer if -fsanitize is specified. Therefore, simply omit +# -static-libasan for clang builds. +ifeq ($(LLVM),) + CFLAGS += -static-libasan +endif + TEST_GEN_PROGS := fchmodat2_test include ../lib.mk diff --git a/tools/testing/selftests/filesystems/statmount/statmount_test.c b/tools/testing/selftests/filesystems/statmount/statmount_test.c index e6d7c4f1c85b..e8c019d72cbf 100644 --- a/tools/testing/selftests/filesystems/statmount/statmount_test.c +++ b/tools/testing/selftests/filesystems/statmount/statmount_test.c @@ -125,8 +125,16 @@ static uint32_t old_root_id, old_parent_id; static void cleanup_namespace(void) { - fchdir(orig_root); - chroot("."); + int ret; + + ret = fchdir(orig_root); + if (ret == -1) + ksft_perror("fchdir to original root"); + + ret = chroot("."); + if (ret == -1) + ksft_perror("chroot to original root"); + umount2(root_mntpoint, MNT_DETACH); rmdir(root_mntpoint); } diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index ce8ff8e8ce3a..ac280dcba996 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -183,6 +183,7 @@ TEST_GEN_PROGS_s390x += s390x/sync_regs_test TEST_GEN_PROGS_s390x += s390x/tprot TEST_GEN_PROGS_s390x += s390x/cmma_test TEST_GEN_PROGS_s390x += s390x/debug_test +TEST_GEN_PROGS_s390x += s390x/shared_zeropage_test TEST_GEN_PROGS_s390x += demand_paging_test TEST_GEN_PROGS_s390x += dirty_log_test TEST_GEN_PROGS_s390x += guest_print_test diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 8eb57de0b587..c0c7c1fe93f9 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -277,6 +277,7 @@ struct kvm_x86_cpu_property { #define X86_PROPERTY_MAX_EXT_LEAF KVM_X86_CPU_PROPERTY(0x80000000, 0, EAX, 0, 31) #define X86_PROPERTY_MAX_PHY_ADDR KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 0, 7) #define X86_PROPERTY_MAX_VIRT_ADDR KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 8, 15) +#define X86_PROPERTY_GUEST_MAX_PHY_ADDR KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 16, 23) #define X86_PROPERTY_SEV_C_BIT KVM_X86_CPU_PROPERTY(0x8000001F, 0, EBX, 0, 5) #define X86_PROPERTY_PHYS_ADDR_REDUCTION KVM_X86_CPU_PROPERTY(0x8000001F, 0, EBX, 6, 11) diff --git a/tools/testing/selftests/kvm/lib/riscv/ucall.c b/tools/testing/selftests/kvm/lib/riscv/ucall.c index 14ee17151a59..b5035c63d516 100644 --- a/tools/testing/selftests/kvm/lib/riscv/ucall.c +++ b/tools/testing/selftests/kvm/lib/riscv/ucall.c @@ -9,6 +9,7 @@ #include "kvm_util.h" #include "processor.h" +#include "sbi.h" void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu) { diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index c664e446136b..594b061aef52 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -1247,9 +1247,20 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm) { const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */ unsigned long ht_gfn, max_gfn, max_pfn; - uint8_t maxphyaddr; + uint8_t maxphyaddr, guest_maxphyaddr; - max_gfn = (1ULL << (vm->pa_bits - vm->page_shift)) - 1; + /* + * Use "guest MAXPHYADDR" from KVM if it's available. Guest MAXPHYADDR + * enumerates the max _mappable_ GPA, which can be less than the raw + * MAXPHYADDR, e.g. if MAXPHYADDR=52, KVM is using TDP, and the CPU + * doesn't support 5-level TDP. + */ + guest_maxphyaddr = kvm_cpu_property(X86_PROPERTY_GUEST_MAX_PHY_ADDR); + guest_maxphyaddr = guest_maxphyaddr ?: vm->pa_bits; + TEST_ASSERT(guest_maxphyaddr <= vm->pa_bits, + "Guest MAXPHYADDR should never be greater than raw MAXPHYADDR"); + + max_gfn = (1ULL << (guest_maxphyaddr - vm->page_shift)) - 1; /* Avoid reserved HyperTransport region on AMD processors. */ if (!host_cpu_is_amd) diff --git a/tools/testing/selftests/kvm/riscv/ebreak_test.c b/tools/testing/selftests/kvm/riscv/ebreak_test.c index 823c132069b4..0e0712854953 100644 --- a/tools/testing/selftests/kvm/riscv/ebreak_test.c +++ b/tools/testing/selftests/kvm/riscv/ebreak_test.c @@ -6,6 +6,7 @@ * */ #include "kvm_util.h" +#include "ucall_common.h" #define LABEL_ADDRESS(v) ((uint64_t)&(v)) diff --git a/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c b/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c index 69bb94e6b227..f299cbfd23ca 100644 --- a/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c +++ b/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c @@ -15,6 +15,7 @@ #include "processor.h" #include "sbi.h" #include "arch_timer.h" +#include "ucall_common.h" /* Maximum counters(firmware + hardware) */ #define RISCV_MAX_PMU_COUNTERS 64 diff --git a/tools/testing/selftests/kvm/s390x/shared_zeropage_test.c b/tools/testing/selftests/kvm/s390x/shared_zeropage_test.c new file mode 100644 index 000000000000..bba0d9a6dcc8 --- /dev/null +++ b/tools/testing/selftests/kvm/s390x/shared_zeropage_test.c @@ -0,0 +1,111 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Test shared zeropage handling (with/without storage keys) + * + * Copyright (C) 2024, Red Hat, Inc. + */ +#include <sys/mman.h> + +#include <linux/fs.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "kselftest.h" +#include "ucall_common.h" + +static void set_storage_key(void *addr, uint8_t skey) +{ + asm volatile("sske %0,%1" : : "d" (skey), "a" (addr)); +} + +static void guest_code(void) +{ + /* Issue some storage key instruction. */ + set_storage_key((void *)0, 0x98); + GUEST_DONE(); +} + +/* + * Returns 1 if the shared zeropage is mapped, 0 if something else is mapped. + * Returns < 0 on error or if nothing is mapped. + */ +static int maps_shared_zeropage(int pagemap_fd, void *addr) +{ + struct page_region region; + struct pm_scan_arg arg = { + .start = (uintptr_t)addr, + .end = (uintptr_t)addr + 4096, + .vec = (uintptr_t)®ion, + .vec_len = 1, + .size = sizeof(struct pm_scan_arg), + .category_mask = PAGE_IS_PFNZERO, + .category_anyof_mask = PAGE_IS_PRESENT, + .return_mask = PAGE_IS_PFNZERO, + }; + return ioctl(pagemap_fd, PAGEMAP_SCAN, &arg); +} + +int main(int argc, char *argv[]) +{ + char *mem, *page0, *page1, *page2, tmp; + const size_t pagesize = getpagesize(); + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct ucall uc; + int pagemap_fd; + + ksft_print_header(); + ksft_set_plan(3); + + /* + * We'll use memory that is not mapped into the VM for simplicity. + * Shared zeropages are enabled/disabled per-process. + */ + mem = mmap(0, 3 * pagesize, PROT_READ, MAP_PRIVATE | MAP_ANON, -1, 0); + TEST_ASSERT(mem != MAP_FAILED, "mmap() failed"); + + /* Disable THP. Ignore errors on older kernels. */ + madvise(mem, 3 * pagesize, MADV_NOHUGEPAGE); + + page0 = mem; + page1 = page0 + pagesize; + page2 = page1 + pagesize; + + /* Can we even detect shared zeropages? */ + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + TEST_REQUIRE(pagemap_fd >= 0); + + tmp = *page0; + asm volatile("" : "+r" (tmp)); + TEST_REQUIRE(maps_shared_zeropage(pagemap_fd, page0) == 1); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + /* Verify that we get the shared zeropage after VM creation. */ + tmp = *page1; + asm volatile("" : "+r" (tmp)); + ksft_test_result(maps_shared_zeropage(pagemap_fd, page1) == 1, + "Shared zeropages should be enabled\n"); + + /* + * Let our VM execute a storage key instruction that should + * unshare all shared zeropages. + */ + vcpu_run(vcpu); + get_ucall(vcpu, &uc); + TEST_ASSERT_EQ(uc.cmd, UCALL_DONE); + + /* Verify that we don't have a shared zeropage anymore. */ + ksft_test_result(!maps_shared_zeropage(pagemap_fd, page1), + "Shared zeropage should be gone\n"); + + /* Verify that we don't get any new shared zeropages. */ + tmp = *page2; + asm volatile("" : "+r" (tmp)); + ksft_test_result(!maps_shared_zeropage(pagemap_fd, page2), + "Shared zeropages should be disabled\n"); + + kvm_vm_free(vm); + + ksft_finished(); +} diff --git a/tools/testing/selftests/kvm/x86_64/sev_init2_tests.c b/tools/testing/selftests/kvm/x86_64/sev_init2_tests.c index 7a4a61be119b..3fb967f40c6a 100644 --- a/tools/testing/selftests/kvm/x86_64/sev_init2_tests.c +++ b/tools/testing/selftests/kvm/x86_64/sev_init2_tests.c @@ -105,11 +105,11 @@ void test_features(uint32_t vm_type, uint64_t supported_features) int i; for (i = 0; i < 64; i++) { - if (!(supported_features & (1u << i))) + if (!(supported_features & BIT_ULL(i))) test_init2_invalid(vm_type, &(struct kvm_sev_init){ .vmsa_features = BIT_ULL(i) }, "unknown feature"); - else if (KNOWN_FEATURES & (1u << i)) + else if (KNOWN_FEATURES & BIT_ULL(i)) test_init2(vm_type, &(struct kvm_sev_init){ .vmsa_features = BIT_ULL(i) }); } diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c index 37de82da9be7..b61803e36d1c 100644 --- a/tools/testing/selftests/mm/ksm_functional_tests.c +++ b/tools/testing/selftests/mm/ksm_functional_tests.c @@ -656,12 +656,33 @@ unmap: munmap(map, size); } +static void init_global_file_handles(void) +{ + mem_fd = open("/proc/self/mem", O_RDWR); + if (mem_fd < 0) + ksft_exit_fail_msg("opening /proc/self/mem failed\n"); + ksm_fd = open("/sys/kernel/mm/ksm/run", O_RDWR); + if (ksm_fd < 0) + ksft_exit_skip("open(\"/sys/kernel/mm/ksm/run\") failed\n"); + ksm_full_scans_fd = open("/sys/kernel/mm/ksm/full_scans", O_RDONLY); + if (ksm_full_scans_fd < 0) + ksft_exit_skip("open(\"/sys/kernel/mm/ksm/full_scans\") failed\n"); + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + if (pagemap_fd < 0) + ksft_exit_skip("open(\"/proc/self/pagemap\") failed\n"); + proc_self_ksm_stat_fd = open("/proc/self/ksm_stat", O_RDONLY); + proc_self_ksm_merging_pages_fd = open("/proc/self/ksm_merging_pages", + O_RDONLY); + ksm_use_zero_pages_fd = open("/sys/kernel/mm/ksm/use_zero_pages", O_RDWR); +} + int main(int argc, char **argv) { unsigned int tests = 8; int err; if (argc > 1 && !strcmp(argv[1], FORK_EXEC_CHILD_PRG_NAME)) { + init_global_file_handles(); exit(test_child_ksm()); } @@ -674,22 +695,7 @@ int main(int argc, char **argv) pagesize = getpagesize(); - mem_fd = open("/proc/self/mem", O_RDWR); - if (mem_fd < 0) - ksft_exit_fail_msg("opening /proc/self/mem failed\n"); - ksm_fd = open("/sys/kernel/mm/ksm/run", O_RDWR); - if (ksm_fd < 0) - ksft_exit_skip("open(\"/sys/kernel/mm/ksm/run\") failed\n"); - ksm_full_scans_fd = open("/sys/kernel/mm/ksm/full_scans", O_RDONLY); - if (ksm_full_scans_fd < 0) - ksft_exit_skip("open(\"/sys/kernel/mm/ksm/full_scans\") failed\n"); - pagemap_fd = open("/proc/self/pagemap", O_RDONLY); - if (pagemap_fd < 0) - ksft_exit_skip("open(\"/proc/self/pagemap\") failed\n"); - proc_self_ksm_stat_fd = open("/proc/self/ksm_stat", O_RDONLY); - proc_self_ksm_merging_pages_fd = open("/proc/self/ksm_merging_pages", - O_RDONLY); - ksm_use_zero_pages_fd = open("/sys/kernel/mm/ksm/use_zero_pages", O_RDWR); + init_global_file_handles(); test_unmerge(); test_unmerge_zero_pages(); diff --git a/tools/testing/selftests/mm/map_fixed_noreplace.c b/tools/testing/selftests/mm/map_fixed_noreplace.c index b74813fdc951..d53de2486080 100644 --- a/tools/testing/selftests/mm/map_fixed_noreplace.c +++ b/tools/testing/selftests/mm/map_fixed_noreplace.c @@ -67,7 +67,8 @@ int main(void) dump_maps(); ksft_exit_fail_msg("Error: munmap failed!?\n"); } - ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() 5*PAGE_SIZE at base\n"); addr = base_addr + page_size; size = 3 * page_size; @@ -76,7 +77,8 @@ int main(void) dump_maps(); ksft_exit_fail_msg("Error: first mmap() failed unexpectedly\n"); } - ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() 3*PAGE_SIZE at base+PAGE_SIZE\n"); /* * Exact same mapping again: @@ -93,7 +95,8 @@ int main(void) dump_maps(); ksft_exit_fail_msg("Error:1: mmap() succeeded when it shouldn't have\n"); } - ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() 5*PAGE_SIZE at base\n"); /* * Second mapping contained within first: @@ -111,7 +114,8 @@ int main(void) dump_maps(); ksft_exit_fail_msg("Error:2: mmap() succeeded when it shouldn't have\n"); } - ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() 2*PAGE_SIZE at base+PAGE_SIZE\n"); /* * Overlap end of existing mapping: @@ -128,7 +132,8 @@ int main(void) dump_maps(); ksft_exit_fail_msg("Error:3: mmap() succeeded when it shouldn't have\n"); } - ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() 2*PAGE_SIZE at base+(3*PAGE_SIZE)\n"); /* * Overlap start of existing mapping: @@ -145,7 +150,8 @@ int main(void) dump_maps(); ksft_exit_fail_msg("Error:4: mmap() succeeded when it shouldn't have\n"); } - ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() 2*PAGE_SIZE bytes at base\n"); /* * Adjacent to start of existing mapping: @@ -162,7 +168,8 @@ int main(void) dump_maps(); ksft_exit_fail_msg("Error:5: mmap() failed when it shouldn't have\n"); } - ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() PAGE_SIZE at base\n"); /* * Adjacent to end of existing mapping: @@ -179,7 +186,8 @@ int main(void) dump_maps(); ksft_exit_fail_msg("Error:6: mmap() failed when it shouldn't have\n"); } - ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() PAGE_SIZE at base+(4*PAGE_SIZE)\n"); addr = base_addr; size = 5 * page_size; diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 49a56eb5d036..666ab7d9390b 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -43,7 +43,6 @@ tap tcp_fastopen_backup_key tcp_inq tcp_mmap -test_unix_oob timestamping tls toeplitz diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 6da63d1831c1..bc3925200637 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -43,6 +43,8 @@ TEST_PROGS += srv6_hl2encap_red_l2vpn_test.sh TEST_PROGS += srv6_end_next_csid_l3vpn_test.sh TEST_PROGS += srv6_end_x_next_csid_l3vpn_test.sh TEST_PROGS += srv6_end_flavors_test.sh +TEST_PROGS += srv6_end_dx4_netfilter_test.sh +TEST_PROGS += srv6_end_dx6_netfilter_test.sh TEST_PROGS += vrf_strict_mode_test.sh TEST_PROGS += arp_ndisc_evict_nocarrier.sh TEST_PROGS += ndisc_unsolicited_na_test.sh diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index 3b83c797650d..50584479540b 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -1,4 +1,4 @@ CFLAGS += $(KHDR_INCLUDES) -TEST_GEN_PROGS := diag_uid test_unix_oob unix_connect scm_pidfd scm_rights +TEST_GEN_PROGS := diag_uid msg_oob scm_pidfd scm_rights unix_connect include ../../lib.mk diff --git a/tools/testing/selftests/net/af_unix/config b/tools/testing/selftests/net/af_unix/config new file mode 100644 index 000000000000..37368567768c --- /dev/null +++ b/tools/testing/selftests/net/af_unix/config @@ -0,0 +1,3 @@ +CONFIG_UNIX=y +CONFIG_AF_UNIX_OOB=y +CONFIG_UNIX_DIAG=m diff --git a/tools/testing/selftests/net/af_unix/msg_oob.c b/tools/testing/selftests/net/af_unix/msg_oob.c new file mode 100644 index 000000000000..16d0c172eaeb --- /dev/null +++ b/tools/testing/selftests/net/af_unix/msg_oob.c @@ -0,0 +1,734 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Amazon.com Inc. or its affiliates. */ + +#include <fcntl.h> +#include <string.h> +#include <unistd.h> + +#include <netinet/in.h> +#include <sys/epoll.h> +#include <sys/ioctl.h> +#include <sys/signalfd.h> +#include <sys/socket.h> + +#include "../../kselftest_harness.h" + +#define BUF_SZ 32 + +FIXTURE(msg_oob) +{ + int fd[4]; /* 0: AF_UNIX sender + * 1: AF_UNIX receiver + * 2: TCP sender + * 3: TCP receiver + */ + int signal_fd; + int epoll_fd[2]; /* 0: AF_UNIX receiver + * 1: TCP receiver + */ + bool tcp_compliant; +}; + +FIXTURE_VARIANT(msg_oob) +{ + bool peek; +}; + +FIXTURE_VARIANT_ADD(msg_oob, no_peek) +{ + .peek = false, +}; + +FIXTURE_VARIANT_ADD(msg_oob, peek) +{ + .peek = true +}; + +static void create_unix_socketpair(struct __test_metadata *_metadata, + FIXTURE_DATA(msg_oob) *self) +{ + int ret; + + ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_NONBLOCK, 0, self->fd); + ASSERT_EQ(ret, 0); +} + +static void create_tcp_socketpair(struct __test_metadata *_metadata, + FIXTURE_DATA(msg_oob) *self) +{ + struct sockaddr_in addr; + socklen_t addrlen; + int listen_fd; + int ret; + + listen_fd = socket(AF_INET, SOCK_STREAM, 0); + ASSERT_GE(listen_fd, 0); + + ret = listen(listen_fd, -1); + ASSERT_EQ(ret, 0); + + addrlen = sizeof(addr); + ret = getsockname(listen_fd, (struct sockaddr *)&addr, &addrlen); + ASSERT_EQ(ret, 0); + + self->fd[2] = socket(AF_INET, SOCK_STREAM, 0); + ASSERT_GE(self->fd[2], 0); + + ret = connect(self->fd[2], (struct sockaddr *)&addr, addrlen); + ASSERT_EQ(ret, 0); + + self->fd[3] = accept(listen_fd, (struct sockaddr *)&addr, &addrlen); + ASSERT_GE(self->fd[3], 0); + + ret = fcntl(self->fd[3], F_SETFL, O_NONBLOCK); + ASSERT_EQ(ret, 0); +} + +static void setup_sigurg(struct __test_metadata *_metadata, + FIXTURE_DATA(msg_oob) *self) +{ + struct signalfd_siginfo siginfo; + int pid = getpid(); + sigset_t mask; + int i, ret; + + for (i = 0; i < 2; i++) { + ret = ioctl(self->fd[i * 2 + 1], FIOSETOWN, &pid); + ASSERT_EQ(ret, 0); + } + + ret = sigemptyset(&mask); + ASSERT_EQ(ret, 0); + + ret = sigaddset(&mask, SIGURG); + ASSERT_EQ(ret, 0); + + ret = sigprocmask(SIG_BLOCK, &mask, NULL); + ASSERT_EQ(ret, 0); + + self->signal_fd = signalfd(-1, &mask, SFD_NONBLOCK); + ASSERT_GE(self->signal_fd, 0); + + ret = read(self->signal_fd, &siginfo, sizeof(siginfo)); + ASSERT_EQ(ret, -1); +} + +static void setup_epollpri(struct __test_metadata *_metadata, + FIXTURE_DATA(msg_oob) *self) +{ + struct epoll_event event = { + .events = EPOLLPRI, + }; + int i; + + for (i = 0; i < 2; i++) { + int ret; + + self->epoll_fd[i] = epoll_create1(0); + ASSERT_GE(self->epoll_fd[i], 0); + + ret = epoll_ctl(self->epoll_fd[i], EPOLL_CTL_ADD, self->fd[i * 2 + 1], &event); + ASSERT_EQ(ret, 0); + } +} + +static void close_sockets(FIXTURE_DATA(msg_oob) *self) +{ + int i; + + for (i = 0; i < 4; i++) + close(self->fd[i]); +} + +FIXTURE_SETUP(msg_oob) +{ + create_unix_socketpair(_metadata, self); + create_tcp_socketpair(_metadata, self); + + setup_sigurg(_metadata, self); + setup_epollpri(_metadata, self); + + self->tcp_compliant = true; +} + +FIXTURE_TEARDOWN(msg_oob) +{ + close_sockets(self); +} + +static void __epollpair(struct __test_metadata *_metadata, + FIXTURE_DATA(msg_oob) *self, + bool oob_remaining) +{ + struct epoll_event event[2] = {}; + int i, ret[2]; + + for (i = 0; i < 2; i++) + ret[i] = epoll_wait(self->epoll_fd[i], &event[i], 1, 0); + + ASSERT_EQ(ret[0], oob_remaining); + + if (self->tcp_compliant) + ASSERT_EQ(ret[0], ret[1]); + + if (oob_remaining) { + ASSERT_EQ(event[0].events, EPOLLPRI); + + if (self->tcp_compliant) + ASSERT_EQ(event[0].events, event[1].events); + } +} + +static void __sendpair(struct __test_metadata *_metadata, + FIXTURE_DATA(msg_oob) *self, + const void *buf, size_t len, int flags) +{ + int i, ret[2]; + + for (i = 0; i < 2; i++) { + struct signalfd_siginfo siginfo = {}; + int bytes; + + ret[i] = send(self->fd[i * 2], buf, len, flags); + + bytes = read(self->signal_fd, &siginfo, sizeof(siginfo)); + + if (flags & MSG_OOB) { + ASSERT_EQ(bytes, sizeof(siginfo)); + ASSERT_EQ(siginfo.ssi_signo, SIGURG); + + bytes = read(self->signal_fd, &siginfo, sizeof(siginfo)); + } + + ASSERT_EQ(bytes, -1); + } + + ASSERT_EQ(ret[0], len); + ASSERT_EQ(ret[0], ret[1]); +} + +static void __recvpair(struct __test_metadata *_metadata, + FIXTURE_DATA(msg_oob) *self, + const void *expected_buf, int expected_len, + int buf_len, int flags) +{ + int i, ret[2], recv_errno[2], expected_errno = 0; + char recv_buf[2][BUF_SZ] = {}; + bool printed = false; + + ASSERT_GE(BUF_SZ, buf_len); + + errno = 0; + + for (i = 0; i < 2; i++) { + ret[i] = recv(self->fd[i * 2 + 1], recv_buf[i], buf_len, flags); + recv_errno[i] = errno; + } + + if (expected_len < 0) { + expected_errno = -expected_len; + expected_len = -1; + } + + if (ret[0] != expected_len || recv_errno[0] != expected_errno) { + TH_LOG("AF_UNIX :%s", ret[0] < 0 ? strerror(recv_errno[0]) : recv_buf[0]); + TH_LOG("Expected:%s", expected_errno ? strerror(expected_errno) : expected_buf); + + ASSERT_EQ(ret[0], expected_len); + ASSERT_EQ(recv_errno[0], expected_errno); + } + + if (ret[0] != ret[1] || recv_errno[0] != recv_errno[1]) { + TH_LOG("AF_UNIX :%s", ret[0] < 0 ? strerror(recv_errno[0]) : recv_buf[0]); + TH_LOG("TCP :%s", ret[1] < 0 ? strerror(recv_errno[1]) : recv_buf[1]); + + printed = true; + + if (self->tcp_compliant) { + ASSERT_EQ(ret[0], ret[1]); + ASSERT_EQ(recv_errno[0], recv_errno[1]); + } + } + + if (expected_len >= 0) { + int cmp; + + cmp = strncmp(expected_buf, recv_buf[0], expected_len); + if (cmp) { + TH_LOG("AF_UNIX :%s", ret[0] < 0 ? strerror(recv_errno[0]) : recv_buf[0]); + TH_LOG("Expected:%s", expected_errno ? strerror(expected_errno) : expected_buf); + + ASSERT_EQ(cmp, 0); + } + + cmp = strncmp(recv_buf[0], recv_buf[1], expected_len); + if (cmp) { + if (!printed) { + TH_LOG("AF_UNIX :%s", ret[0] < 0 ? strerror(recv_errno[0]) : recv_buf[0]); + TH_LOG("TCP :%s", ret[1] < 0 ? strerror(recv_errno[1]) : recv_buf[1]); + } + + if (self->tcp_compliant) + ASSERT_EQ(cmp, 0); + } + } +} + +static void __setinlinepair(struct __test_metadata *_metadata, + FIXTURE_DATA(msg_oob) *self) +{ + int i, oob_inline = 1; + + for (i = 0; i < 2; i++) { + int ret; + + ret = setsockopt(self->fd[i * 2 + 1], SOL_SOCKET, SO_OOBINLINE, + &oob_inline, sizeof(oob_inline)); + ASSERT_EQ(ret, 0); + } +} + +static void __siocatmarkpair(struct __test_metadata *_metadata, + FIXTURE_DATA(msg_oob) *self, + bool oob_head) +{ + int answ[2] = {}; + int i; + + for (i = 0; i < 2; i++) { + int ret; + + ret = ioctl(self->fd[i * 2 + 1], SIOCATMARK, &answ[i]); + ASSERT_EQ(ret, 0); + } + + ASSERT_EQ(answ[0], oob_head); + + if (self->tcp_compliant) + ASSERT_EQ(answ[0], answ[1]); +} + +#define sendpair(buf, len, flags) \ + __sendpair(_metadata, self, buf, len, flags) + +#define recvpair(expected_buf, expected_len, buf_len, flags) \ + do { \ + if (variant->peek) \ + __recvpair(_metadata, self, \ + expected_buf, expected_len, \ + buf_len, (flags) | MSG_PEEK); \ + __recvpair(_metadata, self, \ + expected_buf, expected_len, buf_len, flags); \ + } while (0) + +#define epollpair(oob_remaining) \ + __epollpair(_metadata, self, oob_remaining) + +#define siocatmarkpair(oob_head) \ + __siocatmarkpair(_metadata, self, oob_head) + +#define setinlinepair() \ + __setinlinepair(_metadata, self) + +#define tcp_incompliant \ + for (self->tcp_compliant = false; \ + self->tcp_compliant == false; \ + self->tcp_compliant = true) + +TEST_F(msg_oob, non_oob) +{ + sendpair("x", 1, 0); + epollpair(false); + siocatmarkpair(false); + + recvpair("", -EINVAL, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(false); +} + +TEST_F(msg_oob, oob) +{ + sendpair("x", 1, MSG_OOB); + epollpair(true); + siocatmarkpair(true); + + recvpair("x", 1, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(true); +} + +TEST_F(msg_oob, oob_drop) +{ + sendpair("x", 1, MSG_OOB); + epollpair(true); + siocatmarkpair(true); + + recvpair("", -EAGAIN, 1, 0); /* Drop OOB. */ + epollpair(false); + siocatmarkpair(false); + + recvpair("", -EINVAL, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(false); +} + +TEST_F(msg_oob, oob_ahead) +{ + sendpair("hello", 5, MSG_OOB); + epollpair(true); + siocatmarkpair(false); + + recvpair("o", 1, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(false); + + recvpair("hell", 4, 4, 0); + epollpair(false); + siocatmarkpair(true); +} + +TEST_F(msg_oob, oob_break) +{ + sendpair("hello", 5, MSG_OOB); + epollpair(true); + siocatmarkpair(false); + + recvpair("hell", 4, 5, 0); /* Break at OOB even with enough buffer. */ + epollpair(true); + siocatmarkpair(true); + + recvpair("o", 1, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(true); + + recvpair("", -EAGAIN, 1, 0); + siocatmarkpair(false); +} + +TEST_F(msg_oob, oob_ahead_break) +{ + sendpair("hello", 5, MSG_OOB); + epollpair(true); + siocatmarkpair(false); + + sendpair("world", 5, 0); + epollpair(true); + siocatmarkpair(false); + + recvpair("o", 1, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(false); + + recvpair("hell", 4, 9, 0); /* Break at OOB even after it's recv()ed. */ + epollpair(false); + siocatmarkpair(true); + + recvpair("world", 5, 5, 0); + epollpair(false); + siocatmarkpair(false); +} + +TEST_F(msg_oob, oob_break_drop) +{ + sendpair("hello", 5, MSG_OOB); + epollpair(true); + siocatmarkpair(false); + + sendpair("world", 5, 0); + epollpair(true); + siocatmarkpair(false); + + recvpair("hell", 4, 10, 0); /* Break at OOB even with enough buffer. */ + epollpair(true); + siocatmarkpair(true); + + recvpair("world", 5, 10, 0); /* Drop OOB and recv() the next skb. */ + epollpair(false); + siocatmarkpair(false); + + recvpair("", -EINVAL, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(false); +} + +TEST_F(msg_oob, ex_oob_break) +{ + sendpair("hello", 5, MSG_OOB); + epollpair(true); + siocatmarkpair(false); + + sendpair("wor", 3, MSG_OOB); + epollpair(true); + siocatmarkpair(false); + + sendpair("ld", 2, 0); + epollpair(true); + siocatmarkpair(false); + + recvpair("hellowo", 7, 10, 0); /* Break at OOB but not at ex-OOB. */ + epollpair(true); + siocatmarkpair(true); + + recvpair("r", 1, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(true); + + recvpair("ld", 2, 2, 0); + epollpair(false); + siocatmarkpair(false); +} + +TEST_F(msg_oob, ex_oob_drop) +{ + sendpair("x", 1, MSG_OOB); + epollpair(true); + siocatmarkpair(true); + + sendpair("y", 1, MSG_OOB); /* TCP drops "x" at this moment. */ + epollpair(true); + + tcp_incompliant { + siocatmarkpair(false); + + recvpair("x", 1, 1, 0); /* TCP drops "y" by passing through it. */ + epollpair(true); + siocatmarkpair(true); + + recvpair("y", 1, 1, MSG_OOB); /* TCP returns -EINVAL. */ + epollpair(false); + siocatmarkpair(true); + } +} + +TEST_F(msg_oob, ex_oob_drop_2) +{ + sendpair("x", 1, MSG_OOB); + epollpair(true); + siocatmarkpair(true); + + sendpair("y", 1, MSG_OOB); /* TCP drops "x" at this moment. */ + epollpair(true); + + tcp_incompliant { + siocatmarkpair(false); + } + + recvpair("y", 1, 1, MSG_OOB); + epollpair(false); + + tcp_incompliant { + siocatmarkpair(false); + + recvpair("x", 1, 1, 0); /* TCP returns -EAGAIN. */ + epollpair(false); + siocatmarkpair(true); + } +} + +TEST_F(msg_oob, ex_oob_ahead_break) +{ + sendpair("hello", 5, MSG_OOB); + epollpair(true); + siocatmarkpair(false); + + sendpair("wor", 3, MSG_OOB); + epollpair(true); + siocatmarkpair(false); + + recvpair("r", 1, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(false); + + sendpair("ld", 2, MSG_OOB); + epollpair(true); + siocatmarkpair(false); + + tcp_incompliant { + recvpair("hellowol", 8, 10, 0); /* TCP recv()s "helloworl", why "r" ?? */ + } + + epollpair(true); + siocatmarkpair(true); + + recvpair("d", 1, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(true); +} + +TEST_F(msg_oob, ex_oob_siocatmark) +{ + sendpair("hello", 5, MSG_OOB); + epollpair(true); + siocatmarkpair(false); + + recvpair("o", 1, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(false); + + sendpair("world", 5, MSG_OOB); + epollpair(true); + siocatmarkpair(false); + + recvpair("hell", 4, 4, 0); /* Intentionally stop at ex-OOB. */ + epollpair(true); + siocatmarkpair(false); +} + +TEST_F(msg_oob, inline_oob) +{ + setinlinepair(); + + sendpair("x", 1, MSG_OOB); + epollpair(true); + siocatmarkpair(true); + + recvpair("", -EINVAL, 1, MSG_OOB); + epollpair(true); + siocatmarkpair(true); + + recvpair("x", 1, 1, 0); + epollpair(false); + siocatmarkpair(false); +} + +TEST_F(msg_oob, inline_oob_break) +{ + setinlinepair(); + + sendpair("hello", 5, MSG_OOB); + epollpair(true); + siocatmarkpair(false); + + recvpair("", -EINVAL, 1, MSG_OOB); + epollpair(true); + siocatmarkpair(false); + + recvpair("hell", 4, 5, 0); /* Break at OOB but not at ex-OOB. */ + epollpair(true); + siocatmarkpair(true); + + recvpair("o", 1, 1, 0); + epollpair(false); + siocatmarkpair(false); +} + +TEST_F(msg_oob, inline_oob_ahead_break) +{ + sendpair("hello", 5, MSG_OOB); + epollpair(true); + siocatmarkpair(false); + + sendpair("world", 5, 0); + epollpair(true); + siocatmarkpair(false); + + recvpair("o", 1, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(false); + + setinlinepair(); + + recvpair("hell", 4, 9, 0); /* Break at OOB even with enough buffer. */ + epollpair(false); + siocatmarkpair(true); + + tcp_incompliant { + recvpair("world", 5, 6, 0); /* TCP recv()s "oworld", ... "o" ??? */ + } + + epollpair(false); + siocatmarkpair(false); +} + +TEST_F(msg_oob, inline_ex_oob_break) +{ + sendpair("hello", 5, MSG_OOB); + epollpair(true); + siocatmarkpair(false); + + sendpair("wor", 3, MSG_OOB); + epollpair(true); + siocatmarkpair(false); + + sendpair("ld", 2, 0); + epollpair(true); + siocatmarkpair(false); + + setinlinepair(); + + recvpair("hellowo", 7, 10, 0); /* Break at OOB but not at ex-OOB. */ + epollpair(true); + siocatmarkpair(true); + + recvpair("rld", 3, 3, 0); + epollpair(false); + siocatmarkpair(false); +} + +TEST_F(msg_oob, inline_ex_oob_no_drop) +{ + sendpair("x", 1, MSG_OOB); + epollpair(true); + siocatmarkpair(true); + + setinlinepair(); + + sendpair("y", 1, MSG_OOB); /* TCP does NOT drops "x" at this moment. */ + epollpair(true); + siocatmarkpair(false); + + recvpair("x", 1, 1, 0); + epollpair(true); + siocatmarkpair(true); + + recvpair("y", 1, 1, 0); + epollpair(false); + siocatmarkpair(false); +} + +TEST_F(msg_oob, inline_ex_oob_drop) +{ + sendpair("x", 1, MSG_OOB); + epollpair(true); + siocatmarkpair(true); + + sendpair("y", 1, MSG_OOB); /* TCP drops "x" at this moment. */ + epollpair(true); + + setinlinepair(); + + tcp_incompliant { + siocatmarkpair(false); + + recvpair("x", 1, 1, 0); /* TCP recv()s "y". */ + epollpair(true); + siocatmarkpair(true); + + recvpair("y", 1, 1, 0); /* TCP returns -EAGAIN. */ + epollpair(false); + siocatmarkpair(false); + } +} + +TEST_F(msg_oob, inline_ex_oob_siocatmark) +{ + sendpair("hello", 5, MSG_OOB); + epollpair(true); + siocatmarkpair(false); + + recvpair("o", 1, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(false); + + setinlinepair(); + + sendpair("world", 5, MSG_OOB); + epollpair(true); + siocatmarkpair(false); + + recvpair("hell", 4, 4, 0); /* Intentionally stop at ex-OOB. */ + epollpair(true); + siocatmarkpair(false); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/af_unix/test_unix_oob.c b/tools/testing/selftests/net/af_unix/test_unix_oob.c deleted file mode 100644 index a7c51889acd5..000000000000 --- a/tools/testing/selftests/net/af_unix/test_unix_oob.c +++ /dev/null @@ -1,436 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -#include <stdio.h> -#include <stdlib.h> -#include <sys/socket.h> -#include <arpa/inet.h> -#include <unistd.h> -#include <string.h> -#include <fcntl.h> -#include <sys/ioctl.h> -#include <errno.h> -#include <netinet/tcp.h> -#include <sys/un.h> -#include <sys/signal.h> -#include <sys/poll.h> - -static int pipefd[2]; -static int signal_recvd; -static pid_t producer_id; -static char sock_name[32]; - -static void sig_hand(int sn, siginfo_t *si, void *p) -{ - signal_recvd = sn; -} - -static int set_sig_handler(int signal) -{ - struct sigaction sa; - - sa.sa_sigaction = sig_hand; - sigemptyset(&sa.sa_mask); - sa.sa_flags = SA_SIGINFO | SA_RESTART; - - return sigaction(signal, &sa, NULL); -} - -static void set_filemode(int fd, int set) -{ - int flags = fcntl(fd, F_GETFL, 0); - - if (set) - flags &= ~O_NONBLOCK; - else - flags |= O_NONBLOCK; - fcntl(fd, F_SETFL, flags); -} - -static void signal_producer(int fd) -{ - char cmd; - - cmd = 'S'; - write(fd, &cmd, sizeof(cmd)); -} - -static void wait_for_signal(int fd) -{ - char buf[5]; - - read(fd, buf, 5); -} - -static void die(int status) -{ - fflush(NULL); - unlink(sock_name); - kill(producer_id, SIGTERM); - exit(status); -} - -int is_sioctatmark(int fd) -{ - int ans = -1; - - if (ioctl(fd, SIOCATMARK, &ans, sizeof(ans)) < 0) { -#ifdef DEBUG - perror("SIOCATMARK Failed"); -#endif - } - return ans; -} - -void read_oob(int fd, char *c) -{ - - *c = ' '; - if (recv(fd, c, sizeof(*c), MSG_OOB) < 0) { -#ifdef DEBUG - perror("Reading MSG_OOB Failed"); -#endif - } -} - -int read_data(int pfd, char *buf, int size) -{ - int len = 0; - - memset(buf, size, '0'); - len = read(pfd, buf, size); -#ifdef DEBUG - if (len < 0) - perror("read failed"); -#endif - return len; -} - -static void wait_for_data(int pfd, int event) -{ - struct pollfd pfds[1]; - - pfds[0].fd = pfd; - pfds[0].events = event; - poll(pfds, 1, -1); -} - -void producer(struct sockaddr_un *consumer_addr) -{ - int cfd; - char buf[64]; - int i; - - memset(buf, 'x', sizeof(buf)); - cfd = socket(AF_UNIX, SOCK_STREAM, 0); - - wait_for_signal(pipefd[0]); - if (connect(cfd, (struct sockaddr *)consumer_addr, - sizeof(*consumer_addr)) != 0) { - perror("Connect failed"); - kill(0, SIGTERM); - exit(1); - } - - for (i = 0; i < 2; i++) { - /* Test 1: Test for SIGURG and OOB */ - wait_for_signal(pipefd[0]); - memset(buf, 'x', sizeof(buf)); - buf[63] = '@'; - send(cfd, buf, sizeof(buf), MSG_OOB); - - wait_for_signal(pipefd[0]); - - /* Test 2: Test for OOB being overwitten */ - memset(buf, 'x', sizeof(buf)); - buf[63] = '%'; - send(cfd, buf, sizeof(buf), MSG_OOB); - - memset(buf, 'x', sizeof(buf)); - buf[63] = '#'; - send(cfd, buf, sizeof(buf), MSG_OOB); - - wait_for_signal(pipefd[0]); - - /* Test 3: Test for SIOCATMARK */ - memset(buf, 'x', sizeof(buf)); - buf[63] = '@'; - send(cfd, buf, sizeof(buf), MSG_OOB); - - memset(buf, 'x', sizeof(buf)); - buf[63] = '%'; - send(cfd, buf, sizeof(buf), MSG_OOB); - - memset(buf, 'x', sizeof(buf)); - send(cfd, buf, sizeof(buf), 0); - - wait_for_signal(pipefd[0]); - - /* Test 4: Test for 1byte OOB msg */ - memset(buf, 'x', sizeof(buf)); - buf[0] = '@'; - send(cfd, buf, 1, MSG_OOB); - } -} - -int -main(int argc, char **argv) -{ - int lfd, pfd; - struct sockaddr_un consumer_addr, paddr; - socklen_t len = sizeof(consumer_addr); - char buf[1024]; - int on = 0; - char oob; - int atmark; - - lfd = socket(AF_UNIX, SOCK_STREAM, 0); - memset(&consumer_addr, 0, sizeof(consumer_addr)); - consumer_addr.sun_family = AF_UNIX; - sprintf(sock_name, "unix_oob_%d", getpid()); - unlink(sock_name); - strcpy(consumer_addr.sun_path, sock_name); - - if ((bind(lfd, (struct sockaddr *)&consumer_addr, - sizeof(consumer_addr))) != 0) { - perror("socket bind failed"); - exit(1); - } - - pipe(pipefd); - - listen(lfd, 1); - - producer_id = fork(); - if (producer_id == 0) { - producer(&consumer_addr); - exit(0); - } - - set_sig_handler(SIGURG); - signal_producer(pipefd[1]); - - pfd = accept(lfd, (struct sockaddr *) &paddr, &len); - fcntl(pfd, F_SETOWN, getpid()); - - signal_recvd = 0; - signal_producer(pipefd[1]); - - /* Test 1: - * veriyf that SIGURG is - * delivered, 63 bytes are - * read, oob is '@', and POLLPRI works. - */ - wait_for_data(pfd, POLLPRI); - read_oob(pfd, &oob); - len = read_data(pfd, buf, 1024); - if (!signal_recvd || len != 63 || oob != '@') { - fprintf(stderr, "Test 1 failed sigurg %d len %d %c\n", - signal_recvd, len, oob); - die(1); - } - - signal_recvd = 0; - signal_producer(pipefd[1]); - - /* Test 2: - * Verify that the first OOB is over written by - * the 2nd one and the first OOB is returned as - * part of the read, and sigurg is received. - */ - wait_for_data(pfd, POLLIN | POLLPRI); - len = 0; - while (len < 70) - len = recv(pfd, buf, 1024, MSG_PEEK); - len = read_data(pfd, buf, 1024); - read_oob(pfd, &oob); - if (!signal_recvd || len != 127 || oob != '#') { - fprintf(stderr, "Test 2 failed, sigurg %d len %d OOB %c\n", - signal_recvd, len, oob); - die(1); - } - - signal_recvd = 0; - signal_producer(pipefd[1]); - - /* Test 3: - * verify that 2nd oob over writes - * the first one and read breaks at - * oob boundary returning 127 bytes - * and sigurg is received and atmark - * is set. - * oob is '%' and second read returns - * 64 bytes. - */ - len = 0; - wait_for_data(pfd, POLLIN | POLLPRI); - while (len < 150) - len = recv(pfd, buf, 1024, MSG_PEEK); - len = read_data(pfd, buf, 1024); - atmark = is_sioctatmark(pfd); - read_oob(pfd, &oob); - - if (!signal_recvd || len != 127 || oob != '%' || atmark != 1) { - fprintf(stderr, - "Test 3 failed, sigurg %d len %d OOB %c atmark %d\n", - signal_recvd, len, oob, atmark); - die(1); - } - - signal_recvd = 0; - - len = read_data(pfd, buf, 1024); - if (len != 64) { - fprintf(stderr, "Test 3.1 failed, sigurg %d len %d OOB %c\n", - signal_recvd, len, oob); - die(1); - } - - signal_recvd = 0; - signal_producer(pipefd[1]); - - /* Test 4: - * verify that a single byte - * oob message is delivered. - * set non blocking mode and - * check proper error is - * returned and sigurg is - * received and correct - * oob is read. - */ - - set_filemode(pfd, 0); - - wait_for_data(pfd, POLLIN | POLLPRI); - len = read_data(pfd, buf, 1024); - if ((len == -1) && (errno == 11)) - len = 0; - - read_oob(pfd, &oob); - - if (!signal_recvd || len != 0 || oob != '@') { - fprintf(stderr, "Test 4 failed, sigurg %d len %d OOB %c\n", - signal_recvd, len, oob); - die(1); - } - - set_filemode(pfd, 1); - - /* Inline Testing */ - - on = 1; - if (setsockopt(pfd, SOL_SOCKET, SO_OOBINLINE, &on, sizeof(on))) { - perror("SO_OOBINLINE"); - die(1); - } - - signal_recvd = 0; - signal_producer(pipefd[1]); - - /* Test 1 -- Inline: - * Check that SIGURG is - * delivered and 63 bytes are - * read and oob is '@' - */ - - wait_for_data(pfd, POLLIN | POLLPRI); - len = read_data(pfd, buf, 1024); - - if (!signal_recvd || len != 63) { - fprintf(stderr, "Test 1 Inline failed, sigurg %d len %d\n", - signal_recvd, len); - die(1); - } - - len = read_data(pfd, buf, 1024); - - if (len != 1) { - fprintf(stderr, - "Test 1.1 Inline failed, sigurg %d len %d oob %c\n", - signal_recvd, len, oob); - die(1); - } - - signal_recvd = 0; - signal_producer(pipefd[1]); - - /* Test 2 -- Inline: - * Verify that the first OOB is over written by - * the 2nd one and read breaks correctly on - * 2nd OOB boundary with the first OOB returned as - * part of the read, and sigurg is delivered and - * siocatmark returns true. - * next read returns one byte, the oob byte - * and siocatmark returns false. - */ - len = 0; - wait_for_data(pfd, POLLIN | POLLPRI); - while (len < 70) - len = recv(pfd, buf, 1024, MSG_PEEK); - len = read_data(pfd, buf, 1024); - atmark = is_sioctatmark(pfd); - if (len != 127 || atmark != 1 || !signal_recvd) { - fprintf(stderr, "Test 2 Inline failed, len %d atmark %d\n", - len, atmark); - die(1); - } - - len = read_data(pfd, buf, 1024); - atmark = is_sioctatmark(pfd); - if (len != 1 || buf[0] != '#' || atmark == 1) { - fprintf(stderr, "Test 2.1 Inline failed, len %d data %c atmark %d\n", - len, buf[0], atmark); - die(1); - } - - signal_recvd = 0; - signal_producer(pipefd[1]); - - /* Test 3 -- Inline: - * verify that 2nd oob over writes - * the first one and read breaks at - * oob boundary returning 127 bytes - * and sigurg is received and siocatmark - * is true after the read. - * subsequent read returns 65 bytes - * because of oob which should be '%'. - */ - len = 0; - wait_for_data(pfd, POLLIN | POLLPRI); - while (len < 126) - len = recv(pfd, buf, 1024, MSG_PEEK); - len = read_data(pfd, buf, 1024); - atmark = is_sioctatmark(pfd); - if (!signal_recvd || len != 127 || !atmark) { - fprintf(stderr, - "Test 3 Inline failed, sigurg %d len %d data %c\n", - signal_recvd, len, buf[0]); - die(1); - } - - len = read_data(pfd, buf, 1024); - atmark = is_sioctatmark(pfd); - if (len != 65 || buf[0] != '%' || atmark != 0) { - fprintf(stderr, - "Test 3.1 Inline failed, len %d oob %c atmark %d\n", - len, buf[0], atmark); - die(1); - } - - signal_recvd = 0; - signal_producer(pipefd[1]); - - /* Test 4 -- Inline: - * verify that a single - * byte oob message is delivered - * and read returns one byte, the oob - * byte and sigurg is received - */ - wait_for_data(pfd, POLLIN | POLLPRI); - len = read_data(pfd, buf, 1024); - if (!signal_recvd || len != 1 || buf[0] != '@') { - fprintf(stderr, - "Test 4 Inline failed, signal %d len %d data %c\n", - signal_recvd, len, buf[0]); - die(1); - } - die(0); -} diff --git a/tools/testing/selftests/net/amt.sh b/tools/testing/selftests/net/amt.sh index 7e7ed6c558da..d458b45c775b 100755 --- a/tools/testing/selftests/net/amt.sh +++ b/tools/testing/selftests/net/amt.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # Author: Taehee Yoo <[email protected]> diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 04de7a6ba6f3..f46e27cd1e70 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -26,7 +26,6 @@ CONFIG_INET_ESP=y CONFIG_INET_ESP_OFFLOAD=y CONFIG_NET_FOU=y CONFIG_NET_FOU_IP_TUNNELS=y -CONFIG_IP_GRE=m CONFIG_NETFILTER=y CONFIG_NETFILTER_ADVANCED=y CONFIG_NF_CONNTRACK=m @@ -101,3 +100,5 @@ CONFIG_NETFILTER_XT_MATCH_POLICY=m CONFIG_CRYPTO_ARIA=y CONFIG_XFRM_INTERFACE=m CONFIG_XFRM_USER=m +CONFIG_IP_NF_MATCH_RPFILTER=m +CONFIG_IP6_NF_MATCH_RPFILTER=m diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index fa7b59ff4029..224346426ef2 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -39,6 +39,7 @@ TEST_PROGS = bridge_fdb_learning_limit.sh \ ipip_hier_gre.sh \ lib_sh_test.sh \ local_termination.sh \ + min_max_mtu.sh \ mirror_gre_bound.sh \ mirror_gre_bridge_1d.sh \ mirror_gre_bridge_1d_vlan.sh \ @@ -70,6 +71,7 @@ TEST_PROGS = bridge_fdb_learning_limit.sh \ router_broadcast.sh \ router_mpath_nh_res.sh \ router_mpath_nh.sh \ + router_mpath_seed.sh \ router_multicast.sh \ router_multipath.sh \ router_nh.sh \ diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index eabbdf00d8ca..9086d2015296 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -1134,12 +1134,19 @@ bridge_ageing_time_get() } declare -A SYSCTL_ORIG +sysctl_save() +{ + local key=$1; shift + + SYSCTL_ORIG[$key]=$(sysctl -n $key) +} + sysctl_set() { local key=$1; shift local value=$1; shift - SYSCTL_ORIG[$key]=$(sysctl -n $key) + sysctl_save "$key" sysctl -qw $key="$value" } diff --git a/tools/testing/selftests/net/forwarding/min_max_mtu.sh b/tools/testing/selftests/net/forwarding/min_max_mtu.sh new file mode 100755 index 000000000000..97bb8b221bed --- /dev/null +++ b/tools/testing/selftests/net/forwarding/min_max_mtu.sh @@ -0,0 +1,283 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +--------------------+ +# | H1 | +# | | +# | $h1.10 + | +# | 192.0.2.2/24 | | +# | 2001:db8:1::2/64 | | +# | | | +# | $h1 + | +# | | | +# +------------------|-+ +# | +# +------------------|-+ +# | SW | | +# | $swp1 + | +# | | | +# | $swp1.10 + | +# | 192.0.2.1/24 | +# | 2001:db8:1::1/64 | +# | | +# +--------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + max_mtu_config_test + max_mtu_traffic_test + min_mtu_config_test + min_mtu_traffic_test +" + +NUM_NETIFS=2 +source lib.sh + +h1_create() +{ + simple_if_init $h1 + vlan_create $h1 10 v$h1 192.0.2.2/24 2001:db8:1::2/64 +} + +h1_destroy() +{ + vlan_destroy $h1 10 192.0.2.2/24 2001:db8:1::2/64 + simple_if_fini $h1 +} + +switch_create() +{ + ip li set dev $swp1 up + vlan_create $swp1 10 "" 192.0.2.1/24 2001:db8:1::1/64 +} + +switch_destroy() +{ + ip li set dev $swp1 down + vlan_destroy $swp1 10 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + vrf_prepare + + h1_create + + switch_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + switch_destroy + + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1.10 192.0.2.1 +} + +ping_ipv6() +{ + ping6_test $h1.10 2001:db8:1::1 +} + +min_max_mtu_get_if() +{ + local dev=$1; shift + local min_max=$1; shift + + ip -d -j link show $dev | jq ".[].$min_max" +} + +ensure_compatible_min_max_mtu() +{ + local min_max=$1; shift + + local mtu=$(min_max_mtu_get_if ${NETIFS[p1]} $min_max) + local i + + for ((i = 2; i <= NUM_NETIFS; ++i)); do + local current_mtu=$(min_max_mtu_get_if ${NETIFS[p$i]} $min_max) + + if [ $current_mtu -ne $mtu ]; then + return 1 + fi + done +} + +mtu_set_if() +{ + local dev=$1; shift + local mtu=$1; shift + local should_fail=${1:-0}; shift + + mtu_set $dev $mtu 2>/dev/null + check_err_fail $should_fail $? "Set MTU $mtu for $dev" +} + +mtu_set_all_if() +{ + local mtu=$1; shift + local i + + for ((i = 1; i <= NUM_NETIFS; ++i)); do + mtu_set_if ${NETIFS[p$i]} $mtu + mtu_set_if ${NETIFS[p$i]}.10 $mtu + done +} + +mtu_restore_all_if() +{ + local i + + for ((i = 1; i <= NUM_NETIFS; ++i)); do + mtu_restore ${NETIFS[p$i]}.10 + mtu_restore ${NETIFS[p$i]} + done +} + +mtu_test_ping4() +{ + local mtu=$1; shift + local should_fail=$1; shift + + # Ping adds 8 bytes for ICMP header and 20 bytes for IP header + local ping_headers_len=$((20 + 8)) + local pkt_size=$((mtu - ping_headers_len)) + + ping_do $h1.10 192.0.2.1 "-s $pkt_size -M do" + check_err_fail $should_fail $? "Ping, packet size: $pkt_size" +} + +mtu_test_ping6() +{ + local mtu=$1; shift + local should_fail=$1; shift + + # Ping adds 8 bytes for ICMP header and 40 bytes for IPv6 header + local ping6_headers_len=$((40 + 8)) + local pkt_size=$((mtu - ping6_headers_len)) + + ping6_do $h1.10 2001:db8:1::1 "-s $pkt_size -M do" + check_err_fail $should_fail $? "Ping6, packet size: $pkt_size" +} + +max_mtu_config_test() +{ + local i + + RET=0 + + for ((i = 1; i <= NUM_NETIFS; ++i)); do + local dev=${NETIFS[p$i]} + local max_mtu=$(min_max_mtu_get_if $dev "max_mtu") + local should_fail + + should_fail=0 + mtu_set_if $dev $max_mtu $should_fail + mtu_restore $dev + + should_fail=1 + mtu_set_if $dev $((max_mtu + 1)) $should_fail + mtu_restore $dev + done + + log_test "Test maximum MTU configuration" +} + +max_mtu_traffic_test() +{ + local should_fail + local max_mtu + + RET=0 + + if ! ensure_compatible_min_max_mtu "max_mtu"; then + log_test_xfail "Topology has incompatible maximum MTU values" + return + fi + + max_mtu=$(min_max_mtu_get_if ${NETIFS[p1]} "max_mtu") + + should_fail=0 + mtu_set_all_if $max_mtu + mtu_test_ping4 $max_mtu $should_fail + mtu_test_ping6 $max_mtu $should_fail + mtu_restore_all_if + + should_fail=1 + mtu_set_all_if $((max_mtu - 1)) + mtu_test_ping4 $max_mtu $should_fail + mtu_test_ping6 $max_mtu $should_fail + mtu_restore_all_if + + log_test "Test traffic, packet size is maximum MTU" +} + +min_mtu_config_test() +{ + local i + + RET=0 + + for ((i = 1; i <= NUM_NETIFS; ++i)); do + local dev=${NETIFS[p$i]} + local min_mtu=$(min_max_mtu_get_if $dev "min_mtu") + local should_fail + + should_fail=0 + mtu_set_if $dev $min_mtu $should_fail + mtu_restore $dev + + should_fail=1 + mtu_set_if $dev $((min_mtu - 1)) $should_fail + mtu_restore $dev + done + + log_test "Test minimum MTU configuration" +} + +min_mtu_traffic_test() +{ + local should_fail=0 + local min_mtu + + RET=0 + + if ! ensure_compatible_min_max_mtu "min_mtu"; then + log_test_xfail "Topology has incompatible minimum MTU values" + return + fi + + min_mtu=$(min_max_mtu_get_if ${NETIFS[p1]} "min_mtu") + mtu_set_all_if $min_mtu + mtu_test_ping4 $min_mtu $should_fail + # Do not test minimum MTU with IPv6, as IPv6 requires higher MTU. + + mtu_restore_all_if + + log_test "Test traffic, packet size is minimum MTU" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/router_mpath_seed.sh b/tools/testing/selftests/net/forwarding/router_mpath_seed.sh new file mode 100755 index 000000000000..314cb906c1eb --- /dev/null +++ b/tools/testing/selftests/net/forwarding/router_mpath_seed.sh @@ -0,0 +1,333 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +-------------------------+ +-------------------------+ +# | H1 | | H2 | +# | $h1 + | | + $h2 | +# | 192.0.2.1/28 | | | | 192.0.2.34/28 | +# | 2001:db8:1::1/64 | | | | 2001:db8:3::2/64 | +# +-------------------|-----+ +-|-----------------------+ +# | | +# +-------------------|-----+ +-|-----------------------+ +# | R1 | | | | R2 | +# | $rp11 + | | + $rp21 | +# | 192.0.2.2/28 | | 192.0.2.33/28 | +# | 2001:db8:1::2/64 | | 2001:db8:3::1/64 | +# | | | | +# | $rp12 + | | + $rp22 | +# | 192.0.2.17/28 | | | | 192.0.2.18..27/28 | +# | 2001:db8:2::17/64 | | | | 2001:db8:2::18..27/64 | +# +-------------------|-----+ +-|-----------------------+ +# | | +# `----------' + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + test_mpath_seed_stability_ipv4 + test_mpath_seed_stability_ipv6 + test_mpath_seed_get + test_mpath_seed_ipv4 + test_mpath_seed_ipv6 +" +NUM_NETIFS=6 +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64 + ip -4 route add 192.0.2.32/28 vrf v$h1 nexthop via 192.0.2.2 + ip -6 route add 2001:db8:3::/64 vrf v$h1 nexthop via 2001:db8:1::2 +} + +h1_destroy() +{ + ip -6 route del 2001:db8:3::/64 vrf v$h1 nexthop via 2001:db8:1::2 + ip -4 route del 192.0.2.32/28 vrf v$h1 nexthop via 192.0.2.2 + simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.34/28 2001:db8:3::2/64 + ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.33 + ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:3::1 +} + +h2_destroy() +{ + ip -6 route del 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:3::1 + ip -4 route del 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.33 + simple_if_fini $h2 192.0.2.34/28 2001:db8:3::2/64 +} + +router1_create() +{ + simple_if_init $rp11 192.0.2.2/28 2001:db8:1::2/64 + __simple_if_init $rp12 v$rp11 192.0.2.17/28 2001:db8:2::17/64 +} + +router1_destroy() +{ + __simple_if_fini $rp12 192.0.2.17/28 2001:db8:2::17/64 + simple_if_fini $rp11 192.0.2.2/28 2001:db8:1::2/64 +} + +router2_create() +{ + simple_if_init $rp21 192.0.2.33/28 2001:db8:3::1/64 + __simple_if_init $rp22 v$rp21 192.0.2.18/28 2001:db8:2::18/64 + ip -4 route add 192.0.2.0/28 vrf v$rp21 nexthop via 192.0.2.17 + ip -6 route add 2001:db8:1::/64 vrf v$rp21 nexthop via 2001:db8:2::17 +} + +router2_destroy() +{ + ip -6 route del 2001:db8:1::/64 vrf v$rp21 nexthop via 2001:db8:2::17 + ip -4 route del 192.0.2.0/28 vrf v$rp21 nexthop via 192.0.2.17 + __simple_if_fini $rp22 192.0.2.18/28 2001:db8:2::18/64 + simple_if_fini $rp21 192.0.2.33/28 2001:db8:3::1/64 +} + +nexthops_create() +{ + local i + for i in $(seq 10); do + ip nexthop add id $((1000 + i)) via 192.0.2.18 dev $rp12 + ip nexthop add id $((2000 + i)) via 2001:db8:2::18 dev $rp12 + done + + ip nexthop add id 1000 group $(seq -s / 1001 1010) hw_stats on + ip nexthop add id 2000 group $(seq -s / 2001 2010) hw_stats on + ip -4 route add 192.0.2.32/28 vrf v$rp11 nhid 1000 + ip -6 route add 2001:db8:3::/64 vrf v$rp11 nhid 2000 +} + +nexthops_destroy() +{ + local i + + ip -6 route del 2001:db8:3::/64 vrf v$rp11 nhid 2000 + ip -4 route del 192.0.2.32/28 vrf v$rp11 nhid 1000 + ip nexthop del id 2000 + ip nexthop del id 1000 + + for i in $(seq 10 -1 1); do + ip nexthop del id $((2000 + i)) + ip nexthop del id $((1000 + i)) + done +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + rp11=${NETIFS[p2]} + + rp12=${NETIFS[p3]} + rp22=${NETIFS[p4]} + + rp21=${NETIFS[p5]} + h2=${NETIFS[p6]} + + sysctl_save net.ipv4.fib_multipath_hash_seed + + vrf_prepare + + h1_create + h2_create + router1_create + router2_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + nexthops_destroy + router2_destroy + router1_destroy + h2_destroy + h1_destroy + + vrf_cleanup + + sysctl_restore net.ipv4.fib_multipath_hash_seed +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.34 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:3::2 +} + +test_mpath_seed_get() +{ + RET=0 + + local i + for ((i = 0; i < 100; i++)); do + local seed_w=$((999331 * i)) + sysctl -qw net.ipv4.fib_multipath_hash_seed=$seed_w + local seed_r=$(sysctl -n net.ipv4.fib_multipath_hash_seed) + ((seed_r == seed_w)) + check_err $? "mpath seed written as $seed_w, but read as $seed_r" + done + + log_test "mpath seed set/get" +} + +nh_stats_snapshot() +{ + local group_id=$1; shift + + ip -j -s -s nexthop show id $group_id | + jq -c '[.[].group_stats | sort_by(.id) | .[].packets]' +} + +get_active_nh() +{ + local s0=$1; shift + local s1=$1; shift + + jq -n --argjson s0 "$s0" --argjson s1 "$s1" -f /dev/stdin <<-"EOF" + [range($s0 | length)] | + map($s1[.] - $s0[.]) | + map(if . > 8 then 1 else 0 end) | + index(1) + EOF +} + +probe_nh() +{ + local group_id=$1; shift + local -a mz=("$@") + + local s0=$(nh_stats_snapshot $group_id) + "${mz[@]}" + local s1=$(nh_stats_snapshot $group_id) + + get_active_nh "$s0" "$s1" +} + +probe_seed() +{ + local group_id=$1; shift + local seed=$1; shift + local -a mz=("$@") + + sysctl -qw net.ipv4.fib_multipath_hash_seed=$seed + probe_nh "$group_id" "${mz[@]}" +} + +test_mpath_seed() +{ + local group_id=$1; shift + local what=$1; shift + local -a mz=("$@") + local ii + + RET=0 + + local -a tally=(0 0 0 0 0 0 0 0 0 0) + for ((ii = 0; ii < 100; ii++)); do + local act=$(probe_seed $group_id $((999331 * ii)) "${mz[@]}") + ((tally[act]++)) + done + + local tally_str="${tally[@]}" + for ((ii = 0; ii < ${#tally[@]}; ii++)); do + ((tally[ii] > 0)) + check_err $? "NH #$ii not hit, tally='$tally_str'" + done + + log_test "mpath seed $what" + sysctl -qw net.ipv4.fib_multipath_hash_seed=0 +} + +test_mpath_seed_ipv4() +{ + test_mpath_seed 1000 IPv4 \ + $MZ $h1 -A 192.0.2.1 -B 192.0.2.34 -q \ + -p 64 -d 0 -c 10 -t udp +} + +test_mpath_seed_ipv6() +{ + test_mpath_seed 2000 IPv6 \ + $MZ -6 $h1 -A 2001:db8:1::1 -B 2001:db8:3::2 -q \ + -p 64 -d 0 -c 10 -t udp +} + +check_mpath_seed_stability() +{ + local seed=$1; shift + local act_0=$1; shift + local act_1=$1; shift + + ((act_0 == act_1)) + check_err $? "seed $seed: active NH moved from $act_0 to $act_1 after seed change" +} + +test_mpath_seed_stability() +{ + local group_id=$1; shift + local what=$1; shift + local -a mz=("$@") + + RET=0 + + local seed_0=0 + local seed_1=3221338814 + local seed_2=3735928559 + + # Initial active NH before touching the seed at all. + local act_ini=$(probe_nh $group_id "${mz[@]}") + + local act_0_0=$(probe_seed $group_id $seed_0 "${mz[@]}") + local act_1_0=$(probe_seed $group_id $seed_1 "${mz[@]}") + local act_2_0=$(probe_seed $group_id $seed_2 "${mz[@]}") + + local act_0_1=$(probe_seed $group_id $seed_0 "${mz[@]}") + local act_1_1=$(probe_seed $group_id $seed_1 "${mz[@]}") + local act_2_1=$(probe_seed $group_id $seed_2 "${mz[@]}") + + check_mpath_seed_stability initial $act_ini $act_0_0 + check_mpath_seed_stability $seed_0 $act_0_0 $act_0_1 + check_mpath_seed_stability $seed_1 $act_1_0 $act_1_1 + check_mpath_seed_stability $seed_2 $act_2_0 $act_2_1 + + log_test "mpath seed stability $what" + sysctl -qw net.ipv4.fib_multipath_hash_seed=0 +} + +test_mpath_seed_stability_ipv4() +{ + test_mpath_seed_stability 1000 IPv4 \ + $MZ $h1 -A 192.0.2.1 -B 192.0.2.34 -q \ + -p 64 -d 0 -c 10 -t udp +} + +test_mpath_seed_stability_ipv6() +{ + test_mpath_seed_stability 2000 IPv6 \ + $MZ -6 $h1 -A 2001:db8:1::1 -B 2001:db8:3::2 -q \ + -p 64 -d 0 -c 10 -t udp +} + +trap cleanup EXIT + +setup_prepare +setup_wait +nexthops_create + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 9155c914c064..915f319bcc8b 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -125,28 +125,36 @@ slowwait_for_counter() slowwait "$timeout" until_counter_is ">= $((base + delta))" "$@" } +remove_ns_list() +{ + local item=$1 + local ns + local ns_list=("${NS_LIST[@]}") + NS_LIST=() + + for ns in "${ns_list[@]}"; do + if [ "${ns}" != "${item}" ]; then + NS_LIST+=("${ns}") + fi + done +} + cleanup_ns() { local ns="" - local errexit=0 local ret=0 - # disable errexit temporary - if [[ $- =~ "e" ]]; then - errexit=1 - set +e - fi - for ns in "$@"; do [ -z "${ns}" ] && continue - ip netns delete "${ns}" &> /dev/null + ip netns delete "${ns}" &> /dev/null || true if ! busywait $BUSYWAIT_TIMEOUT ip netns list \| grep -vq "^$ns$" &> /dev/null; then echo "Warn: Failed to remove namespace $ns" ret=1 + else + remove_ns_list "${ns}" fi done - [ $errexit -eq 1 ] && set -e return $ret } @@ -159,29 +167,30 @@ cleanup_all_ns() # setup_ns local remote setup_ns() { - local ns="" local ns_name="" local ns_list=() - local ns_exist= for ns_name in "$@"; do + # avoid conflicts with local var: internal error + if [ "${ns_name}" = "ns_name" ]; then + echo "Failed to setup namespace '${ns_name}': invalid name" + cleanup_ns "${ns_list[@]}" + exit $ksft_fail + fi + # Some test may setup/remove same netns multi times - if unset ${ns_name} 2> /dev/null; then - ns="${ns_name,,}-$(mktemp -u XXXXXX)" - eval readonly ${ns_name}="$ns" - ns_exist=false + if [ -z "${!ns_name}" ]; then + eval "${ns_name}=${ns_name,,}-$(mktemp -u XXXXXX)" else - eval ns='$'${ns_name} - cleanup_ns "$ns" - ns_exist=true + cleanup_ns "${!ns_name}" fi - if ! ip netns add "$ns"; then + if ! ip netns add "${!ns_name}"; then echo "Failed to create namespace $ns_name" cleanup_ns "${ns_list[@]}" return $ksft_skip fi - ip -n "$ns" link set lo up - ! $ns_exist && ns_list+=("$ns") + ip -n "${!ns_name}" link set lo up + ns_list+=("${!ns_name}") done NS_LIST+=("${ns_list[@]}") } diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index 4769b4eb1ea1..b6ce3f33d41e 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -57,6 +57,11 @@ def ksft_ge(a, b, comment=""): _fail("Check failed", a, "<", b, comment) +def ksft_lt(a, b, comment=""): + if a >= b: + _fail("Check failed", a, ">=", b, comment) + + class ksft_raises: def __init__(self, expected_type): self.exception = None diff --git a/tools/testing/selftests/net/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py index 0540ea24921d..405aa510aaf2 100644 --- a/tools/testing/selftests/net/lib/py/utils.py +++ b/tools/testing/selftests/net/lib/py/utils.py @@ -1,12 +1,18 @@ # SPDX-License-Identifier: GPL-2.0 +import errno import json as _json import random import re +import socket import subprocess import time +class CmdExitFailure(Exception): + pass + + class cmd: def __init__(self, comm, shell=True, fail=True, ns=None, background=False, host=None, timeout=5): if ns: @@ -41,8 +47,8 @@ class cmd: if self.proc.returncode != 0 and fail: if len(stderr) > 0 and stderr[-1] == "\n": stderr = stderr[:-1] - raise Exception("Command failed: %s\nSTDOUT: %s\nSTDERR: %s" % - (self.proc.args, stdout, stderr)) + raise CmdExitFailure("Command failed: %s\nSTDOUT: %s\nSTDERR: %s" % + (self.proc.args, stdout, stderr)) class bkg(cmd): @@ -77,11 +83,24 @@ def ip(args, json=None, ns=None, host=None): return tool('ip', args, json=json, host=host) +def ethtool(args, json=None, ns=None, host=None): + return tool('ethtool', args, json=json, ns=ns, host=host) + + def rand_port(): """ - Get unprivileged port, for now just random, one day we may decide to check if used. + Get a random unprivileged port, try to make sure it's not already used. """ - return random.randint(10000, 65535) + for _ in range(1000): + port = random.randint(10000, 65535) + try: + with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s: + s.bind(("", port)) + return port + except OSError as e: + if e.errno != errno.EADDRINUSE: + raise + raise Exception("Can't find any free unprivileged port") def wait_port_listen(port, proto="tcp", ns=None, host=None, sleep=0.005, deadline=5): diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 2b66c5fa71eb..108aeeb84ef1 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -2249,9 +2249,10 @@ remove_tests() if reset "remove invalid addresses"; then pm_nl_set_limits $ns1 3 3 pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + # broadcast IP: no packet for this address will be received on ns1 + pm_nl_add_endpoint $ns1 224.0.0.1 flags signal pm_nl_add_endpoint $ns1 10.0.3.1 flags signal - pm_nl_add_endpoint $ns1 10.0.14.1 flags signal - pm_nl_set_limits $ns2 3 3 + pm_nl_set_limits $ns2 2 2 addr_nr_ns1=-3 speed=10 \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 6ffa9b7a3260..194c8fc2e55a 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -1,6 +1,9 @@ #! /bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/../lib.sh" +. "$(dirname "${0}")/../net_helper.sh" + readonly KSFT_PASS=0 readonly KSFT_FAIL=1 readonly KSFT_SKIP=4 @@ -361,20 +364,7 @@ mptcp_lib_check_transfer() { # $1: ns, $2: port mptcp_lib_wait_local_port_listen() { - local listener_ns="${1}" - local port="${2}" - - local port_hex - port_hex="$(printf "%04X" "${port}")" - - local _ - for _ in $(seq 10); do - ip netns exec "${listener_ns}" cat /proc/net/tcp* | \ - awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) \ - {rc=0; exit}} END {exit rc}" && - break - sleep 0.1 - done + wait_local_port_listen "${@}" "tcp" } mptcp_lib_check_output() { @@ -438,17 +428,13 @@ mptcp_lib_check_tools() { } mptcp_lib_ns_init() { - local sec rndh - - sec=$(date +%s) - rndh=$(printf %x "${sec}")-$(mktemp -u XXXXXX) + if ! setup_ns ${@}; then + mptcp_lib_pr_fail "Failed to setup namespace ${@}" + exit ${KSFT_FAIL} + fi local netns for netns in "${@}"; do - eval "${netns}=${netns}-${rndh}" - - ip netns add "${!netns}" || exit ${KSFT_SKIP} - ip -net "${!netns}" link set lo up ip netns exec "${!netns}" sysctl -q net.mptcp.enabled=1 ip netns exec "${!netns}" sysctl -q net.ipv4.conf.all.rp_filter=0 ip netns exec "${!netns}" sysctl -q net.ipv4.conf.default.rp_filter=0 @@ -456,9 +442,10 @@ mptcp_lib_ns_init() { } mptcp_lib_ns_exit() { + cleanup_ns "${@}" + local netns for netns in "${@}"; do - ip netns del "${netns}" rm -f /tmp/"${netns}".{nstat,out} done } diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 9e2981f2d7f5..9cb05978269d 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -160,10 +160,12 @@ make_connection() local is_v6=$1 local app_port=$app4_port local connect_addr="10.0.1.1" + local client_addr="10.0.1.2" local listen_addr="0.0.0.0" if [ "$is_v6" = "v6" ] then connect_addr="dead:beef:1::1" + client_addr="dead:beef:1::2" listen_addr="::" app_port=$app6_port else @@ -206,6 +208,7 @@ make_connection() [ "$server_serverside" = 1 ] then test_pass + print_title "Connection info: ${client_addr}:${client_port} -> ${connect_addr}:${app_port}" else test_fail "Expected tokens (c:${client_token} - s:${server_token}) and server (c:${client_serverside} - s:${server_serverside})" mptcp_lib_result_print_all_tap @@ -297,7 +300,7 @@ test_announce() ip netns exec "$ns2"\ ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id $client_addr_id dev\ ns2eth1 - print_test "ADD_ADDR id:${client_addr_id} 10.0.2.2 (ns2) => ns1, reuse port" + print_test "ADD_ADDR id:client 10.0.2.2 (ns2) => ns1, reuse port" sleep 0.5 verify_announce_event $server_evts $ANNOUNCED $server4_token "10.0.2.2" $client_addr_id \ "$client4_port" @@ -306,7 +309,7 @@ test_announce() :>"$server_evts" ip netns exec "$ns2" ./pm_nl_ctl ann\ dead:beef:2::2 token "$client6_token" id $client_addr_id dev ns2eth1 - print_test "ADD_ADDR6 id:${client_addr_id} dead:beef:2::2 (ns2) => ns1, reuse port" + print_test "ADD_ADDR6 id:client dead:beef:2::2 (ns2) => ns1, reuse port" sleep 0.5 verify_announce_event "$server_evts" "$ANNOUNCED" "$server6_token" "dead:beef:2::2"\ "$client_addr_id" "$client6_port" "v6" @@ -316,7 +319,7 @@ test_announce() client_addr_id=$((client_addr_id+1)) ip netns exec "$ns2" ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id\ $client_addr_id dev ns2eth1 port $new4_port - print_test "ADD_ADDR id:${client_addr_id} 10.0.2.2 (ns2) => ns1, new port" + print_test "ADD_ADDR id:client+1 10.0.2.2 (ns2) => ns1, new port" sleep 0.5 verify_announce_event "$server_evts" "$ANNOUNCED" "$server4_token" "10.0.2.2"\ "$client_addr_id" "$new4_port" @@ -327,7 +330,7 @@ test_announce() # ADD_ADDR from the server to client machine reusing the subflow port ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\ $server_addr_id dev ns1eth2 - print_test "ADD_ADDR id:${server_addr_id} 10.0.2.1 (ns1) => ns2, reuse port" + print_test "ADD_ADDR id:server 10.0.2.1 (ns1) => ns2, reuse port" sleep 0.5 verify_announce_event "$client_evts" "$ANNOUNCED" "$client4_token" "10.0.2.1"\ "$server_addr_id" "$app4_port" @@ -336,7 +339,7 @@ test_announce() :>"$client_evts" ip netns exec "$ns1" ./pm_nl_ctl ann dead:beef:2::1 token "$server6_token" id\ $server_addr_id dev ns1eth2 - print_test "ADD_ADDR6 id:${server_addr_id} dead:beef:2::1 (ns1) => ns2, reuse port" + print_test "ADD_ADDR6 id:server dead:beef:2::1 (ns1) => ns2, reuse port" sleep 0.5 verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "dead:beef:2::1"\ "$server_addr_id" "$app6_port" "v6" @@ -346,7 +349,7 @@ test_announce() server_addr_id=$((server_addr_id+1)) ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\ $server_addr_id dev ns1eth2 port $new4_port - print_test "ADD_ADDR id:${server_addr_id} 10.0.2.1 (ns1) => ns2, new port" + print_test "ADD_ADDR id:server+1 10.0.2.1 (ns1) => ns2, new port" sleep 0.5 verify_announce_event "$client_evts" "$ANNOUNCED" "$client4_token" "10.0.2.1"\ "$server_addr_id" "$new4_port" @@ -380,7 +383,7 @@ test_remove() local invalid_token=$(( client4_token - 1 )) ip netns exec "$ns2" ./pm_nl_ctl rem token $invalid_token id\ $client_addr_id > /dev/null 2>&1 - print_test "RM_ADDR id:${client_addr_id} ns2 => ns1, invalid token" + print_test "RM_ADDR id:client ns2 => ns1, invalid token" local type type=$(mptcp_lib_evts_get_info type "$server_evts") if [ "$type" = "" ] @@ -394,7 +397,7 @@ test_remove() local invalid_id=$(( client_addr_id + 1 )) ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\ $invalid_id > /dev/null 2>&1 - print_test "RM_ADDR id:${invalid_id} ns2 => ns1, invalid id" + print_test "RM_ADDR id:client+1 ns2 => ns1, invalid id" type=$(mptcp_lib_evts_get_info type "$server_evts") if [ "$type" = "" ] then @@ -407,7 +410,7 @@ test_remove() :>"$server_evts" ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\ $client_addr_id - print_test "RM_ADDR id:${client_addr_id} ns2 => ns1" + print_test "RM_ADDR id:client ns2 => ns1" sleep 0.5 verify_remove_event "$server_evts" "$REMOVED" "$server4_token" "$client_addr_id" @@ -416,7 +419,7 @@ test_remove() client_addr_id=$(( client_addr_id - 1 )) ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\ $client_addr_id - print_test "RM_ADDR id:${client_addr_id} ns2 => ns1" + print_test "RM_ADDR id:client-1 ns2 => ns1" sleep 0.5 verify_remove_event "$server_evts" "$REMOVED" "$server4_token" "$client_addr_id" @@ -424,7 +427,7 @@ test_remove() :>"$server_evts" ip netns exec "$ns2" ./pm_nl_ctl rem token "$client6_token" id\ $client_addr_id - print_test "RM_ADDR6 id:${client_addr_id} ns2 => ns1" + print_test "RM_ADDR6 id:client-1 ns2 => ns1" sleep 0.5 verify_remove_event "$server_evts" "$REMOVED" "$server6_token" "$client_addr_id" @@ -434,7 +437,7 @@ test_remove() # RM_ADDR from the server to client machine ip netns exec "$ns1" ./pm_nl_ctl rem token "$server4_token" id\ $server_addr_id - print_test "RM_ADDR id:${server_addr_id} ns1 => ns2" + print_test "RM_ADDR id:server ns1 => ns2" sleep 0.5 verify_remove_event "$client_evts" "$REMOVED" "$client4_token" "$server_addr_id" @@ -443,7 +446,7 @@ test_remove() server_addr_id=$(( server_addr_id - 1 )) ip netns exec "$ns1" ./pm_nl_ctl rem token "$server4_token" id\ $server_addr_id - print_test "RM_ADDR id:${server_addr_id} ns1 => ns2" + print_test "RM_ADDR id:server-1 ns1 => ns2" sleep 0.5 verify_remove_event "$client_evts" "$REMOVED" "$client4_token" "$server_addr_id" @@ -451,7 +454,7 @@ test_remove() :>"$client_evts" ip netns exec "$ns1" ./pm_nl_ctl rem token "$server6_token" id\ $server_addr_id - print_test "RM_ADDR6 id:${server_addr_id} ns1 => ns2" + print_test "RM_ADDR6 id:server-1 ns1 => ns2" sleep 0.5 verify_remove_event "$client_evts" "$REMOVED" "$client6_token" "$server_addr_id" } @@ -479,8 +482,14 @@ verify_subflow_events() local locid local remid local info + local e_dport_txt - info="${e_saddr} (${e_from}) => ${e_daddr}:${e_dport} (${e_to})" + # only display the fixed ports + if [ "${e_dport}" -ge "${app4_port}" ] && [ "${e_dport}" -le "${app6_port}" ]; then + e_dport_txt=":${e_dport}" + fi + + info="${e_saddr} (${e_from}) => ${e_daddr}${e_dport_txt} (${e_to})" if [ "$e_type" = "$SUB_ESTABLISHED" ] then @@ -766,7 +775,7 @@ test_subflows_v4_v6_mix() :>"$client_evts" ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server6_token" id\ $server_addr_id dev ns1eth2 - print_test "ADD_ADDR4 id:${server_addr_id} 10.0.2.1 (ns1) => ns2, reuse port" + print_test "ADD_ADDR4 id:server 10.0.2.1 (ns1) => ns2, reuse port" sleep 0.5 verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "10.0.2.1"\ "$server_addr_id" "$app6_port" @@ -861,7 +870,7 @@ test_listener() local listener_pid=$! sleep 0.5 - print_test "CREATE_LISTENER 10.0.2.2:$client4_port" + print_test "CREATE_LISTENER 10.0.2.2 (client port)" verify_listener_events $client_evts $LISTENER_CREATED $AF_INET 10.0.2.2 $client4_port # ADD_ADDR from client to server machine reusing the subflow port @@ -878,13 +887,14 @@ test_listener() mptcp_lib_kill_wait $listener_pid sleep 0.5 - print_test "CLOSE_LISTENER 10.0.2.2:$client4_port" + print_test "CLOSE_LISTENER 10.0.2.2 (client port)" verify_listener_events $client_evts $LISTENER_CLOSED $AF_INET 10.0.2.2 $client4_port } print_title "Make connections" make_connection make_connection "v6" +print_title "Will be using address IDs ${client_addr_id} (client) and ${server_addr_id} (server)" test_announce test_remove diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index 5cae53543849..15bca0708717 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # # OVS kernel module self tests diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py index 1dd057afd3fb..9f8dec2f6539 100644 --- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -531,7 +531,7 @@ class ovsactions(nla): for flat_act in parse_flat_map: if parse_starts_block(actstr, flat_act[0], False): actstr = actstr[len(flat_act[0]):] - self["attrs"].append([flat_act[1]]) + self["attrs"].append([flat_act[1], True]) actstr = actstr[strspn(actstr, ", ") :] parsed = True diff --git a/tools/testing/selftests/net/srv6_end_dx4_netfilter_test.sh b/tools/testing/selftests/net/srv6_end_dx4_netfilter_test.sh new file mode 100755 index 000000000000..e23210aa547f --- /dev/null +++ b/tools/testing/selftests/net/srv6_end_dx4_netfilter_test.sh @@ -0,0 +1,335 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# author: Jianguo Wu <[email protected]> +# +# Mostly copied from tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh. +# +# This script is designed for testing the support of netfilter hooks for +# SRv6 End.DX4 behavior. +# +# Hereafter a network diagram is shown, where one tenants (named 100) offer +# IPv4 L3 VPN services allowing hosts to communicate with each other across +# an IPv6 network. +# +# Routers rt-1 and rt-2 implement IPv4 L3 VPN services leveraging the SRv6 +# architecture. The key components for such VPNs are: a) SRv6 Encap behavior, +# b) SRv6 End.DX4 behavior. +# +# To explain how an IPv4 L3 VPN based on SRv6 works, let us briefly consider an +# example where, within the same domain of tenant 100, the host hs-1 pings +# the host hs-2. +# +# First of all, L2 reachability of the host hs-2 is taken into account by +# the router rt-1 which acts as an arp proxy. +# +# When the host hs-1 sends an IPv4 packet destined to hs-2, the router rt-1 +# receives the packet on the internal veth-t100 interface, rt-1 contains the +# SRv6 Encap route for encapsulating the IPv4 packet in a IPv6 plus the Segment +# Routing Header (SRH) packet. This packet is sent through the (IPv6) core +# network up to the router rt-2 that receives it on veth0 interface. +# +# The rt-2 router uses the 'localsid' routing table to process incoming +# IPv6+SRH packets which belong to the VPN of the tenant 100. For each of these +# packets, the SRv6 End.DX4 behavior removes the outer IPv6+SRH headers and +# routs the packet to the specified nexthop. Afterwards, the packet is sent to +# the host hs-2 through the veth-t100 interface. +# +# The ping response follows the same processing but this time the role of rt-1 +# and rt-2 are swapped. +# +# And when net.netfilter.nf_hooks_lwtunnel is set to 1 in rt-1 or rt-2, and a +# rpfilter iptables rule is added, SRv6 packets will go through netfilter PREROUTING +# hooks. +# +# +# +-------------------+ +-------------------+ +# | | | | +# | hs-1 netns | | hs-2 netns | +# | | | | +# | +-------------+ | | +-------------+ | +# | | veth0 | | | | veth0 | | +# | | 10.0.0.1/24 | | | | 10.0.0.2/24 | | +# | +-------------+ | | +-------------+ | +# | . | | . | +# +-------------------+ +-------------------+ +# . . +# . . +# . . +# +-----------------------------------+ +-----------------------------------+ +# | . | | . | +# | +---------------+ | | +---------------- | +# | | veth-t100 | | | | veth-t100 | | +# | | 10.0.0.11/24 | +----------+ | | +----------+ | 10.0.0.22/24 | | +# | +-------+-------+ | route | | | | route | +-------+-------- | +# | | table | | | | table | | +# | +----------+ | | +----------+ | +# | +--------------+ | | +--------------+ | +# | | veth0 | | | | veth0 | | +# | | 2001:11::1/64 |.|...|.| 2001:11::2/64 | | +# | +--------------+ | | +--------------+ | +# | | | | +# | rt-1 netns | | rt-2 netns | +# | | | | +# +-----------------------------------+ +-----------------------------------+ +# +# ~~~~~~~~~~~~~~~~~~~~~~~~~ +# | Network configuration | +# ~~~~~~~~~~~~~~~~~~~~~~~~~ +# +# rt-1: localsid table +# +----------------------------------------------------------------+ +# |SID |Action | +# +----------------------------------------------------------------+ +# |fc00:21:100::6004|apply SRv6 End.DX4 nh4 10.0.0.1 dev veth-t100 | +# +----------------------------------------------------------------+ +# +# rt-1: route table +# +---------------------------------------------------+ +# |host |Action | +# +---------------------------------------------------+ +# |10.0.0.2 |apply seg6 encap segs fc00:12:100::6004| +# +---------------------------------------------------+ +# |10.0.0.0/24|forward to dev veth_t100 | +# +---------------------------------------------------+ +# +# +# rt-2: localsid table +# +---------------------------------------------------------------+ +# |SID |Action | +# +---------------------------------------------------------------+ +# |fc00:12:100::6004|apply SRv6 End.DX4 nh4 10.0.0.2 dev veth-t100| +# +---------------------------------------------------------------+ +# +# rt-2: route table +# +---------------------------------------------------+ +# |host |Action | +# +---------------------------------------------------+ +# |10.0.0.1 |apply seg6 encap segs fc00:21:100::6004| +# +---------------------------------------------------+ +# |10.0.0.0/24|forward to dev veth_t100 | +# +---------------------------------------------------+ +# + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +readonly IPv6_RT_NETWORK=2001:11 +readonly IPv4_HS_NETWORK=10.0.0 +readonly SID_LOCATOR=fc00 + +PING_TIMEOUT_SEC=4 + +ret=0 + +PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + nsuccess=$((nsuccess+1)) + printf "\n TEST: %-60s [ OK ]\n" "${msg}" + else + ret=1 + nfail=$((nfail+1)) + printf "\n TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi +} + +print_log_test_results() +{ + if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} + fi +} + +log_section() +{ + echo + echo "################################################################################" + echo "TEST SECTION: $*" + echo "################################################################################" +} + +cleanup() +{ + ip link del veth-rt-1 2>/dev/null || true + ip link del veth-rt-2 2>/dev/null || true + + # destroy routers rt-* and hosts hs-* + for ns in $(ip netns show | grep -E 'rt-*|hs-*'); do + ip netns del ${ns} || true + done +} + +# Setup the basic networking for the routers +setup_rt_networking() +{ + local rt=$1 + local nsname=rt-${rt} + + ip netns add ${nsname} + + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + + ip link set veth-rt-${rt} netns ${nsname} + ip -netns ${nsname} link set veth-rt-${rt} name veth0 + + ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 nodad + ip -netns ${nsname} link set veth0 up + ip -netns ${nsname} link set lo up + + ip netns exec ${nsname} sysctl -wq net.ipv4.ip_forward=1 + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.forwarding=1 +} + +setup_rt_netfilter() +{ + local rt=$1 + local nsname=rt-${rt} + + ip netns exec ${nsname} sysctl -wq net.netfilter.nf_hooks_lwtunnel=1 + ip netns exec ${nsname} iptables -t raw -A PREROUTING -m rpfilter --invert -j DROP +} + +setup_hs() +{ + local hs=$1 + local rt=$2 + local tid=$3 + local hsname=hs-${hs} + local rtname=rt-${rt} + local rtveth=veth-t${tid} + + # set the networking for the host + ip netns add ${hsname} + + ip -netns ${hsname} link add veth0 type veth peer name ${rtveth} + ip -netns ${hsname} link set ${rtveth} netns ${rtname} + ip -netns ${hsname} addr add ${IPv4_HS_NETWORK}.${hs}/24 dev veth0 + ip -netns ${hsname} link set veth0 up + ip -netns ${hsname} link set lo up + + ip -netns ${rtname} addr add ${IPv4_HS_NETWORK}.${rt}${hs}/24 dev ${rtveth} + ip -netns ${rtname} link set ${rtveth} up + + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.proxy_arp=1 +} + +setup_vpn_config() +{ + local hssrc=$1 + local rtsrc=$2 + local hsdst=$3 + local rtdst=$4 + local tid=$5 + + local hssrc_name=hs-t${tid}-${hssrc} + local hsdst_name=hs-t${tid}-${hsdst} + local rtsrc_name=rt-${rtsrc} + local rtdst_name=rt-${rtdst} + local vpn_sid=${SID_LOCATOR}:${hssrc}${hsdst}:${tid}::6004 + + # set the encap route for encapsulating packets which arrive from the + # host hssrc and destined to the access router rtsrc. + ip -netns ${rtsrc_name} -4 route add ${IPv4_HS_NETWORK}.${hsdst}/32 \ + encap seg6 mode encap segs ${vpn_sid} dev veth0 + ip -netns ${rtsrc_name} -6 route add ${vpn_sid}/128 \ + via 2001:11::${rtdst} dev veth0 + + # set the decap route for decapsulating packets which arrive from + # the rtdst router and destined to the hsdst host. + ip -netns ${rtdst_name} -6 route add ${vpn_sid}/128 \ + encap seg6local action End.DX4 nh4 ${IPv4_HS_NETWORK}.${hsdst} dev veth-t${tid} +} + +setup() +{ + ip link add veth-rt-1 type veth peer name veth-rt-2 + # setup the networking for router rt-1 and router rt-2 + setup_rt_networking 1 + setup_rt_networking 2 + + # setup two hosts for the tenant 100. + # - host hs-1 is directly connected to the router rt-1; + # - host hs-2 is directly connected to the router rt-2. + setup_hs 1 1 100 + setup_hs 2 2 100 + + # setup the IPv4 L3 VPN which connects the host hs-1 and host hs-2. + setup_vpn_config 1 1 2 2 100 #args: src_host src_router dst_host dst_router tenant + setup_vpn_config 2 2 1 1 100 +} + +check_hs_connectivity() +{ + local hssrc=$1 + local hsdst=$2 + local tid=$3 + + ip netns exec hs-${hssrc} ping -c 1 -W ${PING_TIMEOUT_SEC} \ + ${IPv4_HS_NETWORK}.${hsdst} >/dev/null 2>&1 +} + +check_and_log_hs_connectivity() +{ + local hssrc=$1 + local hsdst=$2 + local tid=$3 + + check_hs_connectivity ${hssrc} ${hsdst} ${tid} + log_test $? 0 "Hosts connectivity: hs-${hssrc} -> hs-${hsdst} (tenant ${tid})" +} + +host_tests() +{ + log_section "SRv6 VPN connectivity test among hosts in the same tenant" + + check_and_log_hs_connectivity 1 2 100 + check_and_log_hs_connectivity 2 1 100 +} + +router_netfilter_tests() +{ + log_section "SRv6 VPN connectivity test with netfilter enabled in routers" + setup_rt_netfilter 1 + setup_rt_netfilter 2 + + check_and_log_hs_connectivity 1 2 100 + check_and_log_hs_connectivity 2 1 100 +} + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit $ksft_skip +fi + +if [ ! -x "$(command -v ip)" ]; then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +cleanup &>/dev/null + +setup + +host_tests +router_netfilter_tests + +print_log_test_results + +cleanup &>/dev/null + +exit ${ret} diff --git a/tools/testing/selftests/net/srv6_end_dx6_netfilter_test.sh b/tools/testing/selftests/net/srv6_end_dx6_netfilter_test.sh new file mode 100755 index 000000000000..9e69a2ed5bc3 --- /dev/null +++ b/tools/testing/selftests/net/srv6_end_dx6_netfilter_test.sh @@ -0,0 +1,340 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# author: Jianguo Wu <[email protected]> +# +# Mostly copied from tools/testing/selftests/net/srv6_end_dt6_l3vpn_test.sh. +# +# This script is designed for testing the support of netfilter hooks for +# SRv6 End.DX4 behavior. +# +# Hereafter a network diagram is shown, where one tenants (named 100) offer +# IPv6 L3 VPN services allowing hosts to communicate with each other across +# an IPv6 network. +# +# Routers rt-1 and rt-2 implement IPv6 L3 VPN services leveraging the SRv6 +# architecture. The key components for such VPNs are: a) SRv6 Encap behavior, +# b) SRv6 End.DX4 behavior. +# +# To explain how an IPv6 L3 VPN based on SRv6 works, let us briefly consider an +# example where, within the same domain of tenant 100, the host hs-1 pings +# the host hs-2. +# +# First of all, L2 reachability of the host hs-2 is taken into account by +# the router rt-1 which acts as an arp proxy. +# +# When the host hs-1 sends an IPv6 packet destined to hs-2, the router rt-1 +# receives the packet on the internal veth-t100 interface, rt-1 contains the +# SRv6 Encap route for encapsulating the IPv6 packet in a IPv6 plus the Segment +# Routing Header (SRH) packet. This packet is sent through the (IPv6) core +# network up to the router rt-2 that receives it on veth0 interface. +# +# The rt-2 router uses the 'localsid' routing table to process incoming +# IPv6+SRH packets which belong to the VPN of the tenant 100. For each of these +# packets, the SRv6 End.DX4 behavior removes the outer IPv6+SRH headers and +# routs the packet to the specified nexthop. Afterwards, the packet is sent to +# the host hs-2 through the veth-t100 interface. +# +# The ping response follows the same processing but this time the role of rt-1 +# and rt-2 are swapped. +# +# And when net.netfilter.nf_hooks_lwtunnel is set to 1 in rt-1 or rt-2, and a +# rpfilter iptables rule is added, SRv6 packets will go through netfilter PREROUTING +# hooks. +# +# +# +-------------------+ +-------------------+ +# | | | | +# | hs-1 netns | | hs-2 netns | +# | | | | +# | +-------------+ | | +-------------+ | +# | | veth0 | | | | veth0 | | +# | | cafe::1/64 | | | | cafe::2/64 | | +# | +-------------+ | | +-------------+ | +# | . | | . | +# +-------------------+ +-------------------+ +# . . +# . . +# . . +# +-----------------------------------+ +-----------------------------------+ +# | . | | . | +# | +---------------+ | | +---------------- | +# | | veth-t100 | | | | veth-t100 | | +# | | cafe::11/64 | +----------+ | | +----------+ | cafe::22/64 | | +# | +-------+-------+ | route | | | | route | +-------+-------- | +# | | table | | | | table | | +# | +----------+ | | +----------+ | +# | +--------------+ | | +--------------+ | +# | | veth0 | | | | veth0 | | +# | | 2001:11::1/64 |.|...|.| 2001:11::2/64 | | +# | +--------------+ | | +--------------+ | +# | | | | +# | rt-1 netns | | rt-2 netns | +# | | | | +# +-----------------------------------+ +-----------------------------------+ +# +# ~~~~~~~~~~~~~~~~~~~~~~~~~ +# | Network configuration | +# ~~~~~~~~~~~~~~~~~~~~~~~~~ +# +# rt-1: localsid table +# +----------------------------------------------------------------+ +# |SID |Action | +# +----------------------------------------------------------------+ +# |fc00:21:100::6004|apply SRv6 End.DX6 nh6 cafe::1 dev veth-t100 | +# +----------------------------------------------------------------+ +# +# rt-1: route table +# +---------------------------------------------------+ +# |host |Action | +# +---------------------------------------------------+ +# |cafe::2 |apply seg6 encap segs fc00:12:100::6004| +# +---------------------------------------------------+ +# |cafe::/64 |forward to dev veth_t100 | +# +---------------------------------------------------+ +# +# +# rt-2: localsid table +# +---------------------------------------------------------------+ +# |SID |Action | +# +---------------------------------------------------------------+ +# |fc00:12:100::6004|apply SRv6 End.DX6 nh6 cafe::2 dev veth-t100 | +# +---------------------------------------------------------------+ +# +# rt-2: route table +# +---------------------------------------------------+ +# |host |Action | +# +---------------------------------------------------+ +# |cafe::1 |apply seg6 encap segs fc00:21:100::6004| +# +---------------------------------------------------+ +# |cafe::/64 |forward to dev veth_t100 | +# +---------------------------------------------------+ +# + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +readonly IPv6_RT_NETWORK=2001:11 +readonly IPv6_HS_NETWORK=cafe +readonly SID_LOCATOR=fc00 + +PING_TIMEOUT_SEC=4 + +ret=0 + +PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + nsuccess=$((nsuccess+1)) + printf "\n TEST: %-60s [ OK ]\n" "${msg}" + else + ret=1 + nfail=$((nfail+1)) + printf "\n TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi +} + +print_log_test_results() +{ + if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} + fi +} + +log_section() +{ + echo + echo "################################################################################" + echo "TEST SECTION: $*" + echo "################################################################################" +} + +cleanup() +{ + ip link del veth-rt-1 2>/dev/null || true + ip link del veth-rt-2 2>/dev/null || true + + # destroy routers rt-* and hosts hs-* + for ns in $(ip netns show | grep -E 'rt-*|hs-*'); do + ip netns del ${ns} || true + done +} + +# Setup the basic networking for the routers +setup_rt_networking() +{ + local rt=$1 + local nsname=rt-${rt} + + ip netns add ${nsname} + + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + + ip link set veth-rt-${rt} netns ${nsname} + ip -netns ${nsname} link set veth-rt-${rt} name veth0 + + ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 nodad + ip -netns ${nsname} link set veth0 up + ip -netns ${nsname} link set lo up + + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.forwarding=1 +} + +setup_rt_netfilter() +{ + local rt=$1 + local nsname=rt-${rt} + + ip netns exec ${nsname} sysctl -wq net.netfilter.nf_hooks_lwtunnel=1 + ip netns exec ${nsname} ip6tables -t raw -A PREROUTING -m rpfilter --invert -j DROP +} + +setup_hs() +{ + local hs=$1 + local rt=$2 + local tid=$3 + local hsname=hs-${hs} + local rtname=rt-${rt} + local rtveth=veth-t${tid} + + # set the networking for the host + ip netns add ${hsname} + + ip -netns ${hsname} link add veth0 type veth peer name ${rtveth} + ip -netns ${hsname} link set ${rtveth} netns ${rtname} + ip -netns ${hsname} addr add ${IPv6_HS_NETWORK}::${hs}/64 dev veth0 nodad + ip -netns ${hsname} link set veth0 up + ip -netns ${hsname} link set lo up + + ip -netns ${rtname} addr add ${IPv6_HS_NETWORK}::${rt}${hs}/64 dev ${rtveth} + ip -netns ${rtname} link set ${rtveth} up + + ip netns exec ${rtname} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${rtname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + + ip netns exec ${rtname} sysctl -wq net.ipv6.conf.${rtveth}.proxy_ndp=1 +} + +setup_vpn_config() +{ + local hssrc=$1 + local rtsrc=$2 + local hsdst=$3 + local rtdst=$4 + local tid=$5 + + local hssrc_name=hs-t${tid}-${hssrc} + local hsdst_name=hs-t${tid}-${hsdst} + local rtsrc_name=rt-${rtsrc} + local rtdst_name=rt-${rtdst} + local rtveth=veth-t${tid} + local vpn_sid=${SID_LOCATOR}:${hssrc}${hsdst}:${tid}::6004 + + ip -netns ${rtsrc_name} -6 neigh add proxy ${IPv6_HS_NETWORK}::${hsdst} dev ${rtveth} + + # set the encap route for encapsulating packets which arrive from the + # host hssrc and destined to the access router rtsrc. + ip -netns ${rtsrc_name} -6 route add ${IPv6_HS_NETWORK}::${hsdst}/128 \ + encap seg6 mode encap segs ${vpn_sid} dev veth0 + ip -netns ${rtsrc_name} -6 route add ${vpn_sid}/128 \ + via 2001:11::${rtdst} dev veth0 + + # set the decap route for decapsulating packets which arrive from + # the rtdst router and destined to the hsdst host. + ip -netns ${rtdst_name} -6 route add ${vpn_sid}/128 \ + encap seg6local action End.DX6 nh6 ${IPv6_HS_NETWORK}::${hsdst} dev veth-t${tid} +} + +setup() +{ + ip link add veth-rt-1 type veth peer name veth-rt-2 + # setup the networking for router rt-1 and router rt-2 + setup_rt_networking 1 + setup_rt_networking 2 + + # setup two hosts for the tenant 100. + # - host hs-1 is directly connected to the router rt-1; + # - host hs-2 is directly connected to the router rt-2. + setup_hs 1 1 100 + setup_hs 2 2 100 + + # setup the IPv4 L3 VPN which connects the host hs-1 and host hs-2. + setup_vpn_config 1 1 2 2 100 #args: src_host src_router dst_host dst_router tenant + setup_vpn_config 2 2 1 1 100 +} + +check_hs_connectivity() +{ + local hssrc=$1 + local hsdst=$2 + local tid=$3 + + ip netns exec hs-${hssrc} ping -6 -c 1 -W ${PING_TIMEOUT_SEC} \ + ${IPv6_HS_NETWORK}::${hsdst} >/dev/null 2>&1 +} + +check_and_log_hs_connectivity() +{ + local hssrc=$1 + local hsdst=$2 + local tid=$3 + + check_hs_connectivity ${hssrc} ${hsdst} ${tid} + log_test $? 0 "Hosts connectivity: hs-${hssrc} -> hs-${hsdst} (tenant ${tid})" +} + +host_tests() +{ + log_section "SRv6 VPN connectivity test among hosts in the same tenant" + + check_and_log_hs_connectivity 1 2 100 + check_and_log_hs_connectivity 2 1 100 +} + +router_netfilter_tests() +{ + log_section "SRv6 VPN connectivity test with netfilter enabled in routers" + setup_rt_netfilter 1 + setup_rt_netfilter 2 + + check_and_log_hs_connectivity 1 2 100 + check_and_log_hs_connectivity 2 1 100 +} + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit $ksft_skip +fi + +if [ ! -x "$(command -v ip)" ]; then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +cleanup &>/dev/null + +setup + +host_tests +router_netfilter_tests + +print_log_test_results + +cleanup &>/dev/null + +exit ${ret} diff --git a/tools/testing/selftests/openat2/Makefile b/tools/testing/selftests/openat2/Makefile index 254d676a2689..185dc76ebb5f 100644 --- a/tools/testing/selftests/openat2/Makefile +++ b/tools/testing/selftests/openat2/Makefile @@ -1,8 +1,18 @@ # SPDX-License-Identifier: GPL-2.0-or-later -CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined -static-libasan +CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined TEST_GEN_PROGS := openat2_test resolve_test rename_attack_test +# gcc requires -static-libasan in order to ensure that Address Sanitizer's +# library is the first one loaded. However, clang already statically links the +# Address Sanitizer if -fsanitize is specified. Therefore, simply omit +# -static-libasan for clang builds. +ifeq ($(LLVM),) + CFLAGS += -static-libasan +endif + +LOCAL_HDRS += helpers.h + include ../lib.mk -$(TEST_GEN_PROGS): helpers.c helpers.h +$(TEST_GEN_PROGS): helpers.c diff --git a/tools/testing/selftests/seccomp/seccomp_benchmark.c b/tools/testing/selftests/seccomp/seccomp_benchmark.c index b83099160fbc..94886c82ae60 100644 --- a/tools/testing/selftests/seccomp/seccomp_benchmark.c +++ b/tools/testing/selftests/seccomp/seccomp_benchmark.c @@ -194,14 +194,14 @@ int main(int argc, char *argv[]) ksft_set_plan(7); ksft_print_msg("Running on:\n"); - ksft_print_msg(""); + ksft_print_msg("%s", ""); system("uname -a"); ksft_print_msg("Current BPF sysctl settings:\n"); /* Avoid using "sysctl" which may not be installed. */ - ksft_print_msg(""); + ksft_print_msg("%s", ""); system("grep -H . /proc/sys/net/core/bpf_jit_enable"); - ksft_print_msg(""); + ksft_print_msg("%s", ""); system("grep -H . /proc/sys/net/core/bpf_jit_harden"); affinity(); diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c index 86d267db87bb..7bc74969a819 100644 --- a/virt/kvm/dirty_ring.c +++ b/virt/kvm/dirty_ring.c @@ -55,6 +55,9 @@ static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask) struct kvm_memory_slot *memslot; int as_id, id; + if (!mask) + return; + as_id = slot >> 16; id = (u16)slot; diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 0f4e0cf4f158..747fe251e445 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -510,8 +510,10 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, } if (folio_test_hwpoison(folio)) { + folio_unlock(folio); + folio_put(folio); r = -EHWPOISON; - goto out_unlock; + goto out_fput; } page = folio_file_page(folio, index); @@ -522,7 +524,6 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, r = 0; -out_unlock: folio_unlock(folio); out_fput: fput(file); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 14841acb8b95..1192942aef91 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -651,7 +651,7 @@ static __always_inline kvm_mn_ret_t __kvm_handle_hva_range(struct kvm *kvm, range->on_lock(kvm); if (IS_KVM_NULL_FN(range->handler)) - break; + goto mmu_unlock; } r.ret |= range->handler(kvm, &gfn_range); } @@ -660,6 +660,7 @@ static __always_inline kvm_mn_ret_t __kvm_handle_hva_range(struct kvm *kvm, if (range->flush_on_ret && r.ret) kvm_flush_remote_tlbs(kvm); +mmu_unlock: if (r.found_memslot) KVM_MMU_UNLOCK(kvm); @@ -4025,12 +4026,13 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) { struct kvm *kvm = me->kvm; struct kvm_vcpu *vcpu; - int last_boosted_vcpu = me->kvm->last_boosted_vcpu; + int last_boosted_vcpu; unsigned long i; int yielded = 0; int try = 3; int pass; + last_boosted_vcpu = READ_ONCE(kvm->last_boosted_vcpu); kvm_vcpu_set_in_spin_loop(me, true); /* * We boost the priority of a VCPU that is runnable but not @@ -4068,7 +4070,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) yielded = kvm_vcpu_yield_to(vcpu); if (yielded > 0) { - kvm->last_boosted_vcpu = i; + WRITE_ONCE(kvm->last_boosted_vcpu, i); break; } else if (yielded < 0) { try--; @@ -4427,7 +4429,7 @@ static long kvm_vcpu_ioctl(struct file *filp, struct kvm_regs *kvm_regs; r = -ENOMEM; - kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL_ACCOUNT); + kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL); if (!kvm_regs) goto out; r = kvm_arch_vcpu_ioctl_get_regs(vcpu, kvm_regs); @@ -4454,8 +4456,7 @@ out_free1: break; } case KVM_GET_SREGS: { - kvm_sregs = kzalloc(sizeof(struct kvm_sregs), - GFP_KERNEL_ACCOUNT); + kvm_sregs = kzalloc(sizeof(struct kvm_sregs), GFP_KERNEL); r = -ENOMEM; if (!kvm_sregs) goto out; @@ -4547,7 +4548,7 @@ out_free1: break; } case KVM_GET_FPU: { - fpu = kzalloc(sizeof(struct kvm_fpu), GFP_KERNEL_ACCOUNT); + fpu = kzalloc(sizeof(struct kvm_fpu), GFP_KERNEL); r = -ENOMEM; if (!fpu) goto out; @@ -6210,7 +6211,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) active = kvm_active_vms; mutex_unlock(&kvm_lock); - env = kzalloc(sizeof(*env), GFP_KERNEL_ACCOUNT); + env = kzalloc(sizeof(*env), GFP_KERNEL); if (!env) return; @@ -6226,7 +6227,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) add_uevent_var(env, "PID=%d", kvm->userspace_pid); if (!IS_ERR(kvm->debugfs_dentry)) { - char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL_ACCOUNT); + char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL); if (p) { tmp = dentry_path_raw(kvm->debugfs_dentry, p, PATH_MAX); |
