diff options
539 files changed, 9755 insertions, 3973 deletions
@@ -223,6 +223,8 @@ Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com> Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com> Domen Puncer <domen@coderock.org> Douglas Gilbert <dougg@torque.net> +Drew Fustini <fustini@kernel.org> <drew@pdp7.com> +<duje@dujemihanovic.xyz> <duje.mihanovic@skole.hr> Ed L. Cashin <ecashin@coraid.com> Elliot Berman <quic_eberman@quicinc.com> <eberman@codeaurora.org> Enric Balletbo i Serra <eballetbo@kernel.org> <enric.balletbo@collabora.com> @@ -830,3 +832,6 @@ Yosry Ahmed <yosry.ahmed@linux.dev> <yosryahmed@google.com> Yusuke Goda <goda.yusuke@renesas.com> Zack Rusin <zack.rusin@broadcom.com> <zackr@vmware.com> Zhu Yanjun <zyjzyj2000@gmail.com> <yanjunz@nvidia.com> +Zijun Hu <zijun.hu@oss.qualcomm.com> <quic_zijuhu@quicinc.com> +Zijun Hu <zijun.hu@oss.qualcomm.com> <zijuhu@codeaurora.org> +Zijun Hu <zijun_hu@htc.com> diff --git a/Documentation/ABI/testing/sysfs-edac-scrub b/Documentation/ABI/testing/sysfs-edac-scrub index c43be90deab4..ab6014743da5 100644 --- a/Documentation/ABI/testing/sysfs-edac-scrub +++ b/Documentation/ABI/testing/sysfs-edac-scrub @@ -49,6 +49,12 @@ Description: (RO) Supported minimum scrub cycle duration in seconds by the memory scrubber. + Device-based scrub: returns the minimum scrub cycle + supported by the memory device. + + Region-based scrub: returns the max of minimum scrub cycles + supported by individual memory devices that back the region. + What: /sys/bus/edac/devices/<dev-name>/scrubX/max_cycle_duration Date: March 2025 KernelVersion: 6.15 @@ -57,6 +63,16 @@ Description: (RO) Supported maximum scrub cycle duration in seconds by the memory scrubber. + Device-based scrub: returns the maximum scrub cycle supported + by the memory device. + + Region-based scrub: returns the min of maximum scrub cycles + supported by individual memory devices that back the region. + + If the memory device does not provide maximum scrub cycle + information, return the maximum supported value of the scrub + cycle field. + What: /sys/bus/edac/devices/<dev-name>/scrubX/current_cycle_duration Date: March 2025 KernelVersion: 6.15 diff --git a/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi83.yaml b/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi83.yaml index 9b5f3f3eab19..e69b6343a8eb 100644 --- a/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi83.yaml +++ b/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi83.yaml @@ -118,15 +118,11 @@ $defs: ti,lvds-vod-swing-clock-microvolt: description: LVDS diferential output voltage <min max> for clock lanes in microvolts. - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 2 maxItems: 2 ti,lvds-vod-swing-data-microvolt: description: LVDS diferential output voltage <min max> for data lanes in microvolts. - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 2 maxItems: 2 allOf: diff --git a/Documentation/devicetree/bindings/net/airoha,an7583-mdio.yaml b/Documentation/devicetree/bindings/net/airoha,an7583-mdio.yaml new file mode 100644 index 000000000000..3e7e68ec1560 --- /dev/null +++ b/Documentation/devicetree/bindings/net/airoha,an7583-mdio.yaml @@ -0,0 +1,59 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/airoha,an7583-mdio.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Airoha AN7583 Dedicated MDIO Controller + +maintainers: + - Christian Marangi <ansuelsmth@gmail.com> + +description: + Airoha AN7583 SoC have 3 different MDIO Controller. + + One comes from the intergated Switch based on MT7530. + + The other 2 (that this schema describe) live under the SCU + register supporting both C22 and C45 PHYs. + +$ref: mdio.yaml# + +properties: + compatible: + const: airoha,an7583-mdio + + reg: + enum: [0xc8, 0xcc] + + clocks: + maxItems: 1 + + resets: + maxItems: 1 + + clock-frequency: + default: 2500000 + +required: + - compatible + - reg + - clocks + - resets + +unevaluatedProperties: false + +examples: + - | + system-controller { + #address-cells = <1>; + #size-cells = <0>; + + mdio-bus@c8 { + compatible = "airoha,an7583-mdio"; + reg = <0xc8>; + + clocks = <&scu>; + resets = <&scu>; + }; + }; diff --git a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml index 7b6a2fde8175..0ae415f1e69c 100644 --- a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml +++ b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml @@ -21,6 +21,7 @@ properties: - items: - enum: - allwinner,sun20i-d1-emac + - allwinner,sun50i-a100-emac - allwinner,sun50i-h6-emac - allwinner,sun50i-h616-emac0 - allwinner,sun55i-a523-emac0 diff --git a/Documentation/devicetree/bindings/net/altr,gmii-to-sgmii-2.0.yaml b/Documentation/devicetree/bindings/net/altr,gmii-to-sgmii-2.0.yaml new file mode 100644 index 000000000000..aafb6447b6c2 --- /dev/null +++ b/Documentation/devicetree/bindings/net/altr,gmii-to-sgmii-2.0.yaml @@ -0,0 +1,49 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +# Copyright (C) 2025 Altera Corporation +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/altr,gmii-to-sgmii-2.0.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Altera GMII to SGMII Converter + +maintainers: + - Matthew Gerlach <matthew.gerlach@altera.com> + +description: + This binding describes the Altera GMII to SGMII converter. + +properties: + compatible: + const: altr,gmii-to-sgmii-2.0 + + reg: + items: + - description: Registers for the emac splitter IP + - description: Registers for the GMII to SGMII converter. + - description: Registers for TSE control. + + reg-names: + items: + - const: hps_emac_interface_splitter_avalon_slave + - const: gmii_to_sgmii_adapter_avalon_slave + - const: eth_tse_control_port + +required: + - compatible + - reg + - reg-names + +unevaluatedProperties: false + +examples: + - | + phy@ff000240 { + compatible = "altr,gmii-to-sgmii-2.0"; + reg = <0xff000240 0x00000008>, + <0xff000200 0x00000040>, + <0xff000250 0x00000008>; + reg-names = "hps_emac_interface_splitter_avalon_slave", + "gmii_to_sgmii_adapter_avalon_slave", + "eth_tse_control_port"; + }; diff --git a/Documentation/devicetree/bindings/net/altr,socfpga-stmmac.yaml b/Documentation/devicetree/bindings/net/altr,socfpga-stmmac.yaml new file mode 100644 index 000000000000..c5d8dfe5b801 --- /dev/null +++ b/Documentation/devicetree/bindings/net/altr,socfpga-stmmac.yaml @@ -0,0 +1,166 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/altr,socfpga-stmmac.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Altera SOCFPGA SoC DWMAC controller + +maintainers: + - Matthew Gerlach <matthew.gerlach@altera.com> + +description: + This binding describes the Altera SOCFPGA SoC implementation of the + Synopsys DWMAC for the Cyclone5, Arria5, Stratix10, and Agilex7 families + of chips. + # TODO: Determine how to handle the Arria10 reset-name, stmmaceth-ocp, that + # does not validate against net/snps,dwmac.yaml. + +select: + properties: + compatible: + contains: + enum: + - altr,socfpga-stmmac + - altr,socfpga-stmmac-a10-s10 + + required: + - compatible + +properties: + compatible: + oneOf: + - items: + - const: altr,socfpga-stmmac + - const: snps,dwmac-3.70a + - const: snps,dwmac + - items: + - const: altr,socfpga-stmmac-a10-s10 + - const: snps,dwmac-3.72a + - const: snps,dwmac + - items: + - const: altr,socfpga-stmmac-a10-s10 + - const: snps,dwmac-3.74a + - const: snps,dwmac + + clocks: + minItems: 1 + items: + - description: GMAC main clock + - description: + PTP reference clock. This clock is used for programming the + Timestamp Addend Register. If not passed then the system + clock will be used and this is fine on some platforms. + + clock-names: + minItems: 1 + items: + - const: stmmaceth + - const: ptp_ref + + iommus: + maxItems: 2 + + phy-mode: + enum: + - gmii + - mii + - rgmii + - rgmii-id + - rgmii-rxid + - rgmii-txid + - sgmii + - 1000base-x + + rxc-skew-ps: + description: Skew control of RXC pad + + rxd0-skew-ps: + description: Skew control of RX data 0 pad + + rxd1-skew-ps: + description: Skew control of RX data 1 pad + + rxd2-skew-ps: + description: Skew control of RX data 2 pad + + rxd3-skew-ps: + description: Skew control of RX data 3 pad + + rxdv-skew-ps: + description: Skew control of RX CTL pad + + txc-skew-ps: + description: Skew control of TXC pad + + txen-skew-ps: + description: Skew control of TXC pad + + altr,emac-splitter: + $ref: /schemas/types.yaml#/definitions/phandle + description: + Should be the phandle to the emac splitter soft IP node if DWMAC + controller is connected an emac splitter. + + altr,f2h_ptp_ref_clk: + $ref: /schemas/types.yaml#/definitions/phandle + description: + Phandle to Precision Time Protocol reference clock. This clock is + common to gmac instances and defaults to osc1. + + altr,gmii-to-sgmii-converter: + $ref: /schemas/types.yaml#/definitions/phandle + description: + Should be the phandle to the gmii to sgmii converter soft IP. + + altr,sysmgr-syscon: + $ref: /schemas/types.yaml#/definitions/phandle-array + description: + Should be the phandle to the system manager node that encompass + the glue register, the register offset, and the register shift. + On Cyclone5/Arria5, the register shift represents the PHY mode + bits, while on the Arria10/Stratix10/Agilex platforms, the + register shift represents bit for each emac to enable/disable + signals from the FPGA fabric to the EMAC modules. + items: + - items: + - description: phandle to the system manager node + - description: offset of the control register + - description: shift within the control register + +patternProperties: + "^mdio[0-9]$": + type: object + +required: + - compatible + - clocks + - clock-names + - altr,sysmgr-syscon + +allOf: + - $ref: snps,dwmac.yaml# + +unevaluatedProperties: false + +examples: + + - | + #include <dt-bindings/interrupt-controller/arm-gic.h> + #include <dt-bindings/interrupt-controller/irq.h> + soc { + #address-cells = <1>; + #size-cells = <1>; + ethernet@ff700000 { + compatible = "altr,socfpga-stmmac", "snps,dwmac-3.70a", + "snps,dwmac"; + altr,sysmgr-syscon = <&sysmgr 0x60 0>; + reg = <0xff700000 0x2000>; + interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq"; + mac-address = [00 00 00 00 00 00]; /* Filled in by U-Boot */ + clocks = <&emac_0_clk>; + clock-names = "stmmaceth"; + phy-mode = "sgmii"; + }; + }; diff --git a/Documentation/devicetree/bindings/net/dsa/micrel,ks8995.yaml b/Documentation/devicetree/bindings/net/dsa/micrel,ks8995.yaml new file mode 100644 index 000000000000..854808ff5ad5 --- /dev/null +++ b/Documentation/devicetree/bindings/net/dsa/micrel,ks8995.yaml @@ -0,0 +1,135 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/dsa/micrel,ks8995.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Micrel KS8995 Family DSA Switches + +maintainers: + - Linus Walleij <linus.walleij@linaro.org> + +description: + The Micrel KS8995 DSA Switches are 100 Mbit switches that were produced in + the early-to-mid 2000s. The chip features a CPU port and four outgoing ports, + each with an internal PHY. The chip itself is managed over SPI, but all the + PHYs need to be accessed from an external MDIO channel. + + Further, a fifth PHY is available and can be used separately from the switch + fabric, connected to an external MII interface name MII-P5. This is + unrelated from the CPU-facing port 5 which is used for DSA MII traffic. + +properties: + compatible: + enum: + - micrel,ks8995 + - micrel,ksz8795 + - micrel,ksz8864 + + reg: + maxItems: 1 + + reset-gpios: + description: GPIO to be used to reset the whole device + maxItems: 1 + +allOf: + - $ref: dsa.yaml#/$defs/ethernet-ports + - $ref: /schemas/spi/spi-peripheral-props.yaml# + +required: + - compatible + - reg + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + + spi { + #address-cells = <1>; + #size-cells = <0>; + + ethernet-switch@0 { + compatible = "micrel,ks8995"; + reg = <0>; + spi-max-frequency = <25000000>; + + ethernet-ports { + #address-cells = <1>; + #size-cells = <0>; + + ethernet-port@0 { + reg = <0>; + label = "lan1"; + }; + ethernet-port@1 { + reg = <1>; + label = "lan2"; + }; + ethernet-port@2 { + reg = <2>; + label = "lan3"; + }; + ethernet-port@3 { + reg = <3>; + label = "lan4"; + }; + ethernet-port@4 { + reg = <4>; + ethernet = <&mac2>; + phy-mode = "mii"; + fixed-link { + speed = <100>; + full-duplex; + }; + }; + }; + }; + }; + + soc { + #address-cells = <1>; + #size-cells = <1>; + + /* The WAN port connected on MII-P5 */ + ethernet-port@1000 { + reg = <0x00001000 0x1000>; + label = "wan"; + phy-mode = "mii"; + phy-handle = <&phy5>; + }; + + mac2: ethernet-port@2000 { + reg = <0x00002000 0x1000>; + phy-mode = "mii"; + fixed-link { + speed = <100>; + full-duplex; + }; + }; + }; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + /* LAN PHYs 1-4 accessible over external MDIO */ + phy1: ethernet-phy@1 { + reg = <1>; + }; + phy2: ethernet-phy@2 { + reg = <2>; + }; + phy3: ethernet-phy@3 { + reg = <3>; + }; + phy4: ethernet-phy@4 { + reg = <4>; + }; + /* WAN PHY accessible over external MDIO */ + phy5: ethernet-phy@5 { + reg = <5>; + }; + }; diff --git a/Documentation/devicetree/bindings/net/lpc-eth.txt b/Documentation/devicetree/bindings/net/lpc-eth.txt deleted file mode 100644 index cfe0e5991d46..000000000000 --- a/Documentation/devicetree/bindings/net/lpc-eth.txt +++ /dev/null @@ -1,28 +0,0 @@ -* NXP LPC32xx SoC Ethernet Controller - -Required properties: -- compatible: Should be "nxp,lpc-eth" -- reg: Address and length of the register set for the device -- interrupts: Should contain ethernet controller interrupt - -Optional properties: -- phy-mode: See ethernet.txt file in the same directory. If the property is - absent, "rmii" is assumed. -- use-iram: Use LPC32xx internal SRAM (IRAM) for DMA buffering - -Optional subnodes: -- mdio : specifies the mdio bus, used as a container for phy nodes according to - phy.txt in the same directory - - -Example: - - mac: ethernet@31060000 { - compatible = "nxp,lpc-eth"; - reg = <0x31060000 0x1000>; - interrupt-parent = <&mic>; - interrupts = <29 0>; - - phy-mode = "rmii"; - use-iram; - }; diff --git a/Documentation/devicetree/bindings/net/micrel-ks8995.txt b/Documentation/devicetree/bindings/net/micrel-ks8995.txt deleted file mode 100644 index 281bc2498d12..000000000000 --- a/Documentation/devicetree/bindings/net/micrel-ks8995.txt +++ /dev/null @@ -1,20 +0,0 @@ -Micrel KS8995 SPI controlled Ethernet Switch families - -Required properties (according to spi-bus.txt): -- compatible: either "micrel,ks8995", "micrel,ksz8864" or "micrel,ksz8795" - -Optional properties: -- reset-gpios : phandle of gpio that will be used to reset chip during probe - -Example: - -spi-master { - ... - switch@0 { - compatible = "micrel,ksz8795"; - - reg = <0>; - spi-max-frequency = <50000000>; - reset-gpios = <&gpio0 46 GPIO_ACTIVE_LOW>; - }; -}; diff --git a/Documentation/devicetree/bindings/net/nfc/ti,trf7970a.yaml b/Documentation/devicetree/bindings/net/nfc/ti,trf7970a.yaml index d0332eb76ad2..5f49bd9ac5e6 100644 --- a/Documentation/devicetree/bindings/net/nfc/ti,trf7970a.yaml +++ b/Documentation/devicetree/bindings/net/nfc/ti,trf7970a.yaml @@ -55,6 +55,12 @@ properties: description: | Regulator for supply voltage to VIN pin + ti,rx-gain-reduction-db: + $ref: /schemas/types.yaml#/definitions/uint32 + description: | + Specify an RX gain reduction to reduce antenna sensitivity with 5dB per + increment, with a maximum of 15dB. Supported values: [0, 5, 10, 15]. + required: - compatible - interrupts @@ -95,5 +101,6 @@ examples: irq-status-read-quirk; en2-rf-quirk; clock-frequency = <27120000>; + ti,rx-gain-reduction-db = <15>; }; }; diff --git a/Documentation/devicetree/bindings/net/nxp,lpc-eth.yaml b/Documentation/devicetree/bindings/net/nxp,lpc-eth.yaml new file mode 100644 index 000000000000..dfe9446a5375 --- /dev/null +++ b/Documentation/devicetree/bindings/net/nxp,lpc-eth.yaml @@ -0,0 +1,48 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/nxp,lpc-eth.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: NXP LPC32xx SoC Ethernet Controller + +maintainers: + - Frank Li <Frank.Li@nxp.com> + +properties: + compatible: + const: nxp,lpc-eth + + reg: + maxItems: 1 + + clocks: + maxItems: 1 + + interrupts: + maxItems: 1 + + use-iram: + $ref: /schemas/types.yaml#/definitions/flag + description: Use LPC32xx internal SRAM (IRAM) for DMA buffering + +required: + - compatible + - reg + - interrupts + +allOf: + - $ref: ethernet-controller.yaml# + +unevaluatedProperties: false + +examples: + - | + ethernet@31060000 { + compatible = "nxp,lpc-eth"; + reg = <0x31060000 0x1000>; + interrupt-parent = <&mic>; + interrupts = <29 0>; + phy-mode = "rmii"; + use-iram; + }; diff --git a/Documentation/devicetree/bindings/net/nxp,lpc1850-dwmac.txt b/Documentation/devicetree/bindings/net/nxp,lpc1850-dwmac.txt deleted file mode 100644 index 7edba1264f6f..000000000000 --- a/Documentation/devicetree/bindings/net/nxp,lpc1850-dwmac.txt +++ /dev/null @@ -1,20 +0,0 @@ -* NXP LPC1850 GMAC ethernet controller - -This device is a platform glue layer for stmmac. -Please see stmmac.txt for the other unchanged properties. - -Required properties: - - compatible: Should contain "nxp,lpc1850-dwmac" - -Examples: - -mac: ethernet@40010000 { - compatible = "nxp,lpc1850-dwmac", "snps,dwmac-3.611", "snps,dwmac"; - reg = <0x40010000 0x2000>; - interrupts = <5>; - interrupt-names = "macirq"; - clocks = <&ccu1 CLK_CPU_ETHERNET>; - clock-names = "stmmaceth"; - resets = <&rgu 22>; - reset-names = "stmmaceth"; -} diff --git a/Documentation/devicetree/bindings/net/nxp,lpc1850-dwmac.yaml b/Documentation/devicetree/bindings/net/nxp,lpc1850-dwmac.yaml new file mode 100644 index 000000000000..05acd9bc7616 --- /dev/null +++ b/Documentation/devicetree/bindings/net/nxp,lpc1850-dwmac.yaml @@ -0,0 +1,85 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/nxp,lpc1850-dwmac.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: NXP LPC1850 GMAC ethernet controller + +maintainers: + - Frank Li <Frank.Li@nxp.com> + +# We need a select here so we don't match all nodes with 'snps,dwmac' +select: + properties: + compatible: + contains: + enum: + - nxp,lpc1850-dwmac + required: + - compatible + +properties: + compatible: + items: + - enum: + - nxp,lpc1850-dwmac + - const: snps,dwmac-3.611 + - const: snps,dwmac + + reg: + maxItems: 1 + + clocks: + maxItems: 1 + + clock-names: + items: + - const: stmmaceth + + interrupts: + maxItems: 1 + + interrupt-names: + items: + - const: macirq + + resets: + maxItems: 1 + + reset-names: + items: + - const: stmmaceth + +required: + - compatible + - reg + - clocks + - clock-names + - interrupts + - interrupt-names + +allOf: + - $ref: snps,dwmac.yaml# + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/clock/lpc18xx-ccu.h> + + ethernet@40010000 { + compatible = "nxp,lpc1850-dwmac", "snps,dwmac-3.611", "snps,dwmac"; + reg = <0x40010000 0x2000>; + interrupts = <5>; + interrupt-names = "macirq"; + clocks = <&ccu1 CLK_CPU_ETHERNET>; + clock-names = "stmmaceth"; + resets = <&rgu 22>; + reset-names = "stmmaceth"; + rx-fifo-depth = <256>; + tx-fifo-depth = <256>; + snps,pbl = <4>; + snps,force_thresh_dma_mode; + phy-mode = "rgmii-id"; + }; diff --git a/Documentation/devicetree/bindings/net/renesas,r9a09g057-gbeth.yaml b/Documentation/devicetree/bindings/net/renesas,rzv2h-gbeth.yaml index 9961253d1d41..23e39bcea96b 100644 --- a/Documentation/devicetree/bindings/net/renesas,r9a09g057-gbeth.yaml +++ b/Documentation/devicetree/bindings/net/renesas,rzv2h-gbeth.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: http://devicetree.org/schemas/net/renesas,r9a09g057-gbeth.yaml# +$id: http://devicetree.org/schemas/net/renesas,rzv2h-gbeth.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: GBETH glue layer for Renesas RZ/V2H(P) (and similar SoCs) diff --git a/Documentation/devicetree/bindings/net/socfpga-dwmac.txt b/Documentation/devicetree/bindings/net/socfpga-dwmac.txt deleted file mode 100644 index 612a8e8abc88..000000000000 --- a/Documentation/devicetree/bindings/net/socfpga-dwmac.txt +++ /dev/null @@ -1,57 +0,0 @@ -Altera SOCFPGA SoC DWMAC controller - -This is a variant of the dwmac/stmmac driver an inherits all descriptions -present in Documentation/devicetree/bindings/net/stmmac.txt. - -The device node has additional properties: - -Required properties: - - compatible : For Cyclone5/Arria5 SoCs it should contain - "altr,socfpga-stmmac". For Arria10/Agilex/Stratix10 SoCs - "altr,socfpga-stmmac-a10-s10". - Along with "snps,dwmac" and any applicable more detailed - designware version numbers documented in stmmac.txt - - altr,sysmgr-syscon : Should be the phandle to the system manager node that - encompasses the glue register, the register offset, and the register shift. - On Cyclone5/Arria5, the register shift represents the PHY mode bits, while - on the Arria10/Stratix10/Agilex platforms, the register shift represents - bit for each emac to enable/disable signals from the FPGA fabric to the - EMAC modules. - - altr,f2h_ptp_ref_clk use f2h_ptp_ref_clk instead of default eosc1 clock - for ptp ref clk. This affects all emacs as the clock is common. - -Optional properties: -altr,emac-splitter: Should be the phandle to the emac splitter soft IP node if - DWMAC controller is connected emac splitter. -phy-mode: The phy mode the ethernet operates in -altr,sgmii-to-sgmii-converter: phandle to the TSE SGMII converter - -This device node has additional phandle dependency, the sgmii converter: - -Required properties: - - compatible : Should be altr,gmii-to-sgmii-2.0 - - reg-names : Should be "eth_tse_control_port" - -Example: - -gmii_to_sgmii_converter: phy@100000240 { - compatible = "altr,gmii-to-sgmii-2.0"; - reg = <0x00000001 0x00000240 0x00000008>, - <0x00000001 0x00000200 0x00000040>; - reg-names = "eth_tse_control_port"; - clocks = <&sgmii_1_clk_0 &emac1 1 &sgmii_clk_125 &sgmii_clk_125>; - clock-names = "tse_pcs_ref_clk_clock_connection", "tse_rx_cdr_refclk"; -}; - -gmac0: ethernet@ff700000 { - compatible = "altr,socfpga-stmmac", "snps,dwmac-3.70a", "snps,dwmac"; - altr,sysmgr-syscon = <&sysmgr 0x60 0>; - reg = <0xff700000 0x2000>; - interrupts = <0 115 4>; - interrupt-names = "macirq"; - mac-address = [00 00 00 00 00 00];/* Filled in by U-Boot */ - clocks = <&emac_0_clk>; - clock-names = "stmmaceth"; - phy-mode = "sgmii"; - altr,gmii-to-sgmii-converter = <&gmii_to_sgmii_converter>; -}; diff --git a/Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml b/Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml index 4dd2dc9c678b..8afbd9ebd73f 100644 --- a/Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml +++ b/Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml @@ -80,6 +80,8 @@ examples: interrupt-parent = <&intc>; interrupts = <296 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq"; + phy-handle = <&phy0>; + phy-mode = "rgmii-id"; resets = <&rst 30>; reset-names = "stmmaceth"; snps,multicast-filter-bins = <0>; @@ -91,7 +93,6 @@ examples: snps,mtl-rx-config = <&gmac0_mtl_rx_setup>; snps,mtl-tx-config = <&gmac0_mtl_tx_setup>; snps,axi-config = <&gmac0_stmmac_axi_setup>; - status = "disabled"; gmac0_mtl_rx_setup: rx-queues-config { snps,rx-queues-to-use = <8>; diff --git a/Documentation/devicetree/bindings/serial/8250.yaml b/Documentation/devicetree/bindings/serial/8250.yaml index 33d2016b6509..c6bc27709bf7 100644 --- a/Documentation/devicetree/bindings/serial/8250.yaml +++ b/Documentation/devicetree/bindings/serial/8250.yaml @@ -45,7 +45,7 @@ allOf: - ns16550 - ns16550a then: - anyOf: + oneOf: - required: [ clock-frequency ] - required: [ clocks ] diff --git a/Documentation/devicetree/bindings/serial/altera_jtaguart.txt b/Documentation/devicetree/bindings/serial/altera_jtaguart.txt deleted file mode 100644 index 55a901051e8f..000000000000 --- a/Documentation/devicetree/bindings/serial/altera_jtaguart.txt +++ /dev/null @@ -1,5 +0,0 @@ -Altera JTAG UART - -Required properties: -- compatible : should be "ALTR,juart-1.0" <DEPRECATED> -- compatible : should be "altr,juart-1.0" diff --git a/Documentation/devicetree/bindings/serial/altera_uart.txt b/Documentation/devicetree/bindings/serial/altera_uart.txt deleted file mode 100644 index 81bf7ffb1a81..000000000000 --- a/Documentation/devicetree/bindings/serial/altera_uart.txt +++ /dev/null @@ -1,8 +0,0 @@ -Altera UART - -Required properties: -- compatible : should be "ALTR,uart-1.0" <DEPRECATED> -- compatible : should be "altr,uart-1.0" - -Optional properties: -- clock-frequency : frequency of the clock input to the UART diff --git a/Documentation/devicetree/bindings/serial/altr,juart-1.0.yaml b/Documentation/devicetree/bindings/serial/altr,juart-1.0.yaml new file mode 100644 index 000000000000..02e20fa591da --- /dev/null +++ b/Documentation/devicetree/bindings/serial/altr,juart-1.0.yaml @@ -0,0 +1,19 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/serial/altr,juart-1.0.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Altera JTAG UART + +maintainers: + - Dinh Nguyen <dinguyen@kernel.org> + +properties: + compatible: + const: altr,juart-1.0 + +required: + - compatible + +additionalProperties: false diff --git a/Documentation/devicetree/bindings/serial/altr,uart-1.0.yaml b/Documentation/devicetree/bindings/serial/altr,uart-1.0.yaml new file mode 100644 index 000000000000..72d4972e1e22 --- /dev/null +++ b/Documentation/devicetree/bindings/serial/altr,uart-1.0.yaml @@ -0,0 +1,25 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/serial/altr,uart-1.0.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Altera UART + +maintainers: + - Dinh Nguyen <dinguyen@kernel.org> + +allOf: + - $ref: /schemas/serial/serial.yaml# + +properties: + compatible: + const: altr,uart-1.0 + + clock-frequency: + description: Frequency of the clock input to the UART. + +required: + - compatible + +unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml b/Documentation/devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml index 234089b5954d..b43df10c5ef4 100644 --- a/Documentation/devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml +++ b/Documentation/devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: http://devicetree.org/schemas//soc/fsl/fsl,ls1028a-reset.yaml# +$id: http://devicetree.org/schemas/soc/fsl/fsl,ls1028a-reset.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale Layerscape Reset Registers Module diff --git a/Documentation/driver-api/dpll.rst b/Documentation/driver-api/dpll.rst index 195e1e5d9a58..eca72d9b9ed8 100644 --- a/Documentation/driver-api/dpll.rst +++ b/Documentation/driver-api/dpll.rst @@ -253,6 +253,31 @@ the pin. ``DPLL_A_PIN_ESYNC_PULSE`` pulse type of Embedded SYNC ========================================= ================================= +Reference SYNC +============== + +The device may support the Reference SYNC feature, which allows the combination +of two inputs into a input pair. In this configuration, clock signals +from both inputs are used to synchronize the DPLL device. The higher frequency +signal is utilized for the loop bandwidth of the DPLL, while the lower frequency +signal is used to syntonize the output signal of the DPLL device. This feature +enables the provision of a high-quality loop bandwidth signal from an external +source. + +A capable input provides a list of inputs that can be bound with to create +Reference SYNC. To control this feature, the user must request a desired +state for a target pin: use ``DPLL_PIN_STATE_CONNECTED`` to enable or +``DPLL_PIN_STATE_DISCONNECTED`` to disable the feature. An input pin can be +bound to only one other pin at any given time. + + ============================== ========================================== + ``DPLL_A_PIN_REFERENCE_SYNC`` nested attribute for providing info or + requesting configuration of the Reference + SYNC feature + ``DPLL_A_PIN_ID`` target pin id for Reference SYNC feature + ``DPLL_A_PIN_STATE`` state of Reference SYNC connection + ============================== ========================================== + Configuration commands group ============================ diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml index bfba466d694a..1c4bb0cbe5f0 100644 --- a/Documentation/netlink/specs/devlink.yaml +++ b/Documentation/netlink/specs/devlink.yaml @@ -224,6 +224,10 @@ definitions: value: 10 - name: binary + - + name: rate-tc-index-max + type: const + value: 7 attribute-sets: - @@ -844,7 +848,23 @@ attribute-sets: - name: region-direct type: flag - + - + name: rate-tc-bws + type: nest + multi-attr: true + nested-attributes: dl-rate-tc-bws + - + name: rate-tc-index + type: u8 + checks: + max: rate-tc-index-max + - + name: rate-tc-bw + type: u32 + doc: | + Specifies the bandwidth share assigned to the Traffic Class. + The bandwidth for the traffic class is determined + in proportion to the sum of the shares of all configured classes. - name: dl-dev-stats subset-of: devlink @@ -1249,6 +1269,14 @@ attribute-sets: - name: flash type: flag + - + name: dl-rate-tc-bws + subset-of: devlink + attributes: + - + name: rate-tc-index + - + name: rate-tc-bw operations: enum-model: directional @@ -2176,6 +2204,7 @@ operations: - rate-tx-priority - rate-tx-weight - rate-parent-node-name + - rate-tc-bws - name: rate-new @@ -2196,6 +2225,7 @@ operations: - rate-tx-priority - rate-tx-weight - rate-parent-node-name + - rate-tc-bws - name: rate-del diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index c13440efab24..5decee61a2c4 100644 --- a/Documentation/netlink/specs/dpll.yaml +++ b/Documentation/netlink/specs/dpll.yaml @@ -428,6 +428,15 @@ attribute-sets: doc: | A ratio of high to low state of a SYNC signal pulse embedded into base clock frequency. Value is in percents. + - + name: reference-sync + type: nest + multi-attr: true + nested-attributes: reference-sync + doc: | + Capable pin provides list of pins that can be bound to create a + reference-sync pin pair. + - name: pin-parent-device subset-of: pin @@ -458,6 +467,14 @@ attribute-sets: name: frequency-min - name: frequency-max + - + name: reference-sync + subset-of: pin + attributes: + - + name: id + - + name: state operations: enum-name: dpll_cmd @@ -598,6 +615,7 @@ operations: - esync-frequency - esync-frequency-supported - esync-pulse + - reference-sync dump: request: @@ -625,6 +643,7 @@ operations: - parent-pin - phase-adjust - esync-frequency + - reference-sync - name: pin-create-ntf doc: Notification about pin appearing diff --git a/Documentation/netlink/specs/rt-neigh.yaml b/Documentation/netlink/specs/rt-neigh.yaml index 25cc2d528d2f..30a9ee16f128 100644 --- a/Documentation/netlink/specs/rt-neigh.yaml +++ b/Documentation/netlink/specs/rt-neigh.yaml @@ -79,6 +79,7 @@ definitions: entries: - managed - locked + - ext-validated - name: rtm-type type: enum diff --git a/Documentation/networking/device_drivers/ethernet/meta/fbnic.rst b/Documentation/networking/device_drivers/ethernet/meta/fbnic.rst index f8592dec8851..afb8353daefd 100644 --- a/Documentation/networking/device_drivers/ethernet/meta/fbnic.rst +++ b/Documentation/networking/device_drivers/ethernet/meta/fbnic.rst @@ -28,6 +28,36 @@ devlink dev info provides version information for all three components. In addition to the version the hg commit hash of the build is included as a separate entry. +Configuration +------------- + +Ringparams (ethtool -g / -G) +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +fbnic has two submission (host -> device) rings for every completion +(device -> host) ring. The three ring objects together form a single +"queue" as used by higher layer software (a Rx, or a Tx queue). + +For Rx the two submission rings are used to pass empty pages to the NIC. +Ring 0 is the Header Page Queue (HPQ), NIC will use its pages to place +L2-L4 headers (or full frames if frame is not header-data split). +Ring 1 is the Payload Page Queue (PPQ) and used for packet payloads. +The completion ring is used to receive packet notifications / metadata. +ethtool ``rx`` ringparam maps to the size of the completion ring, +``rx-mini`` to the HPQ, and ``rx-jumbo`` to the PPQ. + +For Tx both submission rings can be used to submit packets, the completion +ring carries notifications for both. fbnic uses one of the submission +rings for normal traffic from the stack and the second one for XDP frames. +ethtool ``tx`` ringparam controls both the size of the submission rings +and the completion ring. + +Every single entry on the HPQ and PPQ (``rx-mini``, ``rx-jumbo``) +corresponds to 4kB of allocated memory, while entries on the remaining +rings are in units of descriptors (8B). The ideal ratio of submission +and completion ring sizes will depend on the workload, as for small packets +multiple packets will fit into a single page. + Upgrading Firmware ------------------ diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst index 9d22d41a7cd1..5e397798a402 100644 --- a/Documentation/networking/devlink/devlink-port.rst +++ b/Documentation/networking/devlink/devlink-port.rst @@ -418,6 +418,14 @@ API allows to configure following rate object's parameters: to all node children limits. ``tx_max`` is an upper limit for children. ``tx_share`` is a total bandwidth distributed among children. +``tc_bw`` + Allow users to set the bandwidth allocation per traffic class on rate + objects. This enables fine-grained QoS configurations by assigning a relative + share value to each traffic class. The bandwidth is distributed in proportion + to the share value for each class, relative to the sum of all shares. + When applied to a non-leaf node, tc_bw determines how bandwidth is shared + among its child elements. + ``tx_priority`` and ``tx_weight`` can be used simultaneously. In that case nodes with the same priority form a WFQ subgroup in the sibling group and arbitration among them is based on assigned weights. diff --git a/Documentation/networking/devlink/netdevsim.rst b/Documentation/networking/devlink/netdevsim.rst index 88482725422c..3932004eae82 100644 --- a/Documentation/networking/devlink/netdevsim.rst +++ b/Documentation/networking/devlink/netdevsim.rst @@ -62,7 +62,7 @@ Rate objects The ``netdevsim`` driver supports rate objects management, which includes: -- registerging/unregistering leaf rate objects per VF devlink port; +- registering/unregistering leaf rate objects per VF devlink port; - creation/deletion node rate objects; - setting tx_share and tx_max rate values for any rate object type; - setting parent node for any rate object type. diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 9af5a8935d57..2cad74e18f71 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -1891,10 +1891,10 @@ proxy_arp_pvlan - BOOLEAN This technology is known by different names: - In RFC 3069 it is called VLAN Aggregation. - Cisco and Allied Telesyn call it Private VLAN. - Hewlett-Packard call it Source-Port filtering or port-isolation. - Ericsson call it MAC-Forced Forwarding (RFC Draft). + - In RFC 3069 it is called VLAN Aggregation. + - Cisco and Allied Telesyn call it Private VLAN. + - Hewlett-Packard call it Source-Port filtering or port-isolation. + - Ericsson call it MAC-Forced Forwarding (RFC Draft). proxy_delay - INTEGER Delay proxy response. @@ -2487,8 +2487,10 @@ fib_notify_on_flag_change - INTEGER ioam6_id - INTEGER Define the IOAM id of this node. Uses only 24 bits out of 32 in total. - Min: 0 - Max: 0xFFFFFF + Possible value range: + + - Min: 0 + - Max: 0xFFFFFF Default: 0xFFFFFF @@ -2496,8 +2498,10 @@ ioam6_id_wide - LONG INTEGER Define the wide IOAM id of this node. Uses only 56 bits out of 64 in total. Can be different from ioam6_id. - Min: 0 - Max: 0xFFFFFFFFFFFFFF + Possible value range: + + - Min: 0 + - Max: 0xFFFFFFFFFFFFFF Default: 0xFFFFFFFFFFFFFF @@ -3322,31 +3326,27 @@ pf_enable - INTEGER https://datatracker.ietf.org/doc/draft-ietf-tsvwg-sctp-failover for details. - 1: Enable pf. + Possible values: - 0: Disable pf. + - 1: Enable pf. + - 0: Disable pf. Default: 1 pf_expose - INTEGER Unset or enable/disable pf (pf is short for potentially failed) state exposure. Applications can control the exposure of the PF path state - in the SCTP_PEER_ADDR_CHANGE event and the SCTP_GET_PEER_ADDR_INFO - sockopt. When it's unset, no SCTP_PEER_ADDR_CHANGE event with - SCTP_ADDR_PF state will be sent and a SCTP_PF-state transport info - can be got via SCTP_GET_PEER_ADDR_INFO sockopt; When it's enabled, - a SCTP_PEER_ADDR_CHANGE event will be sent for a transport becoming - SCTP_PF state and a SCTP_PF-state transport info can be got via - SCTP_GET_PEER_ADDR_INFO sockopt; When it's disabled, no - SCTP_PEER_ADDR_CHANGE event will be sent and it returns -EACCES when - trying to get a SCTP_PF-state transport info via SCTP_GET_PEER_ADDR_INFO - sockopt. - - 0: Unset pf state exposure, Compatible with old applications. + in the SCTP_PEER_ADDR_CHANGE event and access of SCTP_PF-state + transport info via SCTP_GET_PEER_ADDR_INFO sockopt. - 1: Disable pf state exposure. + Possible values: - 2: Enable pf state exposure. + - 0: Unset pf state exposure (compatible with old applications). No + event will be sent but the transport info can be queried. + - 1: Disable pf state exposure. No event will be sent and trying to + obtain transport info will return -EACCESS. + - 2: Enable pf state exposure. The event will be sent for a transport + becoming SCTP_PF state and transport info can be obtained. Default: 0 @@ -3542,13 +3542,11 @@ sndbuf_policy - INTEGER sctp_mem - vector of 3 INTEGERs: min, pressure, max Number of pages allowed for queueing by all SCTP sockets. - min: Below this number of pages SCTP is not bothered about its - memory appetite. When amount of memory allocated by SCTP exceeds - this number, SCTP starts to moderate memory usage. - - pressure: This value was introduced to follow format of tcp_mem. - - max: Number of pages allowed for queueing by all SCTP sockets. + * min: Below this number of pages SCTP is not bothered about its + memory usage. When amount of memory allocated by SCTP exceeds + this number, SCTP starts to moderate memory usage. + * pressure: This value was introduced to follow format of tcp_mem. + * max: Maximum number of allowed pages. Default is calculated at boot time from amount of available memory. @@ -3556,9 +3554,9 @@ sctp_rmem - vector of 3 INTEGERs: min, default, max Only the first value ("min") is used, "default" and "max" are ignored. - min: Minimal size of receive buffer used by SCTP socket. - It is guaranteed to each SCTP socket (but not association) even - under moderate memory pressure. + * min: Minimal size of receive buffer used by SCTP socket. + It is guaranteed to each SCTP socket (but not association) even + under moderate memory pressure. Default: 4K @@ -3566,14 +3564,16 @@ sctp_wmem - vector of 3 INTEGERs: min, default, max Only the first value ("min") is used, "default" and "max" are ignored. - min: Minimum size of send buffer that can be used by SCTP sockets. - It is guaranteed to each SCTP socket (but not association) even - under moderate memory pressure. + * min: Minimum size of send buffer that can be used by SCTP sockets. + It is guaranteed to each SCTP socket (but not association) even + under moderate memory pressure. Default: 4K addr_scope_policy - INTEGER - Control IPv4 address scoping - draft-stewart-tsvwg-sctp-ipv4-00 + Control IPv4 address scoping (see + https://datatracker.ietf.org/doc/draft-stewart-tsvwg-sctp-ipv4/00/ + for details). - 0 - Disable IPv4 address scoping - 1 - Enable IPv4 address scoping diff --git a/Documentation/networking/tls.rst b/Documentation/networking/tls.rst index c7904a1bc167..36cc7afc2527 100644 --- a/Documentation/networking/tls.rst +++ b/Documentation/networking/tls.rst @@ -16,11 +16,13 @@ User interface Creating a TLS connection ------------------------- -First create a new TCP socket and set the TLS ULP. +First create a new TCP socket and once the connection is established set the +TLS ULP. .. code-block:: c sock = socket(AF_INET, SOCK_STREAM, 0); + connect(sock, addr, addrlen); setsockopt(sock, SOL_TCP, TCP_ULP, "tls", sizeof("tls")); Setting the TLS ULP allows us to set/get TLS socket options. Currently diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst index 1ac62dc3a66f..e1755610b4bc 100644 --- a/Documentation/process/maintainer-netdev.rst +++ b/Documentation/process/maintainer-netdev.rst @@ -312,7 +312,7 @@ Posting as one thread is discouraged because it confuses patchwork (as of patchwork 2.2.2). Co-posting selftests --------------------- +~~~~~~~~~~~~~~~~~~~~ Selftests should be part of the same series as the code changes. Specifically for fixes both code change and related test should go into diff --git a/MAINTAINERS b/MAINTAINERS index bb9df569a3ff..14196433aa87 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3261,10 +3261,15 @@ M: Dinh Nguyen <dinguyen@kernel.org> S: Maintained F: drivers/clk/socfpga/ +ARM/SOCFPGA DWMAC GLUE LAYER BINDINGS +M: Matthew Gerlach <matthew.gerlach@altera.com> +S: Maintained +F: Documentation/devicetree/bindings/net/altr,gmii-to-sgmii-2.0.yaml +F: Documentation/devicetree/bindings/net/altr,socfpga-stmmac.yaml + ARM/SOCFPGA DWMAC GLUE LAYER M: Maxime Chevallier <maxime.chevallier@bootlin.com> S: Maintained -F: Documentation/devicetree/bindings/net/socfpga-dwmac.txt F: drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c ARM/SOCFPGA EDAC BINDINGS @@ -15550,6 +15555,7 @@ F: drivers/net/ethernet/mellanox/mlx4/en_* MELLANOX ETHERNET DRIVER (mlx5e) M: Saeed Mahameed <saeedm@nvidia.com> M: Tariq Toukan <tariqt@nvidia.com> +M: Mark Bloch <mbloch@nvidia.com> L: netdev@vger.kernel.org S: Maintained W: https://www.nvidia.com/networking/ @@ -15619,6 +15625,7 @@ MELLANOX MLX5 core VPI driver M: Saeed Mahameed <saeedm@nvidia.com> M: Leon Romanovsky <leonro@nvidia.com> M: Tariq Toukan <tariqt@nvidia.com> +M: Mark Bloch <mbloch@nvidia.com> L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org S: Maintained @@ -15676,6 +15683,8 @@ MEMBLOCK AND MEMORY MANAGEMENT INITIALIZATION M: Mike Rapoport <rppt@kernel.org> L: linux-mm@kvack.org S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rppt/memblock.git for-next +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rppt/memblock.git fixes F: Documentation/core-api/boot-time-mm.rst F: Documentation/core-api/kho/bindings/memblock/* F: include/linux/memblock.h @@ -15848,6 +15857,17 @@ F: mm/numa.c F: mm/numa_emulation.c F: mm/numa_memblks.c +MEMORY MANAGEMENT - OOM KILLER +M: Michal Hocko <mhocko@suse.com> +R: David Rientjes <rientjes@google.com> +R: Shakeel Butt <shakeel.butt@linux.dev> +L: linux-mm@kvack.org +S: Maintained +F: include/linux/oom.h +F: include/trace/events/oom.h +F: include/uapi/linux/oom.h +F: mm/oom_kill.c + MEMORY MANAGEMENT - PAGE ALLOCATOR M: Andrew Morton <akpm@linux-foundation.org> M: Vlastimil Babka <vbabka@suse.cz> @@ -15862,8 +15882,17 @@ F: include/linux/compaction.h F: include/linux/gfp.h F: include/linux/page-isolation.h F: mm/compaction.c +F: mm/debug_page_alloc.c +F: mm/fail_page_alloc.c F: mm/page_alloc.c +F: mm/page_ext.c +F: mm/page_frag_cache.c F: mm/page_isolation.c +F: mm/page_owner.c +F: mm/page_poison.c +F: mm/page_reporting.c +F: mm/show_mem.c +F: mm/shuffle.c MEMORY MANAGEMENT - RECLAIM M: Andrew Morton <akpm@linux-foundation.org> @@ -15923,9 +15952,9 @@ F: mm/swapfile.c MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE) M: Andrew Morton <akpm@linux-foundation.org> M: David Hildenbrand <david@redhat.com> +M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> R: Zi Yan <ziy@nvidia.com> R: Baolin Wang <baolin.wang@linux.alibaba.com> -R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> R: Liam R. Howlett <Liam.Howlett@oracle.com> R: Nico Pache <npache@redhat.com> R: Ryan Roberts <ryan.roberts@arm.com> @@ -21176,7 +21205,7 @@ M: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com> L: netdev@vger.kernel.org L: linux-renesas-soc@vger.kernel.org S: Maintained -F: Documentation/devicetree/bindings/net/renesas,r9a09g057-gbeth.yaml +F: Documentation/devicetree/bindings/net/renesas,rzv2h-gbeth.yaml F: drivers/net/ethernet/stmicro/stmmac/dwmac-renesas-gbeth.c RENESAS RZ/V2H(P) USB2PHY PORT RESET DRIVER @@ -21388,7 +21417,7 @@ N: spacemit K: spacemit RISC-V THEAD SoC SUPPORT -M: Drew Fustini <drew@pdp7.com> +M: Drew Fustini <fustini@kernel.org> M: Guo Ren <guoren@kernel.org> M: Fu Wei <wefu@redhat.com> L: linux-riscv@lists.infradead.org @@ -22564,9 +22593,11 @@ S: Maintained F: drivers/misc/sgi-xp/ SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS +M: D. Wythe <alibuda@linux.alibaba.com> +M: Dust Li <dust.li@linux.alibaba.com> +M: Sidraya Jayagond <sidraya@linux.ibm.com> M: Wenjia Zhang <wenjia@linux.ibm.com> -M: Jan Karcher <jaka@linux.ibm.com> -R: D. Wythe <alibuda@linux.alibaba.com> +R: Mahanta Jambigi <mjambigi@linux.ibm.com> R: Tony Lu <tonylu@linux.alibaba.com> R: Wen Gu <guwen@linux.alibaba.com> L: linux-rdma@vger.kernel.org @@ -24077,6 +24108,7 @@ M: Bin Du <bin.du@amd.com> L: linux-i2c@vger.kernel.org S: Maintained F: drivers/i2c/busses/i2c-designware-amdisp.c +F: include/linux/soc/amd/isp4_misc.h SYNOPSYS DESIGNWARE MMC/SD/SDIO DRIVER M: Jaehoon Chung <jh80.chung@samsung.com> @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 16 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-linksys-wrv54g.dts b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-linksys-wrv54g.dts index 98275a363c57..cb1842c83ac8 100644 --- a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-linksys-wrv54g.dts +++ b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-linksys-wrv54g.dts @@ -72,10 +72,55 @@ cs-gpios = <&gpio0 5 GPIO_ACTIVE_LOW>; num-chipselects = <1>; - switch@0 { + ethernet-switch@0 { compatible = "micrel,ks8995"; reg = <0>; spi-max-frequency = <50000000>; + + /* + * The PHYs are accessed over the external MDIO + * bus and not internally through the switch control + * registers. + */ + ethernet-ports { + #address-cells = <1>; + #size-cells = <0>; + + ethernet-port@0 { + reg = <0>; + label = "1"; + phy-mode = "mii"; + phy-handle = <&phy1>; + }; + ethernet-port@1 { + reg = <1>; + label = "2"; + phy-mode = "mii"; + phy-handle = <&phy2>; + }; + ethernet-port@2 { + reg = <2>; + label = "3"; + phy-mode = "mii"; + phy-handle = <&phy3>; + }; + ethernet-port@3 { + reg = <3>; + label = "4"; + phy-mode = "mii"; + phy-handle = <&phy4>; + }; + ethernet-port@4 { + reg = <4>; + ethernet = <ðb>; + phy-mode = "mii"; + fixed-link { + speed = <100>; + full-duplex; + }; + }; + + }; }; }; @@ -135,40 +180,59 @@ }; /* - * EthB - connected to the KS8995 switch ports 1-4 - * FIXME: the boardfile defines .phy_mask = 0x1e for this port to enable output to - * all four switch ports, also using an out of tree multiphy patch. - * Do we need a new binding and property for this? + * EthB connects to the KS8995 CPU port and faces ports 1-4 + * through the switch fabric. + * + * To complicate things, the MDIO channel is also only + * accessible through EthB, but used independently for PHY + * control. */ - ethernet@c8009000 { + ethb: ethernet@c8009000 { status = "okay"; queue-rx = <&qmgr 3>; queue-txready = <&qmgr 20>; - phy-mode = "rgmii"; - phy-handle = <&phy4>; + phy-mode = "mii"; + fixed-link { + speed = <100>; + full-duplex; + }; mdio { #address-cells = <1>; #size-cells = <0>; - /* Should be ports 1-4 on the KS8995 switch */ + /* + * LAN ports 1-4 on the KS8995 switch + * and PHY5 for WAN need to be accessed + * through this external MDIO channel. + */ + phy1: ethernet-phy@1 { + reg = <1>; + }; + phy2: ethernet-phy@2 { + reg = <2>; + }; + phy3: ethernet-phy@3 { + reg = <3>; + }; phy4: ethernet-phy@4 { reg = <4>; }; - - /* Should be port 5 on the KS8995 switch */ phy5: ethernet-phy@5 { reg = <5>; }; }; }; - /* EthC - connected to KS8995 switch port 5 */ - ethernet@c800a000 { + /* + * EthC connects to MII-P5 on the KS8995 bypassing + * all of the switch logic and facing PHY5 + */ + ethc: ethernet@c800a000 { status = "okay"; queue-rx = <&qmgr 4>; queue-txready = <&qmgr 21>; - phy-mode = "rgmii"; + phy-mode = "mii"; phy-handle = <&phy5>; }; }; diff --git a/arch/loongarch/include/asm/addrspace.h b/arch/loongarch/include/asm/addrspace.h index fe198b473f84..e739dbc6329d 100644 --- a/arch/loongarch/include/asm/addrspace.h +++ b/arch/loongarch/include/asm/addrspace.h @@ -18,12 +18,12 @@ /* * This gives the physical RAM offset. */ -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #ifndef PHYS_OFFSET #define PHYS_OFFSET _UL(0) #endif extern unsigned long vm_map_base; -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #ifndef IO_BASE #define IO_BASE CSR_DMW0_BASE @@ -66,7 +66,7 @@ extern unsigned long vm_map_base; #define FIXADDR_TOP ((unsigned long)(long)(int)0xfffe0000) #endif -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ #define _ATYPE_ #define _ATYPE32_ #define _ATYPE64_ @@ -85,7 +85,7 @@ extern unsigned long vm_map_base; /* * 32/64-bit LoongArch address spaces */ -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ #define _ACAST32_ #define _ACAST64_ #else diff --git a/arch/loongarch/include/asm/alternative-asm.h b/arch/loongarch/include/asm/alternative-asm.h index ff3d10ac393f..7dc29bd9b2f0 100644 --- a/arch/loongarch/include/asm/alternative-asm.h +++ b/arch/loongarch/include/asm/alternative-asm.h @@ -2,7 +2,7 @@ #ifndef _ASM_ALTERNATIVE_ASM_H #define _ASM_ALTERNATIVE_ASM_H -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ #include <asm/asm.h> @@ -77,6 +77,6 @@ .previous .endm -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* _ASM_ALTERNATIVE_ASM_H */ diff --git a/arch/loongarch/include/asm/alternative.h b/arch/loongarch/include/asm/alternative.h index cee7b29785ab..b5bae21fb3c8 100644 --- a/arch/loongarch/include/asm/alternative.h +++ b/arch/loongarch/include/asm/alternative.h @@ -2,7 +2,7 @@ #ifndef _ASM_ALTERNATIVE_H #define _ASM_ALTERNATIVE_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <linux/types.h> #include <linux/stddef.h> @@ -106,6 +106,6 @@ extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end); #define alternative_2(oldinstr, newinstr1, feature1, newinstr2, feature2) \ (asm volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2) ::: "memory")) -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* _ASM_ALTERNATIVE_H */ diff --git a/arch/loongarch/include/asm/asm-extable.h b/arch/loongarch/include/asm/asm-extable.h index df05005f2b80..d60bdf2e6377 100644 --- a/arch/loongarch/include/asm/asm-extable.h +++ b/arch/loongarch/include/asm/asm-extable.h @@ -7,7 +7,7 @@ #define EX_TYPE_UACCESS_ERR_ZERO 2 #define EX_TYPE_BPF 3 -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ #define __ASM_EXTABLE_RAW(insn, fixup, type, data) \ .pushsection __ex_table, "a"; \ @@ -22,7 +22,7 @@ __ASM_EXTABLE_RAW(\insn, \fixup, EX_TYPE_FIXUP, 0) .endm -#else /* __ASSEMBLY__ */ +#else /* __ASSEMBLER__ */ #include <linux/bits.h> #include <linux/stringify.h> @@ -60,6 +60,6 @@ #define _ASM_EXTABLE_UACCESS_ERR(insn, fixup, err) \ _ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, zero) -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* __ASM_ASM_EXTABLE_H */ diff --git a/arch/loongarch/include/asm/asm.h b/arch/loongarch/include/asm/asm.h index f591b3245def..f018d26fc995 100644 --- a/arch/loongarch/include/asm/asm.h +++ b/arch/loongarch/include/asm/asm.h @@ -110,7 +110,7 @@ #define LONG_SRA srai.w #define LONG_SRAV sra.w -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ #define LONG .word #endif #define LONGSIZE 4 @@ -131,7 +131,7 @@ #define LONG_SRA srai.d #define LONG_SRAV sra.d -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ #define LONG .dword #endif #define LONGSIZE 8 @@ -158,7 +158,7 @@ #define PTR_SCALESHIFT 2 -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ #define PTR .word #endif #define PTRSIZE 4 @@ -181,7 +181,7 @@ #define PTR_SCALESHIFT 3 -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ #define PTR .dword #endif #define PTRSIZE 8 diff --git a/arch/loongarch/include/asm/cpu.h b/arch/loongarch/include/asm/cpu.h index 98cf4d7b4b0a..dfb982fe8701 100644 --- a/arch/loongarch/include/asm/cpu.h +++ b/arch/loongarch/include/asm/cpu.h @@ -46,7 +46,7 @@ #define PRID_PRODUCT_MASK 0x0fff -#if !defined(__ASSEMBLY__) +#if !defined(__ASSEMBLER__) enum cpu_type_enum { CPU_UNKNOWN, @@ -55,7 +55,7 @@ enum cpu_type_enum { CPU_LAST }; -#endif /* !__ASSEMBLY */ +#endif /* !__ASSEMBLER__ */ /* * ISA Level encodings diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h index 6e0a99763a9a..f4caaf764f9e 100644 --- a/arch/loongarch/include/asm/ftrace.h +++ b/arch/loongarch/include/asm/ftrace.h @@ -14,7 +14,7 @@ #define MCOUNT_INSN_SIZE 4 /* sizeof mcount call */ -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #ifndef CONFIG_DYNAMIC_FTRACE @@ -84,7 +84,7 @@ __arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr) #endif -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* CONFIG_FUNCTION_TRACER */ diff --git a/arch/loongarch/include/asm/gpr-num.h b/arch/loongarch/include/asm/gpr-num.h index 996038da806d..af95b941f48b 100644 --- a/arch/loongarch/include/asm/gpr-num.h +++ b/arch/loongarch/include/asm/gpr-num.h @@ -2,7 +2,7 @@ #ifndef __ASM_GPR_NUM_H #define __ASM_GPR_NUM_H -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ .equ .L__gpr_num_zero, 0 .irp num,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31 @@ -25,7 +25,7 @@ .equ .L__gpr_num_$s\num, 23 + \num .endr -#else /* __ASSEMBLY__ */ +#else /* __ASSEMBLER__ */ #define __DEFINE_ASM_GPR_NUMS \ " .equ .L__gpr_num_zero, 0\n" \ @@ -47,6 +47,6 @@ " .equ .L__gpr_num_$s\\num, 23 + \\num\n" \ " .endr\n" \ -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* __ASM_GPR_NUM_H */ diff --git a/arch/loongarch/include/asm/irqflags.h b/arch/loongarch/include/asm/irqflags.h index 003172b8406b..620163628a7f 100644 --- a/arch/loongarch/include/asm/irqflags.h +++ b/arch/loongarch/include/asm/irqflags.h @@ -5,7 +5,7 @@ #ifndef _ASM_IRQFLAGS_H #define _ASM_IRQFLAGS_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <linux/compiler.h> #include <linux/stringify.h> @@ -80,6 +80,6 @@ static inline int arch_irqs_disabled(void) return arch_irqs_disabled_flags(arch_local_save_flags()); } -#endif /* #ifndef __ASSEMBLY__ */ +#endif /* #ifndef __ASSEMBLER__ */ #endif /* _ASM_IRQFLAGS_H */ diff --git a/arch/loongarch/include/asm/jump_label.h b/arch/loongarch/include/asm/jump_label.h index 8a924bd69d19..4000c7603d8e 100644 --- a/arch/loongarch/include/asm/jump_label.h +++ b/arch/loongarch/include/asm/jump_label.h @@ -7,7 +7,7 @@ #ifndef __ASM_JUMP_LABEL_H #define __ASM_JUMP_LABEL_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <linux/types.h> @@ -50,5 +50,5 @@ l_yes: return true; } -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* __ASM_JUMP_LABEL_H */ diff --git a/arch/loongarch/include/asm/kasan.h b/arch/loongarch/include/asm/kasan.h index 7f52bd31b9d4..62f139a9c87d 100644 --- a/arch/loongarch/include/asm/kasan.h +++ b/arch/loongarch/include/asm/kasan.h @@ -2,7 +2,7 @@ #ifndef __ASM_KASAN_H #define __ASM_KASAN_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <linux/linkage.h> #include <linux/mmzone.h> diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h index d84dac88a584..a0994d226eff 100644 --- a/arch/loongarch/include/asm/loongarch.h +++ b/arch/loongarch/include/asm/loongarch.h @@ -9,15 +9,15 @@ #include <linux/linkage.h> #include <linux/types.h> -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <larchintrin.h> /* CPUCFG */ #define read_cpucfg(reg) __cpucfg(reg) -#endif /* !__ASSEMBLY__ */ +#endif /* !__ASSEMBLER__ */ -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ /* LoongArch Registers */ #define REG_ZERO 0x0 @@ -53,7 +53,7 @@ #define REG_S7 0x1e #define REG_S8 0x1f -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ /* Bit fields for CPUCFG registers */ #define LOONGARCH_CPUCFG0 0x0 @@ -171,7 +171,7 @@ * SW emulation for KVM hypervirsor, see arch/loongarch/include/uapi/asm/kvm_para.h */ -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ /* CSR */ #define csr_read32(reg) __csrrd_w(reg) @@ -187,7 +187,7 @@ #define iocsr_write32(val, reg) __iocsrwr_w(val, reg) #define iocsr_write64(val, reg) __iocsrwr_d(val, reg) -#endif /* !__ASSEMBLY__ */ +#endif /* !__ASSEMBLER__ */ /* CSR register number */ @@ -1195,7 +1195,7 @@ #define LOONGARCH_IOCSR_EXTIOI_ROUTE_BASE 0x1c00 #define IOCSR_EXTIOI_VECTOR_NUM 256 -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ static __always_inline u64 drdtime(void) { @@ -1357,7 +1357,7 @@ __BUILD_CSR_OP(tlbidx) #define clear_csr_estat(val) \ csr_xchg32(~(val), val, LOONGARCH_CSR_ESTAT) -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ /* Generic EntryLo bit definitions */ #define ENTRYLO_V (_ULCAST_(1) << 0) diff --git a/arch/loongarch/include/asm/orc_types.h b/arch/loongarch/include/asm/orc_types.h index caf1f71a1057..d5fa98d1d177 100644 --- a/arch/loongarch/include/asm/orc_types.h +++ b/arch/loongarch/include/asm/orc_types.h @@ -34,7 +34,7 @@ #define ORC_TYPE_REGS 3 #define ORC_TYPE_REGS_PARTIAL 4 -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ /* * This struct is more or less a vastly simplified version of the DWARF Call * Frame Information standard. It contains only the necessary parts of DWARF @@ -53,6 +53,6 @@ struct orc_entry { unsigned int type:3; unsigned int signal:1; }; -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* _ORC_TYPES_H */ diff --git a/arch/loongarch/include/asm/page.h b/arch/loongarch/include/asm/page.h index 7368f12b7cb1..a3aaf34fba16 100644 --- a/arch/loongarch/include/asm/page.h +++ b/arch/loongarch/include/asm/page.h @@ -15,7 +15,7 @@ #define HPAGE_MASK (~(HPAGE_SIZE - 1)) #define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <linux/kernel.h> #include <linux/pfn.h> @@ -110,6 +110,6 @@ extern int __virt_addr_valid(volatile void *kaddr); #include <asm-generic/memory_model.h> #include <asm-generic/getorder.h> -#endif /* !__ASSEMBLY__ */ +#endif /* !__ASSEMBLER__ */ #endif /* _ASM_PAGE_H */ diff --git a/arch/loongarch/include/asm/pgtable-bits.h b/arch/loongarch/include/asm/pgtable-bits.h index 45bfc65a0c9f..7bbfb04a54cc 100644 --- a/arch/loongarch/include/asm/pgtable-bits.h +++ b/arch/loongarch/include/asm/pgtable-bits.h @@ -92,7 +92,7 @@ #define PAGE_KERNEL_WUC __pgprot(_PAGE_PRESENT | __READABLE | __WRITEABLE | \ _PAGE_GLOBAL | _PAGE_KERN | _CACHE_WUC) -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #define _PAGE_IOREMAP pgprot_val(PAGE_KERNEL_SUC) @@ -127,6 +127,6 @@ static inline pgprot_t pgprot_writecombine(pgprot_t _prot) return __pgprot(prot); } -#endif /* !__ASSEMBLY__ */ +#endif /* !__ASSEMBLER__ */ #endif /* _ASM_PGTABLE_BITS_H */ diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index b30185302c07..f2aeff544cee 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -55,7 +55,7 @@ #define USER_PTRS_PER_PGD ((TASK_SIZE64 / PGDIR_SIZE)?(TASK_SIZE64 / PGDIR_SIZE):1) -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <linux/mm_types.h> #include <linux/mmzone.h> @@ -618,6 +618,6 @@ static inline long pmd_protnone(pmd_t pmd) #define HAVE_ARCH_UNMAPPED_AREA #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN -#endif /* !__ASSEMBLY__ */ +#endif /* !__ASSEMBLER__ */ #endif /* _ASM_PGTABLE_H */ diff --git a/arch/loongarch/include/asm/prefetch.h b/arch/loongarch/include/asm/prefetch.h index 1672262a5e2e..0b168cdaae9a 100644 --- a/arch/loongarch/include/asm/prefetch.h +++ b/arch/loongarch/include/asm/prefetch.h @@ -8,7 +8,7 @@ #define Pref_Load 0 #define Pref_Store 8 -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ .macro __pref hint addr #ifdef CONFIG_CPU_HAS_PREFETCH diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h index ad0bd234a0f1..3a47f52959a8 100644 --- a/arch/loongarch/include/asm/smp.h +++ b/arch/loongarch/include/asm/smp.h @@ -39,7 +39,7 @@ int loongson_cpu_disable(void); void loongson_cpu_die(unsigned int cpu); #endif -static inline void plat_smp_setup(void) +static inline void __init plat_smp_setup(void) { loongson_smp_setup(); } diff --git a/arch/loongarch/include/asm/thread_info.h b/arch/loongarch/include/asm/thread_info.h index 4f5a9441754e..9dfa2ef00816 100644 --- a/arch/loongarch/include/asm/thread_info.h +++ b/arch/loongarch/include/asm/thread_info.h @@ -10,7 +10,7 @@ #ifdef __KERNEL__ -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <asm/processor.h> @@ -53,7 +53,7 @@ static inline struct thread_info *current_thread_info(void) register unsigned long current_stack_pointer __asm__("$sp"); -#endif /* !__ASSEMBLY__ */ +#endif /* !__ASSEMBLER__ */ /* thread information allocation */ #define THREAD_SIZE SZ_16K diff --git a/arch/loongarch/include/asm/types.h b/arch/loongarch/include/asm/types.h index baf15a0dcf8b..0edd731f3d6a 100644 --- a/arch/loongarch/include/asm/types.h +++ b/arch/loongarch/include/asm/types.h @@ -8,7 +8,7 @@ #include <asm-generic/int-ll64.h> #include <uapi/asm/types.h> -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ #define _ULCAST_ #define _U64CAST_ #else diff --git a/arch/loongarch/include/asm/unwind_hints.h b/arch/loongarch/include/asm/unwind_hints.h index 2c68bc72736c..16c7f7e465a0 100644 --- a/arch/loongarch/include/asm/unwind_hints.h +++ b/arch/loongarch/include/asm/unwind_hints.h @@ -5,7 +5,7 @@ #include <linux/objtool.h> #include <asm/orc_types.h> -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ .macro UNWIND_HINT_UNDEFINED UNWIND_HINT type=UNWIND_HINT_TYPE_UNDEFINED @@ -23,7 +23,7 @@ UNWIND_HINT sp_reg=ORC_REG_SP type=UNWIND_HINT_TYPE_CALL .endm -#else /* !__ASSEMBLY__ */ +#else /* !__ASSEMBLER__ */ #define UNWIND_HINT_SAVE \ UNWIND_HINT(UNWIND_HINT_TYPE_SAVE, 0, 0, 0) @@ -31,6 +31,6 @@ #define UNWIND_HINT_RESTORE \ UNWIND_HINT(UNWIND_HINT_TYPE_RESTORE, 0, 0, 0) -#endif /* !__ASSEMBLY__ */ +#endif /* !__ASSEMBLER__ */ #endif /* _ASM_LOONGARCH_UNWIND_HINTS_H */ diff --git a/arch/loongarch/include/asm/vdso/arch_data.h b/arch/loongarch/include/asm/vdso/arch_data.h index 322d0a5f1c84..395ec223bcbe 100644 --- a/arch/loongarch/include/asm/vdso/arch_data.h +++ b/arch/loongarch/include/asm/vdso/arch_data.h @@ -7,7 +7,7 @@ #ifndef _VDSO_ARCH_DATA_H #define _VDSO_ARCH_DATA_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <asm/asm.h> #include <asm/vdso.h> @@ -20,6 +20,6 @@ struct vdso_arch_data { struct vdso_pcpu_data pdata[NR_CPUS]; }; -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif diff --git a/arch/loongarch/include/asm/vdso/getrandom.h b/arch/loongarch/include/asm/vdso/getrandom.h index a81724b69f29..2ff05003c6e7 100644 --- a/arch/loongarch/include/asm/vdso/getrandom.h +++ b/arch/loongarch/include/asm/vdso/getrandom.h @@ -5,7 +5,7 @@ #ifndef __ASM_VDSO_GETRANDOM_H #define __ASM_VDSO_GETRANDOM_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <asm/unistd.h> #include <asm/vdso/vdso.h> @@ -28,6 +28,6 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns return ret; } -#endif /* !__ASSEMBLY__ */ +#endif /* !__ASSEMBLER__ */ #endif /* __ASM_VDSO_GETRANDOM_H */ diff --git a/arch/loongarch/include/asm/vdso/gettimeofday.h b/arch/loongarch/include/asm/vdso/gettimeofday.h index f15503e3336c..dcafabca9bb6 100644 --- a/arch/loongarch/include/asm/vdso/gettimeofday.h +++ b/arch/loongarch/include/asm/vdso/gettimeofday.h @@ -7,7 +7,7 @@ #ifndef __ASM_VDSO_GETTIMEOFDAY_H #define __ASM_VDSO_GETTIMEOFDAY_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <asm/unistd.h> #include <asm/vdso/vdso.h> @@ -89,6 +89,6 @@ static inline bool loongarch_vdso_hres_capable(void) } #define __arch_vdso_hres_capable loongarch_vdso_hres_capable -#endif /* !__ASSEMBLY__ */ +#endif /* !__ASSEMBLER__ */ #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/loongarch/include/asm/vdso/processor.h b/arch/loongarch/include/asm/vdso/processor.h index ef5770b343a0..1e255373b0b8 100644 --- a/arch/loongarch/include/asm/vdso/processor.h +++ b/arch/loongarch/include/asm/vdso/processor.h @@ -5,10 +5,10 @@ #ifndef __ASM_VDSO_PROCESSOR_H #define __ASM_VDSO_PROCESSOR_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #define cpu_relax() barrier() -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* __ASM_VDSO_PROCESSOR_H */ diff --git a/arch/loongarch/include/asm/vdso/vdso.h b/arch/loongarch/include/asm/vdso/vdso.h index 50c65fb29daf..04bd2d452876 100644 --- a/arch/loongarch/include/asm/vdso/vdso.h +++ b/arch/loongarch/include/asm/vdso/vdso.h @@ -7,7 +7,7 @@ #ifndef _ASM_VDSO_VDSO_H #define _ASM_VDSO_VDSO_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <asm/asm.h> #include <asm/page.h> @@ -16,6 +16,6 @@ #define VVAR_SIZE (VDSO_NR_PAGES << PAGE_SHIFT) -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif diff --git a/arch/loongarch/include/asm/vdso/vsyscall.h b/arch/loongarch/include/asm/vdso/vsyscall.h index 1140b54b4bc8..558eb9dfda52 100644 --- a/arch/loongarch/include/asm/vdso/vsyscall.h +++ b/arch/loongarch/include/asm/vdso/vsyscall.h @@ -2,13 +2,13 @@ #ifndef __ASM_VDSO_VSYSCALL_H #define __ASM_VDSO_VSYSCALL_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <vdso/datapage.h> /* The asm-generic header needs to be included after the definitions above */ #include <asm-generic/vdso/vsyscall.h> -#endif /* !__ASSEMBLY__ */ +#endif /* !__ASSEMBLER__ */ #endif /* __ASM_VDSO_VSYSCALL_H */ diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c index a54cd6fd3796..1367ca759468 100644 --- a/arch/loongarch/kernel/acpi.c +++ b/arch/loongarch/kernel/acpi.c @@ -10,6 +10,7 @@ #include <linux/init.h> #include <linux/acpi.h> #include <linux/efi-bgrt.h> +#include <linux/export.h> #include <linux/irq.h> #include <linux/irqdomain.h> #include <linux/memblock.h> diff --git a/arch/loongarch/kernel/alternative.c b/arch/loongarch/kernel/alternative.c index 4ad13847e962..0e0c766df1e3 100644 --- a/arch/loongarch/kernel/alternative.c +++ b/arch/loongarch/kernel/alternative.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only +#include <linux/export.h> #include <linux/mm.h> #include <linux/module.h> #include <asm/alternative.h> diff --git a/arch/loongarch/kernel/efi.c b/arch/loongarch/kernel/efi.c index de21e72759ee..860a3bc030e0 100644 --- a/arch/loongarch/kernel/efi.c +++ b/arch/loongarch/kernel/efi.c @@ -144,6 +144,18 @@ void __init efi_init(void) if (efi_memmap_init_early(&data) < 0) panic("Unable to map EFI memory map.\n"); + /* + * Reserve the physical memory region occupied by the EFI + * memory map table (header + descriptors). This is crucial + * for kdump, as the kdump kernel relies on this original + * memmap passed by the bootloader. Without reservation, + * this region could be overwritten by the primary kernel. + * Also, set the EFI_PRESERVE_BS_REGIONS flag to indicate that + * critical boot services code/data regions like this are preserved. + */ + memblock_reserve((phys_addr_t)boot_memmap, sizeof(*tbl) + data.size); + set_bit(EFI_PRESERVE_BS_REGIONS, &efi.flags); + early_memunmap(tbl, sizeof(*tbl)); } diff --git a/arch/loongarch/kernel/elf.c b/arch/loongarch/kernel/elf.c index 0fa81ced28dc..3d98c6aa00db 100644 --- a/arch/loongarch/kernel/elf.c +++ b/arch/loongarch/kernel/elf.c @@ -6,7 +6,6 @@ #include <linux/binfmts.h> #include <linux/elf.h> -#include <linux/export.h> #include <linux/sched.h> #include <asm/cpu-features.h> diff --git a/arch/loongarch/kernel/kfpu.c b/arch/loongarch/kernel/kfpu.c index 4c476904227f..141b49bd989c 100644 --- a/arch/loongarch/kernel/kfpu.c +++ b/arch/loongarch/kernel/kfpu.c @@ -4,6 +4,7 @@ */ #include <linux/cpu.h> +#include <linux/export.h> #include <linux/init.h> #include <asm/fpu.h> #include <asm/smp.h> diff --git a/arch/loongarch/kernel/paravirt.c b/arch/loongarch/kernel/paravirt.c index e5a39bbad078..b1b51f920b23 100644 --- a/arch/loongarch/kernel/paravirt.c +++ b/arch/loongarch/kernel/paravirt.c @@ -1,5 +1,4 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/export.h> #include <linux/types.h> #include <linux/interrupt.h> #include <linux/irq_work.h> diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c index bc75a3a69fc8..367906b10f81 100644 --- a/arch/loongarch/kernel/time.c +++ b/arch/loongarch/kernel/time.c @@ -102,7 +102,7 @@ static int constant_timer_next_event(unsigned long delta, struct clock_event_dev return 0; } -static unsigned long __init get_loops_per_jiffy(void) +static unsigned long get_loops_per_jiffy(void) { unsigned long lpj = (unsigned long)const_clock_freq; diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index 47fc2de6d150..3d9be6ca7ec5 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -13,6 +13,7 @@ #include <linux/kernel.h> #include <linux/kexec.h> #include <linux/module.h> +#include <linux/export.h> #include <linux/extable.h> #include <linux/mm.h> #include <linux/sched/mm.h> diff --git a/arch/loongarch/kernel/unwind_guess.c b/arch/loongarch/kernel/unwind_guess.c index 98379b7d4147..08d7951b2f60 100644 --- a/arch/loongarch/kernel/unwind_guess.c +++ b/arch/loongarch/kernel/unwind_guess.c @@ -3,6 +3,7 @@ * Copyright (C) 2022 Loongson Technology Corporation Limited */ #include <asm/unwind.h> +#include <linux/export.h> unsigned long unwind_get_return_address(struct unwind_state *state) { diff --git a/arch/loongarch/kernel/unwind_orc.c b/arch/loongarch/kernel/unwind_orc.c index d623935a7547..0005be49b056 100644 --- a/arch/loongarch/kernel/unwind_orc.c +++ b/arch/loongarch/kernel/unwind_orc.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only -#include <linux/objtool.h> +#include <linux/export.h> #include <linux/module.h> +#include <linux/objtool.h> #include <linux/sort.h> #include <asm/exception.h> #include <asm/orc_header.h> diff --git a/arch/loongarch/kernel/unwind_prologue.c b/arch/loongarch/kernel/unwind_prologue.c index 929ae240280a..729e775bd40d 100644 --- a/arch/loongarch/kernel/unwind_prologue.c +++ b/arch/loongarch/kernel/unwind_prologue.c @@ -3,6 +3,7 @@ * Copyright (C) 2022 Loongson Technology Corporation Limited */ #include <linux/cpumask.h> +#include <linux/export.h> #include <linux/ftrace.h> #include <linux/kallsyms.h> diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c index f39929d7bf8a..a75f865d6fb9 100644 --- a/arch/loongarch/kvm/intc/eiointc.c +++ b/arch/loongarch/kvm/intc/eiointc.c @@ -9,7 +9,8 @@ static void eiointc_set_sw_coreisr(struct loongarch_eiointc *s) { - int ipnum, cpu, irq_index, irq_mask, irq; + int ipnum, cpu, cpuid, irq_index, irq_mask, irq; + struct kvm_vcpu *vcpu; for (irq = 0; irq < EIOINTC_IRQS; irq++) { ipnum = s->ipmap.reg_u8[irq / 32]; @@ -20,7 +21,12 @@ static void eiointc_set_sw_coreisr(struct loongarch_eiointc *s) irq_index = irq / 32; irq_mask = BIT(irq & 0x1f); - cpu = s->coremap.reg_u8[irq]; + cpuid = s->coremap.reg_u8[irq]; + vcpu = kvm_get_vcpu_by_cpuid(s->kvm, cpuid); + if (!vcpu) + continue; + + cpu = vcpu->vcpu_id; if (!!(s->coreisr.reg_u32[cpu][irq_index] & irq_mask)) set_bit(irq, s->sw_coreisr[cpu][ipnum]); else @@ -66,20 +72,25 @@ static void eiointc_update_irq(struct loongarch_eiointc *s, int irq, int level) } static inline void eiointc_update_sw_coremap(struct loongarch_eiointc *s, - int irq, void *pvalue, u32 len, bool notify) + int irq, u64 val, u32 len, bool notify) { - int i, cpu; - u64 val = *(u64 *)pvalue; + int i, cpu, cpuid; + struct kvm_vcpu *vcpu; for (i = 0; i < len; i++) { - cpu = val & 0xff; + cpuid = val & 0xff; val = val >> 8; if (!(s->status & BIT(EIOINTC_ENABLE_CPU_ENCODE))) { - cpu = ffs(cpu) - 1; - cpu = (cpu >= 4) ? 0 : cpu; + cpuid = ffs(cpuid) - 1; + cpuid = (cpuid >= 4) ? 0 : cpuid; } + vcpu = kvm_get_vcpu_by_cpuid(s->kvm, cpuid); + if (!vcpu) + continue; + + cpu = vcpu->vcpu_id; if (s->sw_coremap[irq + i] == cpu) continue; @@ -305,6 +316,11 @@ static int kvm_eiointc_read(struct kvm_vcpu *vcpu, return -EINVAL; } + if (addr & (len - 1)) { + kvm_err("%s: eiointc not aligned addr %llx len %d\n", __func__, addr, len); + return -EINVAL; + } + vcpu->kvm->stat.eiointc_read_exits++; spin_lock_irqsave(&eiointc->lock, flags); switch (len) { @@ -398,7 +414,7 @@ static int loongarch_eiointc_writeb(struct kvm_vcpu *vcpu, irq = offset - EIOINTC_COREMAP_START; index = irq; s->coremap.reg_u8[index] = data; - eiointc_update_sw_coremap(s, irq, (void *)&data, sizeof(data), true); + eiointc_update_sw_coremap(s, irq, data, sizeof(data), true); break; default: ret = -EINVAL; @@ -436,17 +452,16 @@ static int loongarch_eiointc_writew(struct kvm_vcpu *vcpu, break; case EIOINTC_ENABLE_START ... EIOINTC_ENABLE_END: index = (offset - EIOINTC_ENABLE_START) >> 1; - old_data = s->enable.reg_u32[index]; + old_data = s->enable.reg_u16[index]; s->enable.reg_u16[index] = data; /* * 1: enable irq. * update irq when isr is set. */ data = s->enable.reg_u16[index] & ~old_data & s->isr.reg_u16[index]; - index = index << 1; for (i = 0; i < sizeof(data); i++) { u8 mask = (data >> (i * 8)) & 0xff; - eiointc_enable_irq(vcpu, s, index + i, mask, 1); + eiointc_enable_irq(vcpu, s, index * 2 + i, mask, 1); } /* * 0: disable irq. @@ -455,7 +470,7 @@ static int loongarch_eiointc_writew(struct kvm_vcpu *vcpu, data = ~s->enable.reg_u16[index] & old_data & s->isr.reg_u16[index]; for (i = 0; i < sizeof(data); i++) { u8 mask = (data >> (i * 8)) & 0xff; - eiointc_enable_irq(vcpu, s, index, mask, 0); + eiointc_enable_irq(vcpu, s, index * 2 + i, mask, 0); } break; case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END: @@ -484,7 +499,7 @@ static int loongarch_eiointc_writew(struct kvm_vcpu *vcpu, irq = offset - EIOINTC_COREMAP_START; index = irq >> 1; s->coremap.reg_u16[index] = data; - eiointc_update_sw_coremap(s, irq, (void *)&data, sizeof(data), true); + eiointc_update_sw_coremap(s, irq, data, sizeof(data), true); break; default: ret = -EINVAL; @@ -529,10 +544,9 @@ static int loongarch_eiointc_writel(struct kvm_vcpu *vcpu, * update irq when isr is set. */ data = s->enable.reg_u32[index] & ~old_data & s->isr.reg_u32[index]; - index = index << 2; for (i = 0; i < sizeof(data); i++) { u8 mask = (data >> (i * 8)) & 0xff; - eiointc_enable_irq(vcpu, s, index + i, mask, 1); + eiointc_enable_irq(vcpu, s, index * 4 + i, mask, 1); } /* * 0: disable irq. @@ -541,7 +555,7 @@ static int loongarch_eiointc_writel(struct kvm_vcpu *vcpu, data = ~s->enable.reg_u32[index] & old_data & s->isr.reg_u32[index]; for (i = 0; i < sizeof(data); i++) { u8 mask = (data >> (i * 8)) & 0xff; - eiointc_enable_irq(vcpu, s, index, mask, 0); + eiointc_enable_irq(vcpu, s, index * 4 + i, mask, 0); } break; case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END: @@ -570,7 +584,7 @@ static int loongarch_eiointc_writel(struct kvm_vcpu *vcpu, irq = offset - EIOINTC_COREMAP_START; index = irq >> 2; s->coremap.reg_u32[index] = data; - eiointc_update_sw_coremap(s, irq, (void *)&data, sizeof(data), true); + eiointc_update_sw_coremap(s, irq, data, sizeof(data), true); break; default: ret = -EINVAL; @@ -615,10 +629,9 @@ static int loongarch_eiointc_writeq(struct kvm_vcpu *vcpu, * update irq when isr is set. */ data = s->enable.reg_u64[index] & ~old_data & s->isr.reg_u64[index]; - index = index << 3; for (i = 0; i < sizeof(data); i++) { u8 mask = (data >> (i * 8)) & 0xff; - eiointc_enable_irq(vcpu, s, index + i, mask, 1); + eiointc_enable_irq(vcpu, s, index * 8 + i, mask, 1); } /* * 0: disable irq. @@ -627,7 +640,7 @@ static int loongarch_eiointc_writeq(struct kvm_vcpu *vcpu, data = ~s->enable.reg_u64[index] & old_data & s->isr.reg_u64[index]; for (i = 0; i < sizeof(data); i++) { u8 mask = (data >> (i * 8)) & 0xff; - eiointc_enable_irq(vcpu, s, index, mask, 0); + eiointc_enable_irq(vcpu, s, index * 8 + i, mask, 0); } break; case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END: @@ -656,7 +669,7 @@ static int loongarch_eiointc_writeq(struct kvm_vcpu *vcpu, irq = offset - EIOINTC_COREMAP_START; index = irq >> 3; s->coremap.reg_u64[index] = data; - eiointc_update_sw_coremap(s, irq, (void *)&data, sizeof(data), true); + eiointc_update_sw_coremap(s, irq, data, sizeof(data), true); break; default: ret = -EINVAL; @@ -679,6 +692,11 @@ static int kvm_eiointc_write(struct kvm_vcpu *vcpu, return -EINVAL; } + if (addr & (len - 1)) { + kvm_err("%s: eiointc not aligned addr %llx len %d\n", __func__, addr, len); + return -EINVAL; + } + vcpu->kvm->stat.eiointc_write_exits++; spin_lock_irqsave(&eiointc->lock, flags); switch (len) { @@ -787,7 +805,7 @@ static int kvm_eiointc_ctrl_access(struct kvm_device *dev, int ret = 0; unsigned long flags; unsigned long type = (unsigned long)attr->attr; - u32 i, start_irq; + u32 i, start_irq, val; void __user *data; struct loongarch_eiointc *s = dev->kvm->arch.eiointc; @@ -795,8 +813,14 @@ static int kvm_eiointc_ctrl_access(struct kvm_device *dev, spin_lock_irqsave(&s->lock, flags); switch (type) { case KVM_DEV_LOONGARCH_EXTIOI_CTRL_INIT_NUM_CPU: - if (copy_from_user(&s->num_cpu, data, 4)) + if (copy_from_user(&val, data, 4)) ret = -EFAULT; + else { + if (val >= EIOINTC_ROUTE_MAX_VCPUS) + ret = -EINVAL; + else + s->num_cpu = val; + } break; case KVM_DEV_LOONGARCH_EXTIOI_CTRL_INIT_FEATURE: if (copy_from_user(&s->features, data, 4)) @@ -809,7 +833,7 @@ static int kvm_eiointc_ctrl_access(struct kvm_device *dev, for (i = 0; i < (EIOINTC_IRQS / 4); i++) { start_irq = i * 4; eiointc_update_sw_coremap(s, start_irq, - (void *)&s->coremap.reg_u32[i], sizeof(u32), false); + s->coremap.reg_u32[i], sizeof(u32), false); } break; default: @@ -824,7 +848,7 @@ static int kvm_eiointc_regs_access(struct kvm_device *dev, struct kvm_device_attr *attr, bool is_write) { - int addr, cpuid, offset, ret = 0; + int addr, cpu, offset, ret = 0; unsigned long flags; void *p = NULL; void __user *data; @@ -832,7 +856,7 @@ static int kvm_eiointc_regs_access(struct kvm_device *dev, s = dev->kvm->arch.eiointc; addr = attr->attr; - cpuid = addr >> 16; + cpu = addr >> 16; addr &= 0xffff; data = (void __user *)attr->addr; switch (addr) { @@ -857,8 +881,11 @@ static int kvm_eiointc_regs_access(struct kvm_device *dev, p = &s->isr.reg_u32[offset]; break; case EIOINTC_COREISR_START ... EIOINTC_COREISR_END: + if (cpu >= s->num_cpu) + return -EINVAL; + offset = (addr - EIOINTC_COREISR_START) / 4; - p = &s->coreisr.reg_u32[cpuid][offset]; + p = &s->coreisr.reg_u32[cpu][offset]; break; case EIOINTC_COREMAP_START ... EIOINTC_COREMAP_END: offset = (addr - EIOINTC_COREMAP_START) / 4; @@ -899,9 +926,15 @@ static int kvm_eiointc_sw_status_access(struct kvm_device *dev, data = (void __user *)attr->addr; switch (addr) { case KVM_DEV_LOONGARCH_EXTIOI_SW_STATUS_NUM_CPU: + if (is_write) + return ret; + p = &s->num_cpu; break; case KVM_DEV_LOONGARCH_EXTIOI_SW_STATUS_FEATURE: + if (is_write) + return ret; + p = &s->features; break; case KVM_DEV_LOONGARCH_EXTIOI_SW_STATUS_STATE: diff --git a/arch/loongarch/lib/crc32-loongarch.c b/arch/loongarch/lib/crc32-loongarch.c index b37cd8537b45..db22c2ec55e2 100644 --- a/arch/loongarch/lib/crc32-loongarch.c +++ b/arch/loongarch/lib/crc32-loongarch.c @@ -11,6 +11,7 @@ #include <asm/cpu-features.h> #include <linux/crc32.h> +#include <linux/export.h> #include <linux/module.h> #include <linux/unaligned.h> diff --git a/arch/loongarch/lib/csum.c b/arch/loongarch/lib/csum.c index df309ae4045d..bcc9d01d8c41 100644 --- a/arch/loongarch/lib/csum.c +++ b/arch/loongarch/lib/csum.c @@ -2,6 +2,7 @@ // Copyright (C) 2019-2020 Arm Ltd. #include <linux/compiler.h> +#include <linux/export.h> #include <linux/kasan-checks.h> #include <linux/kernel.h> diff --git a/arch/loongarch/mm/ioremap.c b/arch/loongarch/mm/ioremap.c index 70ca73019811..df949a3d0f34 100644 --- a/arch/loongarch/mm/ioremap.c +++ b/arch/loongarch/mm/ioremap.c @@ -16,12 +16,12 @@ void __init early_iounmap(void __iomem *addr, unsigned long size) } -void *early_memremap_ro(resource_size_t phys_addr, unsigned long size) +void * __init early_memremap_ro(resource_size_t phys_addr, unsigned long size) { return early_memremap(phys_addr, size); } -void *early_memremap_prot(resource_size_t phys_addr, unsigned long size, +void * __init early_memremap_prot(resource_size_t phys_addr, unsigned long size, unsigned long prot_val) { return early_memremap(phys_addr, size); diff --git a/arch/loongarch/pci/pci.c b/arch/loongarch/pci/pci.c index 2726639150bc..5bc9627a6cf9 100644 --- a/arch/loongarch/pci/pci.c +++ b/arch/loongarch/pci/pci.c @@ -3,7 +3,6 @@ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ #include <linux/kernel.h> -#include <linux/export.h> #include <linux/init.h> #include <linux/acpi.h> #include <linux/types.h> diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 438ce7df24c3..5bd5aae60d53 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -1075,7 +1075,6 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) */ #ifdef CONFIG_64BIT #define TASK_SIZE_64 (PGDIR_SIZE * PTRS_PER_PGD / 2) -#define TASK_SIZE_MAX LONG_MAX #ifdef CONFIG_COMPAT #define TASK_SIZE_32 (_AC(0x80000000, UL) - PAGE_SIZE) diff --git a/arch/riscv/include/asm/runtime-const.h b/arch/riscv/include/asm/runtime-const.h index 451fd76b8811..d766e2b9e6df 100644 --- a/arch/riscv/include/asm/runtime-const.h +++ b/arch/riscv/include/asm/runtime-const.h @@ -206,7 +206,7 @@ static inline void __runtime_fixup_32(__le16 *lui_parcel, __le16 *addi_parcel, u addi_insn_mask &= 0x07fff; } - if (lower_immediate & 0x00000fff) { + if (lower_immediate & 0x00000fff || lui_insn == RISCV_INSN_NOP4) { /* replace upper 12 bits of addi with lower 12 bits of val */ addi_insn &= addi_insn_mask; addi_insn |= (lower_immediate & 0x00000fff) << 20; diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index d472da4450e6..525e50db24f7 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -127,6 +127,7 @@ do { \ #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define __get_user_8(x, ptr, label) \ +do { \ u32 __user *__ptr = (u32 __user *)(ptr); \ u32 __lo, __hi; \ asm_goto_output( \ @@ -141,7 +142,7 @@ do { \ : : label); \ (x) = (__typeof__(x))((__typeof__((x) - (x)))( \ (((u64)__hi << 32) | __lo))); \ - +} while (0) #else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ #define __get_user_8(x, ptr, label) \ do { \ diff --git a/arch/riscv/include/asm/vdso/getrandom.h b/arch/riscv/include/asm/vdso/getrandom.h index 8dc92441702a..c6d66895c1f5 100644 --- a/arch/riscv/include/asm/vdso/getrandom.h +++ b/arch/riscv/include/asm/vdso/getrandom.h @@ -18,7 +18,7 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns register unsigned int flags asm("a2") = _flags; asm volatile ("ecall\n" - : "+r" (ret) + : "=r" (ret) : "r" (nr), "r" (buffer), "r" (len), "r" (flags) : "memory"); diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h index 45c9b426fcc5..b61786d43c20 100644 --- a/arch/riscv/include/asm/vector.h +++ b/arch/riscv/include/asm/vector.h @@ -205,11 +205,11 @@ static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to, THEAD_VSETVLI_T4X0E8M8D1 THEAD_VSB_V_V0T0 "add t0, t0, t4\n\t" - THEAD_VSB_V_V0T0 + THEAD_VSB_V_V8T0 "add t0, t0, t4\n\t" - THEAD_VSB_V_V0T0 + THEAD_VSB_V_V16T0 "add t0, t0, t4\n\t" - THEAD_VSB_V_V0T0 + THEAD_VSB_V_V24T0 : : "r" (datap) : "memory", "t0", "t4"); } else { asm volatile ( @@ -241,11 +241,11 @@ static inline void __riscv_v_vstate_restore(struct __riscv_v_ext_state *restore_ THEAD_VSETVLI_T4X0E8M8D1 THEAD_VLB_V_V0T0 "add t0, t0, t4\n\t" - THEAD_VLB_V_V0T0 + THEAD_VLB_V_V8T0 "add t0, t0, t4\n\t" - THEAD_VLB_V_V0T0 + THEAD_VLB_V_V16T0 "add t0, t0, t4\n\t" - THEAD_VLB_V_V0T0 + THEAD_VLB_V_V24T0 : : "r" (datap) : "memory", "t0", "t4"); } else { asm volatile ( diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index f7c9a1caa83e..14888e5ea19a 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -50,6 +50,7 @@ atomic_t hart_lottery __section(".sdata") #endif ; unsigned long boot_cpu_hartid; +EXPORT_SYMBOL_GPL(boot_cpu_hartid); /* * Place kernel memory regions on the resource tree so that diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c index dd8e4af6583f..93043924fe6c 100644 --- a/arch/riscv/kernel/traps_misaligned.c +++ b/arch/riscv/kernel/traps_misaligned.c @@ -454,7 +454,7 @@ static int handle_scalar_misaligned_load(struct pt_regs *regs) val.data_u64 = 0; if (user_mode(regs)) { - if (copy_from_user_nofault(&val, (u8 __user *)addr, len)) + if (copy_from_user(&val, (u8 __user *)addr, len)) return -1; } else { memcpy(&val, (u8 *)addr, len); @@ -555,7 +555,7 @@ static int handle_scalar_misaligned_store(struct pt_regs *regs) return -EOPNOTSUPP; if (user_mode(regs)) { - if (copy_to_user_nofault((u8 __user *)addr, &val, len)) + if (copy_to_user((u8 __user *)addr, &val, len)) return -1; } else { memcpy((u8 *)addr, &val, len); diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S index 7c15b0f4ee3b..c29ef12a63bb 100644 --- a/arch/riscv/kernel/vdso/vdso.lds.S +++ b/arch/riscv/kernel/vdso/vdso.lds.S @@ -30,7 +30,7 @@ SECTIONS *(.data .data.* .gnu.linkonce.d.*) *(.dynbss) *(.bss .bss.* .gnu.linkonce.b.*) - } + } :text .note : { *(.note.*) } :text :note diff --git a/arch/riscv/kernel/vendor_extensions/sifive.c b/arch/riscv/kernel/vendor_extensions/sifive.c index 1411337dc1e6..8fcf67e8c07f 100644 --- a/arch/riscv/kernel/vendor_extensions/sifive.c +++ b/arch/riscv/kernel/vendor_extensions/sifive.c @@ -8,7 +8,7 @@ #include <linux/types.h> /* All SiFive vendor extensions supported in Linux */ -const struct riscv_isa_ext_data riscv_isa_vendor_ext_sifive[] = { +static const struct riscv_isa_ext_data riscv_isa_vendor_ext_sifive[] = { __RISCV_ISA_EXT_DATA(xsfvfnrclipxfqf, RISCV_ISA_VENDOR_EXT_XSFVFNRCLIPXFQF), __RISCV_ISA_EXT_DATA(xsfvfwmaccqqq, RISCV_ISA_VENDOR_EXT_XSFVFWMACCQQQ), __RISCV_ISA_EXT_DATA(xsfvqmaccdod, RISCV_ISA_VENDOR_EXT_XSFVQMACCDOD), diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index 62c0ab4a4b9d..0905fa99a31e 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -265,7 +265,7 @@ static __always_inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *r addr = kernel_stack_pointer(regs) + n * sizeof(long); if (!regs_within_kernel_stack(regs, addr)) return 0; - return READ_ONCE_NOCHECK(addr); + return READ_ONCE_NOCHECK(*(unsigned long *)addr); } /** diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index 2fbee3887d13..d930416d4c90 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -54,6 +54,7 @@ static inline bool ers_result_indicates_abort(pci_ers_result_t ers_res) case PCI_ERS_RESULT_CAN_RECOVER: case PCI_ERS_RESULT_RECOVERED: case PCI_ERS_RESULT_NEED_RESET: + case PCI_ERS_RESULT_NONE: return false; default: return true; @@ -78,10 +79,6 @@ static bool is_driver_supported(struct pci_driver *driver) return false; if (!driver->err_handler->error_detected) return false; - if (!driver->err_handler->slot_reset) - return false; - if (!driver->err_handler->resume) - return false; return true; } @@ -106,6 +103,10 @@ static pci_ers_result_t zpci_event_do_error_state_clear(struct pci_dev *pdev, struct zpci_dev *zdev = to_zpci(pdev); int rc; + /* The underlying device may have been disabled by the event */ + if (!zdev_enabled(zdev)) + return PCI_ERS_RESULT_NEED_RESET; + pr_info("%s: Unblocking device access for examination\n", pci_name(pdev)); rc = zpci_reset_load_store_blocked(zdev); if (rc) { @@ -114,16 +115,18 @@ static pci_ers_result_t zpci_event_do_error_state_clear(struct pci_dev *pdev, return PCI_ERS_RESULT_NEED_RESET; } - if (driver->err_handler->mmio_enabled) { + if (driver->err_handler->mmio_enabled) ers_res = driver->err_handler->mmio_enabled(pdev); - if (ers_result_indicates_abort(ers_res)) { - pr_info("%s: Automatic recovery failed after MMIO re-enable\n", - pci_name(pdev)); - return ers_res; - } else if (ers_res == PCI_ERS_RESULT_NEED_RESET) { - pr_debug("%s: Driver needs reset to recover\n", pci_name(pdev)); - return ers_res; - } + else + ers_res = PCI_ERS_RESULT_NONE; + + if (ers_result_indicates_abort(ers_res)) { + pr_info("%s: Automatic recovery failed after MMIO re-enable\n", + pci_name(pdev)); + return ers_res; + } else if (ers_res == PCI_ERS_RESULT_NEED_RESET) { + pr_debug("%s: Driver needs reset to recover\n", pci_name(pdev)); + return ers_res; } pr_debug("%s: Unblocking DMA\n", pci_name(pdev)); @@ -150,7 +153,12 @@ static pci_ers_result_t zpci_event_do_reset(struct pci_dev *pdev, return ers_res; } pdev->error_state = pci_channel_io_normal; - ers_res = driver->err_handler->slot_reset(pdev); + + if (driver->err_handler->slot_reset) + ers_res = driver->err_handler->slot_reset(pdev); + else + ers_res = PCI_ERS_RESULT_NONE; + if (ers_result_indicates_abort(ers_res)) { pr_info("%s: Automatic recovery failed after slot reset\n", pci_name(pdev)); return ers_res; @@ -214,7 +222,7 @@ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev) goto out_unlock; } - if (ers_res == PCI_ERS_RESULT_CAN_RECOVER) { + if (ers_res != PCI_ERS_RESULT_NEED_RESET) { ers_res = zpci_event_do_error_state_clear(pdev, driver); if (ers_result_indicates_abort(ers_res)) { status_str = "failed (abort on MMIO enable)"; @@ -225,6 +233,16 @@ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev) if (ers_res == PCI_ERS_RESULT_NEED_RESET) ers_res = zpci_event_do_reset(pdev, driver); + /* + * ers_res can be PCI_ERS_RESULT_NONE either because the driver + * decided to return it, indicating that it abstains from voting + * on how to recover, or because it didn't implement the callback. + * Both cases assume, that if there is nothing else causing a + * disconnect, we recovered successfully. + */ + if (ers_res == PCI_ERS_RESULT_NONE) + ers_res = PCI_ERS_RESULT_RECOVERED; + if (ers_res != PCI_ERS_RESULT_RECOVERED) { pr_err("%s: Automatic recovery failed; operator intervention is required\n", pci_name(pdev)); @@ -273,6 +291,8 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid); struct pci_dev *pdev = NULL; pci_ers_result_t ers_res; + u32 fh = 0; + int rc; zpci_dbg(3, "err fid:%x, fh:%x, pec:%x\n", ccdf->fid, ccdf->fh, ccdf->pec); @@ -281,6 +301,15 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) if (zdev) { mutex_lock(&zdev->state_lock); + rc = clp_refresh_fh(zdev->fid, &fh); + if (rc) + goto no_pdev; + if (!fh || ccdf->fh != fh) { + /* Ignore events with stale handles */ + zpci_dbg(3, "err fid:%x, fh:%x (stale %x)\n", + ccdf->fid, fh, ccdf->fh); + goto no_pdev; + } zpci_update_fh(zdev, ccdf->fh); if (zdev->zbus->bus) pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index 363110e6b2e3..a2c1f2d24b64 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -9,6 +9,14 @@ #include <asm/cpufeature.h> #include <asm/msr.h> +/* + * Define bits that are always set to 1 in DR7, only bit 10 is + * architecturally reserved to '1'. + * + * This is also the init/reset value for DR7. + */ +#define DR7_FIXED_1 0x00000400 + DECLARE_PER_CPU(unsigned long, cpu_dr7); #ifndef CONFIG_PARAVIRT_XXL @@ -100,8 +108,8 @@ static __always_inline void native_set_debugreg(int regno, unsigned long value) static inline void hw_breakpoint_disable(void) { - /* Zero the control register for HW Breakpoint */ - set_debugreg(0UL, 7); + /* Reset the control register for HW Breakpoint */ + set_debugreg(DR7_FIXED_1, 7); /* Zero-out the individual HW breakpoint address registers */ set_debugreg(0UL, 0); @@ -125,9 +133,12 @@ static __always_inline unsigned long local_db_save(void) return 0; get_debugreg(dr7, 7); - dr7 &= ~0x400; /* architecturally set bit */ + + /* Architecturally set bit */ + dr7 &= ~DR7_FIXED_1; if (dr7) - set_debugreg(0, 7); + set_debugreg(DR7_FIXED_1, 7); + /* * Ensure the compiler doesn't lower the above statements into * the critical section; disabling breakpoints late would not diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index b4a391929cdb..639d9bcee842 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -31,6 +31,7 @@ #include <asm/apic.h> #include <asm/pvclock-abi.h> +#include <asm/debugreg.h> #include <asm/desc.h> #include <asm/mtrr.h> #include <asm/msr-index.h> @@ -249,7 +250,6 @@ enum x86_intercept_stage; #define DR7_BP_EN_MASK 0x000000ff #define DR7_GE (1 << 9) #define DR7_GD (1 << 13) -#define DR7_FIXED_1 0x00000400 #define DR7_VOLATILE 0xffff2bff #define KVM_GUESTDBG_VALID_MASK \ diff --git a/arch/x86/include/uapi/asm/debugreg.h b/arch/x86/include/uapi/asm/debugreg.h index 0007ba077c0c..41da492dfb01 100644 --- a/arch/x86/include/uapi/asm/debugreg.h +++ b/arch/x86/include/uapi/asm/debugreg.h @@ -15,7 +15,26 @@ which debugging register was responsible for the trap. The other bits are either reserved or not of interest to us. */ -/* Define reserved bits in DR6 which are always set to 1 */ +/* + * Define bits in DR6 which are set to 1 by default. + * + * This is also the DR6 architectural value following Power-up, Reset or INIT. + * + * Note, with the introduction of Bus Lock Detection (BLD) and Restricted + * Transactional Memory (RTM), the DR6 register has been modified: + * + * 1) BLD flag (bit 11) is no longer reserved to 1 if the CPU supports + * Bus Lock Detection. The assertion of a bus lock could clear it. + * + * 2) RTM flag (bit 16) is no longer reserved to 1 if the CPU supports + * restricted transactional memory. #DB occurred inside an RTM region + * could clear it. + * + * Apparently, DR6.BLD and DR6.RTM are active low bits. + * + * As a result, DR6_RESERVED is an incorrect name now, but it is kept for + * compatibility. + */ #define DR6_RESERVED (0xFFFF0FF0) #define DR_TRAP0 (0x1) /* db0 */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 8feb8fd2957a..27125e009847 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -2243,20 +2243,16 @@ EXPORT_PER_CPU_SYMBOL(__stack_chk_guard); #endif #endif -/* - * Clear all 6 debug registers: - */ -static void clear_all_debug_regs(void) +static void initialize_debug_regs(void) { - int i; - - for (i = 0; i < 8; i++) { - /* Ignore db4, db5 */ - if ((i == 4) || (i == 5)) - continue; - - set_debugreg(0, i); - } + /* Control register first -- to make sure everything is disabled. */ + set_debugreg(DR7_FIXED_1, 7); + set_debugreg(DR6_RESERVED, 6); + /* dr5 and dr4 don't exist */ + set_debugreg(0, 3); + set_debugreg(0, 2); + set_debugreg(0, 1); + set_debugreg(0, 0); } #ifdef CONFIG_KGDB @@ -2417,7 +2413,7 @@ void cpu_init(void) load_mm_ldt(&init_mm); - clear_all_debug_regs(); + initialize_debug_regs(); dbg_restore_debug_regs(); doublefault_init_cpu_tss(); diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 102641fd2172..8b1a9733d13e 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -385,7 +385,7 @@ static void kgdb_disable_hw_debug(struct pt_regs *regs) struct perf_event *bp; /* Disable hardware debugging while we are in kgdb: */ - set_debugreg(0UL, 7); + set_debugreg(DR7_FIXED_1, 7); for (i = 0; i < HBP_NUM; i++) { if (!breakinfo[i].enabled) continue; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index a10e180cbf23..3ef15c2f152f 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -93,7 +93,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode, /* Only print out debug registers if they are in their non-default state. */ if ((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) && - (d6 == DR6_RESERVED) && (d7 == 0x400)) + (d6 == DR6_RESERVED) && (d7 == DR7_FIXED_1)) return; printk("%sDR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n", diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 8d6cf25127aa..b972bf72fb8b 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -133,7 +133,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode, /* Only print out debug registers if they are in their non-default state. */ if (!((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) && - (d6 == DR6_RESERVED) && (d7 == 0x400))) { + (d6 == DR6_RESERVED) && (d7 == DR7_FIXED_1))) { printk("%sDR0: %016lx DR1: %016lx DR2: %016lx\n", log_lvl, d0, d1, d2); printk("%sDR3: %016lx DR6: %016lx DR7: %016lx\n", diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index c5c897a86418..36354b470590 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -1022,24 +1022,32 @@ static bool is_sysenter_singlestep(struct pt_regs *regs) #endif } -static __always_inline unsigned long debug_read_clear_dr6(void) +static __always_inline unsigned long debug_read_reset_dr6(void) { unsigned long dr6; + get_debugreg(dr6, 6); + dr6 ^= DR6_RESERVED; /* Flip to positive polarity */ + /* * The Intel SDM says: * - * Certain debug exceptions may clear bits 0-3. The remaining - * contents of the DR6 register are never cleared by the - * processor. To avoid confusion in identifying debug - * exceptions, debug handlers should clear the register before - * returning to the interrupted task. + * Certain debug exceptions may clear bits 0-3 of DR6. + * + * BLD induced #DB clears DR6.BLD and any other debug + * exception doesn't modify DR6.BLD. * - * Keep it simple: clear DR6 immediately. + * RTM induced #DB clears DR6.RTM and any other debug + * exception sets DR6.RTM. + * + * To avoid confusion in identifying debug exceptions, + * debug handlers should set DR6.BLD and DR6.RTM, and + * clear other DR6 bits before returning. + * + * Keep it simple: write DR6 with its architectural reset + * value 0xFFFF0FF0, defined as DR6_RESERVED, immediately. */ - get_debugreg(dr6, 6); set_debugreg(DR6_RESERVED, 6); - dr6 ^= DR6_RESERVED; /* Flip to positive polarity */ return dr6; } @@ -1239,13 +1247,13 @@ out: /* IST stack entry */ DEFINE_IDTENTRY_DEBUG(exc_debug) { - exc_debug_kernel(regs, debug_read_clear_dr6()); + exc_debug_kernel(regs, debug_read_reset_dr6()); } /* User entry, runs on regular task stack */ DEFINE_IDTENTRY_DEBUG_USER(exc_debug) { - exc_debug_user(regs, debug_read_clear_dr6()); + exc_debug_user(regs, debug_read_reset_dr6()); } #ifdef CONFIG_X86_FRED @@ -1264,7 +1272,7 @@ DEFINE_FREDENTRY_DEBUG(exc_debug) { /* * FRED #DB stores DR6 on the stack in the format which - * debug_read_clear_dr6() returns for the IDT entry points. + * debug_read_reset_dr6() returns for the IDT entry points. */ unsigned long dr6 = fred_event_data(regs); @@ -1279,7 +1287,7 @@ DEFINE_FREDENTRY_DEBUG(exc_debug) /* 32 bit does not have separate entry points. */ DEFINE_IDTENTRY_RAW(exc_debug) { - unsigned long dr6 = debug_read_clear_dr6(); + unsigned long dr6 = debug_read_reset_dr6(); if (user_mode(regs)) exc_debug_user(regs, dr6); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b58a74c1722d..a9d992d5652f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -11035,7 +11035,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (unlikely(vcpu->arch.switch_db_regs && !(vcpu->arch.switch_db_regs & KVM_DEBUGREG_AUTO_SWITCH))) { - set_debugreg(0, 7); + set_debugreg(DR7_FIXED_1, 7); set_debugreg(vcpu->arch.eff_db[0], 0); set_debugreg(vcpu->arch.eff_db[1], 1); set_debugreg(vcpu->arch.eff_db[2], 2); @@ -11044,7 +11044,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) kvm_x86_call(set_dr6)(vcpu, vcpu->arch.dr6); } else if (unlikely(hw_breakpoint_active())) { - set_debugreg(0, 7); + set_debugreg(DR7_FIXED_1, 7); } vcpu->arch.host_debugctl = get_debugctlmsr(); diff --git a/block/genhd.c b/block/genhd.c index 8171a6bc3210..c26733f6324b 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -128,23 +128,27 @@ static void part_stat_read_all(struct block_device *part, static void bdev_count_inflight_rw(struct block_device *part, unsigned int inflight[2], bool mq_driver) { + int write = 0; + int read = 0; int cpu; if (mq_driver) { blk_mq_in_driver_rw(part, inflight); - } else { - for_each_possible_cpu(cpu) { - inflight[READ] += part_stat_local_read_cpu( - part, in_flight[READ], cpu); - inflight[WRITE] += part_stat_local_read_cpu( - part, in_flight[WRITE], cpu); - } + return; + } + + for_each_possible_cpu(cpu) { + read += part_stat_local_read_cpu(part, in_flight[READ], cpu); + write += part_stat_local_read_cpu(part, in_flight[WRITE], cpu); } - if (WARN_ON_ONCE((int)inflight[READ] < 0)) - inflight[READ] = 0; - if (WARN_ON_ONCE((int)inflight[WRITE] < 0)) - inflight[WRITE] = 0; + /* + * While iterating all CPUs, some IOs may be issued from a CPU already + * traversed and complete on a CPU that has not yet been traversed, + * causing the inflight number to be negative. + */ + inflight[READ] = read > 0 ? read : 0; + inflight[WRITE] = write > 0 ? write : 0; } /** diff --git a/crypto/wp512.c b/crypto/wp512.c index 41f13d490333..229b189a7988 100644 --- a/crypto/wp512.c +++ b/crypto/wp512.c @@ -21,10 +21,10 @@ */ #include <crypto/internal/hash.h> #include <linux/init.h> +#include <linux/kernel.h> #include <linux/module.h> -#include <linux/mm.h> -#include <asm/byteorder.h> -#include <linux/types.h> +#include <linux/string.h> +#include <linux/unaligned.h> #define WP512_DIGEST_SIZE 64 #define WP384_DIGEST_SIZE 48 @@ -37,9 +37,6 @@ struct wp512_ctx { u8 bitLength[WP512_LENGTHBYTES]; - u8 buffer[WP512_BLOCK_SIZE]; - int bufferBits; - int bufferPos; u64 hash[WP512_DIGEST_SIZE/8]; }; @@ -779,16 +776,16 @@ static const u64 rc[WHIRLPOOL_ROUNDS] = { * The core Whirlpool transform. */ -static __no_kmsan_checks void wp512_process_buffer(struct wp512_ctx *wctx) { +static __no_kmsan_checks void wp512_process_buffer(struct wp512_ctx *wctx, + const u8 *buffer) { int i, r; u64 K[8]; /* the round key */ u64 block[8]; /* mu(buffer) */ u64 state[8]; /* the cipher state */ u64 L[8]; - const __be64 *buffer = (const __be64 *)wctx->buffer; for (i = 0; i < 8; i++) - block[i] = be64_to_cpu(buffer[i]); + block[i] = get_unaligned_be64(buffer + i * 8); state[0] = block[0] ^ (K[0] = wctx->hash[0]); state[1] = block[1] ^ (K[1] = wctx->hash[1]); @@ -991,8 +988,6 @@ static int wp512_init(struct shash_desc *desc) { int i; memset(wctx->bitLength, 0, 32); - wctx->bufferBits = wctx->bufferPos = 0; - wctx->buffer[0] = 0; for (i = 0; i < 8; i++) { wctx->hash[i] = 0L; } @@ -1000,84 +995,54 @@ static int wp512_init(struct shash_desc *desc) { return 0; } -static int wp512_update(struct shash_desc *desc, const u8 *source, - unsigned int len) +static void wp512_add_length(u8 *bitLength, u64 value) { - struct wp512_ctx *wctx = shash_desc_ctx(desc); - int sourcePos = 0; - unsigned int bits_len = len * 8; // convert to number of bits - int sourceGap = (8 - ((int)bits_len & 7)) & 7; - int bufferRem = wctx->bufferBits & 7; + u32 carry; int i; - u32 b, carry; - u8 *buffer = wctx->buffer; - u8 *bitLength = wctx->bitLength; - int bufferBits = wctx->bufferBits; - int bufferPos = wctx->bufferPos; - u64 value = bits_len; for (i = 31, carry = 0; i >= 0 && (carry != 0 || value != 0ULL); i--) { carry += bitLength[i] + ((u32)value & 0xff); bitLength[i] = (u8)carry; carry >>= 8; value >>= 8; } - while (bits_len > 8) { - b = ((source[sourcePos] << sourceGap) & 0xff) | - ((source[sourcePos + 1] & 0xff) >> (8 - sourceGap)); - buffer[bufferPos++] |= (u8)(b >> bufferRem); - bufferBits += 8 - bufferRem; - if (bufferBits == WP512_BLOCK_SIZE * 8) { - wp512_process_buffer(wctx); - bufferBits = bufferPos = 0; - } - buffer[bufferPos] = b << (8 - bufferRem); - bufferBits += bufferRem; - bits_len -= 8; - sourcePos++; - } - if (bits_len > 0) { - b = (source[sourcePos] << sourceGap) & 0xff; - buffer[bufferPos] |= b >> bufferRem; - } else { - b = 0; - } - if (bufferRem + bits_len < 8) { - bufferBits += bits_len; - } else { - bufferPos++; - bufferBits += 8 - bufferRem; - bits_len -= 8 - bufferRem; - if (bufferBits == WP512_BLOCK_SIZE * 8) { - wp512_process_buffer(wctx); - bufferBits = bufferPos = 0; - } - buffer[bufferPos] = b << (8 - bufferRem); - bufferBits += (int)bits_len; - } +} - wctx->bufferBits = bufferBits; - wctx->bufferPos = bufferPos; +static int wp512_update(struct shash_desc *desc, const u8 *source, + unsigned int len) +{ + struct wp512_ctx *wctx = shash_desc_ctx(desc); + unsigned int remain = len % WP512_BLOCK_SIZE; + u64 bits_len = (len - remain) * 8ull; + u8 *bitLength = wctx->bitLength; - return 0; + wp512_add_length(bitLength, bits_len); + do { + wp512_process_buffer(wctx, source); + source += WP512_BLOCK_SIZE; + bits_len -= WP512_BLOCK_SIZE * 8; + } while (bits_len); + + return remain; } -static int wp512_final(struct shash_desc *desc, u8 *out) +static int wp512_finup(struct shash_desc *desc, const u8 *src, + unsigned int bufferPos, u8 *out) { struct wp512_ctx *wctx = shash_desc_ctx(desc); int i; - u8 *buffer = wctx->buffer; u8 *bitLength = wctx->bitLength; - int bufferBits = wctx->bufferBits; - int bufferPos = wctx->bufferPos; __be64 *digest = (__be64 *)out; + u8 buffer[WP512_BLOCK_SIZE]; - buffer[bufferPos] |= 0x80U >> (bufferBits & 7); + wp512_add_length(bitLength, bufferPos * 8); + memcpy(buffer, src, bufferPos); + buffer[bufferPos] = 0x80U; bufferPos++; if (bufferPos > WP512_BLOCK_SIZE - WP512_LENGTHBYTES) { if (bufferPos < WP512_BLOCK_SIZE) memset(&buffer[bufferPos], 0, WP512_BLOCK_SIZE - bufferPos); - wp512_process_buffer(wctx); + wp512_process_buffer(wctx, buffer); bufferPos = 0; } if (bufferPos < WP512_BLOCK_SIZE - WP512_LENGTHBYTES) @@ -1086,31 +1051,32 @@ static int wp512_final(struct shash_desc *desc, u8 *out) bufferPos = WP512_BLOCK_SIZE - WP512_LENGTHBYTES; memcpy(&buffer[WP512_BLOCK_SIZE - WP512_LENGTHBYTES], bitLength, WP512_LENGTHBYTES); - wp512_process_buffer(wctx); + wp512_process_buffer(wctx, buffer); + memzero_explicit(buffer, sizeof(buffer)); for (i = 0; i < WP512_DIGEST_SIZE/8; i++) digest[i] = cpu_to_be64(wctx->hash[i]); - wctx->bufferBits = bufferBits; - wctx->bufferPos = bufferPos; return 0; } -static int wp384_final(struct shash_desc *desc, u8 *out) +static int wp384_finup(struct shash_desc *desc, const u8 *src, + unsigned int len, u8 *out) { u8 D[64]; - wp512_final(desc, D); + wp512_finup(desc, src, len, D); memcpy(out, D, WP384_DIGEST_SIZE); memzero_explicit(D, WP512_DIGEST_SIZE); return 0; } -static int wp256_final(struct shash_desc *desc, u8 *out) +static int wp256_finup(struct shash_desc *desc, const u8 *src, + unsigned int len, u8 *out) { u8 D[64]; - wp512_final(desc, D); + wp512_finup(desc, src, len, D); memcpy(out, D, WP256_DIGEST_SIZE); memzero_explicit(D, WP512_DIGEST_SIZE); @@ -1121,11 +1087,12 @@ static struct shash_alg wp_algs[3] = { { .digestsize = WP512_DIGEST_SIZE, .init = wp512_init, .update = wp512_update, - .final = wp512_final, + .finup = wp512_finup, .descsize = sizeof(struct wp512_ctx), .base = { .cra_name = "wp512", .cra_driver_name = "wp512-generic", + .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY, .cra_blocksize = WP512_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -1133,11 +1100,12 @@ static struct shash_alg wp_algs[3] = { { .digestsize = WP384_DIGEST_SIZE, .init = wp512_init, .update = wp512_update, - .final = wp384_final, + .finup = wp384_finup, .descsize = sizeof(struct wp512_ctx), .base = { .cra_name = "wp384", .cra_driver_name = "wp384-generic", + .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY, .cra_blocksize = WP512_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -1145,11 +1113,12 @@ static struct shash_alg wp_algs[3] = { { .digestsize = WP256_DIGEST_SIZE, .init = wp512_init, .update = wp512_update, - .final = wp256_final, + .finup = wp256_finup, .descsize = sizeof(struct wp512_ctx), .base = { .cra_name = "wp256", .cra_driver_name = "wp256-generic", + .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY, .cra_blocksize = WP512_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index e5e5c2e81d09..aa93b0ecbbc6 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1450,7 +1450,7 @@ static bool ahci_broken_lpm(struct pci_dev *pdev) { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_VERSION, "ASUSPRO D840MB_M840SA"), + DMI_MATCH(DMI_PRODUCT_NAME, "ASUSPRO D840MB_M840SA"), }, /* 320 is broken, there is no known good version. */ }, diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index d36f44f5ee80..c3e3c3b65a6d 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1148,8 +1148,8 @@ exit: blk_mq_end_request(req, res); } -static void ublk_complete_io_cmd(struct ublk_io *io, struct request *req, - int res, unsigned issue_flags) +static struct io_uring_cmd *__ublk_prep_compl_io_cmd(struct ublk_io *io, + struct request *req) { /* read cmd first because req will overwrite it */ struct io_uring_cmd *cmd = io->cmd; @@ -1164,6 +1164,13 @@ static void ublk_complete_io_cmd(struct ublk_io *io, struct request *req, io->flags &= ~UBLK_IO_FLAG_ACTIVE; io->req = req; + return cmd; +} + +static void ublk_complete_io_cmd(struct ublk_io *io, struct request *req, + int res, unsigned issue_flags) +{ + struct io_uring_cmd *cmd = __ublk_prep_compl_io_cmd(io, req); /* tell ublksrv one io request is coming */ io_uring_cmd_done(cmd, res, 0, issue_flags); @@ -1416,6 +1423,14 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; } +static inline bool ublk_belong_to_same_batch(const struct ublk_io *io, + const struct ublk_io *io2) +{ + return (io_uring_cmd_ctx_handle(io->cmd) == + io_uring_cmd_ctx_handle(io2->cmd)) && + (io->task == io2->task); +} + static void ublk_queue_rqs(struct rq_list *rqlist) { struct rq_list requeue_list = { }; @@ -1427,7 +1442,8 @@ static void ublk_queue_rqs(struct rq_list *rqlist) struct ublk_queue *this_q = req->mq_hctx->driver_data; struct ublk_io *this_io = &this_q->ios[req->tag]; - if (io && io->task != this_io->task && !rq_list_empty(&submit_list)) + if (io && !ublk_belong_to_same_batch(io, this_io) && + !rq_list_empty(&submit_list)) ublk_queue_cmd_list(io, &submit_list); io = this_io; @@ -2148,10 +2164,9 @@ static int ublk_commit_and_fetch(const struct ublk_queue *ubq, return 0; } -static bool ublk_get_data(const struct ublk_queue *ubq, struct ublk_io *io) +static bool ublk_get_data(const struct ublk_queue *ubq, struct ublk_io *io, + struct request *req) { - struct request *req = io->req; - /* * We have handled UBLK_IO_NEED_GET_DATA command, * so clear UBLK_IO_FLAG_NEED_GET_DATA now and just @@ -2178,6 +2193,7 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, u32 cmd_op = cmd->cmd_op; unsigned tag = ub_cmd->tag; int ret = -EINVAL; + struct request *req; pr_devel("%s: received: cmd op %d queue %d tag %d result %d\n", __func__, cmd->cmd_op, ub_cmd->q_id, tag, @@ -2236,11 +2252,19 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, goto out; break; case UBLK_IO_NEED_GET_DATA: - io->addr = ub_cmd->addr; - if (!ublk_get_data(ubq, io)) - return -EIOCBQUEUED; - - return UBLK_IO_RES_OK; + /* + * ublk_get_data() may fail and fallback to requeue, so keep + * uring_cmd active first and prepare for handling new requeued + * request + */ + req = io->req; + ublk_fill_io_cmd(io, cmd, ub_cmd->addr); + io->flags &= ~UBLK_IO_FLAG_OWNED_BY_SRV; + if (likely(ublk_get_data(ubq, io, req))) { + __ublk_prep_compl_io_cmd(io, req); + return UBLK_IO_RES_OK; + } + break; default: goto out; } @@ -2825,7 +2849,8 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header) if (copy_from_user(&info, argp, sizeof(info))) return -EFAULT; - if (info.queue_depth > UBLK_MAX_QUEUE_DEPTH || info.nr_hw_queues > UBLK_MAX_NR_QUEUES) + if (info.queue_depth > UBLK_MAX_QUEUE_DEPTH || !info.queue_depth || + info.nr_hw_queues > UBLK_MAX_NR_QUEUES || !info.nr_hw_queues) return -EINVAL; if (capable(CAP_SYS_ADMIN)) diff --git a/drivers/cxl/core/edac.c b/drivers/cxl/core/edac.c index 2cbc664e5d62..623aaa4439c4 100644 --- a/drivers/cxl/core/edac.c +++ b/drivers/cxl/core/edac.c @@ -103,10 +103,10 @@ static int cxl_scrub_get_attrbs(struct cxl_patrol_scrub_context *cxl_ps_ctx, u8 *cap, u16 *cycle, u8 *flags, u8 *min_cycle) { struct cxl_mailbox *cxl_mbox; - u8 min_scrub_cycle = U8_MAX; struct cxl_region_params *p; struct cxl_memdev *cxlmd; struct cxl_region *cxlr; + u8 min_scrub_cycle = 0; int i, ret; if (!cxl_ps_ctx->cxlr) { @@ -133,8 +133,12 @@ static int cxl_scrub_get_attrbs(struct cxl_patrol_scrub_context *cxl_ps_ctx, if (ret) return ret; + /* + * The min_scrub_cycle of a region is the max of minimum scrub + * cycles supported by memdevs that back the region. + */ if (min_cycle) - min_scrub_cycle = min(*min_cycle, min_scrub_cycle); + min_scrub_cycle = max(*min_cycle, min_scrub_cycle); } if (min_cycle) @@ -1099,8 +1103,10 @@ int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd, union cxl_event *evt) old_rec = xa_store(&array_rec->rec_gen_media, le64_to_cpu(rec->media_hdr.phys_addr), rec, GFP_KERNEL); - if (xa_is_err(old_rec)) + if (xa_is_err(old_rec)) { + kfree(rec); return xa_err(old_rec); + } kfree(old_rec); @@ -1127,8 +1133,10 @@ int cxl_store_rec_dram(struct cxl_memdev *cxlmd, union cxl_event *evt) old_rec = xa_store(&array_rec->rec_dram, le64_to_cpu(rec->media_hdr.phys_addr), rec, GFP_KERNEL); - if (xa_is_err(old_rec)) + if (xa_is_err(old_rec)) { + kfree(rec); return xa_err(old_rec); + } kfree(old_rec); @@ -1315,7 +1323,7 @@ cxl_mem_get_rec_dram(struct cxl_memdev *cxlmd, attrbs.bank = ctx->bank; break; case EDAC_REPAIR_RANK_SPARING: - attrbs.repair_type = CXL_BANK_SPARING; + attrbs.repair_type = CXL_RANK_SPARING; break; default: return NULL; diff --git a/drivers/cxl/core/features.c b/drivers/cxl/core/features.c index 6f2eae1eb126..7c750599ea69 100644 --- a/drivers/cxl/core/features.c +++ b/drivers/cxl/core/features.c @@ -544,7 +544,7 @@ static bool cxlctl_validate_set_features(struct cxl_features_state *cxlfs, u32 flags; if (rpc_in->op_size < sizeof(uuid_t)) - return ERR_PTR(-EINVAL); + return false; feat = cxl_feature_info(cxlfs, &rpc_in->set_feat_in.uuid); if (IS_ERR(feat)) diff --git a/drivers/cxl/core/ras.c b/drivers/cxl/core/ras.c index 485a831695c7..2731ba3a0799 100644 --- a/drivers/cxl/core/ras.c +++ b/drivers/cxl/core/ras.c @@ -31,40 +31,38 @@ static void cxl_cper_trace_uncorr_port_prot_err(struct pci_dev *pdev, ras_cap.header_log); } -static void cxl_cper_trace_corr_prot_err(struct pci_dev *pdev, - struct cxl_ras_capability_regs ras_cap) +static void cxl_cper_trace_corr_prot_err(struct cxl_memdev *cxlmd, + struct cxl_ras_capability_regs ras_cap) { u32 status = ras_cap.cor_status & ~ras_cap.cor_mask; - struct cxl_dev_state *cxlds; - cxlds = pci_get_drvdata(pdev); - if (!cxlds) - return; - - trace_cxl_aer_correctable_error(cxlds->cxlmd, status); + trace_cxl_aer_correctable_error(cxlmd, status); } -static void cxl_cper_trace_uncorr_prot_err(struct pci_dev *pdev, - struct cxl_ras_capability_regs ras_cap) +static void +cxl_cper_trace_uncorr_prot_err(struct cxl_memdev *cxlmd, + struct cxl_ras_capability_regs ras_cap) { u32 status = ras_cap.uncor_status & ~ras_cap.uncor_mask; - struct cxl_dev_state *cxlds; u32 fe; - cxlds = pci_get_drvdata(pdev); - if (!cxlds) - return; - if (hweight32(status) > 1) fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK, ras_cap.cap_control)); else fe = status; - trace_cxl_aer_uncorrectable_error(cxlds->cxlmd, status, fe, + trace_cxl_aer_uncorrectable_error(cxlmd, status, fe, ras_cap.header_log); } +static int match_memdev_by_parent(struct device *dev, const void *uport) +{ + if (is_cxl_memdev(dev) && dev->parent == uport) + return 1; + return 0; +} + static void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *data) { unsigned int devfn = PCI_DEVFN(data->prot_err.agent_addr.device, @@ -73,13 +71,12 @@ static void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *data) pci_get_domain_bus_and_slot(data->prot_err.agent_addr.segment, data->prot_err.agent_addr.bus, devfn); + struct cxl_memdev *cxlmd; int port_type; if (!pdev) return; - guard(device)(&pdev->dev); - port_type = pci_pcie_type(pdev); if (port_type == PCI_EXP_TYPE_ROOT_PORT || port_type == PCI_EXP_TYPE_DOWNSTREAM || @@ -92,10 +89,20 @@ static void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *data) return; } + guard(device)(&pdev->dev); + if (!pdev->dev.driver) + return; + + struct device *mem_dev __free(put_device) = bus_find_device( + &cxl_bus_type, NULL, pdev, match_memdev_by_parent); + if (!mem_dev) + return; + + cxlmd = to_cxl_memdev(mem_dev); if (data->severity == AER_CORRECTABLE) - cxl_cper_trace_corr_prot_err(pdev, data->ras_cap); + cxl_cper_trace_corr_prot_err(cxlmd, data->ras_cap); else - cxl_cper_trace_uncorr_prot_err(pdev, data->ras_cap); + cxl_cper_trace_uncorr_prot_err(cxlmd, data->ras_cap); } static void cxl_cper_prot_err_work_fn(struct work_struct *work) diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c index 20bdc52f63a5..a461095efd8a 100644 --- a/drivers/dpll/dpll_core.c +++ b/drivers/dpll/dpll_core.c @@ -506,6 +506,7 @@ dpll_pin_alloc(u64 clock_id, u32 pin_idx, struct module *module, refcount_set(&pin->refcount, 1); xa_init_flags(&pin->dpll_refs, XA_FLAGS_ALLOC); xa_init_flags(&pin->parent_refs, XA_FLAGS_ALLOC); + xa_init_flags(&pin->ref_sync_pins, XA_FLAGS_ALLOC); ret = xa_alloc_cyclic(&dpll_pin_xa, &pin->id, pin, xa_limit_32b, &dpll_pin_xa_id, GFP_KERNEL); if (ret < 0) @@ -514,6 +515,7 @@ dpll_pin_alloc(u64 clock_id, u32 pin_idx, struct module *module, err_xa_alloc: xa_destroy(&pin->dpll_refs); xa_destroy(&pin->parent_refs); + xa_destroy(&pin->ref_sync_pins); dpll_pin_prop_free(&pin->prop); err_pin_prop: kfree(pin); @@ -595,6 +597,7 @@ void dpll_pin_put(struct dpll_pin *pin) xa_erase(&dpll_pin_xa, pin->id); xa_destroy(&pin->dpll_refs); xa_destroy(&pin->parent_refs); + xa_destroy(&pin->ref_sync_pins); dpll_pin_prop_free(&pin->prop); kfree_rcu(pin, rcu); } @@ -659,11 +662,26 @@ dpll_pin_register(struct dpll_device *dpll, struct dpll_pin *pin, } EXPORT_SYMBOL_GPL(dpll_pin_register); +static void dpll_pin_ref_sync_pair_del(u32 ref_sync_pin_id) +{ + struct dpll_pin *pin, *ref_sync_pin; + unsigned long i; + + xa_for_each(&dpll_pin_xa, i, pin) { + ref_sync_pin = xa_load(&pin->ref_sync_pins, ref_sync_pin_id); + if (ref_sync_pin) { + xa_erase(&pin->ref_sync_pins, ref_sync_pin_id); + __dpll_pin_change_ntf(pin); + } + } +} + static void __dpll_pin_unregister(struct dpll_device *dpll, struct dpll_pin *pin, const struct dpll_pin_ops *ops, void *priv, void *cookie) { ASSERT_DPLL_PIN_REGISTERED(pin); + dpll_pin_ref_sync_pair_del(pin->id); dpll_xa_ref_pin_del(&dpll->pin_refs, pin, ops, priv, cookie); dpll_xa_ref_dpll_del(&pin->dpll_refs, dpll, ops, priv, cookie); if (xa_empty(&pin->dpll_refs)) @@ -783,6 +801,33 @@ void dpll_pin_on_pin_unregister(struct dpll_pin *parent, struct dpll_pin *pin, } EXPORT_SYMBOL_GPL(dpll_pin_on_pin_unregister); +/** + * dpll_pin_ref_sync_pair_add - create a reference sync signal pin pair + * @pin: pin which produces the base frequency + * @ref_sync_pin: pin which produces the sync signal + * + * Once pins are paired, the user-space configuration of reference sync pair + * is possible. + * Context: Acquires a lock (dpll_lock) + * Return: + * * 0 on success + * * negative - error value + */ +int dpll_pin_ref_sync_pair_add(struct dpll_pin *pin, + struct dpll_pin *ref_sync_pin) +{ + int ret; + + mutex_lock(&dpll_lock); + ret = xa_insert(&pin->ref_sync_pins, ref_sync_pin->id, + ref_sync_pin, GFP_KERNEL); + __dpll_pin_change_ntf(pin); + mutex_unlock(&dpll_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(dpll_pin_ref_sync_pair_add); + static struct dpll_device_registration * dpll_device_registration_first(struct dpll_device *dpll) { diff --git a/drivers/dpll/dpll_core.h b/drivers/dpll/dpll_core.h index 9b11e637397b..8ce969bbeb64 100644 --- a/drivers/dpll/dpll_core.h +++ b/drivers/dpll/dpll_core.h @@ -44,6 +44,7 @@ struct dpll_device { * @module: module of creator * @dpll_refs: hold referencees to dplls pin was registered with * @parent_refs: hold references to parent pins pin was registered with + * @ref_sync_pins: hold references to pins for Reference SYNC feature * @prop: pin properties copied from the registerer * @refcount: refcount * @rcu: rcu_head for kfree_rcu() @@ -55,6 +56,7 @@ struct dpll_pin { struct module *module; struct xarray dpll_refs; struct xarray parent_refs; + struct xarray ref_sync_pins; struct dpll_pin_properties prop; refcount_t refcount; struct rcu_head rcu; diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index 4619aaa18b9c..036f21cac0a9 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -48,6 +48,24 @@ dpll_msg_add_dev_parent_handle(struct sk_buff *msg, u32 id) return 0; } +static bool dpll_pin_available(struct dpll_pin *pin) +{ + struct dpll_pin_ref *par_ref; + unsigned long i; + + if (!xa_get_mark(&dpll_pin_xa, pin->id, DPLL_REGISTERED)) + return false; + xa_for_each(&pin->parent_refs, i, par_ref) + if (xa_get_mark(&dpll_pin_xa, par_ref->pin->id, + DPLL_REGISTERED)) + return true; + xa_for_each(&pin->dpll_refs, i, par_ref) + if (xa_get_mark(&dpll_device_xa, par_ref->dpll->id, + DPLL_REGISTERED)) + return true; + return false; +} + /** * dpll_msg_add_pin_handle - attach pin handle attribute to a given message * @msg: pointer to sk_buff message to attach a pin handle @@ -428,6 +446,47 @@ nest_cancel: return -EMSGSIZE; } +static int +dpll_msg_add_pin_ref_sync(struct sk_buff *msg, struct dpll_pin *pin, + struct dpll_pin_ref *ref, + struct netlink_ext_ack *extack) +{ + const struct dpll_pin_ops *ops = dpll_pin_ops(ref); + struct dpll_device *dpll = ref->dpll; + void *pin_priv, *ref_sync_pin_priv; + struct dpll_pin *ref_sync_pin; + enum dpll_pin_state state; + struct nlattr *nest; + unsigned long index; + int ret; + + pin_priv = dpll_pin_on_dpll_priv(dpll, pin); + xa_for_each(&pin->ref_sync_pins, index, ref_sync_pin) { + if (!dpll_pin_available(ref_sync_pin)) + continue; + ref_sync_pin_priv = dpll_pin_on_dpll_priv(dpll, ref_sync_pin); + if (WARN_ON(!ops->ref_sync_get)) + return -EOPNOTSUPP; + ret = ops->ref_sync_get(pin, pin_priv, ref_sync_pin, + ref_sync_pin_priv, &state, extack); + if (ret) + return ret; + nest = nla_nest_start(msg, DPLL_A_PIN_REFERENCE_SYNC); + if (!nest) + return -EMSGSIZE; + if (nla_put_s32(msg, DPLL_A_PIN_ID, ref_sync_pin->id)) + goto nest_cancel; + if (nla_put_s32(msg, DPLL_A_PIN_STATE, state)) + goto nest_cancel; + nla_nest_end(msg, nest); + } + return 0; + +nest_cancel: + nla_nest_cancel(msg, nest); + return -EMSGSIZE; +} + static bool dpll_pin_is_freq_supported(struct dpll_pin *pin, u32 freq) { int fs; @@ -572,6 +631,10 @@ dpll_cmd_pin_get_one(struct sk_buff *msg, struct dpll_pin *pin, ret = dpll_msg_add_pin_esync(msg, pin, ref, extack); if (ret) return ret; + if (!xa_empty(&pin->ref_sync_pins)) + ret = dpll_msg_add_pin_ref_sync(msg, pin, ref, extack); + if (ret) + return ret; if (xa_empty(&pin->parent_refs)) ret = dpll_msg_add_pin_dplls(msg, pin, extack); else @@ -665,24 +728,6 @@ __dpll_device_change_ntf(struct dpll_device *dpll) return dpll_device_event_send(DPLL_CMD_DEVICE_CHANGE_NTF, dpll); } -static bool dpll_pin_available(struct dpll_pin *pin) -{ - struct dpll_pin_ref *par_ref; - unsigned long i; - - if (!xa_get_mark(&dpll_pin_xa, pin->id, DPLL_REGISTERED)) - return false; - xa_for_each(&pin->parent_refs, i, par_ref) - if (xa_get_mark(&dpll_pin_xa, par_ref->pin->id, - DPLL_REGISTERED)) - return true; - xa_for_each(&pin->dpll_refs, i, par_ref) - if (xa_get_mark(&dpll_device_xa, par_ref->dpll->id, - DPLL_REGISTERED)) - return true; - return false; -} - /** * dpll_device_change_ntf - notify that the dpll device has been changed * @dpll: registered dpll pointer @@ -745,7 +790,7 @@ int dpll_pin_delete_ntf(struct dpll_pin *pin) return dpll_pin_event_send(DPLL_CMD_PIN_DELETE_NTF, pin); } -static int __dpll_pin_change_ntf(struct dpll_pin *pin) +int __dpll_pin_change_ntf(struct dpll_pin *pin) { return dpll_pin_event_send(DPLL_CMD_PIN_CHANGE_NTF, pin); } @@ -936,6 +981,108 @@ rollback: } static int +dpll_pin_ref_sync_state_set(struct dpll_pin *pin, + unsigned long ref_sync_pin_idx, + const enum dpll_pin_state state, + struct netlink_ext_ack *extack) + +{ + struct dpll_pin_ref *ref, *failed; + const struct dpll_pin_ops *ops; + enum dpll_pin_state old_state; + struct dpll_pin *ref_sync_pin; + struct dpll_device *dpll; + unsigned long i; + int ret; + + ref_sync_pin = xa_find(&pin->ref_sync_pins, &ref_sync_pin_idx, + ULONG_MAX, XA_PRESENT); + if (!ref_sync_pin) { + NL_SET_ERR_MSG(extack, "reference sync pin not found"); + return -EINVAL; + } + if (!dpll_pin_available(ref_sync_pin)) { + NL_SET_ERR_MSG(extack, "reference sync pin not available"); + return -EINVAL; + } + ref = dpll_xa_ref_dpll_first(&pin->dpll_refs); + ASSERT_NOT_NULL(ref); + ops = dpll_pin_ops(ref); + if (!ops->ref_sync_set || !ops->ref_sync_get) { + NL_SET_ERR_MSG(extack, "reference sync not supported by this pin"); + return -EOPNOTSUPP; + } + dpll = ref->dpll; + ret = ops->ref_sync_get(pin, dpll_pin_on_dpll_priv(dpll, pin), + ref_sync_pin, + dpll_pin_on_dpll_priv(dpll, ref_sync_pin), + &old_state, extack); + if (ret) { + NL_SET_ERR_MSG(extack, "unable to get old reference sync state"); + return ret; + } + if (state == old_state) + return 0; + xa_for_each(&pin->dpll_refs, i, ref) { + ops = dpll_pin_ops(ref); + dpll = ref->dpll; + ret = ops->ref_sync_set(pin, dpll_pin_on_dpll_priv(dpll, pin), + ref_sync_pin, + dpll_pin_on_dpll_priv(dpll, + ref_sync_pin), + state, extack); + if (ret) { + failed = ref; + NL_SET_ERR_MSG_FMT(extack, "reference sync set failed for dpll_id:%u", + dpll->id); + goto rollback; + } + } + __dpll_pin_change_ntf(pin); + + return 0; + +rollback: + xa_for_each(&pin->dpll_refs, i, ref) { + if (ref == failed) + break; + ops = dpll_pin_ops(ref); + dpll = ref->dpll; + if (ops->ref_sync_set(pin, dpll_pin_on_dpll_priv(dpll, pin), + ref_sync_pin, + dpll_pin_on_dpll_priv(dpll, ref_sync_pin), + old_state, extack)) + NL_SET_ERR_MSG(extack, "set reference sync rollback failed"); + } + return ret; +} + +static int +dpll_pin_ref_sync_set(struct dpll_pin *pin, struct nlattr *nest, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[DPLL_A_PIN_MAX + 1]; + enum dpll_pin_state state; + u32 sync_pin_id; + + nla_parse_nested(tb, DPLL_A_PIN_MAX, nest, + dpll_reference_sync_nl_policy, extack); + if (!tb[DPLL_A_PIN_ID]) { + NL_SET_ERR_MSG(extack, "sync pin id expected"); + return -EINVAL; + } + sync_pin_id = nla_get_u32(tb[DPLL_A_PIN_ID]); + + if (!tb[DPLL_A_PIN_STATE]) { + NL_SET_ERR_MSG(extack, "sync pin state expected"); + return -EINVAL; + } + state = nla_get_u32(tb[DPLL_A_PIN_STATE]); + + return dpll_pin_ref_sync_state_set(pin, sync_pin_id, state, extack); +} + +static int dpll_pin_on_pin_state_set(struct dpll_pin *pin, u32 parent_idx, enum dpll_pin_state state, struct netlink_ext_ack *extack) @@ -1241,6 +1388,11 @@ dpll_pin_set_from_nlattr(struct dpll_pin *pin, struct genl_info *info) if (ret) return ret; break; + case DPLL_A_PIN_REFERENCE_SYNC: + ret = dpll_pin_ref_sync_set(pin, a, info->extack); + if (ret) + return ret; + break; } } diff --git a/drivers/dpll/dpll_netlink.h b/drivers/dpll/dpll_netlink.h index a9cfd55f57fc..dd28b56d27c5 100644 --- a/drivers/dpll/dpll_netlink.h +++ b/drivers/dpll/dpll_netlink.h @@ -11,3 +11,5 @@ int dpll_device_delete_ntf(struct dpll_device *dpll); int dpll_pin_create_ntf(struct dpll_pin *pin); int dpll_pin_delete_ntf(struct dpll_pin *pin); + +int __dpll_pin_change_ntf(struct dpll_pin *pin); diff --git a/drivers/dpll/dpll_nl.c b/drivers/dpll/dpll_nl.c index 8de90310c3be..9f2efaf25268 100644 --- a/drivers/dpll/dpll_nl.c +++ b/drivers/dpll/dpll_nl.c @@ -24,6 +24,11 @@ const struct nla_policy dpll_pin_parent_pin_nl_policy[DPLL_A_PIN_STATE + 1] = { [DPLL_A_PIN_STATE] = NLA_POLICY_RANGE(NLA_U32, 1, 3), }; +const struct nla_policy dpll_reference_sync_nl_policy[DPLL_A_PIN_STATE + 1] = { + [DPLL_A_PIN_ID] = { .type = NLA_U32, }, + [DPLL_A_PIN_STATE] = NLA_POLICY_RANGE(NLA_U32, 1, 3), +}; + /* DPLL_CMD_DEVICE_ID_GET - do */ static const struct nla_policy dpll_device_id_get_nl_policy[DPLL_A_TYPE + 1] = { [DPLL_A_MODULE_NAME] = { .type = NLA_NUL_STRING, }, @@ -63,7 +68,7 @@ static const struct nla_policy dpll_pin_get_dump_nl_policy[DPLL_A_PIN_ID + 1] = }; /* DPLL_CMD_PIN_SET - do */ -static const struct nla_policy dpll_pin_set_nl_policy[DPLL_A_PIN_ESYNC_FREQUENCY + 1] = { +static const struct nla_policy dpll_pin_set_nl_policy[DPLL_A_PIN_REFERENCE_SYNC + 1] = { [DPLL_A_PIN_ID] = { .type = NLA_U32, }, [DPLL_A_PIN_FREQUENCY] = { .type = NLA_U64, }, [DPLL_A_PIN_DIRECTION] = NLA_POLICY_RANGE(NLA_U32, 1, 2), @@ -73,6 +78,7 @@ static const struct nla_policy dpll_pin_set_nl_policy[DPLL_A_PIN_ESYNC_FREQUENCY [DPLL_A_PIN_PARENT_PIN] = NLA_POLICY_NESTED(dpll_pin_parent_pin_nl_policy), [DPLL_A_PIN_PHASE_ADJUST] = { .type = NLA_S32, }, [DPLL_A_PIN_ESYNC_FREQUENCY] = { .type = NLA_U64, }, + [DPLL_A_PIN_REFERENCE_SYNC] = NLA_POLICY_NESTED(dpll_reference_sync_nl_policy), }; /* Ops table for dpll */ @@ -140,7 +146,7 @@ static const struct genl_split_ops dpll_nl_ops[] = { .doit = dpll_nl_pin_set_doit, .post_doit = dpll_pin_post_doit, .policy = dpll_pin_set_nl_policy, - .maxattr = DPLL_A_PIN_ESYNC_FREQUENCY, + .maxattr = DPLL_A_PIN_REFERENCE_SYNC, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, }; diff --git a/drivers/dpll/dpll_nl.h b/drivers/dpll/dpll_nl.h index f491262bee4f..3da10cfe9a6e 100644 --- a/drivers/dpll/dpll_nl.h +++ b/drivers/dpll/dpll_nl.h @@ -14,6 +14,7 @@ /* Common nested types */ extern const struct nla_policy dpll_pin_parent_device_nl_policy[DPLL_A_PIN_PHASE_OFFSET + 1]; extern const struct nla_policy dpll_pin_parent_pin_nl_policy[DPLL_A_PIN_STATE + 1]; +extern const struct nla_policy dpll_reference_sync_nl_policy[DPLL_A_PIN_STATE + 1]; int dpll_lock_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info); diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index b681c0663203..07f1e9dc1ca7 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -1209,7 +1209,9 @@ static int umc_get_cs_mode(int dimm, u8 ctrl, struct amd64_pvt *pvt) if (csrow_enabled(2 * dimm + 1, ctrl, pvt)) cs_mode |= CS_ODD_PRIMARY; - /* Asymmetric dual-rank DIMM support. */ + if (csrow_sec_enabled(2 * dimm, ctrl, pvt)) + cs_mode |= CS_EVEN_SECONDARY; + if (csrow_sec_enabled(2 * dimm + 1, ctrl, pvt)) cs_mode |= CS_ODD_SECONDARY; @@ -1230,12 +1232,13 @@ static int umc_get_cs_mode(int dimm, u8 ctrl, struct amd64_pvt *pvt) return cs_mode; } -static int __addr_mask_to_cs_size(u32 addr_mask_orig, unsigned int cs_mode, - int csrow_nr, int dimm) +static int calculate_cs_size(u32 mask, unsigned int cs_mode) { - u32 msb, weight, num_zero_bits; - u32 addr_mask_deinterleaved; - int size = 0; + int msb, weight, num_zero_bits; + u32 deinterleaved_mask; + + if (!mask) + return 0; /* * The number of zero bits in the mask is equal to the number of bits @@ -1248,19 +1251,30 @@ static int __addr_mask_to_cs_size(u32 addr_mask_orig, unsigned int cs_mode, * without swapping with the most significant bit. This can be handled * by keeping the MSB where it is and ignoring the single zero bit. */ - msb = fls(addr_mask_orig) - 1; - weight = hweight_long(addr_mask_orig); + msb = fls(mask) - 1; + weight = hweight_long(mask); num_zero_bits = msb - weight - !!(cs_mode & CS_3R_INTERLEAVE); /* Take the number of zero bits off from the top of the mask. */ - addr_mask_deinterleaved = GENMASK_ULL(msb - num_zero_bits, 1); + deinterleaved_mask = GENMASK(msb - num_zero_bits, 1); + edac_dbg(1, " Deinterleaved AddrMask: 0x%x\n", deinterleaved_mask); + + return (deinterleaved_mask >> 2) + 1; +} + +static int __addr_mask_to_cs_size(u32 addr_mask, u32 addr_mask_sec, + unsigned int cs_mode, int csrow_nr, int dimm) +{ + int size; edac_dbg(1, "CS%d DIMM%d AddrMasks:\n", csrow_nr, dimm); - edac_dbg(1, " Original AddrMask: 0x%x\n", addr_mask_orig); - edac_dbg(1, " Deinterleaved AddrMask: 0x%x\n", addr_mask_deinterleaved); + edac_dbg(1, " Primary AddrMask: 0x%x\n", addr_mask); /* Register [31:1] = Address [39:9]. Size is in kBs here. */ - size = (addr_mask_deinterleaved >> 2) + 1; + size = calculate_cs_size(addr_mask, cs_mode); + + edac_dbg(1, " Secondary AddrMask: 0x%x\n", addr_mask_sec); + size += calculate_cs_size(addr_mask_sec, cs_mode); /* Return size in MBs. */ return size >> 10; @@ -1269,8 +1283,8 @@ static int __addr_mask_to_cs_size(u32 addr_mask_orig, unsigned int cs_mode, static int umc_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc, unsigned int cs_mode, int csrow_nr) { + u32 addr_mask = 0, addr_mask_sec = 0; int cs_mask_nr = csrow_nr; - u32 addr_mask_orig; int dimm, size = 0; /* No Chip Selects are enabled. */ @@ -1308,13 +1322,13 @@ static int umc_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc, if (!pvt->flags.zn_regs_v2) cs_mask_nr >>= 1; - /* Asymmetric dual-rank DIMM support. */ - if ((csrow_nr & 1) && (cs_mode & CS_ODD_SECONDARY)) - addr_mask_orig = pvt->csels[umc].csmasks_sec[cs_mask_nr]; - else - addr_mask_orig = pvt->csels[umc].csmasks[cs_mask_nr]; + if (cs_mode & (CS_EVEN_PRIMARY | CS_ODD_PRIMARY)) + addr_mask = pvt->csels[umc].csmasks[cs_mask_nr]; + + if (cs_mode & (CS_EVEN_SECONDARY | CS_ODD_SECONDARY)) + addr_mask_sec = pvt->csels[umc].csmasks_sec[cs_mask_nr]; - return __addr_mask_to_cs_size(addr_mask_orig, cs_mode, csrow_nr, dimm); + return __addr_mask_to_cs_size(addr_mask, addr_mask_sec, cs_mode, csrow_nr, dimm); } static void umc_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl) @@ -3512,9 +3526,10 @@ static void gpu_get_err_info(struct mce *m, struct err_info *err) static int gpu_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc, unsigned int cs_mode, int csrow_nr) { - u32 addr_mask_orig = pvt->csels[umc].csmasks[csrow_nr]; + u32 addr_mask = pvt->csels[umc].csmasks[csrow_nr]; + u32 addr_mask_sec = pvt->csels[umc].csmasks_sec[csrow_nr]; - return __addr_mask_to_cs_size(addr_mask_orig, cs_mode, csrow_nr, csrow_nr >> 1); + return __addr_mask_to_cs_size(addr_mask, addr_mask_sec, cs_mode, csrow_nr, csrow_nr >> 1); } static void gpu_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index a0e9bf9b2710..81b3443c8d7f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -321,10 +321,12 @@ static int amdgpu_discovery_read_binary_from_file(struct amdgpu_device *adev, const struct firmware *fw; int r; - r = request_firmware(&fw, fw_name, adev->dev); + r = firmware_request_nowarn(&fw, fw_name, adev->dev); if (r) { - dev_err(adev->dev, "can't load firmware \"%s\"\n", - fw_name); + if (amdgpu_discovery == 2) + dev_err(adev->dev, "can't load firmware \"%s\"\n", fw_name); + else + drm_info(&adev->ddev, "Optional firmware \"%s\" was not found\n", fw_name); return r; } @@ -459,16 +461,12 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev) /* Read from file if it is the preferred option */ fw_name = amdgpu_discovery_get_fw_name(adev); if (fw_name != NULL) { - dev_info(adev->dev, "use ip discovery information from file"); + drm_dbg(&adev->ddev, "use ip discovery information from file"); r = amdgpu_discovery_read_binary_from_file(adev, adev->mman.discovery_bin, fw_name); - - if (r) { - dev_err(adev->dev, "failed to read ip discovery binary from file\n"); - r = -EINVAL; + if (r) goto out; - } - } else { + drm_dbg(&adev->ddev, "use ip discovery information from memory"); r = amdgpu_discovery_read_binary_from_mem( adev, adev->mman.discovery_bin); if (r) @@ -1338,10 +1336,8 @@ static int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev) int r; r = amdgpu_discovery_init(adev); - if (r) { - DRM_ERROR("amdgpu_discovery_init failed\n"); + if (r) return r; - } wafl_ver = 0; adev->gfx.xcc_mask = 0; @@ -2579,8 +2575,10 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) break; default: r = amdgpu_discovery_reg_base_init(adev); - if (r) - return -EINVAL; + if (r) { + drm_err(&adev->ddev, "discovery failed: %d\n", r); + return r; + } amdgpu_discovery_harvest_ip(adev); amdgpu_discovery_get_gfx_info(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index d377a7c57d5e..ad9be3656653 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -2235,6 +2235,25 @@ static int gfx_v9_0_sw_init(struct amdgpu_ip_block *ip_block) } switch (amdgpu_ip_version(adev, GC_HWIP, 0)) { + case IP_VERSION(9, 0, 1): + case IP_VERSION(9, 2, 1): + case IP_VERSION(9, 4, 0): + case IP_VERSION(9, 2, 2): + case IP_VERSION(9, 1, 0): + case IP_VERSION(9, 3, 0): + adev->gfx.cleaner_shader_ptr = gfx_9_4_2_cleaner_shader_hex; + adev->gfx.cleaner_shader_size = sizeof(gfx_9_4_2_cleaner_shader_hex); + if (adev->gfx.me_fw_version >= 167 && + adev->gfx.pfp_fw_version >= 196 && + adev->gfx.mec_fw_version >= 474) { + adev->gfx.enable_cleaner_shader = true; + r = amdgpu_gfx_cleaner_shader_sw_init(adev, adev->gfx.cleaner_shader_size); + if (r) { + adev->gfx.enable_cleaner_shader = false; + dev_err(adev->dev, "Failed to initialize cleaner shader\n"); + } + } + break; case IP_VERSION(9, 4, 2): adev->gfx.cleaner_shader_ptr = gfx_9_4_2_cleaner_shader_hex; adev->gfx.cleaner_shader_size = sizeof(gfx_9_4_2_cleaner_shader_hex); diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index c9eba537de09..28eb846280dd 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -1630,10 +1630,12 @@ static int mes_v11_0_hw_init(struct amdgpu_ip_block *ip_block) if (r) goto failure; - r = mes_v11_0_set_hw_resources_1(&adev->mes); - if (r) { - DRM_ERROR("failed mes_v11_0_set_hw_resources_1, r=%d\n", r); - goto failure; + if ((adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x50) { + r = mes_v11_0_set_hw_resources_1(&adev->mes); + if (r) { + DRM_ERROR("failed mes_v11_0_set_hw_resources_1, r=%d\n", r); + goto failure; + } } r = mes_v11_0_query_sched_status(&adev->mes); diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index b4f17332d466..6b222630f3fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -1742,7 +1742,8 @@ static int mes_v12_0_hw_init(struct amdgpu_ip_block *ip_block) if (r) goto failure; - mes_v12_0_set_hw_resources_1(&adev->mes, AMDGPU_MES_SCHED_PIPE); + if ((adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x4b) + mes_v12_0_set_hw_resources_1(&adev->mes, AMDGPU_MES_SCHED_PIPE); mes_v12_0_init_aggregated_doorbell(&adev->mes); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c index 5a70ae17be04..a9bdf8d61d6c 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c @@ -1374,9 +1374,22 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block) else DRM_ERROR("Failed to allocated memory for SDMA IP Dump\n"); - /* add firmware version checks here */ - if (0 && !adev->sdma.disable_uq) - adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; + switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) { + case IP_VERSION(6, 0, 0): + if ((adev->sdma.instance[0].fw_version >= 24) && !adev->sdma.disable_uq) + adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; + break; + case IP_VERSION(6, 0, 2): + if ((adev->sdma.instance[0].fw_version >= 21) && !adev->sdma.disable_uq) + adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; + break; + case IP_VERSION(6, 0, 3): + if ((adev->sdma.instance[0].fw_version >= 25) && !adev->sdma.disable_uq) + adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; + break; + default: + break; + } r = amdgpu_sdma_sysfs_reset_mask_init(adev); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c index ad47d0bdf777..86903eccbd4e 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c @@ -1349,9 +1349,15 @@ static int sdma_v7_0_sw_init(struct amdgpu_ip_block *ip_block) else DRM_ERROR("Failed to allocated memory for SDMA IP Dump\n"); - /* add firmware version checks here */ - if (0 && !adev->sdma.disable_uq) - adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; + switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) { + case IP_VERSION(7, 0, 0): + case IP_VERSION(7, 0, 1): + if ((adev->sdma.instance[0].fw_version >= 7836028) && !adev->sdma.disable_uq) + adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; + break; + default: + break; + } return r; } 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 bc4cd11bfc79..0b8ac9edc070 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -4718,16 +4718,16 @@ static int get_brightness_range(const struct amdgpu_dm_backlight_caps *caps, return 1; } -/* Rescale from [min..max] to [0..AMDGPU_MAX_BL_LEVEL] */ +/* Rescale from [min..max] to [0..MAX_BACKLIGHT_LEVEL] */ static inline u32 scale_input_to_fw(int min, int max, u64 input) { - return DIV_ROUND_CLOSEST_ULL(input * AMDGPU_MAX_BL_LEVEL, max - min); + return DIV_ROUND_CLOSEST_ULL(input * MAX_BACKLIGHT_LEVEL, max - min); } -/* Rescale from [0..AMDGPU_MAX_BL_LEVEL] to [min..max] */ +/* Rescale from [0..MAX_BACKLIGHT_LEVEL] to [min..max] */ static inline u32 scale_fw_to_input(int min, int max, u64 input) { - return min + DIV_ROUND_CLOSEST_ULL(input * (max - min), AMDGPU_MAX_BL_LEVEL); + return min + DIV_ROUND_CLOSEST_ULL(input * (max - min), MAX_BACKLIGHT_LEVEL); } static void convert_custom_brightness(const struct amdgpu_dm_backlight_caps *caps, @@ -4947,7 +4947,7 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) drm_dbg(drm, "Backlight caps: min: %d, max: %d, ac %d, dc %d\n", min, max, caps->ac_level, caps->dc_level); } else - props.brightness = props.max_brightness = AMDGPU_MAX_BL_LEVEL; + props.brightness = props.max_brightness = MAX_BACKLIGHT_LEVEL; if (caps->data_points && !(amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE)) drm_info(drm, "Using custom brightness curve\n"); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index d4395b92fb85..9e3e51a2dc49 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -1029,6 +1029,10 @@ enum dc_edid_status dm_helpers_read_local_edid( return EDID_NO_RESPONSE; edid = drm_edid_raw(drm_edid); // FIXME: Get rid of drm_edid_raw() + if (!edid || + edid->extensions >= sizeof(sink->dc_edid.raw_edid) / EDID_LENGTH) + return EDID_BAD_INPUT; + sink->dc_edid.length = EDID_LENGTH * (edid->extensions + 1); memmove(sink->dc_edid.raw_edid, (uint8_t *)edid, sink->dc_edid.length); diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 60224f476e1d..de9c23537465 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -348,12 +348,18 @@ static void ti_sn65dsi86_enable_comms(struct ti_sn65dsi86 *pdata, * 200 ms. We'll assume that the panel driver will have the hardcoded * delay in its prepare and always disable HPD. * - * If HPD somehow makes sense on some future panel we'll have to - * change this to be conditional on someone specifying that HPD should - * be used. + * For DisplayPort bridge type, we need HPD. So we use the bridge type + * to conditionally disable HPD. + * NOTE: The bridge type is set in ti_sn_bridge_probe() but enable_comms() + * can be called before. So for DisplayPort, HPD will be enabled once + * bridge type is set. We are using bridge type instead of "no-hpd" + * property because it is not used properly in devicetree description + * and hence is unreliable. */ - regmap_update_bits(pdata->regmap, SN_HPD_DISABLE_REG, HPD_DISABLE, - HPD_DISABLE); + + if (pdata->bridge.type != DRM_MODE_CONNECTOR_DisplayPort) + regmap_update_bits(pdata->regmap, SN_HPD_DISABLE_REG, HPD_DISABLE, + HPD_DISABLE); pdata->comms_enabled = true; @@ -1195,9 +1201,14 @@ static enum drm_connector_status ti_sn_bridge_detect(struct drm_bridge *bridge) struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge); int val = 0; - pm_runtime_get_sync(pdata->dev); + /* + * Runtime reference is grabbed in ti_sn_bridge_hpd_enable() + * as the chip won't report HPD just after being powered on. + * HPD_DEBOUNCED_STATE reflects correct state only after the + * debounce time (~100-400 ms). + */ + regmap_read(pdata->regmap, SN_HPD_DISABLE_REG, &val); - pm_runtime_put_autosuspend(pdata->dev); return val & HPD_DEBOUNCED_STATE ? connector_status_connected : connector_status_disconnected; @@ -1220,6 +1231,26 @@ static void ti_sn65dsi86_debugfs_init(struct drm_bridge *bridge, struct dentry * debugfs_create_file("status", 0600, debugfs, pdata, &status_fops); } +static void ti_sn_bridge_hpd_enable(struct drm_bridge *bridge) +{ + struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge); + + /* + * Device needs to be powered on before reading the HPD state + * for reliable hpd detection in ti_sn_bridge_detect() due to + * the high debounce time. + */ + + pm_runtime_get_sync(pdata->dev); +} + +static void ti_sn_bridge_hpd_disable(struct drm_bridge *bridge) +{ + struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge); + + pm_runtime_put_autosuspend(pdata->dev); +} + static const struct drm_bridge_funcs ti_sn_bridge_funcs = { .attach = ti_sn_bridge_attach, .detach = ti_sn_bridge_detach, @@ -1234,6 +1265,8 @@ static const struct drm_bridge_funcs ti_sn_bridge_funcs = { .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, .debugfs_init = ti_sn65dsi86_debugfs_init, + .hpd_enable = ti_sn_bridge_hpd_enable, + .hpd_disable = ti_sn_bridge_hpd_disable, }; static void ti_sn_bridge_parse_lanes(struct ti_sn65dsi86 *pdata, @@ -1321,8 +1354,26 @@ static int ti_sn_bridge_probe(struct auxiliary_device *adev, pdata->bridge.type = pdata->next_bridge->type == DRM_MODE_CONNECTOR_DisplayPort ? DRM_MODE_CONNECTOR_DisplayPort : DRM_MODE_CONNECTOR_eDP; - if (pdata->bridge.type == DRM_MODE_CONNECTOR_DisplayPort) - pdata->bridge.ops = DRM_BRIDGE_OP_EDID | DRM_BRIDGE_OP_DETECT; + if (pdata->bridge.type == DRM_MODE_CONNECTOR_DisplayPort) { + pdata->bridge.ops = DRM_BRIDGE_OP_EDID | DRM_BRIDGE_OP_DETECT | + DRM_BRIDGE_OP_HPD; + /* + * If comms were already enabled they would have been enabled + * with the wrong value of HPD_DISABLE. Update it now. Comms + * could be enabled if anyone is holding a pm_runtime reference + * (like if a GPIO is in use). Note that in most cases nobody + * is doing AUX channel xfers before the bridge is added so + * HPD doesn't _really_ matter then. The only exception is in + * the eDP case where the panel wants to read the EDID before + * the bridge is added. We always consistently have HPD disabled + * for eDP. + */ + mutex_lock(&pdata->comms_mutex); + if (pdata->comms_enabled) + regmap_update_bits(pdata->regmap, SN_HPD_DISABLE_REG, + HPD_DISABLE, 0); + mutex_unlock(&pdata->comms_mutex); + }; drm_bridge_add(&pdata->bridge); diff --git a/drivers/gpu/drm/display/drm_bridge_connector.c b/drivers/gpu/drm/display/drm_bridge_connector.c index 7d2e499ea5de..262e93e07a28 100644 --- a/drivers/gpu/drm/display/drm_bridge_connector.c +++ b/drivers/gpu/drm/display/drm_bridge_connector.c @@ -708,11 +708,14 @@ struct drm_connector *drm_bridge_connector_init(struct drm_device *drm, if (bridge_connector->bridge_hdmi_audio || bridge_connector->bridge_dp_audio) { struct device *dev; + struct drm_bridge *bridge; if (bridge_connector->bridge_hdmi_audio) - dev = bridge_connector->bridge_hdmi_audio->hdmi_audio_dev; + bridge = bridge_connector->bridge_hdmi_audio; else - dev = bridge_connector->bridge_dp_audio->hdmi_audio_dev; + bridge = bridge_connector->bridge_dp_audio; + + dev = bridge->hdmi_audio_dev; ret = drm_connector_hdmi_audio_init(connector, dev, &drm_bridge_connector_hdmi_audio_funcs, diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c index f2a6559a2710..dc622c78db9d 100644 --- a/drivers/gpu/drm/display/drm_dp_helper.c +++ b/drivers/gpu/drm/display/drm_dp_helper.c @@ -725,7 +725,7 @@ ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset, * monitor doesn't power down exactly after the throw away read. */ if (!aux->is_remote) { - ret = drm_dp_dpcd_probe(aux, DP_DPCD_REV); + ret = drm_dp_dpcd_probe(aux, DP_LANE0_1_STATUS); if (ret < 0) return ret; } diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c index edbeab88ff2b..d983ee85cf13 100644 --- a/drivers/gpu/drm/drm_writeback.c +++ b/drivers/gpu/drm/drm_writeback.c @@ -343,17 +343,18 @@ EXPORT_SYMBOL(drm_writeback_connector_init_with_encoder); /** * drm_writeback_connector_cleanup - Cleanup the writeback connector * @dev: DRM device - * @wb_connector: Pointer to the writeback connector to clean up + * @data: Pointer to the writeback connector to clean up * * This will decrement the reference counter of blobs and destroy properties. It * will also clean the remaining jobs in this writeback connector. Caution: This helper will not * clean up the attached encoder and the drm_connector. */ static void drm_writeback_connector_cleanup(struct drm_device *dev, - struct drm_writeback_connector *wb_connector) + void *data) { unsigned long flags; struct drm_writeback_job *pos, *n; + struct drm_writeback_connector *wb_connector = data; delete_writeback_properties(dev); drm_property_blob_put(wb_connector->pixel_formats_blob_ptr); @@ -405,7 +406,7 @@ int drmm_writeback_connector_init(struct drm_device *dev, if (ret) return ret; - ret = drmm_add_action_or_reset(dev, (void *)drm_writeback_connector_cleanup, + ret = drmm_add_action_or_reset(dev, drm_writeback_connector_cleanup, wb_connector); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/display/intel_snps_hdmi_pll.c b/drivers/gpu/drm/i915/display/intel_snps_hdmi_pll.c index 74bb3bedf30f..5111bdc3075b 100644 --- a/drivers/gpu/drm/i915/display/intel_snps_hdmi_pll.c +++ b/drivers/gpu/drm/i915/display/intel_snps_hdmi_pll.c @@ -103,8 +103,8 @@ static void get_ana_cp_int_prop(u64 vco_clk, DIV_ROUND_DOWN_ULL(curve_1_interpolated, CURVE0_MULTIPLIER))); ana_cp_int_temp = - DIV_ROUND_CLOSEST_ULL(DIV_ROUND_DOWN_ULL(adjusted_vco_clk1, curve_2_scaled1), - CURVE2_MULTIPLIER); + DIV64_U64_ROUND_CLOSEST(DIV_ROUND_DOWN_ULL(adjusted_vco_clk1, curve_2_scaled1), + CURVE2_MULTIPLIER); *ana_cp_int = max(1, min(ana_cp_int_temp, 127)); diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index 990bfaba3ce4..5bc696bfbb0f 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -108,7 +108,7 @@ static unsigned int config_bit(const u64 config) return other_bit(config); } -static u32 config_mask(const u64 config) +static __always_inline u32 config_mask(const u64 config) { unsigned int bit = config_bit(config); diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c index 68f064f33d4b..9f4ade25787a 100644 --- a/drivers/gpu/drm/xe/display/xe_display.c +++ b/drivers/gpu/drm/xe/display/xe_display.c @@ -104,6 +104,8 @@ int xe_display_create(struct xe_device *xe) spin_lock_init(&xe->display.fb_tracking.lock); xe->display.hotplug.dp_wq = alloc_ordered_workqueue("xe-dp", 0); + if (!xe->display.hotplug.dp_wq) + return -ENOMEM; return drmm_add_action_or_reset(&xe->drm, display_destroy, NULL); } diff --git a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c index f95375451e2f..9f941fc2e36b 100644 --- a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c +++ b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c @@ -17,10 +17,7 @@ u32 intel_dsb_buffer_ggtt_offset(struct intel_dsb_buffer *dsb_buf) void intel_dsb_buffer_write(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val) { - struct xe_device *xe = dsb_buf->vma->bo->tile->xe; - iosys_map_wr(&dsb_buf->vma->bo->vmap, idx * 4, u32, val); - xe_device_l2_flush(xe); } u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx) @@ -30,12 +27,9 @@ u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx) void intel_dsb_buffer_memset(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val, size_t size) { - struct xe_device *xe = dsb_buf->vma->bo->tile->xe; - WARN_ON(idx > (dsb_buf->buf_size - size) / sizeof(*dsb_buf->cmd_buf)); iosys_map_memset(&dsb_buf->vma->bo->vmap, idx * 4, val, size); - xe_device_l2_flush(xe); } bool intel_dsb_buffer_create(struct intel_crtc *crtc, struct intel_dsb_buffer *dsb_buf, size_t size) @@ -74,9 +68,12 @@ void intel_dsb_buffer_cleanup(struct intel_dsb_buffer *dsb_buf) void intel_dsb_buffer_flush_map(struct intel_dsb_buffer *dsb_buf) { + struct xe_device *xe = dsb_buf->vma->bo->tile->xe; + /* * The memory barrier here is to ensure coherency of DSB vs MMIO, * both for weak ordering archs and discrete cards. */ - xe_device_wmb(dsb_buf->vma->bo->tile->xe); + xe_device_wmb(xe); + xe_device_l2_flush(xe); } diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c index d918ae1c8061..55259969480b 100644 --- a/drivers/gpu/drm/xe/display/xe_fb_pin.c +++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c @@ -164,6 +164,9 @@ static int __xe_pin_fb_vma_dpt(const struct intel_framebuffer *fb, vma->dpt = dpt; vma->node = dpt->ggtt_node[tile0->id]; + + /* Ensure DPT writes are flushed */ + xe_device_l2_flush(xe); return 0; } @@ -333,8 +336,6 @@ static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb, if (ret) goto err_unpin; - /* Ensure DPT writes are flushed */ - xe_device_l2_flush(xe); return vma; err_unpin: diff --git a/drivers/gpu/drm/xe/regs/xe_mchbar_regs.h b/drivers/gpu/drm/xe/regs/xe_mchbar_regs.h index 5394a1373a6b..ef2bf984723f 100644 --- a/drivers/gpu/drm/xe/regs/xe_mchbar_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_mchbar_regs.h @@ -40,6 +40,7 @@ #define PCU_CR_PACKAGE_RAPL_LIMIT XE_REG(MCHBAR_MIRROR_BASE_SNB + 0x59a0) #define PWR_LIM_VAL REG_GENMASK(14, 0) #define PWR_LIM_EN REG_BIT(15) +#define PWR_LIM REG_GENMASK(15, 0) #define PWR_LIM_TIME REG_GENMASK(23, 17) #define PWR_LIM_TIME_X REG_GENMASK(23, 22) #define PWR_LIM_TIME_Y REG_GENMASK(21, 17) diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c index 7062115909f2..2c799958c1e4 100644 --- a/drivers/gpu/drm/xe/xe_ggtt.c +++ b/drivers/gpu/drm/xe/xe_ggtt.c @@ -201,6 +201,13 @@ static const struct xe_ggtt_pt_ops xelpg_pt_wa_ops = { .ggtt_set_pte = xe_ggtt_set_pte_and_flush, }; +static void dev_fini_ggtt(void *arg) +{ + struct xe_ggtt *ggtt = arg; + + drain_workqueue(ggtt->wq); +} + /** * xe_ggtt_init_early - Early GGTT initialization * @ggtt: the &xe_ggtt to be initialized @@ -257,6 +264,10 @@ int xe_ggtt_init_early(struct xe_ggtt *ggtt) if (err) return err; + err = devm_add_action_or_reset(xe->drm.dev, dev_fini_ggtt, ggtt); + if (err) + return err; + if (IS_SRIOV_VF(xe)) { err = xe_gt_sriov_vf_prepare_ggtt(xe_tile_get_gt(ggtt->tile, 0)); if (err) diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c index d0ac48d8f4f7..bbcbb348256f 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.c +++ b/drivers/gpu/drm/xe/xe_guc_ct.c @@ -34,6 +34,11 @@ #include "xe_pm.h" #include "xe_trace_guc.h" +static void receive_g2h(struct xe_guc_ct *ct); +static void g2h_worker_func(struct work_struct *w); +static void safe_mode_worker_func(struct work_struct *w); +static void ct_exit_safe_mode(struct xe_guc_ct *ct); + #if IS_ENABLED(CONFIG_DRM_XE_DEBUG) enum { /* Internal states, not error conditions */ @@ -186,14 +191,11 @@ static void guc_ct_fini(struct drm_device *drm, void *arg) { struct xe_guc_ct *ct = arg; + ct_exit_safe_mode(ct); destroy_workqueue(ct->g2h_wq); xa_destroy(&ct->fence_lookup); } -static void receive_g2h(struct xe_guc_ct *ct); -static void g2h_worker_func(struct work_struct *w); -static void safe_mode_worker_func(struct work_struct *w); - static void primelockdep(struct xe_guc_ct *ct) { if (!IS_ENABLED(CONFIG_LOCKDEP)) diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c index 74f31639b37f..f008e8049700 100644 --- a/drivers/gpu/drm/xe/xe_hwmon.c +++ b/drivers/gpu/drm/xe/xe_hwmon.c @@ -159,8 +159,8 @@ static int xe_hwmon_pcode_read_power_limit(const struct xe_hwmon *hwmon, u32 att return ret; } -static int xe_hwmon_pcode_write_power_limit(const struct xe_hwmon *hwmon, u32 attr, u8 channel, - u32 uval) +static int xe_hwmon_pcode_rmw_power_limit(const struct xe_hwmon *hwmon, u32 attr, u8 channel, + u32 clr, u32 set) { struct xe_tile *root_tile = xe_device_get_root_tile(hwmon->xe); u32 val0, val1; @@ -179,7 +179,7 @@ static int xe_hwmon_pcode_write_power_limit(const struct xe_hwmon *hwmon, u32 at channel, val0, val1, ret); if (attr == PL1_HWMON_ATTR) - val0 = uval; + val0 = (val0 & ~clr) | set; else return -EIO; @@ -339,7 +339,7 @@ static int xe_hwmon_power_max_write(struct xe_hwmon *hwmon, u32 attr, int channe if (hwmon->xe->info.has_mbx_power_limits) { drm_dbg(&hwmon->xe->drm, "disabling %s on channel %d\n", PWR_ATTR_TO_STR(attr), channel); - xe_hwmon_pcode_write_power_limit(hwmon, attr, channel, 0); + xe_hwmon_pcode_rmw_power_limit(hwmon, attr, channel, PWR_LIM_EN, 0); xe_hwmon_pcode_read_power_limit(hwmon, attr, channel, ®_val); } else { reg_val = xe_mmio_rmw32(mmio, rapl_limit, PWR_LIM_EN, 0); @@ -370,10 +370,9 @@ static int xe_hwmon_power_max_write(struct xe_hwmon *hwmon, u32 attr, int channe } if (hwmon->xe->info.has_mbx_power_limits) - ret = xe_hwmon_pcode_write_power_limit(hwmon, attr, channel, reg_val); + ret = xe_hwmon_pcode_rmw_power_limit(hwmon, attr, channel, PWR_LIM, reg_val); else - reg_val = xe_mmio_rmw32(mmio, rapl_limit, PWR_LIM_EN | PWR_LIM_VAL, - reg_val); + reg_val = xe_mmio_rmw32(mmio, rapl_limit, PWR_LIM, reg_val); unlock: mutex_unlock(&hwmon->hwmon_lock); return ret; @@ -563,14 +562,11 @@ xe_hwmon_power_max_interval_store(struct device *dev, struct device_attribute *a mutex_lock(&hwmon->hwmon_lock); - if (hwmon->xe->info.has_mbx_power_limits) { - ret = xe_hwmon_pcode_read_power_limit(hwmon, power_attr, channel, (u32 *)&r); - r = (r & ~PWR_LIM_TIME) | rxy; - xe_hwmon_pcode_write_power_limit(hwmon, power_attr, channel, r); - } else { + if (hwmon->xe->info.has_mbx_power_limits) + xe_hwmon_pcode_rmw_power_limit(hwmon, power_attr, channel, PWR_LIM_TIME, rxy); + else r = xe_mmio_rmw32(mmio, xe_hwmon_get_reg(hwmon, REG_PKG_RAPL_LIMIT, channel), PWR_LIM_TIME, rxy); - } mutex_unlock(&hwmon->hwmon_lock); @@ -1138,12 +1134,12 @@ xe_hwmon_get_preregistration_info(struct xe_hwmon *hwmon) } else { drm_info(&hwmon->xe->drm, "Using mailbox commands for power limits\n"); /* Write default limits to read from pcode from now on. */ - xe_hwmon_pcode_write_power_limit(hwmon, PL1_HWMON_ATTR, - CHANNEL_CARD, - hwmon->pl1_on_boot[CHANNEL_CARD]); - xe_hwmon_pcode_write_power_limit(hwmon, PL1_HWMON_ATTR, - CHANNEL_PKG, - hwmon->pl1_on_boot[CHANNEL_PKG]); + xe_hwmon_pcode_rmw_power_limit(hwmon, PL1_HWMON_ATTR, + CHANNEL_CARD, PWR_LIM | PWR_LIM_TIME, + hwmon->pl1_on_boot[CHANNEL_CARD]); + xe_hwmon_pcode_rmw_power_limit(hwmon, PL1_HWMON_ATTR, + CHANNEL_PKG, PWR_LIM | PWR_LIM_TIME, + hwmon->pl1_on_boot[CHANNEL_PKG]); hwmon->scl_shift_power = PWR_UNIT; hwmon->scl_shift_energy = ENERGY_UNIT; hwmon->scl_shift_time = TIME_UNIT; diff --git a/drivers/hid/hid-appletb-kbd.c b/drivers/hid/hid-appletb-kbd.c index 6f251b284018..2e0caf52af13 100644 --- a/drivers/hid/hid-appletb-kbd.c +++ b/drivers/hid/hid-appletb-kbd.c @@ -438,6 +438,8 @@ static int appletb_kbd_probe(struct hid_device *hdev, const struct hid_device_id return 0; close_hw: + if (kbd->backlight_dev) + put_device(&kbd->backlight_dev->dev); hid_hw_close(hdev); stop_hw: hid_hw_stop(hdev); @@ -453,6 +455,9 @@ static void appletb_kbd_remove(struct hid_device *hdev) input_unregister_handler(&kbd->inp_handler); timer_delete_sync(&kbd->inactivity_timer); + if (kbd->backlight_dev) + put_device(&kbd->backlight_dev->dev); + hid_hw_close(hdev); hid_hw_stop(hdev); } diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index e3fb4e2fe911..c6468568aea1 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -312,6 +312,8 @@ #define USB_DEVICE_ID_ASUS_AK1D 0x1125 #define USB_DEVICE_ID_CHICONY_TOSHIBA_WT10A 0x1408 #define USB_DEVICE_ID_CHICONY_ACER_SWITCH12 0x1421 +#define USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA 0xb824 +#define USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA2 0xb82c #define USB_VENDOR_ID_CHUNGHWAT 0x2247 #define USB_DEVICE_ID_CHUNGHWAT_MULTITOUCH 0x0001 @@ -819,6 +821,7 @@ #define USB_DEVICE_ID_LENOVO_TPPRODOCK 0x6067 #define USB_DEVICE_ID_LENOVO_X1_COVER 0x6085 #define USB_DEVICE_ID_LENOVO_X1_TAB 0x60a3 +#define USB_DEVICE_ID_LENOVO_X1_TAB2 0x60a4 #define USB_DEVICE_ID_LENOVO_X1_TAB3 0x60b5 #define USB_DEVICE_ID_LENOVO_X12_TAB 0x60fe #define USB_DEVICE_ID_LENOVO_X12_TAB2 0x61ae @@ -1525,4 +1528,7 @@ #define USB_VENDOR_ID_SIGNOTEC 0x2133 #define USB_DEVICE_ID_SIGNOTEC_VIEWSONIC_PD1011 0x0018 +#define USB_VENDOR_ID_SMARTLINKTECHNOLOGY 0x4c4a +#define USB_DEVICE_ID_SMARTLINKTECHNOLOGY_4155 0x4155 + #endif diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 9d80635a91eb..ff1784b5c2a4 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -2343,7 +2343,7 @@ int hidinput_connect(struct hid_device *hid, unsigned int force) } if (list_empty(&hid->inputs)) { - hid_err(hid, "No inputs registered, leaving\n"); + hid_dbg(hid, "No inputs registered, leaving\n"); goto out_unwind; } diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c index af29ba840522..b3121fa7a72d 100644 --- a/drivers/hid/hid-lenovo.c +++ b/drivers/hid/hid-lenovo.c @@ -492,6 +492,7 @@ static int lenovo_input_mapping(struct hid_device *hdev, case USB_DEVICE_ID_LENOVO_X12_TAB: case USB_DEVICE_ID_LENOVO_X12_TAB2: case USB_DEVICE_ID_LENOVO_X1_TAB: + case USB_DEVICE_ID_LENOVO_X1_TAB2: case USB_DEVICE_ID_LENOVO_X1_TAB3: return lenovo_input_mapping_x1_tab_kbd(hdev, hi, field, usage, bit, max); default: @@ -548,11 +549,14 @@ static void lenovo_features_set_cptkbd(struct hid_device *hdev) /* * Tell the keyboard a driver understands it, and turn F7, F9, F11 into - * regular keys + * regular keys (Compact only) */ - ret = lenovo_send_cmd_cptkbd(hdev, 0x01, 0x03); - if (ret) - hid_warn(hdev, "Failed to switch F7/9/11 mode: %d\n", ret); + if (hdev->product == USB_DEVICE_ID_LENOVO_CUSBKBD || + hdev->product == USB_DEVICE_ID_LENOVO_CBTKBD) { + ret = lenovo_send_cmd_cptkbd(hdev, 0x01, 0x03); + if (ret) + hid_warn(hdev, "Failed to switch F7/9/11 mode: %d\n", ret); + } /* Switch middle button to native mode */ ret = lenovo_send_cmd_cptkbd(hdev, 0x09, 0x01); @@ -605,6 +609,7 @@ static ssize_t attr_fn_lock_store(struct device *dev, case USB_DEVICE_ID_LENOVO_X12_TAB2: case USB_DEVICE_ID_LENOVO_TP10UBKBD: case USB_DEVICE_ID_LENOVO_X1_TAB: + case USB_DEVICE_ID_LENOVO_X1_TAB2: case USB_DEVICE_ID_LENOVO_X1_TAB3: ret = lenovo_led_set_tp10ubkbd(hdev, TP10UBKBD_FN_LOCK_LED, value); if (ret) @@ -861,6 +866,7 @@ static int lenovo_event(struct hid_device *hdev, struct hid_field *field, case USB_DEVICE_ID_LENOVO_X12_TAB2: case USB_DEVICE_ID_LENOVO_TP10UBKBD: case USB_DEVICE_ID_LENOVO_X1_TAB: + case USB_DEVICE_ID_LENOVO_X1_TAB2: case USB_DEVICE_ID_LENOVO_X1_TAB3: return lenovo_event_tp10ubkbd(hdev, field, usage, value); default: @@ -1144,6 +1150,7 @@ static int lenovo_led_brightness_set(struct led_classdev *led_cdev, case USB_DEVICE_ID_LENOVO_X12_TAB2: case USB_DEVICE_ID_LENOVO_TP10UBKBD: case USB_DEVICE_ID_LENOVO_X1_TAB: + case USB_DEVICE_ID_LENOVO_X1_TAB2: case USB_DEVICE_ID_LENOVO_X1_TAB3: ret = lenovo_led_set_tp10ubkbd(hdev, tp10ubkbd_led[led_nr], value); break; @@ -1384,6 +1391,7 @@ static int lenovo_probe(struct hid_device *hdev, case USB_DEVICE_ID_LENOVO_X12_TAB2: case USB_DEVICE_ID_LENOVO_TP10UBKBD: case USB_DEVICE_ID_LENOVO_X1_TAB: + case USB_DEVICE_ID_LENOVO_X1_TAB2: case USB_DEVICE_ID_LENOVO_X1_TAB3: ret = lenovo_probe_tp10ubkbd(hdev); break; @@ -1473,6 +1481,7 @@ static void lenovo_remove(struct hid_device *hdev) case USB_DEVICE_ID_LENOVO_X12_TAB2: case USB_DEVICE_ID_LENOVO_TP10UBKBD: case USB_DEVICE_ID_LENOVO_X1_TAB: + case USB_DEVICE_ID_LENOVO_X1_TAB2: case USB_DEVICE_ID_LENOVO_X1_TAB3: lenovo_remove_tp10ubkbd(hdev); break; @@ -1524,6 +1533,8 @@ static const struct hid_device_id lenovo_devices[] = { { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB2) }, + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB3) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X12_TAB) }, diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index b41001e02da7..a1c54ffe02b4 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -2132,12 +2132,18 @@ static const struct hid_device_id mt_devices[] = { HID_DEVICE(BUS_I2C, HID_GROUP_GENERIC, USB_VENDOR_ID_LG, I2C_DEVICE_ID_LG_7010) }, - /* Lenovo X1 TAB Gen 2 */ + /* Lenovo X1 TAB Gen 1 */ { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT, HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8, USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB) }, + /* Lenovo X1 TAB Gen 2 */ + { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT, + HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8, + USB_VENDOR_ID_LENOVO, + USB_DEVICE_ID_LENOVO_X1_TAB2) }, + /* Lenovo X1 TAB Gen 3 */ { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT, HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8, diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c index 839d5bcd72b1..fb4985988615 100644 --- a/drivers/hid/hid-nintendo.c +++ b/drivers/hid/hid-nintendo.c @@ -308,6 +308,7 @@ enum joycon_ctlr_state { JOYCON_CTLR_STATE_INIT, JOYCON_CTLR_STATE_READ, JOYCON_CTLR_STATE_REMOVED, + JOYCON_CTLR_STATE_SUSPENDED, }; /* Controller type received as part of device info */ @@ -2750,14 +2751,46 @@ static void nintendo_hid_remove(struct hid_device *hdev) static int nintendo_hid_resume(struct hid_device *hdev) { - int ret = joycon_init(hdev); + struct joycon_ctlr *ctlr = hid_get_drvdata(hdev); + int ret; + + hid_dbg(hdev, "resume\n"); + if (!joycon_using_usb(ctlr)) { + hid_dbg(hdev, "no-op resume for bt ctlr\n"); + ctlr->ctlr_state = JOYCON_CTLR_STATE_READ; + return 0; + } + ret = joycon_init(hdev); if (ret) - hid_err(hdev, "Failed to restore controller after resume"); + hid_err(hdev, + "Failed to restore controller after resume: %d\n", + ret); + else + ctlr->ctlr_state = JOYCON_CTLR_STATE_READ; return ret; } +static int nintendo_hid_suspend(struct hid_device *hdev, pm_message_t message) +{ + struct joycon_ctlr *ctlr = hid_get_drvdata(hdev); + + hid_dbg(hdev, "suspend: %d\n", message.event); + /* + * Avoid any blocking loops in suspend/resume transitions. + * + * joycon_enforce_subcmd_rate() can result in repeated retries if for + * whatever reason the controller stops providing input reports. + * + * This has been observed with bluetooth controllers which lose + * connectivity prior to suspend (but not long enough to result in + * complete disconnection). + */ + ctlr->ctlr_state = JOYCON_CTLR_STATE_SUSPENDED; + return 0; +} + #endif static const struct hid_device_id nintendo_hid_devices[] = { @@ -2796,6 +2829,7 @@ static struct hid_driver nintendo_hid_driver = { #ifdef CONFIG_PM .resume = nintendo_hid_resume, + .suspend = nintendo_hid_suspend, #endif }; static int __init nintendo_init(void) diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 7fefeb413ec3..31508da93ba2 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -757,6 +757,8 @@ static const struct hid_device_id hid_ignore_list[] = { { HID_USB_DEVICE(USB_VENDOR_ID_AVERMEDIA, USB_DEVICE_ID_AVER_FM_MR800) }, { HID_USB_DEVICE(USB_VENDOR_ID_AXENTIA, USB_DEVICE_ID_AXENTIA_FM_RADIO) }, { HID_USB_DEVICE(USB_VENDOR_ID_BERKSHIRE, USB_DEVICE_ID_BERKSHIRE_PCWD) }, + { HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA) }, + { HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA2) }, { HID_USB_DEVICE(USB_VENDOR_ID_CIDC, 0x0103) }, { HID_USB_DEVICE(USB_VENDOR_ID_CYGNAL, USB_DEVICE_ID_CYGNAL_RADIO_SI470X) }, { HID_USB_DEVICE(USB_VENDOR_ID_CYGNAL, USB_DEVICE_ID_CYGNAL_RADIO_SI4713) }, @@ -904,6 +906,7 @@ static const struct hid_device_id hid_ignore_list[] = { #endif { HID_USB_DEVICE(USB_VENDOR_ID_YEALINK, USB_DEVICE_ID_YEALINK_P1K_P4K_B2K) }, { HID_USB_DEVICE(USB_VENDOR_ID_QUANTA, USB_DEVICE_ID_QUANTA_HP_5MP_CAMERA_5473) }, + { HID_USB_DEVICE(USB_VENDOR_ID_SMARTLINKTECHNOLOGY, USB_DEVICE_ID_SMARTLINKTECHNOLOGY_4155) }, { } }; diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h index 07e90d51f073..fa5d68c36313 100644 --- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h +++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h @@ -38,6 +38,7 @@ #define PCI_DEVICE_ID_INTEL_ISH_LNL_M 0xA845 #define PCI_DEVICE_ID_INTEL_ISH_PTL_H 0xE345 #define PCI_DEVICE_ID_INTEL_ISH_PTL_P 0xE445 +#define PCI_DEVICE_ID_INTEL_ISH_WCL 0x4D45 #define REVISION_ID_CHT_A0 0x6 #define REVISION_ID_CHT_Ax_SI 0x0 diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c index ff0fc8010072..c57483224db6 100644 --- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c +++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c @@ -27,10 +27,12 @@ enum ishtp_driver_data_index { ISHTP_DRIVER_DATA_NONE, ISHTP_DRIVER_DATA_LNL_M, ISHTP_DRIVER_DATA_PTL, + ISHTP_DRIVER_DATA_WCL, }; #define ISH_FW_GEN_LNL_M "lnlm" #define ISH_FW_GEN_PTL "ptl" +#define ISH_FW_GEN_WCL "wcl" #define ISH_FIRMWARE_PATH(gen) "intel/ish/ish_" gen ".bin" #define ISH_FIRMWARE_PATH_ALL "intel/ish/ish_*.bin" @@ -42,6 +44,9 @@ static struct ishtp_driver_data ishtp_driver_data[] = { [ISHTP_DRIVER_DATA_PTL] = { .fw_generation = ISH_FW_GEN_PTL, }, + [ISHTP_DRIVER_DATA_WCL] = { + .fw_generation = ISH_FW_GEN_WCL, + }, }; static const struct pci_device_id ish_pci_tbl[] = { @@ -67,9 +72,10 @@ static const struct pci_device_id ish_pci_tbl[] = { {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_MTL_P)}, {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_ARL_H)}, {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_ARL_S)}, - {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_LNL_M), .driver_data = ISHTP_DRIVER_DATA_LNL_M}, - {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_PTL_H), .driver_data = ISHTP_DRIVER_DATA_PTL}, - {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_PTL_P), .driver_data = ISHTP_DRIVER_DATA_PTL}, + {PCI_DEVICE_DATA(INTEL, ISH_LNL_M, ISHTP_DRIVER_DATA_LNL_M)}, + {PCI_DEVICE_DATA(INTEL, ISH_PTL_H, ISHTP_DRIVER_DATA_PTL)}, + {PCI_DEVICE_DATA(INTEL, ISH_PTL_P, ISHTP_DRIVER_DATA_PTL)}, + {PCI_DEVICE_DATA(INTEL, ISH_WCL, ISHTP_DRIVER_DATA_WCL)}, {} }; MODULE_DEVICE_TABLE(pci, ish_pci_tbl); diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-protocol.c b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-protocol.c index f493df0d5dc4..a63f8c833252 100644 --- a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-protocol.c +++ b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-protocol.c @@ -4,6 +4,7 @@ #include <linux/bitfield.h> #include <linux/hid.h> #include <linux/hid-over-i2c.h> +#include <linux/unaligned.h> #include "intel-thc-dev.h" #include "intel-thc-dma.h" @@ -200,6 +201,9 @@ int quicki2c_set_report(struct quicki2c_device *qcdev, u8 report_type, int quicki2c_reset(struct quicki2c_device *qcdev) { + u16 input_reg = le16_to_cpu(qcdev->dev_desc.input_reg); + size_t read_len = HIDI2C_LENGTH_LEN; + u32 prd_len = read_len; int ret; qcdev->reset_ack = false; @@ -213,12 +217,32 @@ int quicki2c_reset(struct quicki2c_device *qcdev) ret = wait_event_interruptible_timeout(qcdev->reset_ack_wq, qcdev->reset_ack, HIDI2C_RESET_TIMEOUT * HZ); - if (ret <= 0 || !qcdev->reset_ack) { + if (qcdev->reset_ack) + return 0; + + /* + * Manually read reset response if it wasn't received, in case reset interrupt + * was missed by touch device or THC hardware. + */ + ret = thc_tic_pio_read(qcdev->thc_hw, input_reg, read_len, &prd_len, + (u32 *)qcdev->input_buf); + if (ret) { + dev_err_once(qcdev->dev, "Read Reset Response failed, ret %d\n", ret); + return ret; + } + + /* + * Check response packet length, it's first 16 bits of packet. + * If response packet length is zero, it's reset response, otherwise not. + */ + if (get_unaligned_le16(qcdev->input_buf)) { dev_err_once(qcdev->dev, "Wait reset response timed out ret:%d timeout:%ds\n", ret, HIDI2C_RESET_TIMEOUT); return -ETIMEDOUT; } + qcdev->reset_ack = true; + return 0; } diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index eaf099b2efdb..9a57504e51a1 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -2048,14 +2048,18 @@ static int wacom_initialize_remotes(struct wacom *wacom) remote->remote_dir = kobject_create_and_add("wacom_remote", &wacom->hdev->dev.kobj); - if (!remote->remote_dir) + if (!remote->remote_dir) { + kfifo_free(&remote->remote_fifo); return -ENOMEM; + } error = sysfs_create_files(remote->remote_dir, remote_unpair_attrs); if (error) { hid_err(wacom->hdev, "cannot create sysfs group err: %d\n", error); + kfifo_free(&remote->remote_fifo); + kobject_put(remote->remote_dir); return error; } @@ -2901,6 +2905,7 @@ static void wacom_remove(struct hid_device *hdev) hid_hw_stop(hdev); cancel_delayed_work_sync(&wacom->init_work); + cancel_delayed_work_sync(&wacom->aes_battery_work); cancel_work_sync(&wacom->wireless_work); cancel_work_sync(&wacom->battery_work); cancel_work_sync(&wacom->remote_work); diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index 48c5ab832009..0a4ecccd1851 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -1530,7 +1530,7 @@ config I2C_XGENE_SLIMPRO config SCx200_ACB tristate "Geode ACCESS.bus support" - depends on X86_32 && PCI + depends on X86_32 && PCI && HAS_IOPORT help Enable the use of the ACCESS.bus controllers on the Geode SCx200 and SC1100 processors and the CS5535 and CS5536 Geode companion devices. diff --git a/drivers/i2c/busses/i2c-designware-amdisp.c b/drivers/i2c/busses/i2c-designware-amdisp.c index ad6f08338124..450793d5f839 100644 --- a/drivers/i2c/busses/i2c-designware-amdisp.c +++ b/drivers/i2c/busses/i2c-designware-amdisp.c @@ -8,6 +8,7 @@ #include <linux/module.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> +#include <linux/soc/amd/isp4_misc.h> #include "i2c-designware-core.h" @@ -62,6 +63,7 @@ static int amd_isp_dw_i2c_plat_probe(struct platform_device *pdev) adap = &isp_i2c_dev->adapter; adap->owner = THIS_MODULE; + scnprintf(adap->name, sizeof(adap->name), AMDISP_I2C_ADAP_NAME); ACPI_COMPANION_SET(&adap->dev, ACPI_COMPANION(&pdev->dev)); adap->dev.of_node = pdev->dev.of_node; /* use dynamically allocated adapter id */ diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c index c5394229b77f..9d7d9e47564a 100644 --- a/drivers/i2c/busses/i2c-designware-master.c +++ b/drivers/i2c/busses/i2c-designware-master.c @@ -1042,8 +1042,9 @@ int i2c_dw_probe_master(struct dw_i2c_dev *dev) if (ret) return ret; - snprintf(adap->name, sizeof(adap->name), - "Synopsys DesignWare I2C adapter"); + if (!adap->name[0]) + scnprintf(adap->name, sizeof(adap->name), + "Synopsys DesignWare I2C adapter"); adap->retries = 3; adap->algo = &i2c_dw_algo; adap->quirks = &i2c_dw_quirks; diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index e5732b0557fb..205cc132fdec 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -1008,7 +1008,7 @@ static inline int i2c_imx_isr_read(struct imx_i2c_struct *i2c_imx) /* setup bus to read data */ temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR); temp &= ~I2CR_MTX; - if (i2c_imx->msg->len - 1) + if ((i2c_imx->msg->len - 1) || (i2c_imx->msg->flags & I2C_M_RECV_LEN)) temp &= ~I2CR_TXAK; imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR); @@ -1063,6 +1063,7 @@ static inline void i2c_imx_isr_read_block_data_len(struct imx_i2c_struct *i2c_im wake_up(&i2c_imx->queue); } i2c_imx->msg->len += len; + i2c_imx->msg->buf[i2c_imx->msg_buf_idx++] = len; } static irqreturn_t i2c_imx_master_isr(struct imx_i2c_struct *i2c_imx, unsigned int status) diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index f1cc26ac5b80..8b01df3cc8e9 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -1461,13 +1461,13 @@ omap_i2c_probe(struct platform_device *pdev) if (IS_ERR(mux_state)) { r = PTR_ERR(mux_state); dev_dbg(&pdev->dev, "failed to get I2C mux: %d\n", r); - goto err_disable_pm; + goto err_put_pm; } omap->mux_state = mux_state; r = mux_state_select(omap->mux_state); if (r) { dev_err(&pdev->dev, "failed to select I2C mux: %d\n", r); - goto err_disable_pm; + goto err_put_pm; } } @@ -1515,6 +1515,9 @@ omap_i2c_probe(struct platform_device *pdev) err_unuse_clocks: omap_i2c_write_reg(omap, OMAP_I2C_CON_REG, 0); + if (omap->mux_state) + mux_state_deselect(omap->mux_state); +err_put_pm: pm_runtime_dont_use_autosuspend(omap->dev); pm_runtime_put_sync(omap->dev); err_disable_pm: diff --git a/drivers/i2c/busses/i2c-robotfuzz-osif.c b/drivers/i2c/busses/i2c-robotfuzz-osif.c index 80d45079b763..e0a76fb5bc31 100644 --- a/drivers/i2c/busses/i2c-robotfuzz-osif.c +++ b/drivers/i2c/busses/i2c-robotfuzz-osif.c @@ -111,6 +111,11 @@ static u32 osif_func(struct i2c_adapter *adapter) return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL; } +/* prevent invalid 0-length usb_control_msg */ +static const struct i2c_adapter_quirks osif_quirks = { + .flags = I2C_AQ_NO_ZERO_LEN_READ, +}; + static const struct i2c_algorithm osif_algorithm = { .xfer = osif_xfer, .functionality = osif_func, @@ -143,6 +148,7 @@ static int osif_probe(struct usb_interface *interface, priv->adapter.owner = THIS_MODULE; priv->adapter.class = I2C_CLASS_HWMON; + priv->adapter.quirks = &osif_quirks; priv->adapter.algo = &osif_algorithm; priv->adapter.algo_data = priv; snprintf(priv->adapter.name, sizeof(priv->adapter.name), diff --git a/drivers/i2c/busses/i2c-tiny-usb.c b/drivers/i2c/busses/i2c-tiny-usb.c index a18eab0992a1..57dfe5f1a7d9 100644 --- a/drivers/i2c/busses/i2c-tiny-usb.c +++ b/drivers/i2c/busses/i2c-tiny-usb.c @@ -139,6 +139,11 @@ out: return ret; } +/* prevent invalid 0-length usb_control_msg */ +static const struct i2c_adapter_quirks usb_quirks = { + .flags = I2C_AQ_NO_ZERO_LEN_READ, +}; + /* This is the actual algorithm we define */ static const struct i2c_algorithm usb_algorithm = { .xfer = usb_xfer, @@ -247,6 +252,7 @@ static int i2c_tiny_usb_probe(struct usb_interface *interface, /* setup i2c adapter description */ dev->adapter.owner = THIS_MODULE; dev->adapter.class = I2C_CLASS_HWMON; + dev->adapter.quirks = &usb_quirks; dev->adapter.algo = &usb_algorithm; dev->adapter.algo_data = dev; snprintf(dev->adapter.name, sizeof(dev->adapter.name), diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index 9979a351577f..81cf3c902e81 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -582,8 +582,8 @@ static int __ib_cache_gid_add(struct ib_device *ib_dev, u32 port, out_unlock: mutex_unlock(&table->lock); if (ret) - pr_warn("%s: unable to add gid %pI6 error=%d\n", - __func__, gid->raw, ret); + pr_warn_ratelimited("%s: unable to add gid %pI6 error=%d\n", + __func__, gid->raw, ret); return ret; } diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index c752ae9fad6c..b1c44ec1a3f3 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -76,6 +76,17 @@ static int ib_init_umem_odp(struct ib_umem_odp *umem_odp, end = ALIGN(end, page_size); if (unlikely(end < page_size)) return -EOVERFLOW; + /* + * The mmu notifier can be called within reclaim contexts and takes the + * umem_mutex. This is rare to trigger in testing, teach lockdep about + * it. + */ + if (IS_ENABLED(CONFIG_LOCKDEP)) { + fs_reclaim_acquire(GFP_KERNEL); + mutex_lock(&umem_odp->umem_mutex); + mutex_unlock(&umem_odp->umem_mutex); + fs_reclaim_release(GFP_KERNEL); + } nr_entries = (end - start) >> PAGE_SHIFT; if (!(nr_entries * PAGE_SIZE / page_size)) diff --git a/drivers/infiniband/hw/mlx5/counters.c b/drivers/infiniband/hw/mlx5/counters.c index b847084dcd99..a506fafd2b15 100644 --- a/drivers/infiniband/hw/mlx5/counters.c +++ b/drivers/infiniband/hw/mlx5/counters.c @@ -398,7 +398,7 @@ static int do_get_hw_stats(struct ib_device *ibdev, return ret; /* We don't expose device counters over Vports */ - if (is_mdev_switchdev_mode(dev->mdev) && port_num != 0) + if (is_mdev_switchdev_mode(dev->mdev) && dev->is_rep && port_num != 0) goto done; if (MLX5_CAP_PCAM_FEATURE(dev->mdev, rx_icrc_encapsulated_counter)) { @@ -418,7 +418,7 @@ static int do_get_hw_stats(struct ib_device *ibdev, */ goto done; } - ret = mlx5_lag_query_cong_counters(dev->mdev, + ret = mlx5_lag_query_cong_counters(mdev, stats->value + cnts->num_q_counters, cnts->num_cong_counters, diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index 2479da8620ca..843dcd312242 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -1958,6 +1958,7 @@ subscribe_event_xa_alloc(struct mlx5_devx_event_table *devx_event_table, /* Level1 is valid for future use, no need to free */ return -ENOMEM; + INIT_LIST_HEAD(&obj_event->obj_sub_list); err = xa_insert(&event->object_ids, key_level2, obj_event, @@ -1966,7 +1967,6 @@ subscribe_event_xa_alloc(struct mlx5_devx_event_table *devx_event_table, kfree(obj_event); return err; } - INIT_LIST_HEAD(&obj_event->obj_sub_list); } return 0; @@ -2669,7 +2669,7 @@ static void devx_wait_async_destroy(struct mlx5_async_cmd *cmd) void mlx5_ib_ufile_hw_cleanup(struct ib_uverbs_file *ufile) { - struct mlx5_async_cmd async_cmd[MAX_ASYNC_CMDS]; + struct mlx5_async_cmd *async_cmd; struct ib_ucontext *ucontext = ufile->ucontext; struct ib_device *device = ucontext->device; struct mlx5_ib_dev *dev = to_mdev(device); @@ -2678,6 +2678,10 @@ void mlx5_ib_ufile_hw_cleanup(struct ib_uverbs_file *ufile) int head = 0; int tail = 0; + async_cmd = kcalloc(MAX_ASYNC_CMDS, sizeof(*async_cmd), GFP_KERNEL); + if (!async_cmd) + return; + list_for_each_entry(uobject, &ufile->uobjects, list) { WARN_ON(uverbs_try_lock_object(uobject, UVERBS_LOOKUP_WRITE)); @@ -2713,6 +2717,8 @@ void mlx5_ib_ufile_hw_cleanup(struct ib_uverbs_file *ufile) devx_wait_async_destroy(&async_cmd[head % MAX_ASYNC_CMDS]); head++; } + + kfree(async_cmd); } static ssize_t devx_async_cmd_event_read(struct file *filp, char __user *buf, diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index ce7610740412..df6557ddbdfc 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -1791,6 +1791,33 @@ static void deallocate_uars(struct mlx5_ib_dev *dev, context->devx_uid); } +static int mlx5_ib_enable_lb_mp(struct mlx5_core_dev *master, + struct mlx5_core_dev *slave) +{ + int err; + + err = mlx5_nic_vport_update_local_lb(master, true); + if (err) + return err; + + err = mlx5_nic_vport_update_local_lb(slave, true); + if (err) + goto out; + + return 0; + +out: + mlx5_nic_vport_update_local_lb(master, false); + return err; +} + +static void mlx5_ib_disable_lb_mp(struct mlx5_core_dev *master, + struct mlx5_core_dev *slave) +{ + mlx5_nic_vport_update_local_lb(slave, false); + mlx5_nic_vport_update_local_lb(master, false); +} + int mlx5_ib_enable_lb(struct mlx5_ib_dev *dev, bool td, bool qp) { int err = 0; @@ -3495,6 +3522,8 @@ static void mlx5_ib_unbind_slave_port(struct mlx5_ib_dev *ibdev, lockdep_assert_held(&mlx5_ib_multiport_mutex); + mlx5_ib_disable_lb_mp(ibdev->mdev, mpi->mdev); + mlx5_core_mp_event_replay(ibdev->mdev, MLX5_DRIVER_EVENT_AFFILIATION_REMOVED, NULL); @@ -3590,6 +3619,10 @@ static bool mlx5_ib_bind_slave_port(struct mlx5_ib_dev *ibdev, MLX5_DRIVER_EVENT_AFFILIATION_DONE, &key); + err = mlx5_ib_enable_lb_mp(ibdev->mdev, mpi->mdev); + if (err) + goto unbind; + return true; unbind: diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 57f9bc2a4a3a..bd35e75d9ce5 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -2027,23 +2027,50 @@ void mlx5_ib_revoke_data_direct_mrs(struct mlx5_ib_dev *dev) } } -static int mlx5_revoke_mr(struct mlx5_ib_mr *mr) +static int mlx5_umr_revoke_mr_with_lock(struct mlx5_ib_mr *mr) { - struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device); - struct mlx5_cache_ent *ent = mr->mmkey.cache_ent; - bool is_odp = is_odp_mr(mr); bool is_odp_dma_buf = is_dmabuf_mr(mr) && - !to_ib_umem_dmabuf(mr->umem)->pinned; - bool from_cache = !!ent; - int ret = 0; + !to_ib_umem_dmabuf(mr->umem)->pinned; + bool is_odp = is_odp_mr(mr); + int ret; if (is_odp) mutex_lock(&to_ib_umem_odp(mr->umem)->umem_mutex); if (is_odp_dma_buf) - dma_resv_lock(to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv, NULL); + dma_resv_lock(to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv, + NULL); + + ret = mlx5r_umr_revoke_mr(mr); + + if (is_odp) { + if (!ret) + to_ib_umem_odp(mr->umem)->private = NULL; + mutex_unlock(&to_ib_umem_odp(mr->umem)->umem_mutex); + } + + if (is_odp_dma_buf) { + if (!ret) + to_ib_umem_dmabuf(mr->umem)->private = NULL; + dma_resv_unlock( + to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv); + } - if (mr->mmkey.cacheable && !mlx5r_umr_revoke_mr(mr) && !cache_ent_find_and_store(dev, mr)) { + return ret; +} + +static int mlx5r_handle_mkey_cleanup(struct mlx5_ib_mr *mr) +{ + bool is_odp_dma_buf = is_dmabuf_mr(mr) && + !to_ib_umem_dmabuf(mr->umem)->pinned; + struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device); + struct mlx5_cache_ent *ent = mr->mmkey.cache_ent; + bool is_odp = is_odp_mr(mr); + bool from_cache = !!ent; + int ret; + + if (mr->mmkey.cacheable && !mlx5_umr_revoke_mr_with_lock(mr) && + !cache_ent_find_and_store(dev, mr)) { ent = mr->mmkey.cache_ent; /* upon storing to a clean temp entry - schedule its cleanup */ spin_lock_irq(&ent->mkeys_queue.lock); @@ -2055,7 +2082,7 @@ static int mlx5_revoke_mr(struct mlx5_ib_mr *mr) ent->tmp_cleanup_scheduled = true; } spin_unlock_irq(&ent->mkeys_queue.lock); - goto out; + return 0; } if (ent) { @@ -2064,8 +2091,14 @@ static int mlx5_revoke_mr(struct mlx5_ib_mr *mr) mr->mmkey.cache_ent = NULL; spin_unlock_irq(&ent->mkeys_queue.lock); } + + if (is_odp) + mutex_lock(&to_ib_umem_odp(mr->umem)->umem_mutex); + + if (is_odp_dma_buf) + dma_resv_lock(to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv, + NULL); ret = destroy_mkey(dev, mr); -out: if (is_odp) { if (!ret) to_ib_umem_odp(mr->umem)->private = NULL; @@ -2075,9 +2108,9 @@ out: if (is_odp_dma_buf) { if (!ret) to_ib_umem_dmabuf(mr->umem)->private = NULL; - dma_resv_unlock(to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv); + dma_resv_unlock( + to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv); } - return ret; } @@ -2126,7 +2159,7 @@ static int __mlx5_ib_dereg_mr(struct ib_mr *ibmr) } /* Stop DMA */ - rc = mlx5_revoke_mr(mr); + rc = mlx5r_handle_mkey_cleanup(mr); if (rc) return rc; diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index eaa2f9f5f3a9..f6abd64f07f7 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -259,8 +259,8 @@ static void destroy_unused_implicit_child_mr(struct mlx5_ib_mr *mr) } if (MLX5_CAP_ODP(mr_to_mdev(mr)->mdev, mem_page_fault)) - __xa_erase(&mr_to_mdev(mr)->odp_mkeys, - mlx5_base_mkey(mr->mmkey.key)); + xa_erase(&mr_to_mdev(mr)->odp_mkeys, + mlx5_base_mkey(mr->mmkey.key)); xa_unlock(&imr->implicit_children); /* Freeing a MR is a sleeping operation, so bounce to a work queue */ @@ -532,8 +532,8 @@ static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr, } if (MLX5_CAP_ODP(dev->mdev, mem_page_fault)) { - ret = __xa_store(&dev->odp_mkeys, mlx5_base_mkey(mr->mmkey.key), - &mr->mmkey, GFP_KERNEL); + ret = xa_store(&dev->odp_mkeys, mlx5_base_mkey(mr->mmkey.key), + &mr->mmkey, GFP_KERNEL); if (xa_is_err(ret)) { ret = ERR_PTR(xa_err(ret)); __xa_erase(&imr->implicit_children, idx); diff --git a/drivers/mfd/88pm860x-core.c b/drivers/mfd/88pm860x-core.c index 488e346047c1..77230fbe07be 100644 --- a/drivers/mfd/88pm860x-core.c +++ b/drivers/mfd/88pm860x-core.c @@ -573,7 +573,6 @@ static int device_irq_init(struct pm860x_chip *chip, unsigned long flags = IRQF_TRIGGER_FALLING | IRQF_ONESHOT; int data, mask, ret = -EINVAL; int nr_irqs, irq_base = -1; - struct device_node *node = i2c->dev.of_node; mask = PM8607_B0_MISC1_INV_INT | PM8607_B0_MISC1_INT_CLEAR | PM8607_B0_MISC1_INT_MASK; @@ -624,7 +623,7 @@ static int device_irq_init(struct pm860x_chip *chip, ret = -EBUSY; goto out; } - irq_domain_create_legacy(of_fwnode_handle(node), nr_irqs, chip->irq_base, 0, + irq_domain_create_legacy(dev_fwnode(&i2c->dev), nr_irqs, chip->irq_base, 0, &pm860x_irq_domain_ops, chip); chip->core_irq = i2c->irq; if (!chip->core_irq) diff --git a/drivers/mfd/max8925-core.c b/drivers/mfd/max8925-core.c index 78b16c67a5fc..25377dcce60e 100644 --- a/drivers/mfd/max8925-core.c +++ b/drivers/mfd/max8925-core.c @@ -656,7 +656,6 @@ static int max8925_irq_init(struct max8925_chip *chip, int irq, { unsigned long flags = IRQF_TRIGGER_FALLING | IRQF_ONESHOT; int ret; - struct device_node *node = chip->dev->of_node; /* clear all interrupts */ max8925_reg_read(chip->i2c, MAX8925_CHG_IRQ1); @@ -682,8 +681,9 @@ static int max8925_irq_init(struct max8925_chip *chip, int irq, return -EBUSY; } - irq_domain_create_legacy(of_fwnode_handle(node), MAX8925_NR_IRQS, chip->irq_base, 0, - &max8925_irq_domain_ops, chip); + irq_domain_create_legacy(dev_fwnode(chip->dev), MAX8925_NR_IRQS, + chip->irq_base, 0, &max8925_irq_domain_ops, + chip); /* request irq handler for pmic main irq*/ chip->core_irq = irq; diff --git a/drivers/mfd/twl4030-irq.c b/drivers/mfd/twl4030-irq.c index 232c2bfe8c18..d3ab40651307 100644 --- a/drivers/mfd/twl4030-irq.c +++ b/drivers/mfd/twl4030-irq.c @@ -676,7 +676,6 @@ int twl4030_init_irq(struct device *dev, int irq_num) static struct irq_chip twl4030_irq_chip; int status, i; int irq_base, irq_end, nr_irqs; - struct device_node *node = dev->of_node; /* * TWL core and pwr interrupts must be contiguous because @@ -691,7 +690,7 @@ int twl4030_init_irq(struct device *dev, int irq_num) return irq_base; } - irq_domain_create_legacy(of_fwnode_handle(node), nr_irqs, irq_base, 0, + irq_domain_create_legacy(dev_fwnode(dev), nr_irqs, irq_base, 0, &irq_domain_simple_ops, NULL); irq_end = irq_base + TWL4030_CORE_NR_IRQS; diff --git a/drivers/mmc/core/quirks.h b/drivers/mmc/core/quirks.h index 7f893bafaa60..c417ed34c057 100644 --- a/drivers/mmc/core/quirks.h +++ b/drivers/mmc/core/quirks.h @@ -44,6 +44,12 @@ static const struct mmc_fixup __maybe_unused mmc_sd_fixups[] = { 0, -1ull, SDIO_ANY_ID, SDIO_ANY_ID, add_quirk_sd, MMC_QUIRK_NO_UHS_DDR50_TUNING, EXT_CSD_REV_ANY), + /* + * Some SD cards reports discard support while they don't + */ + MMC_FIXUP(CID_NAME_ANY, CID_MANFID_SANDISK_SD, 0x5344, add_quirk_sd, + MMC_QUIRK_BROKEN_SD_DISCARD), + END_FIXUP }; @@ -147,12 +153,6 @@ static const struct mmc_fixup __maybe_unused mmc_blk_fixups[] = { MMC_FIXUP("M62704", CID_MANFID_KINGSTON, 0x0100, add_quirk_mmc, MMC_QUIRK_TRIM_BROKEN), - /* - * Some SD cards reports discard support while they don't - */ - MMC_FIXUP(CID_NAME_ANY, CID_MANFID_SANDISK_SD, 0x5344, add_quirk_sd, - MMC_QUIRK_BROKEN_SD_DISCARD), - END_FIXUP }; diff --git a/drivers/mmc/core/sd_uhs2.c b/drivers/mmc/core/sd_uhs2.c index 1c31d0dfa961..de17d1611290 100644 --- a/drivers/mmc/core/sd_uhs2.c +++ b/drivers/mmc/core/sd_uhs2.c @@ -91,8 +91,8 @@ static int sd_uhs2_phy_init(struct mmc_host *host) err = host->ops->uhs2_control(host, UHS2_PHY_INIT); if (err) { - pr_err("%s: failed to initial phy for UHS-II!\n", - mmc_hostname(host)); + pr_debug("%s: failed to initial phy for UHS-II!\n", + mmc_hostname(host)); } return err; diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index 31eb90536bce..d7020e06dd55 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -846,12 +846,18 @@ static inline void msdc_dma_setup(struct msdc_host *host, struct msdc_dma *dma, static void msdc_prepare_data(struct msdc_host *host, struct mmc_data *data) { if (!(data->host_cookie & MSDC_PREPARE_FLAG)) { - data->host_cookie |= MSDC_PREPARE_FLAG; data->sg_count = dma_map_sg(host->dev, data->sg, data->sg_len, mmc_get_dma_dir(data)); + if (data->sg_count) + data->host_cookie |= MSDC_PREPARE_FLAG; } } +static bool msdc_data_prepared(struct mmc_data *data) +{ + return data->host_cookie & MSDC_PREPARE_FLAG; +} + static void msdc_unprepare_data(struct msdc_host *host, struct mmc_data *data) { if (data->host_cookie & MSDC_ASYNC_FLAG) @@ -1483,8 +1489,19 @@ static void msdc_ops_request(struct mmc_host *mmc, struct mmc_request *mrq) WARN_ON(!host->hsq_en && host->mrq); host->mrq = mrq; - if (mrq->data) + if (mrq->data) { msdc_prepare_data(host, mrq->data); + if (!msdc_data_prepared(mrq->data)) { + host->mrq = NULL; + /* + * Failed to prepare DMA area, fail fast before + * starting any commands. + */ + mrq->cmd->error = -ENOSPC; + mmc_request_done(mmc_from_priv(host), mrq); + return; + } + } /* if SBC is required, we have HW option and SW option. * if HW option is enabled, and SBC does not have "special" flags, diff --git a/drivers/mmc/host/sdhci-of-k1.c b/drivers/mmc/host/sdhci-of-k1.c index 6880d3e9ab62..2e5da7c5834c 100644 --- a/drivers/mmc/host/sdhci-of-k1.c +++ b/drivers/mmc/host/sdhci-of-k1.c @@ -276,7 +276,8 @@ static int spacemit_sdhci_probe(struct platform_device *pdev) host->mmc->caps |= MMC_CAP_NEED_RSP_BUSY; - if (spacemit_sdhci_get_clocks(dev, pltfm_host)) + ret = spacemit_sdhci_get_clocks(dev, pltfm_host); + if (ret) goto err_pltfm; ret = sdhci_add_host(host); diff --git a/drivers/mmc/host/sdhci-uhs2.c b/drivers/mmc/host/sdhci-uhs2.c index c53b64d50c0d..0efeb9d0c376 100644 --- a/drivers/mmc/host/sdhci-uhs2.c +++ b/drivers/mmc/host/sdhci-uhs2.c @@ -99,8 +99,8 @@ void sdhci_uhs2_reset(struct sdhci_host *host, u16 mask) /* hw clears the bit when it's done */ if (read_poll_timeout_atomic(sdhci_readw, val, !(val & mask), 10, UHS2_RESET_TIMEOUT_100MS, true, host, SDHCI_UHS2_SW_RESET)) { - pr_warn("%s: %s: Reset 0x%x never completed. %s: clean reset bit.\n", __func__, - mmc_hostname(host->mmc), (int)mask, mmc_hostname(host->mmc)); + pr_debug("%s: %s: Reset 0x%x never completed. %s: clean reset bit.\n", __func__, + mmc_hostname(host->mmc), (int)mask, mmc_hostname(host->mmc)); sdhci_writeb(host, 0, SDHCI_UHS2_SW_RESET); return; } @@ -335,8 +335,8 @@ static int sdhci_uhs2_interface_detect(struct sdhci_host *host) if (read_poll_timeout(sdhci_readl, val, (val & SDHCI_UHS2_IF_DETECT), 100, UHS2_INTERFACE_DETECT_TIMEOUT_100MS, true, host, SDHCI_PRESENT_STATE)) { - pr_warn("%s: not detect UHS2 interface in 100ms.\n", mmc_hostname(host->mmc)); - sdhci_dumpregs(host); + pr_debug("%s: not detect UHS2 interface in 100ms.\n", mmc_hostname(host->mmc)); + sdhci_dbg_dumpregs(host, "UHS2 interface detect timeout in 100ms"); return -EIO; } @@ -345,8 +345,8 @@ static int sdhci_uhs2_interface_detect(struct sdhci_host *host) if (read_poll_timeout(sdhci_readl, val, (val & SDHCI_UHS2_LANE_SYNC), 100, UHS2_LANE_SYNC_TIMEOUT_150MS, true, host, SDHCI_PRESENT_STATE)) { - pr_warn("%s: UHS2 Lane sync fail in 150ms.\n", mmc_hostname(host->mmc)); - sdhci_dumpregs(host); + pr_debug("%s: UHS2 Lane sync fail in 150ms.\n", mmc_hostname(host->mmc)); + sdhci_dbg_dumpregs(host, "UHS2 Lane sync fail in 150ms"); return -EIO; } @@ -417,12 +417,12 @@ static int sdhci_uhs2_do_detect_init(struct mmc_host *mmc) host->ops->uhs2_pre_detect_init(host); if (sdhci_uhs2_interface_detect(host)) { - pr_warn("%s: cannot detect UHS2 interface.\n", mmc_hostname(host->mmc)); + pr_debug("%s: cannot detect UHS2 interface.\n", mmc_hostname(host->mmc)); return -EIO; } if (sdhci_uhs2_init(host)) { - pr_warn("%s: UHS2 init fail.\n", mmc_hostname(host->mmc)); + pr_debug("%s: UHS2 init fail.\n", mmc_hostname(host->mmc)); return -EIO; } @@ -504,8 +504,8 @@ static int sdhci_uhs2_check_dormant(struct sdhci_host *host) if (read_poll_timeout(sdhci_readl, val, (val & SDHCI_UHS2_IN_DORMANT_STATE), 100, UHS2_CHECK_DORMANT_TIMEOUT_100MS, true, host, SDHCI_PRESENT_STATE)) { - pr_warn("%s: UHS2 IN_DORMANT fail in 100ms.\n", mmc_hostname(host->mmc)); - sdhci_dumpregs(host); + pr_debug("%s: UHS2 IN_DORMANT fail in 100ms.\n", mmc_hostname(host->mmc)); + sdhci_dbg_dumpregs(host, "UHS2 IN_DORMANT fail in 100ms"); return -EIO; } return 0; diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index f008167d1863..e116f2db34d5 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -2065,15 +2065,10 @@ void sdhci_set_clock(struct sdhci_host *host, unsigned int clock) host->mmc->actual_clock = 0; - clk = sdhci_readw(host, SDHCI_CLOCK_CONTROL); - if (clk & SDHCI_CLOCK_CARD_EN) - sdhci_writew(host, clk & ~SDHCI_CLOCK_CARD_EN, - SDHCI_CLOCK_CONTROL); + sdhci_writew(host, 0, SDHCI_CLOCK_CONTROL); - if (clock == 0) { - sdhci_writew(host, 0, SDHCI_CLOCK_CONTROL); + if (clock == 0) return; - } clk = sdhci_calc_clk(host, clock, &host->mmc->actual_clock); sdhci_enable_clk(host, clk); diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h index f9d65dd0f2b2..70ada1857a4c 100644 --- a/drivers/mmc/host/sdhci.h +++ b/drivers/mmc/host/sdhci.h @@ -900,4 +900,20 @@ void sdhci_switch_external_dma(struct sdhci_host *host, bool en); void sdhci_set_data_timeout_irq(struct sdhci_host *host, bool enable); void __sdhci_set_timeout(struct sdhci_host *host, struct mmc_command *cmd); +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) +#define SDHCI_DBG_ANYWAY 0 +#elif defined(DEBUG) +#define SDHCI_DBG_ANYWAY 1 +#else +#define SDHCI_DBG_ANYWAY 0 +#endif + +#define sdhci_dbg_dumpregs(host, fmt) \ +do { \ + DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ + if (DYNAMIC_DEBUG_BRANCH(descriptor) || SDHCI_DBG_ANYWAY) \ + sdhci_dumpregs(host); \ +} while (0) + #endif /* __SDHCI_HW_H */ diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index c6807e473ab7..a8d8aaa169fc 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -1378,7 +1378,7 @@ static void ad_tx_machine(struct port *port) /* check if tx timer expired, to verify that we do not send more than * 3 packets per second */ - if (port->sm_tx_timer_counter && !(--port->sm_tx_timer_counter)) { + if (!port->sm_tx_timer_counter || !(--port->sm_tx_timer_counter)) { /* check if there is something to send */ if (port->ntt && (port->sm_vars & AD_PORT_LACP_ENABLED)) { __update_lacpdu_from_port(port); @@ -1393,12 +1393,13 @@ static void ad_tx_machine(struct port *port) * again until demanded */ port->ntt = false; + + /* restart tx timer(to verify that we will not + * exceed AD_MAX_TX_IN_SECOND + */ + port->sm_tx_timer_counter = ad_ticks_per_sec / AD_MAX_TX_IN_SECOND; } } - /* restart tx timer(to verify that we will not exceed - * AD_MAX_TX_IN_SECOND - */ - port->sm_tx_timer_counter = ad_ticks_per_sec/AD_MAX_TX_IN_SECOND; } } diff --git a/drivers/net/dsa/hirschmann/hellcreek.c b/drivers/net/dsa/hirschmann/hellcreek.c index 283ec5a6e23c..e0b4758ca583 100644 --- a/drivers/net/dsa/hirschmann/hellcreek.c +++ b/drivers/net/dsa/hirschmann/hellcreek.c @@ -1061,7 +1061,7 @@ static void hellcreek_setup_tc_identity_mapping(struct hellcreek *hellcreek) static int hellcreek_setup_fdb(struct hellcreek *hellcreek) { - static struct hellcreek_fdb_entry l2_ptp = { + static const struct hellcreek_fdb_entry l2_ptp = { /* MAC: 01-1B-19-00-00-00 */ .mac = { 0x01, 0x1b, 0x19, 0x00, 0x00, 0x00 }, .portmask = 0x03, /* Management ports */ @@ -1072,7 +1072,7 @@ static int hellcreek_setup_fdb(struct hellcreek *hellcreek) .reprio_tc = 6, /* TC: 6 as per IEEE 802.1AS */ .reprio_en = 1, }; - static struct hellcreek_fdb_entry udp4_ptp = { + static const struct hellcreek_fdb_entry udp4_ptp = { /* MAC: 01-00-5E-00-01-81 */ .mac = { 0x01, 0x00, 0x5e, 0x00, 0x01, 0x81 }, .portmask = 0x03, /* Management ports */ @@ -1083,7 +1083,7 @@ static int hellcreek_setup_fdb(struct hellcreek *hellcreek) .reprio_tc = 6, .reprio_en = 1, }; - static struct hellcreek_fdb_entry udp6_ptp = { + static const struct hellcreek_fdb_entry udp6_ptp = { /* MAC: 33-33-00-00-01-81 */ .mac = { 0x33, 0x33, 0x00, 0x00, 0x01, 0x81 }, .portmask = 0x03, /* Management ports */ @@ -1094,7 +1094,7 @@ static int hellcreek_setup_fdb(struct hellcreek *hellcreek) .reprio_tc = 6, .reprio_en = 1, }; - static struct hellcreek_fdb_entry l2_p2p = { + static const struct hellcreek_fdb_entry l2_p2p = { /* MAC: 01-80-C2-00-00-0E */ .mac = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x0e }, .portmask = 0x03, /* Management ports */ @@ -1105,7 +1105,7 @@ static int hellcreek_setup_fdb(struct hellcreek *hellcreek) .reprio_tc = 6, /* TC: 6 as per IEEE 802.1AS */ .reprio_en = 1, }; - static struct hellcreek_fdb_entry udp4_p2p = { + static const struct hellcreek_fdb_entry udp4_p2p = { /* MAC: 01-00-5E-00-00-6B */ .mac = { 0x01, 0x00, 0x5e, 0x00, 0x00, 0x6b }, .portmask = 0x03, /* Management ports */ @@ -1116,7 +1116,7 @@ static int hellcreek_setup_fdb(struct hellcreek *hellcreek) .reprio_tc = 6, .reprio_en = 1, }; - static struct hellcreek_fdb_entry udp6_p2p = { + static const struct hellcreek_fdb_entry udp6_p2p = { /* MAC: 33-33-00-00-00-6B */ .mac = { 0x33, 0x33, 0x00, 0x00, 0x00, 0x6b }, .portmask = 0x03, /* Management ports */ @@ -1127,7 +1127,7 @@ static int hellcreek_setup_fdb(struct hellcreek *hellcreek) .reprio_tc = 6, .reprio_en = 1, }; - static struct hellcreek_fdb_entry stp = { + static const struct hellcreek_fdb_entry stp = { /* MAC: 01-80-C2-00-00-00 */ .mac = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }, .portmask = 0x03, /* Management ports */ @@ -1320,13 +1320,13 @@ static int hellcreek_devlink_region_fdb_snapshot(struct devlink *dl, return 0; } -static struct devlink_region_ops hellcreek_region_vlan_ops = { +static const struct devlink_region_ops hellcreek_region_vlan_ops = { .name = "vlan", .snapshot = hellcreek_devlink_region_vlan_snapshot, .destructor = kfree, }; -static struct devlink_region_ops hellcreek_region_fdb_ops = { +static const struct devlink_region_ops hellcreek_region_fdb_ops = { .name = "fdb", .snapshot = hellcreek_devlink_region_fdb_snapshot, .destructor = kfree, @@ -1335,7 +1335,7 @@ static struct devlink_region_ops hellcreek_region_fdb_ops = { static int hellcreek_setup_devlink_regions(struct dsa_switch *ds) { struct hellcreek *hellcreek = ds->priv; - struct devlink_region_ops *ops; + const struct devlink_region_ops *ops; struct devlink_region *region; u64 size; int ret; diff --git a/drivers/net/dsa/mv88e6xxx/devlink.c b/drivers/net/dsa/mv88e6xxx/devlink.c index 195460a0a0d4..da69e0b85879 100644 --- a/drivers/net/dsa/mv88e6xxx/devlink.c +++ b/drivers/net/dsa/mv88e6xxx/devlink.c @@ -376,19 +376,14 @@ static int mv88e6xxx_region_atu_snapshot(struct devlink *dl, struct dsa_switch *ds = dsa_devlink_to_ds(dl); struct mv88e6xxx_devlink_atu_entry *table; struct mv88e6xxx_chip *chip = ds->priv; - int fid = -1, err = 0, count; + int fid = -1, err = 0, count = 0; - table = kmalloc_array(mv88e6xxx_num_databases(chip), - sizeof(struct mv88e6xxx_devlink_atu_entry), - GFP_KERNEL); + table = kcalloc(mv88e6xxx_num_databases(chip), + sizeof(struct mv88e6xxx_devlink_atu_entry), + GFP_KERNEL); if (!table) return -ENOMEM; - memset(table, 0, mv88e6xxx_num_databases(chip) * - sizeof(struct mv88e6xxx_devlink_atu_entry)); - - count = 0; - mv88e6xxx_reg_lock(chip); while (1) { @@ -647,7 +642,7 @@ static struct mv88e6xxx_region_priv mv88e6xxx_region_global1_priv = { .id = MV88E6XXX_REGION_GLOBAL1, }; -static struct devlink_region_ops mv88e6xxx_region_global1_ops = { +static const struct devlink_region_ops mv88e6xxx_region_global1_ops = { .name = "global1", .snapshot = mv88e6xxx_region_global_snapshot, .destructor = kfree, @@ -658,32 +653,32 @@ static struct mv88e6xxx_region_priv mv88e6xxx_region_global2_priv = { .id = MV88E6XXX_REGION_GLOBAL2, }; -static struct devlink_region_ops mv88e6xxx_region_global2_ops = { +static const struct devlink_region_ops mv88e6xxx_region_global2_ops = { .name = "global2", .snapshot = mv88e6xxx_region_global_snapshot, .destructor = kfree, .priv = &mv88e6xxx_region_global2_priv, }; -static struct devlink_region_ops mv88e6xxx_region_atu_ops = { +static const struct devlink_region_ops mv88e6xxx_region_atu_ops = { .name = "atu", .snapshot = mv88e6xxx_region_atu_snapshot, .destructor = kfree, }; -static struct devlink_region_ops mv88e6xxx_region_vtu_ops = { +static const struct devlink_region_ops mv88e6xxx_region_vtu_ops = { .name = "vtu", .snapshot = mv88e6xxx_region_vtu_snapshot, .destructor = kfree, }; -static struct devlink_region_ops mv88e6xxx_region_stu_ops = { +static const struct devlink_region_ops mv88e6xxx_region_stu_ops = { .name = "stu", .snapshot = mv88e6xxx_region_stu_snapshot, .destructor = kfree, }; -static struct devlink_region_ops mv88e6xxx_region_pvt_ops = { +static const struct devlink_region_ops mv88e6xxx_region_pvt_ops = { .name = "pvt", .snapshot = mv88e6xxx_region_pvt_snapshot, .destructor = kfree, @@ -696,13 +691,13 @@ static const struct devlink_port_region_ops mv88e6xxx_region_port_ops = { }; struct mv88e6xxx_region { - struct devlink_region_ops *ops; + const struct devlink_region_ops *ops; u64 size; bool (*cond)(struct mv88e6xxx_chip *chip); }; -static struct mv88e6xxx_region mv88e6xxx_regions[] = { +static const struct mv88e6xxx_region mv88e6xxx_regions[] = { [MV88E6XXX_REGION_GLOBAL1] = { .ops = &mv88e6xxx_region_global1_ops, .size = 32 * sizeof(u16) @@ -768,7 +763,7 @@ int mv88e6xxx_setup_devlink_regions_global(struct dsa_switch *ds) { bool (*cond)(struct mv88e6xxx_chip *chip); struct mv88e6xxx_chip *chip = ds->priv; - struct devlink_region_ops *ops; + const struct devlink_region_ops *ops; struct devlink_region *region; u64 size; int i, j; diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 06dea3a13e77..10a167224bf5 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -551,9 +551,7 @@ static int airoha_fe_init(struct airoha_eth *eth) static int airoha_qdma_fill_rx_queue(struct airoha_queue *q) { - enum dma_data_direction dir = page_pool_get_dma_dir(q->page_pool); struct airoha_qdma *qdma = q->qdma; - struct airoha_eth *eth = qdma->eth; int qid = q - &qdma->q_rx[0]; int nframes = 0; @@ -577,9 +575,6 @@ static int airoha_qdma_fill_rx_queue(struct airoha_queue *q) e->dma_addr = page_pool_get_dma_addr(page) + offset; e->dma_len = SKB_WITH_OVERHEAD(q->buf_size); - dma_sync_single_for_device(eth->dev, e->dma_addr, e->dma_len, - dir); - val = FIELD_PREP(QDMA_DESC_LEN_MASK, e->dma_len); WRITE_ONCE(desc->ctrl, cpu_to_le32(val)); WRITE_ONCE(desc->addr, cpu_to_le32(e->dma_addr)); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h index e1296cbf4ff3..e54e3e36d3f9 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h @@ -364,6 +364,10 @@ #define MAC_RCR_CST_WIDTH 1 #define MAC_RCR_DCRCC_INDEX 3 #define MAC_RCR_DCRCC_WIDTH 1 +#define MAC_RCR_GPSLCE_INDEX 6 +#define MAC_RCR_GPSLCE_WIDTH 1 +#define MAC_RCR_WD_INDEX 7 +#define MAC_RCR_WD_WIDTH 1 #define MAC_RCR_HDSMS_INDEX 12 #define MAC_RCR_HDSMS_WIDTH 3 #define MAC_RCR_IPC_INDEX 9 @@ -374,6 +378,8 @@ #define MAC_RCR_LM_WIDTH 1 #define MAC_RCR_RE_INDEX 0 #define MAC_RCR_RE_WIDTH 1 +#define MAC_RCR_GPSL_INDEX 16 +#define MAC_RCR_GPSL_WIDTH 14 #define MAC_RFCR_PFCE_INDEX 8 #define MAC_RFCR_PFCE_WIDTH 1 #define MAC_RFCR_RFE_INDEX 0 @@ -412,6 +418,8 @@ #define MAC_TCR_VNE_WIDTH 1 #define MAC_TCR_VNM_INDEX 25 #define MAC_TCR_VNM_WIDTH 1 +#define MAC_TCR_JD_INDEX 16 +#define MAC_TCR_JD_WIDTH 1 #define MAC_TIR_TNID_INDEX 0 #define MAC_TIR_TNID_WIDTH 16 #define MAC_TSCR_AV8021ASMEN_INDEX 28 @@ -1269,6 +1277,8 @@ #define MDIO_VEND2_CTRL1_SS13 BIT(13) #endif +#define XGBE_VEND2_MAC_AUTO_SW BIT(9) + /* MDIO mask values */ #define XGBE_AN_CL73_INT_CMPLT BIT(0) #define XGBE_AN_CL73_INC_LINK BIT(1) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index 466b5f6e5578..9e4e79bfe624 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -2850,9 +2850,19 @@ static void xgbe_config_jumbo_enable(struct xgbe_prv_data *pdata) { unsigned int val; - val = (pdata->netdev->mtu > XGMAC_STD_PACKET_MTU) ? 1 : 0; - - XGMAC_IOWRITE_BITS(pdata, MAC_RCR, JE, val); + if (pdata->netdev->mtu > XGMAC_JUMBO_PACKET_MTU) { + XGMAC_IOWRITE_BITS(pdata, MAC_RCR, GPSL, + XGMAC_GIANT_PACKET_MTU); + XGMAC_IOWRITE_BITS(pdata, MAC_RCR, WD, 1); + XGMAC_IOWRITE_BITS(pdata, MAC_TCR, JD, 1); + XGMAC_IOWRITE_BITS(pdata, MAC_RCR, GPSLCE, 1); + } else { + val = pdata->netdev->mtu > XGMAC_STD_PACKET_MTU ? 1 : 0; + XGMAC_IOWRITE_BITS(pdata, MAC_RCR, GPSLCE, 0); + XGMAC_IOWRITE_BITS(pdata, MAC_RCR, WD, 0); + XGMAC_IOWRITE_BITS(pdata, MAC_TCR, JD, 0); + XGMAC_IOWRITE_BITS(pdata, MAC_RCR, JE, val); + } } static void xgbe_config_mac_speed(struct xgbe_prv_data *pdata) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c index 4ebdd123c435..d1f0419edb23 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c @@ -275,7 +275,7 @@ int xgbe_config_netdev(struct xgbe_prv_data *pdata) netdev->priv_flags |= IFF_UNICAST_FLT; netdev->min_mtu = 0; - netdev->max_mtu = XGMAC_JUMBO_PACKET_MTU; + netdev->max_mtu = XGMAC_GIANT_PACKET_MTU - XGBE_ETH_FRAME_HDR; /* Use default watchdog timeout */ netdev->watchdog_timeo = 0; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 71449edbb76d..1a37ec45e650 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -266,6 +266,10 @@ static void xgbe_an37_set(struct xgbe_prv_data *pdata, bool enable, reg |= MDIO_VEND2_CTRL1_AN_RESTART; XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_CTRL1, reg); + + reg = XMDIO_READ(pdata, MDIO_MMD_VEND2, MDIO_PCS_DIG_CTRL); + reg |= XGBE_VEND2_MAC_AUTO_SW; + XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_PCS_DIG_CTRL, reg); } static void xgbe_an37_restart(struct xgbe_prv_data *pdata) @@ -894,6 +898,11 @@ static void xgbe_an37_init(struct xgbe_prv_data *pdata) netif_dbg(pdata, link, pdata->netdev, "CL37 AN (%s) initialized\n", (pdata->an_mode == XGBE_AN_MODE_CL37) ? "BaseX" : "SGMII"); + + reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_CTRL1); + reg &= ~MDIO_AN_CTRL1_ENABLE; + XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_CTRL1, reg); + } static void xgbe_an73_init(struct xgbe_prv_data *pdata) @@ -1295,6 +1304,10 @@ static void xgbe_phy_status(struct xgbe_prv_data *pdata) pdata->phy.link = pdata->phy_if.phy_impl.link_status(pdata, &an_restart); + /* bail out if the link status register read fails */ + if (pdata->phy.link < 0) + return; + if (an_restart) { xgbe_phy_config_aneg(pdata); goto adjust_link; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index 7a4dfa4e19c7..23c39e92e783 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -2746,8 +2746,7 @@ static bool xgbe_phy_valid_speed(struct xgbe_prv_data *pdata, int speed) static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart) { struct xgbe_phy_data *phy_data = pdata->phy_data; - unsigned int reg; - int ret; + int reg, ret; *an_restart = 0; @@ -2781,11 +2780,20 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart) return 0; } - /* Link status is latched low, so read once to clear - * and then read again to get current state - */ - reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1); reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1); + if (reg < 0) + return reg; + + /* Link status is latched low so that momentary link drops + * can be detected. If link was already down read again + * to get the latest state. + */ + + if (!pdata->phy.link && !(reg & MDIO_STAT1_LSTATUS)) { + reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1); + if (reg < 0) + return reg; + } if (pdata->en_rx_adap) { /* if the link is available and adaptation is done, @@ -2804,9 +2812,7 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart) xgbe_phy_set_mode(pdata, phy_data->cur_mode); } - /* check again for the link and adaptation status */ - reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1); - if ((reg & MDIO_STAT1_LSTATUS) && pdata->rx_adapt_done) + if (pdata->rx_adapt_done) return 1; } else if (reg & MDIO_STAT1_LSTATUS) return 1; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index 6359bb87dc13..70169ea23c7f 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -80,11 +80,13 @@ #define XGBE_IRQ_MODE_EDGE 0 #define XGBE_IRQ_MODE_LEVEL 1 +#define XGBE_ETH_FRAME_HDR (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN) #define XGMAC_MIN_PACKET 60 #define XGMAC_STD_PACKET_MTU 1500 #define XGMAC_MAX_STD_PACKET 1518 #define XGMAC_JUMBO_PACKET_MTU 9000 #define XGMAC_MAX_JUMBO_PACKET 9018 +#define XGMAC_GIANT_PACKET_MTU 16368 #define XGMAC_ETH_PREAMBLE (12 + 8) /* Inter-frame gap + preamble */ #define XGMAC_PFC_DATA_LEN 46 @@ -183,12 +185,12 @@ #define XGBE_LINK_TIMEOUT 5 #define XGBE_KR_TRAINING_WAIT_ITER 50 -#define XGBE_SGMII_AN_LINK_STATUS BIT(1) +#define XGBE_SGMII_AN_LINK_DUPLEX BIT(1) #define XGBE_SGMII_AN_LINK_SPEED (BIT(2) | BIT(3)) #define XGBE_SGMII_AN_LINK_SPEED_10 0x00 #define XGBE_SGMII_AN_LINK_SPEED_100 0x04 #define XGBE_SGMII_AN_LINK_SPEED_1000 0x08 -#define XGBE_SGMII_AN_LINK_DUPLEX BIT(4) +#define XGBE_SGMII_AN_LINK_STATUS BIT(4) /* ECC correctable error notification window (seconds) */ #define XGBE_ECC_LIMIT 60 diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h index 42c0efc1b455..4e66fd9b2ab1 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -113,6 +113,8 @@ struct aq_stats_s { #define AQ_HW_POWER_STATE_D0 0U #define AQ_HW_POWER_STATE_D3 3U +#define AQ_FW_WAKE_ON_LINK_RTPM BIT(10) + #define AQ_HW_FLAG_STARTED 0x00000004U #define AQ_HW_FLAG_STOPPING 0x00000008U #define AQ_HW_FLAG_RESETTING 0x00000010U diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index 08630ee94251..ed5231dece3f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -463,7 +463,7 @@ static const struct dev_pm_ops aq_pm_ops = { }; #endif -static struct pci_driver aq_pci_ops = { +static struct pci_driver aq_pci_driver = { .name = AQ_CFG_DRV_NAME, .id_table = aq_pci_tbl, .probe = aq_pci_probe, @@ -476,11 +476,11 @@ static struct pci_driver aq_pci_ops = { int aq_pci_func_register_driver(void) { - return pci_register_driver(&aq_pci_ops); + return pci_register_driver(&aq_pci_driver); } void aq_pci_func_unregister_driver(void) { - pci_unregister_driver(&aq_pci_ops); + pci_unregister_driver(&aq_pci_driver); } diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c index 52e2070a4a2f..7370e3f76b62 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c @@ -462,6 +462,44 @@ static int aq_a2_fw_get_mac_temp(struct aq_hw_s *self, int *temp) return aq_a2_fw_get_phy_temp(self, temp); } +static int aq_a2_fw_set_wol_params(struct aq_hw_s *self, const u8 *mac, u32 wol) +{ + struct mac_address_aligned_s mac_address; + struct link_control_s link_control; + struct wake_on_lan_s wake_on_lan; + + memcpy(mac_address.aligned.mac_address, mac, ETH_ALEN); + hw_atl2_shared_buffer_write(self, mac_address, mac_address); + + memset(&wake_on_lan, 0, sizeof(wake_on_lan)); + + if (wol & WAKE_MAGIC) + wake_on_lan.wake_on_magic_packet = 1U; + + if (wol & (WAKE_PHY | AQ_FW_WAKE_ON_LINK_RTPM)) + wake_on_lan.wake_on_link_up = 1U; + + hw_atl2_shared_buffer_write(self, sleep_proxy, wake_on_lan); + + hw_atl2_shared_buffer_get(self, link_control, link_control); + link_control.mode = AQ_HOST_MODE_SLEEP_PROXY; + hw_atl2_shared_buffer_write(self, link_control, link_control); + + return hw_atl2_shared_buffer_finish_ack(self); +} + +static int aq_a2_fw_set_power(struct aq_hw_s *self, unsigned int power_state, + const u8 *mac) +{ + u32 wol = self->aq_nic_cfg->wol; + int err = 0; + + if (wol) + err = aq_a2_fw_set_wol_params(self, mac, wol); + + return err; +} + static int aq_a2_fw_set_eee_rate(struct aq_hw_s *self, u32 speed) { struct link_options_s link_options; @@ -605,6 +643,7 @@ const struct aq_fw_ops aq_a2_fw_ops = { .set_state = aq_a2_fw_set_state, .update_link_status = aq_a2_fw_update_link_status, .update_stats = aq_a2_fw_update_stats, + .set_power = aq_a2_fw_set_power, .get_mac_temp = aq_a2_fw_get_mac_temp, .get_phy_temp = aq_a2_fw_get_phy_temp, .set_eee_rate = aq_a2_fw_set_eee_rate, diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c index cfdb546a09e7..98a4d089270e 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.c +++ b/drivers/net/ethernet/atheros/atlx/atl1.c @@ -1861,14 +1861,21 @@ static u16 atl1_alloc_rx_buffers(struct atl1_adapter *adapter) break; } - buffer_info->alloced = 1; - buffer_info->skb = skb; - buffer_info->length = (u16) adapter->rx_buffer_len; page = virt_to_page(skb->data); offset = offset_in_page(skb->data); buffer_info->dma = dma_map_page(&pdev->dev, page, offset, adapter->rx_buffer_len, DMA_FROM_DEVICE); + if (dma_mapping_error(&pdev->dev, buffer_info->dma)) { + kfree_skb(skb); + adapter->soft_stats.rx_dropped++; + break; + } + + buffer_info->alloced = 1; + buffer_info->skb = skb; + buffer_info->length = (u16)adapter->rx_buffer_len; + rfd_desc->buffer_addr = cpu_to_le64(buffer_info->dma); rfd_desc->buf_len = cpu_to_le16(adapter->rx_buffer_len); rfd_desc->coalese = 0; @@ -2183,8 +2190,8 @@ static int atl1_tx_csum(struct atl1_adapter *adapter, struct sk_buff *skb, return 0; } -static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb, - struct tx_packet_desc *ptpd) +static bool atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb, + struct tx_packet_desc *ptpd) { struct atl1_tpd_ring *tpd_ring = &adapter->tpd_ring; struct atl1_buffer *buffer_info; @@ -2194,6 +2201,7 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb, unsigned int nr_frags; unsigned int f; int retval; + u16 first_mapped; u16 next_to_use; u16 data_len; u8 hdr_len; @@ -2201,6 +2209,7 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb, buf_len -= skb->data_len; nr_frags = skb_shinfo(skb)->nr_frags; next_to_use = atomic_read(&tpd_ring->next_to_use); + first_mapped = next_to_use; buffer_info = &tpd_ring->buffer_info[next_to_use]; BUG_ON(buffer_info->skb); /* put skb in last TPD */ @@ -2216,6 +2225,8 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb, buffer_info->dma = dma_map_page(&adapter->pdev->dev, page, offset, hdr_len, DMA_TO_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, buffer_info->dma)) + goto dma_err; if (++next_to_use == tpd_ring->count) next_to_use = 0; @@ -2242,6 +2253,9 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb, page, offset, buffer_info->length, DMA_TO_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, + buffer_info->dma)) + goto dma_err; if (++next_to_use == tpd_ring->count) next_to_use = 0; } @@ -2254,6 +2268,8 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb, buffer_info->dma = dma_map_page(&adapter->pdev->dev, page, offset, buf_len, DMA_TO_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, buffer_info->dma)) + goto dma_err; if (++next_to_use == tpd_ring->count) next_to_use = 0; } @@ -2277,6 +2293,9 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb, buffer_info->dma = skb_frag_dma_map(&adapter->pdev->dev, frag, i * ATL1_MAX_TX_BUF_LEN, buffer_info->length, DMA_TO_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, + buffer_info->dma)) + goto dma_err; if (++next_to_use == tpd_ring->count) next_to_use = 0; @@ -2285,6 +2304,22 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb, /* last tpd's buffer-info */ buffer_info->skb = skb; + + return true; + + dma_err: + while (first_mapped != next_to_use) { + buffer_info = &tpd_ring->buffer_info[first_mapped]; + dma_unmap_page(&adapter->pdev->dev, + buffer_info->dma, + buffer_info->length, + DMA_TO_DEVICE); + buffer_info->dma = 0; + + if (++first_mapped == tpd_ring->count) + first_mapped = 0; + } + return false; } static void atl1_tx_queue(struct atl1_adapter *adapter, u16 count, @@ -2355,10 +2390,8 @@ static netdev_tx_t atl1_xmit_frame(struct sk_buff *skb, len = skb_headlen(skb); - if (unlikely(skb->len <= 0)) { - dev_kfree_skb_any(skb); - return NETDEV_TX_OK; - } + if (unlikely(skb->len <= 0)) + goto drop_packet; nr_frags = skb_shinfo(skb)->nr_frags; for (f = 0; f < nr_frags; f++) { @@ -2371,10 +2404,9 @@ static netdev_tx_t atl1_xmit_frame(struct sk_buff *skb, if (mss) { if (skb->protocol == htons(ETH_P_IP)) { proto_hdr_len = skb_tcp_all_headers(skb); - if (unlikely(proto_hdr_len > len)) { - dev_kfree_skb_any(skb); - return NETDEV_TX_OK; - } + if (unlikely(proto_hdr_len > len)) + goto drop_packet; + /* need additional TPD ? */ if (proto_hdr_len != len) count += (len - proto_hdr_len + @@ -2406,23 +2438,26 @@ static netdev_tx_t atl1_xmit_frame(struct sk_buff *skb, } tso = atl1_tso(adapter, skb, ptpd); - if (tso < 0) { - dev_kfree_skb_any(skb); - return NETDEV_TX_OK; - } + if (tso < 0) + goto drop_packet; if (!tso) { ret_val = atl1_tx_csum(adapter, skb, ptpd); - if (ret_val < 0) { - dev_kfree_skb_any(skb); - return NETDEV_TX_OK; - } + if (ret_val < 0) + goto drop_packet; } - atl1_tx_map(adapter, skb, ptpd); + if (!atl1_tx_map(adapter, skb, ptpd)) + goto drop_packet; + atl1_tx_queue(adapter, count, ptpd); atl1_update_mailbox(adapter); return NETDEV_TX_OK; + +drop_packet: + adapter->soft_stats.tx_errors++; + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; } static int atl1_rings_clean(struct napi_struct *napi, int budget) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index f391e63aa79d..f621a5bab1ea 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -3810,12 +3810,14 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, int numa_node) { + const unsigned int agg_size_fac = PAGE_SIZE / BNXT_RX_PAGE_SIZE; + const unsigned int rx_size_fac = PAGE_SIZE / SZ_4K; struct page_pool_params pp = { 0 }; struct page_pool *pool; - pp.pool_size = bp->rx_agg_ring_size; + pp.pool_size = bp->rx_agg_ring_size / agg_size_fac; if (BNXT_RX_PAGE_MODE(bp)) - pp.pool_size += bp->rx_ring_size; + pp.pool_size += bp->rx_ring_size / rx_size_fac; pp.nid = numa_node; pp.napi = &rxr->bnapi->napi; pp.netdev = bp->dev; @@ -3833,7 +3835,7 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp, rxr->need_head_pool = page_pool_is_unreadable(pool); if (bnxt_separate_head_pool(rxr)) { - pp.pool_size = max(bp->rx_ring_size, 1024); + pp.pool_size = min(bp->rx_ring_size / rx_size_fac, 1024); pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV; pool = page_pool_create(&pp); if (IS_ERR(pool)) diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 91104cc2c238..c00b05b2e945 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6686,7 +6686,7 @@ static void tg3_rx_data_free(struct tg3 *tp, struct ring_info *ri, u32 map_sz) * We only need to fill in the address because the other members * of the RX descriptor are invariant, see tg3_init_rings. * - * Note the purposeful assymetry of cpu vs. chip accesses. For + * Note the purposeful asymmetry of cpu vs. chip accesses. For * posting buffers we only dirty the first cache line of the RX * descriptor (containing the address). Whereas for the RX status * buffers the cpu only reads the last cacheline of the RX descriptor @@ -10145,7 +10145,7 @@ static int tg3_reset_hw(struct tg3 *tp, bool reset_phy) tp->grc_mode |= GRC_MODE_HOST_SENDBDS; /* Pseudo-header checksum is done by hardware logic and not - * the offload processers, so make the chip do the pseudo- + * the offload processors, so make the chip do the pseudo- * header checksums on receive. For transmit it is more * convenient to do the pseudo-header checksum in software * as Linux does that on transmit for us in all cases. diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h index b473f8014d9c..a9e7f88fa26d 100644 --- a/drivers/net/ethernet/broadcom/tg3.h +++ b/drivers/net/ethernet/broadcom/tg3.h @@ -2390,7 +2390,7 @@ #define TG3_CL45_D7_EEERES_STAT_LP_1000T 0x0004 -/* Fast Ethernet Tranceiver definitions */ +/* Fast Ethernet Transceiver definitions */ #define MII_TG3_FET_PTEST 0x17 #define MII_TG3_FET_PTEST_TRIM_SEL 0x0010 #define MII_TG3_FET_PTEST_TRIM_2 0x0002 diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 773f5ad972a2..6bc8dfdb3d4b 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -1864,10 +1864,10 @@ static int enic_change_mtu(struct net_device *netdev, int new_mtu) if (enic_is_dynamic(enic) || enic_is_sriov_vf(enic)) return -EOPNOTSUPP; - if (netdev->mtu > enic->port_mtu) + if (new_mtu > enic->port_mtu) netdev_warn(netdev, "interface MTU (%d) set higher than port MTU (%d)\n", - netdev->mtu, enic->port_mtu); + new_mtu, enic->port_mtu); return _enic_change_mtu(netdev, new_mtu); } diff --git a/drivers/net/ethernet/dec/tulip/xircom_cb.c b/drivers/net/ethernet/dec/tulip/xircom_cb.c index 8759f9f76b62..e5d2ede13845 100644 --- a/drivers/net/ethernet/dec/tulip/xircom_cb.c +++ b/drivers/net/ethernet/dec/tulip/xircom_cb.c @@ -143,7 +143,7 @@ static const struct pci_device_id xircom_pci_table[] = { }; MODULE_DEVICE_TABLE(pci, xircom_pci_table); -static struct pci_driver xircom_ops = { +static struct pci_driver xircom_driver = { .name = "xircom_cb", .id_table = xircom_pci_table, .probe = xircom_probe, @@ -1169,4 +1169,4 @@ investigate_write_descriptor(struct net_device *dev, } } -module_pci_driver(xircom_ops); +module_pci_driver(xircom_driver); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 2ec2c3dab250..b82f121cadad 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -3939,6 +3939,7 @@ static int dpaa2_eth_setup_rx_flow(struct dpaa2_eth_priv *priv, MEM_TYPE_PAGE_ORDER0, NULL); if (err) { dev_err(dev, "xdp_rxq_info_reg_mem_model failed\n"); + xdp_rxq_info_unreg(&fq->channel->xdp_rxq); return err; } @@ -4432,17 +4433,25 @@ static int dpaa2_eth_bind_dpni(struct dpaa2_eth_priv *priv) return -EINVAL; } if (err) - return err; + goto out; } err = dpni_get_qdid(priv->mc_io, 0, priv->mc_token, DPNI_QUEUE_TX, &priv->tx_qdid); if (err) { dev_err(dev, "dpni_get_qdid() failed\n"); - return err; + goto out; } return 0; + +out: + while (i--) { + if (priv->fq[i].type == DPAA2_RX_FQ && + xdp_rxq_info_is_reg(&priv->fq[i].channel->xdp_rxq)) + xdp_rxq_info_unreg(&priv->fq[i].channel->xdp_rxq); + } + return err; } /* Allocate rings for storing incoming frame descriptors */ @@ -4825,6 +4834,17 @@ static void dpaa2_eth_del_ch_napi(struct dpaa2_eth_priv *priv) } } +static void dpaa2_eth_free_rx_xdp_rxq(struct dpaa2_eth_priv *priv) +{ + int i; + + for (i = 0; i < priv->num_fqs; i++) { + if (priv->fq[i].type == DPAA2_RX_FQ && + xdp_rxq_info_is_reg(&priv->fq[i].channel->xdp_rxq)) + xdp_rxq_info_unreg(&priv->fq[i].channel->xdp_rxq); + } +} + static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev) { struct device *dev; @@ -5028,6 +5048,7 @@ err_alloc_percpu_extras: free_percpu(priv->percpu_stats); err_alloc_percpu_stats: dpaa2_eth_del_ch_napi(priv); + dpaa2_eth_free_rx_xdp_rxq(priv); err_bind: dpaa2_eth_free_dpbps(priv); err_dpbp_setup: @@ -5080,6 +5101,7 @@ static void dpaa2_eth_remove(struct fsl_mc_device *ls_dev) free_percpu(priv->percpu_extras); dpaa2_eth_del_ch_napi(priv); + dpaa2_eth_free_rx_xdp_rxq(priv); dpaa2_eth_free_dpbps(priv); dpaa2_eth_free_dpio(priv); dpaa2_eth_free_dpni(priv); diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index 872d2cbd088b..62e8ee4d2f04 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -96,17 +96,17 @@ struct enetc_rx_swbd { #define ENETC_TXBDS_MAX_NEEDED(x) ENETC_TXBDS_NEEDED((x) + 1) struct enetc_ring_stats { - unsigned int packets; - unsigned int bytes; - unsigned int rx_alloc_errs; - unsigned int xdp_drops; - unsigned int xdp_tx; - unsigned int xdp_tx_drops; - unsigned int xdp_redirect; - unsigned int xdp_redirect_failures; - unsigned int recycles; - unsigned int recycle_failures; - unsigned int win_drop; + unsigned long packets; + unsigned long bytes; + unsigned long rx_alloc_errs; + unsigned long xdp_drops; + unsigned long xdp_tx; + unsigned long xdp_tx_drops; + unsigned long xdp_redirect; + unsigned long xdp_redirect_failures; + unsigned long recycles; + unsigned long recycle_failures; + unsigned long win_drop; }; struct enetc_xdp_data { diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c index 2e5cef646741..961e76cd8489 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c @@ -142,7 +142,7 @@ static const struct { static const struct { int reg; char name[ETH_GSTRING_LEN] __nonstring; -} enetc_port_counters[] = { +} enetc_pm_counters[] = { { ENETC_PM_REOCT(0), "MAC rx ethernet octets" }, { ENETC_PM_RALN(0), "MAC rx alignment errors" }, { ENETC_PM_RXPF(0), "MAC rx valid pause frames" }, @@ -194,6 +194,12 @@ static const struct { { ENETC_PM_TSCOL(0), "MAC tx single collisions" }, { ENETC_PM_TLCOL(0), "MAC tx late collisions" }, { ENETC_PM_TECOL(0), "MAC tx excessive collisions" }, +}; + +static const struct { + int reg; + char name[ETH_GSTRING_LEN] __nonstring; +} enetc_port_counters[] = { { ENETC_UFDMF, "SI MAC nomatch u-cast discards" }, { ENETC_MFDMF, "SI MAC nomatch m-cast discards" }, { ENETC_PBFDSIR, "SI MAC nomatch b-cast discards" }, @@ -240,6 +246,7 @@ static int enetc_get_sset_count(struct net_device *ndev, int sset) return len; len += ARRAY_SIZE(enetc_port_counters); + len += ARRAY_SIZE(enetc_pm_counters); return len; } @@ -266,6 +273,9 @@ static void enetc_get_strings(struct net_device *ndev, u32 stringset, u8 *data) for (i = 0; i < ARRAY_SIZE(enetc_port_counters); i++) ethtool_cpy(&data, enetc_port_counters[i].name); + for (i = 0; i < ARRAY_SIZE(enetc_pm_counters); i++) + ethtool_cpy(&data, enetc_pm_counters[i].name); + break; } } @@ -302,13 +312,16 @@ static void enetc_get_ethtool_stats(struct net_device *ndev, for (i = 0; i < ARRAY_SIZE(enetc_port_counters); i++) data[o++] = enetc_port_rd(hw, enetc_port_counters[i].reg); + + for (i = 0; i < ARRAY_SIZE(enetc_pm_counters); i++) + data[o++] = enetc_port_rd64(hw, enetc_pm_counters[i].reg); } static void enetc_pause_stats(struct enetc_hw *hw, int mac, struct ethtool_pause_stats *pause_stats) { - pause_stats->tx_pause_frames = enetc_port_rd(hw, ENETC_PM_TXPF(mac)); - pause_stats->rx_pause_frames = enetc_port_rd(hw, ENETC_PM_RXPF(mac)); + pause_stats->tx_pause_frames = enetc_port_rd64(hw, ENETC_PM_TXPF(mac)); + pause_stats->rx_pause_frames = enetc_port_rd64(hw, ENETC_PM_RXPF(mac)); } static void enetc_get_pause_stats(struct net_device *ndev, @@ -335,31 +348,31 @@ static void enetc_get_pause_stats(struct net_device *ndev, static void enetc_mac_stats(struct enetc_hw *hw, int mac, struct ethtool_eth_mac_stats *s) { - s->FramesTransmittedOK = enetc_port_rd(hw, ENETC_PM_TFRM(mac)); - s->SingleCollisionFrames = enetc_port_rd(hw, ENETC_PM_TSCOL(mac)); - s->MultipleCollisionFrames = enetc_port_rd(hw, ENETC_PM_TMCOL(mac)); - s->FramesReceivedOK = enetc_port_rd(hw, ENETC_PM_RFRM(mac)); - s->FrameCheckSequenceErrors = enetc_port_rd(hw, ENETC_PM_RFCS(mac)); - s->AlignmentErrors = enetc_port_rd(hw, ENETC_PM_RALN(mac)); - s->OctetsTransmittedOK = enetc_port_rd(hw, ENETC_PM_TEOCT(mac)); - s->FramesWithDeferredXmissions = enetc_port_rd(hw, ENETC_PM_TDFR(mac)); - s->LateCollisions = enetc_port_rd(hw, ENETC_PM_TLCOL(mac)); - s->FramesAbortedDueToXSColls = enetc_port_rd(hw, ENETC_PM_TECOL(mac)); - s->FramesLostDueToIntMACXmitError = enetc_port_rd(hw, ENETC_PM_TERR(mac)); - s->CarrierSenseErrors = enetc_port_rd(hw, ENETC_PM_TCRSE(mac)); - s->OctetsReceivedOK = enetc_port_rd(hw, ENETC_PM_REOCT(mac)); - s->FramesLostDueToIntMACRcvError = enetc_port_rd(hw, ENETC_PM_RDRNTP(mac)); - s->MulticastFramesXmittedOK = enetc_port_rd(hw, ENETC_PM_TMCA(mac)); - s->BroadcastFramesXmittedOK = enetc_port_rd(hw, ENETC_PM_TBCA(mac)); - s->MulticastFramesReceivedOK = enetc_port_rd(hw, ENETC_PM_RMCA(mac)); - s->BroadcastFramesReceivedOK = enetc_port_rd(hw, ENETC_PM_RBCA(mac)); + s->FramesTransmittedOK = enetc_port_rd64(hw, ENETC_PM_TFRM(mac)); + s->SingleCollisionFrames = enetc_port_rd64(hw, ENETC_PM_TSCOL(mac)); + s->MultipleCollisionFrames = enetc_port_rd64(hw, ENETC_PM_TMCOL(mac)); + s->FramesReceivedOK = enetc_port_rd64(hw, ENETC_PM_RFRM(mac)); + s->FrameCheckSequenceErrors = enetc_port_rd64(hw, ENETC_PM_RFCS(mac)); + s->AlignmentErrors = enetc_port_rd64(hw, ENETC_PM_RALN(mac)); + s->OctetsTransmittedOK = enetc_port_rd64(hw, ENETC_PM_TEOCT(mac)); + s->FramesWithDeferredXmissions = enetc_port_rd64(hw, ENETC_PM_TDFR(mac)); + s->LateCollisions = enetc_port_rd64(hw, ENETC_PM_TLCOL(mac)); + s->FramesAbortedDueToXSColls = enetc_port_rd64(hw, ENETC_PM_TECOL(mac)); + s->FramesLostDueToIntMACXmitError = enetc_port_rd64(hw, ENETC_PM_TERR(mac)); + s->CarrierSenseErrors = enetc_port_rd64(hw, ENETC_PM_TCRSE(mac)); + s->OctetsReceivedOK = enetc_port_rd64(hw, ENETC_PM_REOCT(mac)); + s->FramesLostDueToIntMACRcvError = enetc_port_rd64(hw, ENETC_PM_RDRNTP(mac)); + s->MulticastFramesXmittedOK = enetc_port_rd64(hw, ENETC_PM_TMCA(mac)); + s->BroadcastFramesXmittedOK = enetc_port_rd64(hw, ENETC_PM_TBCA(mac)); + s->MulticastFramesReceivedOK = enetc_port_rd64(hw, ENETC_PM_RMCA(mac)); + s->BroadcastFramesReceivedOK = enetc_port_rd64(hw, ENETC_PM_RBCA(mac)); } static void enetc_ctrl_stats(struct enetc_hw *hw, int mac, struct ethtool_eth_ctrl_stats *s) { - s->MACControlFramesTransmitted = enetc_port_rd(hw, ENETC_PM_TCNP(mac)); - s->MACControlFramesReceived = enetc_port_rd(hw, ENETC_PM_RCNP(mac)); + s->MACControlFramesTransmitted = enetc_port_rd64(hw, ENETC_PM_TCNP(mac)); + s->MACControlFramesReceived = enetc_port_rd64(hw, ENETC_PM_RCNP(mac)); } static const struct ethtool_rmon_hist_range enetc_rmon_ranges[] = { @@ -376,26 +389,26 @@ static const struct ethtool_rmon_hist_range enetc_rmon_ranges[] = { static void enetc_rmon_stats(struct enetc_hw *hw, int mac, struct ethtool_rmon_stats *s) { - s->undersize_pkts = enetc_port_rd(hw, ENETC_PM_RUND(mac)); - s->oversize_pkts = enetc_port_rd(hw, ENETC_PM_ROVR(mac)); - s->fragments = enetc_port_rd(hw, ENETC_PM_RFRG(mac)); - s->jabbers = enetc_port_rd(hw, ENETC_PM_RJBR(mac)); - - s->hist[0] = enetc_port_rd(hw, ENETC_PM_R64(mac)); - s->hist[1] = enetc_port_rd(hw, ENETC_PM_R127(mac)); - s->hist[2] = enetc_port_rd(hw, ENETC_PM_R255(mac)); - s->hist[3] = enetc_port_rd(hw, ENETC_PM_R511(mac)); - s->hist[4] = enetc_port_rd(hw, ENETC_PM_R1023(mac)); - s->hist[5] = enetc_port_rd(hw, ENETC_PM_R1522(mac)); - s->hist[6] = enetc_port_rd(hw, ENETC_PM_R1523X(mac)); - - s->hist_tx[0] = enetc_port_rd(hw, ENETC_PM_T64(mac)); - s->hist_tx[1] = enetc_port_rd(hw, ENETC_PM_T127(mac)); - s->hist_tx[2] = enetc_port_rd(hw, ENETC_PM_T255(mac)); - s->hist_tx[3] = enetc_port_rd(hw, ENETC_PM_T511(mac)); - s->hist_tx[4] = enetc_port_rd(hw, ENETC_PM_T1023(mac)); - s->hist_tx[5] = enetc_port_rd(hw, ENETC_PM_T1522(mac)); - s->hist_tx[6] = enetc_port_rd(hw, ENETC_PM_T1523X(mac)); + s->undersize_pkts = enetc_port_rd64(hw, ENETC_PM_RUND(mac)); + s->oversize_pkts = enetc_port_rd64(hw, ENETC_PM_ROVR(mac)); + s->fragments = enetc_port_rd64(hw, ENETC_PM_RFRG(mac)); + s->jabbers = enetc_port_rd64(hw, ENETC_PM_RJBR(mac)); + + s->hist[0] = enetc_port_rd64(hw, ENETC_PM_R64(mac)); + s->hist[1] = enetc_port_rd64(hw, ENETC_PM_R127(mac)); + s->hist[2] = enetc_port_rd64(hw, ENETC_PM_R255(mac)); + s->hist[3] = enetc_port_rd64(hw, ENETC_PM_R511(mac)); + s->hist[4] = enetc_port_rd64(hw, ENETC_PM_R1023(mac)); + s->hist[5] = enetc_port_rd64(hw, ENETC_PM_R1522(mac)); + s->hist[6] = enetc_port_rd64(hw, ENETC_PM_R1523X(mac)); + + s->hist_tx[0] = enetc_port_rd64(hw, ENETC_PM_T64(mac)); + s->hist_tx[1] = enetc_port_rd64(hw, ENETC_PM_T127(mac)); + s->hist_tx[2] = enetc_port_rd64(hw, ENETC_PM_T255(mac)); + s->hist_tx[3] = enetc_port_rd64(hw, ENETC_PM_T511(mac)); + s->hist_tx[4] = enetc_port_rd64(hw, ENETC_PM_T1023(mac)); + s->hist_tx[5] = enetc_port_rd64(hw, ENETC_PM_T1522(mac)); + s->hist_tx[6] = enetc_port_rd64(hw, ENETC_PM_T1523X(mac)); } static void enetc_get_eth_mac_stats(struct net_device *ndev, diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 74082b98fdbb..73763e8f4879 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -536,6 +536,7 @@ static inline u64 _enetc_rd_reg64_wa(void __iomem *reg) /* port register accessors - PF only */ #define enetc_port_rd(hw, off) enetc_rd_reg((hw)->port + (off)) #define enetc_port_wr(hw, off, val) enetc_wr_reg((hw)->port + (off), val) +#define enetc_port_rd64(hw, off) _enetc_rd_reg64_wa((hw)->port + (off)) #define enetc_port_rd_mdio(hw, off) _enetc_rd_mdio_reg_wa((hw)->port + (off)) #define enetc_port_wr_mdio(hw, off, val) _enetc_wr_mdio_reg_wa(\ (hw)->port + (off), val) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 63dac4272045..d4eed252ad40 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3121,27 +3121,25 @@ static int fec_enet_us_to_itr_clock(struct net_device *ndev, int us) static void fec_enet_itr_coal_set(struct net_device *ndev) { struct fec_enet_private *fep = netdev_priv(ndev); - int rx_itr, tx_itr; + u32 rx_itr = 0, tx_itr = 0; + int rx_ictt, tx_ictt; - /* Must be greater than zero to avoid unpredictable behavior */ - if (!fep->rx_time_itr || !fep->rx_pkts_itr || - !fep->tx_time_itr || !fep->tx_pkts_itr) - return; - - /* Select enet system clock as Interrupt Coalescing - * timer Clock Source - */ - rx_itr = FEC_ITR_CLK_SEL; - tx_itr = FEC_ITR_CLK_SEL; + rx_ictt = fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr); + tx_ictt = fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr); - /* set ICFT and ICTT */ - rx_itr |= FEC_ITR_ICFT(fep->rx_pkts_itr); - rx_itr |= FEC_ITR_ICTT(fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr)); - tx_itr |= FEC_ITR_ICFT(fep->tx_pkts_itr); - tx_itr |= FEC_ITR_ICTT(fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr)); + if (rx_ictt > 0 && fep->rx_pkts_itr > 1) { + /* Enable with enet system clock as Interrupt Coalescing timer Clock Source */ + rx_itr = FEC_ITR_EN | FEC_ITR_CLK_SEL; + rx_itr |= FEC_ITR_ICFT(fep->rx_pkts_itr); + rx_itr |= FEC_ITR_ICTT(rx_ictt); + } - rx_itr |= FEC_ITR_EN; - tx_itr |= FEC_ITR_EN; + if (tx_ictt > 0 && fep->tx_pkts_itr > 1) { + /* Enable with enet system clock as Interrupt Coalescing timer Clock Source */ + tx_itr = FEC_ITR_EN | FEC_ITR_CLK_SEL; + tx_itr |= FEC_ITR_ICFT(fep->tx_pkts_itr); + tx_itr |= FEC_ITR_ICTT(tx_ictt); + } writel(tx_itr, fep->hwp + FEC_TXIC0); writel(rx_itr, fep->hwp + FEC_RXIC0); diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 0ae7387e0599..712f7ef2a00a 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -2304,6 +2304,8 @@ struct ice_aqc_get_cgu_abilities { u8 rsvd[3]; }; +#define ICE_AQC_CGU_IN_CFG_FLG2_REFSYNC_EN BIT(7) + /* Set CGU input config (direct 0x0C62) */ struct ice_aqc_set_cgu_input_config { u8 input_idx; diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index bc292d61892c..84cd8c6dcf39 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -2302,7 +2302,7 @@ ice_parse_1588_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p, info->clk_src = ((number & ICE_TS_CLK_SRC_M) != 0); } else { info->clk_freq = ICE_TSPLL_FREQ_156_250; - info->clk_src = ICE_CLK_SRC_TCXO; + info->clk_src = ICE_CLK_SRC_TIME_REF; } if (info->clk_freq < NUM_ICE_TSPLL_FREQ) { diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index ed375babcde3..e8979b80c2f0 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -39,194 +39,46 @@ #define FEC_RECEIVER_ID_PCS0 (0x33 << FEC_RECV_ID_SHIFT) #define FEC_RECEIVER_ID_PCS1 (0x34 << FEC_RECV_ID_SHIFT) -#define ICE_CGU_R9 0x24 -union ice_cgu_r9 { - struct { - u32 time_ref_freq_sel : 3; - u32 clk_eref1_en : 1; - u32 clk_eref0_en : 1; - u32 time_ref_en : 1; - u32 time_sync_en : 1; - u32 one_pps_out_en : 1; - u32 clk_ref_synce_en : 1; - u32 clk_synce1_en : 1; - u32 clk_synce0_en : 1; - u32 net_clk_ref1_en : 1; - u32 net_clk_ref0_en : 1; - u32 clk_synce1_amp : 2; - u32 misc6 : 1; - u32 clk_synce0_amp : 2; - u32 one_pps_out_amp : 2; - u32 misc24 : 12; - }; - u32 val; -}; +#define ICE_CGU_R9 0x24 +#define ICE_CGU_R9_TIME_REF_FREQ_SEL GENMASK(2, 0) +#define ICE_CGU_R9_CLK_EREF0_EN BIT(4) +#define ICE_CGU_R9_TIME_REF_EN BIT(5) +#define ICE_CGU_R9_TIME_SYNC_EN BIT(6) +#define ICE_CGU_R9_ONE_PPS_OUT_EN BIT(7) +#define ICE_CGU_R9_ONE_PPS_OUT_AMP GENMASK(19, 18) -#define ICE_CGU_R16 0x40 -union ice_cgu_r16 { - struct { - u32 synce_remndr : 6; - u32 synce_phlmt_en : 1; - u32 misc13 : 17; - u32 ck_refclkfreq : 8; - }; - u32 val; -}; +#define ICE_CGU_R16 0x40 +#define ICE_CGU_R16_TSPLL_CK_REFCLKFREQ GENMASK(31, 24) -#define ICE_CGU_R19 0x4c -union ice_cgu_r19_e82x { - struct { - u32 fbdiv_intgr : 8; - u32 fdpll_ulck_thr : 5; - u32 misc15 : 3; - u32 ndivratio : 4; - u32 tspll_iref_ndivratio : 3; - u32 misc19 : 1; - u32 japll_ndivratio : 4; - u32 japll_iref_ndivratio : 3; - u32 misc27 : 1; - }; - u32 val; -}; +#define ICE_CGU_R19 0x4C +#define ICE_CGU_R19_TSPLL_FBDIV_INTGR_E82X GENMASK(7, 0) +#define ICE_CGU_R19_TSPLL_FBDIV_INTGR_E825 GENMASK(9, 0) +#define ICE_CGU_R19_TSPLL_NDIVRATIO GENMASK(19, 16) -union ice_cgu_r19_e825 { - struct { - u32 tspll_fbdiv_intgr : 10; - u32 fdpll_ulck_thr : 5; - u32 misc15 : 1; - u32 tspll_ndivratio : 4; - u32 tspll_iref_ndivratio : 3; - u32 misc19 : 1; - u32 japll_ndivratio : 4; - u32 japll_postdiv_pdivratio : 3; - u32 misc27 : 1; - }; - u32 val; -}; +#define ICE_CGU_R22 0x58 +#define ICE_CGU_R22_TIME1588CLK_DIV GENMASK(23, 20) +#define ICE_CGU_R22_TIME1588CLK_DIV2 BIT(30) -#define ICE_CGU_R22 0x58 -union ice_cgu_r22 { - struct { - u32 fdpll_frac_div_out_nc : 2; - u32 fdpll_lock_int_for : 1; - u32 synce_hdov_int_for : 1; - u32 synce_lock_int_for : 1; - u32 fdpll_phlead_slip_nc : 1; - u32 fdpll_acc1_ovfl_nc : 1; - u32 fdpll_acc2_ovfl_nc : 1; - u32 synce_status_nc : 6; - u32 fdpll_acc1f_ovfl : 1; - u32 misc18 : 1; - u32 fdpllclk_div : 4; - u32 time1588clk_div : 4; - u32 synceclk_div : 4; - u32 synceclk_sel_div2 : 1; - u32 fdpllclk_sel_div2 : 1; - u32 time1588clk_sel_div2 : 1; - u32 misc3 : 1; - }; - u32 val; -}; +#define ICE_CGU_R23 0x5C +#define ICE_CGU_R24 0x60 +#define ICE_CGU_R24_FBDIV_FRAC GENMASK(21, 0) +#define ICE_CGU_R23_R24_TSPLL_ENABLE BIT(24) +#define ICE_CGU_R23_R24_REF1588_CK_DIV GENMASK(30, 27) +#define ICE_CGU_R23_R24_TIME_REF_SEL BIT(31) -#define ICE_CGU_R23 0x5C -union ice_cgu_r23 { - struct { - u32 cgupll_fbdiv_intgr : 10; - u32 ux56pll_fbdiv_intgr : 10; - u32 misc20 : 4; - u32 ts_pll_enable : 1; - u32 time_sync_tspll_align_sel : 1; - u32 ext_synce_sel : 1; - u32 ref1588_ck_div : 4; - u32 time_ref_sel : 1; +#define ICE_CGU_BW_TDC 0x31C +#define ICE_CGU_BW_TDC_PLLLOCK_SEL GENMASK(30, 29) - }; - u32 val; -}; +#define ICE_CGU_RO_LOCK 0x3F0 +#define ICE_CGU_RO_LOCK_TRUE_LOCK BIT(12) +#define ICE_CGU_RO_LOCK_UNLOCK BIT(13) -#define ICE_CGU_R24 0x60 -union ice_cgu_r24 { - struct { - u32 fbdiv_frac : 22; - u32 misc20 : 2; - u32 ts_pll_enable : 1; - u32 time_sync_tspll_align_sel : 1; - u32 ext_synce_sel : 1; - u32 ref1588_ck_div : 4; - u32 time_ref_sel : 1; - }; - u32 val; -}; +#define ICE_CGU_CNTR_BIST 0x344 +#define ICE_CGU_CNTR_BIST_PLLLOCK_SEL_0 BIT(15) +#define ICE_CGU_CNTR_BIST_PLLLOCK_SEL_1 BIT(16) -#define TSPLL_CNTR_BIST_SETTINGS 0x344 -union tspll_cntr_bist_settings { - struct { - u32 i_irefgen_settling_time_cntr_7_0 : 8; - u32 i_irefgen_settling_time_ro_standby_1_0 : 2; - u32 reserved195 : 5; - u32 i_plllock_sel_0 : 1; - u32 i_plllock_sel_1 : 1; - u32 i_plllock_cnt_6_0 : 7; - u32 i_plllock_cnt_10_7 : 4; - u32 reserved200 : 4; - }; - u32 val; -}; - -#define TSPLL_RO_BWM_LF 0x370 -union tspll_ro_bwm_lf { - struct { - u32 bw_freqov_high_cri_7_0 : 8; - u32 bw_freqov_high_cri_9_8 : 2; - u32 biascaldone_cri : 1; - u32 plllock_gain_tran_cri : 1; - u32 plllock_true_lock_cri : 1; - u32 pllunlock_flag_cri : 1; - u32 afcerr_cri : 1; - u32 afcdone_cri : 1; - u32 feedfwrdgain_cal_cri_7_0 : 8; - u32 m2fbdivmod_cri_7_0 : 8; - }; - u32 val; -}; - -#define TSPLL_RO_LOCK_E825C 0x3f0 -union tspll_ro_lock_e825c { - struct { - u32 bw_freqov_high_cri_7_0 : 8; - u32 bw_freqov_high_cri_9_8 : 2; - u32 reserved455 : 1; - u32 plllock_gain_tran_cri : 1; - u32 plllock_true_lock_cri : 1; - u32 pllunlock_flag_cri : 1; - u32 afcerr_cri : 1; - u32 afcdone_cri : 1; - u32 feedfwrdgain_cal_cri_7_0 : 8; - u32 reserved462 : 8; - }; - u32 val; -}; - -#define TSPLL_BW_TDC_E825C 0x31c -union tspll_bw_tdc_e825c { - struct { - u32 i_tdc_offset_lock_1_0 : 2; - u32 i_bbthresh1_2_0 : 3; - u32 i_bbthresh2_2_0 : 3; - u32 i_tdcsel_1_0 : 2; - u32 i_tdcovccorr_en_h : 1; - u32 i_divretimeren : 1; - u32 i_bw_ampmeas_window : 1; - u32 i_bw_lowerbound_2_0 : 3; - u32 i_bw_upperbound_2_0 : 3; - u32 i_bw_mode_1_0 : 2; - u32 i_ft_mode_sel_2_0 : 3; - u32 i_bwphase_4_0 : 5; - u32 i_plllock_sel_1_0 : 2; - u32 i_afc_divratio : 1; - }; - u32 val; -}; +#define ICE_CGU_RO_BWM_LF 0x370 +#define ICE_CGU_RO_BWM_LF_TRUE_LOCK BIT(12) int ice_init_hw(struct ice_hw *hw); void ice_deinit_hw(struct ice_hw *hw); diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index d6190d9e32ba..39743cdba986 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -36,6 +36,19 @@ #define ICE_DPLL_PIN_SW_2_OUTPUT_ABS_IDX \ (ICE_DPLL_PIN_SW_OUTPUT_ABS(ICE_DPLL_PIN_SW_2_IDX)) +#define ICE_SR_PFA_DPLL_DEFAULTS 0x152 +#define ICE_DPLL_PFA_REF_SYNC_TYPE 0x2420 +#define ICE_DPLL_PFA_REF_SYNC_TYPE2 0x2424 +#define ICE_DPLL_PFA_END 0xFFFF +#define ICE_DPLL_PFA_HEADER_LEN 4 +#define ICE_DPLL_PFA_ENTRY_LEN 3 +#define ICE_DPLL_PFA_MAILBOX_REF_SYNC_PIN_S 4 +#define ICE_DPLL_PFA_MASK_OFFSET 1 +#define ICE_DPLL_PFA_VALUE_OFFSET 2 + +#define ICE_DPLL_E810C_SFP_NC_PINS 2 +#define ICE_DPLL_E810C_SFP_NC_START 4 + /** * enum ice_dpll_pin_type - enumerate ice pin types: * @ICE_DPLL_PIN_INVALID: invalid pin type @@ -2107,6 +2120,149 @@ ice_dpll_sw_esync_get(const struct dpll_pin *pin, void *pin_priv, extack); } +/* + * ice_dpll_input_ref_sync_set - callback for setting reference sync feature + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @ref_pin: pin pointer for reference sync pair + * @ref_pin_priv: private data pointer of ref_pin + * @state: requested state for reference sync for pin pair + * @extack: error reporting + * + * Dpll subsystem callback. Handler for setting reference sync frequency + * feature for input pin. + * + * Context: Acquires and releases pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_input_ref_sync_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_pin *ref_pin, void *ref_pin_priv, + const enum dpll_pin_state state, + struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_pf *pf = p->pf; + u8 flags_en = 0; + int ret; + + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; + mutex_lock(&pf->dplls.lock); + + if (p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_INPUT_EN) + flags_en = ICE_AQC_SET_CGU_IN_CFG_FLG2_INPUT_EN; + if (state == DPLL_PIN_STATE_CONNECTED) + flags_en |= ICE_AQC_CGU_IN_CFG_FLG2_REFSYNC_EN; + ret = ice_aq_set_input_pin_cfg(&pf->hw, p->idx, 0, flags_en, 0, 0); + if (!ret) + ret = ice_dpll_pin_state_update(pf, p, ICE_DPLL_PIN_TYPE_INPUT, + extack); + mutex_unlock(&pf->dplls.lock); + + return ret; +} + +/** + * ice_dpll_input_ref_sync_get - callback for getting reference sync config + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @ref_pin: pin pointer for reference sync pair + * @ref_pin_priv: private data pointer of ref_pin + * @state: on success holds reference sync state for pin pair + * @extack: error reporting + * + * Dpll subsystem callback. Handler for setting reference sync frequency + * feature for input pin. + * + * Context: Acquires and releases pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_input_ref_sync_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_pin *ref_pin, void *ref_pin_priv, + enum dpll_pin_state *state, + struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_pf *pf = p->pf; + + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; + mutex_lock(&pf->dplls.lock); + if (p->flags[0] & ICE_AQC_CGU_IN_CFG_FLG2_REFSYNC_EN) + *state = DPLL_PIN_STATE_CONNECTED; + else + *state = DPLL_PIN_STATE_DISCONNECTED; + mutex_unlock(&pf->dplls.lock); + + return 0; +} + +/* + * ice_dpll_sw_input_ref_sync_set - callback for setting reference sync feature + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @ref_pin: pin pointer for reference sync pair + * @ref_pin_priv: private data pointer of ref_pin + * @state: requested state for reference sync for pin pair + * @extack: error reporting + * + * Dpll subsystem callback. Handler for setting reference sync + * feature for input pins. + * + * Context: Calls a function which acquires and releases pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_sw_input_ref_sync_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_pin *ref_pin, + void *ref_pin_priv, + const enum dpll_pin_state state, + struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + + return ice_dpll_input_ref_sync_set(pin, p->input, ref_pin, ref_pin_priv, + state, extack); +} + +/** + * ice_dpll_sw_input_ref_sync_get - callback for getting reference sync config + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @ref_pin: pin pointer for reference sync pair + * @ref_pin_priv: private data pointer of ref_pin + * @state: on success holds reference sync state for pin pair + * @extack: error reporting + * + * Dpll subsystem callback. Handler for setting reference sync feature for + * input pins. + * + * Context: Calls a function which acquires and releases pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_sw_input_ref_sync_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_pin *ref_pin, + void *ref_pin_priv, + enum dpll_pin_state *state, + struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + + return ice_dpll_input_ref_sync_get(pin, p->input, ref_pin, ref_pin_priv, + state, extack); +} + /** * ice_dpll_rclk_state_on_pin_set - set a state on rclk pin * @pin: pointer to a pin @@ -2234,6 +2390,8 @@ static const struct dpll_pin_ops ice_dpll_pin_sma_ops = { .phase_offset_get = ice_dpll_phase_offset_get, .esync_set = ice_dpll_sw_esync_set, .esync_get = ice_dpll_sw_esync_get, + .ref_sync_set = ice_dpll_sw_input_ref_sync_set, + .ref_sync_get = ice_dpll_sw_input_ref_sync_get, }; static const struct dpll_pin_ops ice_dpll_pin_ufl_ops = { @@ -2262,6 +2420,8 @@ static const struct dpll_pin_ops ice_dpll_input_ops = { .phase_offset_get = ice_dpll_phase_offset_get, .esync_set = ice_dpll_input_esync_set, .esync_get = ice_dpll_input_esync_get, + .ref_sync_set = ice_dpll_input_ref_sync_set, + .ref_sync_get = ice_dpll_input_ref_sync_get, }; static const struct dpll_pin_ops ice_dpll_output_ops = { @@ -2561,6 +2721,88 @@ resched: } /** + * ice_dpll_init_ref_sync_inputs - initialize reference sync pin pairs + * @pf: pf private structure + * + * Read DPLL TLV capabilities and initialize reference sync pin pairs in + * dpll subsystem. + * + * Return: + * * 0 - success or nothing to do (no ref-sync tlv are present) + * * negative - AQ failure + */ +static int ice_dpll_init_ref_sync_inputs(struct ice_pf *pf) +{ + struct ice_dpll_pin *inputs = pf->dplls.inputs; + struct ice_hw *hw = &pf->hw; + u16 addr, len, end, hdr; + int ret; + + ret = ice_get_pfa_module_tlv(hw, &hdr, &len, ICE_SR_PFA_DPLL_DEFAULTS); + if (ret) { + dev_err(ice_pf_to_dev(pf), + "Failed to read PFA dpll defaults TLV ret=%d\n", ret); + return ret; + } + end = hdr + len; + + for (addr = hdr + ICE_DPLL_PFA_HEADER_LEN; addr < end; + addr += ICE_DPLL_PFA_ENTRY_LEN) { + unsigned long bit, ul_mask, offset; + u16 pin, mask, buf; + bool valid = false; + + ret = ice_read_sr_word(hw, addr, &buf); + if (ret) + return ret; + + switch (buf) { + case ICE_DPLL_PFA_REF_SYNC_TYPE: + case ICE_DPLL_PFA_REF_SYNC_TYPE2: + { + u16 mask_addr = addr + ICE_DPLL_PFA_MASK_OFFSET; + u16 val_addr = addr + ICE_DPLL_PFA_VALUE_OFFSET; + + ret = ice_read_sr_word(hw, mask_addr, &mask); + if (ret) + return ret; + ret = ice_read_sr_word(hw, val_addr, &pin); + if (ret) + return ret; + if (buf == ICE_DPLL_PFA_REF_SYNC_TYPE) + pin >>= ICE_DPLL_PFA_MAILBOX_REF_SYNC_PIN_S; + valid = true; + break; + } + case ICE_DPLL_PFA_END: + addr = end; + break; + default: + continue; + } + if (!valid) + continue; + + ul_mask = mask; + offset = 0; + for_each_set_bit(bit, &ul_mask, BITS_PER_TYPE(u16)) { + int i, j; + + if (hw->device_id == ICE_DEV_ID_E810C_SFP && + pin > ICE_DPLL_E810C_SFP_NC_START) + offset = -ICE_DPLL_E810C_SFP_NC_PINS; + i = pin + offset; + j = bit + offset; + if (i < 0 || j < 0) + return -ERANGE; + inputs[i].ref_sync = j; + } + } + + return 0; +} + +/** * ice_dpll_release_pins - release pins resources from dpll subsystem * @pins: pointer to pins array * @count: number of pins @@ -2635,6 +2877,36 @@ ice_dpll_unregister_pins(struct dpll_device *dpll, struct ice_dpll_pin *pins, } /** + * ice_dpll_pin_ref_sync_register - register reference sync pins + * @pins: pointer to pins array + * @count: number of pins + * + * Register reference sync pins in dpll subsystem. + * + * Return: + * * 0 - success + * * negative - registration failure reason + */ +static int +ice_dpll_pin_ref_sync_register(struct ice_dpll_pin *pins, int count) +{ + int ret, i; + + for (i = 0; i < count; i++) { + if (!pins[i].hidden && pins[i].ref_sync) { + int j = pins[i].ref_sync; + + ret = dpll_pin_ref_sync_pair_add(pins[i].pin, + pins[j].pin); + if (ret) + return ret; + } + } + + return 0; +} + +/** * ice_dpll_register_pins - register pins with a dpll * @dpll: dpll pointer to register pins with * @pins: pointer to pins array @@ -2922,6 +3194,14 @@ static int ice_dpll_init_pins(struct ice_pf *pf, bool cgu) goto deinit_sma; count += ICE_DPLL_PIN_SW_NUM; } + ret = ice_dpll_pin_ref_sync_register(pf->dplls.inputs, + pf->dplls.num_inputs); + if (ret) + goto deinit_ufl; + ret = ice_dpll_pin_ref_sync_register(pf->dplls.sma, + ICE_DPLL_PIN_SW_NUM); + if (ret) + goto deinit_ufl; } else { count += pf->dplls.num_outputs + 2 * ICE_DPLL_PIN_SW_NUM; } @@ -3219,6 +3499,8 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf, pins[i].prop.freq_supported_num = freq_supp_num; pins[i].pf = pf; } + if (input) + ret = ice_dpll_init_ref_sync_inputs(pf); return ret; } @@ -3284,6 +3566,8 @@ static int ice_dpll_init_info_sw_pins(struct ice_pf *pf) pin->pf = pf; pin->prop.board_label = ice_dpll_sw_pin_sma[i]; pin->input = &d->inputs[pin_abs_idx]; + if (pin->input->ref_sync) + pin->ref_sync = pin->input->ref_sync - pin_abs_idx; pin->output = &d->outputs[ICE_DPLL_PIN_SW_OUTPUT_ABS(i)]; ice_dpll_phase_range_set(&pin->prop.phase_range, phase_adj_max); } diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.h b/drivers/net/ethernet/intel/ice/ice_dpll.h index a5a5b61c5115..c0da03384ce9 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.h +++ b/drivers/net/ethernet/intel/ice/ice_dpll.h @@ -32,6 +32,7 @@ enum ice_dpll_pin_sw { * @freq: current frequency of a pin * @phase_adjust: current phase adjust value * @phase_offset: monitored phase offset value + * @ref_sync: store id of reference sync pin */ struct ice_dpll_pin { struct dpll_pin *pin; @@ -49,6 +50,7 @@ struct ice_dpll_pin { enum dpll_pin_direction direction; s64 phase_offset; u8 status; + u8 ref_sync; bool active; bool hidden; }; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index b8cf8d64aaaa..e7005d757477 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -2892,6 +2892,10 @@ static int ice_ptp_rebuild_owner(struct ice_pf *pf) if (err) return err; + err = ice_tspll_init(hw); + if (err) + return err; + /* Acquire the global hardware lock */ if (!ice_ptp_lock(hw)) { err = -EBUSY; @@ -3059,6 +3063,13 @@ static int ice_ptp_init_owner(struct ice_pf *pf) return err; } + err = ice_tspll_init(hw); + if (err) { + dev_err(ice_pf_to_dev(pf), "Failed to initialize CGU, status %d\n", + err); + return err; + } + /* Acquire the global hardware lock */ if (!ice_ptp_lock(hw)) { err = -EBUSY; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 278231443546..e8e439fd64a4 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -2116,20 +2116,6 @@ int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port) } /** - * ice_ptp_init_phc_e825 - Perform E825 specific PHC initialization - * @hw: pointer to HW struct - * - * Perform E825-specific PTP hardware clock initialization steps. - * - * Return: 0 on success, negative error code otherwise. - */ -static int ice_ptp_init_phc_e825(struct ice_hw *hw) -{ - /* Initialize the Clock Generation Unit */ - return ice_tspll_init(hw); -} - -/** * ice_ptp_read_tx_hwtstamp_status_eth56g - Get TX timestamp status * @hw: pointer to the HW struct * @ts_status: the timestamp mask pointer @@ -2788,7 +2774,6 @@ static int ice_ptp_set_vernier_wl(struct ice_hw *hw) */ static int ice_ptp_init_phc_e82x(struct ice_hw *hw) { - int err; u32 val; /* Enable reading switch and PHY registers over the sideband queue */ @@ -2798,11 +2783,6 @@ static int ice_ptp_init_phc_e82x(struct ice_hw *hw) val |= (PF_SB_REM_DEV_CTL_SWITCH_READ | PF_SB_REM_DEV_CTL_PHY0); wr32(hw, PF_SB_REM_DEV_CTL, val); - /* Initialize the Clock Generation Unit */ - err = ice_tspll_init(hw); - if (err) - return err; - /* Set window length for all the ports */ return ice_ptp_set_vernier_wl(hw); } @@ -5584,7 +5564,7 @@ int ice_ptp_init_phc(struct ice_hw *hw) case ICE_MAC_GENERIC: return ice_ptp_init_phc_e82x(hw); case ICE_MAC_GENERIC_3K_E825: - return ice_ptp_init_phc_e825(hw); + return 0; default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/intel/ice/ice_tspll.c b/drivers/net/ethernet/intel/ice/ice_tspll.c index 08af4ced50eb..66320a4ab86f 100644 --- a/drivers/net/ethernet/intel/ice/ice_tspll.c +++ b/drivers/net/ethernet/intel/ice/ice_tspll.c @@ -72,6 +72,58 @@ static const char *ice_tspll_clk_freq_str(enum ice_tspll_freq clk_freq) } /** + * ice_tspll_default_freq - Return default frequency for a MAC type + * @mac_type: MAC type + * + * Return: default TSPLL frequency for a correct MAC type, -ERANGE otherwise. + */ +static enum ice_tspll_freq ice_tspll_default_freq(enum ice_mac_type mac_type) +{ + switch (mac_type) { + case ICE_MAC_GENERIC: + return ICE_TSPLL_FREQ_25_000; + case ICE_MAC_GENERIC_3K_E825: + return ICE_TSPLL_FREQ_156_250; + default: + return -ERANGE; + } +} + +/** + * ice_tspll_check_params - Check if TSPLL params are correct + * @hw: Pointer to the HW struct + * @clk_freq: Clock frequency to program + * @clk_src: Clock source to select (TIME_REF or TCXO) + * + * Return: true if TSPLL params are correct, false otherwise. + */ +static bool ice_tspll_check_params(struct ice_hw *hw, + enum ice_tspll_freq clk_freq, + enum ice_clk_src clk_src) +{ + if (clk_freq >= NUM_ICE_TSPLL_FREQ) { + dev_warn(ice_hw_to_dev(hw), "Invalid TSPLL frequency %u\n", + clk_freq); + return false; + } + + if (clk_src >= NUM_ICE_CLK_SRC) { + dev_warn(ice_hw_to_dev(hw), "Invalid clock source %u\n", + clk_src); + return false; + } + + if ((hw->mac_type == ICE_MAC_GENERIC_3K_E825 || + clk_src == ICE_CLK_SRC_TCXO) && + clk_freq != ice_tspll_default_freq(hw->mac_type)) { + dev_warn(ice_hw_to_dev(hw), "Unsupported frequency for this clock source\n"); + return false; + } + + return true; +} + +/** * ice_tspll_clk_src_str - Convert time_ref_src to string * @clk_src: Clock source * @@ -127,120 +179,121 @@ static void ice_tspll_log_cfg(struct ice_hw *hw, bool enable, u8 clk_src, static int ice_tspll_cfg_e82x(struct ice_hw *hw, enum ice_tspll_freq clk_freq, enum ice_clk_src clk_src) { - union tspll_ro_bwm_lf bwm_lf; - union ice_cgu_r19_e82x dw19; - union ice_cgu_r22 dw22; - union ice_cgu_r24 dw24; - union ice_cgu_r9 dw9; + u32 val, r9, r24; int err; - if (clk_freq >= NUM_ICE_TSPLL_FREQ) { - dev_warn(ice_hw_to_dev(hw), "Invalid TIME_REF frequency %u\n", - clk_freq); - return -EINVAL; - } - - if (clk_src >= NUM_ICE_CLK_SRC) { - dev_warn(ice_hw_to_dev(hw), "Invalid clock source %u\n", - clk_src); - return -EINVAL; - } - - if (clk_src == ICE_CLK_SRC_TCXO && clk_freq != ICE_TSPLL_FREQ_25_000) { - dev_warn(ice_hw_to_dev(hw), - "TCXO only supports 25 MHz frequency\n"); - return -EINVAL; - } - - err = ice_read_cgu_reg(hw, ICE_CGU_R9, &dw9.val); + err = ice_read_cgu_reg(hw, ICE_CGU_R9, &r9); if (err) return err; - err = ice_read_cgu_reg(hw, ICE_CGU_R24, &dw24.val); + err = ice_read_cgu_reg(hw, ICE_CGU_R24, &r24); if (err) return err; - err = ice_read_cgu_reg(hw, TSPLL_RO_BWM_LF, &bwm_lf.val); + err = ice_read_cgu_reg(hw, ICE_CGU_RO_BWM_LF, &val); if (err) return err; - ice_tspll_log_cfg(hw, dw24.ts_pll_enable, dw24.time_ref_sel, - dw9.time_ref_freq_sel, bwm_lf.plllock_true_lock_cri, + ice_tspll_log_cfg(hw, !!FIELD_GET(ICE_CGU_R23_R24_TSPLL_ENABLE, r24), + FIELD_GET(ICE_CGU_R23_R24_TIME_REF_SEL, r24), + FIELD_GET(ICE_CGU_R9_TIME_REF_FREQ_SEL, r9), + !!FIELD_GET(ICE_CGU_RO_BWM_LF_TRUE_LOCK, val), false); /* Disable the PLL before changing the clock source or frequency */ - if (dw24.ts_pll_enable) { - dw24.ts_pll_enable = 0; + if (FIELD_GET(ICE_CGU_R23_R24_TSPLL_ENABLE, r24)) { + r24 &= ~ICE_CGU_R23_R24_TSPLL_ENABLE; - err = ice_write_cgu_reg(hw, ICE_CGU_R24, dw24.val); + err = ice_write_cgu_reg(hw, ICE_CGU_R24, r24); if (err) return err; } /* Set the frequency */ - dw9.time_ref_freq_sel = clk_freq; - err = ice_write_cgu_reg(hw, ICE_CGU_R9, dw9.val); + r9 &= ~ICE_CGU_R9_TIME_REF_FREQ_SEL; + r9 |= FIELD_PREP(ICE_CGU_R9_TIME_REF_FREQ_SEL, clk_freq); + err = ice_write_cgu_reg(hw, ICE_CGU_R9, r9); if (err) return err; /* Configure the TSPLL feedback divisor */ - err = ice_read_cgu_reg(hw, ICE_CGU_R19, &dw19.val); + err = ice_read_cgu_reg(hw, ICE_CGU_R19, &val); if (err) return err; - dw19.fbdiv_intgr = e82x_tspll_params[clk_freq].feedback_div; - dw19.ndivratio = 1; + val &= ~(ICE_CGU_R19_TSPLL_FBDIV_INTGR_E82X | ICE_CGU_R19_TSPLL_NDIVRATIO); + val |= FIELD_PREP(ICE_CGU_R19_TSPLL_FBDIV_INTGR_E82X, + e82x_tspll_params[clk_freq].feedback_div); + val |= FIELD_PREP(ICE_CGU_R19_TSPLL_NDIVRATIO, 1); - err = ice_write_cgu_reg(hw, ICE_CGU_R19, dw19.val); + err = ice_write_cgu_reg(hw, ICE_CGU_R19, val); if (err) return err; /* Configure the TSPLL post divisor */ - err = ice_read_cgu_reg(hw, ICE_CGU_R22, &dw22.val); + err = ice_read_cgu_reg(hw, ICE_CGU_R22, &val); if (err) return err; - dw22.time1588clk_div = e82x_tspll_params[clk_freq].post_pll_div; - dw22.time1588clk_sel_div2 = 0; + val &= ~(ICE_CGU_R22_TIME1588CLK_DIV | + ICE_CGU_R22_TIME1588CLK_DIV2); + val |= FIELD_PREP(ICE_CGU_R22_TIME1588CLK_DIV, + e82x_tspll_params[clk_freq].post_pll_div); - err = ice_write_cgu_reg(hw, ICE_CGU_R22, dw22.val); + err = ice_write_cgu_reg(hw, ICE_CGU_R22, val); if (err) return err; /* Configure the TSPLL pre divisor and clock source */ - err = ice_read_cgu_reg(hw, ICE_CGU_R24, &dw24.val); + err = ice_read_cgu_reg(hw, ICE_CGU_R24, &r24); if (err) return err; - dw24.ref1588_ck_div = e82x_tspll_params[clk_freq].refclk_pre_div; - dw24.fbdiv_frac = e82x_tspll_params[clk_freq].frac_n_div; - dw24.time_ref_sel = clk_src; + r24 &= ~(ICE_CGU_R23_R24_REF1588_CK_DIV | ICE_CGU_R24_FBDIV_FRAC | + ICE_CGU_R23_R24_TIME_REF_SEL); + r24 |= FIELD_PREP(ICE_CGU_R23_R24_REF1588_CK_DIV, + e82x_tspll_params[clk_freq].refclk_pre_div); + r24 |= FIELD_PREP(ICE_CGU_R24_FBDIV_FRAC, + e82x_tspll_params[clk_freq].frac_n_div); + r24 |= FIELD_PREP(ICE_CGU_R23_R24_TIME_REF_SEL, clk_src); - err = ice_write_cgu_reg(hw, ICE_CGU_R24, dw24.val); + err = ice_write_cgu_reg(hw, ICE_CGU_R24, r24); if (err) return err; + /* Wait to ensure everything is stable */ + usleep_range(10, 20); + /* Finally, enable the PLL */ - dw24.ts_pll_enable = 1; + r24 |= ICE_CGU_R23_R24_TSPLL_ENABLE; - err = ice_write_cgu_reg(hw, ICE_CGU_R24, dw24.val); + err = ice_write_cgu_reg(hw, ICE_CGU_R24, r24); if (err) return err; - /* Wait to verify if the PLL locks */ - usleep_range(1000, 5000); + /* Wait at least 1 ms to verify if the PLL locks */ + usleep_range(USEC_PER_MSEC, 2 * USEC_PER_MSEC); - err = ice_read_cgu_reg(hw, TSPLL_RO_BWM_LF, &bwm_lf.val); + err = ice_read_cgu_reg(hw, ICE_CGU_RO_BWM_LF, &val); if (err) return err; - if (!bwm_lf.plllock_true_lock_cri) { - dev_warn(ice_hw_to_dev(hw), "TSPLL failed to lock\n"); + if (!(val & ICE_CGU_RO_BWM_LF_TRUE_LOCK)) { + dev_warn(ice_hw_to_dev(hw), "CGU PLL failed to lock\n"); return -EBUSY; } - ice_tspll_log_cfg(hw, dw24.ts_pll_enable, clk_src, clk_freq, true, - true); + err = ice_read_cgu_reg(hw, ICE_CGU_R9, &r9); + if (err) + return err; + err = ice_read_cgu_reg(hw, ICE_CGU_R24, &r24); + if (err) + return err; + + ice_tspll_log_cfg(hw, !!FIELD_GET(ICE_CGU_R23_R24_TSPLL_ENABLE, r24), + FIELD_GET(ICE_CGU_R23_R24_TIME_REF_SEL, r24), + FIELD_GET(ICE_CGU_R9_TIME_REF_FREQ_SEL, r9), + true, true); return 0; } @@ -256,18 +309,17 @@ static int ice_tspll_cfg_e82x(struct ice_hw *hw, enum ice_tspll_freq clk_freq, */ static int ice_tspll_dis_sticky_bits_e82x(struct ice_hw *hw) { - union tspll_cntr_bist_settings cntr_bist; + u32 val; int err; - err = ice_read_cgu_reg(hw, TSPLL_CNTR_BIST_SETTINGS, &cntr_bist.val); + err = ice_read_cgu_reg(hw, ICE_CGU_CNTR_BIST, &val); if (err) return err; - /* Disable sticky lock detection so lock err reported is accurate */ - cntr_bist.i_plllock_sel_0 = 0; - cntr_bist.i_plllock_sel_1 = 0; + val &= ~(ICE_CGU_CNTR_BIST_PLLLOCK_SEL_0 | + ICE_CGU_CNTR_BIST_PLLLOCK_SEL_1); - return ice_write_cgu_reg(hw, TSPLL_CNTR_BIST_SETTINGS, cntr_bist.val); + return ice_write_cgu_reg(hw, ICE_CGU_CNTR_BIST, val); } /** @@ -288,115 +340,106 @@ static int ice_tspll_dis_sticky_bits_e82x(struct ice_hw *hw) static int ice_tspll_cfg_e825c(struct ice_hw *hw, enum ice_tspll_freq clk_freq, enum ice_clk_src clk_src) { - union tspll_ro_lock_e825c ro_lock; - union ice_cgu_r19_e825 dw19; - union ice_cgu_r16 dw16; - union ice_cgu_r23 dw23; - union ice_cgu_r22 dw22; - union ice_cgu_r9 dw9; + u32 val, r9, r23; int err; - if (clk_freq >= NUM_ICE_TSPLL_FREQ) { - dev_warn(ice_hw_to_dev(hw), "Invalid TIME_REF frequency %u\n", - clk_freq); - return -EINVAL; - } - - if (clk_src >= NUM_ICE_CLK_SRC) { - dev_warn(ice_hw_to_dev(hw), "Invalid clock source %u\n", - clk_src); - return -EINVAL; - } - - if (clk_freq != ICE_TSPLL_FREQ_156_250) { - dev_warn(ice_hw_to_dev(hw), "Adapter only supports 156.25 MHz frequency\n"); - return -EINVAL; - } - - err = ice_read_cgu_reg(hw, ICE_CGU_R9, &dw9.val); - if (err) - return err; - - err = ice_read_cgu_reg(hw, ICE_CGU_R16, &dw16.val); + err = ice_read_cgu_reg(hw, ICE_CGU_R9, &r9); if (err) return err; - err = ice_read_cgu_reg(hw, ICE_CGU_R23, &dw23.val); + err = ice_read_cgu_reg(hw, ICE_CGU_R23, &r23); if (err) return err; - err = ice_read_cgu_reg(hw, TSPLL_RO_LOCK_E825C, &ro_lock.val); + err = ice_read_cgu_reg(hw, ICE_CGU_RO_LOCK, &val); if (err) return err; - ice_tspll_log_cfg(hw, dw23.ts_pll_enable, dw23.time_ref_sel, - dw9.time_ref_freq_sel, - ro_lock.plllock_true_lock_cri, false); + ice_tspll_log_cfg(hw, !!FIELD_GET(ICE_CGU_R23_R24_TSPLL_ENABLE, r23), + FIELD_GET(ICE_CGU_R23_R24_TIME_REF_SEL, r23), + FIELD_GET(ICE_CGU_R9_TIME_REF_FREQ_SEL, r9), + !!FIELD_GET(ICE_CGU_RO_LOCK_TRUE_LOCK, val), + false); /* Disable the PLL before changing the clock source or frequency */ - if (dw23.ts_pll_enable) { - dw23.ts_pll_enable = 0; + if (FIELD_GET(ICE_CGU_R23_R24_TSPLL_ENABLE, r23)) { + r23 &= ~ICE_CGU_R23_R24_TSPLL_ENABLE; - err = ice_write_cgu_reg(hw, ICE_CGU_R23, dw23.val); + err = ice_write_cgu_reg(hw, ICE_CGU_R23, r23); if (err) return err; } - /* Set the frequency */ - dw9.time_ref_freq_sel = clk_freq; - - /* Enable the correct receiver */ - if (clk_src == ICE_CLK_SRC_TCXO) { - dw9.time_ref_en = 0; - dw9.clk_eref0_en = 1; - } else { - dw9.time_ref_en = 1; - dw9.clk_eref0_en = 0; + if (FIELD_GET(ICE_CGU_R9_TIME_SYNC_EN, r9)) { + r9 &= ~ICE_CGU_R9_TIME_SYNC_EN; + + err = ice_write_cgu_reg(hw, ICE_CGU_R9, r9); + if (err) + return err; } - err = ice_write_cgu_reg(hw, ICE_CGU_R9, dw9.val); + + /* Set the frequency and enable the correct receiver */ + r9 &= ~(ICE_CGU_R9_TIME_REF_FREQ_SEL | ICE_CGU_R9_CLK_EREF0_EN | + ICE_CGU_R9_TIME_REF_EN); + r9 |= FIELD_PREP(ICE_CGU_R9_TIME_REF_FREQ_SEL, clk_freq); + if (clk_src == ICE_CLK_SRC_TCXO) + r9 |= ICE_CGU_R9_CLK_EREF0_EN; + else + r9 |= ICE_CGU_R9_TIME_REF_EN; + r9 |= ICE_CGU_R9_TIME_SYNC_EN; + err = ice_write_cgu_reg(hw, ICE_CGU_R9, r9); if (err) return err; /* Choose the referenced frequency */ - dw16.ck_refclkfreq = ICE_TSPLL_CK_REFCLKFREQ_E825; - err = ice_write_cgu_reg(hw, ICE_CGU_R16, dw16.val); + err = ice_read_cgu_reg(hw, ICE_CGU_R16, &val); + if (err) + return err; + val &= ~ICE_CGU_R16_TSPLL_CK_REFCLKFREQ; + val |= FIELD_PREP(ICE_CGU_R16_TSPLL_CK_REFCLKFREQ, + ICE_TSPLL_CK_REFCLKFREQ_E825); + err = ice_write_cgu_reg(hw, ICE_CGU_R16, val); if (err) return err; /* Configure the TSPLL feedback divisor */ - err = ice_read_cgu_reg(hw, ICE_CGU_R19, &dw19.val); + err = ice_read_cgu_reg(hw, ICE_CGU_R19, &val); if (err) return err; - dw19.tspll_fbdiv_intgr = ICE_TSPLL_FBDIV_INTGR_E825; - dw19.tspll_ndivratio = ICE_TSPLL_NDIVRATIO_E825; + val &= ~(ICE_CGU_R19_TSPLL_FBDIV_INTGR_E825 | + ICE_CGU_R19_TSPLL_NDIVRATIO); + val |= FIELD_PREP(ICE_CGU_R19_TSPLL_FBDIV_INTGR_E825, + ICE_TSPLL_FBDIV_INTGR_E825); + val |= FIELD_PREP(ICE_CGU_R19_TSPLL_NDIVRATIO, + ICE_TSPLL_NDIVRATIO_E825); - err = ice_write_cgu_reg(hw, ICE_CGU_R19, dw19.val); + err = ice_write_cgu_reg(hw, ICE_CGU_R19, val); if (err) return err; - /* Configure the TSPLL post divisor */ - err = ice_read_cgu_reg(hw, ICE_CGU_R22, &dw22.val); + /* Configure the TSPLL post divisor, these two are constant */ + err = ice_read_cgu_reg(hw, ICE_CGU_R22, &val); if (err) return err; - /* These two are constant for E825C */ - dw22.time1588clk_div = 5; - dw22.time1588clk_sel_div2 = 0; + val &= ~(ICE_CGU_R22_TIME1588CLK_DIV | + ICE_CGU_R22_TIME1588CLK_DIV2); + val |= FIELD_PREP(ICE_CGU_R22_TIME1588CLK_DIV, 5); - err = ice_write_cgu_reg(hw, ICE_CGU_R22, dw22.val); + err = ice_write_cgu_reg(hw, ICE_CGU_R22, val); if (err) return err; - /* Configure the TSPLL pre divisor and clock source */ - err = ice_read_cgu_reg(hw, ICE_CGU_R23, &dw23.val); + /* Configure the TSPLL pre divisor (constant) and clock source */ + err = ice_read_cgu_reg(hw, ICE_CGU_R23, &r23); if (err) return err; - dw23.ref1588_ck_div = 0; - dw23.time_ref_sel = clk_src; + r23 &= ~(ICE_CGU_R23_R24_REF1588_CK_DIV | ICE_CGU_R23_R24_TIME_REF_SEL); + r23 |= FIELD_PREP(ICE_CGU_R23_R24_TIME_REF_SEL, clk_src); - err = ice_write_cgu_reg(hw, ICE_CGU_R23, dw23.val); + err = ice_write_cgu_reg(hw, ICE_CGU_R23, r23); if (err) return err; @@ -405,27 +448,39 @@ static int ice_tspll_cfg_e825c(struct ice_hw *hw, enum ice_tspll_freq clk_freq, if (err) return err; + /* Wait to ensure everything is stable */ + usleep_range(10, 20); + /* Finally, enable the PLL */ - dw23.ts_pll_enable = 1; + r23 |= ICE_CGU_R23_R24_TSPLL_ENABLE; - err = ice_write_cgu_reg(hw, ICE_CGU_R23, dw23.val); + err = ice_write_cgu_reg(hw, ICE_CGU_R23, r23); if (err) return err; - /* Wait to verify if the PLL locks */ - usleep_range(1000, 5000); + /* Wait at least 1 ms to verify if the PLL locks */ + usleep_range(USEC_PER_MSEC, 2 * USEC_PER_MSEC); - err = ice_read_cgu_reg(hw, TSPLL_RO_LOCK_E825C, &ro_lock.val); + err = ice_read_cgu_reg(hw, ICE_CGU_RO_LOCK, &val); if (err) return err; - if (!ro_lock.plllock_true_lock_cri) { - dev_warn(ice_hw_to_dev(hw), "TSPLL failed to lock\n"); + if (!(val & ICE_CGU_RO_LOCK_TRUE_LOCK)) { + dev_warn(ice_hw_to_dev(hw), "CGU PLL failed to lock\n"); return -EBUSY; } - ice_tspll_log_cfg(hw, dw23.ts_pll_enable, clk_src, clk_freq, true, - true); + err = ice_read_cgu_reg(hw, ICE_CGU_R9, &r9); + if (err) + return err; + err = ice_read_cgu_reg(hw, ICE_CGU_R23, &r23); + if (err) + return err; + + ice_tspll_log_cfg(hw, !!FIELD_GET(ICE_CGU_R23_R24_TSPLL_ENABLE, r23), + FIELD_GET(ICE_CGU_R23_R24_TIME_REF_SEL, r23), + FIELD_GET(ICE_CGU_R9_TIME_REF_FREQ_SEL, r9), + true, true); return 0; } @@ -441,20 +496,18 @@ static int ice_tspll_cfg_e825c(struct ice_hw *hw, enum ice_tspll_freq clk_freq, */ static int ice_tspll_dis_sticky_bits_e825c(struct ice_hw *hw) { - union tspll_bw_tdc_e825c bw_tdc; + u32 val; int err; - err = ice_read_cgu_reg(hw, TSPLL_BW_TDC_E825C, &bw_tdc.val); + err = ice_read_cgu_reg(hw, ICE_CGU_BW_TDC, &val); if (err) return err; - bw_tdc.i_plllock_sel_1_0 = 0; + val &= ~ICE_CGU_BW_TDC_PLLLOCK_SEL; - return ice_write_cgu_reg(hw, TSPLL_BW_TDC_E825C, bw_tdc.val); + return ice_write_cgu_reg(hw, ICE_CGU_BW_TDC, val); } -#define ICE_ONE_PPS_OUT_AMP_MAX 3 - /** * ice_tspll_cfg_pps_out_e825c - Enable/disable 1PPS output and set amplitude * @hw: pointer to the HW struct @@ -464,16 +517,64 @@ static int ice_tspll_dis_sticky_bits_e825c(struct ice_hw *hw) */ int ice_tspll_cfg_pps_out_e825c(struct ice_hw *hw, bool enable) { - union ice_cgu_r9 r9; + u32 val; int err; - err = ice_read_cgu_reg(hw, ICE_CGU_R9, &r9.val); + err = ice_read_cgu_reg(hw, ICE_CGU_R9, &val); if (err) return err; - r9.one_pps_out_en = enable; - r9.one_pps_out_amp = enable * ICE_ONE_PPS_OUT_AMP_MAX; - return ice_write_cgu_reg(hw, ICE_CGU_R9, r9.val); + val &= ~(ICE_CGU_R9_ONE_PPS_OUT_EN | ICE_CGU_R9_ONE_PPS_OUT_AMP); + val |= FIELD_PREP(ICE_CGU_R9_ONE_PPS_OUT_EN, enable) | + ICE_CGU_R9_ONE_PPS_OUT_AMP; + + return ice_write_cgu_reg(hw, ICE_CGU_R9, val); +} + +/** + * ice_tspll_cfg - Configure the Clock Generation Unit TSPLL + * @hw: Pointer to the HW struct + * @clk_freq: Clock frequency to program + * @clk_src: Clock source to select (TIME_REF, or TCXO) + * + * Configure the Clock Generation Unit with the desired clock frequency and + * time reference, enabling the TSPLL which drives the PTP hardware clock. + * + * Return: 0 on success, -ERANGE on unsupported MAC type, other negative error + * codes when failed to configure CGU. + */ +static int ice_tspll_cfg(struct ice_hw *hw, enum ice_tspll_freq clk_freq, + enum ice_clk_src clk_src) +{ + switch (hw->mac_type) { + case ICE_MAC_GENERIC: + return ice_tspll_cfg_e82x(hw, clk_freq, clk_src); + case ICE_MAC_GENERIC_3K_E825: + return ice_tspll_cfg_e825c(hw, clk_freq, clk_src); + default: + return -ERANGE; + } +} + +/** + * ice_tspll_dis_sticky_bits - disable TSPLL sticky bits + * @hw: Pointer to the HW struct + * + * Configure the Clock Generation Unit TSPLL sticky bits so they don't latch on + * losing TSPLL lock, but always show current state. + * + * Return: 0 on success, -ERANGE on unsupported MAC type. + */ +static int ice_tspll_dis_sticky_bits(struct ice_hw *hw) +{ + switch (hw->mac_type) { + case ICE_MAC_GENERIC: + return ice_tspll_dis_sticky_bits_e82x(hw); + case ICE_MAC_GENERIC_3K_E825: + return ice_tspll_dis_sticky_bits_e825c(hw); + default: + return -ERANGE; + } } /** @@ -487,25 +588,39 @@ int ice_tspll_cfg_pps_out_e825c(struct ice_hw *hw, bool enable) int ice_tspll_init(struct ice_hw *hw) { struct ice_ts_func_info *ts_info = &hw->func_caps.ts_func_info; + enum ice_tspll_freq tspll_freq; + enum ice_clk_src clk_src; int err; - /* Disable sticky lock detection so lock err reported is accurate. */ - if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) - err = ice_tspll_dis_sticky_bits_e825c(hw); - else - err = ice_tspll_dis_sticky_bits_e82x(hw); + /* Only E822, E823 and E825 products support TSPLL */ + if (hw->mac_type != ICE_MAC_GENERIC && + hw->mac_type != ICE_MAC_GENERIC_3K_E825) + return 0; + + tspll_freq = (enum ice_tspll_freq)ts_info->time_ref; + clk_src = (enum ice_clk_src)ts_info->clk_src; + if (!ice_tspll_check_params(hw, tspll_freq, clk_src)) + return -EINVAL; + + /* Disable sticky lock detection so lock status reported is accurate */ + err = ice_tspll_dis_sticky_bits(hw); if (err) return err; /* Configure the TSPLL using the parameters from the function * capabilities. */ - if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) - err = ice_tspll_cfg_e825c(hw, ts_info->time_ref, - (enum ice_clk_src)ts_info->clk_src); - else - err = ice_tspll_cfg_e82x(hw, ts_info->time_ref, - (enum ice_clk_src)ts_info->clk_src); + err = ice_tspll_cfg(hw, tspll_freq, clk_src); + if (err) { + dev_warn(ice_hw_to_dev(hw), "Failed to lock TSPLL to predefined frequency. Retrying with fallback frequency.\n"); + + /* Try to lock to internal TCXO as a fallback. */ + tspll_freq = ice_tspll_default_freq(hw->mac_type); + clk_src = ICE_CLK_SRC_TCXO; + err = ice_tspll_cfg(hw, tspll_freq, clk_src); + if (err) + dev_warn(ice_hw_to_dev(hw), "Failed to lock TSPLL to fallback frequency.\n"); + } return err; } diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq.c b/drivers/net/ethernet/intel/idpf/idpf_controlq.c index b28991dd1870..48b8e184f3db 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_controlq.c +++ b/drivers/net/ethernet/intel/idpf/idpf_controlq.c @@ -96,7 +96,7 @@ static void idpf_ctlq_init_rxq_bufs(struct idpf_ctlq_info *cq) */ static void idpf_ctlq_shutdown(struct idpf_hw *hw, struct idpf_ctlq_info *cq) { - mutex_lock(&cq->cq_lock); + spin_lock(&cq->cq_lock); /* free ring buffers and the ring itself */ idpf_ctlq_dealloc_ring_res(hw, cq); @@ -104,8 +104,7 @@ static void idpf_ctlq_shutdown(struct idpf_hw *hw, struct idpf_ctlq_info *cq) /* Set ring_size to 0 to indicate uninitialized queue */ cq->ring_size = 0; - mutex_unlock(&cq->cq_lock); - mutex_destroy(&cq->cq_lock); + spin_unlock(&cq->cq_lock); } /** @@ -173,7 +172,7 @@ int idpf_ctlq_add(struct idpf_hw *hw, idpf_ctlq_init_regs(hw, cq, is_rxq); - mutex_init(&cq->cq_lock); + spin_lock_init(&cq->cq_lock); list_add(&cq->cq_list, &hw->cq_list_head); @@ -272,7 +271,7 @@ int idpf_ctlq_send(struct idpf_hw *hw, struct idpf_ctlq_info *cq, int err = 0; int i; - mutex_lock(&cq->cq_lock); + spin_lock(&cq->cq_lock); /* Ensure there are enough descriptors to send all messages */ num_desc_avail = IDPF_CTLQ_DESC_UNUSED(cq); @@ -332,7 +331,7 @@ int idpf_ctlq_send(struct idpf_hw *hw, struct idpf_ctlq_info *cq, wr32(hw, cq->reg.tail, cq->next_to_use); err_unlock: - mutex_unlock(&cq->cq_lock); + spin_unlock(&cq->cq_lock); return err; } @@ -364,7 +363,7 @@ int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count, if (*clean_count > cq->ring_size) return -EBADR; - mutex_lock(&cq->cq_lock); + spin_lock(&cq->cq_lock); ntc = cq->next_to_clean; @@ -397,7 +396,7 @@ int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count, cq->next_to_clean = ntc; - mutex_unlock(&cq->cq_lock); + spin_unlock(&cq->cq_lock); /* Return number of descriptors actually cleaned */ *clean_count = i; @@ -435,7 +434,7 @@ int idpf_ctlq_post_rx_buffs(struct idpf_hw *hw, struct idpf_ctlq_info *cq, if (*buff_count > 0) buffs_avail = true; - mutex_lock(&cq->cq_lock); + spin_lock(&cq->cq_lock); if (tbp >= cq->ring_size) tbp = 0; @@ -524,7 +523,7 @@ post_buffs_out: wr32(hw, cq->reg.tail, cq->next_to_post); } - mutex_unlock(&cq->cq_lock); + spin_unlock(&cq->cq_lock); /* return the number of buffers that were not posted */ *buff_count = *buff_count - i; @@ -552,7 +551,7 @@ int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg, u16 i; /* take the lock before we start messing with the ring */ - mutex_lock(&cq->cq_lock); + spin_lock(&cq->cq_lock); ntc = cq->next_to_clean; @@ -614,7 +613,7 @@ int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg, cq->next_to_clean = ntc; - mutex_unlock(&cq->cq_lock); + spin_unlock(&cq->cq_lock); *num_q_msg = i; if (*num_q_msg == 0) diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h index 9642494a67d8..3414c5f9a831 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h +++ b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h @@ -99,7 +99,7 @@ struct idpf_ctlq_info { enum idpf_ctlq_type cq_type; int q_id; - struct mutex cq_lock; /* control queue lock */ + spinlock_t cq_lock; /* control queue lock */ /* used for interrupt processing */ u16 next_to_use; u16 next_to_clean; diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c index 9bdb309b668e..eaf7a2606faa 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c +++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c @@ -47,7 +47,7 @@ static u32 idpf_get_rxfh_key_size(struct net_device *netdev) struct idpf_vport_user_config_data *user_config; if (!idpf_is_cap_ena_all(np->adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS)) - return -EOPNOTSUPP; + return 0; user_config = &np->adapter->vport_config[np->vport_idx]->user_config; @@ -66,7 +66,7 @@ static u32 idpf_get_rxfh_indir_size(struct net_device *netdev) struct idpf_vport_user_config_data *user_config; if (!idpf_is_cap_ena_all(np->adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS)) - return -EOPNOTSUPP; + return 0; user_config = &np->adapter->vport_config[np->vport_idx]->user_config; diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index 4eb20ec2accb..80382ff4a5fa 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -2314,8 +2314,12 @@ void *idpf_alloc_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem, u64 size) struct idpf_adapter *adapter = hw->back; size_t sz = ALIGN(size, 4096); - mem->va = dma_alloc_coherent(&adapter->pdev->dev, sz, - &mem->pa, GFP_KERNEL); + /* The control queue resources are freed under a spinlock, contiguous + * pages will avoid IOMMU remapping and the use vmap (and vunmap in + * dma_free_*() path. + */ + mem->va = dma_alloc_attrs(&adapter->pdev->dev, sz, &mem->pa, + GFP_KERNEL, DMA_ATTR_FORCE_CONTIGUOUS); mem->size = sz; return mem->va; @@ -2330,8 +2334,8 @@ void idpf_free_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem) { struct idpf_adapter *adapter = hw->back; - dma_free_coherent(&adapter->pdev->dev, mem->size, - mem->va, mem->pa); + dma_free_attrs(&adapter->pdev->dev, mem->size, + mem->va, mem->pa, DMA_ATTR_FORCE_CONTIGUOUS); mem->size = 0; mem->va = NULL; mem->pa = 0; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 2e12915b42a9..4f6632cb9497 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -7144,6 +7144,10 @@ static int igc_probe(struct pci_dev *pdev, adapter->port_num = hw->bus.func; adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE); + /* Disable ASPM L1.2 on I226 devices to avoid packet loss */ + if (igc_is_device_id_i226(hw)) + pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2); + err = pci_save_state(pdev); if (err) goto err_ioremap; @@ -7529,6 +7533,9 @@ static int __igc_resume(struct device *dev, bool rpm) pci_enable_wake(pdev, PCI_D3hot, 0); pci_enable_wake(pdev, PCI_D3cold, 0); + if (igc_is_device_id_i226(hw)) + pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2); + if (igc_init_interrupt_scheme(adapter, true)) { netdev_err(netdev, "Unable to allocate memory for queues\n"); return -ENOMEM; @@ -7654,6 +7661,9 @@ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev) pci_enable_wake(pdev, PCI_D3hot, 0); pci_enable_wake(pdev, PCI_D3cold, 0); + if (igc_is_device_id_i226(hw)) + pci_disable_link_state_locked(pdev, PCIE_LINK_STATE_L1_2); + /* In case of PCI error, adapter loses its HW address * so we should re-assign it here. */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index 971993586fb4..846ee2b9edf1 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -1182,17 +1182,25 @@ static int cgx_link_usertable_index_map(int speed) static void set_mod_args(struct cgx_set_link_mode_args *args, u32 speed, u8 duplex, u8 autoneg, u64 mode) { - /* Fill default values incase of user did not pass - * valid parameters + int mode_baseidx; + u8 cgx_mode; + + if (args->multimode) { + args->mode |= mode; + return; + } + + /* Derive mode_base_idx and mode fields based + * on cgx_mode value */ - if (args->duplex == DUPLEX_UNKNOWN) - args->duplex = duplex; - if (args->speed == SPEED_UNKNOWN) - args->speed = speed; - if (args->an == AUTONEG_UNKNOWN) - args->an = autoneg; + cgx_mode = find_first_bit((unsigned long *)&mode, + CGX_MODE_MAX); args->mode = mode; - args->ports = 0; + mode_baseidx = cgx_mode - 41; + if (mode_baseidx > 0) { + args->mode_baseidx = 1; + args->mode = BIT_ULL(mode_baseidx); + } } static void otx2_map_ethtool_link_modes(u64 bitmask, @@ -1200,16 +1208,16 @@ static void otx2_map_ethtool_link_modes(u64 bitmask, { switch (bitmask) { case ETHTOOL_LINK_MODE_10baseT_Half_BIT: - set_mod_args(args, 10, 1, 1, BIT_ULL(CGX_MODE_SGMII)); + set_mod_args(args, 10, 1, 1, BIT_ULL(CGX_MODE_SGMII_10M_BIT)); break; case ETHTOOL_LINK_MODE_10baseT_Full_BIT: - set_mod_args(args, 10, 0, 1, BIT_ULL(CGX_MODE_SGMII)); + set_mod_args(args, 10, 0, 1, BIT_ULL(CGX_MODE_SGMII_10M_BIT)); break; case ETHTOOL_LINK_MODE_100baseT_Half_BIT: - set_mod_args(args, 100, 1, 1, BIT_ULL(CGX_MODE_SGMII)); + set_mod_args(args, 100, 1, 1, BIT_ULL(CGX_MODE_SGMII_100M_BIT)); break; case ETHTOOL_LINK_MODE_100baseT_Full_BIT: - set_mod_args(args, 100, 0, 1, BIT_ULL(CGX_MODE_SGMII)); + set_mod_args(args, 100, 0, 1, BIT_ULL(CGX_MODE_SGMII_100M_BIT)); break; case ETHTOOL_LINK_MODE_1000baseT_Half_BIT: set_mod_args(args, 1000, 1, 1, BIT_ULL(CGX_MODE_SGMII)); @@ -1481,25 +1489,36 @@ int cgx_get_fwdata_base(u64 *base) } int cgx_set_link_mode(void *cgxd, struct cgx_set_link_mode_args args, + struct cgx_lmac_fwdata_s *linkmodes, int cgx_id, int lmac_id) { struct cgx *cgx = cgxd; u64 req = 0, resp; + u8 bit; if (!cgx) return -ENODEV; - if (args.mode) - otx2_map_ethtool_link_modes(args.mode, &args); - if (!args.speed && args.duplex && !args.an) - return -EINVAL; + for_each_set_bit(bit, args.advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS) + otx2_map_ethtool_link_modes(bit, &args); + + if (args.multimode) { + if (linkmodes->advertised_link_modes_own != CGX_CMD_OWN_NS) + return -EBUSY; + + linkmodes->advertised_link_modes = args.mode; + /* Update ownership */ + linkmodes->advertised_link_modes_own = CGX_CMD_OWN_FIRMWARE; + args.mode = GENMASK_ULL(41, 0); + } req = FIELD_SET(CMDREG_ID, CGX_CMD_MODE_CHANGE, req); req = FIELD_SET(CMDMODECHANGE_SPEED, cgx_link_usertable_index_map(args.speed), req); req = FIELD_SET(CMDMODECHANGE_DUPLEX, args.duplex, req); req = FIELD_SET(CMDMODECHANGE_AN, args.an, req); - req = FIELD_SET(CMDMODECHANGE_PORT, args.ports, req); + req = FIELD_SET(CMDMODECHANGE_MODE_BASEIDX, args.mode_baseidx, req); req = FIELD_SET(CMDMODECHANGE_FLAGS, args.mode, req); return cgx_fwi_cmd_generic(req, &resp, cgx, lmac_id); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h index 1cf12e5c7da8..950231e7ea71 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h @@ -171,6 +171,7 @@ int cgx_set_fec(u64 fec, int cgx_id, int lmac_id); int cgx_get_fec_stats(void *cgxd, int lmac_id, struct cgx_fec_stats_rsp *rsp); int cgx_get_phy_fec_stats(void *cgxd, int lmac_id); int cgx_set_link_mode(void *cgxd, struct cgx_set_link_mode_args args, + struct cgx_lmac_fwdata_s *linkmodes, int cgx_id, int lmac_id); u64 cgx_features_get(void *cgxd); struct mac_ops *get_mac_ops(void *cgxd); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h index d4a27c882a5b..39352d451cc3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h @@ -95,7 +95,31 @@ enum CGX_MODE_ { CGX_MODE_100G_C2M, CGX_MODE_100G_CR4, CGX_MODE_100G_KR4, - CGX_MODE_MAX /* = 29 */ + CGX_MODE_LAUI_2_C2C_BIT, + CGX_MODE_LAUI_2_C2M_BIT, + CGX_MODE_50GBASE_CR2_C_BIT, + CGX_MODE_50GBASE_KR2_C_BIT, /* = 30 */ + CGX_MODE_100GAUI_2_C2C_BIT, + CGX_MODE_100GAUI_2_C2M_BIT, + CGX_MODE_100GBASE_CR2_BIT, + CGX_MODE_100GBASE_KR2_BIT, + CGX_MODE_SFI_1G_BIT, + CGX_MODE_25GBASE_CR_C_BIT, + CGX_MODE_25GBASE_KR_C_BIT, + CGX_MODE_SGMII_10M_BIT, + CGX_MODE_SGMII_100M_BIT, /* = 39 */ + CGX_MODE_2500_BASEX_BIT = 42, /* Mode group 1 */ + CGX_MODE_5000_BASEX_BIT, + CGX_MODE_O_USGMII_BIT, + CGX_MODE_Q_USGMII_BIT, + CGX_MODE_2_5G_USXGMII_BIT, + CGX_MODE_5G_USXGMII_BIT, + CGX_MODE_10G_SXGMII_BIT, + CGX_MODE_10G_DXGMII_BIT, + CGX_MODE_10G_QXGMII_BIT, + CGX_MODE_TP_BIT, + CGX_MODE_FIBER_BIT, + CGX_MODE_MAX /* = 53 */ }; /* REQUEST ID types. Input to firmware */ enum cgx_cmd_id { @@ -258,7 +282,12 @@ struct cgx_lnk_sts { #define CMDMODECHANGE_SPEED GENMASK_ULL(11, 8) #define CMDMODECHANGE_DUPLEX GENMASK_ULL(12, 12) #define CMDMODECHANGE_AN GENMASK_ULL(13, 13) -#define CMDMODECHANGE_PORT GENMASK_ULL(21, 14) +/* this field categorize the mode ID(FLAGS) range to accommodate + * more modes. + * To specify mode ID range of 0 - 41, this field will be 0. + * To specify mode ID range of 42 - 83, this field will be 1. + */ +#define CMDMODECHANGE_MODE_BASEIDX GENMASK_ULL(21, 20) #define CMDMODECHANGE_FLAGS GENMASK_ULL(63, 22) /* LINK_BRING_UP command timeout */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index b3562d658d45..0bc0dc79868b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -10,6 +10,7 @@ #include <linux/etherdevice.h> #include <linux/sizes.h> +#include <linux/ethtool.h> #include "rvu_struct.h" #include "common.h" @@ -658,7 +659,8 @@ struct cgx_lmac_fwdata_s { u64 supported_link_modes; /* only applicable if AN is supported */ u64 advertised_fec; - u64 advertised_link_modes; + u64 advertised_link_modes_own:1; /* CGX_CMD_OWN */ + u64 advertised_link_modes:63; /* Only applicable if SFP/QSFP slot is present */ struct sfp_eeprom_s sfp_eeprom; struct phy_s phy; @@ -675,12 +677,13 @@ struct cgx_set_link_mode_args { u32 speed; u8 duplex; u8 an; - u8 ports; + u8 mode_baseidx; + u8 multimode; u64 mode; + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); }; struct cgx_set_link_mode_req { -#define AUTONEG_UNKNOWN 0xff struct mbox_msghdr hdr; struct cgx_set_link_mode_args args; }; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 7e538ee8a59f..c6bb3aaa8e0d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -2458,9 +2458,9 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw, void (mbox_handler)(struct work_struct *), void (mbox_up_handler)(struct work_struct *)) { - int err = -EINVAL, i, dir, dir_up; void __iomem **mbox_regions; struct ng_rvu *ng_rvu_mbox; + int err, i, dir, dir_up; void __iomem *reg_base; struct rvu_work *mwork; unsigned long *pf_bmap; @@ -2526,6 +2526,7 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw, goto free_regions; break; default: + err = -EINVAL; goto free_regions; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index b79db887ab9b..890a1a5df2de 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -1223,6 +1223,7 @@ int rvu_mbox_handler_cgx_set_link_mode(struct rvu *rvu, struct cgx_set_link_mode_rsp *rsp) { int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); + struct cgx_lmac_fwdata_s *linkmodes; u8 cgx_idx, lmac; void *cgxd; @@ -1231,7 +1232,13 @@ int rvu_mbox_handler_cgx_set_link_mode(struct rvu *rvu, rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_idx, &lmac); cgxd = rvu_cgx_pdata(cgx_idx, rvu); - rsp->status = cgx_set_link_mode(cgxd, req->args, cgx_idx, lmac); + if (rvu->hw->lmac_per_cgx == CGX_LMACS_USX) + linkmodes = &rvu->fwdata->cgx_fw_data_usx[cgx_idx][lmac]; + else + linkmodes = &rvu->fwdata->cgx_fw_data[cgx_idx][lmac]; + + rsp->status = cgx_set_link_mode(cgxd, req->args, linkmodes, + cgx_idx, lmac); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index 9b7f847b9c22..20de517dfb09 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -15,6 +15,7 @@ #include "otx2_common.h" #include "otx2_ptp.h" +#include <cgx_fw_if.h> #define DRV_NAME "rvu-nicpf" #define DRV_VF_NAME "rvu-nicvf" @@ -1126,17 +1127,9 @@ static void otx2_get_link_mode_info(u64 link_mode_bmap, *link_ksettings) { __ETHTOOL_DECLARE_LINK_MODE_MASK(otx2_link_modes) = { 0, }; - const int otx2_sgmii_features[6] = { - ETHTOOL_LINK_MODE_10baseT_Half_BIT, - ETHTOOL_LINK_MODE_10baseT_Full_BIT, - ETHTOOL_LINK_MODE_100baseT_Half_BIT, - ETHTOOL_LINK_MODE_100baseT_Full_BIT, - ETHTOOL_LINK_MODE_1000baseT_Half_BIT, - ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - }; /* CGX link modes to Ethtool link mode mapping */ - const int cgx_link_mode[27] = { - 0, /* SGMII Mode */ + const int cgx_link_mode[CGX_MODE_MAX] = { + 0, /* SGMII 1000baseT */ ETHTOOL_LINK_MODE_1000baseX_Full_BIT, ETHTOOL_LINK_MODE_10000baseT_Full_BIT, ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, @@ -1166,14 +1159,19 @@ static void otx2_get_link_mode_info(u64 link_mode_bmap, }; u8 bit; - for_each_set_bit(bit, (unsigned long *)&link_mode_bmap, 27) { - /* SGMII mode is set */ - if (bit == 0) - linkmode_set_bit_array(otx2_sgmii_features, - ARRAY_SIZE(otx2_sgmii_features), - otx2_link_modes); - else + for_each_set_bit(bit, (unsigned long *)&link_mode_bmap, ARRAY_SIZE(cgx_link_mode)) { + if (bit == CGX_MODE_SGMII_10M_BIT) { + linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, otx2_link_modes); + linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, otx2_link_modes); + } else if (bit == CGX_MODE_SGMII_100M_BIT) { + linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, otx2_link_modes); + linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, otx2_link_modes); + } else if (bit == CGX_MODE_SGMII) { + linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, otx2_link_modes); + linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, otx2_link_modes); + } else { linkmode_set_bit(cgx_link_mode[bit], otx2_link_modes); + } } if (req_mode == OTX2_MODE_ADVERTISED) @@ -1214,23 +1212,10 @@ static int otx2_get_link_ksettings(struct net_device *netdev, return 0; } -static void otx2_get_advertised_mode(const struct ethtool_link_ksettings *cmd, - u64 *mode) -{ - u32 bit_pos; - - /* Firmware does not support requesting multiple advertised modes - * return first set bit - */ - bit_pos = find_first_bit(cmd->link_modes.advertising, - __ETHTOOL_LINK_MODE_MASK_NBITS); - if (bit_pos != __ETHTOOL_LINK_MODE_MASK_NBITS) - *mode = bit_pos; -} - static int otx2_set_link_ksettings(struct net_device *netdev, const struct ethtool_link_ksettings *cmd) { + __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; struct otx2_nic *pf = netdev_priv(netdev); struct ethtool_link_ksettings cur_ks; struct cgx_set_link_mode_req *req; @@ -1267,7 +1252,20 @@ static int otx2_set_link_ksettings(struct net_device *netdev, */ req->args.duplex = cmd->base.duplex ^ 0x1; req->args.an = cmd->base.autoneg; - otx2_get_advertised_mode(cmd, &req->args.mode); + /* Mask unsupported modes and send message to AF */ + linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_NONE_BIT, mask); + linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_BASER_BIT, mask); + linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_RS_BIT, mask); + + linkmode_copy(req->args.advertising, + cmd->link_modes.advertising); + linkmode_andnot(req->args.advertising, + req->args.advertising, mask); + + /* inform AF that we need parse this differently */ + if (bitmap_weight(req->args.advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS) >= 2) + req->args.multimode = true; err = otx2_sync_mbox_msg(&pf->mbox); end: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index 42218834183a..3ffa3fbacd16 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -376,6 +376,8 @@ static const struct devlink_ops mlx5_devlink_ops = { .eswitch_encap_mode_get = mlx5_devlink_eswitch_encap_mode_get, .rate_leaf_tx_share_set = mlx5_esw_devlink_rate_leaf_tx_share_set, .rate_leaf_tx_max_set = mlx5_esw_devlink_rate_leaf_tx_max_set, + .rate_leaf_tc_bw_set = mlx5_esw_devlink_rate_leaf_tc_bw_set, + .rate_node_tc_bw_set = mlx5_esw_devlink_rate_node_tc_bw_set, .rate_node_tx_share_set = mlx5_esw_devlink_rate_node_tx_share_set, .rate_node_tx_max_set = mlx5_esw_devlink_rate_node_tx_max_set, .rate_node_new = mlx5_esw_devlink_rate_node_new, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index dca5ca51a470..e8e5b347f9b2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -952,6 +952,8 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, if (xsk) { err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, MEM_TYPE_XSK_BUFF_POOL, NULL); + if (err) + goto err_free_by_rq_type; xsk_pool_set_rxq_info(rq->xsk_pool, &rq->xdp_rxq); } else { /* Create a page_pool and register it with rxq */ @@ -985,12 +987,13 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, } if (!rq->hd_page_pool) rq->hd_page_pool = rq->page_pool; - if (xdp_rxq_info_is_reg(&rq->xdp_rxq)) + if (xdp_rxq_info_is_reg(&rq->xdp_rxq)) { err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, MEM_TYPE_PAGE_POOL, rq->page_pool); + if (err) + goto err_destroy_page_pool; + } } - if (err) - goto err_destroy_page_pool; for (i = 0; i < wq_sz; i++) { if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index b6ae384396b3..154bbb17ec0e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -64,11 +64,19 @@ static void esw_qos_domain_release(struct mlx5_eswitch *esw) enum sched_node_type { SCHED_NODE_TYPE_VPORTS_TSAR, SCHED_NODE_TYPE_VPORT, + SCHED_NODE_TYPE_TC_ARBITER_TSAR, + SCHED_NODE_TYPE_RATE_LIMITER, + SCHED_NODE_TYPE_VPORT_TC, + SCHED_NODE_TYPE_VPORTS_TC_TSAR, }; static const char * const sched_node_type_str[] = { [SCHED_NODE_TYPE_VPORTS_TSAR] = "vports TSAR", [SCHED_NODE_TYPE_VPORT] = "vport", + [SCHED_NODE_TYPE_TC_ARBITER_TSAR] = "TC Arbiter TSAR", + [SCHED_NODE_TYPE_RATE_LIMITER] = "Rate Limiter", + [SCHED_NODE_TYPE_VPORT_TC] = "vport TC", + [SCHED_NODE_TYPE_VPORTS_TC_TSAR] = "vports TC TSAR", }; struct mlx5_esw_sched_node { @@ -92,6 +100,8 @@ struct mlx5_esw_sched_node { struct mlx5_vport *vport; /* Level in the hierarchy. The root node level is 1. */ u8 level; + /* Valid only when this node represents a traffic class. */ + u8 tc; }; static void esw_qos_node_attach_to_parent(struct mlx5_esw_sched_node *node) @@ -106,6 +116,13 @@ static void esw_qos_node_attach_to_parent(struct mlx5_esw_sched_node *node) } } +static int esw_qos_num_tcs(struct mlx5_core_dev *dev) +{ + int num_tcs = mlx5_max_tc(dev) + 1; + + return num_tcs < DEVLINK_RATE_TCS_MAX ? num_tcs : DEVLINK_RATE_TCS_MAX; +} + static void esw_qos_node_set_parent(struct mlx5_esw_sched_node *node, struct mlx5_esw_sched_node *parent) { @@ -116,8 +133,38 @@ esw_qos_node_set_parent(struct mlx5_esw_sched_node *node, struct mlx5_esw_sched_ esw_qos_node_attach_to_parent(node); } +static void esw_qos_nodes_set_parent(struct list_head *nodes, + struct mlx5_esw_sched_node *parent) +{ + struct mlx5_esw_sched_node *node, *tmp; + + list_for_each_entry_safe(node, tmp, nodes, entry) { + esw_qos_node_set_parent(node, parent); + if (!list_empty(&node->children) && + parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) { + struct mlx5_esw_sched_node *child; + + list_for_each_entry(child, &node->children, entry) { + struct mlx5_vport *vport = child->vport; + + if (vport) + vport->qos.sched_node->parent = parent; + } + } + } +} + void mlx5_esw_qos_vport_qos_free(struct mlx5_vport *vport) { + if (vport->qos.sched_nodes) { + int num_tcs = esw_qos_num_tcs(vport->qos.sched_node->esw->dev); + int i; + + for (i = 0; i < num_tcs; i++) + kfree(vport->qos.sched_nodes[i]); + kfree(vport->qos.sched_nodes); + } + kfree(vport->qos.sched_node); memset(&vport->qos, 0, sizeof(vport->qos)); } @@ -141,16 +188,37 @@ mlx5_esw_qos_vport_get_parent(const struct mlx5_vport *vport) static void esw_qos_sched_elem_warn(struct mlx5_esw_sched_node *node, int err, const char *op) { - if (node->vport) { + switch (node->type) { + case SCHED_NODE_TYPE_VPORTS_TC_TSAR: + esw_warn(node->esw->dev, + "E-Switch %s %s scheduling element failed (tc=%d,err=%d)\n", + op, sched_node_type_str[node->type], node->tc, err); + break; + case SCHED_NODE_TYPE_VPORT_TC: + esw_warn(node->esw->dev, + "E-Switch %s %s scheduling element failed (vport=%d,tc=%d,err=%d)\n", + op, + sched_node_type_str[node->type], + node->vport->vport, node->tc, err); + break; + case SCHED_NODE_TYPE_VPORT: esw_warn(node->esw->dev, "E-Switch %s %s scheduling element failed (vport=%d,err=%d)\n", op, sched_node_type_str[node->type], node->vport->vport, err); - return; + break; + case SCHED_NODE_TYPE_RATE_LIMITER: + case SCHED_NODE_TYPE_TC_ARBITER_TSAR: + case SCHED_NODE_TYPE_VPORTS_TSAR: + esw_warn(node->esw->dev, + "E-Switch %s %s scheduling element failed (err=%d)\n", + op, sched_node_type_str[node->type], err); + break; + default: + esw_warn(node->esw->dev, + "E-Switch %s scheduling element failed (err=%d)\n", + op, err); + break; } - - esw_warn(node->esw->dev, - "E-Switch %s %s scheduling element failed (err=%d)\n", - op, sched_node_type_str[node->type], err); } static int esw_qos_node_create_sched_element(struct mlx5_esw_sched_node *node, void *ctx, @@ -233,6 +301,24 @@ static int esw_qos_sched_elem_config(struct mlx5_esw_sched_node *node, u32 max_r return 0; } +static int esw_qos_create_rate_limit_element(struct mlx5_esw_sched_node *node, + struct netlink_ext_ack *extack) +{ + u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; + + if (!mlx5_qos_element_type_supported( + node->esw->dev, + SCHEDULING_CONTEXT_ELEMENT_TYPE_RATE_LIMIT, + SCHEDULING_HIERARCHY_E_SWITCH)) + return -EOPNOTSUPP; + + MLX5_SET(scheduling_context, sched_ctx, max_average_bw, node->max_rate); + MLX5_SET(scheduling_context, sched_ctx, element_type, + SCHEDULING_CONTEXT_ELEMENT_TYPE_RATE_LIMIT); + + return esw_qos_node_create_sched_element(node, sched_ctx, extack); +} + static u32 esw_qos_calculate_min_rate_divider(struct mlx5_eswitch *esw, struct mlx5_esw_sched_node *parent) { @@ -266,11 +352,13 @@ static u32 esw_qos_calculate_min_rate_divider(struct mlx5_eswitch *esw, return 0; } -static u32 esw_qos_calc_bw_share(u32 min_rate, u32 divider, u32 fw_max) +static u32 esw_qos_calc_bw_share(u32 value, u32 divider, u32 fw_max) { if (!divider) return 0; - return min_t(u32, max_t(u32, DIV_ROUND_UP(min_rate, divider), MLX5_MIN_BW_SHARE), fw_max); + return min_t(u32, fw_max, + max_t(u32, + DIV_ROUND_UP(value, divider), MLX5_MIN_BW_SHARE)); } static void esw_qos_update_sched_node_bw_share(struct mlx5_esw_sched_node *node, @@ -297,7 +385,13 @@ static void esw_qos_normalize_min_rate(struct mlx5_eswitch *esw, if (node->esw != esw || node->ix == esw->qos.root_tsar_ix) continue; - esw_qos_update_sched_node_bw_share(node, divider, extack); + /* Vports TC TSARs don't have a minimum rate configured, + * so there's no need to update the bw_share on them. + */ + if (node->type != SCHED_NODE_TYPE_VPORTS_TC_TSAR) { + esw_qos_update_sched_node_bw_share(node, divider, + extack); + } if (list_empty(&node->children)) continue; @@ -306,6 +400,20 @@ static void esw_qos_normalize_min_rate(struct mlx5_eswitch *esw, } } +static u32 esw_qos_calculate_tc_bw_divider(u32 *tc_bw) +{ + u32 total = 0; + int i; + + for (i = 0; i < DEVLINK_RATE_TCS_MAX; i++) + total += tc_bw[i]; + + /* If total is zero, tc-bw config is disabled and we shouldn't reach + * here. + */ + return WARN_ON(!total) ? 1 : total; +} + static int esw_qos_set_node_min_rate(struct mlx5_esw_sched_node *node, u32 min_rate, struct netlink_ext_ack *extack) { @@ -350,28 +458,64 @@ esw_qos_create_node_sched_elem(struct mlx5_core_dev *dev, u32 parent_element_id, tsar_ix); } -static int esw_qos_vport_create_sched_element(struct mlx5_esw_sched_node *vport_node, - struct netlink_ext_ack *extack) +static int +esw_qos_vport_create_sched_element(struct mlx5_esw_sched_node *vport_node, + struct netlink_ext_ack *extack) { u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; struct mlx5_core_dev *dev = vport_node->esw->dev; void *attr; - if (!mlx5_qos_element_type_supported(dev, - SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT, - SCHEDULING_HIERARCHY_E_SWITCH)) + if (!mlx5_qos_element_type_supported( + dev, + SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT, + SCHEDULING_HIERARCHY_E_SWITCH)) return -EOPNOTSUPP; MLX5_SET(scheduling_context, sched_ctx, element_type, SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT); attr = MLX5_ADDR_OF(scheduling_context, sched_ctx, element_attributes); MLX5_SET(vport_element, attr, vport_number, vport_node->vport->vport); - MLX5_SET(scheduling_context, sched_ctx, parent_element_id, vport_node->parent->ix); - MLX5_SET(scheduling_context, sched_ctx, max_average_bw, vport_node->max_rate); + MLX5_SET(scheduling_context, sched_ctx, parent_element_id, + vport_node->parent->ix); + MLX5_SET(scheduling_context, sched_ctx, max_average_bw, + vport_node->max_rate); return esw_qos_node_create_sched_element(vport_node, sched_ctx, extack); } +static int +esw_qos_vport_tc_create_sched_element(struct mlx5_esw_sched_node *vport_tc_node, + u32 rate_limit_elem_ix, + struct netlink_ext_ack *extack) +{ + u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; + struct mlx5_core_dev *dev = vport_tc_node->esw->dev; + void *attr; + + if (!mlx5_qos_element_type_supported( + dev, + SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC, + SCHEDULING_HIERARCHY_E_SWITCH)) + return -EOPNOTSUPP; + + MLX5_SET(scheduling_context, sched_ctx, element_type, + SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC); + attr = MLX5_ADDR_OF(scheduling_context, sched_ctx, element_attributes); + MLX5_SET(vport_tc_element, attr, vport_number, + vport_tc_node->vport->vport); + MLX5_SET(vport_tc_element, attr, traffic_class, vport_tc_node->tc); + MLX5_SET(scheduling_context, sched_ctx, max_bw_obj_id, + rate_limit_elem_ix); + MLX5_SET(scheduling_context, sched_ctx, parent_element_id, + vport_tc_node->parent->ix); + MLX5_SET(scheduling_context, sched_ctx, bw_share, + vport_tc_node->bw_share); + + return esw_qos_node_create_sched_element(vport_tc_node, sched_ctx, + extack); +} + static struct mlx5_esw_sched_node * __esw_qos_alloc_node(struct mlx5_eswitch *esw, u32 tsar_ix, enum sched_node_type type, struct mlx5_esw_sched_node *parent) @@ -388,6 +532,14 @@ __esw_qos_alloc_node(struct mlx5_eswitch *esw, u32 tsar_ix, enum sched_node_type node->parent = parent; INIT_LIST_HEAD(&node->children); esw_qos_node_attach_to_parent(node); + if (!parent) { + /* The caller is responsible for inserting the node into the + * parent list if necessary. This function can also be used with + * a NULL parent, which doesn't necessarily indicate that it + * refers to the root scheduling element. + */ + list_del_init(&node->entry); + } return node; } @@ -404,6 +556,149 @@ static void esw_qos_destroy_node(struct mlx5_esw_sched_node *node, struct netlin __esw_qos_free_node(node); } +static int esw_qos_create_vports_tc_node(struct mlx5_esw_sched_node *parent, + u8 tc, struct netlink_ext_ack *extack) +{ + u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; + struct mlx5_core_dev *dev = parent->esw->dev; + struct mlx5_esw_sched_node *vports_tc_node; + void *attr; + int err; + + if (!mlx5_qos_element_type_supported( + dev, + SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR, + SCHEDULING_HIERARCHY_E_SWITCH) || + !mlx5_qos_tsar_type_supported(dev, + TSAR_ELEMENT_TSAR_TYPE_DWRR, + SCHEDULING_HIERARCHY_E_SWITCH)) + return -EOPNOTSUPP; + + vports_tc_node = __esw_qos_alloc_node(parent->esw, 0, + SCHED_NODE_TYPE_VPORTS_TC_TSAR, + parent); + if (!vports_tc_node) { + NL_SET_ERR_MSG_MOD(extack, "E-Switch alloc node failed"); + esw_warn(dev, "Failed to alloc vports TC node (tc=%d)\n", tc); + return -ENOMEM; + } + + attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes); + MLX5_SET(tsar_element, attr, tsar_type, TSAR_ELEMENT_TSAR_TYPE_DWRR); + MLX5_SET(tsar_element, attr, traffic_class, tc); + MLX5_SET(scheduling_context, tsar_ctx, parent_element_id, parent->ix); + MLX5_SET(scheduling_context, tsar_ctx, element_type, + SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR); + + err = esw_qos_node_create_sched_element(vports_tc_node, tsar_ctx, + extack); + if (err) + goto err_create_sched_element; + + vports_tc_node->tc = tc; + + return 0; + +err_create_sched_element: + __esw_qos_free_node(vports_tc_node); + return err; +} + +static void +esw_qos_tc_arbiter_get_bw_shares(struct mlx5_esw_sched_node *tc_arbiter_node, + u32 *tc_bw) +{ + struct mlx5_esw_sched_node *vports_tc_node; + + list_for_each_entry(vports_tc_node, &tc_arbiter_node->children, entry) + tc_bw[vports_tc_node->tc] = vports_tc_node->bw_share; +} + +static void +esw_qos_set_tc_arbiter_bw_shares(struct mlx5_esw_sched_node *tc_arbiter_node, + u32 *tc_bw, struct netlink_ext_ack *extack) +{ + struct mlx5_eswitch *esw = tc_arbiter_node->esw; + struct mlx5_esw_sched_node *vports_tc_node; + u32 divider, fw_max_bw_share; + + fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share); + divider = esw_qos_calculate_tc_bw_divider(tc_bw); + list_for_each_entry(vports_tc_node, &tc_arbiter_node->children, entry) { + u8 tc = vports_tc_node->tc; + u32 bw_share; + + bw_share = tc_bw[tc] * fw_max_bw_share; + bw_share = esw_qos_calc_bw_share(bw_share, divider, + fw_max_bw_share); + esw_qos_sched_elem_config(vports_tc_node, 0, bw_share, extack); + } +} + +static void +esw_qos_destroy_vports_tc_nodes(struct mlx5_esw_sched_node *tc_arbiter_node, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *vports_tc_node, *tmp; + + list_for_each_entry_safe(vports_tc_node, tmp, + &tc_arbiter_node->children, entry) + esw_qos_destroy_node(vports_tc_node, extack); +} + +static int +esw_qos_create_vports_tc_nodes(struct mlx5_esw_sched_node *tc_arbiter_node, + struct netlink_ext_ack *extack) +{ + struct mlx5_eswitch *esw = tc_arbiter_node->esw; + int err, i, num_tcs = esw_qos_num_tcs(esw->dev); + + for (i = 0; i < num_tcs; i++) { + err = esw_qos_create_vports_tc_node(tc_arbiter_node, i, extack); + if (err) + goto err_tc_node_create; + } + + return 0; + +err_tc_node_create: + esw_qos_destroy_vports_tc_nodes(tc_arbiter_node, NULL); + return err; +} + +static int esw_qos_create_tc_arbiter_sched_elem( + struct mlx5_esw_sched_node *tc_arbiter_node, + struct netlink_ext_ack *extack) +{ + u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; + u32 tsar_parent_ix; + void *attr; + + if (!mlx5_qos_tsar_type_supported(tc_arbiter_node->esw->dev, + TSAR_ELEMENT_TSAR_TYPE_TC_ARB, + SCHEDULING_HIERARCHY_E_SWITCH)) { + NL_SET_ERR_MSG_MOD(extack, + "E-Switch TC Arbiter scheduling element is not supported"); + return -EOPNOTSUPP; + } + + attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes); + MLX5_SET(tsar_element, attr, tsar_type, TSAR_ELEMENT_TSAR_TYPE_TC_ARB); + tsar_parent_ix = tc_arbiter_node->parent ? tc_arbiter_node->parent->ix : + tc_arbiter_node->esw->qos.root_tsar_ix; + MLX5_SET(scheduling_context, tsar_ctx, parent_element_id, + tsar_parent_ix); + MLX5_SET(scheduling_context, tsar_ctx, element_type, + SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR); + MLX5_SET(scheduling_context, tsar_ctx, max_average_bw, + tc_arbiter_node->max_rate); + MLX5_SET(scheduling_context, tsar_ctx, bw_share, + tc_arbiter_node->bw_share); + + return esw_qos_node_create_sched_element(tc_arbiter_node, tsar_ctx, + extack); +} + static struct mlx5_esw_sched_node * __esw_qos_create_vports_sched_node(struct mlx5_eswitch *esw, struct mlx5_esw_sched_node *parent, struct netlink_ext_ack *extack) @@ -426,6 +721,7 @@ __esw_qos_create_vports_sched_node(struct mlx5_eswitch *esw, struct mlx5_esw_sch goto err_alloc_node; } + list_add_tail(&node->entry, &esw->qos.domain->nodes); esw_qos_normalize_min_rate(esw, NULL, extack); trace_mlx5_esw_node_qos_create(esw->dev, node, node->ix); @@ -467,6 +763,9 @@ static void __esw_qos_destroy_node(struct mlx5_esw_sched_node *node, struct netl { struct mlx5_eswitch *esw = node->esw; + if (node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) + esw_qos_destroy_vports_tc_nodes(node, extack); + trace_mlx5_esw_node_qos_destroy(esw->dev, node, node->ix); esw_qos_destroy_node(node, extack); esw_qos_normalize_min_rate(esw, NULL, extack); @@ -498,6 +797,9 @@ static int esw_qos_create(struct mlx5_eswitch *esw, struct netlink_ext_ack *exta SCHED_NODE_TYPE_VPORTS_TSAR, NULL)) esw->qos.node0 = ERR_PTR(-ENOMEM); + else + list_add_tail(&esw->qos.node0->entry, + &esw->qos.domain->nodes); } if (IS_ERR(esw->qos.node0)) { err = PTR_ERR(esw->qos.node0); @@ -555,12 +857,239 @@ static void esw_qos_put(struct mlx5_eswitch *esw) esw_qos_destroy(esw); } +static void +esw_qos_tc_arbiter_scheduling_teardown(struct mlx5_esw_sched_node *node, + struct netlink_ext_ack *extack) +{ + /* Clean up all Vports TC nodes within the TC arbiter node. */ + esw_qos_destroy_vports_tc_nodes(node, extack); + /* Destroy the scheduling element for the TC arbiter node itself. */ + esw_qos_node_destroy_sched_element(node, extack); +} + +static int esw_qos_tc_arbiter_scheduling_setup(struct mlx5_esw_sched_node *node, + struct netlink_ext_ack *extack) +{ + u32 curr_ix = node->ix; + int err; + + err = esw_qos_create_tc_arbiter_sched_elem(node, extack); + if (err) + return err; + /* Initialize the vports TC nodes within created TC arbiter TSAR. */ + err = esw_qos_create_vports_tc_nodes(node, extack); + if (err) + goto err_vports_tc_nodes; + + node->type = SCHED_NODE_TYPE_TC_ARBITER_TSAR; + + return 0; + +err_vports_tc_nodes: + /* If initialization fails, clean up the scheduling element + * for the TC arbiter node. + */ + esw_qos_node_destroy_sched_element(node, NULL); + node->ix = curr_ix; + return err; +} + +static int +esw_qos_create_vport_tc_sched_node(struct mlx5_vport *vport, + u32 rate_limit_elem_ix, + struct mlx5_esw_sched_node *vports_tc_node, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; + struct mlx5_esw_sched_node *vport_tc_node; + u8 tc = vports_tc_node->tc; + int err; + + vport_tc_node = __esw_qos_alloc_node(vport_node->esw, 0, + SCHED_NODE_TYPE_VPORT_TC, + vports_tc_node); + if (!vport_tc_node) + return -ENOMEM; + + vport_tc_node->min_rate = vport_node->min_rate; + vport_tc_node->tc = tc; + vport_tc_node->vport = vport; + err = esw_qos_vport_tc_create_sched_element(vport_tc_node, + rate_limit_elem_ix, + extack); + if (err) + goto err_out; + + vport->qos.sched_nodes[tc] = vport_tc_node; + + return 0; +err_out: + __esw_qos_free_node(vport_tc_node); + return err; +} + +static void +esw_qos_destroy_vport_tc_sched_elements(struct mlx5_vport *vport, + struct netlink_ext_ack *extack) +{ + int i, num_tcs = esw_qos_num_tcs(vport->qos.sched_node->esw->dev); + + for (i = 0; i < num_tcs; i++) { + if (vport->qos.sched_nodes[i]) { + __esw_qos_destroy_node(vport->qos.sched_nodes[i], + extack); + } + } + + kfree(vport->qos.sched_nodes); + vport->qos.sched_nodes = NULL; +} + +static int +esw_qos_create_vport_tc_sched_elements(struct mlx5_vport *vport, + enum sched_node_type type, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; + struct mlx5_esw_sched_node *tc_arbiter_node, *vports_tc_node; + int err, num_tcs = esw_qos_num_tcs(vport_node->esw->dev); + u32 rate_limit_elem_ix; + + vport->qos.sched_nodes = kcalloc(num_tcs, + sizeof(struct mlx5_esw_sched_node *), + GFP_KERNEL); + if (!vport->qos.sched_nodes) { + NL_SET_ERR_MSG_MOD(extack, + "Allocating the vport TC scheduling elements failed."); + return -ENOMEM; + } + + rate_limit_elem_ix = type == SCHED_NODE_TYPE_RATE_LIMITER ? + vport_node->ix : 0; + tc_arbiter_node = type == SCHED_NODE_TYPE_RATE_LIMITER ? + vport_node->parent : vport_node; + list_for_each_entry(vports_tc_node, &tc_arbiter_node->children, entry) { + err = esw_qos_create_vport_tc_sched_node(vport, + rate_limit_elem_ix, + vports_tc_node, + extack); + if (err) + goto err_create_vport_tc; + } + + return 0; + +err_create_vport_tc: + esw_qos_destroy_vport_tc_sched_elements(vport, NULL); + + return err; +} + +static int +esw_qos_vport_tc_enable(struct mlx5_vport *vport, enum sched_node_type type, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; + int err, new_level, max_level; + + if (type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) { + /* Increase the parent's level by 2 to account for both the + * TC arbiter and the vports TC scheduling element. + */ + new_level = vport_node->parent->level + 2; + max_level = 1 << MLX5_CAP_QOS(vport_node->esw->dev, + log_esw_max_sched_depth); + if (new_level > max_level) { + NL_SET_ERR_MSG_MOD(extack, + "TC arbitration on leafs is not supported beyond max scheduling depth"); + return -EOPNOTSUPP; + } + } + + esw_assert_qos_lock_held(vport->dev->priv.eswitch); + + if (type == SCHED_NODE_TYPE_RATE_LIMITER) + err = esw_qos_create_rate_limit_element(vport_node, extack); + else + err = esw_qos_tc_arbiter_scheduling_setup(vport_node, extack); + if (err) + return err; + + /* Rate limiters impact multiple nodes not directly connected to them + * and are not direct members of the QoS hierarchy. + * Unlink it from the parent to reflect that. + */ + if (type == SCHED_NODE_TYPE_RATE_LIMITER) { + list_del_init(&vport_node->entry); + vport_node->level = 0; + } + + err = esw_qos_create_vport_tc_sched_elements(vport, type, extack); + if (err) + goto err_sched_nodes; + + return 0; + +err_sched_nodes: + if (type == SCHED_NODE_TYPE_RATE_LIMITER) { + esw_qos_node_destroy_sched_element(vport_node, NULL); + list_add_tail(&vport_node->entry, + &vport_node->parent->children); + vport_node->level = vport_node->parent->level + 1; + } else { + esw_qos_tc_arbiter_scheduling_teardown(vport_node, NULL); + } + return err; +} + +static void esw_qos_vport_tc_disable(struct mlx5_vport *vport, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; + enum sched_node_type curr_type = vport_node->type; + + esw_qos_destroy_vport_tc_sched_elements(vport, extack); + + if (curr_type == SCHED_NODE_TYPE_RATE_LIMITER) + esw_qos_node_destroy_sched_element(vport_node, extack); + else + esw_qos_tc_arbiter_scheduling_teardown(vport_node, extack); +} + +static int esw_qos_set_vport_tcs_min_rate(struct mlx5_vport *vport, + u32 min_rate, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; + int err, i, num_tcs = esw_qos_num_tcs(vport_node->esw->dev); + + for (i = 0; i < num_tcs; i++) { + err = esw_qos_set_node_min_rate(vport->qos.sched_nodes[i], + min_rate, extack); + if (err) + goto err_out; + } + vport_node->min_rate = min_rate; + + return 0; +err_out: + for (--i; i >= 0; i--) { + esw_qos_set_node_min_rate(vport->qos.sched_nodes[i], + vport_node->min_rate, extack); + } + return err; +} + static void esw_qos_vport_disable(struct mlx5_vport *vport, struct netlink_ext_ack *extack) { struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; struct mlx5_esw_sched_node *parent = vport_node->parent; + enum sched_node_type curr_type = vport_node->type; - esw_qos_node_destroy_sched_element(vport_node, extack); + if (curr_type == SCHED_NODE_TYPE_VPORT) + esw_qos_node_destroy_sched_element(vport_node, extack); + else + esw_qos_vport_tc_disable(vport, extack); vport_node->bw_share = 0; list_del_init(&vport_node->entry); @@ -569,7 +1098,9 @@ static void esw_qos_vport_disable(struct mlx5_vport *vport, struct netlink_ext_a trace_mlx5_esw_vport_qos_destroy(vport_node->esw->dev, vport); } -static int esw_qos_vport_enable(struct mlx5_vport *vport, struct mlx5_esw_sched_node *parent, +static int esw_qos_vport_enable(struct mlx5_vport *vport, + enum sched_node_type type, + struct mlx5_esw_sched_node *parent, struct netlink_ext_ack *extack) { int err; @@ -577,10 +1108,16 @@ static int esw_qos_vport_enable(struct mlx5_vport *vport, struct mlx5_esw_sched_ esw_assert_qos_lock_held(vport->dev->priv.eswitch); esw_qos_node_set_parent(vport->qos.sched_node, parent); - err = esw_qos_vport_create_sched_element(vport->qos.sched_node, extack); + if (type == SCHED_NODE_TYPE_VPORT) { + err = esw_qos_vport_create_sched_element(vport->qos.sched_node, + extack); + } else { + err = esw_qos_vport_tc_enable(vport, type, extack); + } if (err) return err; + vport->qos.sched_node->type = type; esw_qos_normalize_min_rate(parent->esw, parent, extack); trace_mlx5_esw_vport_qos_create(vport->dev, vport, vport->qos.sched_node->max_rate, @@ -611,9 +1148,8 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t sched_node->min_rate = min_rate; sched_node->vport = vport; vport->qos.sched_node = sched_node; - err = esw_qos_vport_enable(vport, parent, extack); + err = esw_qos_vport_enable(vport, type, parent, extack); if (err) { - __esw_qos_free_node(sched_node); esw_qos_put(esw); vport->qos.sched_node = NULL; } @@ -666,6 +1202,8 @@ static int mlx5_esw_qos_set_vport_min_rate(struct mlx5_vport *vport, u32 min_rat if (!vport_node) return mlx5_esw_qos_vport_enable(vport, SCHED_NODE_TYPE_VPORT, NULL, 0, min_rate, extack); + else if (vport_node->type == SCHED_NODE_TYPE_RATE_LIMITER) + return esw_qos_set_vport_tcs_min_rate(vport, min_rate, extack); else return esw_qos_set_node_min_rate(vport_node, min_rate, extack); } @@ -698,12 +1236,73 @@ bool mlx5_esw_qos_get_vport_rate(struct mlx5_vport *vport, u32 *max_rate, u32 *m return enabled; } +static int esw_qos_vport_tc_check_type(enum sched_node_type curr_type, + enum sched_node_type new_type, + struct netlink_ext_ack *extack) +{ + if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && + new_type == SCHED_NODE_TYPE_RATE_LIMITER) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot switch from vport-level TC arbitration to node-level TC arbitration"); + return -EOPNOTSUPP; + } + + if (curr_type == SCHED_NODE_TYPE_RATE_LIMITER && + new_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot switch from node-level TC arbitration to vport-level TC arbitration"); + return -EOPNOTSUPP; + } + + return 0; +} + +static int esw_qos_vport_update(struct mlx5_vport *vport, + enum sched_node_type type, + struct mlx5_esw_sched_node *parent, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *curr_parent = vport->qos.sched_node->parent; + enum sched_node_type curr_type = vport->qos.sched_node->type; + u32 curr_tc_bw[DEVLINK_RATE_TCS_MAX] = {0}; + int err; + + esw_assert_qos_lock_held(vport->dev->priv.eswitch); + parent = parent ?: curr_parent; + if (curr_type == type && curr_parent == parent) + return 0; + + err = esw_qos_vport_tc_check_type(curr_type, type, extack); + if (err) + return err; + + if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && curr_type == type) { + esw_qos_tc_arbiter_get_bw_shares(vport->qos.sched_node, + curr_tc_bw); + } + + esw_qos_vport_disable(vport, extack); + + err = esw_qos_vport_enable(vport, type, parent, extack); + if (err) { + esw_qos_vport_enable(vport, curr_type, curr_parent, NULL); + extack = NULL; + } + + if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && curr_type == type) { + esw_qos_set_tc_arbiter_bw_shares(vport->qos.sched_node, + curr_tc_bw, extack); + } + + return err; +} + static int esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw_sched_node *parent, struct netlink_ext_ack *extack) { struct mlx5_eswitch *esw = vport->dev->priv.eswitch; struct mlx5_esw_sched_node *curr_parent; - int err; + enum sched_node_type type; esw_assert_qos_lock_held(esw); curr_parent = vport->qos.sched_node->parent; @@ -711,15 +1310,205 @@ static int esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw if (curr_parent == parent) return 0; - esw_qos_vport_disable(vport, extack); + /* Set vport QoS type based on parent node type if different from + * default QoS; otherwise, use the vport's current QoS type. + */ + if (parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) + type = SCHED_NODE_TYPE_RATE_LIMITER; + else if (curr_parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) + type = SCHED_NODE_TYPE_VPORT; + else + type = vport->qos.sched_node->type; + + return esw_qos_vport_update(vport, type, parent, extack); +} - err = esw_qos_vport_enable(vport, parent, extack); +static void +esw_qos_switch_vport_tcs_to_vport(struct mlx5_esw_sched_node *tc_arbiter_node, + struct mlx5_esw_sched_node *node, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *vports_tc_node, *vport_tc_node, *tmp; + + vports_tc_node = list_first_entry(&tc_arbiter_node->children, + struct mlx5_esw_sched_node, + entry); + + list_for_each_entry_safe(vport_tc_node, tmp, &vports_tc_node->children, + entry) + esw_qos_vport_update_parent(vport_tc_node->vport, node, extack); +} + +static int esw_qos_switch_tc_arbiter_node_to_vports( + struct mlx5_esw_sched_node *tc_arbiter_node, + struct mlx5_esw_sched_node *node, + struct netlink_ext_ack *extack) +{ + u32 parent_tsar_ix = node->parent ? + node->parent->ix : node->esw->qos.root_tsar_ix; + int err; + + err = esw_qos_create_node_sched_elem(node->esw->dev, parent_tsar_ix, + node->max_rate, node->bw_share, + &node->ix); if (err) { - if (esw_qos_vport_enable(vport, curr_parent, NULL)) - esw_warn(parent->esw->dev, "vport restore QoS failed (vport=%d)\n", - vport->vport); + NL_SET_ERR_MSG_MOD(extack, + "Failed to create scheduling element for vports node when disabliing vports TC QoS"); + return err; + } + + node->type = SCHED_NODE_TYPE_VPORTS_TSAR; + + /* Disable TC QoS for vports in the arbiter node. */ + esw_qos_switch_vport_tcs_to_vport(tc_arbiter_node, node, extack); + + return 0; +} + +static int esw_qos_switch_vports_node_to_tc_arbiter( + struct mlx5_esw_sched_node *node, + struct mlx5_esw_sched_node *tc_arbiter_node, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *vport_node, *tmp; + struct mlx5_vport *vport; + int err; + + /* Enable TC QoS for each vport in the node. */ + list_for_each_entry_safe(vport_node, tmp, &node->children, entry) { + vport = vport_node->vport; + err = esw_qos_vport_update_parent(vport, tc_arbiter_node, + extack); + if (err) + goto err_out; + } + + /* Destroy the current vports node TSAR. */ + err = mlx5_destroy_scheduling_element_cmd(node->esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + node->ix); + if (err) + goto err_out; + + return 0; +err_out: + /* Restore vports back into the node if an error occurs. */ + esw_qos_switch_vport_tcs_to_vport(tc_arbiter_node, node, NULL); + + return err; +} + +static struct mlx5_esw_sched_node * +esw_qos_move_node(struct mlx5_esw_sched_node *curr_node) +{ + struct mlx5_esw_sched_node *new_node; + + new_node = __esw_qos_alloc_node(curr_node->esw, curr_node->ix, + curr_node->type, NULL); + if (!IS_ERR(new_node)) + esw_qos_nodes_set_parent(&curr_node->children, new_node); + + return new_node; +} + +static int esw_qos_node_disable_tc_arbitration(struct mlx5_esw_sched_node *node, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *curr_node; + int err; + + if (node->type != SCHED_NODE_TYPE_TC_ARBITER_TSAR) + return 0; + + /* Allocate a new rate node to hold the current state, which will allow + * for restoring the vports back to this node after disabling TC + * arbitration. + */ + curr_node = esw_qos_move_node(node); + if (IS_ERR(curr_node)) { + NL_SET_ERR_MSG_MOD(extack, "Failed setting up vports node"); + return PTR_ERR(curr_node); + } + + /* Disable TC QoS for all vports, and assign them back to the node. */ + err = esw_qos_switch_tc_arbiter_node_to_vports(curr_node, node, extack); + if (err) + goto err_out; + + /* Clean up the TC arbiter node after disabling TC QoS for vports. */ + esw_qos_tc_arbiter_scheduling_teardown(curr_node, extack); + goto out; +err_out: + esw_qos_nodes_set_parent(&curr_node->children, node); +out: + __esw_qos_free_node(curr_node); + return err; +} + +static int esw_qos_node_enable_tc_arbitration(struct mlx5_esw_sched_node *node, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *curr_node, *child; + int err, new_level, max_level; + + if (node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) + return 0; + + /* Increase the hierarchy level by one to account for the additional + * vports TC scheduling node, and verify that the new level does not + * exceed the maximum allowed depth. + */ + new_level = node->level + 1; + max_level = 1 << MLX5_CAP_QOS(node->esw->dev, log_esw_max_sched_depth); + if (new_level > max_level) { + NL_SET_ERR_MSG_MOD(extack, + "TC arbitration on nodes is not supported beyond max scheduling depth"); + return -EOPNOTSUPP; + } + + /* Ensure the node does not contain non-leaf children before assigning + * TC bandwidth. + */ + if (!list_empty(&node->children)) { + list_for_each_entry(child, &node->children, entry) { + if (!child->vport) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot configure TC bandwidth on a node with non-leaf children"); + return -EOPNOTSUPP; + } + } } + /* Allocate a new node that will store the information of the current + * node. This will be used later to restore the node if necessary. + */ + curr_node = esw_qos_move_node(node); + if (IS_ERR(curr_node)) { + NL_SET_ERR_MSG_MOD(extack, "Failed setting up node TC QoS"); + return PTR_ERR(curr_node); + } + + /* Initialize the TC arbiter node for QoS management. + * This step prepares the node for handling Traffic Class arbitration. + */ + err = esw_qos_tc_arbiter_scheduling_setup(node, extack); + if (err) + goto err_setup; + + /* Enable TC QoS for each vport within the current node. */ + err = esw_qos_switch_vports_node_to_tc_arbiter(curr_node, node, extack); + if (err) + goto err_switch_vports; + goto out; + +err_switch_vports: + esw_qos_tc_arbiter_scheduling_teardown(node, NULL); + node->ix = curr_node->ix; + node->type = curr_node->type; +err_setup: + esw_qos_nodes_set_parent(&curr_node->children, node); +out: + __esw_qos_free_node(curr_node); return err; } @@ -848,6 +1637,41 @@ static int esw_qos_devlink_rate_to_mbps(struct mlx5_core_dev *mdev, const char * return 0; } +static bool esw_qos_validate_unsupported_tc_bw(struct mlx5_eswitch *esw, + u32 *tc_bw) +{ + int i, num_tcs = esw_qos_num_tcs(esw->dev); + + for (i = num_tcs; i < DEVLINK_RATE_TCS_MAX; i++) { + if (tc_bw[i]) + return false; + } + + return true; +} + +static bool esw_qos_vport_validate_unsupported_tc_bw(struct mlx5_vport *vport, + u32 *tc_bw) +{ + struct mlx5_eswitch *esw = vport->qos.sched_node ? + vport->qos.sched_node->parent->esw : + vport->dev->priv.eswitch; + + return esw_qos_validate_unsupported_tc_bw(esw, tc_bw); +} + +static bool esw_qos_tc_bw_disabled(u32 *tc_bw) +{ + int i; + + for (i = 0; i < DEVLINK_RATE_TCS_MAX; i++) { + if (tc_bw[i]) + return false; + } + + return true; +} + int mlx5_esw_qos_init(struct mlx5_eswitch *esw) { if (esw->qos.domain) @@ -906,6 +1730,90 @@ int mlx5_esw_devlink_rate_leaf_tx_max_set(struct devlink_rate *rate_leaf, void * return err; } +int mlx5_esw_devlink_rate_leaf_tc_bw_set(struct devlink_rate *rate_leaf, + void *priv, + u32 *tc_bw, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *vport_node; + struct mlx5_vport *vport = priv; + struct mlx5_eswitch *esw; + bool disable; + int err = 0; + + esw = vport->dev->priv.eswitch; + if (!mlx5_esw_allowed(esw)) + return -EPERM; + + disable = esw_qos_tc_bw_disabled(tc_bw); + esw_qos_lock(esw); + + if (!esw_qos_vport_validate_unsupported_tc_bw(vport, tc_bw)) { + NL_SET_ERR_MSG_MOD(extack, + "E-Switch traffic classes number is not supported"); + err = -EOPNOTSUPP; + goto unlock; + } + + vport_node = vport->qos.sched_node; + if (disable && !vport_node) + goto unlock; + + if (disable) { + if (vport_node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) + err = esw_qos_vport_update(vport, SCHED_NODE_TYPE_VPORT, + NULL, extack); + goto unlock; + } + + if (!vport_node) { + err = mlx5_esw_qos_vport_enable(vport, + SCHED_NODE_TYPE_TC_ARBITER_TSAR, + NULL, 0, 0, extack); + vport_node = vport->qos.sched_node; + } else { + err = esw_qos_vport_update(vport, + SCHED_NODE_TYPE_TC_ARBITER_TSAR, + NULL, extack); + } + if (!err) + esw_qos_set_tc_arbiter_bw_shares(vport_node, tc_bw, extack); +unlock: + esw_qos_unlock(esw); + return err; +} + +int mlx5_esw_devlink_rate_node_tc_bw_set(struct devlink_rate *rate_node, + void *priv, + u32 *tc_bw, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *node = priv; + struct mlx5_eswitch *esw = node->esw; + bool disable; + int err; + + if (!esw_qos_validate_unsupported_tc_bw(esw, tc_bw)) { + NL_SET_ERR_MSG_MOD(extack, + "E-Switch traffic classes number is not supported"); + return -EOPNOTSUPP; + } + + disable = esw_qos_tc_bw_disabled(tc_bw); + esw_qos_lock(esw); + if (disable) { + err = esw_qos_node_disable_tc_arbitration(node, extack); + goto unlock; + } + + err = esw_qos_node_enable_tc_arbitration(node, extack); + if (!err) + esw_qos_set_tc_arbiter_bw_shares(node, tc_bw, extack); +unlock: + esw_qos_unlock(esw); + return err; +} + int mlx5_esw_devlink_rate_node_tx_share_set(struct devlink_rate *rate_node, void *priv, u64 tx_share, struct netlink_ext_ack *extack) { @@ -996,10 +1904,16 @@ int mlx5_esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw_s } esw_qos_lock(esw); - if (!vport->qos.sched_node && parent) - err = mlx5_esw_qos_vport_enable(vport, SCHED_NODE_TYPE_VPORT, parent, 0, 0, extack); - else if (vport->qos.sched_node) + if (!vport->qos.sched_node && parent) { + enum sched_node_type type; + + type = parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR ? + SCHED_NODE_TYPE_RATE_LIMITER : SCHED_NODE_TYPE_VPORT; + err = mlx5_esw_qos_vport_enable(vport, type, parent, 0, 0, + extack); + } else if (vport->qos.sched_node) { err = esw_qos_vport_update_parent(vport, parent, extack); + } esw_qos_unlock(esw); return err; } @@ -1019,6 +1933,20 @@ int mlx5_esw_devlink_rate_leaf_parent_set(struct devlink_rate *devlink_rate, return mlx5_esw_qos_vport_update_parent(vport, node, extack); } +static bool esw_qos_is_node_empty(struct mlx5_esw_sched_node *node) +{ + if (list_empty(&node->children)) + return true; + + if (node->type != SCHED_NODE_TYPE_TC_ARBITER_TSAR) + return false; + + node = list_first_entry(&node->children, struct mlx5_esw_sched_node, + entry); + + return esw_qos_is_node_empty(node); +} + static int mlx5_esw_qos_node_validate_set_parent(struct mlx5_esw_sched_node *node, struct mlx5_esw_sched_node *parent, @@ -1032,13 +1960,26 @@ mlx5_esw_qos_node_validate_set_parent(struct mlx5_esw_sched_node *node, return -EOPNOTSUPP; } - if (!list_empty(&node->children)) { + if (!esw_qos_is_node_empty(node)) { NL_SET_ERR_MSG_MOD(extack, "Cannot reassign a node that contains rate objects"); return -EOPNOTSUPP; } + if (parent && parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot attach a node to a parent with TC bandwidth configured"); + return -EOPNOTSUPP; + } + new_level = parent ? parent->level + 1 : 2; + if (node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) { + /* Increase by one to account for the vports TC scheduling + * element. + */ + new_level += 1; + } + max_level = 1 << MLX5_CAP_QOS(node->esw->dev, log_esw_max_sched_depth); if (new_level > max_level) { NL_SET_ERR_MSG_MOD(extack, @@ -1049,6 +1990,32 @@ mlx5_esw_qos_node_validate_set_parent(struct mlx5_esw_sched_node *node, return 0; } +static int +esw_qos_tc_arbiter_node_update_parent(struct mlx5_esw_sched_node *node, + struct mlx5_esw_sched_node *parent, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *curr_parent = node->parent; + u32 curr_tc_bw[DEVLINK_RATE_TCS_MAX] = {0}; + struct mlx5_eswitch *esw = node->esw; + int err; + + esw_qos_tc_arbiter_get_bw_shares(node, curr_tc_bw); + esw_qos_tc_arbiter_scheduling_teardown(node, extack); + esw_qos_node_set_parent(node, parent); + err = esw_qos_tc_arbiter_scheduling_setup(node, extack); + if (err) { + esw_qos_node_set_parent(node, curr_parent); + if (esw_qos_tc_arbiter_scheduling_setup(node, extack)) { + esw_warn(esw->dev, "Node restore QoS failed\n"); + return err; + } + } + esw_qos_set_tc_arbiter_bw_shares(node, curr_tc_bw, extack); + + return err; +} + static int esw_qos_vports_node_update_parent(struct mlx5_esw_sched_node *node, struct mlx5_esw_sched_node *parent, struct netlink_ext_ack *extack) @@ -1094,7 +2061,13 @@ static int mlx5_esw_qos_node_update_parent(struct mlx5_esw_sched_node *node, esw_qos_lock(esw); curr_parent = node->parent; - err = esw_qos_vports_node_update_parent(node, parent, extack); + if (node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) { + err = esw_qos_tc_arbiter_node_update_parent(node, parent, + extack); + } else { + err = esw_qos_vports_node_update_parent(node, parent, extack); + } + if (err) goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h index ed40ec8f027e..0a50982b0e27 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h @@ -21,6 +21,14 @@ int mlx5_esw_devlink_rate_leaf_tx_share_set(struct devlink_rate *rate_leaf, void u64 tx_share, struct netlink_ext_ack *extack); int mlx5_esw_devlink_rate_leaf_tx_max_set(struct devlink_rate *rate_leaf, void *priv, u64 tx_max, struct netlink_ext_ack *extack); +int mlx5_esw_devlink_rate_leaf_tc_bw_set(struct devlink_rate *rate_node, + void *priv, + u32 *tc_bw, + struct netlink_ext_ack *extack); +int mlx5_esw_devlink_rate_node_tc_bw_set(struct devlink_rate *rate_node, + void *priv, + u32 *tc_bw, + struct netlink_ext_ack *extack); int mlx5_esw_devlink_rate_node_tx_share_set(struct devlink_rate *rate_node, void *priv, u64 tx_share, struct netlink_ext_ack *extack); int mlx5_esw_devlink_rate_node_tx_max_set(struct devlink_rate *rate_node, void *priv, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 8573d36785f4..d59fdcb29cb8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -212,10 +212,20 @@ struct mlx5_vport { struct mlx5_vport_info info; - /* Protected with the E-Switch qos domain lock. */ + /* Protected with the E-Switch qos domain lock. The Vport QoS can + * either be disabled (sched_node is NULL) or in one of three states: + * 1. Regular QoS (sched_node is a vport node). + * 2. TC QoS enabled on the vport (sched_node is a TC arbiter). + * 3. TC QoS enabled on the vport's parent node + * (sched_node is a rate limit node). + * When TC is enabled in either mode, the vport owns vport TC scheduling + * nodes. + */ struct { - /* Vport scheduling element node. */ + /* Vport scheduling node. */ struct mlx5_esw_sched_node *sched_node; + /* Array of vport traffic class scheduling nodes. */ + struct mlx5_esw_sched_node **sched_nodes; } qos; u16 vport; diff --git a/drivers/net/ethernet/microsoft/Kconfig b/drivers/net/ethernet/microsoft/Kconfig index 901fbffbf718..3f36ee6a8ece 100644 --- a/drivers/net/ethernet/microsoft/Kconfig +++ b/drivers/net/ethernet/microsoft/Kconfig @@ -22,6 +22,7 @@ config MICROSOFT_MANA depends on PCI_HYPERV select AUXILIARY_BUS select PAGE_POOL + select NET_SHAPER help This driver supports Microsoft Azure Network Adapter (MANA). So far, the driver is only supported on X86_64. diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 55dd7dee718c..a468cd8e5f36 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -10,6 +10,7 @@ #include <linux/irqdomain.h> #include <net/mana/mana.h> +#include <net/mana/hw_channel.h> struct dentry *mana_debugfs_root; @@ -68,6 +69,24 @@ static void mana_gd_init_registers(struct pci_dev *pdev) mana_gd_init_vf_regs(pdev); } +/* Suppress logging when we set timeout to zero */ +bool mana_need_log(struct gdma_context *gc, int err) +{ + struct hw_channel_context *hwc; + + if (err != -ETIMEDOUT) + return true; + + if (!gc) + return true; + + hwc = gc->hwc.driver_data; + if (hwc && hwc->hwc_timeout == 0) + return false; + + return true; +} + static int mana_gd_query_max_resources(struct pci_dev *pdev) { struct gdma_context *gc = pci_get_drvdata(pdev); @@ -278,8 +297,9 @@ static int mana_gd_disable_queue(struct gdma_queue *queue) err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp); if (err || resp.hdr.status) { - dev_err(gc->dev, "Failed to disable queue: %d, 0x%x\n", err, - resp.hdr.status); + if (mana_need_log(gc, err)) + dev_err(gc->dev, "Failed to disable queue: %d, 0x%x\n", err, + resp.hdr.status); return err ? err : -EPROTO; } @@ -366,25 +386,12 @@ EXPORT_SYMBOL_NS(mana_gd_ring_cq, "NET_MANA"); #define MANA_SERVICE_PERIOD 10 -struct mana_serv_work { - struct work_struct serv_work; - struct pci_dev *pdev; -}; - -static void mana_serv_func(struct work_struct *w) +static void mana_serv_fpga(struct pci_dev *pdev) { - struct mana_serv_work *mns_wk; struct pci_bus *bus, *parent; - struct pci_dev *pdev; - - mns_wk = container_of(w, struct mana_serv_work, serv_work); - pdev = mns_wk->pdev; pci_lock_rescan_remove(); - if (!pdev) - goto out; - bus = pdev->bus; if (!bus) { dev_err(&pdev->dev, "MANA service: no bus\n"); @@ -405,7 +412,74 @@ static void mana_serv_func(struct work_struct *w) out: pci_unlock_rescan_remove(); +} + +static void mana_serv_reset(struct pci_dev *pdev) +{ + struct gdma_context *gc = pci_get_drvdata(pdev); + struct hw_channel_context *hwc; + + if (!gc) { + dev_err(&pdev->dev, "MANA service: no GC\n"); + return; + } + + hwc = gc->hwc.driver_data; + if (!hwc) { + dev_err(&pdev->dev, "MANA service: no HWC\n"); + goto out; + } + + /* HWC is not responding in this case, so don't wait */ + hwc->hwc_timeout = 0; + + dev_info(&pdev->dev, "MANA reset cycle start\n"); + mana_gd_suspend(pdev, PMSG_SUSPEND); + + msleep(MANA_SERVICE_PERIOD * 1000); + + mana_gd_resume(pdev); + + dev_info(&pdev->dev, "MANA reset cycle completed\n"); + +out: + gc->in_service = false; +} + +struct mana_serv_work { + struct work_struct serv_work; + struct pci_dev *pdev; + enum gdma_eqe_type type; +}; + +static void mana_serv_func(struct work_struct *w) +{ + struct mana_serv_work *mns_wk; + struct pci_dev *pdev; + + mns_wk = container_of(w, struct mana_serv_work, serv_work); + pdev = mns_wk->pdev; + + if (!pdev) + goto out; + + switch (mns_wk->type) { + case GDMA_EQE_HWC_FPGA_RECONFIG: + mana_serv_fpga(pdev); + break; + + case GDMA_EQE_HWC_RESET_REQUEST: + mana_serv_reset(pdev); + break; + + default: + dev_err(&pdev->dev, "MANA service: unknown type %d\n", + mns_wk->type); + break; + } + +out: pci_dev_put(pdev); kfree(mns_wk); module_put(THIS_MODULE); @@ -462,6 +536,7 @@ static void mana_gd_process_eqe(struct gdma_queue *eq) break; case GDMA_EQE_HWC_FPGA_RECONFIG: + case GDMA_EQE_HWC_RESET_REQUEST: dev_info(gc->dev, "Recv MANA service type:%d\n", type); if (gc->in_service) { @@ -483,6 +558,7 @@ static void mana_gd_process_eqe(struct gdma_queue *eq) dev_info(gc->dev, "Start MANA service type:%d\n", type); gc->in_service = true; mns_wk->pdev = to_pci_dev(gc->dev); + mns_wk->type = type; pci_dev_get(mns_wk->pdev); INIT_WORK(&mns_wk->serv_work, mana_serv_func); schedule_work(&mns_wk->serv_work); @@ -634,7 +710,8 @@ int mana_gd_test_eq(struct gdma_context *gc, struct gdma_queue *eq) err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp); if (err) { - dev_err(dev, "test_eq failed: %d\n", err); + if (mana_need_log(gc, err)) + dev_err(dev, "test_eq failed: %d\n", err); goto out; } @@ -669,7 +746,7 @@ static void mana_gd_destroy_eq(struct gdma_context *gc, bool flush_evenets, if (flush_evenets) { err = mana_gd_test_eq(gc, queue); - if (err) + if (err && mana_need_log(gc, err)) dev_warn(gc->dev, "Failed to flush EQ: %d\n", err); } @@ -815,8 +892,9 @@ int mana_gd_destroy_dma_region(struct gdma_context *gc, u64 dma_region_handle) err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp); if (err || resp.hdr.status) { - dev_err(gc->dev, "Failed to destroy DMA region: %d, 0x%x\n", - err, resp.hdr.status); + if (mana_need_log(gc, err)) + dev_err(gc->dev, "Failed to destroy DMA region: %d, 0x%x\n", + err, resp.hdr.status); return -EPROTO; } @@ -1116,8 +1194,9 @@ int mana_gd_deregister_device(struct gdma_dev *gd) err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp); if (err || resp.hdr.status) { - dev_err(gc->dev, "Failed to deregister device: %d, 0x%x\n", - err, resp.hdr.status); + if (mana_need_log(gc, err)) + dev_err(gc->dev, "Failed to deregister device: %d, 0x%x\n", + err, resp.hdr.status); if (!err) err = -EPROTO; } @@ -1915,7 +1994,7 @@ static void mana_gd_remove(struct pci_dev *pdev) } /* The 'state' parameter is not used. */ -static int mana_gd_suspend(struct pci_dev *pdev, pm_message_t state) +int mana_gd_suspend(struct pci_dev *pdev, pm_message_t state) { struct gdma_context *gc = pci_get_drvdata(pdev); @@ -1931,7 +2010,7 @@ static int mana_gd_suspend(struct pci_dev *pdev, pm_message_t state) * fail -- if this happens, it's safer to just report an error than try to undo * what has been done. */ -static int mana_gd_resume(struct pci_dev *pdev) +int mana_gd_resume(struct pci_dev *pdev) { struct gdma_context *gc = pci_get_drvdata(pdev); int err; diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index 650d22654d49..ef072e24c46d 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -880,7 +880,9 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len, if (!wait_for_completion_timeout(&ctx->comp_event, (msecs_to_jiffies(hwc->hwc_timeout)))) { - dev_err(hwc->dev, "HWC: Request timed out!\n"); + if (hwc->hwc_timeout != 0) + dev_err(hwc->dev, "HWC: Request timed out!\n"); + err = -ETIMEDOUT; goto out; } diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 016fd808ccad..a7973651ae51 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -47,6 +47,15 @@ static const struct file_operations mana_dbg_q_fops = { .read = mana_dbg_q_read, }; +static bool mana_en_need_log(struct mana_port_context *apc, int err) +{ + if (apc && apc->ac && apc->ac->gdma_dev && + apc->ac->gdma_dev->gdma_context) + return mana_need_log(apc->ac->gdma_dev->gdma_context, err); + else + return true; +} + /* Microsoft Azure Network Adapter (MANA) functions */ static int mana_open(struct net_device *ndev) @@ -854,7 +863,8 @@ static int mana_send_request(struct mana_context *ac, void *in_buf, if (err == -EOPNOTSUPP) return err; - if (req->req.msg_type != MANA_QUERY_PHY_STAT) + if (req->req.msg_type != MANA_QUERY_PHY_STAT && + mana_need_log(gc, err)) dev_err(dev, "Failed to send mana message: %d, 0x%x\n", err, resp->status); return err ? err : -EPROTO; @@ -931,8 +941,10 @@ static void mana_pf_deregister_hw_vport(struct mana_port_context *apc) err = mana_send_request(apc->ac, &req, sizeof(req), &resp, sizeof(resp)); if (err) { - netdev_err(apc->ndev, "Failed to unregister hw vPort: %d\n", - err); + if (mana_en_need_log(apc, err)) + netdev_err(apc->ndev, "Failed to unregister hw vPort: %d\n", + err); + return; } @@ -987,8 +999,10 @@ static void mana_pf_deregister_filter(struct mana_port_context *apc) err = mana_send_request(apc->ac, &req, sizeof(req), &resp, sizeof(resp)); if (err) { - netdev_err(apc->ndev, "Failed to unregister filter: %d\n", - err); + if (mana_en_need_log(apc, err)) + netdev_err(apc->ndev, "Failed to unregister filter: %d\n", + err); + return; } @@ -1218,7 +1232,9 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc, err = mana_send_request(apc->ac, req, req_buf_size, &resp, sizeof(resp)); if (err) { - netdev_err(ndev, "Failed to configure vPort RX: %d\n", err); + if (mana_en_need_log(apc, err)) + netdev_err(ndev, "Failed to configure vPort RX: %d\n", err); + goto out; } @@ -1402,7 +1418,9 @@ void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, err = mana_send_request(apc->ac, &req, sizeof(req), &resp, sizeof(resp)); if (err) { - netdev_err(ndev, "Failed to destroy WQ object: %d\n", err); + if (mana_en_need_log(apc, err)) + netdev_err(ndev, "Failed to destroy WQ object: %d\n", err); + return; } @@ -3067,11 +3085,10 @@ static int mana_dealloc_queues(struct net_device *ndev) apc->rss_state = TRI_STATE_FALSE; err = mana_config_rss(apc, TRI_STATE_FALSE, false, false); - if (err) { + if (err && mana_en_need_log(apc, err)) netdev_err(ndev, "Failed to disable vPort: %d\n", err); - return err; - } + /* Even in err case, still need to cleanup the vPort */ mana_destroy_vport(apc); return 0; diff --git a/drivers/net/ethernet/sfc/ethtool_common.c b/drivers/net/ethernet/sfc/ethtool_common.c index 823263969f92..fa303e171d98 100644 --- a/drivers/net/ethernet/sfc/ethtool_common.c +++ b/drivers/net/ethernet/sfc/ethtool_common.c @@ -810,13 +810,10 @@ int efx_ethtool_get_rxfh_fields(struct net_device *net_dev, ctx = &efx->rss_context.priv; - mutex_lock(&net_dev->ethtool->rss_lock); if (info->rss_context) { ctx = efx_find_rss_context_entry(efx, info->rss_context); - if (!ctx) { - rc = -ENOENT; - goto out_unlock; - } + if (!ctx) + return -ENOENT; } data = 0; @@ -850,8 +847,6 @@ int efx_ethtool_get_rxfh_fields(struct net_device *net_dev, } out_setdata_unlock: info->data = data; -out_unlock: - mutex_unlock(&net_dev->ethtool->rss_lock); return rc; } diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 5c0f306fb019..b98c259f672d 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -404,7 +404,6 @@ struct efx_rx_page_state { * @old_rx_packets: Value of @rx_packets as of last efx_init_rx_queue() * @old_rx_bytes: Value of @rx_bytes as of last efx_init_rx_queue() * @xdp_rxq_info: XDP specific RX queue information. - * @xdp_rxq_info_valid: Is xdp_rxq_info valid data?. */ struct efx_rx_queue { struct efx_nic *efx; @@ -443,7 +442,6 @@ struct efx_rx_queue { unsigned long old_rx_packets; unsigned long old_rx_bytes; struct xdp_rxq_info xdp_rxq_info; - bool xdp_rxq_info_valid; }; enum efx_sync_events_state { diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index f4f75299dfa9..5306f4c44be4 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -269,8 +269,6 @@ void efx_init_rx_queue(struct efx_rx_queue *rx_queue) "Failure to initialise XDP queue information rc=%d\n", rc); efx->xdp_rxq_info_failed = true; - } else { - rx_queue->xdp_rxq_info_valid = true; } /* Set up RX descriptor ring */ @@ -302,10 +300,8 @@ void efx_fini_rx_queue(struct efx_rx_queue *rx_queue) efx_fini_rx_recycle_ring(rx_queue); - if (rx_queue->xdp_rxq_info_valid) + if (xdp_rxq_info_is_reg(&rx_queue->xdp_rxq_info)) xdp_rxq_info_unreg(&rx_queue->xdp_rxq_info); - - rx_queue->xdp_rxq_info_valid = false; } void efx_remove_rx_queue(struct efx_rx_queue *rx_queue) diff --git a/drivers/net/ethernet/sfc/siena/net_driver.h b/drivers/net/ethernet/sfc/siena/net_driver.h index 2be3bad3c993..4cf556782133 100644 --- a/drivers/net/ethernet/sfc/siena/net_driver.h +++ b/drivers/net/ethernet/sfc/siena/net_driver.h @@ -384,7 +384,6 @@ struct efx_rx_page_state { * @recycle_count: RX buffer recycle counter. * @slow_fill: Timer used to defer efx_nic_generate_fill_event(). * @xdp_rxq_info: XDP specific RX queue information. - * @xdp_rxq_info_valid: Is xdp_rxq_info valid data?. */ struct efx_rx_queue { struct efx_nic *efx; @@ -417,7 +416,6 @@ struct efx_rx_queue { /* Statistics to supplement MAC stats */ unsigned long rx_packets; struct xdp_rxq_info xdp_rxq_info; - bool xdp_rxq_info_valid; }; enum efx_sync_events_state { diff --git a/drivers/net/ethernet/sfc/siena/rx_common.c b/drivers/net/ethernet/sfc/siena/rx_common.c index 98d27174015d..4ae09505e417 100644 --- a/drivers/net/ethernet/sfc/siena/rx_common.c +++ b/drivers/net/ethernet/sfc/siena/rx_common.c @@ -268,8 +268,6 @@ void efx_siena_init_rx_queue(struct efx_rx_queue *rx_queue) "Failure to initialise XDP queue information rc=%d\n", rc); efx->xdp_rxq_info_failed = true; - } else { - rx_queue->xdp_rxq_info_valid = true; } /* Set up RX descriptor ring */ @@ -299,10 +297,8 @@ void efx_siena_fini_rx_queue(struct efx_rx_queue *rx_queue) efx_fini_rx_recycle_ring(rx_queue); - if (rx_queue->xdp_rxq_info_valid) + if (xdp_rxq_info_is_reg(&rx_queue->xdp_rxq_info)) xdp_rxq_info_unreg(&rx_queue->xdp_rxq_info); - - rx_queue->xdp_rxq_info_valid = false; } void efx_siena_remove_rx_queue(struct efx_rx_queue *rx_queue) diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 75d7e10944d4..67625fb12101 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -3336,7 +3336,7 @@ static int niu_rbr_add_page(struct niu *np, struct rx_ring_info *rp, addr = np->ops->map_page(np->device, page, 0, PAGE_SIZE, DMA_FROM_DEVICE); - if (!addr) { + if (np->ops->mapping_error(np->device, addr)) { __free_page(page); return -ENOMEM; } @@ -6676,6 +6676,8 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb, len = skb_headlen(skb); mapping = np->ops->map_single(np->device, skb->data, len, DMA_TO_DEVICE); + if (np->ops->mapping_error(np->device, mapping)) + goto out_drop; prod = rp->prod; @@ -6717,6 +6719,8 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb, mapping = np->ops->map_page(np->device, skb_frag_page(frag), skb_frag_off(frag), len, DMA_TO_DEVICE); + if (np->ops->mapping_error(np->device, mapping)) + goto out_unmap; rp->tx_buffs[prod].skb = NULL; rp->tx_buffs[prod].mapping = mapping; @@ -6741,6 +6745,19 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb, out: return NETDEV_TX_OK; +out_unmap: + while (i--) { + const skb_frag_t *frag; + + prod = PREVIOUS_TX(rp, prod); + frag = &skb_shinfo(skb)->frags[i]; + np->ops->unmap_page(np->device, rp->tx_buffs[prod].mapping, + skb_frag_size(frag), DMA_TO_DEVICE); + } + + np->ops->unmap_single(np->device, rp->tx_buffs[rp->prod].mapping, + skb_headlen(skb), DMA_TO_DEVICE); + out_drop: rp->tx_errors++; kfree_skb(skb); @@ -9645,6 +9662,11 @@ static void niu_pci_unmap_single(struct device *dev, u64 dma_address, dma_unmap_single(dev, dma_address, size, direction); } +static int niu_pci_mapping_error(struct device *dev, u64 addr) +{ + return dma_mapping_error(dev, addr); +} + static const struct niu_ops niu_pci_ops = { .alloc_coherent = niu_pci_alloc_coherent, .free_coherent = niu_pci_free_coherent, @@ -9652,6 +9674,7 @@ static const struct niu_ops niu_pci_ops = { .unmap_page = niu_pci_unmap_page, .map_single = niu_pci_map_single, .unmap_single = niu_pci_unmap_single, + .mapping_error = niu_pci_mapping_error, }; static void niu_driver_version(void) @@ -10020,6 +10043,11 @@ static void niu_phys_unmap_single(struct device *dev, u64 dma_address, /* Nothing to do. */ } +static int niu_phys_mapping_error(struct device *dev, u64 dma_address) +{ + return false; +} + static const struct niu_ops niu_phys_ops = { .alloc_coherent = niu_phys_alloc_coherent, .free_coherent = niu_phys_free_coherent, @@ -10027,6 +10055,7 @@ static const struct niu_ops niu_phys_ops = { .unmap_page = niu_phys_unmap_page, .map_single = niu_phys_map_single, .unmap_single = niu_phys_unmap_single, + .mapping_error = niu_phys_mapping_error, }; static int niu_of_probe(struct platform_device *op) diff --git a/drivers/net/ethernet/sun/niu.h b/drivers/net/ethernet/sun/niu.h index 04c215f91fc0..0b169c08b0f2 100644 --- a/drivers/net/ethernet/sun/niu.h +++ b/drivers/net/ethernet/sun/niu.h @@ -2879,6 +2879,9 @@ struct tx_ring_info { #define NEXT_TX(tp, index) \ (((index) + 1) < (tp)->pending ? ((index) + 1) : 0) +#define PREVIOUS_TX(tp, index) \ + (((index) - 1) >= 0 ? ((index) - 1) : (((tp)->pending) - 1)) + static inline u32 niu_tx_avail(struct tx_ring_info *tp) { return (tp->pending - @@ -3140,6 +3143,7 @@ struct niu_ops { enum dma_data_direction direction); void (*unmap_single)(struct device *dev, u64 dma_address, size_t size, enum dma_data_direction direction); + int (*mapping_error)(struct device *dev, u64 dma_address); }; struct niu_link_config { diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c index c57cc4f27249..55e252789db3 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -1705,6 +1705,7 @@ static void wx_set_rss_queues(struct wx *wx) clear_bit(WX_FLAG_FDIR_HASH, wx->flags); + wx->ring_feature[RING_F_FDIR].indices = 1; /* Use Flow Director in addition to RSS to ensure the best * distribution of flows across cores, even when an FDIR flow * isn't matched. @@ -1746,7 +1747,7 @@ static void wx_set_num_queues(struct wx *wx) */ static int wx_acquire_msix_vectors(struct wx *wx) { - struct irq_affinity affd = { .pre_vectors = 1 }; + struct irq_affinity affd = { .post_vectors = 1 }; int nvecs, i; /* We start by asking for one vector per queue pair */ @@ -1783,16 +1784,24 @@ static int wx_acquire_msix_vectors(struct wx *wx) return nvecs; } - wx->msix_entry->entry = 0; - wx->msix_entry->vector = pci_irq_vector(wx->pdev, 0); nvecs -= 1; for (i = 0; i < nvecs; i++) { wx->msix_q_entries[i].entry = i; - wx->msix_q_entries[i].vector = pci_irq_vector(wx->pdev, i + 1); + wx->msix_q_entries[i].vector = pci_irq_vector(wx->pdev, i); } wx->num_q_vectors = nvecs; + wx->msix_entry->entry = nvecs; + wx->msix_entry->vector = pci_irq_vector(wx->pdev, nvecs); + + if (test_bit(WX_FLAG_IRQ_VECTOR_SHARED, wx->flags)) { + wx->msix_entry->entry = 0; + wx->msix_entry->vector = pci_irq_vector(wx->pdev, 0); + wx->msix_q_entries[0].entry = 0; + wx->msix_q_entries[0].vector = pci_irq_vector(wx->pdev, 1); + } + return 0; } @@ -2291,6 +2300,8 @@ static void wx_set_ivar(struct wx *wx, s8 direction, if (direction == -1) { /* other causes */ + if (test_bit(WX_FLAG_IRQ_VECTOR_SHARED, wx->flags)) + msix_vector = 0; msix_vector |= WX_PX_IVAR_ALLOC_VAL; index = 0; ivar = rd32(wx, WX_PX_MISC_IVAR); @@ -2299,8 +2310,6 @@ static void wx_set_ivar(struct wx *wx, s8 direction, wr32(wx, WX_PX_MISC_IVAR, ivar); } else { /* tx or rx causes */ - if (!(wx->mac.type == wx_mac_em && wx->num_vfs == 7)) - msix_vector += 1; /* offset for queue vectors */ msix_vector |= WX_PX_IVAR_ALLOC_VAL; index = ((16 * (queue & 1)) + (8 * direction)); ivar = rd32(wx, WX_PX_IVAR(queue >> 1)); @@ -2339,7 +2348,7 @@ void wx_write_eitr(struct wx_q_vector *q_vector) itr_reg |= WX_PX_ITR_CNT_WDIS; - wr32(wx, WX_PX_ITR(v_idx + 1), itr_reg); + wr32(wx, WX_PX_ITR(v_idx), itr_reg); } /** @@ -2392,9 +2401,9 @@ void wx_configure_vectors(struct wx *wx) wx_write_eitr(q_vector); } - wx_set_ivar(wx, -1, 0, 0); + wx_set_ivar(wx, -1, 0, v_idx); if (pdev->msix_enabled) - wr32(wx, WX_PX_ITR(0), 1950); + wr32(wx, WX_PX_ITR(v_idx), 1950); } EXPORT_SYMBOL(wx_configure_vectors); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_sriov.c b/drivers/net/ethernet/wangxun/libwx/wx_sriov.c index e8656d9d733b..c82ae137756c 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_sriov.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_sriov.c @@ -64,6 +64,7 @@ static void wx_sriov_clear_data(struct wx *wx) wr32m(wx, WX_PSR_VM_CTL, WX_PSR_VM_CTL_POOL_MASK, 0); wx->ring_feature[RING_F_VMDQ].offset = 0; + clear_bit(WX_FLAG_IRQ_VECTOR_SHARED, wx->flags); clear_bit(WX_FLAG_SRIOV_ENABLED, wx->flags); /* Disable VMDq flag so device will be set in NM mode */ if (wx->ring_feature[RING_F_VMDQ].limit == 1) @@ -78,6 +79,9 @@ static int __wx_enable_sriov(struct wx *wx, u8 num_vfs) set_bit(WX_FLAG_SRIOV_ENABLED, wx->flags); dev_info(&wx->pdev->dev, "SR-IOV enabled with %d VFs\n", num_vfs); + if (num_vfs == 7 && wx->mac.type == wx_mac_em) + set_bit(WX_FLAG_IRQ_VECTOR_SHARED, wx->flags); + /* Enable VMDq flag so device will be set in VM mode */ set_bit(WX_FLAG_VMDQ_ENABLED, wx->flags); if (!wx->ring_feature[RING_F_VMDQ].limit) diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h index 7730c9fc3e02..c363379126c0 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_type.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h @@ -1191,6 +1191,7 @@ enum wx_pf_flags { WX_FLAG_VMDQ_ENABLED, WX_FLAG_VLAN_PROMISC, WX_FLAG_SRIOV_ENABLED, + WX_FLAG_IRQ_VECTOR_SHARED, WX_FLAG_FDIR_CAPABLE, WX_FLAG_FDIR_HASH, WX_FLAG_FDIR_PERFECT, @@ -1343,7 +1344,7 @@ struct wx { }; #define WX_INTR_ALL (~0ULL) -#define WX_INTR_Q(i) BIT((i) + 1) +#define WX_INTR_Q(i) BIT((i)) /* register operations */ #define wr32(a, reg, value) writel((value), ((a)->hw_addr + (reg))) diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c index b5022c49dc5e..e0fc897b0a58 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c @@ -161,7 +161,7 @@ static void ngbe_irq_enable(struct wx *wx, bool queues) if (queues) wx_intr_enable(wx, NGBE_INTR_ALL); else - wx_intr_enable(wx, NGBE_INTR_MISC); + wx_intr_enable(wx, NGBE_INTR_MISC(wx)); } /** @@ -286,7 +286,7 @@ static int ngbe_request_msix_irqs(struct wx *wx) * for queue. But when num_vfs == 7, vector[1] is assigned to vf6. * Misc and queue should reuse interrupt vector[0]. */ - if (wx->num_vfs == 7) + if (test_bit(WX_FLAG_IRQ_VECTOR_SHARED, wx->flags)) err = request_irq(wx->msix_entry->vector, ngbe_misc_and_queue, 0, netdev->name, wx); else diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h index bb74263f0498..3b2ca7f47e33 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h @@ -87,7 +87,7 @@ #define NGBE_PX_MISC_IC_TIMESYNC BIT(11) /* time sync */ #define NGBE_INTR_ALL 0x1FF -#define NGBE_INTR_MISC BIT(0) +#define NGBE_INTR_MISC(A) BIT((A)->msix_entry->entry) #define NGBE_PHY_CONFIG(reg_offset) (0x14000 + ((reg_offset) * 4)) #define NGBE_CFG_LAN_SPEED 0x14440 diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c index 7dbcf41750c1..dc87ccad9652 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c @@ -294,6 +294,7 @@ static void txgbe_mac_link_up_aml(struct phylink_config *config, wx_fc_enable(wx, tx_pause, rx_pause); txgbe_reconfig_mac(wx); + txgbe_enable_sec_tx_path(wx); txcfg = rd32(wx, TXGBE_AML_MAC_TX_CFG); txcfg &= ~TXGBE_AML_MAC_TX_CFG_SPEED_MASK; diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c index 20b9a28bcb55..3885283681ec 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c @@ -31,7 +31,7 @@ void txgbe_irq_enable(struct wx *wx, bool queues) wr32(wx, WX_PX_MISC_IEN, misc_ien); /* unmask interrupt */ - wx_intr_enable(wx, TXGBE_INTR_MISC); + wx_intr_enable(wx, TXGBE_INTR_MISC(wx)); if (queues) wx_intr_enable(wx, TXGBE_INTR_QALL(wx)); } @@ -78,7 +78,6 @@ free_queue_irqs: free_irq(wx->msix_q_entries[vector].vector, wx->q_vector[vector]); } - wx_reset_interrupt_capability(wx); return err; } @@ -132,7 +131,7 @@ static irqreturn_t txgbe_misc_irq_handle(int irq, void *data) txgbe->eicr = eicr; if (eicr & TXGBE_PX_MISC_IC_VF_MBOX) { wx_msg_task(txgbe->wx); - wx_intr_enable(wx, TXGBE_INTR_MISC); + wx_intr_enable(wx, TXGBE_INTR_MISC(wx)); } return IRQ_WAKE_THREAD; } @@ -184,7 +183,7 @@ static irqreturn_t txgbe_misc_irq_thread_fn(int irq, void *data) nhandled++; } - wx_intr_enable(wx, TXGBE_INTR_MISC); + wx_intr_enable(wx, TXGBE_INTR_MISC(wx)); return (nhandled > 0 ? IRQ_HANDLED : IRQ_NONE); } @@ -211,6 +210,7 @@ void txgbe_free_misc_irq(struct txgbe *txgbe) free_irq(txgbe->link_irq, txgbe); free_irq(txgbe->misc.irq, txgbe); txgbe_del_irq_domain(txgbe); + txgbe->wx->misc_irq_domain = false; } int txgbe_setup_misc_irq(struct txgbe *txgbe) diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c index f3d2778b8e35..a5867f3c93fc 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c @@ -458,10 +458,14 @@ static int txgbe_open(struct net_device *netdev) wx_configure(wx); - err = txgbe_request_queue_irqs(wx); + err = txgbe_setup_misc_irq(wx->priv); if (err) goto err_free_resources; + err = txgbe_request_queue_irqs(wx); + if (err) + goto err_free_misc_irq; + /* Notify the stack of the actual queue counts. */ err = netif_set_real_num_tx_queues(netdev, wx->num_tx_queues); if (err) @@ -479,6 +483,9 @@ static int txgbe_open(struct net_device *netdev) err_free_irq: wx_free_irq(wx); +err_free_misc_irq: + txgbe_free_misc_irq(wx->priv); + wx_reset_interrupt_capability(wx); err_free_resources: wx_free_resources(wx); err_reset: @@ -519,6 +526,7 @@ static int txgbe_close(struct net_device *netdev) wx_ptp_stop(wx); txgbe_down(wx); wx_free_irq(wx); + txgbe_free_misc_irq(wx->priv); wx_free_resources(wx); txgbe_fdir_filter_exit(wx); wx_control_hw(wx, false); @@ -564,7 +572,6 @@ static void txgbe_shutdown(struct pci_dev *pdev) int txgbe_setup_tc(struct net_device *dev, u8 tc) { struct wx *wx = netdev_priv(dev); - struct txgbe *txgbe = wx->priv; /* Hardware has to reinitialize queues and interrupts to * match packet buffer alignment. Unfortunately, the @@ -575,7 +582,6 @@ int txgbe_setup_tc(struct net_device *dev, u8 tc) else txgbe_reset(wx); - txgbe_free_misc_irq(txgbe); wx_clear_interrupt_scheme(wx); if (tc) @@ -584,7 +590,6 @@ int txgbe_setup_tc(struct net_device *dev, u8 tc) netdev_reset_tc(dev); wx_init_interrupt_scheme(wx); - txgbe_setup_misc_irq(txgbe); if (netif_running(dev)) txgbe_open(dev); @@ -882,13 +887,9 @@ static int txgbe_probe(struct pci_dev *pdev, txgbe_init_fdir(txgbe); - err = txgbe_setup_misc_irq(txgbe); - if (err) - goto err_release_hw; - err = txgbe_init_phy(txgbe); if (err) - goto err_free_misc_irq; + goto err_release_hw; err = register_netdev(netdev); if (err) @@ -916,8 +917,6 @@ static int txgbe_probe(struct pci_dev *pdev, err_remove_phy: txgbe_remove_phy(txgbe); -err_free_misc_irq: - txgbe_free_misc_irq(txgbe); err_release_hw: wx_clear_interrupt_scheme(wx); wx_control_hw(wx, false); @@ -957,7 +956,6 @@ static void txgbe_remove(struct pci_dev *pdev) unregister_netdev(netdev); txgbe_remove_phy(txgbe); - txgbe_free_misc_irq(txgbe); wx_free_isb_resources(wx); pci_release_selected_regions(pdev, diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h index 42ec815159e8..41915d7dd372 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h @@ -302,8 +302,8 @@ struct txgbe_fdir_filter { #define TXGBE_DEFAULT_RX_WORK 128 #endif -#define TXGBE_INTR_MISC BIT(0) -#define TXGBE_INTR_QALL(A) GENMASK((A)->num_q_vectors, 1) +#define TXGBE_INTR_MISC(A) BIT((A)->num_q_vectors) +#define TXGBE_INTR_QALL(A) (TXGBE_INTR_MISC(A) - 1) #define TXGBE_MAX_EITR GENMASK(11, 3) diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index 67424888ff0a..d3dc0914450a 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -333,6 +333,7 @@ static void ifb_setup(struct net_device *dev) dev->min_mtu = 0; dev->max_mtu = 0; + netif_set_tso_max_size(dev, GSO_MAX_SIZE); } static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev) diff --git a/drivers/net/mdio/Kconfig b/drivers/net/mdio/Kconfig index 7db40aaa079d..e1e32b687068 100644 --- a/drivers/net/mdio/Kconfig +++ b/drivers/net/mdio/Kconfig @@ -27,6 +27,13 @@ config ACPI_MDIO help ACPI MDIO bus (Ethernet PHY) accessors +config MDIO_AIROHA + tristate "Airoha AN7583 MDIO bus controller" + depends on ARCH_AIROHA || COMPILE_TEST + help + This module provides a driver for the MDIO busses found in the + Airoha AN7583 SoC's. + config MDIO_SUN4I tristate "Allwinner sun4i MDIO interface support" depends on ARCH_SUNXI || COMPILE_TEST diff --git a/drivers/net/mdio/Makefile b/drivers/net/mdio/Makefile index c23778e73890..fbec636700e7 100644 --- a/drivers/net/mdio/Makefile +++ b/drivers/net/mdio/Makefile @@ -5,6 +5,7 @@ obj-$(CONFIG_ACPI_MDIO) += acpi_mdio.o obj-$(CONFIG_FWNODE_MDIO) += fwnode_mdio.o obj-$(CONFIG_OF_MDIO) += of_mdio.o +obj-$(CONFIG_MDIO_AIROHA) += mdio-airoha.o obj-$(CONFIG_MDIO_ASPEED) += mdio-aspeed.o obj-$(CONFIG_MDIO_BCM_IPROC) += mdio-bcm-iproc.o obj-$(CONFIG_MDIO_BCM_UNIMAC) += mdio-bcm-unimac.o diff --git a/drivers/net/mdio/mdio-airoha.c b/drivers/net/mdio/mdio-airoha.c new file mode 100644 index 000000000000..1dc9939c8d7d --- /dev/null +++ b/drivers/net/mdio/mdio-airoha.c @@ -0,0 +1,276 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Airoha AN7583 MDIO interface driver + * + * Copyright (C) 2025 Christian Marangi <ansuelsmth@gmail.com> + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/kernel.h> +#include <linux/mfd/syscon.h> +#include <linux/module.h> +#include <linux/of_mdio.h> +#include <linux/of_address.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/reset.h> + +/* MII address register definitions */ +#define AN7583_MII_BUSY BIT(31) +#define AN7583_MII_RDY BIT(30) /* RO signal BUS is ready */ +#define AN7583_MII_CL22_REG_ADDR GENMASK(29, 25) +#define AN7583_MII_CL45_DEV_ADDR AN7583_MII_CL22_REG_ADDR +#define AN7583_MII_PHY_ADDR GENMASK(24, 20) +#define AN7583_MII_CMD GENMASK(19, 18) +#define AN7583_MII_CMD_CL22_WRITE FIELD_PREP_CONST(AN7583_MII_CMD, 0x1) +#define AN7583_MII_CMD_CL22_READ FIELD_PREP_CONST(AN7583_MII_CMD, 0x2) +#define AN7583_MII_CMD_CL45_ADDR FIELD_PREP_CONST(AN7583_MII_CMD, 0x0) +#define AN7583_MII_CMD_CL45_WRITE FIELD_PREP_CONST(AN7583_MII_CMD, 0x1) +#define AN7583_MII_CMD_CL45_POSTREAD_INCADDR FIELD_PREP_CONST(AN7583_MII_CMD, 0x2) +#define AN7583_MII_CMD_CL45_READ FIELD_PREP_CONST(AN7583_MII_CMD, 0x3) +#define AN7583_MII_ST GENMASK(17, 16) +#define AN7583_MII_ST_CL45 FIELD_PREP_CONST(AN7583_MII_ST, 0x0) +#define AN7583_MII_ST_CL22 FIELD_PREP_CONST(AN7583_MII_ST, 0x1) +#define AN7583_MII_RWDATA GENMASK(15, 0) +#define AN7583_MII_CL45_REG_ADDR AN7583_MII_RWDATA + +#define AN7583_MII_MDIO_DELAY_USEC 100 +#define AN7583_MII_MDIO_RETRY_MSEC 100 + +struct airoha_mdio_data { + u32 base_addr; + struct regmap *regmap; + struct clk *clk; + struct reset_control *reset; +}; + +static int airoha_mdio_wait_busy(struct airoha_mdio_data *priv) +{ + u32 busy; + + return regmap_read_poll_timeout(priv->regmap, priv->base_addr, busy, + !(busy & AN7583_MII_BUSY), + AN7583_MII_MDIO_DELAY_USEC, + AN7583_MII_MDIO_RETRY_MSEC * USEC_PER_MSEC); +} + +static void airoha_mdio_reset(struct airoha_mdio_data *priv) +{ + /* There seems to be Hardware bug where AN7583_MII_RWDATA + * is not wiped in the context of unconnected PHY and the + * previous read value is returned. + * + * Example: (only one PHY on the BUS at 0x1f) + * - read at 0x1f report at 0x2 0x7500 + * - read at 0x0 report 0x7500 on every address + * + * To workaround this, we reset the Mdio BUS at every read + * to have consistent values on read operation. + */ + reset_control_assert(priv->reset); + reset_control_deassert(priv->reset); +} + +static int airoha_mdio_read(struct mii_bus *bus, int addr, int regnum) +{ + struct airoha_mdio_data *priv = bus->priv; + u32 val; + int ret; + + airoha_mdio_reset(priv); + + val = AN7583_MII_BUSY | AN7583_MII_ST_CL22 | + AN7583_MII_CMD_CL22_READ; + val |= FIELD_PREP(AN7583_MII_PHY_ADDR, addr); + val |= FIELD_PREP(AN7583_MII_CL22_REG_ADDR, regnum); + + ret = regmap_write(priv->regmap, priv->base_addr, val); + if (ret) + return ret; + + ret = airoha_mdio_wait_busy(priv); + if (ret) + return ret; + + ret = regmap_read(priv->regmap, priv->base_addr, &val); + if (ret) + return ret; + + return FIELD_GET(AN7583_MII_RWDATA, val); +} + +static int airoha_mdio_write(struct mii_bus *bus, int addr, int regnum, + u16 value) +{ + struct airoha_mdio_data *priv = bus->priv; + u32 val; + int ret; + + val = AN7583_MII_BUSY | AN7583_MII_ST_CL22 | + AN7583_MII_CMD_CL22_WRITE; + val |= FIELD_PREP(AN7583_MII_PHY_ADDR, addr); + val |= FIELD_PREP(AN7583_MII_CL22_REG_ADDR, regnum); + val |= FIELD_PREP(AN7583_MII_RWDATA, value); + + ret = regmap_write(priv->regmap, priv->base_addr, val); + if (ret) + return ret; + + ret = airoha_mdio_wait_busy(priv); + + return ret; +} + +static int airoha_mdio_cl45_read(struct mii_bus *bus, int addr, int devnum, + int regnum) +{ + struct airoha_mdio_data *priv = bus->priv; + u32 val; + int ret; + + airoha_mdio_reset(priv); + + val = AN7583_MII_BUSY | AN7583_MII_ST_CL45 | + AN7583_MII_CMD_CL45_ADDR; + val |= FIELD_PREP(AN7583_MII_PHY_ADDR, addr); + val |= FIELD_PREP(AN7583_MII_CL45_DEV_ADDR, devnum); + val |= FIELD_PREP(AN7583_MII_CL45_REG_ADDR, regnum); + + ret = regmap_write(priv->regmap, priv->base_addr, val); + if (ret) + return ret; + + ret = airoha_mdio_wait_busy(priv); + if (ret) + return ret; + + val = AN7583_MII_BUSY | AN7583_MII_ST_CL45 | + AN7583_MII_CMD_CL45_READ; + val |= FIELD_PREP(AN7583_MII_PHY_ADDR, addr); + val |= FIELD_PREP(AN7583_MII_CL45_DEV_ADDR, devnum); + + ret = regmap_write(priv->regmap, priv->base_addr, val); + if (ret) + return ret; + + ret = airoha_mdio_wait_busy(priv); + if (ret) + return ret; + + ret = regmap_read(priv->regmap, priv->base_addr, &val); + if (ret) + return ret; + + return FIELD_GET(AN7583_MII_RWDATA, val); +} + +static int airoha_mdio_cl45_write(struct mii_bus *bus, int addr, int devnum, + int regnum, u16 value) +{ + struct airoha_mdio_data *priv = bus->priv; + u32 val; + int ret; + + val = AN7583_MII_BUSY | AN7583_MII_ST_CL45 | + AN7583_MII_CMD_CL45_ADDR; + val |= FIELD_PREP(AN7583_MII_PHY_ADDR, addr); + val |= FIELD_PREP(AN7583_MII_CL45_DEV_ADDR, devnum); + val |= FIELD_PREP(AN7583_MII_CL45_REG_ADDR, regnum); + + ret = regmap_write(priv->regmap, priv->base_addr, val); + if (ret) + return ret; + + ret = airoha_mdio_wait_busy(priv); + if (ret) + return ret; + + val = AN7583_MII_BUSY | AN7583_MII_ST_CL45 | + AN7583_MII_CMD_CL45_WRITE; + val |= FIELD_PREP(AN7583_MII_PHY_ADDR, addr); + val |= FIELD_PREP(AN7583_MII_CL45_DEV_ADDR, devnum); + val |= FIELD_PREP(AN7583_MII_RWDATA, value); + + ret = regmap_write(priv->regmap, priv->base_addr, val); + if (ret) + return ret; + + ret = airoha_mdio_wait_busy(priv); + + return ret; +} + +static int airoha_mdio_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct airoha_mdio_data *priv; + struct mii_bus *bus; + u32 addr, freq; + int ret; + + ret = of_property_read_u32(dev->of_node, "reg", &addr); + if (ret) + return ret; + + bus = devm_mdiobus_alloc_size(dev, sizeof(*priv)); + if (!bus) + return -ENOMEM; + + priv = bus->priv; + priv->base_addr = addr; + priv->regmap = device_node_to_regmap(dev->parent->of_node); + + priv->clk = devm_clk_get_enabled(dev, NULL); + if (IS_ERR(priv->clk)) + return PTR_ERR(priv->clk); + + priv->reset = devm_reset_control_get_exclusive(dev, NULL); + if (IS_ERR(priv->reset)) + return PTR_ERR(priv->reset); + + reset_control_deassert(priv->reset); + + bus->name = "airoha_mdio_bus"; + snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(dev)); + bus->parent = dev; + bus->read = airoha_mdio_read; + bus->write = airoha_mdio_write; + bus->read_c45 = airoha_mdio_cl45_read; + bus->write_c45 = airoha_mdio_cl45_write; + + /* Check if a custom frequency is defined in DT or default to 2.5 MHz */ + if (of_property_read_u32(dev->of_node, "clock-frequency", &freq)) + freq = 2500000; + + ret = clk_set_rate(priv->clk, freq); + if (ret) + return ret; + + ret = devm_of_mdiobus_register(dev, bus, dev->of_node); + if (ret) { + reset_control_assert(priv->reset); + return ret; + } + + return 0; +} + +static const struct of_device_id airoha_mdio_dt_ids[] = { + { .compatible = "airoha,an7583-mdio" }, + { } +}; +MODULE_DEVICE_TABLE(of, airoha_mdio_dt_ids); + +static struct platform_driver airoha_mdio_driver = { + .probe = airoha_mdio_probe, + .driver = { + .name = "airoha-mdio", + .of_match_table = airoha_mdio_dt_ids, + }, +}; + +module_platform_driver(airoha_mdio_driver); + +MODULE_DESCRIPTION("Airoha AN7583 MDIO interface driver"); +MODULE_AUTHOR("Christian Marangi <ansuelsmth@gmail.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 3e0b61202f0c..b3647691060c 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -388,6 +388,17 @@ static const struct file_operations nsim_dev_rate_parent_fops = { .owner = THIS_MODULE, }; +static void nsim_dev_tc_bw_debugfs_init(struct dentry *ddir, u32 *tc_bw) +{ + int i; + + for (i = 0; i < DEVLINK_RATE_TCS_MAX; i++) { + char name[16]; + + snprintf(name, sizeof(name), "tc%d_bw", i); + debugfs_create_u32(name, 0400, ddir, &tc_bw[i]); + } +} static int nsim_dev_port_debugfs_init(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port) { @@ -415,6 +426,8 @@ static int nsim_dev_port_debugfs_init(struct nsim_dev *nsim_dev, nsim_dev_port->ddir, &nsim_dev_port->parent_name, &nsim_dev_rate_parent_fops); + nsim_dev_tc_bw_debugfs_init(nsim_dev_port->ddir, + nsim_dev_port->tc_bw); } debugfs_create_symlink("dev", nsim_dev_port->ddir, dev_link_name); @@ -1172,6 +1185,19 @@ static int nsim_rate_bytes_to_units(char *name, u64 *rate, struct netlink_ext_ac return 0; } +static int nsim_leaf_tc_bw_set(struct devlink_rate *devlink_rate, + void *priv, u32 *tc_bw, + struct netlink_ext_ack *extack) +{ + struct nsim_dev_port *nsim_dev_port = priv; + int i; + + for (i = 0; i < DEVLINK_RATE_TCS_MAX; i++) + nsim_dev_port->tc_bw[i] = tc_bw[i]; + + return 0; +} + static int nsim_leaf_tx_share_set(struct devlink_rate *devlink_rate, void *priv, u64 tx_share, struct netlink_ext_ack *extack) { @@ -1210,8 +1236,21 @@ struct nsim_rate_node { char *parent_name; u16 tx_share; u16 tx_max; + u32 tc_bw[DEVLINK_RATE_TCS_MAX]; }; +static int nsim_node_tc_bw_set(struct devlink_rate *devlink_rate, void *priv, + u32 *tc_bw, struct netlink_ext_ack *extack) +{ + struct nsim_rate_node *nsim_node = priv; + int i; + + for (i = 0; i < DEVLINK_RATE_TCS_MAX; i++) + nsim_node->tc_bw[i] = tc_bw[i]; + + return 0; +} + static int nsim_node_tx_share_set(struct devlink_rate *devlink_rate, void *priv, u64 tx_share, struct netlink_ext_ack *extack) { @@ -1264,6 +1303,8 @@ static int nsim_rate_node_new(struct devlink_rate *node, void **priv, &nsim_node->parent_name, &nsim_dev_rate_parent_fops); + nsim_dev_tc_bw_debugfs_init(nsim_node->ddir, nsim_node->tc_bw); + *priv = nsim_node; return 0; } @@ -1340,8 +1381,10 @@ static const struct devlink_ops nsim_dev_devlink_ops = { .trap_policer_counter_get = nsim_dev_devlink_trap_policer_counter_get, .rate_leaf_tx_share_set = nsim_leaf_tx_share_set, .rate_leaf_tx_max_set = nsim_leaf_tx_max_set, + .rate_leaf_tc_bw_set = nsim_leaf_tc_bw_set, .rate_node_tx_share_set = nsim_node_tx_share_set, .rate_node_tx_max_set = nsim_node_tx_max_set, + .rate_node_tc_bw_set = nsim_node_tc_bw_set, .rate_node_new = nsim_rate_node_new, .rate_node_del = nsim_rate_node_del, .rate_leaf_parent_set = nsim_rate_leaf_parent_set, diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 4a0c48c7a384..809dd29fc5fe 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -276,6 +276,7 @@ struct nsim_dev_port { struct dentry *ddir; struct dentry *rate_parent; char *parent_name; + u32 tc_bw[DEVLINK_RATE_TCS_MAX]; struct netdevsim *ns; }; diff --git a/drivers/net/phy/air_en8811h.c b/drivers/net/phy/air_en8811h.c index 57fbd8df9438..badd65f0ccee 100644 --- a/drivers/net/phy/air_en8811h.c +++ b/drivers/net/phy/air_en8811h.c @@ -11,6 +11,7 @@ * Copyright (C) 2023 Airoha Technology Corp. */ +#include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/phy.h> #include <linux/firmware.h> @@ -157,6 +158,7 @@ struct en8811h_priv { struct led led[EN8811H_LED_COUNT]; struct clk_hw hw; struct phy_device *phydev; + unsigned int cko_is_enabled; }; enum { @@ -865,11 +867,30 @@ static int en8811h_clk_is_enabled(struct clk_hw *hw) return (pbus_value & EN8811H_CLK_CGM_CKO); } +static int en8811h_clk_save_context(struct clk_hw *hw) +{ + struct en8811h_priv *priv = clk_hw_to_en8811h_priv(hw); + + priv->cko_is_enabled = en8811h_clk_is_enabled(hw); + + return 0; +} + +static void en8811h_clk_restore_context(struct clk_hw *hw) +{ + struct en8811h_priv *priv = clk_hw_to_en8811h_priv(hw); + + if (!priv->cko_is_enabled) + en8811h_clk_disable(hw); +} + static const struct clk_ops en8811h_clk_ops = { - .recalc_rate = en8811h_clk_recalc_rate, - .enable = en8811h_clk_enable, - .disable = en8811h_clk_disable, - .is_enabled = en8811h_clk_is_enabled, + .recalc_rate = en8811h_clk_recalc_rate, + .enable = en8811h_clk_enable, + .disable = en8811h_clk_disable, + .is_enabled = en8811h_clk_is_enabled, + .save_context = en8811h_clk_save_context, + .restore_context = en8811h_clk_restore_context, }; static int en8811h_clk_provider_setup(struct device *dev, struct clk_hw *hw) @@ -1149,6 +1170,20 @@ static irqreturn_t en8811h_handle_interrupt(struct phy_device *phydev) return IRQ_HANDLED; } +static int en8811h_resume(struct phy_device *phydev) +{ + clk_restore_context(); + + return genphy_resume(phydev); +} + +static int en8811h_suspend(struct phy_device *phydev) +{ + clk_save_context(); + + return genphy_suspend(phydev); +} + static struct phy_driver en8811h_driver[] = { { PHY_ID_MATCH_MODEL(EN8811H_PHY_ID), @@ -1159,6 +1194,8 @@ static struct phy_driver en8811h_driver[] = { .get_rate_matching = en8811h_get_rate_matching, .config_aneg = en8811h_config_aneg, .read_status = en8811h_read_status, + .resume = en8811h_resume, + .suspend = en8811h_suspend, .config_intr = en8811h_clear_intr, .handle_interrupt = en8811h_handle_interrupt, .led_hw_is_supported = en8811h_led_hw_is_supported, diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index d0429dc8f561..74fd6ff32c6c 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -2173,6 +2173,136 @@ static void kszphy_get_phy_stats(struct phy_device *phydev, stats->rx_errors = priv->phy_stats.rx_err_pkt_cnt; } +/* Base register for Signal Quality Indicator (SQI) - Channel A + * + * MMD Address: MDIO_MMD_PMAPMD (0x01) + * Register: 0xAC (Channel A) + * Each channel (pair) has its own register: + * Channel A: 0xAC + * Channel B: 0xAD + * Channel C: 0xAE + * Channel D: 0xAF + */ +#define KSZ9477_MMD_SIGNAL_QUALITY_CHAN_A 0xac + +/* SQI field mask for bits [14:8] + * + * SQI indicates relative quality of the signal. + * A lower value indicates better signal quality. + */ +#define KSZ9477_MMD_SQI_MASK GENMASK(14, 8) + +#define KSZ9477_MAX_CHANNELS 4 +#define KSZ9477_SQI_MAX 7 + +/* Number of SQI samples to average for a stable result. + * + * Reference: KSZ9477S Datasheet DS00002392C, Section 4.1.11 (page 26) + * For noisy environments, a minimum of 30–50 readings is recommended. + */ +#define KSZ9477_SQI_SAMPLE_COUNT 40 + +/* The hardware SQI register provides a raw value from 0-127, where a lower + * value indicates better signal quality. However, empirical testing has + * shown that only the 0-7 range is relevant for a functional link. A raw + * value of 8 or higher was measured directly before link drop. This aligns + * with the OPEN Alliance recommendation that SQI=0 should represent the + * pre-failure state. + * + * This table provides a non-linear mapping from the useful raw hardware + * values (0-7) to the standard 0-7 SQI scale, where higher is better. + */ +static const u8 ksz_sqi_mapping[] = { + 7, /* raw 0 -> SQI 7 */ + 7, /* raw 1 -> SQI 7 */ + 6, /* raw 2 -> SQI 6 */ + 5, /* raw 3 -> SQI 5 */ + 4, /* raw 4 -> SQI 4 */ + 3, /* raw 5 -> SQI 3 */ + 2, /* raw 6 -> SQI 2 */ + 1, /* raw 7 -> SQI 1 */ +}; + +/** + * kszphy_get_sqi - Read, average, and map Signal Quality Index (SQI) + * @phydev: the PHY device + * + * This function reads and processes the raw Signal Quality Index from the + * PHY. Based on empirical testing, a raw value of 8 or higher indicates a + * pre-failure state and is mapped to SQI 0. Raw values from 0-7 are + * mapped to the standard 0-7 SQI scale via a lookup table. + * + * Return: SQI value (0–7), or a negative errno on failure. + */ +static int kszphy_get_sqi(struct phy_device *phydev) +{ + int sum[KSZ9477_MAX_CHANNELS] = { 0 }; + int worst_sqi = KSZ9477_SQI_MAX; + int i, val, raw_sqi, ch; + u8 channels; + + /* Determine applicable channels based on link speed */ + if (phydev->speed == SPEED_1000) + channels = 4; + else if (phydev->speed == SPEED_100) + channels = 1; + else + return -EOPNOTSUPP; + + /* Sample and accumulate SQI readings for each pair (currently only one). + * + * Reference: KSZ9477S Datasheet DS00002392C, Section 4.1.11 (page 26) + * - The SQI register is updated every 2 µs. + * - Values may fluctuate significantly, even in low-noise environments. + * - For reliable estimation, average a minimum of 30–50 samples + * (recommended for noisy environments) + * - In noisy environments, individual readings are highly unreliable. + * + * We use 40 samples per pair with a delay of 3 µs between each + * read to ensure new values are captured (2 µs update interval). + */ + for (i = 0; i < KSZ9477_SQI_SAMPLE_COUNT; i++) { + for (ch = 0; ch < channels; ch++) { + val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, + KSZ9477_MMD_SIGNAL_QUALITY_CHAN_A + ch); + if (val < 0) + return val; + + raw_sqi = FIELD_GET(KSZ9477_MMD_SQI_MASK, val); + sum[ch] += raw_sqi; + + /* We communicate with the PHY via MDIO via SPI or + * I2C, which is relatively slow. At least slower than + * the update interval of the SQI register. + * So, we can skip the delay between reads. + */ + } + } + + /* Calculate average for each channel and find the worst SQI */ + for (ch = 0; ch < channels; ch++) { + int avg_raw_sqi = sum[ch] / KSZ9477_SQI_SAMPLE_COUNT; + int mapped_sqi; + + /* Handle the pre-fail/failed state first. */ + if (avg_raw_sqi >= ARRAY_SIZE(ksz_sqi_mapping)) + mapped_sqi = 0; + else + /* Use the lookup table for the good signal range. */ + mapped_sqi = ksz_sqi_mapping[avg_raw_sqi]; + + if (mapped_sqi < worst_sqi) + worst_sqi = mapped_sqi; + } + + return worst_sqi; +} + +static int kszphy_get_sqi_max(struct phy_device *phydev) +{ + return KSZ9477_SQI_MAX; +} + static void kszphy_enable_clk(struct phy_device *phydev) { struct kszphy_priv *priv = phydev->priv; @@ -5801,6 +5931,8 @@ static struct phy_driver ksphy_driver[] = { .update_stats = kszphy_update_stats, .cable_test_start = ksz9x31_cable_test_start, .cable_test_get_status = ksz9x31_cable_test_get_status, + .get_sqi = kszphy_get_sqi, + .get_sqi_max = kszphy_get_sqi_max, } }; module_phy_driver(ksphy_driver); diff --git a/drivers/net/tap.c b/drivers/net/tap.c index bdf0788d8e66..d82eb7276a8b 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -1044,9 +1044,8 @@ static const struct file_operations tap_fops = { static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp) { - struct tun_xdp_hdr *hdr = xdp->data_hard_start; - struct virtio_net_hdr *gso = &hdr->gso; - int buflen = hdr->buflen; + struct virtio_net_hdr *gso = xdp->data_hard_start; + int buflen = xdp->frame_sz; int vnet_hdr_len = 0; struct tap_dev *tap; struct sk_buff *skb; diff --git a/drivers/net/thunderbolt/main.c b/drivers/net/thunderbolt/main.c index 0a53ec293d04..dcaa62377808 100644 --- a/drivers/net/thunderbolt/main.c +++ b/drivers/net/thunderbolt/main.c @@ -396,9 +396,9 @@ static void tbnet_tear_down(struct tbnet *net, bool send_logout) ret = tb_xdomain_disable_paths(net->xd, net->local_transmit_path, - net->rx_ring.ring->hop, + net->tx_ring.ring->hop, net->remote_transmit_path, - net->tx_ring.ring->hop); + net->rx_ring.ring->hop); if (ret) netdev_warn(net->dev, "failed to disable DMA paths\n"); @@ -662,9 +662,9 @@ static void tbnet_connected_work(struct work_struct *work) goto err_free_rx_buffers; ret = tb_xdomain_enable_paths(net->xd, net->local_transmit_path, - net->rx_ring.ring->hop, + net->tx_ring.ring->hop, net->remote_transmit_path, - net->tx_ring.ring->hop); + net->rx_ring.ring->hop); if (ret) { netdev_err(net->dev, "failed to enable DMA paths\n"); goto err_free_tx_buffers; @@ -924,8 +924,12 @@ static int tbnet_open(struct net_device *dev) netif_carrier_off(dev); - ring = tb_ring_alloc_tx(xd->tb->nhi, -1, TBNET_RING_SIZE, - RING_FLAG_FRAME); + flags = RING_FLAG_FRAME; + /* Only enable full E2E if the other end supports it too */ + if (tbnet_e2e && net->svc->prtcstns & TBNET_E2E) + flags |= RING_FLAG_E2E; + + ring = tb_ring_alloc_tx(xd->tb->nhi, -1, TBNET_RING_SIZE, flags); if (!ring) { netdev_err(dev, "failed to allocate Tx ring\n"); return -ENOMEM; @@ -944,11 +948,6 @@ static int tbnet_open(struct net_device *dev) sof_mask = BIT(TBIP_PDF_FRAME_START); eof_mask = BIT(TBIP_PDF_FRAME_END); - flags = RING_FLAG_FRAME; - /* Only enable full E2E if the other end supports it too */ - if (tbnet_e2e && net->svc->prtcstns & TBNET_E2E) - flags |= RING_FLAG_E2E; - ring = tb_ring_alloc_rx(xd->tb->nhi, -1, TBNET_RING_SIZE, flags, net->tx_ring.ring->hop, sof_mask, eof_mask, tbnet_start_poll, net); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index f8c5e2fd04df..447c37959504 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2356,13 +2356,12 @@ static int tun_xdp_one(struct tun_struct *tun, struct tun_page *tpage) { unsigned int datasize = xdp->data_end - xdp->data; - struct tun_xdp_hdr *hdr = xdp->data_hard_start; - struct virtio_net_hdr *gso = &hdr->gso; + struct virtio_net_hdr *gso = xdp->data_hard_start; struct bpf_prog *xdp_prog; struct sk_buff *skb = NULL; struct sk_buff_head *queue; u32 rxhash = 0, act; - int buflen = hdr->buflen; + int buflen = xdp->frame_sz; int metasize = 0; int ret = 0; bool skb_xdp = false; diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index f00284c9ad34..f3347fb0c400 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -2831,6 +2831,10 @@ static int lan78xx_phy_init(struct lan78xx_net *dev) if (ret < 0) return ret; + ret = lan78xx_mac_prepare_for_phy(dev); + if (ret < 0) + goto phylink_uninit; + /* If no PHY is found, set up a fixed link. It is very specific to * the LAN7801 and is used in special cases like EVB-KSZ9897-1 where * LAN7801 acts as a USB-to-Ethernet interface to a switch without @@ -2840,11 +2844,12 @@ static int lan78xx_phy_init(struct lan78xx_net *dev) ret = lan78xx_set_fixed_link(dev); if (ret < 0) goto phylink_uninit; - } - ret = lan78xx_mac_prepare_for_phy(dev); - if (ret < 0) - goto phylink_uninit; + /* No PHY found, so set up a fixed link and return early. + * No need to configure PHY IRQ or attach to phylink. + */ + return 0; + } /* if phyirq is not set, use polling mode in phylib */ if (dev->domain_data.phyirq > 0) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 07e41dce4203..9f6e0153ed2d 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -778,6 +778,26 @@ static unsigned int mergeable_ctx_to_truesize(void *mrg_ctx) return (unsigned long)mrg_ctx & ((1 << MRG_CTX_HEADER_SHIFT) - 1); } +static int check_mergeable_len(struct net_device *dev, void *mrg_ctx, + unsigned int len) +{ + unsigned int headroom, tailroom, room, truesize; + + truesize = mergeable_ctx_to_truesize(mrg_ctx); + headroom = mergeable_ctx_to_headroom(mrg_ctx); + tailroom = headroom ? sizeof(struct skb_shared_info) : 0; + room = SKB_DATA_ALIGN(headroom + tailroom); + + if (len > truesize - room) { + pr_debug("%s: rx error: len %u exceeds truesize %lu\n", + dev->name, len, (unsigned long)(truesize - room)); + DEV_STATS_INC(dev, rx_length_errors); + return -1; + } + + return 0; +} + static struct sk_buff *virtnet_build_skb(void *buf, unsigned int buflen, unsigned int headroom, unsigned int len) @@ -1084,7 +1104,7 @@ static bool tx_may_stop(struct virtnet_info *vi, * Since most packets only take 1 or 2 ring slots, stopping the queue * early means 16 slots are typically wasted. */ - if (sq->vq->num_free < 2+MAX_SKB_FRAGS) { + if (sq->vq->num_free < MAX_SKB_FRAGS + 2) { struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum); netif_tx_stop_queue(txq); @@ -1116,7 +1136,7 @@ static void check_sq_full_and_disable(struct virtnet_info *vi, } else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) { /* More just got used, free them then recheck. */ free_old_xmit(sq, txq, false); - if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) { + if (sq->vq->num_free >= MAX_SKB_FRAGS + 2) { netif_start_subqueue(dev, qnum); u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.wake); @@ -1127,15 +1147,29 @@ static void check_sq_full_and_disable(struct virtnet_info *vi, } } +/* Note that @len is the length of received data without virtio header */ static struct xdp_buff *buf_to_xdp(struct virtnet_info *vi, - struct receive_queue *rq, void *buf, u32 len) + struct receive_queue *rq, void *buf, + u32 len, bool first_buf) { struct xdp_buff *xdp; u32 bufsize; xdp = (struct xdp_buff *)buf; - bufsize = xsk_pool_get_rx_frame_size(rq->xsk_pool) + vi->hdr_len; + /* In virtnet_add_recvbuf_xsk, we use part of XDP_PACKET_HEADROOM for + * virtio header and ask the vhost to fill data from + * hard_start + XDP_PACKET_HEADROOM - vi->hdr_len + * The first buffer has virtio header so the remaining region for frame + * data is + * xsk_pool_get_rx_frame_size() + * While other buffers than the first one do not have virtio header, so + * the maximum frame data's length can be + * xsk_pool_get_rx_frame_size() + vi->hdr_len + */ + bufsize = xsk_pool_get_rx_frame_size(rq->xsk_pool); + if (!first_buf) + bufsize += vi->hdr_len; if (unlikely(len > bufsize)) { pr_debug("%s: rx error: len %u exceeds truesize %u\n", @@ -1260,7 +1294,7 @@ static int xsk_append_merge_buffer(struct virtnet_info *vi, u64_stats_add(&stats->bytes, len); - xdp = buf_to_xdp(vi, rq, buf, len); + xdp = buf_to_xdp(vi, rq, buf, len, false); if (!xdp) goto err; @@ -1358,7 +1392,7 @@ static void virtnet_receive_xsk_buf(struct virtnet_info *vi, struct receive_queu u64_stats_add(&stats->bytes, len); - xdp = buf_to_xdp(vi, rq, buf, len); + xdp = buf_to_xdp(vi, rq, buf, len, true); if (!xdp) return; @@ -1797,7 +1831,8 @@ static unsigned int virtnet_get_headroom(struct virtnet_info *vi) * across multiple buffers (num_buf > 1), and we make sure buffers * have enough headroom. */ -static struct page *xdp_linearize_page(struct receive_queue *rq, +static struct page *xdp_linearize_page(struct net_device *dev, + struct receive_queue *rq, int *num_buf, struct page *p, int offset, @@ -1817,18 +1852,27 @@ static struct page *xdp_linearize_page(struct receive_queue *rq, memcpy(page_address(page) + page_off, page_address(p) + offset, *len); page_off += *len; + /* Only mergeable mode can go inside this while loop. In small mode, + * *num_buf == 1, so it cannot go inside. + */ while (--*num_buf) { unsigned int buflen; void *buf; + void *ctx; int off; - buf = virtnet_rq_get_buf(rq, &buflen, NULL); + buf = virtnet_rq_get_buf(rq, &buflen, &ctx); if (unlikely(!buf)) goto err_buf; p = virt_to_head_page(buf); off = buf - page_address(p); + if (check_mergeable_len(dev, ctx, buflen)) { + put_page(p); + goto err_buf; + } + /* guard against a misconfigured or uncooperative backend that * is sending packet larger than the MTU. */ @@ -1917,7 +1961,7 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev, headroom = vi->hdr_len + header_offset; buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - xdp_page = xdp_linearize_page(rq, &num_buf, page, + xdp_page = xdp_linearize_page(dev, rq, &num_buf, page, offset, header_offset, &tlen); if (!xdp_page) @@ -2126,10 +2170,9 @@ static int virtnet_build_xdp_buff_mrg(struct net_device *dev, struct virtnet_rq_stats *stats) { struct virtio_net_hdr_mrg_rxbuf *hdr = buf; - unsigned int headroom, tailroom, room; - unsigned int truesize, cur_frag_size; struct skb_shared_info *shinfo; unsigned int xdp_frags_truesz = 0; + unsigned int truesize; struct page *page; skb_frag_t *frag; int offset; @@ -2172,21 +2215,14 @@ static int virtnet_build_xdp_buff_mrg(struct net_device *dev, page = virt_to_head_page(buf); offset = buf - page_address(page); - truesize = mergeable_ctx_to_truesize(ctx); - headroom = mergeable_ctx_to_headroom(ctx); - tailroom = headroom ? sizeof(struct skb_shared_info) : 0; - room = SKB_DATA_ALIGN(headroom + tailroom); - - cur_frag_size = truesize; - xdp_frags_truesz += cur_frag_size; - if (unlikely(len > truesize - room || cur_frag_size > PAGE_SIZE)) { + if (check_mergeable_len(dev, ctx, len)) { put_page(page); - pr_debug("%s: rx error: len %u exceeds truesize %lu\n", - dev->name, len, (unsigned long)(truesize - room)); - DEV_STATS_INC(dev, rx_length_errors); goto err; } + truesize = mergeable_ctx_to_truesize(ctx); + xdp_frags_truesz += truesize; + frag = &shinfo->frags[shinfo->nr_frags++]; skb_frag_fill_page_desc(frag, page, offset, len); if (page_is_pfmemalloc(page)) @@ -2252,7 +2288,7 @@ static void *mergeable_xdp_get_buf(struct virtnet_info *vi, */ if (!xdp_prog->aux->xdp_has_frags) { /* linearize data for XDP */ - xdp_page = xdp_linearize_page(rq, num_buf, + xdp_page = xdp_linearize_page(vi->dev, rq, num_buf, *page, offset, XDP_PACKET_HEADROOM, len); @@ -2400,18 +2436,12 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, struct sk_buff *head_skb, *curr_skb; unsigned int truesize = mergeable_ctx_to_truesize(ctx); unsigned int headroom = mergeable_ctx_to_headroom(ctx); - unsigned int tailroom = headroom ? sizeof(struct skb_shared_info) : 0; - unsigned int room = SKB_DATA_ALIGN(headroom + tailroom); head_skb = NULL; u64_stats_add(&stats->bytes, len - vi->hdr_len); - if (unlikely(len > truesize - room)) { - pr_debug("%s: rx error: len %u exceeds truesize %lu\n", - dev->name, len, (unsigned long)(truesize - room)); - DEV_STATS_INC(dev, rx_length_errors); + if (check_mergeable_len(dev, ctx, len)) goto err_skb; - } if (unlikely(vi->xdp_enabled)) { struct bpf_prog *xdp_prog; @@ -2446,17 +2476,10 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, u64_stats_add(&stats->bytes, len); page = virt_to_head_page(buf); - truesize = mergeable_ctx_to_truesize(ctx); - headroom = mergeable_ctx_to_headroom(ctx); - tailroom = headroom ? sizeof(struct skb_shared_info) : 0; - room = SKB_DATA_ALIGN(headroom + tailroom); - if (unlikely(len > truesize - room)) { - pr_debug("%s: rx error: len %u exceeds truesize %lu\n", - dev->name, len, (unsigned long)(truesize - room)); - DEV_STATS_INC(dev, rx_length_errors); + if (check_mergeable_len(dev, ctx, len)) goto err_skb; - } + truesize = mergeable_ctx_to_truesize(ctx); curr_skb = virtnet_skb_append_frag(head_skb, curr_skb, page, buf, len, truesize); if (!curr_skb) @@ -2998,7 +3021,7 @@ static void virtnet_poll_cleantx(struct receive_queue *rq, int budget) free_old_xmit(sq, txq, !!budget); } while (unlikely(!virtqueue_enable_cb_delayed(sq->vq))); - if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) { + if (sq->vq->num_free >= MAX_SKB_FRAGS + 2) { if (netif_tx_queue_stopped(txq)) { u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.wake); @@ -3195,7 +3218,7 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget) else free_old_xmit(sq, txq, !!budget); - if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) { + if (sq->vq->num_free >= MAX_SKB_FRAGS + 2) { if (netif_tx_queue_stopped(txq)) { u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.wake); @@ -3481,6 +3504,12 @@ static int virtnet_tx_resize(struct virtnet_info *vi, struct send_queue *sq, { int qindex, err; + if (ring_num <= MAX_SKB_FRAGS + 2) { + netdev_err(vi->dev, "tx size (%d) cannot be smaller than %d\n", + ring_num, MAX_SKB_FRAGS + 2); + return -EINVAL; + } + qindex = sq - vi->sq; virtnet_tx_pause(vi, sq); diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c index 4ff56d9f8f28..adc89e651e27 100644 --- a/drivers/net/vxlan/vxlan_vnifilter.c +++ b/drivers/net/vxlan/vxlan_vnifilter.c @@ -971,15 +971,10 @@ static int vxlan_vnifilter_process(struct sk_buff *skb, struct nlmsghdr *nlh, if (!(vxlan->cfg.flags & VXLAN_F_VNIFILTER)) return -EOPNOTSUPP; - nlmsg_for_each_attr(attr, nlh, sizeof(*tmsg), rem) { - switch (nla_type(attr)) { - case VXLAN_VNIFILTER_ENTRY: - err = vxlan_process_vni_filter(vxlan, attr, - nlh->nlmsg_type, extack); - break; - default: - continue; - } + nlmsg_for_each_attr_type(attr, VXLAN_VNIFILTER_ENTRY, nlh, + sizeof(*tmsg), rem) { + err = vxlan_process_vni_filter(vxlan, attr, nlh->nlmsg_type, + extack); vnis++; if (err) break; diff --git a/drivers/net/wireless/mediatek/mt76/channel.c b/drivers/net/wireless/mediatek/mt76/channel.c index cc2d888e3f17..77b75792eb48 100644 --- a/drivers/net/wireless/mediatek/mt76/channel.c +++ b/drivers/net/wireless/mediatek/mt76/channel.c @@ -173,13 +173,13 @@ void mt76_unassign_vif_chanctx(struct ieee80211_hw *hw, if (!mlink) goto out; - if (link_conf != &vif->bss_conf) + if (mlink != (struct mt76_vif_link *)vif->drv_priv) rcu_assign_pointer(mvif->link[link_id], NULL); dev->drv->vif_link_remove(phy, vif, link_conf, mlink); mlink->ctx = NULL; - if (link_conf != &vif->bss_conf) + if (mlink != (struct mt76_vif_link *)vif->drv_priv) kfree_rcu(mlink, rcu_head); out: diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index 35b4ec91979e..87f531297f85 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -643,10 +643,8 @@ mt76_dma_rx_fill_buf(struct mt76_dev *dev, struct mt76_queue *q, while (q->queued < q->ndesc - 1) { struct mt76_queue_buf qbuf = {}; - enum dma_data_direction dir; - dma_addr_t addr; - int offset; void *buf = NULL; + int offset; if (mt76_queue_is_wed_rro_ind(q)) goto done; @@ -655,11 +653,8 @@ mt76_dma_rx_fill_buf(struct mt76_dev *dev, struct mt76_queue *q, if (!buf) break; - addr = page_pool_get_dma_addr(virt_to_head_page(buf)) + offset; - dir = page_pool_get_dma_dir(q->page_pool); - dma_sync_single_for_device(dev->dma_dev, addr, len, dir); - - qbuf.addr = addr + q->buf_offset; + qbuf.addr = page_pool_get_dma_addr(virt_to_head_page(buf)) + + offset + q->buf_offset; done: qbuf.len = len - q->buf_offset; qbuf.skip_unmap = false; diff --git a/drivers/net/wireless/mediatek/mt76/mcu.c b/drivers/net/wireless/mediatek/mt76/mcu.c index 3353012e8542..65d4c2adb538 100644 --- a/drivers/net/wireless/mediatek/mt76/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mcu.c @@ -78,6 +78,10 @@ int mt76_mcu_skb_send_and_get_msg(struct mt76_dev *dev, struct sk_buff *skb, unsigned long expires; int ret, seq; + if (mt76_is_sdio(dev)) + if (test_bit(MT76_RESET, &dev->phy.state) && atomic_read(&dev->bus_hung)) + return -EIO; + if (ret_skb) *ret_skb = NULL; diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index 14927a92f9d1..00ac071010aa 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -983,6 +983,8 @@ struct mt76_dev { struct mt76_usb usb; struct mt76_sdio sdio; }; + + atomic_t bus_hung; }; /* per-phy stats. */ @@ -1865,6 +1867,9 @@ mt76_vif_link(struct mt76_dev *dev, struct ieee80211_vif *vif, int link_id) struct mt76_vif_link *mlink = (struct mt76_vif_link *)vif->drv_priv; struct mt76_vif_data *mvif = mlink->mvif; + if (!link_id) + return mlink; + return mt76_dereference(mvif->link[link_id], dev); } @@ -1875,7 +1880,7 @@ mt76_vif_conf_link(struct mt76_dev *dev, struct ieee80211_vif *vif, struct mt76_vif_link *mlink = (struct mt76_vif_link *)vif->drv_priv; struct mt76_vif_data *mvif = mlink->mvif; - if (link_conf == &vif->bss_conf) + if (link_conf == &vif->bss_conf || !link_conf->link_id) return mlink; return mt76_dereference(mvif->link[link_conf->link_id], dev); diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c index 427542777abc..cf948628e588 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c @@ -197,6 +197,8 @@ mt7915_mcu_parse_response(struct mt76_dev *mdev, int cmd, static void mt7915_mcu_set_timeout(struct mt76_dev *mdev, int cmd) { + mdev->mcu.timeout = 5 * HZ; + if ((cmd & __MCU_CMD_FIELD_ID) != MCU_CMD_EXT_CID) return; @@ -208,6 +210,9 @@ mt7915_mcu_set_timeout(struct mt76_dev *mdev, int cmd) case MCU_EXT_CMD_BSS_INFO_UPDATE: mdev->mcu.timeout = 2 * HZ; return; + case MCU_EXT_CMD_EFUSE_BUFFER_MODE: + mdev->mcu.timeout = 10 * HZ; + return; default: break; } @@ -2110,16 +2115,21 @@ static int mt7915_load_firmware(struct mt7915_dev *dev) { int ret; - /* make sure fw is download state */ - if (mt7915_firmware_state(dev, false)) { - /* restart firmware once */ - mt76_connac_mcu_restart(&dev->mt76); - ret = mt7915_firmware_state(dev, false); - if (ret) { - dev_err(dev->mt76.dev, - "Firmware is not ready for download\n"); - return ret; - } + /* Release Semaphore if taken by previous failed attempt */ + ret = mt76_connac_mcu_patch_sem_ctrl(&dev->mt76, false); + if (ret != PATCH_REL_SEM_SUCCESS) { + dev_err(dev->mt76.dev, "Could not release semaphore\n"); + /* Continue anyways */ + } + + /* Always restart MCU firmware */ + mt76_connac_mcu_restart(&dev->mt76); + + /* Check if MCU is ready */ + ret = mt7915_firmware_state(dev, false); + if (ret) { + dev_err(dev->mt76.dev, "Firmware did not enter download state\n"); + return ret; } ret = mt76_connac2_load_patch(&dev->mt76, fw_name_var(dev, ROM_PATCH)); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c index 5dd57de59f27..7b75193039f7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c @@ -675,6 +675,8 @@ void mt7921_mac_reset_work(struct work_struct *work) if (!ret) break; } + if (mt76_is_sdio(&dev->mt76) && atomic_read(&dev->mt76.bus_hung)) + return; if (i == 10) dev_err(dev->mt76.dev, "chip reset failed\n"); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c index 45b9f35aab17..d8d36b3c3068 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c @@ -150,6 +150,8 @@ static int mt7921s_probe(struct sdio_func *func, if (ret) goto error; + atomic_set(&mdev->bus_hung, false); + mdev->rev = (mt76_rr(dev, MT_HW_CHIPID) << 16) | (mt76_rr(dev, MT_HW_REV) & 0xff); dev_dbg(mdev->dev, "ASIC revision: %04x\n", mdev->rev); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c index 1f77cf71ca70..a9eb6252a904 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c @@ -6,6 +6,8 @@ #include "mt7921.h" #include "../mt76_connac2_mac.h" #include "../sdio.h" +#include <linux/mmc/host.h> +#include <linux/kallsyms.h> static void mt7921s_enable_irq(struct mt76_dev *dev) { @@ -35,6 +37,9 @@ int mt7921s_wfsys_reset(struct mt792x_dev *dev) struct mt76_sdio *sdio = &dev->mt76.sdio; u32 val, status; + if (atomic_read(&dev->mt76.bus_hung)) + return 0; + mt7921s_mcu_drv_pmctrl(dev); sdio_claim_host(sdio->func); @@ -91,11 +96,64 @@ int mt7921s_init_reset(struct mt792x_dev *dev) return 0; } +static struct mt76_sdio *msdio; +static void mt7921s_card_reset(struct work_struct *work) +{ + struct mmc_host *sdio_host = msdio->func->card->host; + + sdio_claim_host(msdio->func); + sdio_release_irq(msdio->func); + sdio_release_host(msdio->func); + + mmc_remove_host(sdio_host); + msleep(50); + mmc_add_host(sdio_host); +} + +static DECLARE_WORK(sdio_reset_work, mt7921s_card_reset); +static int mt7921s_check_bus(struct mt76_dev *dev) +{ + struct mt76_sdio *sdio = &dev->sdio; + int err; + + sdio_claim_host(sdio->func); + sdio_readl(dev->sdio.func, MCR_WHCR, &err); + sdio_release_host(sdio->func); + + return err; +} + +static int mt7921s_host_reset(struct mt792x_dev *dev) +{ + struct mt76_dev *mdev = &dev->mt76; + int err = -1; + + if (!atomic_read(&mdev->bus_hung)) + err = mt7921s_check_bus(&dev->mt76); + + if (err) { + atomic_set(&mdev->bus_hung, true); + msdio = &dev->mt76.sdio; + dev_err(mdev->dev, "SDIO bus problem detected(%d), resetting card!!\n", err); + schedule_work(&sdio_reset_work); + return err; + } + + atomic_set(&mdev->bus_hung, false); + + return 0; +} + int mt7921s_mac_reset(struct mt792x_dev *dev) { int err; mt76_connac_free_pending_tx_skbs(&dev->pm, NULL); + + mt7921s_host_reset(dev); + if (atomic_read(&dev->mt76.bus_hung)) + return 0; + mt76_txq_schedule_all(&dev->mphy); mt76_worker_disable(&dev->mt76.tx_worker); set_bit(MT76_MCU_RESET, &dev->mphy.state); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c index b8542be0d945..16f3cc58a192 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c @@ -2866,7 +2866,7 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif, for (i = 0; i < sreq->n_ssids; i++) { if (!sreq->ssids[i].ssid_len) continue; - if (i > MT7925_RNR_SCAN_MAX_BSSIDS) + if (i >= MT7925_RNR_SCAN_MAX_BSSIDS) break; ssid->ssids[i].ssid_len = cpu_to_le32(sreq->ssids[i].ssid_len); @@ -2883,7 +2883,7 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif, mt76_connac_mcu_build_rnr_scan_param(mdev, sreq); for (j = 0; j < mdev->rnr.bssid_num; j++) { - if (j > MT7925_RNR_SCAN_MAX_BSSIDS) + if (j >= MT7925_RNR_SCAN_MAX_BSSIDS) break; tlv = mt76_connac_mcu_add_tlv(skb, UNI_SCAN_BSSID, diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c index 43a7ac0f718e..381009c4b6b6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c +++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c @@ -666,6 +666,7 @@ int mt792x_init_wiphy(struct ieee80211_hw *hw) ieee80211_hw_set(hw, SUPPORTS_DYNAMIC_PS); ieee80211_hw_set(hw, SUPPORTS_VHT_EXT_NSS_BW); ieee80211_hw_set(hw, CONNECTION_MONITOR); + ieee80211_hw_set(hw, NO_VIRTUAL_MONITOR); if (is_mt7921(&dev->mt76)) ieee80211_hw_set(hw, CHANCTX_STA_CSA); diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 0dbd4662bc84..02e10d744feb 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -1087,9 +1087,9 @@ int mt7996_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, if (wcid->offchannel) mlink = rcu_dereference(mvif->mt76.offchannel_link); if (!mlink) - mlink = &mvif->deflink.mt76; + mlink = rcu_dereference(mvif->mt76.link[wcid->link_id]); - txp->fw.bss_idx = mlink->idx; + txp->fw.bss_idx = mlink ? mlink->idx : mvif->deflink.mt76.idx; } txp->fw.token = cpu_to_le16(id); @@ -1129,15 +1129,14 @@ u32 mt7996_wed_init_buf(void *ptr, dma_addr_t phys, int token_id) } static void -mt7996_tx_check_aggr(struct ieee80211_sta *sta, struct sk_buff *skb) +mt7996_tx_check_aggr(struct ieee80211_link_sta *link_sta, + struct mt76_wcid *wcid, struct sk_buff *skb) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); bool is_8023 = info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP; - struct mt7996_sta_link *msta_link; - struct mt7996_sta *msta; u16 fc, tid; - if (!sta || !(sta->deflink.ht_cap.ht_supported || sta->deflink.he_cap.has_he)) + if (!(link_sta->ht_cap.ht_supported || link_sta->he_cap.has_he)) return; tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; @@ -1146,7 +1145,8 @@ mt7996_tx_check_aggr(struct ieee80211_sta *sta, struct sk_buff *skb) if (is_8023) { fc = IEEE80211_FTYPE_DATA | - (sta->wme ? IEEE80211_STYPE_QOS_DATA : IEEE80211_STYPE_DATA); + (link_sta->sta->wme ? IEEE80211_STYPE_QOS_DATA + : IEEE80211_STYPE_DATA); } else { /* No need to get precise TID for Action/Management Frame, * since it will not meet the following Frame Control @@ -1162,19 +1162,16 @@ mt7996_tx_check_aggr(struct ieee80211_sta *sta, struct sk_buff *skb) if (unlikely(fc != (IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_DATA))) return; - msta = (struct mt7996_sta *)sta->drv_priv; - msta_link = &msta->deflink; - - if (!test_and_set_bit(tid, &msta_link->wcid.ampdu_state)) - ieee80211_start_tx_ba_session(sta, tid, 0); + if (!test_and_set_bit(tid, &wcid->ampdu_state)) + ieee80211_start_tx_ba_session(link_sta->sta, tid, 0); } static void mt7996_txwi_free(struct mt7996_dev *dev, struct mt76_txwi_cache *t, - struct ieee80211_sta *sta, struct list_head *free_list) + struct ieee80211_link_sta *link_sta, + struct mt76_wcid *wcid, struct list_head *free_list) { struct mt76_dev *mdev = &dev->mt76; - struct mt76_wcid *wcid; __le32 *txwi; u16 wcid_idx; @@ -1183,12 +1180,10 @@ mt7996_txwi_free(struct mt7996_dev *dev, struct mt76_txwi_cache *t, goto out; txwi = (__le32 *)mt76_get_txwi_ptr(mdev, t); - if (sta) { - wcid = (struct mt76_wcid *)sta->drv_priv; + if (link_sta) { wcid_idx = wcid->idx; - if (likely(t->skb->protocol != cpu_to_be16(ETH_P_PAE))) - mt7996_tx_check_aggr(sta, t->skb); + mt7996_tx_check_aggr(link_sta, wcid, t->skb); } else { wcid_idx = le32_get_bits(txwi[9], MT_TXD9_WLAN_IDX); } @@ -1207,8 +1202,8 @@ mt7996_mac_tx_free(struct mt7996_dev *dev, void *data, int len) struct mt76_dev *mdev = &dev->mt76; struct mt76_phy *phy2 = mdev->phys[MT_BAND1]; struct mt76_phy *phy3 = mdev->phys[MT_BAND2]; + struct ieee80211_link_sta *link_sta = NULL; struct mt76_txwi_cache *txwi; - struct ieee80211_sta *sta = NULL; struct mt76_wcid *wcid = NULL; LIST_HEAD(free_list); struct sk_buff *skb, *tmp; @@ -1245,7 +1240,7 @@ mt7996_mac_tx_free(struct mt7996_dev *dev, void *data, int len) */ info = le32_to_cpu(*cur_info); if (info & MT_TXFREE_INFO_PAIR) { - struct mt7996_sta_link *msta_link; + struct ieee80211_sta *sta; u16 idx; idx = FIELD_GET(MT_TXFREE_INFO_WLAN_ID, info); @@ -1254,9 +1249,11 @@ mt7996_mac_tx_free(struct mt7996_dev *dev, void *data, int len) if (!sta) goto next; - msta_link = container_of(wcid, struct mt7996_sta_link, - wcid); - mt76_wcid_add_poll(&dev->mt76, &msta_link->wcid); + link_sta = rcu_dereference(sta->link[wcid->link_id]); + if (!link_sta) + goto next; + + mt76_wcid_add_poll(&dev->mt76, wcid); next: /* ver 7 has a new DW with pair = 1, skip it */ if (ver == 7 && ((void *)(cur_info + 1) < end) && @@ -1289,7 +1286,8 @@ next: if (!txwi) continue; - mt7996_txwi_free(dev, txwi, sta, &free_list); + mt7996_txwi_free(dev, txwi, link_sta, wcid, + &free_list); } } @@ -1748,7 +1746,7 @@ void mt7996_tx_token_put(struct mt7996_dev *dev) spin_lock_bh(&dev->mt76.token_lock); idr_for_each_entry(&dev->mt76.token, txwi, id) { - mt7996_txwi_free(dev, txwi, NULL, NULL); + mt7996_txwi_free(dev, txwi, NULL, NULL, NULL); dev->mt76.token_count--; } spin_unlock_bh(&dev->mt76.token_lock); diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c index 5283aee619a9..f846b8309ae2 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c @@ -960,8 +960,8 @@ mt7996_mac_sta_deinit_link(struct mt7996_dev *dev, } static void -mt7996_mac_sta_remove_links(struct mt7996_dev *dev, struct ieee80211_sta *sta, - unsigned long links) +mt7996_mac_sta_remove_links(struct mt7996_dev *dev, struct ieee80211_vif *vif, + struct ieee80211_sta *sta, unsigned long links) { struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv; struct mt76_dev *mdev = &dev->mt76; @@ -969,6 +969,8 @@ mt7996_mac_sta_remove_links(struct mt7996_dev *dev, struct ieee80211_sta *sta, for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) { struct mt7996_sta_link *msta_link = NULL; + struct mt7996_vif_link *link; + struct mt76_phy *mphy; msta_link = rcu_replace_pointer(msta->link[link_id], msta_link, lockdep_is_held(&mdev->mutex)); @@ -976,6 +978,15 @@ mt7996_mac_sta_remove_links(struct mt7996_dev *dev, struct ieee80211_sta *sta, continue; mt7996_mac_sta_deinit_link(dev, msta_link); + link = mt7996_vif_link(dev, vif, link_id); + if (!link) + continue; + + mphy = mt76_vif_link_phy(&link->mt76); + if (!mphy) + continue; + + mphy->num_sta--; if (msta->deflink_id == link_id) { msta->deflink_id = IEEE80211_LINK_UNSPECIFIED; continue; @@ -997,6 +1008,7 @@ mt7996_mac_sta_add_links(struct mt7996_dev *dev, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf; struct ieee80211_link_sta *link_sta; struct mt7996_vif_link *link; + struct mt76_phy *mphy; if (rcu_access_pointer(msta->link[link_id])) continue; @@ -1023,12 +1035,19 @@ mt7996_mac_sta_add_links(struct mt7996_dev *dev, struct ieee80211_vif *vif, link_id); if (err) goto error_unlink; + + mphy = mt76_vif_link_phy(&link->mt76); + if (!mphy) { + err = -EINVAL; + goto error_unlink; + } + mphy->num_sta++; } return 0; error_unlink: - mt7996_mac_sta_remove_links(dev, sta, new_links); + mt7996_mac_sta_remove_links(dev, vif, sta, new_links); return err; } @@ -1045,7 +1064,7 @@ mt7996_mac_sta_change_links(struct ieee80211_hw *hw, struct ieee80211_vif *vif, mutex_lock(&dev->mt76.mutex); - mt7996_mac_sta_remove_links(dev, sta, rem); + mt7996_mac_sta_remove_links(dev, vif, sta, rem); ret = mt7996_mac_sta_add_links(dev, vif, sta, add); mutex_unlock(&dev->mt76.mutex); @@ -1054,25 +1073,21 @@ mt7996_mac_sta_change_links(struct ieee80211_hw *hw, struct ieee80211_vif *vif, } static int -mt7996_mac_sta_add(struct mt76_phy *mphy, struct ieee80211_vif *vif, +mt7996_mac_sta_add(struct mt7996_dev *dev, struct ieee80211_vif *vif, struct ieee80211_sta *sta) { - struct mt76_dev *mdev = mphy->dev; - struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76); struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv; struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; - unsigned long links = sta->mlo ? sta->valid_links : BIT(0); + unsigned long links = sta->valid_links ? sta->valid_links : BIT(0); int err; - mutex_lock(&mdev->mutex); + mutex_lock(&dev->mt76.mutex); msta->deflink_id = IEEE80211_LINK_UNSPECIFIED; msta->vif = mvif; err = mt7996_mac_sta_add_links(dev, vif, sta, links); - if (!err) - mphy->num_sta++; - mutex_unlock(&mdev->mutex); + mutex_unlock(&dev->mt76.mutex); return err; } @@ -1119,7 +1134,6 @@ mt7996_mac_sta_event(struct mt7996_dev *dev, struct ieee80211_vif *vif, return err; msta_link->wcid.tx_info |= MT_WCID_TX_INFO_SET; - msta_link->wcid.sta = 1; break; case MT76_STA_EVENT_AUTHORIZE: err = mt7996_mcu_add_sta(dev, link_conf, link_sta, @@ -1151,19 +1165,14 @@ mt7996_mac_sta_event(struct mt7996_dev *dev, struct ieee80211_vif *vif, } static void -mt7996_mac_sta_remove(struct mt76_phy *mphy, struct ieee80211_vif *vif, +mt7996_mac_sta_remove(struct mt7996_dev *dev, struct ieee80211_vif *vif, struct ieee80211_sta *sta) { - struct mt76_dev *mdev = mphy->dev; - struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76); - unsigned long links = sta->mlo ? sta->valid_links : BIT(0); - - mutex_lock(&mdev->mutex); + unsigned long links = sta->valid_links ? sta->valid_links : BIT(0); - mt7996_mac_sta_remove_links(dev, sta, links); - mphy->num_sta--; - - mutex_unlock(&mdev->mutex); + mutex_lock(&dev->mt76.mutex); + mt7996_mac_sta_remove_links(dev, vif, sta, links); + mutex_unlock(&dev->mt76.mutex); } static int @@ -1171,20 +1180,16 @@ mt7996_sta_state(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, enum ieee80211_sta_state old_state, enum ieee80211_sta_state new_state) { - struct mt76_phy *mphy = mt76_vif_phy(hw, vif); struct mt7996_dev *dev = mt7996_hw_dev(hw); enum mt76_sta_event ev; - if (!mphy) - return -EINVAL; - if (old_state == IEEE80211_STA_NOTEXIST && new_state == IEEE80211_STA_NONE) - return mt7996_mac_sta_add(mphy, vif, sta); + return mt7996_mac_sta_add(dev, vif, sta); if (old_state == IEEE80211_STA_NONE && new_state == IEEE80211_STA_NOTEXIST) - mt7996_mac_sta_remove(mphy, vif, sta); + mt7996_mac_sta_remove(dev, vif, sta); if (old_state == IEEE80211_STA_AUTH && new_state == IEEE80211_STA_ASSOC) @@ -1217,10 +1222,17 @@ static void mt7996_tx(struct ieee80211_hw *hw, if (vif) { struct mt7996_vif *mvif = (void *)vif->drv_priv; - struct mt76_vif_link *mlink; + struct mt76_vif_link *mlink = &mvif->deflink.mt76; + + if (link_id < IEEE80211_LINK_UNSPECIFIED) + mlink = rcu_dereference(mvif->mt76.link[link_id]); + + if (!mlink) { + ieee80211_free_txskb(hw, skb); + goto unlock; + } - mlink = rcu_dereference(mvif->mt76.link[link_id]); - if (mlink && mlink->wcid) + if (mlink->wcid) wcid = mlink->wcid; if (mvif->mt76.roc_phy && @@ -1229,7 +1241,7 @@ static void mt7996_tx(struct ieee80211_hw *hw, if (mphy->roc_link) wcid = mphy->roc_link->wcid; } else { - mphy = mt76_vif_link_phy(&mvif->deflink.mt76); + mphy = mt76_vif_link_phy(mlink); } } @@ -1238,7 +1250,7 @@ static void mt7996_tx(struct ieee80211_hw *hw, goto unlock; } - if (control->sta) { + if (control->sta && link_id < IEEE80211_LINK_UNSPECIFIED) { struct mt7996_sta *msta = (void *)control->sta->drv_priv; struct mt7996_sta_link *msta_link; diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c index f0adc0b4b8b6..0374872db477 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c @@ -2216,15 +2216,15 @@ mt7996_mcu_add_group(struct mt7996_dev *dev, struct ieee80211_vif *vif, static void mt7996_mcu_sta_mld_setup_tlv(struct mt7996_dev *dev, struct sk_buff *skb, + struct ieee80211_vif *vif, struct ieee80211_sta *sta) { struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv; - unsigned long links = sta->valid_links; - unsigned int nlinks = hweight16(links); + unsigned int nlinks = hweight16(sta->valid_links); struct mld_setup_link *mld_setup_link; + struct ieee80211_link_sta *link_sta; struct sta_rec_mld_setup *mld_setup; struct mt7996_sta_link *msta_link; - struct ieee80211_vif *vif; unsigned int link_id; struct tlv *tlv; @@ -2242,18 +2242,16 @@ mt7996_mcu_sta_mld_setup_tlv(struct mt7996_dev *dev, struct sk_buff *skb, mld_setup->primary_id = cpu_to_le16(msta_link->wcid.idx); if (nlinks > 1) { - link_id = __ffs(links & ~BIT(msta->deflink_id)); - msta_link = mt76_dereference(msta->link[msta->deflink_id], - &dev->mt76); + link_id = __ffs(sta->valid_links & ~BIT(msta->deflink_id)); + msta_link = mt76_dereference(msta->link[link_id], &dev->mt76); if (!msta_link) return; } mld_setup->seconed_id = cpu_to_le16(msta_link->wcid.idx); mld_setup->link_num = nlinks; - vif = container_of((void *)msta->vif, struct ieee80211_vif, drv_priv); mld_setup_link = (struct mld_setup_link *)mld_setup->link_info; - for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) { + for_each_sta_active_link(vif, sta, link_sta, link_id) { struct mt7996_vif_link *link; msta_link = mt76_dereference(msta->link[link_id], &dev->mt76); @@ -2345,7 +2343,8 @@ int mt7996_mcu_add_sta(struct mt7996_dev *dev, mt7996_mcu_sta_muru_tlv(dev, skb, link_conf, link_sta); if (sta->mlo) { - mt7996_mcu_sta_mld_setup_tlv(dev, skb, sta); + mt7996_mcu_sta_mld_setup_tlv(dev, skb, link_conf->vif, + sta); mt7996_mcu_sta_eht_mld_tlv(dev, skb, sta); } } diff --git a/drivers/net/wireless/mediatek/mt76/sdio_txrx.c b/drivers/net/wireless/mediatek/mt76/sdio_txrx.c index 0a927a7313a6..f882d21c9f63 100644 --- a/drivers/net/wireless/mediatek/mt76/sdio_txrx.c +++ b/drivers/net/wireless/mediatek/mt76/sdio_txrx.c @@ -112,6 +112,7 @@ mt76s_rx_run_queue(struct mt76_dev *dev, enum mt76_rxq_id qid, if (err < 0) { dev_err(dev->dev, "sdio read data failed:%d\n", err); + atomic_set(&dev->bus_hung, true); put_page(page); return err; } @@ -234,9 +235,10 @@ static int __mt76s_xmit_queue(struct mt76_dev *dev, u8 *data, int len) err = sdio_writesb(sdio->func, MCR_WTDR1, data, len); sdio_release_host(sdio->func); - if (err) + if (err) { dev_err(dev->dev, "sdio write failed: %d\n", err); - + atomic_set(&dev->bus_hung, true); + } return err; } diff --git a/drivers/net/wireless/mediatek/mt76/wed.c b/drivers/net/wireless/mediatek/mt76/wed.c index f89e4537555c..63f69e152b1c 100644 --- a/drivers/net/wireless/mediatek/mt76/wed.c +++ b/drivers/net/wireless/mediatek/mt76/wed.c @@ -34,11 +34,10 @@ u32 mt76_wed_init_rx_buf(struct mtk_wed_device *wed, int size) struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed); struct mtk_wed_bm_desc *desc = wed->rx_buf_ring.desc; struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN]; - int i, len = SKB_WITH_OVERHEAD(q->buf_size); struct mt76_txwi_cache *t = NULL; + int i; for (i = 0; i < size; i++) { - enum dma_data_direction dir; dma_addr_t addr; u32 offset; int token; @@ -53,9 +52,6 @@ u32 mt76_wed_init_rx_buf(struct mtk_wed_device *wed, int size) goto unmap; addr = page_pool_get_dma_addr(virt_to_head_page(buf)) + offset; - dir = page_pool_get_dma_dir(q->page_pool); - dma_sync_single_for_device(dev->dma_dev, addr, len, dir); - desc->buf0 = cpu_to_le32(addr); token = mt76_rx_token_consume(dev, buf, t, addr); if (token < 0) { diff --git a/drivers/nfc/trf7970a.c b/drivers/nfc/trf7970a.c index 9e1a34e23af2..d17c701c7888 100644 --- a/drivers/nfc/trf7970a.c +++ b/drivers/nfc/trf7970a.c @@ -272,12 +272,18 @@ #define TRF7970A_MODULATOR_EN_OOK BIT(6) #define TRF7970A_MODULATOR_27MHZ BIT(7) +#define TRF7970A_RX_GAIN_REDUCTION_MAX_DB 15 +#define TRF7970A_RX_GAIN_REDUCTION_DB_PER_LSB 5 #define TRF7970A_RX_SPECIAL_SETTINGS_NO_LIM BIT(0) #define TRF7970A_RX_SPECIAL_SETTINGS_AGCR BIT(1) -#define TRF7970A_RX_SPECIAL_SETTINGS_GD_0DB (0x0 << 2) -#define TRF7970A_RX_SPECIAL_SETTINGS_GD_5DB (0x1 << 2) -#define TRF7970A_RX_SPECIAL_SETTINGS_GD_10DB (0x2 << 2) -#define TRF7970A_RX_SPECIAL_SETTINGS_GD_15DB (0x3 << 2) +#define TRF7970A_RX_SPECIAL_SETTINGS_GD_SHIFT 2 +#define TRF7970A_RX_SPECIAL_SETTINGS_GD_MAX (0x3) +#define TRF7970A_RX_SPECIAL_SETTINGS_GD_MASK (TRF7970A_RX_SPECIAL_SETTINGS_GD_MAX << \ + TRF7970A_RX_SPECIAL_SETTINGS_GD_SHIFT) +#define TRF7970A_RX_SPECIAL_SETTINGS_GD_0DB (0x0 << TRF7970A_RX_SPECIAL_SETTINGS_GD_SHIFT) +#define TRF7970A_RX_SPECIAL_SETTINGS_GD_5DB (0x1 << TRF7970A_RX_SPECIAL_SETTINGS_GD_SHIFT) +#define TRF7970A_RX_SPECIAL_SETTINGS_GD_10DB (0x2 << TRF7970A_RX_SPECIAL_SETTINGS_GD_SHIFT) +#define TRF7970A_RX_SPECIAL_SETTINGS_GD_15DB (0x3 << TRF7970A_RX_SPECIAL_SETTINGS_GD_SHIFT) #define TRF7970A_RX_SPECIAL_SETTINGS_HBT BIT(4) #define TRF7970A_RX_SPECIAL_SETTINGS_M848 BIT(5) #define TRF7970A_RX_SPECIAL_SETTINGS_C424 BIT(6) @@ -452,6 +458,8 @@ struct trf7970a { unsigned int timeout; bool ignore_timeout; struct delayed_work timeout_work; + u8 rx_gain_reduction; + bool custom_rx_gain_reduction; }; static int trf7970a_cmd(struct trf7970a *trf, u8 opcode) @@ -551,6 +559,41 @@ static int trf7970a_read_irqstatus(struct trf7970a *trf, u8 *status) return ret; } +static int trf7970a_update_rx_gain_reduction(struct trf7970a *trf) +{ + int ret = 0; + u8 reg; + + if (!trf->custom_rx_gain_reduction) + return 0; + + ret = trf7970a_read(trf, TRF7970A_RX_SPECIAL_SETTINGS, ®); + if (ret) + return ret; + reg &= ~(TRF7970A_RX_SPECIAL_SETTINGS_GD_MASK); + reg |= trf->rx_gain_reduction; + + ret = trf7970a_write(trf, TRF7970A_RX_SPECIAL_SETTINGS, reg); + + return ret; +} + +static int trf7970a_update_iso_ctrl_register(struct trf7970a *trf, u8 iso_ctrl) +{ + int ret; + + ret = trf7970a_write(trf, TRF7970A_ISO_CTRL, iso_ctrl); + if (ret) + return ret; + /* + * Every time the ISO_CTRL register is written, the RX special setting register is reset by + * the chip. When a custom gain reguduction is required, it should be rewritten now. + */ + ret = trf7970a_update_rx_gain_reduction(trf); + + return ret; +} + static int trf7970a_read_target_proto(struct trf7970a *trf, u8 *target_proto) { int ret; @@ -930,8 +973,7 @@ static irqreturn_t trf7970a_irq(int irq, void *dev_id) } if (iso_ctrl != trf->iso_ctrl) { - ret = trf7970a_write(trf, TRF7970A_ISO_CTRL, - iso_ctrl); + ret = trf7970a_update_iso_ctrl_register(trf, iso_ctrl); if (ret) goto err_unlock_exit; @@ -1035,6 +1077,11 @@ static int trf7970a_init(struct trf7970a *trf) if (ret) goto err_out; + /* Set the gain reduction after soft init */ + ret = trf7970a_update_rx_gain_reduction(trf); + if (ret) + goto err_out; + ret = trf7970a_cmd(trf, TRF7970A_CMD_IDLE); if (ret) goto err_out; @@ -1309,7 +1356,7 @@ static int trf7970a_in_config_framing(struct trf7970a *trf, int framing) } if (iso_ctrl != trf->iso_ctrl) { - ret = trf7970a_write(trf, TRF7970A_ISO_CTRL, iso_ctrl); + ret = trf7970a_update_iso_ctrl_register(trf, iso_ctrl); if (ret) return ret; @@ -1441,7 +1488,7 @@ static int trf7970a_per_cmd_config(struct trf7970a *trf, } if (iso_ctrl != trf->iso_ctrl) { - ret = trf7970a_write(trf, TRF7970A_ISO_CTRL, iso_ctrl); + ret = trf7970a_update_iso_ctrl_register(trf, iso_ctrl); if (ret) return ret; @@ -1605,8 +1652,7 @@ static int trf7970a_tg_config_rf_tech(struct trf7970a *trf, int tech) */ if ((trf->framing == NFC_DIGITAL_FRAMING_NFC_DEP_ACTIVATED) && (trf->iso_ctrl_tech != trf->iso_ctrl)) { - ret = trf7970a_write(trf, TRF7970A_ISO_CTRL, - trf->iso_ctrl_tech); + ret = trf7970a_update_iso_ctrl_register(trf, trf->iso_ctrl_tech); trf->iso_ctrl = trf->iso_ctrl_tech; } @@ -1654,7 +1700,7 @@ static int trf7970a_tg_config_framing(struct trf7970a *trf, int framing) trf->framing = framing; if (iso_ctrl != trf->iso_ctrl) { - ret = trf7970a_write(trf, TRF7970A_ISO_CTRL, iso_ctrl); + ret = trf7970a_update_iso_ctrl_register(trf, iso_ctrl); if (ret) return ret; @@ -1755,6 +1801,10 @@ static int _trf7970a_tg_listen(struct nfc_digital_dev *ddev, u16 timeout, if (ret) goto out_err; + ret = trf7970a_update_rx_gain_reduction(trf); + if (ret) + goto out_err; + ret = trf7970a_write(trf, TRF7970A_REG_IO_CTRL, trf->io_ctrl | TRF7970A_REG_IO_CTRL_VRS(0x1)); if (ret) @@ -1945,6 +1995,10 @@ static int trf7970a_startup(struct trf7970a *trf) if (ret) return ret; + ret = trf7970a_update_rx_gain_reduction(trf); + if (ret) + return ret; + pm_runtime_set_active(trf->dev); pm_runtime_enable(trf->dev); pm_runtime_mark_last_busy(trf->dev); @@ -1993,6 +2047,7 @@ static int trf7970a_probe(struct spi_device *spi) struct trf7970a *trf; int uvolts, autosuspend_delay, ret; u32 clk_freq = TRF7970A_13MHZ_CLOCK_FREQUENCY; + u32 rx_gain_reduction_db; if (!np) { dev_err(&spi->dev, "No Device Tree entry\n"); @@ -2054,6 +2109,20 @@ static int trf7970a_probe(struct spi_device *spi) trf->modulator_sys_clk_ctrl = 0; } + if (of_property_read_u32(np, "ti,rx-gain-reduction-db", &rx_gain_reduction_db) == 0) { + if (rx_gain_reduction_db > TRF7970A_RX_GAIN_REDUCTION_MAX_DB) { + dev_warn(trf->dev, "RX Gain reduction too high. Ignored\n"); + } else if ((rx_gain_reduction_db % TRF7970A_RX_GAIN_REDUCTION_DB_PER_LSB)) { + dev_warn(trf->dev, "RX Gain must be set in 5 dB increments. Ignored\n"); + } else { + dev_dbg(trf->dev, "RX gain set to -%udB\n", rx_gain_reduction_db); + trf->rx_gain_reduction = ((rx_gain_reduction_db / + TRF7970A_RX_GAIN_REDUCTION_DB_PER_LSB) << + TRF7970A_RX_SPECIAL_SETTINGS_GD_SHIFT); + trf->custom_rx_gain_reduction = true; + } + } + ret = devm_request_threaded_irq(trf->dev, spi->irq, NULL, trf7970a_irq, IRQF_TRIGGER_RISING | IRQF_ONESHOT, diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 92697f98c601..e533d791955d 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2015,21 +2015,41 @@ static void nvme_configure_metadata(struct nvme_ctrl *ctrl, } -static void nvme_update_atomic_write_disk_info(struct nvme_ns *ns, - struct nvme_id_ns *id, struct queue_limits *lim, - u32 bs, u32 atomic_bs) +static u32 nvme_configure_atomic_write(struct nvme_ns *ns, + struct nvme_id_ns *id, struct queue_limits *lim, u32 bs) { - unsigned int boundary = 0; + u32 atomic_bs, boundary = 0; - if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf) { - if (le16_to_cpu(id->nabspf)) + /* + * We do not support an offset for the atomic boundaries. + */ + if (id->nabo) + return bs; + + if ((id->nsfeat & NVME_NS_FEAT_ATOMICS) && id->nawupf) { + /* + * Use the per-namespace atomic write unit when available. + */ + atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs; + if (id->nabspf) boundary = (le16_to_cpu(id->nabspf) + 1) * bs; + } else { + /* + * Use the controller wide atomic write unit. This sucks + * because the limit is defined in terms of logical blocks while + * namespaces can have different formats, and because there is + * no clear language in the specification prohibiting different + * values for different controllers in the subsystem. + */ + atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs; } + lim->atomic_write_hw_max = atomic_bs; lim->atomic_write_hw_boundary = boundary; lim->atomic_write_hw_unit_min = bs; lim->atomic_write_hw_unit_max = rounddown_pow_of_two(atomic_bs); lim->features |= BLK_FEAT_ATOMIC_WRITES; + return atomic_bs; } static u32 nvme_max_drv_segments(struct nvme_ctrl *ctrl) @@ -2067,34 +2087,8 @@ static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id, valid = false; } - atomic_bs = phys_bs = bs; - if (id->nabo == 0) { - /* - * Bit 1 indicates whether NAWUPF is defined for this namespace - * and whether it should be used instead of AWUPF. If NAWUPF == - * 0 then AWUPF must be used instead. - */ - if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf) - atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs; - else - atomic_bs = (1 + ns->ctrl->awupf) * bs; - - /* - * Set subsystem atomic bs. - */ - if (ns->ctrl->subsys->atomic_bs) { - if (atomic_bs != ns->ctrl->subsys->atomic_bs) { - dev_err_ratelimited(ns->ctrl->device, - "%s: Inconsistent Atomic Write Size, Namespace will not be added: Subsystem=%d bytes, Controller/Namespace=%d bytes\n", - ns->disk ? ns->disk->disk_name : "?", - ns->ctrl->subsys->atomic_bs, - atomic_bs); - } - } else - ns->ctrl->subsys->atomic_bs = atomic_bs; - - nvme_update_atomic_write_disk_info(ns, id, lim, bs, atomic_bs); - } + phys_bs = bs; + atomic_bs = nvme_configure_atomic_write(ns, id, lim, bs); if (id->nsfeat & NVME_NS_FEAT_IO_OPT) { /* NPWG = Namespace Preferred Write Granularity */ @@ -2382,16 +2376,6 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, if (!nvme_update_disk_info(ns, id, &lim)) capacity = 0; - /* - * Validate the max atomic write size fits within the subsystem's - * atomic write capabilities. - */ - if (lim.atomic_write_hw_max > ns->ctrl->subsys->atomic_bs) { - blk_mq_unfreeze_queue(ns->disk->queue, memflags); - ret = -ENXIO; - goto out; - } - nvme_config_discard(ns, &lim); if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && ns->head->ids.csi == NVME_CSI_ZNS) @@ -3215,6 +3199,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) memcpy(subsys->model, id->mn, sizeof(subsys->model)); subsys->vendor_id = le16_to_cpu(id->vid); subsys->cmic = id->cmic; + subsys->awupf = le16_to_cpu(id->awupf); /* Versions prior to 1.4 don't necessarily report a valid type */ if (id->cntrltype == NVME_CTRL_DISC || @@ -3552,6 +3537,15 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) if (ret) goto out_free; } + + if (le16_to_cpu(id->awupf) != ctrl->subsys->awupf) { + dev_err_ratelimited(ctrl->device, + "inconsistent AWUPF, controller not added (%u/%u).\n", + le16_to_cpu(id->awupf), ctrl->subsys->awupf); + ret = -EINVAL; + goto out_free; + } + memcpy(ctrl->subsys->firmware_rev, id->fr, sizeof(ctrl->subsys->firmware_rev)); @@ -3647,7 +3641,6 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) dev_pm_qos_expose_latency_tolerance(ctrl->device); else if (!ctrl->apst_enabled && prev_apst_enabled) dev_pm_qos_hide_latency_tolerance(ctrl->device); - ctrl->awupf = le16_to_cpu(id->awupf); out_free: kfree(id); return ret; @@ -4036,6 +4029,10 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) list_add_tail_rcu(&ns->siblings, &head->list); ns->head = head; mutex_unlock(&ctrl->subsys->lock); + +#ifdef CONFIG_NVME_MULTIPATH + cancel_delayed_work(&head->remove_work); +#endif return 0; out_put_ns_head: diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index e040e467f9fa..316a269842fa 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -1311,7 +1311,7 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) */ if (!try_module_get(THIS_MODULE)) goto out; - queue_delayed_work(nvme_wq, &head->remove_work, + mod_delayed_work(nvme_wq, &head->remove_work, head->delayed_removal_secs * HZ); } else { list_del_init(&head->entry); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index a468cdc5b5cb..7df2ea21851f 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -410,7 +410,6 @@ struct nvme_ctrl { enum nvme_ctrl_type cntrltype; enum nvme_dctype dctype; - u16 awupf; /* 0's based value. */ }; static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl) @@ -443,11 +442,11 @@ struct nvme_subsystem { u8 cmic; enum nvme_subsys_type subtype; u16 vendor_id; + u16 awupf; /* 0's based value. */ struct ida ns_ida; #ifdef CONFIG_NVME_MULTIPATH enum nvme_iopolicy iopolicy; #endif - u32 atomic_bs; }; /* diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index b78e0e417324..af370628e583 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -1676,19 +1676,24 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) return NULL; root_ops = kzalloc(sizeof(*root_ops), GFP_KERNEL); - if (!root_ops) - goto free_ri; + if (!root_ops) { + kfree(ri); + return NULL; + } ri->cfg = pci_acpi_setup_ecam_mapping(root); - if (!ri->cfg) - goto free_root_ops; + if (!ri->cfg) { + kfree(ri); + kfree(root_ops); + return NULL; + } root_ops->release_info = pci_acpi_generic_release_info; root_ops->prepare_resources = pci_acpi_root_prepare_resources; root_ops->pci_ops = (struct pci_ops *)&ri->cfg->ops->pci_ops; bus = acpi_pci_root_create(root, root_ops, &ri->common, ri->cfg); if (!bus) - goto free_cfg; + return NULL; /* If we must preserve the resource configuration, claim now */ host = pci_find_host_bridge(bus); @@ -1705,14 +1710,6 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) pcie_bus_configure_settings(child); return bus; - -free_cfg: - pci_ecam_free(ri->cfg); -free_root_ops: - kfree(root_ops); -free_ri: - kfree(ri); - return NULL; } void pcibios_add_bus(struct pci_bus *bus) diff --git a/drivers/pci/pcie/ptm.c b/drivers/pci/pcie/ptm.c index ee5f615a9023..4bd73f038ffb 100644 --- a/drivers/pci/pcie/ptm.c +++ b/drivers/pci/pcie/ptm.c @@ -254,6 +254,7 @@ bool pcie_ptm_enabled(struct pci_dev *dev) } EXPORT_SYMBOL(pcie_ptm_enabled); +#if IS_ENABLED(CONFIG_DEBUG_FS) static ssize_t context_update_write(struct file *file, const char __user *ubuf, size_t count, loff_t *ppos) { @@ -552,3 +553,4 @@ void pcie_ptm_destroy_debugfs(struct pci_ptm_debugfs *ptm_debugfs) debugfs_remove_recursive(ptm_debugfs->debugfs); } EXPORT_SYMBOL_GPL(pcie_ptm_destroy_debugfs); +#endif diff --git a/drivers/platform/x86/amd/amd_isp4.c b/drivers/platform/x86/amd/amd_isp4.c index 0cc01441bcbb..9f291aeb35f1 100644 --- a/drivers/platform/x86/amd/amd_isp4.c +++ b/drivers/platform/x86/amd/amd_isp4.c @@ -11,6 +11,7 @@ #include <linux/mutex.h> #include <linux/platform_device.h> #include <linux/property.h> +#include <linux/soc/amd/isp4_misc.h> #include <linux/string.h> #include <linux/types.h> #include <linux/units.h> @@ -151,7 +152,7 @@ MODULE_DEVICE_TABLE(acpi, amdisp_sensor_ids); static inline bool is_isp_i2c_adapter(struct i2c_adapter *adap) { - return !strcmp(adap->owner->name, "i2c_designware_amdisp"); + return !strcmp(adap->name, AMDISP_I2C_ADAP_NAME); } static void instantiate_isp_i2c_client(struct amdisp_platform *isp4_platform, diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index 4bf421765d03..4ca5a464a46a 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -106,11 +106,9 @@ int ptp_set_pinfunc(struct ptp_clock *ptp, unsigned int pin, int ptp_open(struct posix_clock_context *pccontext, fmode_t fmode) { - struct ptp_clock *ptp = - container_of(pccontext->clk, struct ptp_clock, clock); + struct ptp_clock *ptp = container_of(pccontext->clk, struct ptp_clock, clock); struct timestamp_event_queue *queue; char debugfsname[32]; - unsigned long flags; queue = kzalloc(sizeof(*queue), GFP_KERNEL); if (!queue) @@ -122,9 +120,8 @@ int ptp_open(struct posix_clock_context *pccontext, fmode_t fmode) } bitmap_set(queue->mask, 0, PTP_MAX_CHANNELS); spin_lock_init(&queue->lock); - spin_lock_irqsave(&ptp->tsevqs_lock, flags); - list_add_tail(&queue->qlist, &ptp->tsevqs); - spin_unlock_irqrestore(&ptp->tsevqs_lock, flags); + scoped_guard(spinlock_irq, &ptp->tsevqs_lock) + list_add_tail(&queue->qlist, &ptp->tsevqs); pccontext->private_clkdata = queue; /* Debugfs contents */ @@ -143,402 +140,392 @@ int ptp_open(struct posix_clock_context *pccontext, fmode_t fmode) int ptp_release(struct posix_clock_context *pccontext) { struct timestamp_event_queue *queue = pccontext->private_clkdata; - unsigned long flags; struct ptp_clock *ptp = container_of(pccontext->clk, struct ptp_clock, clock); debugfs_remove(queue->debugfs_instance); pccontext->private_clkdata = NULL; - spin_lock_irqsave(&ptp->tsevqs_lock, flags); - list_del(&queue->qlist); - spin_unlock_irqrestore(&ptp->tsevqs_lock, flags); + scoped_guard(spinlock_irq, &ptp->tsevqs_lock) + list_del(&queue->qlist); bitmap_free(queue->mask); kfree(queue); return 0; } -long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd, - unsigned long arg) +static long ptp_clock_getcaps(struct ptp_clock *ptp, void __user *arg) +{ + struct ptp_clock_caps caps = { + .max_adj = ptp->info->max_adj, + .n_alarm = ptp->info->n_alarm, + .n_ext_ts = ptp->info->n_ext_ts, + .n_per_out = ptp->info->n_per_out, + .pps = ptp->info->pps, + .n_pins = ptp->info->n_pins, + .cross_timestamping = ptp->info->getcrosststamp != NULL, + .adjust_phase = ptp->info->adjphase != NULL && + ptp->info->getmaxphase != NULL, + }; + + if (caps.adjust_phase) + caps.max_phase_adj = ptp->info->getmaxphase(ptp->info); + + return copy_to_user(arg, &caps, sizeof(caps)) ? -EFAULT : 0; +} + +static long ptp_extts_request(struct ptp_clock *ptp, unsigned int cmd, void __user *arg) +{ + struct ptp_clock_request req = { .type = PTP_CLK_REQ_EXTTS }; + struct ptp_clock_info *ops = ptp->info; + unsigned int supported_extts_flags; + + if (copy_from_user(&req.extts, arg, sizeof(req.extts))) + return -EFAULT; + + if (cmd == PTP_EXTTS_REQUEST2) { + /* Tell the drivers to check the flags carefully. */ + req.extts.flags |= PTP_STRICT_FLAGS; + /* Make sure no reserved bit is set. */ + if ((req.extts.flags & ~PTP_EXTTS_VALID_FLAGS) || + req.extts.rsv[0] || req.extts.rsv[1]) + return -EINVAL; + + /* Ensure one of the rising/falling edge bits is set. */ + if ((req.extts.flags & PTP_ENABLE_FEATURE) && + (req.extts.flags & PTP_EXTTS_EDGES) == 0) + return -EINVAL; + } else { + req.extts.flags &= PTP_EXTTS_V1_VALID_FLAGS; + memset(req.extts.rsv, 0, sizeof(req.extts.rsv)); + } + + if (req.extts.index >= ops->n_ext_ts) + return -EINVAL; + + supported_extts_flags = ptp->info->supported_extts_flags; + /* The PTP_ENABLE_FEATURE flag is always supported. */ + supported_extts_flags |= PTP_ENABLE_FEATURE; + /* If the driver does not support strictly checking flags, the + * PTP_RISING_EDGE and PTP_FALLING_EDGE flags are merely hints + * which are not enforced. + */ + if (!(supported_extts_flags & PTP_STRICT_FLAGS)) + supported_extts_flags |= PTP_EXTTS_EDGES; + /* Reject unsupported flags */ + if (req.extts.flags & ~supported_extts_flags) + return -EOPNOTSUPP; + + scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &ptp->pincfg_mux) + return ops->enable(ops, &req, req.extts.flags & PTP_ENABLE_FEATURE ? 1 : 0); +} + +static long ptp_perout_request(struct ptp_clock *ptp, unsigned int cmd, void __user *arg) +{ + struct ptp_clock_request req = { .type = PTP_CLK_REQ_PEROUT }; + struct ptp_perout_request *perout = &req.perout; + struct ptp_clock_info *ops = ptp->info; + + if (copy_from_user(perout, arg, sizeof(*perout))) + return -EFAULT; + + if (cmd == PTP_PEROUT_REQUEST2) { + if (perout->flags & ~PTP_PEROUT_VALID_FLAGS) + return -EINVAL; + + /* + * The "on" field has undefined meaning if + * PTP_PEROUT_DUTY_CYCLE isn't set, we must still treat it + * as reserved, which must be set to zero. + */ + if (!(perout->flags & PTP_PEROUT_DUTY_CYCLE) && + !mem_is_zero(perout->rsv, sizeof(perout->rsv))) + return -EINVAL; + + if (perout->flags & PTP_PEROUT_DUTY_CYCLE) { + /* The duty cycle must be subunitary. */ + if (perout->on.sec > perout->period.sec || + (perout->on.sec == perout->period.sec && + perout->on.nsec > perout->period.nsec)) + return -ERANGE; + } + + if (perout->flags & PTP_PEROUT_PHASE) { + /* + * The phase should be specified modulo the period, + * therefore anything equal or larger than 1 period + * is invalid. + */ + if (perout->phase.sec > perout->period.sec || + (perout->phase.sec == perout->period.sec && + perout->phase.nsec >= perout->period.nsec)) + return -ERANGE; + } + } else { + perout->flags &= PTP_PEROUT_V1_VALID_FLAGS; + memset(perout->rsv, 0, sizeof(perout->rsv)); + } + + if (perout->index >= ops->n_per_out) + return -EINVAL; + if (perout->flags & ~ops->supported_perout_flags) + return -EOPNOTSUPP; + + scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &ptp->pincfg_mux) + return ops->enable(ops, &req, perout->period.sec || perout->period.nsec); +} + +static long ptp_enable_pps(struct ptp_clock *ptp, bool enable) +{ + struct ptp_clock_request req = { .type = PTP_CLK_REQ_PPS }; + struct ptp_clock_info *ops = ptp->info; + + if (!capable(CAP_SYS_TIME)) + return -EPERM; + + scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &ptp->pincfg_mux) + return ops->enable(ops, &req, enable); +} + +static long ptp_sys_offset_precise(struct ptp_clock *ptp, void __user *arg) { - struct ptp_clock *ptp = - container_of(pccontext->clk, struct ptp_clock, clock); - unsigned int i, pin_index, supported_extts_flags; - struct ptp_sys_offset_extended *extoff = NULL; struct ptp_sys_offset_precise precise_offset; struct system_device_crosststamp xtstamp; - struct ptp_clock_info *ops = ptp->info; - struct ptp_sys_offset *sysoff = NULL; - struct timestamp_event_queue *tsevq; + struct timespec64 ts; + int err; + + if (!ptp->info->getcrosststamp) + return -EOPNOTSUPP; + + err = ptp->info->getcrosststamp(ptp->info, &xtstamp); + if (err) + return err; + + memset(&precise_offset, 0, sizeof(precise_offset)); + ts = ktime_to_timespec64(xtstamp.device); + precise_offset.device.sec = ts.tv_sec; + precise_offset.device.nsec = ts.tv_nsec; + ts = ktime_to_timespec64(xtstamp.sys_realtime); + precise_offset.sys_realtime.sec = ts.tv_sec; + precise_offset.sys_realtime.nsec = ts.tv_nsec; + ts = ktime_to_timespec64(xtstamp.sys_monoraw); + precise_offset.sys_monoraw.sec = ts.tv_sec; + precise_offset.sys_monoraw.nsec = ts.tv_nsec; + + return copy_to_user(arg, &precise_offset, sizeof(precise_offset)) ? -EFAULT : 0; +} + +static long ptp_sys_offset_extended(struct ptp_clock *ptp, void __user *arg) +{ + struct ptp_sys_offset_extended *extoff __free(kfree) = NULL; struct ptp_system_timestamp sts; - struct ptp_clock_request req; - struct ptp_clock_caps caps; + + if (!ptp->info->gettimex64) + return -EOPNOTSUPP; + + extoff = memdup_user(arg, sizeof(*extoff)); + if (IS_ERR(extoff)) + return PTR_ERR(extoff); + + if (extoff->n_samples > PTP_MAX_SAMPLES || extoff->rsv[0] || extoff->rsv[1]) + return -EINVAL; + + switch (extoff->clockid) { + case CLOCK_REALTIME: + case CLOCK_MONOTONIC: + case CLOCK_MONOTONIC_RAW: + break; + case CLOCK_AUX ... CLOCK_AUX_LAST: + if (IS_ENABLED(CONFIG_POSIX_AUX_CLOCKS)) + break; + fallthrough; + default: + return -EINVAL; + } + + sts.clockid = extoff->clockid; + for (unsigned int i = 0; i < extoff->n_samples; i++) { + struct timespec64 ts; + int err; + + err = ptp->info->gettimex64(ptp->info, &ts, &sts); + if (err) + return err; + + /* Filter out disabled or unavailable clocks */ + if (sts.pre_ts.tv_sec < 0 || sts.post_ts.tv_sec < 0) + return -EINVAL; + + extoff->ts[i][0].sec = sts.pre_ts.tv_sec; + extoff->ts[i][0].nsec = sts.pre_ts.tv_nsec; + extoff->ts[i][1].sec = ts.tv_sec; + extoff->ts[i][1].nsec = ts.tv_nsec; + extoff->ts[i][2].sec = sts.post_ts.tv_sec; + extoff->ts[i][2].nsec = sts.post_ts.tv_nsec; + } + + return copy_to_user(arg, extoff, sizeof(*extoff)) ? -EFAULT : 0; +} + +static long ptp_sys_offset(struct ptp_clock *ptp, void __user *arg) +{ + struct ptp_sys_offset *sysoff __free(kfree) = NULL; struct ptp_clock_time *pct; - struct ptp_pin_desc pd; struct timespec64 ts; - int enable, err = 0; + + sysoff = memdup_user(arg, sizeof(*sysoff)); + if (IS_ERR(sysoff)) + return PTR_ERR(sysoff); + + if (sysoff->n_samples > PTP_MAX_SAMPLES) + return -EINVAL; + + pct = &sysoff->ts[0]; + for (unsigned int i = 0; i < sysoff->n_samples; i++) { + struct ptp_clock_info *ops = ptp->info; + int err; + + ktime_get_real_ts64(&ts); + pct->sec = ts.tv_sec; + pct->nsec = ts.tv_nsec; + pct++; + if (ops->gettimex64) + err = ops->gettimex64(ops, &ts, NULL); + else + err = ops->gettime64(ops, &ts); + if (err) + return err; + pct->sec = ts.tv_sec; + pct->nsec = ts.tv_nsec; + pct++; + } + ktime_get_real_ts64(&ts); + pct->sec = ts.tv_sec; + pct->nsec = ts.tv_nsec; + + return copy_to_user(arg, sysoff, sizeof(*sysoff)) ? -EFAULT : 0; +} + +static long ptp_pin_getfunc(struct ptp_clock *ptp, unsigned int cmd, void __user *arg) +{ + struct ptp_clock_info *ops = ptp->info; + struct ptp_pin_desc pd; + + if (copy_from_user(&pd, arg, sizeof(pd))) + return -EFAULT; + + if (cmd == PTP_PIN_GETFUNC2 && !mem_is_zero(pd.rsv, sizeof(pd.rsv))) + return -EINVAL; + + if (pd.index >= ops->n_pins) + return -EINVAL; + + scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &ptp->pincfg_mux) + pd = ops->pin_config[array_index_nospec(pd.index, ops->n_pins)]; + + return copy_to_user(arg, &pd, sizeof(pd)) ? -EFAULT : 0; +} + +static long ptp_pin_setfunc(struct ptp_clock *ptp, unsigned int cmd, void __user *arg) +{ + struct ptp_clock_info *ops = ptp->info; + struct ptp_pin_desc pd; + unsigned int pin_index; + + if (copy_from_user(&pd, arg, sizeof(pd))) + return -EFAULT; + + if (cmd == PTP_PIN_SETFUNC2 && !mem_is_zero(pd.rsv, sizeof(pd.rsv))) + return -EINVAL; + + if (pd.index >= ops->n_pins) + return -EINVAL; + + pin_index = array_index_nospec(pd.index, ops->n_pins); + scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &ptp->pincfg_mux) + return ptp_set_pinfunc(ptp, pin_index, pd.func, pd.chan); +} + +static long ptp_mask_clear_all(struct timestamp_event_queue *tsevq) +{ + bitmap_clear(tsevq->mask, 0, PTP_MAX_CHANNELS); + return 0; +} + +static long ptp_mask_en_single(struct timestamp_event_queue *tsevq, void __user *arg) +{ + unsigned int channel; + + if (copy_from_user(&channel, arg, sizeof(channel))) + return -EFAULT; + if (channel >= PTP_MAX_CHANNELS) + return -EFAULT; + set_bit(channel, tsevq->mask); + return 0; +} + +long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd, + unsigned long arg) +{ + struct ptp_clock *ptp = container_of(pccontext->clk, struct ptp_clock, clock); + void __user *argptr; if (in_compat_syscall() && cmd != PTP_ENABLE_PPS && cmd != PTP_ENABLE_PPS2) arg = (unsigned long)compat_ptr(arg); - - tsevq = pccontext->private_clkdata; + argptr = (void __force __user *)arg; switch (cmd) { - case PTP_CLOCK_GETCAPS: case PTP_CLOCK_GETCAPS2: - memset(&caps, 0, sizeof(caps)); - - caps.max_adj = ptp->info->max_adj; - caps.n_alarm = ptp->info->n_alarm; - caps.n_ext_ts = ptp->info->n_ext_ts; - caps.n_per_out = ptp->info->n_per_out; - caps.pps = ptp->info->pps; - caps.n_pins = ptp->info->n_pins; - caps.cross_timestamping = ptp->info->getcrosststamp != NULL; - caps.adjust_phase = ptp->info->adjphase != NULL && - ptp->info->getmaxphase != NULL; - if (caps.adjust_phase) - caps.max_phase_adj = ptp->info->getmaxphase(ptp->info); - if (copy_to_user((void __user *)arg, &caps, sizeof(caps))) - err = -EFAULT; - break; + return ptp_clock_getcaps(ptp, argptr); case PTP_EXTTS_REQUEST: case PTP_EXTTS_REQUEST2: - if ((pccontext->fp->f_mode & FMODE_WRITE) == 0) { - err = -EACCES; - break; - } - memset(&req, 0, sizeof(req)); - - if (copy_from_user(&req.extts, (void __user *)arg, - sizeof(req.extts))) { - err = -EFAULT; - break; - } - if (cmd == PTP_EXTTS_REQUEST2) { - /* Tell the drivers to check the flags carefully. */ - req.extts.flags |= PTP_STRICT_FLAGS; - /* Make sure no reserved bit is set. */ - if ((req.extts.flags & ~PTP_EXTTS_VALID_FLAGS) || - req.extts.rsv[0] || req.extts.rsv[1]) { - err = -EINVAL; - break; - } - /* Ensure one of the rising/falling edge bits is set. */ - if ((req.extts.flags & PTP_ENABLE_FEATURE) && - (req.extts.flags & PTP_EXTTS_EDGES) == 0) { - err = -EINVAL; - break; - } - } else if (cmd == PTP_EXTTS_REQUEST) { - req.extts.flags &= PTP_EXTTS_V1_VALID_FLAGS; - req.extts.rsv[0] = 0; - req.extts.rsv[1] = 0; - } - if (req.extts.index >= ops->n_ext_ts) { - err = -EINVAL; - break; - } - supported_extts_flags = ptp->info->supported_extts_flags; - /* The PTP_ENABLE_FEATURE flag is always supported. */ - supported_extts_flags |= PTP_ENABLE_FEATURE; - /* If the driver does not support strictly checking flags, the - * PTP_RISING_EDGE and PTP_FALLING_EDGE flags are merely - * hints which are not enforced. - */ - if (!(supported_extts_flags & PTP_STRICT_FLAGS)) - supported_extts_flags |= PTP_EXTTS_EDGES; - /* Reject unsupported flags */ - if (req.extts.flags & ~supported_extts_flags) - return -EOPNOTSUPP; - req.type = PTP_CLK_REQ_EXTTS; - enable = req.extts.flags & PTP_ENABLE_FEATURE ? 1 : 0; - if (mutex_lock_interruptible(&ptp->pincfg_mux)) - return -ERESTARTSYS; - err = ops->enable(ops, &req, enable); - mutex_unlock(&ptp->pincfg_mux); - break; + if ((pccontext->fp->f_mode & FMODE_WRITE) == 0) + return -EACCES; + return ptp_extts_request(ptp, cmd, argptr); case PTP_PEROUT_REQUEST: case PTP_PEROUT_REQUEST2: - if ((pccontext->fp->f_mode & FMODE_WRITE) == 0) { - err = -EACCES; - break; - } - memset(&req, 0, sizeof(req)); - - if (copy_from_user(&req.perout, (void __user *)arg, - sizeof(req.perout))) { - err = -EFAULT; - break; - } - if (cmd == PTP_PEROUT_REQUEST2) { - struct ptp_perout_request *perout = &req.perout; - - if (perout->flags & ~PTP_PEROUT_VALID_FLAGS) { - err = -EINVAL; - break; - } - /* - * The "on" field has undefined meaning if - * PTP_PEROUT_DUTY_CYCLE isn't set, we must still treat - * it as reserved, which must be set to zero. - */ - if (!(perout->flags & PTP_PEROUT_DUTY_CYCLE) && - (perout->rsv[0] || perout->rsv[1] || - perout->rsv[2] || perout->rsv[3])) { - err = -EINVAL; - break; - } - if (perout->flags & PTP_PEROUT_DUTY_CYCLE) { - /* The duty cycle must be subunitary. */ - if (perout->on.sec > perout->period.sec || - (perout->on.sec == perout->period.sec && - perout->on.nsec > perout->period.nsec)) { - err = -ERANGE; - break; - } - } - if (perout->flags & PTP_PEROUT_PHASE) { - /* - * The phase should be specified modulo the - * period, therefore anything equal or larger - * than 1 period is invalid. - */ - if (perout->phase.sec > perout->period.sec || - (perout->phase.sec == perout->period.sec && - perout->phase.nsec >= perout->period.nsec)) { - err = -ERANGE; - break; - } - } - } else if (cmd == PTP_PEROUT_REQUEST) { - req.perout.flags &= PTP_PEROUT_V1_VALID_FLAGS; - req.perout.rsv[0] = 0; - req.perout.rsv[1] = 0; - req.perout.rsv[2] = 0; - req.perout.rsv[3] = 0; - } - if (req.perout.index >= ops->n_per_out) { - err = -EINVAL; - break; - } - if (req.perout.flags & ~ptp->info->supported_perout_flags) - return -EOPNOTSUPP; - req.type = PTP_CLK_REQ_PEROUT; - enable = req.perout.period.sec || req.perout.period.nsec; - if (mutex_lock_interruptible(&ptp->pincfg_mux)) - return -ERESTARTSYS; - err = ops->enable(ops, &req, enable); - mutex_unlock(&ptp->pincfg_mux); - break; + if ((pccontext->fp->f_mode & FMODE_WRITE) == 0) + return -EACCES; + return ptp_perout_request(ptp, cmd, argptr); case PTP_ENABLE_PPS: case PTP_ENABLE_PPS2: - if ((pccontext->fp->f_mode & FMODE_WRITE) == 0) { - err = -EACCES; - break; - } - memset(&req, 0, sizeof(req)); - - if (!capable(CAP_SYS_TIME)) - return -EPERM; - req.type = PTP_CLK_REQ_PPS; - enable = arg ? 1 : 0; - if (mutex_lock_interruptible(&ptp->pincfg_mux)) - return -ERESTARTSYS; - err = ops->enable(ops, &req, enable); - mutex_unlock(&ptp->pincfg_mux); - break; + if ((pccontext->fp->f_mode & FMODE_WRITE) == 0) + return -EACCES; + return ptp_enable_pps(ptp, !!arg); case PTP_SYS_OFFSET_PRECISE: case PTP_SYS_OFFSET_PRECISE2: - if (!ptp->info->getcrosststamp) { - err = -EOPNOTSUPP; - break; - } - err = ptp->info->getcrosststamp(ptp->info, &xtstamp); - if (err) - break; - - memset(&precise_offset, 0, sizeof(precise_offset)); - ts = ktime_to_timespec64(xtstamp.device); - precise_offset.device.sec = ts.tv_sec; - precise_offset.device.nsec = ts.tv_nsec; - ts = ktime_to_timespec64(xtstamp.sys_realtime); - precise_offset.sys_realtime.sec = ts.tv_sec; - precise_offset.sys_realtime.nsec = ts.tv_nsec; - ts = ktime_to_timespec64(xtstamp.sys_monoraw); - precise_offset.sys_monoraw.sec = ts.tv_sec; - precise_offset.sys_monoraw.nsec = ts.tv_nsec; - if (copy_to_user((void __user *)arg, &precise_offset, - sizeof(precise_offset))) - err = -EFAULT; - break; + return ptp_sys_offset_precise(ptp, argptr); case PTP_SYS_OFFSET_EXTENDED: case PTP_SYS_OFFSET_EXTENDED2: - if (!ptp->info->gettimex64) { - err = -EOPNOTSUPP; - break; - } - extoff = memdup_user((void __user *)arg, sizeof(*extoff)); - if (IS_ERR(extoff)) { - err = PTR_ERR(extoff); - extoff = NULL; - break; - } - if (extoff->n_samples > PTP_MAX_SAMPLES || - extoff->rsv[0] || extoff->rsv[1] || - (extoff->clockid != CLOCK_REALTIME && - extoff->clockid != CLOCK_MONOTONIC && - extoff->clockid != CLOCK_MONOTONIC_RAW)) { - err = -EINVAL; - break; - } - sts.clockid = extoff->clockid; - for (i = 0; i < extoff->n_samples; i++) { - err = ptp->info->gettimex64(ptp->info, &ts, &sts); - if (err) - goto out; - extoff->ts[i][0].sec = sts.pre_ts.tv_sec; - extoff->ts[i][0].nsec = sts.pre_ts.tv_nsec; - extoff->ts[i][1].sec = ts.tv_sec; - extoff->ts[i][1].nsec = ts.tv_nsec; - extoff->ts[i][2].sec = sts.post_ts.tv_sec; - extoff->ts[i][2].nsec = sts.post_ts.tv_nsec; - } - if (copy_to_user((void __user *)arg, extoff, sizeof(*extoff))) - err = -EFAULT; - break; + return ptp_sys_offset_extended(ptp, argptr); case PTP_SYS_OFFSET: case PTP_SYS_OFFSET2: - sysoff = memdup_user((void __user *)arg, sizeof(*sysoff)); - if (IS_ERR(sysoff)) { - err = PTR_ERR(sysoff); - sysoff = NULL; - break; - } - if (sysoff->n_samples > PTP_MAX_SAMPLES) { - err = -EINVAL; - break; - } - pct = &sysoff->ts[0]; - for (i = 0; i < sysoff->n_samples; i++) { - ktime_get_real_ts64(&ts); - pct->sec = ts.tv_sec; - pct->nsec = ts.tv_nsec; - pct++; - if (ops->gettimex64) - err = ops->gettimex64(ops, &ts, NULL); - else - err = ops->gettime64(ops, &ts); - if (err) - goto out; - pct->sec = ts.tv_sec; - pct->nsec = ts.tv_nsec; - pct++; - } - ktime_get_real_ts64(&ts); - pct->sec = ts.tv_sec; - pct->nsec = ts.tv_nsec; - if (copy_to_user((void __user *)arg, sysoff, sizeof(*sysoff))) - err = -EFAULT; - break; + return ptp_sys_offset(ptp, argptr); case PTP_PIN_GETFUNC: case PTP_PIN_GETFUNC2: - if (copy_from_user(&pd, (void __user *)arg, sizeof(pd))) { - err = -EFAULT; - break; - } - if ((pd.rsv[0] || pd.rsv[1] || pd.rsv[2] - || pd.rsv[3] || pd.rsv[4]) - && cmd == PTP_PIN_GETFUNC2) { - err = -EINVAL; - break; - } else if (cmd == PTP_PIN_GETFUNC) { - pd.rsv[0] = 0; - pd.rsv[1] = 0; - pd.rsv[2] = 0; - pd.rsv[3] = 0; - pd.rsv[4] = 0; - } - pin_index = pd.index; - if (pin_index >= ops->n_pins) { - err = -EINVAL; - break; - } - pin_index = array_index_nospec(pin_index, ops->n_pins); - if (mutex_lock_interruptible(&ptp->pincfg_mux)) - return -ERESTARTSYS; - pd = ops->pin_config[pin_index]; - mutex_unlock(&ptp->pincfg_mux); - if (!err && copy_to_user((void __user *)arg, &pd, sizeof(pd))) - err = -EFAULT; - break; + return ptp_pin_getfunc(ptp, cmd, argptr); case PTP_PIN_SETFUNC: case PTP_PIN_SETFUNC2: - if ((pccontext->fp->f_mode & FMODE_WRITE) == 0) { - err = -EACCES; - break; - } - if (copy_from_user(&pd, (void __user *)arg, sizeof(pd))) { - err = -EFAULT; - break; - } - if ((pd.rsv[0] || pd.rsv[1] || pd.rsv[2] - || pd.rsv[3] || pd.rsv[4]) - && cmd == PTP_PIN_SETFUNC2) { - err = -EINVAL; - break; - } else if (cmd == PTP_PIN_SETFUNC) { - pd.rsv[0] = 0; - pd.rsv[1] = 0; - pd.rsv[2] = 0; - pd.rsv[3] = 0; - pd.rsv[4] = 0; - } - pin_index = pd.index; - if (pin_index >= ops->n_pins) { - err = -EINVAL; - break; - } - pin_index = array_index_nospec(pin_index, ops->n_pins); - if (mutex_lock_interruptible(&ptp->pincfg_mux)) - return -ERESTARTSYS; - err = ptp_set_pinfunc(ptp, pin_index, pd.func, pd.chan); - mutex_unlock(&ptp->pincfg_mux); - break; + if ((pccontext->fp->f_mode & FMODE_WRITE) == 0) + return -EACCES; + return ptp_pin_setfunc(ptp, cmd, argptr); case PTP_MASK_CLEAR_ALL: - bitmap_clear(tsevq->mask, 0, PTP_MAX_CHANNELS); - break; + return ptp_mask_clear_all(pccontext->private_clkdata); case PTP_MASK_EN_SINGLE: - if (copy_from_user(&i, (void __user *)arg, sizeof(i))) { - err = -EFAULT; - break; - } - if (i >= PTP_MAX_CHANNELS) { - err = -EFAULT; - break; - } - set_bit(i, tsevq->mask); - break; + return ptp_mask_en_single(pccontext->private_clkdata, argptr); default: - err = -ENOTTY; - break; + return -ENOTTY; } - -out: - kfree(extoff); - kfree(sysoff); - return err; } __poll_t ptp_poll(struct posix_clock_context *pccontext, struct file *fp, @@ -562,71 +549,46 @@ __poll_t ptp_poll(struct posix_clock_context *pccontext, struct file *fp, ssize_t ptp_read(struct posix_clock_context *pccontext, uint rdflags, char __user *buf, size_t cnt) { - struct ptp_clock *ptp = - container_of(pccontext->clk, struct ptp_clock, clock); + struct ptp_clock *ptp = container_of(pccontext->clk, struct ptp_clock, clock); struct timestamp_event_queue *queue; struct ptp_extts_event *event; - unsigned long flags; - size_t qcnt, i; - int result; + ssize_t result; queue = pccontext->private_clkdata; - if (!queue) { - result = -EINVAL; - goto exit; - } + if (!queue) + return -EINVAL; - if (cnt % sizeof(struct ptp_extts_event) != 0) { - result = -EINVAL; - goto exit; - } + if (cnt % sizeof(*event) != 0) + return -EINVAL; if (cnt > EXTTS_BUFSIZE) cnt = EXTTS_BUFSIZE; - cnt = cnt / sizeof(struct ptp_extts_event); - - if (wait_event_interruptible(ptp->tsev_wq, - ptp->defunct || queue_cnt(queue))) { + if (wait_event_interruptible(ptp->tsev_wq, ptp->defunct || queue_cnt(queue))) return -ERESTARTSYS; - } - if (ptp->defunct) { - result = -ENODEV; - goto exit; - } + if (ptp->defunct) + return -ENODEV; event = kmalloc(EXTTS_BUFSIZE, GFP_KERNEL); - if (!event) { - result = -ENOMEM; - goto exit; - } - - spin_lock_irqsave(&queue->lock, flags); + if (!event) + return -ENOMEM; - qcnt = queue_cnt(queue); + scoped_guard(spinlock_irq, &queue->lock) { + size_t qcnt = min((size_t)queue_cnt(queue), cnt / sizeof(*event)); - if (cnt > qcnt) - cnt = qcnt; - - for (i = 0; i < cnt; i++) { - event[i] = queue->buf[queue->head]; - /* Paired with READ_ONCE() in queue_cnt() */ - WRITE_ONCE(queue->head, (queue->head + 1) % PTP_MAX_TIMESTAMPS); + for (size_t i = 0; i < qcnt; i++) { + event[i] = queue->buf[queue->head]; + /* Paired with READ_ONCE() in queue_cnt() */ + WRITE_ONCE(queue->head, (queue->head + 1) % PTP_MAX_TIMESTAMPS); + } + cnt = qcnt * sizeof(*event); } - spin_unlock_irqrestore(&queue->lock, flags); - - cnt = cnt * sizeof(struct ptp_extts_event); - result = cnt; - if (copy_to_user(buf, event, cnt)) { + if (copy_to_user(buf, event, cnt)) result = -EFAULT; - goto free_event; - } -free_event: kfree(event); -exit: return result; } diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index 8172869bd3d7..0743c6acd6e2 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -692,8 +692,12 @@ static irqreturn_t cmos_interrupt(int irq, void *p) { u8 irqstat; u8 rtc_control; + unsigned long flags; - spin_lock(&rtc_lock); + /* We cannot use spin_lock() here, as cmos_interrupt() is also called + * in a non-irq context. + */ + spin_lock_irqsave(&rtc_lock, flags); /* When the HPET interrupt handler calls us, the interrupt * status is passed as arg1 instead of the irq number. But @@ -727,7 +731,7 @@ static irqreturn_t cmos_interrupt(int irq, void *p) hpet_mask_rtc_irq_bit(RTC_AIE); CMOS_READ(RTC_INTR_FLAGS); } - spin_unlock(&rtc_lock); + spin_unlock_irqrestore(&rtc_lock, flags); if (is_intr(irqstat)) { rtc_update_irq(p, 1, irqstat); @@ -1295,9 +1299,7 @@ static void cmos_check_wkalrm(struct device *dev) * ACK the rtc irq here */ if (t_now >= cmos->alarm_expires && cmos_use_acpi_alarm()) { - local_irq_disable(); cmos_interrupt(0, (void *)cmos->rtc); - local_irq_enable(); return; } diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c index 31c7dca8f469..2e1ac0c42e93 100644 --- a/drivers/rtc/rtc-pcf2127.c +++ b/drivers/rtc/rtc-pcf2127.c @@ -1538,7 +1538,12 @@ static int pcf2127_spi_probe(struct spi_device *spi) variant = &pcf21xx_cfg[type]; } - config.max_register = variant->max_register, + if (variant->type == PCF2131) { + config.read_flag_mask = 0x0; + config.write_flag_mask = 0x0; + } + + config.max_register = variant->max_register; regmap = devm_regmap_init_spi(spi, &config); if (IS_ERR(regmap)) { diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c index db5c9b641277..a7220b4d0e8d 100644 --- a/drivers/rtc/rtc-s5m.c +++ b/drivers/rtc/rtc-s5m.c @@ -10,6 +10,7 @@ #include <linux/module.h> #include <linux/i2c.h> #include <linux/bcd.h> +#include <linux/reboot.h> #include <linux/regmap.h> #include <linux/rtc.h> #include <linux/platform_device.h> @@ -53,6 +54,7 @@ enum { * Device | Write time | Read time | Write alarm * ================================================= * S5M8767 | UDR + TIME | | UDR + * S2MPG10 | WUDR | RUDR | AUDR * S2MPS11/14 | WUDR | RUDR | WUDR + RUDR * S2MPS13 | WUDR | RUDR | WUDR + AUDR * S2MPS15 | WUDR | RUDR | AUDR @@ -99,6 +101,20 @@ static const struct s5m_rtc_reg_config s5m_rtc_regs = { .write_alarm_udr_mask = S5M_RTC_UDR_MASK, }; +/* Register map for S2MPG10 */ +static const struct s5m_rtc_reg_config s2mpg10_rtc_regs = { + .regs_count = 7, + .time = S2MPG10_RTC_SEC, + .ctrl = S2MPG10_RTC_CTRL, + .alarm0 = S2MPG10_RTC_A0SEC, + .alarm1 = S2MPG10_RTC_A1SEC, + .udr_update = S2MPG10_RTC_UPDATE, + .autoclear_udr_mask = S2MPS15_RTC_WUDR_MASK | S2MPS15_RTC_AUDR_MASK, + .read_time_udr_mask = S2MPS_RTC_RUDR_MASK, + .write_time_udr_mask = S2MPS15_RTC_WUDR_MASK, + .write_alarm_udr_mask = S2MPS15_RTC_AUDR_MASK, +}; + /* Register map for S2MPS13 */ static const struct s5m_rtc_reg_config s2mps13_rtc_regs = { .regs_count = 7, @@ -227,8 +243,8 @@ static int s5m8767_wait_for_udr_update(struct s5m_rtc_info *info) return ret; } -static int s5m_check_peding_alarm_interrupt(struct s5m_rtc_info *info, - struct rtc_wkalrm *alarm) +static int s5m_check_pending_alarm_interrupt(struct s5m_rtc_info *info, + struct rtc_wkalrm *alarm) { int ret; unsigned int val; @@ -238,6 +254,7 @@ static int s5m_check_peding_alarm_interrupt(struct s5m_rtc_info *info, ret = regmap_read(info->regmap, S5M_RTC_STATUS, &val); val &= S5M_ALARM0_STATUS; break; + case S2MPG10: case S2MPS15X: case S2MPS14X: case S2MPS13X: @@ -262,17 +279,9 @@ static int s5m_check_peding_alarm_interrupt(struct s5m_rtc_info *info, static int s5m8767_rtc_set_time_reg(struct s5m_rtc_info *info) { int ret; - unsigned int data; - ret = regmap_read(info->regmap, info->regs->udr_update, &data); - if (ret < 0) { - dev_err(info->dev, "failed to read update reg(%d)\n", ret); - return ret; - } - - data |= info->regs->write_time_udr_mask; - - ret = regmap_write(info->regmap, info->regs->udr_update, data); + ret = regmap_set_bits(info->regmap, info->regs->udr_update, + info->regs->write_time_udr_mask); if (ret < 0) { dev_err(info->dev, "failed to write update reg(%d)\n", ret); return ret; @@ -286,20 +295,14 @@ static int s5m8767_rtc_set_time_reg(struct s5m_rtc_info *info) static int s5m8767_rtc_set_alarm_reg(struct s5m_rtc_info *info) { int ret; - unsigned int data; + unsigned int udr_mask; - ret = regmap_read(info->regmap, info->regs->udr_update, &data); - if (ret < 0) { - dev_err(info->dev, "%s: fail to read update reg(%d)\n", - __func__, ret); - return ret; - } - - data |= info->regs->write_alarm_udr_mask; + udr_mask = info->regs->write_alarm_udr_mask; switch (info->device_type) { case S5M8767X: - data &= ~S5M_RTC_TIME_EN_MASK; + udr_mask |= S5M_RTC_TIME_EN_MASK; break; + case S2MPG10: case S2MPS15X: case S2MPS14X: case S2MPS13X: @@ -309,7 +312,8 @@ static int s5m8767_rtc_set_alarm_reg(struct s5m_rtc_info *info) return -EINVAL; } - ret = regmap_write(info->regmap, info->regs->udr_update, data); + ret = regmap_update_bits(info->regmap, info->regs->udr_update, + udr_mask, info->regs->write_alarm_udr_mask); if (ret < 0) { dev_err(info->dev, "%s: fail to write update reg(%d)\n", __func__, ret); @@ -320,8 +324,8 @@ static int s5m8767_rtc_set_alarm_reg(struct s5m_rtc_info *info) /* On S2MPS13 the AUDR is not auto-cleared */ if (info->device_type == S2MPS13X) - regmap_update_bits(info->regmap, info->regs->udr_update, - S2MPS13_RTC_AUDR_MASK, 0); + regmap_clear_bits(info->regmap, info->regs->udr_update, + S2MPS13_RTC_AUDR_MASK); return ret; } @@ -333,10 +337,8 @@ static int s5m_rtc_read_time(struct device *dev, struct rtc_time *tm) int ret; if (info->regs->read_time_udr_mask) { - ret = regmap_update_bits(info->regmap, - info->regs->udr_update, - info->regs->read_time_udr_mask, - info->regs->read_time_udr_mask); + ret = regmap_set_bits(info->regmap, info->regs->udr_update, + info->regs->read_time_udr_mask); if (ret) { dev_err(dev, "Failed to prepare registers for time reading: %d\n", @@ -351,6 +353,7 @@ static int s5m_rtc_read_time(struct device *dev, struct rtc_time *tm) switch (info->device_type) { case S5M8767X: + case S2MPG10: case S2MPS15X: case S2MPS14X: case S2MPS13X: @@ -374,6 +377,7 @@ static int s5m_rtc_set_time(struct device *dev, struct rtc_time *tm) switch (info->device_type) { case S5M8767X: + case S2MPG10: case S2MPS15X: case S2MPS14X: case S2MPS13X: @@ -411,6 +415,7 @@ static int s5m_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) switch (info->device_type) { case S5M8767X: + case S2MPG10: case S2MPS15X: case S2MPS14X: case S2MPS13X: @@ -430,7 +435,7 @@ static int s5m_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) dev_dbg(dev, "%s: %ptR(%d)\n", __func__, &alrm->time, alrm->time.tm_wday); - return s5m_check_peding_alarm_interrupt(info, alrm); + return s5m_check_pending_alarm_interrupt(info, alrm); } static int s5m_rtc_stop_alarm(struct s5m_rtc_info *info) @@ -449,6 +454,7 @@ static int s5m_rtc_stop_alarm(struct s5m_rtc_info *info) switch (info->device_type) { case S5M8767X: + case S2MPG10: case S2MPS15X: case S2MPS14X: case S2MPS13X: @@ -487,6 +493,7 @@ static int s5m_rtc_start_alarm(struct s5m_rtc_info *info) switch (info->device_type) { case S5M8767X: + case S2MPG10: case S2MPS15X: case S2MPS14X: case S2MPS13X: @@ -524,6 +531,7 @@ static int s5m_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) switch (info->device_type) { case S5M8767X: + case S2MPG10: case S2MPS15X: case S2MPS14X: case S2MPS13X: @@ -604,6 +612,7 @@ static int s5m8767_rtc_init_reg(struct s5m_rtc_info *info) ret = regmap_raw_write(info->regmap, S5M_ALARM0_CONF, data, 2); break; + case S2MPG10: case S2MPS15X: case S2MPS14X: case S2MPS13X: @@ -634,59 +643,92 @@ static int s5m8767_rtc_init_reg(struct s5m_rtc_info *info) return ret; } +static int s5m_rtc_restart_s2mpg10(struct sys_off_data *data) +{ + struct s5m_rtc_info *info = data->cb_data; + int ret; + + if (data->mode != REBOOT_COLD && data->mode != REBOOT_HARD) + return NOTIFY_DONE; + + /* + * Arm watchdog with maximum timeout (2 seconds), and perform full reset + * on expiry. + */ + ret = regmap_set_bits(info->regmap, S2MPG10_RTC_WTSR, + (S2MPG10_WTSR_COLDTIMER | S2MPG10_WTSR_COLDRST + | S2MPG10_WTSR_WTSRT | S2MPG10_WTSR_WTSR_EN)); + + return ret ? NOTIFY_BAD : NOTIFY_DONE; +} + static int s5m_rtc_probe(struct platform_device *pdev) { struct sec_pmic_dev *s5m87xx = dev_get_drvdata(pdev->dev.parent); + enum sec_device_type device_type = + platform_get_device_id(pdev)->driver_data; struct s5m_rtc_info *info; - struct i2c_client *i2c; - const struct regmap_config *regmap_cfg; int ret, alarm_irq; info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL); if (!info) return -ENOMEM; - switch (platform_get_device_id(pdev)->driver_data) { - case S2MPS15X: - regmap_cfg = &s2mps14_rtc_regmap_config; - info->regs = &s2mps15_rtc_regs; - alarm_irq = S2MPS14_IRQ_RTCA0; - break; - case S2MPS14X: - regmap_cfg = &s2mps14_rtc_regmap_config; - info->regs = &s2mps14_rtc_regs; - alarm_irq = S2MPS14_IRQ_RTCA0; - break; - case S2MPS13X: - regmap_cfg = &s2mps14_rtc_regmap_config; - info->regs = &s2mps13_rtc_regs; - alarm_irq = S2MPS14_IRQ_RTCA0; - break; - case S5M8767X: - regmap_cfg = &s5m_rtc_regmap_config; - info->regs = &s5m_rtc_regs; - alarm_irq = S5M8767_IRQ_RTCA1; - break; - default: - return dev_err_probe(&pdev->dev, -ENODEV, - "Device type %lu is not supported by RTC driver\n", - platform_get_device_id(pdev)->driver_data); - } + info->regmap = dev_get_regmap(pdev->dev.parent, "rtc"); + if (!info->regmap) { + const struct regmap_config *regmap_cfg; + struct i2c_client *i2c; - i2c = devm_i2c_new_dummy_device(&pdev->dev, s5m87xx->i2c->adapter, - RTC_I2C_ADDR); - if (IS_ERR(i2c)) - return dev_err_probe(&pdev->dev, PTR_ERR(i2c), - "Failed to allocate I2C for RTC\n"); + switch (device_type) { + case S2MPS15X: + regmap_cfg = &s2mps14_rtc_regmap_config; + info->regs = &s2mps15_rtc_regs; + alarm_irq = S2MPS14_IRQ_RTCA0; + break; + case S2MPS14X: + regmap_cfg = &s2mps14_rtc_regmap_config; + info->regs = &s2mps14_rtc_regs; + alarm_irq = S2MPS14_IRQ_RTCA0; + break; + case S2MPS13X: + regmap_cfg = &s2mps14_rtc_regmap_config; + info->regs = &s2mps13_rtc_regs; + alarm_irq = S2MPS14_IRQ_RTCA0; + break; + case S5M8767X: + regmap_cfg = &s5m_rtc_regmap_config; + info->regs = &s5m_rtc_regs; + alarm_irq = S5M8767_IRQ_RTCA1; + break; + default: + return dev_err_probe(&pdev->dev, -ENODEV, + "Unsupported device type %d\n", + device_type); + } - info->regmap = devm_regmap_init_i2c(i2c, regmap_cfg); - if (IS_ERR(info->regmap)) - return dev_err_probe(&pdev->dev, PTR_ERR(info->regmap), - "Failed to allocate RTC register map\n"); + i2c = devm_i2c_new_dummy_device(&pdev->dev, + s5m87xx->i2c->adapter, + RTC_I2C_ADDR); + if (IS_ERR(i2c)) + return dev_err_probe(&pdev->dev, PTR_ERR(i2c), + "Failed to allocate I2C\n"); + + info->regmap = devm_regmap_init_i2c(i2c, regmap_cfg); + if (IS_ERR(info->regmap)) + return dev_err_probe(&pdev->dev, PTR_ERR(info->regmap), + "Failed to allocate regmap\n"); + } else if (device_type == S2MPG10) { + info->regs = &s2mpg10_rtc_regs; + alarm_irq = S2MPG10_IRQ_RTCA0; + } else { + return dev_err_probe(&pdev->dev, -ENODEV, + "Unsupported device type %d\n", + device_type); + } info->dev = &pdev->dev; info->s5m87xx = s5m87xx; - info->device_type = platform_get_device_id(pdev)->driver_data; + info->device_type = device_type; if (s5m87xx->irq_data) { info->irq = regmap_irq_get_virq(s5m87xx->irq_data, alarm_irq); @@ -721,7 +763,23 @@ static int s5m_rtc_probe(struct platform_device *pdev) return dev_err_probe(&pdev->dev, ret, "Failed to request alarm IRQ %d\n", info->irq); - device_init_wakeup(&pdev->dev, true); + + ret = devm_device_init_wakeup(&pdev->dev); + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, + "Failed to init wakeup\n"); + } + + if (of_device_is_system_power_controller(pdev->dev.parent->of_node) && + info->device_type == S2MPG10) { + ret = devm_register_sys_off_handler(&pdev->dev, + SYS_OFF_MODE_RESTART, + SYS_OFF_PRIO_HIGH + 1, + s5m_rtc_restart_s2mpg10, + info); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "Failed to register restart handler\n"); } return devm_rtc_register_device(info->rtc_dev); @@ -755,6 +813,7 @@ static SIMPLE_DEV_PM_OPS(s5m_rtc_pm_ops, s5m_rtc_suspend, s5m_rtc_resume); static const struct platform_device_id s5m_rtc_id[] = { { "s5m-rtc", S5M8767X }, + { "s2mpg10-rtc", S2MPG10 }, { "s2mps13-rtc", S2MPS13X }, { "s2mps14-rtc", S2MPS14X }, { "s2mps15-rtc", S2MPS15X }, diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index cef60770f68b..b3fcdcae379e 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -86,7 +86,7 @@ static void *_copy_apqns_from_user(void __user *uapqns, size_t nr_apqns) if (!uapqns || nr_apqns == 0) return NULL; - return memdup_user(uapqns, nr_apqns * sizeof(struct pkey_apqn)); + return memdup_array_user(uapqns, nr_apqns, sizeof(struct pkey_apqn)); } static int pkey_ioctl_genseck(struct pkey_genseck __user *ugs) diff --git a/drivers/staging/rtl8723bs/core/rtw_security.c b/drivers/staging/rtl8723bs/core/rtw_security.c index 1e9eff01b1aa..e9f382c280d9 100644 --- a/drivers/staging/rtl8723bs/core/rtw_security.c +++ b/drivers/staging/rtl8723bs/core/rtw_security.c @@ -868,29 +868,21 @@ static signed int aes_cipher(u8 *key, uint hdrlen, num_blocks, payload_index; u8 pn_vector[6]; - u8 mic_iv[16]; - u8 mic_header1[16]; - u8 mic_header2[16]; - u8 ctr_preload[16]; + u8 mic_iv[16] = {}; + u8 mic_header1[16] = {}; + u8 mic_header2[16] = {}; + u8 ctr_preload[16] = {}; /* Intermediate Buffers */ - u8 chain_buffer[16]; - u8 aes_out[16]; - u8 padded_buffer[16]; + u8 chain_buffer[16] = {}; + u8 aes_out[16] = {}; + u8 padded_buffer[16] = {}; u8 mic[8]; uint frtype = GetFrameType(pframe); uint frsubtype = GetFrameSubType(pframe); frsubtype = frsubtype>>4; - memset((void *)mic_iv, 0, 16); - memset((void *)mic_header1, 0, 16); - memset((void *)mic_header2, 0, 16); - memset((void *)ctr_preload, 0, 16); - memset((void *)chain_buffer, 0, 16); - memset((void *)aes_out, 0, 16); - memset((void *)padded_buffer, 0, 16); - if ((hdrlen == WLAN_HDR_A3_LEN) || (hdrlen == WLAN_HDR_A3_QOS_LEN)) a4_exists = 0; else @@ -1080,15 +1072,15 @@ static signed int aes_decipher(u8 *key, uint hdrlen, num_blocks, payload_index; signed int res = _SUCCESS; u8 pn_vector[6]; - u8 mic_iv[16]; - u8 mic_header1[16]; - u8 mic_header2[16]; - u8 ctr_preload[16]; + u8 mic_iv[16] = {}; + u8 mic_header1[16] = {}; + u8 mic_header2[16] = {}; + u8 ctr_preload[16] = {}; /* Intermediate Buffers */ - u8 chain_buffer[16]; - u8 aes_out[16]; - u8 padded_buffer[16]; + u8 chain_buffer[16] = {}; + u8 aes_out[16] = {}; + u8 padded_buffer[16] = {}; u8 mic[8]; uint frtype = GetFrameType(pframe); @@ -1096,14 +1088,6 @@ static signed int aes_decipher(u8 *key, uint hdrlen, frsubtype = frsubtype>>4; - memset((void *)mic_iv, 0, 16); - memset((void *)mic_header1, 0, 16); - memset((void *)mic_header2, 0, 16); - memset((void *)ctr_preload, 0, 16); - memset((void *)chain_buffer, 0, 16); - memset((void *)aes_out, 0, 16); - memset((void *)padded_buffer, 0, 16); - /* start to decrypt the payload */ num_blocks = (plen-8) / 16; /* plen including LLC, payload_length and mic) */ diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index bd02ee898f5d..500dfc009d03 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -235,6 +235,7 @@ struct imx_port { enum imx_tx_state tx_state; struct hrtimer trigger_start_tx; struct hrtimer trigger_stop_tx; + unsigned int rxtl; }; struct imx_port_ucrs { @@ -1339,6 +1340,7 @@ static void imx_uart_clear_rx_errors(struct imx_port *sport) #define TXTL_DEFAULT 8 #define RXTL_DEFAULT 8 /* 8 characters or aging timer */ +#define RXTL_CONSOLE_DEFAULT 1 #define TXTL_DMA 8 /* DMA burst setting */ #define RXTL_DMA 9 /* DMA burst setting */ @@ -1457,7 +1459,7 @@ static void imx_uart_disable_dma(struct imx_port *sport) ucr1 &= ~(UCR1_RXDMAEN | UCR1_TXDMAEN | UCR1_ATDMAEN); imx_uart_writel(sport, ucr1, UCR1); - imx_uart_setup_ufcr(sport, TXTL_DEFAULT, RXTL_DEFAULT); + imx_uart_setup_ufcr(sport, TXTL_DEFAULT, sport->rxtl); sport->dma_is_enabled = 0; } @@ -1482,7 +1484,12 @@ static int imx_uart_startup(struct uart_port *port) return retval; } - imx_uart_setup_ufcr(sport, TXTL_DEFAULT, RXTL_DEFAULT); + if (uart_console(&sport->port)) + sport->rxtl = RXTL_CONSOLE_DEFAULT; + else + sport->rxtl = RXTL_DEFAULT; + + imx_uart_setup_ufcr(sport, TXTL_DEFAULT, sport->rxtl); /* disable the DREN bit (Data Ready interrupt enable) before * requesting IRQs @@ -1948,7 +1955,7 @@ static int imx_uart_poll_init(struct uart_port *port) if (retval) clk_disable_unprepare(sport->clk_ipg); - imx_uart_setup_ufcr(sport, TXTL_DEFAULT, RXTL_DEFAULT); + imx_uart_setup_ufcr(sport, TXTL_DEFAULT, sport->rxtl); uart_port_lock_irqsave(&sport->port, &flags); @@ -2040,7 +2047,7 @@ static int imx_uart_rs485_config(struct uart_port *port, struct ktermios *termio /* If the receiver trigger is 0, set it to a default value */ ufcr = imx_uart_readl(sport, UFCR); if ((ufcr & UFCR_RXTL_MASK) == 0) - imx_uart_setup_ufcr(sport, TXTL_DEFAULT, RXTL_DEFAULT); + imx_uart_setup_ufcr(sport, TXTL_DEFAULT, sport->rxtl); imx_uart_start_rx(port); } @@ -2302,7 +2309,7 @@ imx_uart_console_setup(struct console *co, char *options) else imx_uart_console_get_options(sport, &baud, &parity, &bits); - imx_uart_setup_ufcr(sport, TXTL_DEFAULT, RXTL_DEFAULT); + imx_uart_setup_ufcr(sport, TXTL_DEFAULT, sport->rxtl); retval = uart_set_options(&sport->port, co, baud, parity, bits, flow); diff --git a/drivers/tty/serial/serial_base_bus.c b/drivers/tty/serial/serial_base_bus.c index 5d1677f1b651..cb3b127b06b6 100644 --- a/drivers/tty/serial/serial_base_bus.c +++ b/drivers/tty/serial/serial_base_bus.c @@ -72,6 +72,7 @@ static int serial_base_device_init(struct uart_port *port, dev->parent = parent_dev; dev->bus = &serial_base_bus_type; dev->release = release; + device_set_of_node_from_dev(dev, parent_dev); if (!serial_base_initialized) { dev_dbg(port->dev, "uart_add_one_port() called before arch_initcall()?\n"); diff --git a/drivers/tty/vt/ucs.c b/drivers/tty/vt/ucs.c index 6ead622b7713..03877485dfb7 100644 --- a/drivers/tty/vt/ucs.c +++ b/drivers/tty/vt/ucs.c @@ -206,7 +206,7 @@ static int ucs_page_entry_cmp(const void *key, const void *element) /** * ucs_get_fallback() - Get a substitution for the provided Unicode character - * @base: Base Unicode code point (UCS-4) + * @cp: Unicode code point (UCS-4) * * Get a simpler fallback character for the provided Unicode character. * This is used for terminal display when corresponding glyph is unavailable. diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index ed39d9cb4432..62049ceb34de 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -4650,6 +4650,7 @@ void do_unblank_screen(int leaving_gfx) set_palette(vc); set_cursor(vc); vt_event_post(VT_EVENT_UNBLANK, vc->vc_num, vc->vc_num); + notify_update(vc); } EXPORT_SYMBOL(do_unblank_screen); diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 7cbfc7d718b3..9dbd88eb9ff4 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -668,7 +668,6 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, struct socket *sock = vhost_vq_get_backend(vq); struct virtio_net_hdr *gso; struct xdp_buff *xdp = &nvq->xdp[nvq->batched_xdp]; - struct tun_xdp_hdr *hdr; size_t len = iov_iter_count(from); int headroom = vhost_sock_xdp(sock) ? XDP_PACKET_HEADROOM : 0; int buflen = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); @@ -691,15 +690,13 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, if (unlikely(!buf)) return -ENOMEM; - copied = copy_from_iter(buf + offsetof(struct tun_xdp_hdr, gso), - sock_hlen, from); - if (copied != sock_hlen) { + copied = copy_from_iter(buf + pad - sock_hlen, len, from); + if (copied != len) { ret = -EFAULT; goto err; } - hdr = buf; - gso = &hdr->gso; + gso = buf + pad - sock_hlen; if (!sock_hlen) memset(buf, 0, pad); @@ -718,16 +715,11 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, } } - len -= sock_hlen; - copied = copy_from_iter(buf + pad, len, from); - if (copied != len) { - ret = -EFAULT; - goto err; - } + /* pad contains sock_hlen */ + memcpy(buf, buf + pad - sock_hlen, sock_hlen); xdp_init_buff(xdp, buflen, NULL); - xdp_prepare_buff(xdp, buf, pad, len, true); - hdr->buflen = buflen; + xdp_prepare_buff(xdp, buf, pad, len - sock_hlen, true); ++nvq->batched_xdp; diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index b784aab66867..4397392bfef0 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -2797,7 +2797,7 @@ int virtqueue_resize(struct virtqueue *_vq, u32 num, void (*recycle_done)(struct virtqueue *vq)) { struct vring_virtqueue *vq = to_vvq(_vq); - int err; + int err, err_reset; if (num > vq->vq.num_max) return -E2BIG; @@ -2819,7 +2819,11 @@ int virtqueue_resize(struct virtqueue *_vq, u32 num, else err = virtqueue_resize_split(_vq, num); - return virtqueue_enable_after_reset(_vq); + err_reset = virtqueue_enable_after_reset(_vq); + if (err_reset) + return err_reset; + + return err; } EXPORT_SYMBOL_GPL(virtqueue_resize); diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c index b228a5a64479..66de46318620 100644 --- a/fs/bcachefs/alloc_background.c +++ b/fs/bcachefs/alloc_background.c @@ -1406,6 +1406,9 @@ int bch2_check_discard_freespace_key(struct btree_trans *trans, struct btree_ite : BCH_DATA_free; struct printbuf buf = PRINTBUF; + unsigned fsck_flags = (async_repair ? FSCK_ERR_NO_LOG : 0)| + FSCK_CAN_FIX|FSCK_CAN_IGNORE; + struct bpos bucket = iter->pos; bucket.offset &= ~(~0ULL << 56); u64 genbits = iter->pos.offset & (~0ULL << 56); @@ -1419,9 +1422,10 @@ int bch2_check_discard_freespace_key(struct btree_trans *trans, struct btree_ite return ret; if (!bch2_dev_bucket_exists(c, bucket)) { - if (fsck_err(trans, need_discard_freespace_key_to_invalid_dev_bucket, - "entry in %s btree for nonexistant dev:bucket %llu:%llu", - bch2_btree_id_str(iter->btree_id), bucket.inode, bucket.offset)) + if (__fsck_err(trans, fsck_flags, + need_discard_freespace_key_to_invalid_dev_bucket, + "entry in %s btree for nonexistant dev:bucket %llu:%llu", + bch2_btree_id_str(iter->btree_id), bucket.inode, bucket.offset)) goto delete; ret = 1; goto out; @@ -1433,7 +1437,8 @@ int bch2_check_discard_freespace_key(struct btree_trans *trans, struct btree_ite if (a->data_type != state || (state == BCH_DATA_free && genbits != alloc_freespace_genbits(*a))) { - if (fsck_err(trans, need_discard_freespace_key_bad, + if (__fsck_err(trans, fsck_flags, + need_discard_freespace_key_bad, "%s\nincorrectly set at %s:%llu:%llu:0 (free %u, genbits %llu should be %llu)", (bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf), bch2_btree_id_str(iter->btree_id), diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c index e76809e71858..77d93beb3c8f 100644 --- a/fs/bcachefs/backpointers.c +++ b/fs/bcachefs/backpointers.c @@ -353,7 +353,7 @@ static struct bkey_s_c __bch2_backpointer_get_key(struct btree_trans *trans, return ret ? bkey_s_c_err(ret) : bkey_s_c_null; } else { struct btree *b = __bch2_backpointer_get_node(trans, bp, iter, last_flushed, commit); - if (b == ERR_PTR(bch_err_throw(c, backpointer_to_overwritten_btree_node))) + if (b == ERR_PTR(-BCH_ERR_backpointer_to_overwritten_btree_node)) return bkey_s_c_null; if (IS_ERR_OR_NULL(b)) return ((struct bkey_s_c) { .k = ERR_CAST(b) }); diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h index 5a1cede2febf..8043943cdf6a 100644 --- a/fs/bcachefs/bcachefs.h +++ b/fs/bcachefs/bcachefs.h @@ -767,7 +767,8 @@ struct btree_trans_buf { x(sysfs) \ x(btree_write_buffer) \ x(btree_node_scrub) \ - x(async_recovery_passes) + x(async_recovery_passes) \ + x(ioctl_data) enum bch_write_ref { #define x(n) BCH_WRITE_REF_##n, diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c index e92cf3928c63..bac108e93823 100644 --- a/fs/bcachefs/btree_gc.c +++ b/fs/bcachefs/btree_gc.c @@ -503,8 +503,14 @@ again: prt_newline(&buf); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); + /* + * XXX: we're not passing the trans object here because we're not set up + * to handle a transaction restart - this code needs to be rewritten + * when we start doing online topology repair + */ + bch2_trans_unlock_long(trans); if (mustfix_fsck_err_on(!have_child, - trans, btree_node_topology_interior_node_empty, + c, btree_node_topology_interior_node_empty, "empty interior btree node at %s", buf.buf)) ret = DROP_THIS_NODE; err: @@ -528,32 +534,39 @@ fsck_err: return ret; } -static int bch2_check_root(struct btree_trans *trans, enum btree_id i, +static int bch2_check_root(struct btree_trans *trans, enum btree_id btree, bool *reconstructed_root) { struct bch_fs *c = trans->c; - struct btree_root *r = bch2_btree_id_root(c, i); + struct btree_root *r = bch2_btree_id_root(c, btree); struct printbuf buf = PRINTBUF; int ret = 0; - bch2_btree_id_to_text(&buf, i); + bch2_btree_id_to_text(&buf, btree); if (r->error) { bch_info(c, "btree root %s unreadable, must recover from scan", buf.buf); - r->alive = false; - r->error = 0; + ret = bch2_btree_has_scanned_nodes(c, btree); + if (ret < 0) + goto err; - if (!bch2_btree_has_scanned_nodes(c, i)) { + if (!ret) { __fsck_err(trans, - FSCK_CAN_FIX|(!btree_id_important(i) ? FSCK_AUTOFIX : 0), + FSCK_CAN_FIX|(!btree_id_important(btree) ? FSCK_AUTOFIX : 0), btree_root_unreadable_and_scan_found_nothing, "no nodes found for btree %s, continue?", buf.buf); - bch2_btree_root_alloc_fake_trans(trans, i, 0); + + r->alive = false; + r->error = 0; + bch2_btree_root_alloc_fake_trans(trans, btree, 0); } else { - bch2_btree_root_alloc_fake_trans(trans, i, 1); - bch2_shoot_down_journal_keys(c, i, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); - ret = bch2_get_scanned_nodes(c, i, 0, POS_MIN, SPOS_MAX); + r->alive = false; + r->error = 0; + bch2_btree_root_alloc_fake_trans(trans, btree, 1); + + bch2_shoot_down_journal_keys(c, btree, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); + ret = bch2_get_scanned_nodes(c, btree, 0, POS_MIN, SPOS_MAX); if (ret) goto err; } diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index d8f3c4c65e90..08b22bddd747 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -557,7 +557,9 @@ static int __btree_err(int ret, const char *fmt, ...) { if (c->recovery.curr_pass == BCH_RECOVERY_PASS_scan_for_btree_nodes) - return bch_err_throw(c, fsck_fix); + return ret == -BCH_ERR_btree_node_read_err_fixable + ? bch_err_throw(c, fsck_fix) + : ret; bool have_retry = false; int ret2; @@ -723,12 +725,11 @@ void bch2_btree_node_drop_keys_outside_node(struct btree *b) static int validate_bset(struct bch_fs *c, struct bch_dev *ca, struct btree *b, struct bset *i, - unsigned offset, unsigned sectors, int write, + unsigned offset, int write, struct bch_io_failures *failed, struct printbuf *err_msg) { unsigned version = le16_to_cpu(i->version); - unsigned ptr_written = btree_ptr_sectors_written(bkey_i_to_s_c(&b->key)); struct printbuf buf1 = PRINTBUF; struct printbuf buf2 = PRINTBUF; int ret = 0; @@ -778,15 +779,6 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca, btree_node_unsupported_version, "BSET_SEPARATE_WHITEOUTS no longer supported"); - if (!write && - btree_err_on(offset + sectors > (ptr_written ?: btree_sectors(c)), - -BCH_ERR_btree_node_read_err_fixable, - c, ca, b, i, NULL, - bset_past_end_of_btree_node, - "bset past end of btree node (offset %u len %u but written %zu)", - offset, sectors, ptr_written ?: btree_sectors(c))) - i->u64s = 0; - btree_err_on(offset && !i->u64s, -BCH_ERR_btree_node_read_err_fixable, c, ca, b, i, NULL, @@ -1151,6 +1143,14 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, "unknown checksum type %llu", BSET_CSUM_TYPE(i)); if (first) { + sectors = vstruct_sectors(b->data, c->block_bits); + if (btree_err_on(b->written + sectors > (ptr_written ?: btree_sectors(c)), + -BCH_ERR_btree_node_read_err_fixable, + c, ca, b, i, NULL, + bset_past_end_of_btree_node, + "bset past end of btree node (offset %u len %u but written %zu)", + b->written, sectors, ptr_written ?: btree_sectors(c))) + i->u64s = 0; if (good_csum_type) { struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, b->data); bool csum_bad = bch2_crc_cmp(b->data->csum, csum); @@ -1178,9 +1178,15 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, c, NULL, b, NULL, NULL, btree_node_unsupported_version, "btree node does not have NEW_EXTENT_OVERWRITE set"); - - sectors = vstruct_sectors(b->data, c->block_bits); } else { + sectors = vstruct_sectors(bne, c->block_bits); + if (btree_err_on(b->written + sectors > (ptr_written ?: btree_sectors(c)), + -BCH_ERR_btree_node_read_err_fixable, + c, ca, b, i, NULL, + bset_past_end_of_btree_node, + "bset past end of btree node (offset %u len %u but written %zu)", + b->written, sectors, ptr_written ?: btree_sectors(c))) + i->u64s = 0; if (good_csum_type) { struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, bne); bool csum_bad = bch2_crc_cmp(bne->csum, csum); @@ -1201,14 +1207,12 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, "decrypting btree node: %s", bch2_err_str(ret))) goto fsck_err; } - - sectors = vstruct_sectors(bne, c->block_bits); } b->version_ondisk = min(b->version_ondisk, le16_to_cpu(i->version)); - ret = validate_bset(c, ca, b, i, b->written, sectors, READ, failed, err_msg); + ret = validate_bset(c, ca, b, i, b->written, READ, failed, err_msg); if (ret) goto fsck_err; @@ -1982,28 +1986,12 @@ static void btree_node_scrub_work(struct work_struct *work) prt_newline(&err); if (!btree_node_scrub_check(c, scrub->buf, scrub->written, &err)) { - struct btree_trans *trans = bch2_trans_get(c); - - struct btree_iter iter; - bch2_trans_node_iter_init(trans, &iter, scrub->btree, - scrub->key.k->k.p, 0, scrub->level - 1, 0); - - struct btree *b; - int ret = lockrestart_do(trans, - PTR_ERR_OR_ZERO(b = bch2_btree_iter_peek_node(trans, &iter))); - if (ret) - goto err; - - if (bkey_i_to_btree_ptr_v2(&b->key)->v.seq == scrub->seq) { - bch_err(c, "error validating btree node during scrub on %s at btree %s", - scrub->ca->name, err.buf); - - ret = bch2_btree_node_rewrite(trans, &iter, b, 0, 0); - } -err: - bch2_trans_iter_exit(trans, &iter); - bch2_trans_begin(trans); - bch2_trans_put(trans); + int ret = bch2_trans_do(c, + bch2_btree_node_rewrite_key(trans, scrub->btree, scrub->level - 1, + scrub->key.k, 0)); + if (!bch2_err_matches(ret, ENOENT) && + !bch2_err_matches(ret, EROFS)) + bch_err_fn_ratelimited(c, ret); } printbuf_exit(&err); @@ -2267,7 +2255,7 @@ static void btree_node_write_endio(struct bio *bio) } static int validate_bset_for_write(struct bch_fs *c, struct btree *b, - struct bset *i, unsigned sectors) + struct bset *i) { int ret = bch2_bkey_validate(c, bkey_i_to_s_c(&b->key), (struct bkey_validate_context) { @@ -2282,7 +2270,7 @@ static int validate_bset_for_write(struct bch_fs *c, struct btree *b, } ret = validate_bset_keys(c, b, i, WRITE, NULL, NULL) ?: - validate_bset(c, NULL, b, i, b->written, sectors, WRITE, NULL, NULL); + validate_bset(c, NULL, b, i, b->written, WRITE, NULL, NULL); if (ret) { bch2_inconsistent_error(c); dump_stack(); @@ -2475,7 +2463,7 @@ do_write: /* if we're going to be encrypting, check metadata validity first: */ if (validate_before_checksum && - validate_bset_for_write(c, b, i, sectors_to_write)) + validate_bset_for_write(c, b, i)) goto err; ret = bset_encrypt(c, i, b->written << 9); @@ -2492,7 +2480,7 @@ do_write: /* if we're not encrypting, check metadata after checksumming: */ if (!validate_before_checksum && - validate_bset_for_write(c, b, i, sectors_to_write)) + validate_bset_for_write(c, b, i)) goto err; /* diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c index b78403376c07..352f9cd2634f 100644 --- a/fs/bcachefs/btree_iter.c +++ b/fs/bcachefs/btree_iter.c @@ -2076,14 +2076,14 @@ inline bool bch2_btree_iter_rewind(struct btree_trans *trans, struct btree_iter static noinline void bch2_btree_trans_peek_prev_updates(struct btree_trans *trans, struct btree_iter *iter, - struct bkey_s_c *k) + struct bpos search_key, struct bkey_s_c *k) { struct bpos end = path_l(btree_iter_path(trans, iter))->b->data->min_key; trans_for_each_update(trans, i) if (!i->key_cache_already_flushed && i->btree_id == iter->btree_id && - bpos_le(i->k->k.p, iter->pos) && + bpos_le(i->k->k.p, search_key) && bpos_ge(i->k->k.p, k->k ? k->k->p : end)) { iter->k = i->k->k; *k = bkey_i_to_s_c(i->k); @@ -2092,6 +2092,7 @@ void bch2_btree_trans_peek_prev_updates(struct btree_trans *trans, struct btree_ static noinline void bch2_btree_trans_peek_updates(struct btree_trans *trans, struct btree_iter *iter, + struct bpos search_key, struct bkey_s_c *k) { struct btree_path *path = btree_iter_path(trans, iter); @@ -2100,7 +2101,7 @@ void bch2_btree_trans_peek_updates(struct btree_trans *trans, struct btree_iter trans_for_each_update(trans, i) if (!i->key_cache_already_flushed && i->btree_id == iter->btree_id && - bpos_ge(i->k->k.p, path->pos) && + bpos_ge(i->k->k.p, search_key) && bpos_le(i->k->k.p, k->k ? k->k->p : end)) { iter->k = i->k->k; *k = bkey_i_to_s_c(i->k); @@ -2122,13 +2123,14 @@ void bch2_btree_trans_peek_slot_updates(struct btree_trans *trans, struct btree_ static struct bkey_i *bch2_btree_journal_peek(struct btree_trans *trans, struct btree_iter *iter, + struct bpos search_pos, struct bpos end_pos) { struct btree_path *path = btree_iter_path(trans, iter); return bch2_journal_keys_peek_max(trans->c, iter->btree_id, path->level, - path->pos, + search_pos, end_pos, &iter->journal_idx); } @@ -2138,7 +2140,7 @@ struct bkey_s_c btree_trans_peek_slot_journal(struct btree_trans *trans, struct btree_iter *iter) { struct btree_path *path = btree_iter_path(trans, iter); - struct bkey_i *k = bch2_btree_journal_peek(trans, iter, path->pos); + struct bkey_i *k = bch2_btree_journal_peek(trans, iter, path->pos, path->pos); if (k) { iter->k = k->k; @@ -2151,11 +2153,12 @@ struct bkey_s_c btree_trans_peek_slot_journal(struct btree_trans *trans, static noinline void btree_trans_peek_journal(struct btree_trans *trans, struct btree_iter *iter, + struct bpos search_key, struct bkey_s_c *k) { struct btree_path *path = btree_iter_path(trans, iter); struct bkey_i *next_journal = - bch2_btree_journal_peek(trans, iter, + bch2_btree_journal_peek(trans, iter, search_key, k->k ? k->k->p : path_l(path)->b->key.k.p); if (next_journal) { iter->k = next_journal->k; @@ -2165,13 +2168,14 @@ void btree_trans_peek_journal(struct btree_trans *trans, static struct bkey_i *bch2_btree_journal_peek_prev(struct btree_trans *trans, struct btree_iter *iter, + struct bpos search_key, struct bpos end_pos) { struct btree_path *path = btree_iter_path(trans, iter); return bch2_journal_keys_peek_prev_min(trans->c, iter->btree_id, path->level, - path->pos, + search_key, end_pos, &iter->journal_idx); } @@ -2179,11 +2183,12 @@ static struct bkey_i *bch2_btree_journal_peek_prev(struct btree_trans *trans, static noinline void btree_trans_peek_prev_journal(struct btree_trans *trans, struct btree_iter *iter, + struct bpos search_key, struct bkey_s_c *k) { struct btree_path *path = btree_iter_path(trans, iter); struct bkey_i *next_journal = - bch2_btree_journal_peek_prev(trans, iter, + bch2_btree_journal_peek_prev(trans, iter, search_key, k->k ? k->k->p : path_l(path)->b->key.k.p); if (next_journal) { @@ -2292,11 +2297,11 @@ static struct bkey_s_c __bch2_btree_iter_peek(struct btree_trans *trans, struct } if (unlikely(iter->flags & BTREE_ITER_with_journal)) - btree_trans_peek_journal(trans, iter, &k); + btree_trans_peek_journal(trans, iter, search_key, &k); if (unlikely((iter->flags & BTREE_ITER_with_updates) && trans->nr_updates)) - bch2_btree_trans_peek_updates(trans, iter, &k); + bch2_btree_trans_peek_updates(trans, iter, search_key, &k); if (k.k && bkey_deleted(k.k)) { /* @@ -2326,6 +2331,20 @@ static struct bkey_s_c __bch2_btree_iter_peek(struct btree_trans *trans, struct } bch2_btree_iter_verify(trans, iter); + + if (trace___btree_iter_peek_enabled()) { + CLASS(printbuf, buf)(); + + int ret = bkey_err(k); + if (ret) + prt_str(&buf, bch2_err_str(ret)); + else if (k.k) + bch2_bkey_val_to_text(&buf, trans->c, k); + else + prt_str(&buf, "(null)"); + trace___btree_iter_peek(trans->c, buf.buf); + } + return k; } @@ -2484,6 +2503,19 @@ out_no_locked: bch2_btree_iter_verify_entry_exit(iter); + if (trace_btree_iter_peek_max_enabled()) { + CLASS(printbuf, buf)(); + + int ret = bkey_err(k); + if (ret) + prt_str(&buf, bch2_err_str(ret)); + else if (k.k) + bch2_bkey_val_to_text(&buf, trans->c, k); + else + prt_str(&buf, "(null)"); + trace_btree_iter_peek_max(trans->c, buf.buf); + } + return k; end: bch2_btree_iter_set_pos(trans, iter, end); @@ -2557,11 +2589,11 @@ static struct bkey_s_c __bch2_btree_iter_peek_prev(struct btree_trans *trans, st } if (unlikely(iter->flags & BTREE_ITER_with_journal)) - btree_trans_peek_prev_journal(trans, iter, &k); + btree_trans_peek_prev_journal(trans, iter, search_key, &k); if (unlikely((iter->flags & BTREE_ITER_with_updates) && trans->nr_updates)) - bch2_btree_trans_peek_prev_updates(trans, iter, &k); + bch2_btree_trans_peek_prev_updates(trans, iter, search_key, &k); if (likely(k.k && !bkey_deleted(k.k))) { break; @@ -2724,6 +2756,19 @@ out_no_locked: bch2_btree_iter_verify_entry_exit(iter); bch2_btree_iter_verify(trans, iter); + + if (trace_btree_iter_peek_prev_min_enabled()) { + CLASS(printbuf, buf)(); + + int ret = bkey_err(k); + if (ret) + prt_str(&buf, bch2_err_str(ret)); + else if (k.k) + bch2_bkey_val_to_text(&buf, trans->c, k); + else + prt_str(&buf, "(null)"); + trace_btree_iter_peek_prev_min(trans->c, buf.buf); + } return k; end: bch2_btree_iter_set_pos(trans, iter, end); @@ -2767,8 +2812,10 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre /* extents can't span inode numbers: */ if ((iter->flags & BTREE_ITER_is_extents) && unlikely(iter->pos.offset == KEY_OFFSET_MAX)) { - if (iter->pos.inode == KEY_INODE_MAX) - return bkey_s_c_null; + if (iter->pos.inode == KEY_INODE_MAX) { + k = bkey_s_c_null; + goto out2; + } bch2_btree_iter_set_pos(trans, iter, bpos_nosnap_successor(iter->pos)); } @@ -2785,8 +2832,10 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre } struct btree_path *path = btree_iter_path(trans, iter); - if (unlikely(!btree_path_node(path, path->level))) - return bkey_s_c_null; + if (unlikely(!btree_path_node(path, path->level))) { + k = bkey_s_c_null; + goto out2; + } btree_path_set_should_be_locked(trans, path); @@ -2879,7 +2928,20 @@ out: bch2_btree_iter_verify(trans, iter); ret = bch2_btree_iter_verify_ret(trans, iter, k); if (unlikely(ret)) - return bkey_s_c_err(ret); + k = bkey_s_c_err(ret); +out2: + if (trace_btree_iter_peek_slot_enabled()) { + CLASS(printbuf, buf)(); + + int ret = bkey_err(k); + if (ret) + prt_str(&buf, bch2_err_str(ret)); + else if (k.k) + bch2_bkey_val_to_text(&buf, trans->c, k); + else + prt_str(&buf, "(null)"); + trace_btree_iter_peek_slot(trans->c, buf.buf); + } return k; } @@ -3132,6 +3194,10 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size, unsigned long if (WARN_ON_ONCE(new_bytes > BTREE_TRANS_MEM_MAX)) { #ifdef CONFIG_BCACHEFS_TRANS_KMALLOC_TRACE struct printbuf buf = PRINTBUF; + bch2_log_msg_start(c, &buf); + prt_printf(&buf, "bump allocator exceeded BTREE_TRANS_MEM_MAX (%u)\n", + BTREE_TRANS_MEM_MAX); + bch2_trans_kmalloc_trace_to_text(&buf, &trans->trans_kmalloc_trace); bch2_print_str(c, KERN_ERR, buf.buf); printbuf_exit(&buf); @@ -3159,46 +3225,32 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size, unsigned long mutex_unlock(&s->lock); } - if (trans->used_mempool) { - if (trans->mem_bytes >= new_bytes) - goto out_change_top; - - /* No more space from mempool item, need malloc new one */ - new_mem = kmalloc(new_bytes, GFP_NOWAIT|__GFP_NOWARN); - if (unlikely(!new_mem)) { - bch2_trans_unlock(trans); - - new_mem = kmalloc(new_bytes, GFP_KERNEL); - if (!new_mem) - return ERR_PTR(-BCH_ERR_ENOMEM_trans_kmalloc); + if (trans->used_mempool || new_bytes > BTREE_TRANS_MEM_MAX) { + EBUG_ON(trans->mem_bytes >= new_bytes); + return ERR_PTR(-BCH_ERR_ENOMEM_trans_kmalloc); + } - ret = bch2_trans_relock(trans); - if (ret) { - kfree(new_mem); - return ERR_PTR(ret); - } - } - memcpy(new_mem, trans->mem, trans->mem_top); - trans->used_mempool = false; - mempool_free(trans->mem, &c->btree_trans_mem_pool); - goto out_new_mem; + if (old_bytes) { + trans->realloc_bytes_required = new_bytes; + trace_and_count(c, trans_restart_mem_realloced, trans, _RET_IP_, new_bytes); + return ERR_PTR(btree_trans_restart_ip(trans, + BCH_ERR_transaction_restart_mem_realloced, _RET_IP_)); } - new_mem = krealloc(trans->mem, new_bytes, GFP_NOWAIT|__GFP_NOWARN); + EBUG_ON(trans->mem); + + new_mem = kmalloc(new_bytes, GFP_NOWAIT|__GFP_NOWARN); if (unlikely(!new_mem)) { bch2_trans_unlock(trans); - new_mem = krealloc(trans->mem, new_bytes, GFP_KERNEL); + new_mem = kmalloc(new_bytes, GFP_KERNEL); if (!new_mem && new_bytes <= BTREE_TRANS_MEM_MAX) { new_mem = mempool_alloc(&c->btree_trans_mem_pool, GFP_KERNEL); new_bytes = BTREE_TRANS_MEM_MAX; - memcpy(new_mem, trans->mem, trans->mem_top); trans->used_mempool = true; - kfree(trans->mem); } - if (!new_mem) - return ERR_PTR(-BCH_ERR_ENOMEM_trans_kmalloc); + EBUG_ON(!new_mem); trans->mem = new_mem; trans->mem_bytes = new_bytes; @@ -3207,18 +3259,10 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size, unsigned long if (ret) return ERR_PTR(ret); } -out_new_mem: + trans->mem = new_mem; trans->mem_bytes = new_bytes; - if (old_bytes) { - trace_and_count(c, trans_restart_mem_realloced, trans, _RET_IP_, new_bytes); - return ERR_PTR(btree_trans_restart_ip(trans, - BCH_ERR_transaction_restart_mem_realloced, _RET_IP_)); - } -out_change_top: - bch2_trans_kmalloc_trace(trans, size, ip); - p = trans->mem + trans->mem_top; trans->mem_top += size; memset(p, 0, size); @@ -3279,6 +3323,27 @@ u32 bch2_trans_begin(struct btree_trans *trans) trans->restart_count++; trans->mem_top = 0; + if (trans->restarted == BCH_ERR_transaction_restart_mem_realloced) { + EBUG_ON(!trans->mem || !trans->mem_bytes); + unsigned new_bytes = trans->realloc_bytes_required; + void *new_mem = krealloc(trans->mem, new_bytes, GFP_NOWAIT|__GFP_NOWARN); + if (unlikely(!new_mem)) { + bch2_trans_unlock(trans); + new_mem = krealloc(trans->mem, new_bytes, GFP_KERNEL); + + EBUG_ON(new_bytes > BTREE_TRANS_MEM_MAX); + + if (!new_mem) { + new_mem = mempool_alloc(&trans->c->btree_trans_mem_pool, GFP_KERNEL); + new_bytes = BTREE_TRANS_MEM_MAX; + trans->used_mempool = true; + kfree(trans->mem); + } + } + trans->mem = new_mem; + trans->mem_bytes = new_bytes; + } + trans_for_each_path(trans, path, i) { path->should_be_locked = false; diff --git a/fs/bcachefs/btree_journal_iter.c b/fs/bcachefs/btree_journal_iter.c index cf7398751644..ea839560a136 100644 --- a/fs/bcachefs/btree_journal_iter.c +++ b/fs/bcachefs/btree_journal_iter.c @@ -137,12 +137,15 @@ struct bkey_i *bch2_journal_keys_peek_prev_min(struct bch_fs *c, enum btree_id b struct journal_key *k; BUG_ON(*idx > keys->nr); + + if (!keys->nr) + return NULL; search: if (!*idx) *idx = __bch2_journal_key_search(keys, btree_id, level, pos); - while (*idx && - __journal_key_cmp(btree_id, level, end_pos, idx_to_key(keys, *idx - 1)) <= 0) { + while (*idx < keys->nr && + __journal_key_cmp(btree_id, level, end_pos, idx_to_key(keys, *idx)) >= 0) { (*idx)++; iters++; if (iters == 10) { @@ -151,18 +154,23 @@ search: } } + if (*idx == keys->nr) + --(*idx); + struct bkey_i *ret = NULL; rcu_read_lock(); /* for overwritten_ranges */ - while ((k = *idx < keys->nr ? idx_to_key(keys, *idx) : NULL)) { + while (true) { + k = idx_to_key(keys, *idx); if (__journal_key_cmp(btree_id, level, end_pos, k) > 0) break; if (k->overwritten) { if (k->overwritten_range) - *idx = rcu_dereference(k->overwritten_range)->start - 1; - else - *idx -= 1; + *idx = rcu_dereference(k->overwritten_range)->start; + if (!*idx) + break; + --(*idx); continue; } @@ -171,6 +179,8 @@ search: break; } + if (!*idx) + break; --(*idx); iters++; if (iters == 10) { @@ -641,10 +651,11 @@ static int journal_sort_key_cmp(const void *_l, const void *_r) { const struct journal_key *l = _l; const struct journal_key *r = _r; + int rewind = l->rewind && r->rewind ? -1 : 1; return journal_key_cmp(l, r) ?: - cmp_int(l->journal_seq, r->journal_seq) ?: - cmp_int(l->journal_offset, r->journal_offset); + ((cmp_int(l->journal_seq, r->journal_seq) ?: + cmp_int(l->journal_offset, r->journal_offset)) * rewind); } void bch2_journal_keys_put(struct bch_fs *c) @@ -713,6 +724,8 @@ int bch2_journal_keys_sort(struct bch_fs *c) struct journal_keys *keys = &c->journal_keys; size_t nr_read = 0; + u64 rewind_seq = c->opts.journal_rewind ?: U64_MAX; + genradix_for_each(&c->journal_entries, iter, _i) { i = *_i; @@ -721,28 +734,43 @@ int bch2_journal_keys_sort(struct bch_fs *c) cond_resched(); - for_each_jset_key(k, entry, &i->j) { - struct journal_key n = (struct journal_key) { - .btree_id = entry->btree_id, - .level = entry->level, - .k = k, - .journal_seq = le64_to_cpu(i->j.seq), - .journal_offset = k->_data - i->j._data, - }; - - if (darray_push(keys, n)) { - __journal_keys_sort(keys); - - if (keys->nr * 8 > keys->size * 7) { - bch_err(c, "Too many journal keys for slowpath; have %zu compacted, buf size %zu, processed %zu keys at seq %llu", - keys->nr, keys->size, nr_read, le64_to_cpu(i->j.seq)); - return bch_err_throw(c, ENOMEM_journal_keys_sort); + vstruct_for_each(&i->j, entry) { + bool rewind = !entry->level && + !btree_id_is_alloc(entry->btree_id) && + le64_to_cpu(i->j.seq) >= rewind_seq; + + if (entry->type != (rewind + ? BCH_JSET_ENTRY_overwrite + : BCH_JSET_ENTRY_btree_keys)) + continue; + + if (!rewind && le64_to_cpu(i->j.seq) < c->journal_replay_seq_start) + continue; + + jset_entry_for_each_key(entry, k) { + struct journal_key n = (struct journal_key) { + .btree_id = entry->btree_id, + .level = entry->level, + .rewind = rewind, + .k = k, + .journal_seq = le64_to_cpu(i->j.seq), + .journal_offset = k->_data - i->j._data, + }; + + if (darray_push(keys, n)) { + __journal_keys_sort(keys); + + if (keys->nr * 8 > keys->size * 7) { + bch_err(c, "Too many journal keys for slowpath; have %zu compacted, buf size %zu, processed %zu keys at seq %llu", + keys->nr, keys->size, nr_read, le64_to_cpu(i->j.seq)); + return bch_err_throw(c, ENOMEM_journal_keys_sort); + } + + BUG_ON(darray_push(keys, n)); } - BUG_ON(darray_push(keys, n)); + nr_read++; } - - nr_read++; } } diff --git a/fs/bcachefs/btree_journal_iter_types.h b/fs/bcachefs/btree_journal_iter_types.h index 8b773823704f..86aacb254fb2 100644 --- a/fs/bcachefs/btree_journal_iter_types.h +++ b/fs/bcachefs/btree_journal_iter_types.h @@ -11,8 +11,9 @@ struct journal_key { u32 journal_offset; enum btree_id btree_id:8; unsigned level:8; - bool allocated; - bool overwritten; + bool allocated:1; + bool overwritten:1; + bool rewind:1; struct journal_key_range_overwritten __rcu * overwritten_range; struct bkey_i *k; diff --git a/fs/bcachefs/btree_locking.c b/fs/bcachefs/btree_locking.c index 91a51aef82f1..bed2b4b6ffb9 100644 --- a/fs/bcachefs/btree_locking.c +++ b/fs/bcachefs/btree_locking.c @@ -771,7 +771,7 @@ static inline void __bch2_trans_unlock(struct btree_trans *trans) } static noinline __cold void bch2_trans_relock_fail(struct btree_trans *trans, struct btree_path *path, - struct get_locks_fail *f, bool trace) + struct get_locks_fail *f, bool trace, ulong ip) { if (!trace) goto out; @@ -796,7 +796,7 @@ static noinline __cold void bch2_trans_relock_fail(struct btree_trans *trans, st prt_printf(&buf, " total locked %u.%u.%u", c.n[0], c.n[1], c.n[2]); } - trace_trans_restart_relock(trans, _RET_IP_, buf.buf); + trace_trans_restart_relock(trans, ip, buf.buf); printbuf_exit(&buf); } @@ -806,7 +806,7 @@ out: bch2_trans_verify_locks(trans); } -static inline int __bch2_trans_relock(struct btree_trans *trans, bool trace) +static inline int __bch2_trans_relock(struct btree_trans *trans, bool trace, ulong ip) { bch2_trans_verify_locks(trans); @@ -825,7 +825,7 @@ static inline int __bch2_trans_relock(struct btree_trans *trans, bool trace) if (path->should_be_locked && (ret = btree_path_get_locks(trans, path, false, &f, BCH_ERR_transaction_restart_relock))) { - bch2_trans_relock_fail(trans, path, &f, trace); + bch2_trans_relock_fail(trans, path, &f, trace, ip); return ret; } } @@ -838,12 +838,12 @@ out: int bch2_trans_relock(struct btree_trans *trans) { - return __bch2_trans_relock(trans, true); + return __bch2_trans_relock(trans, true, _RET_IP_); } int bch2_trans_relock_notrace(struct btree_trans *trans) { - return __bch2_trans_relock(trans, false); + return __bch2_trans_relock(trans, false, _RET_IP_); } void bch2_trans_unlock(struct btree_trans *trans) diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c index a35847734a60..23d8c62ea4b6 100644 --- a/fs/bcachefs/btree_node_scan.c +++ b/fs/bcachefs/btree_node_scan.c @@ -521,8 +521,12 @@ bool bch2_btree_node_is_stale(struct bch_fs *c, struct btree *b) return false; } -bool bch2_btree_has_scanned_nodes(struct bch_fs *c, enum btree_id btree) +int bch2_btree_has_scanned_nodes(struct bch_fs *c, enum btree_id btree) { + int ret = bch2_run_print_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes); + if (ret) + return ret; + struct found_btree_node search = { .btree_id = btree, .level = 0, diff --git a/fs/bcachefs/btree_node_scan.h b/fs/bcachefs/btree_node_scan.h index 08687b209787..66e6f9ed19d0 100644 --- a/fs/bcachefs/btree_node_scan.h +++ b/fs/bcachefs/btree_node_scan.h @@ -4,7 +4,7 @@ int bch2_scan_for_btree_nodes(struct bch_fs *); bool bch2_btree_node_is_stale(struct bch_fs *, struct btree *); -bool bch2_btree_has_scanned_nodes(struct bch_fs *, enum btree_id); +int bch2_btree_has_scanned_nodes(struct bch_fs *, enum btree_id); int bch2_get_scanned_nodes(struct bch_fs *, enum btree_id, unsigned, struct bpos, struct bpos); void bch2_find_btree_nodes_exit(struct find_btree_nodes *); diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c index d9710801e3ee..639ef75b3dbd 100644 --- a/fs/bcachefs/btree_trans_commit.c +++ b/fs/bcachefs/btree_trans_commit.c @@ -595,12 +595,13 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, int ret = 0; bch2_trans_verify_not_unlocked_or_in_restart(trans); - +#if 0 + /* todo: bring back dynamic fault injection */ if (race_fault()) { trace_and_count(c, trans_restart_fault_inject, trans, trace_ip); return btree_trans_restart(trans, BCH_ERR_transaction_restart_fault_inject); } - +#endif /* * Check if the insert will fit in the leaf node with the write lock * held, otherwise another thread could write the node changing the @@ -757,6 +758,8 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, btree_trans_journal_entries_start(trans), trans->journal_entries.u64s); + EBUG_ON(trans->journal_res.u64s < trans->journal_entries.u64s); + trans->journal_res.offset += trans->journal_entries.u64s; trans->journal_res.u64s -= trans->journal_entries.u64s; @@ -1003,6 +1006,7 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) { struct btree_insert_entry *errored_at = NULL; struct bch_fs *c = trans->c; + unsigned journal_u64s = 0; int ret = 0; bch2_trans_verify_not_unlocked_or_in_restart(trans); @@ -1031,10 +1035,10 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) EBUG_ON(test_bit(BCH_FS_clean_shutdown, &c->flags)); - trans->journal_u64s = trans->journal_entries.u64s + jset_u64s(trans->accounting.u64s); + journal_u64s = jset_u64s(trans->accounting.u64s); trans->journal_transaction_names = READ_ONCE(c->opts.journal_transaction_names); if (trans->journal_transaction_names) - trans->journal_u64s += jset_u64s(JSET_ENTRY_LOG_U64s); + journal_u64s += jset_u64s(JSET_ENTRY_LOG_U64s); trans_for_each_update(trans, i) { struct btree_path *path = trans->paths + i->path; @@ -1054,11 +1058,11 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) continue; /* we're going to journal the key being updated: */ - trans->journal_u64s += jset_u64s(i->k->k.u64s); + journal_u64s += jset_u64s(i->k->k.u64s); /* and we're also going to log the overwrite: */ if (trans->journal_transaction_names) - trans->journal_u64s += jset_u64s(i->old_k.u64s); + journal_u64s += jset_u64s(i->old_k.u64s); } if (trans->extra_disk_res) { @@ -1076,6 +1080,8 @@ retry: memset(&trans->journal_res, 0, sizeof(trans->journal_res)); memset(&trans->fs_usage_delta, 0, sizeof(trans->fs_usage_delta)); + trans->journal_u64s = journal_u64s + trans->journal_entries.u64s; + ret = do_bch2_trans_commit(trans, flags, &errored_at, _RET_IP_); /* make sure we didn't drop or screw up locks: */ diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h index 3aa4a602bd02..112170fd9c8f 100644 --- a/fs/bcachefs/btree_types.h +++ b/fs/bcachefs/btree_types.h @@ -497,6 +497,7 @@ struct btree_trans { void *mem; unsigned mem_top; unsigned mem_bytes; + unsigned realloc_bytes_required; #ifdef CONFIG_BCACHEFS_TRANS_KMALLOC_TRACE darray_trans_kmalloc_trace trans_kmalloc_trace; #endif diff --git a/fs/bcachefs/btree_update.c b/fs/bcachefs/btree_update.c index e97e78c10f49..ee657b9f4b96 100644 --- a/fs/bcachefs/btree_update.c +++ b/fs/bcachefs/btree_update.c @@ -549,20 +549,26 @@ void *__bch2_trans_subbuf_alloc(struct btree_trans *trans, unsigned u64s) { unsigned new_top = buf->u64s + u64s; - unsigned old_size = buf->size; + unsigned new_size = buf->size; - if (new_top > buf->size) - buf->size = roundup_pow_of_two(new_top); + BUG_ON(roundup_pow_of_two(new_top) > U16_MAX); - void *n = bch2_trans_kmalloc_nomemzero(trans, buf->size * sizeof(u64)); + if (new_top > new_size) + new_size = roundup_pow_of_two(new_top); + + void *n = bch2_trans_kmalloc_nomemzero(trans, new_size * sizeof(u64)); if (IS_ERR(n)) return n; + unsigned offset = (u64 *) n - (u64 *) trans->mem; + BUG_ON(offset > U16_MAX); + if (buf->u64s) memcpy(n, btree_trans_subbuf_base(trans, buf), - old_size * sizeof(u64)); + buf->size * sizeof(u64)); buf->base = (u64 *) n - (u64 *) trans->mem; + buf->size = new_size; void *p = btree_trans_subbuf_top(trans, buf); buf->u64s = new_top; diff --git a/fs/bcachefs/btree_update.h b/fs/bcachefs/btree_update.h index 9feef1dc4de5..0b98ab959719 100644 --- a/fs/bcachefs/btree_update.h +++ b/fs/bcachefs/btree_update.h @@ -170,8 +170,7 @@ bch2_trans_jset_entry_alloc(struct btree_trans *trans, unsigned u64s) int bch2_btree_insert_clone_trans(struct btree_trans *, enum btree_id, struct bkey_i *); -int bch2_btree_write_buffer_insert_err(struct btree_trans *, - enum btree_id, struct bkey_i *); +int bch2_btree_write_buffer_insert_err(struct bch_fs *, enum btree_id, struct bkey_i *); static inline int __must_check bch2_trans_update_buffered(struct btree_trans *trans, enum btree_id btree, @@ -182,7 +181,7 @@ static inline int __must_check bch2_trans_update_buffered(struct btree_trans *tr EBUG_ON(k->k.u64s > BTREE_WRITE_BUFERED_U64s_MAX); if (unlikely(!btree_type_uses_write_buffer(btree))) { - int ret = bch2_btree_write_buffer_insert_err(trans, btree, k); + int ret = bch2_btree_write_buffer_insert_err(trans->c, btree, k); dump_stack(); return ret; } diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c index e77584607f0d..553059b33bfd 100644 --- a/fs/bcachefs/btree_update_interior.c +++ b/fs/bcachefs/btree_update_interior.c @@ -1287,10 +1287,11 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path, do { ret = bch2_btree_reserve_get(trans, as, nr_nodes, target, flags, &cl); - + if (!bch2_err_matches(ret, BCH_ERR_operation_blocked)) + break; bch2_trans_unlock(trans); bch2_wait_on_allocator(c, &cl); - } while (bch2_err_matches(ret, BCH_ERR_operation_blocked)); + } while (1); } if (ret) { @@ -2293,9 +2294,9 @@ err: goto out; } -static int bch2_btree_node_rewrite_key(struct btree_trans *trans, - enum btree_id btree, unsigned level, - struct bkey_i *k, unsigned flags) +int bch2_btree_node_rewrite_key(struct btree_trans *trans, + enum btree_id btree, unsigned level, + struct bkey_i *k, unsigned flags) { struct btree_iter iter; bch2_trans_node_iter_init(trans, &iter, @@ -2367,9 +2368,8 @@ static void async_btree_node_rewrite_work(struct work_struct *work) int ret = bch2_trans_do(c, bch2_btree_node_rewrite_key(trans, a->btree_id, a->level, a->key.k, 0)); - if (ret != -ENOENT && - !bch2_err_matches(ret, EROFS) && - ret != -BCH_ERR_journal_shutdown) + if (!bch2_err_matches(ret, ENOENT) && + !bch2_err_matches(ret, EROFS)) bch_err_fn_ratelimited(c, ret); spin_lock(&c->btree_node_rewrites_lock); diff --git a/fs/bcachefs/btree_update_interior.h b/fs/bcachefs/btree_update_interior.h index b649c36c3fbb..ac04e45a8515 100644 --- a/fs/bcachefs/btree_update_interior.h +++ b/fs/bcachefs/btree_update_interior.h @@ -176,6 +176,9 @@ static inline int bch2_foreground_maybe_merge(struct btree_trans *trans, int bch2_btree_node_rewrite(struct btree_trans *, struct btree_iter *, struct btree *, unsigned, unsigned); +int bch2_btree_node_rewrite_key(struct btree_trans *, + enum btree_id, unsigned, + struct bkey_i *, unsigned); int bch2_btree_node_rewrite_pos(struct btree_trans *, enum btree_id, unsigned, struct bpos, unsigned, unsigned); diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c index 90b21e61d2b6..4b095235a0d2 100644 --- a/fs/bcachefs/btree_write_buffer.c +++ b/fs/bcachefs/btree_write_buffer.c @@ -267,10 +267,9 @@ out: BUG_ON(wb->sorted.size < wb->flushing.keys.nr); } -int bch2_btree_write_buffer_insert_err(struct btree_trans *trans, +int bch2_btree_write_buffer_insert_err(struct bch_fs *c, enum btree_id btree, struct bkey_i *k) { - struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; prt_printf(&buf, "attempting to do write buffer update on non wb btree="); @@ -332,7 +331,7 @@ static int bch2_btree_write_buffer_flush_locked(struct btree_trans *trans) struct btree_write_buffered_key *k = &wb->flushing.keys.data[i->idx]; if (unlikely(!btree_type_uses_write_buffer(k->btree))) { - ret = bch2_btree_write_buffer_insert_err(trans, k->btree, &k->k); + ret = bch2_btree_write_buffer_insert_err(trans->c, k->btree, &k->k); goto err; } @@ -676,6 +675,9 @@ int bch2_btree_write_buffer_maybe_flush(struct btree_trans *trans, goto err; bch2_bkey_buf_copy(last_flushed, c, tmp.k); + + /* can we avoid the unconditional restart? */ + trace_and_count(c, trans_restart_write_buffer_flush, trans, _RET_IP_); ret = bch_err_throw(c, transaction_restart_write_buffer_flush); } err: diff --git a/fs/bcachefs/btree_write_buffer.h b/fs/bcachefs/btree_write_buffer.h index 05f56fd1eed0..c351d21aca0b 100644 --- a/fs/bcachefs/btree_write_buffer.h +++ b/fs/bcachefs/btree_write_buffer.h @@ -89,6 +89,12 @@ static inline int bch2_journal_key_to_wb(struct bch_fs *c, struct journal_keys_to_wb *dst, enum btree_id btree, struct bkey_i *k) { + if (unlikely(!btree_type_uses_write_buffer(btree))) { + int ret = bch2_btree_write_buffer_insert_err(c, btree, k); + dump_stack(); + return ret; + } + EBUG_ON(!dst->seq); return k->k.type == KEY_TYPE_accounting diff --git a/fs/bcachefs/chardev.c b/fs/bcachefs/chardev.c index fde3c2380e28..5ea89aa2b0c4 100644 --- a/fs/bcachefs/chardev.c +++ b/fs/bcachefs/chardev.c @@ -319,6 +319,7 @@ static int bch2_data_thread(void *arg) ctx->stats.ret = BCH_IOCTL_DATA_EVENT_RET_done; ctx->stats.data_type = (int) DATA_PROGRESS_DATA_TYPE_done; } + enumerated_ref_put(&ctx->c->writes, BCH_WRITE_REF_ioctl_data); return 0; } @@ -378,15 +379,24 @@ static long bch2_ioctl_data(struct bch_fs *c, struct bch_data_ctx *ctx; int ret; - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; + if (!enumerated_ref_tryget(&c->writes, BCH_WRITE_REF_ioctl_data)) + return -EROFS; - if (arg.op >= BCH_DATA_OP_NR || arg.flags) - return -EINVAL; + if (!capable(CAP_SYS_ADMIN)) { + ret = -EPERM; + goto put_ref; + } + + if (arg.op >= BCH_DATA_OP_NR || arg.flags) { + ret = -EINVAL; + goto put_ref; + } ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); - if (!ctx) - return -ENOMEM; + if (!ctx) { + ret = -ENOMEM; + goto put_ref; + } ctx->c = c; ctx->arg = arg; @@ -395,7 +405,12 @@ static long bch2_ioctl_data(struct bch_fs *c, &bcachefs_data_ops, bch2_data_thread); if (ret < 0) - kfree(ctx); + goto cleanup; + return ret; +cleanup: + kfree(ctx); +put_ref: + enumerated_ref_put(&c->writes, BCH_WRITE_REF_ioctl_data); return ret; } diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c index 5f1174348974..e848e210a9bf 100644 --- a/fs/bcachefs/data_update.c +++ b/fs/bcachefs/data_update.c @@ -249,6 +249,7 @@ static int data_update_invalid_bkey(struct data_update *m, bch2_bkey_val_to_text(&buf, c, k); prt_str(&buf, "\nnew: "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(insert)); + prt_newline(&buf); bch2_fs_emergency_read_only2(c, &buf); diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h index ac3264134a15..86a842f1e88e 100644 --- a/fs/bcachefs/errcode.h +++ b/fs/bcachefs/errcode.h @@ -137,7 +137,6 @@ x(BCH_ERR_transaction_restart, transaction_restart_relock) \ x(BCH_ERR_transaction_restart, transaction_restart_relock_path) \ x(BCH_ERR_transaction_restart, transaction_restart_relock_path_intent) \ - x(BCH_ERR_transaction_restart, transaction_restart_relock_after_fill) \ x(BCH_ERR_transaction_restart, transaction_restart_too_many_iters) \ x(BCH_ERR_transaction_restart, transaction_restart_lock_node_reused) \ x(BCH_ERR_transaction_restart, transaction_restart_fill_relock) \ @@ -148,11 +147,8 @@ x(BCH_ERR_transaction_restart, transaction_restart_would_deadlock_write)\ x(BCH_ERR_transaction_restart, transaction_restart_deadlock_recursion_limit)\ x(BCH_ERR_transaction_restart, transaction_restart_upgrade) \ - x(BCH_ERR_transaction_restart, transaction_restart_key_cache_upgrade) \ x(BCH_ERR_transaction_restart, transaction_restart_key_cache_fill) \ x(BCH_ERR_transaction_restart, transaction_restart_key_cache_raced) \ - x(BCH_ERR_transaction_restart, transaction_restart_key_cache_realloced)\ - x(BCH_ERR_transaction_restart, transaction_restart_journal_preres_get) \ x(BCH_ERR_transaction_restart, transaction_restart_split_race) \ x(BCH_ERR_transaction_restart, transaction_restart_write_buffer_flush) \ x(BCH_ERR_transaction_restart, transaction_restart_nested) \ @@ -241,7 +237,6 @@ x(BCH_ERR_journal_res_blocked, journal_buf_enomem) \ x(BCH_ERR_journal_res_blocked, journal_stuck) \ x(BCH_ERR_journal_res_blocked, journal_retry_open) \ - x(BCH_ERR_journal_res_blocked, journal_preres_get_blocked) \ x(BCH_ERR_journal_res_blocked, bucket_alloc_blocked) \ x(BCH_ERR_journal_res_blocked, stripe_alloc_blocked) \ x(BCH_ERR_invalid, invalid_sb) \ diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c index a8ec6aae5738..b2a6c041e165 100644 --- a/fs/bcachefs/error.c +++ b/fs/bcachefs/error.c @@ -621,7 +621,9 @@ print: if (s) s->ret = ret; - if (trans) + if (trans && + !(flags & FSCK_ERR_NO_LOG) && + ret == -BCH_ERR_fsck_fix) ret = bch2_trans_log_str(trans, bch2_sb_error_strs[err]) ?: ret; err_unlock: mutex_unlock(&c->fsck_error_msgs_lock); diff --git a/fs/bcachefs/extent_update.c b/fs/bcachefs/extent_update.c index b899ee75f5b9..e76e58a568bf 100644 --- a/fs/bcachefs/extent_update.c +++ b/fs/bcachefs/extent_update.c @@ -139,6 +139,17 @@ int bch2_extent_trim_atomic(struct btree_trans *trans, if (ret) return ret; - bch2_cut_back(end, k); + /* tracepoint */ + + if (bpos_lt(end, k->k.p)) { + if (trace_extent_trim_atomic_enabled()) { + CLASS(printbuf, buf)(); + bch2_bpos_to_text(&buf, end); + prt_newline(&buf); + bch2_bkey_val_to_text(&buf, trans->c, bkey_i_to_s_c(k)); + trace_extent_trim_atomic(trans->c, buf.buf); + } + bch2_cut_back(end, k); + } return 0; } diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index 3063a8ddc2df..db24a76563f8 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -1732,7 +1732,8 @@ static int bch2_fileattr_set(struct mnt_idmap *idmap, bch2_write_inode(c, inode, fssetxattr_inode_update_fn, &s, ATTR_CTIME); mutex_unlock(&inode->ei_update_lock); - return ret; + + return bch2_err_class(ret); } static const struct file_operations bch_file_operations = { diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index 68ed69a255e1..9920f1affc5b 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -327,7 +327,8 @@ static inline bool inode_should_reattach(struct bch_inode_unpacked *inode) (inode->bi_flags & BCH_INODE_has_child_snapshot)) return false; - return !inode->bi_dir && !(inode->bi_flags & BCH_INODE_unlinked); + return !bch2_inode_has_backpointer(inode) && + !(inode->bi_flags & BCH_INODE_unlinked); } static int maybe_delete_dirent(struct btree_trans *trans, struct bpos d_pos, u32 snapshot) @@ -372,6 +373,18 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked * if (inode->bi_subvol) { inode->bi_parent_subvol = BCACHEFS_ROOT_SUBVOL; + struct btree_iter subvol_iter; + struct bkey_i_subvolume *subvol = + bch2_bkey_get_mut_typed(trans, &subvol_iter, + BTREE_ID_subvolumes, POS(0, inode->bi_subvol), + 0, subvolume); + ret = PTR_ERR_OR_ZERO(subvol); + if (ret) + return ret; + + subvol->v.fs_path_parent = BCACHEFS_ROOT_SUBVOL; + bch2_trans_iter_exit(trans, &subvol_iter); + u64 root_inum; ret = subvol_lookup(trans, inode->bi_parent_subvol, &dirent_snapshot, &root_inum); @@ -387,6 +400,8 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked * if (ret) return ret; + bch_verbose(c, "got lostfound inum %llu", lostfound.bi_inum); + lostfound.bi_nlink += S_ISDIR(inode->bi_mode); /* ensure lost+found inode is also present in inode snapshot */ @@ -423,6 +438,16 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked * if (ret) return ret; + { + CLASS(printbuf, buf)(); + ret = bch2_inum_snapshot_to_path(trans, inode->bi_inum, + inode->bi_snapshot, NULL, &buf); + if (ret) + return ret; + + bch_info(c, "reattached at %s", buf.buf); + } + /* * Fix up inodes in child snapshots: if they should also be reattached * update the backpointer field, if they should not be we need to emit @@ -490,13 +515,21 @@ static struct bkey_s_c_dirent dirent_get_by_pos(struct btree_trans *trans, static int remove_backpointer(struct btree_trans *trans, struct bch_inode_unpacked *inode) { - if (!inode->bi_dir) + if (!bch2_inode_has_backpointer(inode)) return 0; + u32 snapshot = inode->bi_snapshot; + + if (inode->bi_parent_subvol) { + int ret = bch2_subvolume_get_snapshot(trans, inode->bi_parent_subvol, &snapshot); + if (ret) + return ret; + } + struct bch_fs *c = trans->c; struct btree_iter iter; struct bkey_s_c_dirent d = dirent_get_by_pos(trans, &iter, - SPOS(inode->bi_dir, inode->bi_dir_offset, inode->bi_snapshot)); + SPOS(inode->bi_dir, inode->bi_dir_offset, snapshot)); int ret = bkey_err(d) ?: dirent_points_to_inode(c, d, inode) ?: bch2_fsck_remove_dirent(trans, d.k->p); @@ -695,14 +728,8 @@ static int snapshots_seen_update(struct bch_fs *c, struct snapshots_seen *s, static bool key_visible_in_snapshot(struct bch_fs *c, struct snapshots_seen *seen, u32 id, u32 ancestor) { - ssize_t i; - EBUG_ON(id > ancestor); - /* @ancestor should be the snapshot most recently added to @seen */ - EBUG_ON(ancestor != seen->pos.snapshot); - EBUG_ON(ancestor != darray_last(seen->ids)); - if (id == ancestor) return true; @@ -718,11 +745,8 @@ static bool key_visible_in_snapshot(struct bch_fs *c, struct snapshots_seen *see * numerically, since snapshot ID lists are kept sorted, so if we find * an id that's an ancestor of @id we're done: */ - - for (i = seen->ids.nr - 2; - i >= 0 && seen->ids.data[i] >= id; - --i) - if (bch2_snapshot_is_ancestor(c, id, seen->ids.data[i])) + darray_for_each_reverse(seen->ids, i) + if (*i != ancestor && bch2_snapshot_is_ancestor(c, id, *i)) return false; return true; @@ -806,7 +830,7 @@ static int add_inode(struct bch_fs *c, struct inode_walker *w, if (!n->whiteout) { return bch2_inode_unpack(inode, &n->inode); } else { - n->inode.bi_inum = inode.k->p.inode; + n->inode.bi_inum = inode.k->p.offset; n->inode.bi_snapshot = inode.k->p.snapshot; return 0; } @@ -903,17 +927,15 @@ lookup_inode_for_snapshot(struct btree_trans *trans, struct inode_walker *w, str w->last_pos.inode, k.k->p.snapshot, i->inode.bi_snapshot, (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { - struct bch_inode_unpacked new = i->inode; - struct bkey_i whiteout; - - new.bi_snapshot = k.k->p.snapshot; - if (!i->whiteout) { + struct bch_inode_unpacked new = i->inode; + new.bi_snapshot = k.k->p.snapshot; ret = __bch2_fsck_write_inode(trans, &new); } else { + struct bkey_i whiteout; bkey_init(&whiteout.k); whiteout.k.type = KEY_TYPE_whiteout; - whiteout.k.p = SPOS(0, i->inode.bi_inum, i->inode.bi_snapshot); + whiteout.k.p = SPOS(0, i->inode.bi_inum, k.k->p.snapshot); ret = bch2_btree_insert_nonextent(trans, BTREE_ID_inodes, &whiteout, BTREE_UPDATE_internal_snapshot_node); @@ -1135,13 +1157,14 @@ static int check_inode(struct btree_trans *trans, if (ret) goto err; - if (u.bi_dir || u.bi_dir_offset) { + if (bch2_inode_has_backpointer(&u)) { ret = check_inode_dirent_inode(trans, &u, &do_update); if (ret) goto err; } - if (fsck_err_on(u.bi_dir && (u.bi_flags & BCH_INODE_unlinked), + if (fsck_err_on(bch2_inode_has_backpointer(&u) && + (u.bi_flags & BCH_INODE_unlinked), trans, inode_unlinked_but_has_dirent, "inode unlinked but has dirent\n%s", (printbuf_reset(&buf), @@ -1438,6 +1461,7 @@ static int check_key_has_inode(struct btree_trans *trans, { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; + struct btree_iter iter2 = {}; int ret = PTR_ERR_OR_ZERO(i); if (ret) return ret; @@ -1447,40 +1471,105 @@ static int check_key_has_inode(struct btree_trans *trans, bool have_inode = i && !i->whiteout; - if (!have_inode && (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_inodes))) { - ret = reconstruct_inode(trans, iter->btree_id, k.k->p.snapshot, k.k->p.inode) ?: - bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); - if (ret) - goto err; + if (!have_inode && (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_inodes))) + goto reconstruct; - inode->last_pos.inode--; - ret = bch_err_throw(c, transaction_restart_nested); - goto err; + if (have_inode && btree_matches_i_mode(iter->btree_id, i->inode.bi_mode)) + goto out; + + prt_printf(&buf, ", "); + + bool have_old_inode = false; + darray_for_each(inode->inodes, i2) + if (!i2->whiteout && + bch2_snapshot_is_ancestor(c, k.k->p.snapshot, i2->inode.bi_snapshot) && + btree_matches_i_mode(iter->btree_id, i2->inode.bi_mode)) { + prt_printf(&buf, "but found good inode in older snapshot\n"); + bch2_inode_unpacked_to_text(&buf, &i2->inode); + prt_newline(&buf); + have_old_inode = true; + break; + } + + struct bkey_s_c k2; + unsigned nr_keys = 0; + + prt_printf(&buf, "found keys:\n"); + + for_each_btree_key_max_norestart(trans, iter2, iter->btree_id, + SPOS(k.k->p.inode, 0, k.k->p.snapshot), + POS(k.k->p.inode, U64_MAX), + 0, k2, ret) { + nr_keys++; + if (nr_keys <= 10) { + bch2_bkey_val_to_text(&buf, c, k2); + prt_newline(&buf); + } + if (nr_keys >= 100) + break; } - if (fsck_err_on(!have_inode, - trans, key_in_missing_inode, - "key in missing inode:\n%s", - (printbuf_reset(&buf), - bch2_bkey_val_to_text(&buf, c, k), buf.buf))) - goto delete; + if (ret) + goto err; - if (fsck_err_on(have_inode && !btree_matches_i_mode(iter->btree_id, i->inode.bi_mode), - trans, key_in_wrong_inode_type, - "key for wrong inode mode %o:\n%s", - i->inode.bi_mode, - (printbuf_reset(&buf), - bch2_bkey_val_to_text(&buf, c, k), buf.buf))) - goto delete; + if (nr_keys > 100) + prt_printf(&buf, "found > %u keys for this missing inode\n", nr_keys); + else if (nr_keys > 10) + prt_printf(&buf, "found %u keys for this missing inode\n", nr_keys); + + if (!have_inode) { + if (fsck_err_on(!have_inode, + trans, key_in_missing_inode, + "key in missing inode%s", buf.buf)) { + /* + * Maybe a deletion that raced with data move, or something + * weird like that? But if we know the inode was deleted, or + * it's just a few keys, we can safely delete them. + * + * If it's many keys, we should probably recreate the inode + */ + if (have_old_inode || nr_keys <= 2) + goto delete; + else + goto reconstruct; + } + } else { + /* + * not autofix, this one would be a giant wtf - bit error in the + * inode corrupting i_mode? + * + * may want to try repairing inode instead of deleting + */ + if (fsck_err_on(!btree_matches_i_mode(iter->btree_id, i->inode.bi_mode), + trans, key_in_wrong_inode_type, + "key for wrong inode mode %o%s", + i->inode.bi_mode, buf.buf)) + goto delete; + } out: err: fsck_err: + bch2_trans_iter_exit(trans, &iter2); printbuf_exit(&buf); bch_err_fn(c, ret); return ret; delete: + /* + * XXX: print out more info + * count up extents for this inode, check if we have different inode in + * an older snapshot version, perhaps decide if we want to reconstitute + */ ret = bch2_btree_delete_at(trans, iter, BTREE_UPDATE_internal_snapshot_node); goto out; +reconstruct: + ret = reconstruct_inode(trans, iter->btree_id, k.k->p.snapshot, k.k->p.inode) ?: + bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); + if (ret) + goto err; + + inode->last_pos.inode--; + ret = bch_err_throw(c, transaction_restart_nested); + goto out; } static int check_i_sectors_notnested(struct btree_trans *trans, struct inode_walker *w) @@ -1822,18 +1911,39 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter, !key_visible_in_snapshot(c, s, i->inode.bi_snapshot, k.k->p.snapshot)) continue; - if (fsck_err_on(k.k->p.offset > round_up(i->inode.bi_size, block_bytes(c)) >> 9 && + u64 last_block = round_up(i->inode.bi_size, block_bytes(c)) >> 9; + + if (fsck_err_on(k.k->p.offset > last_block && !bkey_extent_is_reservation(k), trans, extent_past_end_of_inode, "extent type past end of inode %llu:%u, i_size %llu\n%s", i->inode.bi_inum, i->inode.bi_snapshot, i->inode.bi_size, (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { - struct btree_iter iter2; + struct bkey_i *whiteout = bch2_trans_kmalloc(trans, sizeof(*whiteout)); + ret = PTR_ERR_OR_ZERO(whiteout); + if (ret) + goto err; + + bkey_init(&whiteout->k); + whiteout->k.p = SPOS(k.k->p.inode, + last_block, + i->inode.bi_snapshot); + bch2_key_resize(&whiteout->k, + min(KEY_SIZE_MAX & (~0 << c->block_bits), + U64_MAX - whiteout->k.p.offset)); + - bch2_trans_copy_iter(trans, &iter2, iter); - bch2_btree_iter_set_snapshot(trans, &iter2, i->inode.bi_snapshot); + /* + * Need a normal (not BTREE_ITER_all_snapshots) + * iterator, if we're deleting in a different + * snapshot and need to emit a whiteout + */ + struct btree_iter iter2; + bch2_trans_iter_init(trans, &iter2, BTREE_ID_extents, + bkey_start_pos(&whiteout->k), + BTREE_ITER_intent); ret = bch2_btree_iter_traverse(trans, &iter2) ?: - bch2_btree_delete_at(trans, &iter2, + bch2_trans_update(trans, &iter2, whiteout, BTREE_UPDATE_internal_snapshot_node); bch2_trans_iter_exit(trans, &iter2); if (ret) @@ -1949,14 +2059,22 @@ static int check_subdir_count_notnested(struct btree_trans *trans, struct inode_ continue; } - if (fsck_err_on(i->inode.bi_nlink != i->count, - trans, inode_dir_wrong_nlink, - "directory %llu:%u with wrong i_nlink: got %u, should be %llu", - w->last_pos.inode, i->inode.bi_snapshot, i->inode.bi_nlink, i->count)) { - i->inode.bi_nlink = i->count; - ret = bch2_fsck_write_inode(trans, &i->inode); - if (ret) - break; + if (i->inode.bi_nlink != i->count) { + CLASS(printbuf, buf)(); + + lockrestart_do(trans, + bch2_inum_snapshot_to_path(trans, w->last_pos.inode, + i->inode.bi_snapshot, NULL, &buf)); + + if (fsck_err_on(i->inode.bi_nlink != i->count, + trans, inode_dir_wrong_nlink, + "directory with wrong i_nlink: got %u, should be %llu\n%s", + i->inode.bi_nlink, i->count, buf.buf)) { + i->inode.bi_nlink = i->count; + ret = bch2_fsck_write_inode(trans, &i->inode); + if (ret) + break; + } } } fsck_err: @@ -2493,6 +2611,11 @@ static int check_subvol_path(struct btree_trans *trans, struct btree_iter *iter, if (k.k->type != KEY_TYPE_subvolume) return 0; + subvol_inum start = { + .subvol = k.k->p.offset, + .inum = le64_to_cpu(bkey_s_c_to_subvolume(k).v->inode), + }; + while (k.k->p.offset != BCACHEFS_ROOT_SUBVOL) { ret = darray_push(&subvol_path, k.k->p.offset); if (ret) @@ -2511,11 +2634,11 @@ static int check_subvol_path(struct btree_trans *trans, struct btree_iter *iter, if (darray_u32_has(&subvol_path, parent)) { printbuf_reset(&buf); - prt_printf(&buf, "subvolume loop:\n"); + prt_printf(&buf, "subvolume loop: "); - darray_for_each_reverse(subvol_path, i) - prt_printf(&buf, "%u ", *i); - prt_printf(&buf, "%u", parent); + ret = bch2_inum_to_path(trans, start, &buf); + if (ret) + goto err; if (fsck_err(trans, subvol_loop, "%s", buf.buf)) ret = reattach_subvol(trans, s); @@ -2559,19 +2682,13 @@ int bch2_check_subvolume_structure(struct bch_fs *c) return ret; } -struct pathbuf_entry { - u64 inum; - u32 snapshot; -}; - -typedef DARRAY(struct pathbuf_entry) pathbuf; - -static int bch2_bi_depth_renumber_one(struct btree_trans *trans, struct pathbuf_entry *p, +static int bch2_bi_depth_renumber_one(struct btree_trans *trans, + u64 inum, u32 snapshot, u32 new_depth) { struct btree_iter iter; struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes, - SPOS(0, p->inum, p->snapshot), 0); + SPOS(0, inum, snapshot), 0); struct bch_inode_unpacked inode; int ret = bkey_err(k) ?: @@ -2590,14 +2707,15 @@ err: return ret; } -static int bch2_bi_depth_renumber(struct btree_trans *trans, pathbuf *path, u32 new_bi_depth) +static int bch2_bi_depth_renumber(struct btree_trans *trans, darray_u64 *path, + u32 snapshot, u32 new_bi_depth) { u32 restart_count = trans->restart_count; int ret = 0; darray_for_each_reverse(*path, i) { ret = nested_lockrestart_do(trans, - bch2_bi_depth_renumber_one(trans, i, new_bi_depth)); + bch2_bi_depth_renumber_one(trans, *i, snapshot, new_bi_depth)); bch_err_fn(trans->c, ret); if (ret) break; @@ -2608,37 +2726,36 @@ static int bch2_bi_depth_renumber(struct btree_trans *trans, pathbuf *path, u32 return ret ?: trans_was_restarted(trans, restart_count); } -static bool path_is_dup(pathbuf *p, u64 inum, u32 snapshot) -{ - darray_for_each(*p, i) - if (i->inum == inum && - i->snapshot == snapshot) - return true; - return false; -} - static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k) { struct bch_fs *c = trans->c; struct btree_iter inode_iter = {}; - pathbuf path = {}; + darray_u64 path = {}; struct printbuf buf = PRINTBUF; u32 snapshot = inode_k.k->p.snapshot; bool redo_bi_depth = false; u32 min_bi_depth = U32_MAX; int ret = 0; + struct bpos start = inode_k.k->p; + struct bch_inode_unpacked inode; ret = bch2_inode_unpack(inode_k, &inode); if (ret) return ret; - while (!inode.bi_subvol) { + /* + * If we're running full fsck, check_dirents() will have already ran, + * and we shouldn't see any missing backpointers here - otherwise that's + * handled separately, by check_unreachable_inodes + */ + while (!inode.bi_subvol && + bch2_inode_has_backpointer(&inode)) { struct btree_iter dirent_iter; struct bkey_s_c_dirent d; - u32 parent_snapshot = snapshot; - d = inode_get_dirent(trans, &dirent_iter, &inode, &parent_snapshot); + d = dirent_get_by_pos(trans, &dirent_iter, + SPOS(inode.bi_dir, inode.bi_dir_offset, snapshot)); ret = bkey_err(d.s_c); if (ret && !bch2_err_matches(ret, ENOENT)) goto out; @@ -2656,15 +2773,10 @@ static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k) bch2_trans_iter_exit(trans, &dirent_iter); - ret = darray_push(&path, ((struct pathbuf_entry) { - .inum = inode.bi_inum, - .snapshot = snapshot, - })); + ret = darray_push(&path, inode.bi_inum); if (ret) return ret; - snapshot = parent_snapshot; - bch2_trans_iter_exit(trans, &inode_iter); inode_k = bch2_bkey_get_iter(trans, &inode_iter, BTREE_ID_inodes, SPOS(0, inode.bi_dir, snapshot), 0); @@ -2686,15 +2798,22 @@ static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k) break; inode = parent_inode; - snapshot = inode_k.k->p.snapshot; redo_bi_depth = true; - if (path_is_dup(&path, inode.bi_inum, snapshot)) { + if (darray_find(path, inode.bi_inum)) { printbuf_reset(&buf); - prt_printf(&buf, "directory structure loop:\n"); - darray_for_each_reverse(path, i) - prt_printf(&buf, "%llu:%u ", i->inum, i->snapshot); - prt_printf(&buf, "%llu:%u", inode.bi_inum, snapshot); + prt_printf(&buf, "directory structure loop in snapshot %u: ", + snapshot); + + ret = bch2_inum_snapshot_to_path(trans, start.offset, start.snapshot, NULL, &buf); + if (ret) + goto out; + + if (c->opts.verbose) { + prt_newline(&buf); + darray_for_each(path, i) + prt_printf(&buf, "%llu ", *i); + } if (fsck_err(trans, dir_loop, "%s", buf.buf)) { ret = remove_backpointer(trans, &inode); @@ -2714,7 +2833,7 @@ static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k) min_bi_depth = 0; if (redo_bi_depth) - ret = bch2_bi_depth_renumber(trans, &path, min_bi_depth); + ret = bch2_bi_depth_renumber(trans, &path, snapshot, min_bi_depth); out: fsck_err: bch2_trans_iter_exit(trans, &inode_iter); @@ -2731,7 +2850,7 @@ fsck_err: int bch2_check_directory_structure(struct bch_fs *c) { int ret = bch2_trans_run(c, - for_each_btree_key_commit(trans, iter, BTREE_ID_inodes, POS_MIN, + for_each_btree_key_reverse_commit(trans, iter, BTREE_ID_inodes, POS_MIN, BTREE_ITER_intent| BTREE_ITER_prefetch| BTREE_ITER_all_snapshots, k, diff --git a/fs/bcachefs/inode.h b/fs/bcachefs/inode.h index 82cec2836cbd..b8ec3e628d90 100644 --- a/fs/bcachefs/inode.h +++ b/fs/bcachefs/inode.h @@ -254,6 +254,11 @@ static inline bool bch2_inode_casefold(struct bch_fs *c, const struct bch_inode_ : c->opts.casefold; } +static inline bool bch2_inode_has_backpointer(const struct bch_inode_unpacked *bi) +{ + return bi->bi_dir || bi->bi_dir_offset; +} + /* i_nlink: */ static inline unsigned nlink_bias(umode_t mode) diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c index 04bbdcf58e40..cd184b219a65 100644 --- a/fs/bcachefs/io_read.c +++ b/fs/bcachefs/io_read.c @@ -1491,7 +1491,12 @@ void bch2_read_bio_to_text(struct printbuf *out, struct bch_read_bio *rbio) prt_printf(out, "have_ioref:\t%u\n", rbio->have_ioref); prt_printf(out, "narrow_crcs:\t%u\n", rbio->narrow_crcs); prt_printf(out, "context:\t%u\n", rbio->context); - prt_printf(out, "ret:\t%s\n", bch2_err_str(rbio->ret)); + + int ret = READ_ONCE(rbio->ret); + if (ret < 0) + prt_printf(out, "ret:\t%s\n", bch2_err_str(ret)); + else + prt_printf(out, "ret:\t%i\n", ret); prt_printf(out, "flags:\t"); bch2_prt_bitflags(out, bch2_read_bio_flags, rbio->flags); diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c index dda802a656cf..f22b05e02c1e 100644 --- a/fs/bcachefs/journal.c +++ b/fs/bcachefs/journal.c @@ -1283,7 +1283,7 @@ static int bch2_set_nr_journal_buckets_loop(struct bch_fs *c, struct bch_dev *ca ret = 0; /* wait and retry */ bch2_disk_reservation_put(c, &disk_res); - closure_sync(&cl); + bch2_wait_on_allocator(c, &cl); } return ret; @@ -1474,14 +1474,13 @@ void bch2_fs_journal_stop(struct journal *j) clear_bit(JOURNAL_running, &j->flags); } -int bch2_fs_journal_start(struct journal *j, u64 cur_seq) +int bch2_fs_journal_start(struct journal *j, u64 last_seq, u64 cur_seq) { struct bch_fs *c = container_of(j, struct bch_fs, journal); struct journal_entry_pin_list *p; struct journal_replay *i, **_i; struct genradix_iter iter; bool had_entries = false; - u64 last_seq = cur_seq, nr, seq; /* * @@ -1495,17 +1494,11 @@ int bch2_fs_journal_start(struct journal *j, u64 cur_seq) return -EINVAL; } - genradix_for_each_reverse(&c->journal_entries, iter, _i) { - i = *_i; - - if (journal_replay_ignore(i)) - continue; + /* Clean filesystem? */ + if (!last_seq) + last_seq = cur_seq; - last_seq = le64_to_cpu(i->j.last_seq); - break; - } - - nr = cur_seq - last_seq; + u64 nr = cur_seq - last_seq; /* * Extra fudge factor, in case we crashed when the journal pin fifo was @@ -1532,6 +1525,7 @@ int bch2_fs_journal_start(struct journal *j, u64 cur_seq) j->pin.back = cur_seq; atomic64_set(&j->seq, cur_seq - 1); + u64 seq; fifo_for_each_entry_ptr(p, &j->pin, seq) journal_pin_list_init(p, 1); diff --git a/fs/bcachefs/journal.h b/fs/bcachefs/journal.h index 83734fe4331f..977907038d98 100644 --- a/fs/bcachefs/journal.h +++ b/fs/bcachefs/journal.h @@ -453,7 +453,7 @@ int bch2_fs_journal_alloc(struct bch_fs *); void bch2_dev_journal_stop(struct journal *, struct bch_dev *); void bch2_fs_journal_stop(struct journal *); -int bch2_fs_journal_start(struct journal *, u64); +int bch2_fs_journal_start(struct journal *, u64, u64); void bch2_journal_set_replay_done(struct journal *); void bch2_dev_journal_exit(struct bch_dev *); diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c index 0b15d71a8d2d..dd3f3434c1b0 100644 --- a/fs/bcachefs/journal_io.c +++ b/fs/bcachefs/journal_io.c @@ -160,6 +160,9 @@ static int journal_entry_add(struct bch_fs *c, struct bch_dev *ca, struct printbuf buf = PRINTBUF; int ret = JOURNAL_ENTRY_ADD_OK; + if (last_seq && c->opts.journal_rewind) + last_seq = min(last_seq, c->opts.journal_rewind); + if (!c->journal.oldest_seq_found_ondisk || le64_to_cpu(j->seq) < c->journal.oldest_seq_found_ondisk) c->journal.oldest_seq_found_ondisk = le64_to_cpu(j->seq); @@ -1430,11 +1433,21 @@ int bch2_journal_read(struct bch_fs *c, printbuf_reset(&buf); prt_printf(&buf, "journal read done, replaying entries %llu-%llu", *last_seq, *blacklist_seq - 1); + + /* + * Drop blacklisted entries and entries older than last_seq (or start of + * journal rewind: + */ + u64 drop_before = *last_seq; + if (c->opts.journal_rewind) { + drop_before = min(drop_before, c->opts.journal_rewind); + prt_printf(&buf, " (rewinding from %llu)", c->opts.journal_rewind); + } + + *last_seq = drop_before; if (*start_seq != *blacklist_seq) prt_printf(&buf, " (unflushed %llu-%llu)", *blacklist_seq, *start_seq - 1); bch_info(c, "%s", buf.buf); - - /* Drop blacklisted entries and entries older than last_seq: */ genradix_for_each(&c->journal_entries, radix_iter, _i) { i = *_i; @@ -1442,7 +1455,7 @@ int bch2_journal_read(struct bch_fs *c, continue; seq = le64_to_cpu(i->j.seq); - if (seq < *last_seq) { + if (seq < drop_before) { journal_replay_free(c, i, false); continue; } @@ -1455,7 +1468,7 @@ int bch2_journal_read(struct bch_fs *c, } } - ret = bch2_journal_check_for_missing(c, *last_seq, *blacklist_seq - 1); + ret = bch2_journal_check_for_missing(c, drop_before, *blacklist_seq - 1); if (ret) goto err; @@ -1703,9 +1716,10 @@ static CLOSURE_CALLBACK(journal_write_done) bch2_log_msg_start(c, &buf); if (err == -BCH_ERR_journal_write_err) - prt_printf(&buf, "unable to write journal to sufficient devices"); + prt_printf(&buf, "unable to write journal to sufficient devices\n"); else - prt_printf(&buf, "journal write error marking replicas: %s", bch2_err_str(err)); + prt_printf(&buf, "journal write error marking replicas: %s\n", + bch2_err_str(err)); bch2_fs_emergency_read_only2(c, &buf); diff --git a/fs/bcachefs/namei.c b/fs/bcachefs/namei.c index 779c22eb3979..c3f87c59922d 100644 --- a/fs/bcachefs/namei.c +++ b/fs/bcachefs/namei.c @@ -625,14 +625,26 @@ static int __bch2_inum_to_path(struct btree_trans *trans, { unsigned orig_pos = path->pos; int ret = 0; + DARRAY(subvol_inum) inums = {}; + + if (!snapshot) { + ret = bch2_subvolume_get_snapshot(trans, subvol, &snapshot); + if (ret) + goto disconnected; + } while (true) { - if (!snapshot) { - ret = bch2_subvolume_get_snapshot(trans, subvol, &snapshot); - if (ret) - goto disconnected; + subvol_inum n = (subvol_inum) { subvol ?: snapshot, inum }; + + if (darray_find_p(inums, i, i->subvol == n.subvol && i->inum == n.inum)) { + prt_str_reversed(path, "(loop)"); + break; } + ret = darray_push(&inums, n); + if (ret) + goto err; + struct bch_inode_unpacked inode; ret = bch2_inode_find_by_inum_snapshot(trans, inum, snapshot, &inode, 0); if (ret) @@ -650,7 +662,9 @@ static int __bch2_inum_to_path(struct btree_trans *trans, inum = inode.bi_dir; if (inode.bi_parent_subvol) { subvol = inode.bi_parent_subvol; - snapshot = 0; + ret = bch2_subvolume_get_snapshot(trans, inode.bi_parent_subvol, &snapshot); + if (ret) + goto disconnected; } struct btree_iter d_iter; @@ -662,6 +676,7 @@ static int __bch2_inum_to_path(struct btree_trans *trans, goto disconnected; struct qstr dirent_name = bch2_dirent_get_name(d); + prt_bytes_reversed(path, dirent_name.name, dirent_name.len); prt_char(path, '/'); @@ -677,8 +692,10 @@ out: goto err; reverse_bytes(path->buf + orig_pos, path->pos - orig_pos); + darray_exit(&inums); return 0; err: + darray_exit(&inums); return ret; disconnected: if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) @@ -717,8 +734,7 @@ static int bch2_check_dirent_inode_dirent(struct btree_trans *trans, if (inode_points_to_dirent(target, d)) return 0; - if (!target->bi_dir && - !target->bi_dir_offset) { + if (!bch2_inode_has_backpointer(target)) { fsck_err_on(S_ISDIR(target->bi_mode), trans, inode_dir_missing_backpointer, "directory with missing backpointer\n%s", diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h index 2a02606254b3..b0a76bd6d6f5 100644 --- a/fs/bcachefs/opts.h +++ b/fs/bcachefs/opts.h @@ -379,6 +379,11 @@ enum fsck_err_opts { OPT_BOOL(), \ BCH2_NO_SB_OPT, false, \ NULL, "Exit recovery immediately prior to journal replay")\ + x(journal_rewind, u64, \ + OPT_FS|OPT_MOUNT, \ + OPT_UINT(0, U64_MAX), \ + BCH2_NO_SB_OPT, 0, \ + NULL, "Rewind journal") \ x(recovery_passes, u64, \ OPT_FS|OPT_MOUNT, \ OPT_BITFIELD(bch2_recovery_passes), \ diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index 0b21fa6ff062..d0b7e3a36a54 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -607,6 +607,7 @@ static int read_btree_roots(struct bch_fs *c) buf.buf, bch2_err_str(ret))) { if (btree_id_is_alloc(i)) r->error = 0; + ret = 0; } } @@ -692,7 +693,7 @@ static bool check_version_upgrade(struct bch_fs *c) ret = true; } - if (new_version > c->sb.version_incompat && + if (new_version > c->sb.version_incompat_allowed && c->opts.version_upgrade == BCH_VERSION_UPGRADE_incompatible) { struct printbuf buf = PRINTBUF; @@ -757,6 +758,21 @@ int bch2_fs_recovery(struct bch_fs *c) if (c->opts.nochanges) c->opts.read_only = true; + if (c->opts.journal_rewind) { + bch_info(c, "rewinding journal, fsck required"); + c->opts.fsck = true; + } + + if (go_rw_in_recovery(c)) { + /* + * start workqueues/kworkers early - kthread creation checks for + * pending signals, which is _very_ annoying + */ + ret = bch2_fs_init_rw(c); + if (ret) + goto err; + } + mutex_lock(&c->sb_lock); struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); bool write_sb = false; @@ -965,7 +981,7 @@ use_clean: ret = bch2_journal_log_msg(c, "starting journal at entry %llu, replaying %llu-%llu", journal_seq, last_seq, blacklist_seq - 1) ?: - bch2_fs_journal_start(&c->journal, journal_seq); + bch2_fs_journal_start(&c->journal, last_seq, journal_seq); if (ret) goto err; @@ -1126,7 +1142,7 @@ fsck_err: struct printbuf buf = PRINTBUF; bch2_log_msg_start(c, &buf); - prt_printf(&buf, "error in recovery: %s", bch2_err_str(ret)); + prt_printf(&buf, "error in recovery: %s\n", bch2_err_str(ret)); bch2_fs_emergency_read_only2(c, &buf); bch2_print_str(c, KERN_ERR, buf.buf); @@ -1181,7 +1197,7 @@ int bch2_fs_initialize(struct bch_fs *c) * journal_res_get() will crash if called before this has * set up the journal.pin FIFO and journal.cur pointer: */ - ret = bch2_fs_journal_start(&c->journal, 1); + ret = bch2_fs_journal_start(&c->journal, 1, 1); if (ret) goto err; diff --git a/fs/bcachefs/recovery_passes.c b/fs/bcachefs/recovery_passes.c index 35ac0d64d73a..c09ed2dd4639 100644 --- a/fs/bcachefs/recovery_passes.c +++ b/fs/bcachefs/recovery_passes.c @@ -217,11 +217,7 @@ static int bch2_set_may_go_rw(struct bch_fs *c) set_bit(BCH_FS_may_go_rw, &c->flags); - if (keys->nr || - !c->opts.read_only || - !c->sb.clean || - c->opts.recovery_passes || - (c->opts.fsck && !(c->sb.features & BIT_ULL(BCH_FEATURE_no_alloc_info)))) { + if (go_rw_in_recovery(c)) { if (c->sb.features & BIT_ULL(BCH_FEATURE_no_alloc_info)) { bch_info(c, "mounting a filesystem with no alloc info read-write; will recreate"); bch2_reconstruct_alloc(c); @@ -317,6 +313,9 @@ static bool recovery_pass_needs_set(struct bch_fs *c, */ bool in_recovery = test_bit(BCH_FS_in_recovery, &c->flags); bool persistent = !in_recovery || !(*flags & RUN_RECOVERY_PASS_nopersistent); + bool rewind = in_recovery && + r->curr_pass > pass && + !(r->passes_complete & BIT_ULL(pass)); if (persistent ? !(c->sb.recovery_passes_required & BIT_ULL(pass)) @@ -327,6 +326,9 @@ static bool recovery_pass_needs_set(struct bch_fs *c, (r->passes_ratelimiting & BIT_ULL(pass))) return true; + if (rewind) + return true; + return false; } @@ -341,7 +343,6 @@ int __bch2_run_explicit_recovery_pass(struct bch_fs *c, struct bch_fs_recovery *r = &c->recovery; int ret = 0; - lockdep_assert_held(&c->sb_lock); bch2_printbuf_make_room(out, 1024); @@ -412,10 +413,8 @@ int bch2_run_explicit_recovery_pass(struct bch_fs *c, { int ret = 0; - scoped_guard(mutex, &c->sb_lock) { - if (!recovery_pass_needs_set(c, pass, &flags)) - return 0; - + if (recovery_pass_needs_set(c, pass, &flags)) { + guard(mutex)(&c->sb_lock); ret = __bch2_run_explicit_recovery_pass(c, out, pass, flags); bch2_write_super(c); } diff --git a/fs/bcachefs/recovery_passes.h b/fs/bcachefs/recovery_passes.h index 260571c7105e..2117f0ce1922 100644 --- a/fs/bcachefs/recovery_passes.h +++ b/fs/bcachefs/recovery_passes.h @@ -17,6 +17,15 @@ enum bch_run_recovery_pass_flags { RUN_RECOVERY_PASS_ratelimit = BIT(1), }; +static inline bool go_rw_in_recovery(struct bch_fs *c) +{ + return (c->journal_keys.nr || + !c->opts.read_only || + !c->sb.clean || + c->opts.recovery_passes || + (c->opts.fsck && !(c->sb.features & BIT_ULL(BCH_FEATURE_no_alloc_info)))); +} + int bch2_run_print_explicit_recovery_pass(struct bch_fs *, enum bch_recovery_pass); int __bch2_run_explicit_recovery_pass(struct bch_fs *, struct printbuf *, diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c index a535abd44df3..92b90cfe622b 100644 --- a/fs/bcachefs/reflink.c +++ b/fs/bcachefs/reflink.c @@ -64,6 +64,9 @@ void bch2_reflink_p_to_text(struct printbuf *out, struct bch_fs *c, REFLINK_P_IDX(p.v), le32_to_cpu(p.v->front_pad), le32_to_cpu(p.v->back_pad)); + + if (REFLINK_P_ERROR(p.v)) + prt_str(out, " error"); } bool bch2_reflink_p_merge(struct bch_fs *c, struct bkey_s _l, struct bkey_s_c _r) @@ -269,13 +272,12 @@ struct bkey_s_c bch2_lookup_indirect_extent(struct btree_trans *trans, return k; if (unlikely(!bkey_extent_is_reflink_data(k.k))) { - unsigned size = min((u64) k.k->size, - REFLINK_P_IDX(p.v) + p.k->size + le32_to_cpu(p.v->back_pad) - - reflink_offset); - bch2_key_resize(&iter->k, size); + u64 missing_end = min(k.k->p.offset, + REFLINK_P_IDX(p.v) + p.k->size + le32_to_cpu(p.v->back_pad)); + BUG_ON(reflink_offset == missing_end); int ret = bch2_indirect_extent_missing_error(trans, p, reflink_offset, - k.k->p.offset, should_commit); + missing_end, should_commit); if (ret) { bch2_trans_iter_exit(trans, iter); return bkey_s_c_err(ret); diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h index d06e73884871..0641fb634bd4 100644 --- a/fs/bcachefs/sb-errors_format.h +++ b/fs/bcachefs/sb-errors_format.h @@ -3,9 +3,10 @@ #define _BCACHEFS_SB_ERRORS_FORMAT_H enum bch_fsck_flags { - FSCK_CAN_FIX = 1 << 0, - FSCK_CAN_IGNORE = 1 << 1, - FSCK_AUTOFIX = 1 << 2, + FSCK_CAN_FIX = BIT(0), + FSCK_CAN_IGNORE = BIT(1), + FSCK_AUTOFIX = BIT(2), + FSCK_ERR_NO_LOG = BIT(3), }; #define BCH_SB_ERRS() \ @@ -217,7 +218,7 @@ enum bch_fsck_flags { x(inode_str_hash_invalid, 194, 0) \ x(inode_v3_fields_start_bad, 195, 0) \ x(inode_snapshot_mismatch, 196, 0) \ - x(snapshot_key_missing_inode_snapshot, 314, 0) \ + x(snapshot_key_missing_inode_snapshot, 314, FSCK_AUTOFIX) \ x(inode_unlinked_but_clean, 197, 0) \ x(inode_unlinked_but_nlink_nonzero, 198, 0) \ x(inode_unlinked_and_not_open, 281, 0) \ @@ -251,20 +252,20 @@ enum bch_fsck_flags { x(deleted_inode_not_unlinked, 214, FSCK_AUTOFIX) \ x(deleted_inode_has_child_snapshots, 288, FSCK_AUTOFIX) \ x(extent_overlapping, 215, 0) \ - x(key_in_missing_inode, 216, 0) \ + x(key_in_missing_inode, 216, FSCK_AUTOFIX) \ x(key_in_wrong_inode_type, 217, 0) \ - x(extent_past_end_of_inode, 218, 0) \ + x(extent_past_end_of_inode, 218, FSCK_AUTOFIX) \ 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(dirent_d_type_wrong, 225, FSCK_AUTOFIX) \ 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_inode, 229, FSCK_AUTOFIX) \ x(dirent_to_overwritten_inode, 302, 0) \ x(dirent_to_missing_subvol, 230, 0) \ x(dirent_to_itself, 231, 0) \ @@ -300,7 +301,7 @@ enum bch_fsck_flags { 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, FSCK_AUTOFIX) \ + x(btree_root_unreadable_and_scan_found_nothing, 263, 0) \ x(snapshot_node_missing, 264, FSCK_AUTOFIX) \ x(dup_backpointer_to_bad_csum_extent, 265, 0) \ x(btree_bitmap_not_marked, 266, FSCK_AUTOFIX) \ diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c index 23a332d76b32..4c43d2a2c1f5 100644 --- a/fs/bcachefs/snapshot.c +++ b/fs/bcachefs/snapshot.c @@ -135,7 +135,9 @@ static bool test_ancestor_bitmap(struct snapshot_table *t, u32 id, u32 ancestor) bool __bch2_snapshot_is_ancestor(struct bch_fs *c, u32 id, u32 ancestor) { - bool ret; +#ifdef CONFIG_BCACHEFS_DEBUG + u32 orig_id = id; +#endif guard(rcu)(); struct snapshot_table *t = rcu_dereference(c->snapshots); @@ -147,11 +149,11 @@ bool __bch2_snapshot_is_ancestor(struct bch_fs *c, u32 id, u32 ancestor) while (id && id < ancestor - IS_ANCESTOR_BITMAP) id = get_ancestor_below(t, id, ancestor); - ret = id && id < ancestor + bool ret = id && id < ancestor ? test_ancestor_bitmap(t, id, ancestor) : id == ancestor; - EBUG_ON(ret != __bch2_snapshot_is_ancestor_early(t, id, ancestor)); + EBUG_ON(ret != __bch2_snapshot_is_ancestor_early(t, orig_id, ancestor)); return ret; } @@ -869,7 +871,8 @@ static int check_snapshot_exists(struct btree_trans *trans, u32 id) for_each_btree_key_norestart(trans, iter, BTREE_ID_snapshot_trees, POS_MIN, 0, k, ret) { - if (le32_to_cpu(bkey_s_c_to_snapshot_tree(k).v->root_snapshot) == id) { + if (k.k->type == KEY_TYPE_snapshot_tree && + le32_to_cpu(bkey_s_c_to_snapshot_tree(k).v->root_snapshot) == id) { tree_id = k.k->p.offset; break; } @@ -897,7 +900,8 @@ static int check_snapshot_exists(struct btree_trans *trans, u32 id) for_each_btree_key_norestart(trans, iter, BTREE_ID_subvolumes, POS_MIN, 0, k, ret) { - if (le32_to_cpu(bkey_s_c_to_subvolume(k).v->snapshot) == id) { + if (k.k->type == KEY_TYPE_subvolume && + le32_to_cpu(bkey_s_c_to_subvolume(k).v->snapshot) == id) { snapshot->v.subvol = cpu_to_le32(k.k->p.offset); SET_BCH_SNAPSHOT_SUBVOL(&snapshot->v, true); break; diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c index a5b97c9c5163..69c097ff54e7 100644 --- a/fs/bcachefs/super.c +++ b/fs/bcachefs/super.c @@ -210,7 +210,6 @@ static int bch2_dev_alloc(struct bch_fs *, unsigned); static int bch2_dev_sysfs_online(struct bch_fs *, struct bch_dev *); static void bch2_dev_io_ref_stop(struct bch_dev *, int); static void __bch2_dev_read_only(struct bch_fs *, struct bch_dev *); -static int bch2_fs_init_rw(struct bch_fs *); struct bch_fs *bch2_dev_to_fs(dev_t dev) { @@ -794,7 +793,7 @@ err: return ret; } -static int bch2_fs_init_rw(struct bch_fs *c) +int bch2_fs_init_rw(struct bch_fs *c) { if (test_bit(BCH_FS_rw_init_done, &c->flags)) return 0; @@ -1015,6 +1014,16 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts *opts, if (ret) goto err; + if (go_rw_in_recovery(c)) { + /* + * start workqueues/kworkers early - kthread creation checks for + * pending signals, which is _very_ annoying + */ + ret = bch2_fs_init_rw(c); + if (ret) + goto err; + } + #ifdef CONFIG_UNICODE /* Default encoding until we can potentially have more as an option. */ c->cf_encoding = utf8_load(BCH_FS_DEFAULT_UTF8_ENCODING); diff --git a/fs/bcachefs/super.h b/fs/bcachefs/super.h index dc52f06cb2b9..e90bab9afe78 100644 --- a/fs/bcachefs/super.h +++ b/fs/bcachefs/super.h @@ -46,6 +46,7 @@ void __bch2_fs_stop(struct bch_fs *); void bch2_fs_free(struct bch_fs *); void bch2_fs_stop(struct bch_fs *); +int bch2_fs_init_rw(struct bch_fs *); int bch2_fs_start(struct bch_fs *); struct bch_fs *bch2_fs_open(darray_const_str *, struct bch_opts *); diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h index dc09532796af..9c5a9c551f03 100644 --- a/fs/bcachefs/trace.h +++ b/fs/bcachefs/trace.h @@ -1080,34 +1080,14 @@ TRACE_EVENT(trans_blocked_journal_reclaim, __entry->must_wait) ); -TRACE_EVENT(trans_restart_journal_preres_get, - TP_PROTO(struct btree_trans *trans, - unsigned long caller_ip, - unsigned flags), - TP_ARGS(trans, caller_ip, flags), - - TP_STRUCT__entry( - __array(char, trans_fn, 32 ) - __field(unsigned long, caller_ip ) - __field(unsigned, flags ) - ), - - TP_fast_assign( - strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn)); - __entry->caller_ip = caller_ip; - __entry->flags = flags; - ), - - TP_printk("%s %pS %x", __entry->trans_fn, - (void *) __entry->caller_ip, - __entry->flags) -); - +#if 0 +/* todo: bring back dynamic fault injection */ DEFINE_EVENT(transaction_event, trans_restart_fault_inject, TP_PROTO(struct btree_trans *trans, unsigned long caller_ip), TP_ARGS(trans, caller_ip) ); +#endif DEFINE_EVENT(transaction_event, trans_traverse_all, TP_PROTO(struct btree_trans *trans, @@ -1195,19 +1175,6 @@ DEFINE_EVENT(transaction_restart_iter, trans_restart_relock_parent_for_fill, TP_ARGS(trans, caller_ip, path) ); -DEFINE_EVENT(transaction_restart_iter, trans_restart_relock_after_fill, - TP_PROTO(struct btree_trans *trans, - unsigned long caller_ip, - struct btree_path *path), - TP_ARGS(trans, caller_ip, path) -); - -DEFINE_EVENT(transaction_event, trans_restart_key_cache_upgrade, - TP_PROTO(struct btree_trans *trans, - unsigned long caller_ip), - TP_ARGS(trans, caller_ip) -); - DEFINE_EVENT(transaction_restart_iter, trans_restart_relock_key_cache_fill, TP_PROTO(struct btree_trans *trans, unsigned long caller_ip, @@ -1229,13 +1196,6 @@ DEFINE_EVENT(transaction_restart_iter, trans_restart_relock_path_intent, TP_ARGS(trans, caller_ip, path) ); -DEFINE_EVENT(transaction_restart_iter, trans_restart_traverse, - TP_PROTO(struct btree_trans *trans, - unsigned long caller_ip, - struct btree_path *path), - TP_ARGS(trans, caller_ip, path) -); - DEFINE_EVENT(transaction_restart_iter, trans_restart_memory_allocation_failure, TP_PROTO(struct btree_trans *trans, unsigned long caller_ip, @@ -1294,44 +1254,6 @@ TRACE_EVENT(trans_restart_mem_realloced, __entry->bytes) ); -TRACE_EVENT(trans_restart_key_cache_key_realloced, - TP_PROTO(struct btree_trans *trans, - unsigned long caller_ip, - struct btree_path *path, - unsigned old_u64s, - unsigned new_u64s), - TP_ARGS(trans, caller_ip, path, old_u64s, new_u64s), - - TP_STRUCT__entry( - __array(char, trans_fn, 32 ) - __field(unsigned long, caller_ip ) - __field(enum btree_id, btree_id ) - TRACE_BPOS_entries(pos) - __field(u32, old_u64s ) - __field(u32, new_u64s ) - ), - - TP_fast_assign( - strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn)); - __entry->caller_ip = caller_ip; - - __entry->btree_id = path->btree_id; - TRACE_BPOS_assign(pos, path->pos); - __entry->old_u64s = old_u64s; - __entry->new_u64s = new_u64s; - ), - - TP_printk("%s %pS btree %s pos %llu:%llu:%u old_u64s %u new_u64s %u", - __entry->trans_fn, - (void *) __entry->caller_ip, - bch2_btree_id_str(__entry->btree_id), - __entry->pos_inode, - __entry->pos_offset, - __entry->pos_snapshot, - __entry->old_u64s, - __entry->new_u64s) -); - DEFINE_EVENT(transaction_event, trans_restart_write_buffer_flush, TP_PROTO(struct btree_trans *trans, unsigned long caller_ip), @@ -1490,6 +1412,31 @@ DEFINE_EVENT(fs_str, io_move_evacuate_bucket, TP_ARGS(c, str) ); +DEFINE_EVENT(fs_str, extent_trim_atomic, + TP_PROTO(struct bch_fs *c, const char *str), + TP_ARGS(c, str) +); + +DEFINE_EVENT(fs_str, btree_iter_peek_slot, + TP_PROTO(struct bch_fs *c, const char *str), + TP_ARGS(c, str) +); + +DEFINE_EVENT(fs_str, __btree_iter_peek, + TP_PROTO(struct bch_fs *c, const char *str), + TP_ARGS(c, str) +); + +DEFINE_EVENT(fs_str, btree_iter_peek_max, + TP_PROTO(struct bch_fs *c, const char *str), + TP_ARGS(c, str) +); + +DEFINE_EVENT(fs_str, btree_iter_peek_prev_min, + TP_PROTO(struct bch_fs *c, const char *str), + TP_ARGS(c, str) +); + #ifdef CONFIG_BCACHEFS_PATH_TRACEPOINTS TRACE_EVENT(update_by_path, @@ -1902,21 +1849,6 @@ TRACE_EVENT(btree_path_free, __entry->dup_locked) ); -TRACE_EVENT(btree_path_free_trans_begin, - TP_PROTO(btree_path_idx_t path), - TP_ARGS(path), - - TP_STRUCT__entry( - __field(btree_path_idx_t, idx ) - ), - - TP_fast_assign( - __entry->idx = path; - ), - - TP_printk(" path %3u", __entry->idx) -); - #else /* CONFIG_BCACHEFS_PATH_TRACEPOINTS */ #ifndef _TRACE_BCACHEFS_H @@ -1934,7 +1866,6 @@ static inline void trace_btree_path_traverse_start(struct btree_trans *trans, st static inline void trace_btree_path_traverse_end(struct btree_trans *trans, struct btree_path *path) {} static inline void trace_btree_path_set_pos(struct btree_trans *trans, struct btree_path *path, struct bpos *new_pos) {} static inline void trace_btree_path_free(struct btree_trans *trans, btree_path_idx_t path, struct btree_path *dup) {} -static inline void trace_btree_path_free_trans_begin(btree_path_idx_t path) {} #endif #endif /* CONFIG_BCACHEFS_PATH_TRACEPOINTS */ diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index bfe8d8af46f3..9572bdef49ee 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -9,6 +9,7 @@ #include "fuse_i.h" #include "dev_uring_i.h" +#include <linux/dax.h> #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/file.h> @@ -162,6 +163,9 @@ static void fuse_evict_inode(struct inode *inode) /* Will write inode on close/munmap and in all other dirtiers */ WARN_ON(inode->i_state & I_DIRTY_INODE); + if (FUSE_IS_DAX(inode)) + dax_break_layout_final(inode); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (inode->i_sb->s_flags & SB_ACTIVE) { diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index df4807460596..4bea008dbebd 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1105,6 +1105,7 @@ static void ff_layout_reset_read(struct nfs_pgio_header *hdr) } static int ff_layout_async_handle_error_v4(struct rpc_task *task, + u32 op_status, struct nfs4_state *state, struct nfs_client *clp, struct pnfs_layout_segment *lseg, @@ -1115,34 +1116,42 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task, struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx); struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table; - switch (task->tk_status) { - case -NFS4ERR_BADSESSION: - case -NFS4ERR_BADSLOT: - case -NFS4ERR_BAD_HIGH_SLOT: - case -NFS4ERR_DEADSESSION: - case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: - case -NFS4ERR_SEQ_FALSE_RETRY: - case -NFS4ERR_SEQ_MISORDERED: + switch (op_status) { + case NFS4_OK: + case NFS4ERR_NXIO: + break; + case NFSERR_PERM: + if (!task->tk_xprt) + break; + xprt_force_disconnect(task->tk_xprt); + goto out_retry; + case NFS4ERR_BADSESSION: + case NFS4ERR_BADSLOT: + case NFS4ERR_BAD_HIGH_SLOT: + case NFS4ERR_DEADSESSION: + case NFS4ERR_CONN_NOT_BOUND_TO_SESSION: + case NFS4ERR_SEQ_FALSE_RETRY: + case NFS4ERR_SEQ_MISORDERED: dprintk("%s ERROR %d, Reset session. Exchangeid " "flags 0x%x\n", __func__, task->tk_status, clp->cl_exchange_flags); nfs4_schedule_session_recovery(clp->cl_session, task->tk_status); - break; - case -NFS4ERR_DELAY: + goto out_retry; + case NFS4ERR_DELAY: nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY); fallthrough; - case -NFS4ERR_GRACE: + case NFS4ERR_GRACE: rpc_delay(task, FF_LAYOUT_POLL_RETRY_MAX); - break; - case -NFS4ERR_RETRY_UNCACHED_REP: - break; + goto out_retry; + case NFS4ERR_RETRY_UNCACHED_REP: + goto out_retry; /* Invalidate Layout errors */ - case -NFS4ERR_PNFS_NO_LAYOUT: - case -ESTALE: /* mapped NFS4ERR_STALE */ - case -EBADHANDLE: /* mapped NFS4ERR_BADHANDLE */ - case -EISDIR: /* mapped NFS4ERR_ISDIR */ - case -NFS4ERR_FHEXPIRED: - case -NFS4ERR_WRONG_TYPE: + case NFS4ERR_PNFS_NO_LAYOUT: + case NFS4ERR_STALE: + case NFS4ERR_BADHANDLE: + case NFS4ERR_ISDIR: + case NFS4ERR_FHEXPIRED: + case NFS4ERR_WRONG_TYPE: dprintk("%s Invalid layout error %d\n", __func__, task->tk_status); /* @@ -1155,6 +1164,11 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task, pnfs_destroy_layout(NFS_I(inode)); rpc_wake_up(&tbl->slot_tbl_waitq); goto reset; + default: + break; + } + + switch (task->tk_status) { /* RPC connection errors */ case -ENETDOWN: case -ENETUNREACH: @@ -1174,27 +1188,56 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task, nfs4_delete_deviceid(devid->ld, devid->nfs_client, &devid->deviceid); rpc_wake_up(&tbl->slot_tbl_waitq); - fallthrough; + break; default: - if (ff_layout_avoid_mds_available_ds(lseg)) - return -NFS4ERR_RESET_TO_PNFS; -reset: - dprintk("%s Retry through MDS. Error %d\n", __func__, - task->tk_status); - return -NFS4ERR_RESET_TO_MDS; + break; } + + if (ff_layout_avoid_mds_available_ds(lseg)) + return -NFS4ERR_RESET_TO_PNFS; +reset: + dprintk("%s Retry through MDS. Error %d\n", __func__, + task->tk_status); + return -NFS4ERR_RESET_TO_MDS; + +out_retry: task->tk_status = 0; return -EAGAIN; } /* Retry all errors through either pNFS or MDS except for -EJUKEBOX */ static int ff_layout_async_handle_error_v3(struct rpc_task *task, + u32 op_status, struct nfs_client *clp, struct pnfs_layout_segment *lseg, u32 idx) { struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx); + switch (op_status) { + case NFS_OK: + case NFSERR_NXIO: + break; + case NFSERR_PERM: + if (!task->tk_xprt) + break; + xprt_force_disconnect(task->tk_xprt); + goto out_retry; + case NFSERR_ACCES: + case NFSERR_BADHANDLE: + case NFSERR_FBIG: + case NFSERR_IO: + case NFSERR_NOSPC: + case NFSERR_ROFS: + case NFSERR_STALE: + goto out_reset_to_pnfs; + case NFSERR_JUKEBOX: + nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY); + goto out_retry; + default: + break; + } + switch (task->tk_status) { /* File access problems. Don't mark the device as unavailable */ case -EACCES: @@ -1218,6 +1261,7 @@ static int ff_layout_async_handle_error_v3(struct rpc_task *task, nfs4_delete_deviceid(devid->ld, devid->nfs_client, &devid->deviceid); } +out_reset_to_pnfs: /* FIXME: Need to prevent infinite looping here. */ return -NFS4ERR_RESET_TO_PNFS; out_retry: @@ -1228,6 +1272,7 @@ out_retry: } static int ff_layout_async_handle_error(struct rpc_task *task, + u32 op_status, struct nfs4_state *state, struct nfs_client *clp, struct pnfs_layout_segment *lseg, @@ -1246,10 +1291,11 @@ static int ff_layout_async_handle_error(struct rpc_task *task, switch (vers) { case 3: - return ff_layout_async_handle_error_v3(task, clp, lseg, idx); - case 4: - return ff_layout_async_handle_error_v4(task, state, clp, + return ff_layout_async_handle_error_v3(task, op_status, clp, lseg, idx); + case 4: + return ff_layout_async_handle_error_v4(task, op_status, state, + clp, lseg, idx); default: /* should never happen */ WARN_ON_ONCE(1); @@ -1302,6 +1348,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, switch (status) { case NFS4ERR_DELAY: case NFS4ERR_GRACE: + case NFS4ERR_PERM: break; case NFS4ERR_NXIO: ff_layout_mark_ds_unreachable(lseg, idx); @@ -1334,7 +1381,8 @@ static int ff_layout_read_done_cb(struct rpc_task *task, trace_ff_layout_read_error(hdr, task->tk_status); } - err = ff_layout_async_handle_error(task, hdr->args.context->state, + err = ff_layout_async_handle_error(task, hdr->res.op_status, + hdr->args.context->state, hdr->ds_clp, hdr->lseg, hdr->pgio_mirror_idx); @@ -1507,7 +1555,8 @@ static int ff_layout_write_done_cb(struct rpc_task *task, trace_ff_layout_write_error(hdr, task->tk_status); } - err = ff_layout_async_handle_error(task, hdr->args.context->state, + err = ff_layout_async_handle_error(task, hdr->res.op_status, + hdr->args.context->state, hdr->ds_clp, hdr->lseg, hdr->pgio_mirror_idx); @@ -1556,8 +1605,9 @@ static int ff_layout_commit_done_cb(struct rpc_task *task, trace_ff_layout_commit_error(data, task->tk_status); } - err = ff_layout_async_handle_error(task, NULL, data->ds_clp, - data->lseg, data->ds_commit_index); + err = ff_layout_async_handle_error(task, data->res.op_status, + NULL, data->ds_clp, data->lseg, + data->ds_commit_index); trace_nfs4_pnfs_commit_ds(data, err); switch (err) { diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 8ab7868807a7..a2fa6bc4d74e 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -2589,15 +2589,26 @@ EXPORT_SYMBOL_GPL(nfs_net_id); static int nfs_net_init(struct net *net) { struct nfs_net *nn = net_generic(net, nfs_net_id); + int err; nfs_clients_init(net); if (!rpc_proc_register(net, &nn->rpcstats)) { - nfs_clients_exit(net); - return -ENOMEM; + err = -ENOMEM; + goto err_proc_rpc; } - return nfs_fs_proc_net_init(net); + err = nfs_fs_proc_net_init(net); + if (err) + goto err_proc_nfs; + + return 0; + +err_proc_nfs: + rpc_proc_unregister(net, "nfs"); +err_proc_rpc: + nfs_clients_exit(net); + return err; } static void nfs_net_exit(struct net *net) diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 3adb7d0dbec7..1a7ec68bde15 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2059,8 +2059,10 @@ static void nfs_layoutget_begin(struct pnfs_layout_hdr *lo) static void nfs_layoutget_end(struct pnfs_layout_hdr *lo) { if (atomic_dec_and_test(&lo->plh_outstanding) && - test_and_clear_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags)) + test_and_clear_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags)) { + smp_mb__after_atomic(); wake_up_bit(&lo->plh_flags, NFS_LAYOUT_DRAIN); + } } static bool pnfs_is_first_layoutget(struct pnfs_layout_hdr *lo) diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 6a42cc7a845a..657d44afc062 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1621,10 +1621,9 @@ int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info) return -EINVAL; /* count number of SERVER_THREADS values */ - nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) { - if (nla_type(attr) == NFSD_A_SERVER_THREADS) - nrpools++; - } + nlmsg_for_each_attr_type(attr, NFSD_A_SERVER_THREADS, info->nlhdr, + GENL_HDRLEN, rem) + nrpools++; mutex_lock(&nfsd_mutex); @@ -1635,12 +1634,11 @@ int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info) } i = 0; - nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) { - if (nla_type(attr) == NFSD_A_SERVER_THREADS) { - nthreads[i++] = nla_get_u32(attr); - if (i >= nrpools) - break; - } + nlmsg_for_each_attr_type(attr, NFSD_A_SERVER_THREADS, info->nlhdr, + GENL_HDRLEN, rem) { + nthreads[i++] = nla_get_u32(attr); + if (i >= nrpools) + break; } if (info->attrs[NFSD_A_SERVER_GRACETIME] || @@ -1781,14 +1779,12 @@ int nfsd_nl_version_set_doit(struct sk_buff *skb, struct genl_info *info) for (i = 0; i <= NFSD_SUPPORTED_MINOR_VERSION; i++) nfsd_minorversion(nn, i, NFSD_CLEAR); - nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) { + nlmsg_for_each_attr_type(attr, NFSD_A_SERVER_PROTO_VERSION, info->nlhdr, + GENL_HDRLEN, rem) { struct nlattr *tb[NFSD_A_VERSION_MAX + 1]; u32 major, minor = 0; bool enabled; - if (nla_type(attr) != NFSD_A_SERVER_PROTO_VERSION) - continue; - if (nla_parse_nested(tb, NFSD_A_VERSION_MAX, attr, nfsd_version_nl_policy, info->extack) < 0) continue; @@ -1939,14 +1935,12 @@ int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info) * Walk the list of server_socks from userland and move any that match * back to sv_permsocks */ - nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) { + nlmsg_for_each_attr_type(attr, NFSD_A_SERVER_SOCK_ADDR, info->nlhdr, + GENL_HDRLEN, rem) { struct nlattr *tb[NFSD_A_SOCK_MAX + 1]; const char *xcl_name; struct sockaddr *sa; - if (nla_type(attr) != NFSD_A_SERVER_SOCK_ADDR) - continue; - if (nla_parse_nested(tb, NFSD_A_SOCK_MAX, attr, nfsd_sock_nl_policy, info->extack) < 0) continue; @@ -2001,15 +1995,13 @@ int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info) svc_xprt_destroy_all(serv, net); /* walk list of addrs again, open any that still don't exist */ - nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) { + nlmsg_for_each_attr_type(attr, NFSD_A_SERVER_SOCK_ADDR, info->nlhdr, + GENL_HDRLEN, rem) { struct nlattr *tb[NFSD_A_SOCK_MAX + 1]; const char *xcl_name; struct sockaddr *sa; int ret; - if (nla_type(attr) != NFSD_A_SERVER_SOCK_ADDR) - continue; - if (nla_parse_nested(tb, NFSD_A_SOCK_MAX, attr, nfsd_sock_nl_policy, info->extack) < 0) continue; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 27972c0749e7..4be91eb6ea5c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -2182,7 +2182,7 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p, categories |= PAGE_IS_FILE; } - if (is_zero_pfn(pmd_pfn(pmd))) + if (is_huge_zero_pmd(pmd)) categories |= PAGE_IS_PFNZERO; if (pmd_soft_dirty(pmd)) categories |= PAGE_IS_SOFT_DIRTY; diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 45e94e18f4d5..318a8405d475 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -709,6 +709,7 @@ inc_rfc1001_len(void *buf, int count) struct TCP_Server_Info { struct list_head tcp_ses_list; struct list_head smb_ses_list; + struct list_head rlist; /* reconnect list */ spinlock_t srv_lock; /* protect anything here that is not protected */ __u64 conn_id; /* connection identifier (useful for debugging) */ int srv_count; /* reference counter */ diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index c48869c29e15..685c65dcb8c4 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -124,6 +124,14 @@ static void smb2_query_server_interfaces(struct work_struct *work) (SMB_INTERFACE_POLL_INTERVAL * HZ)); } +#define set_need_reco(server) \ +do { \ + spin_lock(&server->srv_lock); \ + if (server->tcpStatus != CifsExiting) \ + server->tcpStatus = CifsNeedReconnect; \ + spin_unlock(&server->srv_lock); \ +} while (0) + /* * Update the tcpStatus for the server. * This is used to signal the cifsd thread to call cifs_reconnect @@ -137,39 +145,45 @@ void cifs_signal_cifsd_for_reconnect(struct TCP_Server_Info *server, bool all_channels) { - struct TCP_Server_Info *pserver; + struct TCP_Server_Info *nserver; struct cifs_ses *ses; + LIST_HEAD(reco); int i; - /* If server is a channel, select the primary channel */ - pserver = SERVER_IS_CHAN(server) ? server->primary_server : server; - /* if we need to signal just this channel */ if (!all_channels) { - spin_lock(&server->srv_lock); - if (server->tcpStatus != CifsExiting) - server->tcpStatus = CifsNeedReconnect; - spin_unlock(&server->srv_lock); + set_need_reco(server); return; } - spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { - if (cifs_ses_exiting(ses)) - continue; - spin_lock(&ses->chan_lock); - for (i = 0; i < ses->chan_count; i++) { - if (!ses->chans[i].server) + if (SERVER_IS_CHAN(server)) + server = server->primary_server; + scoped_guard(spinlock, &cifs_tcp_ses_lock) { + set_need_reco(server); + list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + spin_lock(&ses->ses_lock); + if (ses->ses_status == SES_EXITING) { + spin_unlock(&ses->ses_lock); continue; - - spin_lock(&ses->chans[i].server->srv_lock); - if (ses->chans[i].server->tcpStatus != CifsExiting) - ses->chans[i].server->tcpStatus = CifsNeedReconnect; - spin_unlock(&ses->chans[i].server->srv_lock); + } + spin_lock(&ses->chan_lock); + for (i = 1; i < ses->chan_count; i++) { + nserver = ses->chans[i].server; + if (!nserver) + continue; + nserver->srv_count++; + list_add(&nserver->rlist, &reco); + } + spin_unlock(&ses->chan_lock); + spin_unlock(&ses->ses_lock); } - spin_unlock(&ses->chan_lock); } - spin_unlock(&cifs_tcp_ses_lock); + + list_for_each_entry_safe(server, nserver, &reco, rlist) { + list_del_init(&server->rlist); + set_need_reco(server); + cifs_put_tcp_session(server, 0); + } } /* diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index 511611206dab..1c40e42e4d89 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -875,15 +875,8 @@ globalroot: abs_path += sizeof("\\DosDevices\\")-1; else if (strstarts(abs_path, "\\GLOBAL??\\")) abs_path += sizeof("\\GLOBAL??\\")-1; - else { - /* Unhandled absolute symlink, points outside of DOS/Win32 */ - cifs_dbg(VFS, - "absolute symlink '%s' cannot be converted from NT format " - "because points to unknown target\n", - smb_target); - rc = -EIO; - goto out; - } + else + goto out_unhandled_target; /* Sometimes path separator after \?? is double backslash */ if (abs_path[0] == '\\') @@ -910,13 +903,7 @@ globalroot: abs_path++; abs_path[0] = drive_letter; } else { - /* Unhandled absolute symlink. Report an error. */ - cifs_dbg(VFS, - "absolute symlink '%s' cannot be converted from NT format " - "because points to unknown target\n", - smb_target); - rc = -EIO; - goto out; + goto out_unhandled_target; } abs_path_len = strlen(abs_path)+1; @@ -966,6 +953,7 @@ globalroot: * These paths have same format as Linux symlinks, so no * conversion is needed. */ +out_unhandled_target: linux_target = smb_target; smb_target = NULL; } diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index cbc85bca006f..754e94a0e07f 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -907,8 +907,10 @@ wait_send_queue: .local_dma_lkey = sc->ib.pd->local_dma_lkey, .direction = DMA_TO_DEVICE, }; + size_t payload_len = umin(*_remaining_data_length, + sp->max_send_size - sizeof(*packet)); - rc = smb_extract_iter_to_rdma(iter, *_remaining_data_length, + rc = smb_extract_iter_to_rdma(iter, payload_len, &extract); if (rc < 0) goto err_dma; @@ -1013,6 +1015,27 @@ static int smbd_post_send_empty(struct smbd_connection *info) return smbd_post_send_iter(info, NULL, &remaining_data_length); } +static int smbd_post_send_full_iter(struct smbd_connection *info, + struct iov_iter *iter, + int *_remaining_data_length) +{ + int rc = 0; + + /* + * smbd_post_send_iter() respects the + * negotiated max_send_size, so we need to + * loop until the full iter is posted + */ + + while (iov_iter_count(iter) > 0) { + rc = smbd_post_send_iter(info, iter, _remaining_data_length); + if (rc < 0) + break; + } + + return rc; +} + /* * Post a receive request to the transport * The remote peer can only send data when a receive request is posted @@ -1452,6 +1475,9 @@ static int allocate_caches_and_workqueue(struct smbd_connection *info) char name[MAX_NAME_LEN]; int rc; + if (WARN_ON_ONCE(sp->max_recv_size < sizeof(struct smbdirect_data_transfer))) + return -ENOMEM; + scnprintf(name, MAX_NAME_LEN, "smbd_request_%p", info); info->request_cache = kmem_cache_create( @@ -1469,12 +1495,17 @@ static int allocate_caches_and_workqueue(struct smbd_connection *info) goto out1; scnprintf(name, MAX_NAME_LEN, "smbd_response_%p", info); + + struct kmem_cache_args response_args = { + .align = __alignof__(struct smbd_response), + .useroffset = (offsetof(struct smbd_response, packet) + + sizeof(struct smbdirect_data_transfer)), + .usersize = sp->max_recv_size - sizeof(struct smbdirect_data_transfer), + }; info->response_cache = - kmem_cache_create( - name, - sizeof(struct smbd_response) + - sp->max_recv_size, - 0, SLAB_HWCACHE_ALIGN, NULL); + kmem_cache_create(name, + sizeof(struct smbd_response) + sp->max_recv_size, + &response_args, SLAB_HWCACHE_ALIGN); if (!info->response_cache) goto out2; @@ -1747,35 +1778,39 @@ try_again: } /* - * Receive data from receive reassembly queue + * Receive data from the transport's receive reassembly queue * All the incoming data packets are placed in reassembly queue - * buf: the buffer to read data into + * iter: the buffer to read data into * size: the length of data to read * return value: actual data read - * Note: this implementation copies the data from reassebmly queue to receive + * + * Note: this implementation copies the data from reassembly queue to receive * buffers used by upper layer. This is not the optimal code path. A better way * to do it is to not have upper layer allocate its receive buffers but rather * borrow the buffer from reassembly queue, and return it after data is * consumed. But this will require more changes to upper layer code, and also * need to consider packet boundaries while they still being reassembled. */ -static int smbd_recv_buf(struct smbd_connection *info, char *buf, - unsigned int size) +int smbd_recv(struct smbd_connection *info, struct msghdr *msg) { struct smbdirect_socket *sc = &info->socket; struct smbd_response *response; struct smbdirect_data_transfer *data_transfer; + size_t size = iov_iter_count(&msg->msg_iter); int to_copy, to_read, data_read, offset; u32 data_length, remaining_data_length, data_offset; int rc; + if (WARN_ON_ONCE(iov_iter_rw(&msg->msg_iter) == WRITE)) + return -EINVAL; /* It's a bug in upper layer to get there */ + again: /* * No need to hold the reassembly queue lock all the time as we are * the only one reading from the front of the queue. The transport * may add more entries to the back of the queue at the same time */ - log_read(INFO, "size=%d info->reassembly_data_length=%d\n", size, + log_read(INFO, "size=%zd info->reassembly_data_length=%d\n", size, info->reassembly_data_length); if (info->reassembly_data_length >= size) { int queue_length; @@ -1813,7 +1848,10 @@ again: if (response->first_segment && size == 4) { unsigned int rfc1002_len = data_length + remaining_data_length; - *((__be32 *)buf) = cpu_to_be32(rfc1002_len); + __be32 rfc1002_hdr = cpu_to_be32(rfc1002_len); + if (copy_to_iter(&rfc1002_hdr, sizeof(rfc1002_hdr), + &msg->msg_iter) != sizeof(rfc1002_hdr)) + return -EFAULT; data_read = 4; response->first_segment = false; log_read(INFO, "returning rfc1002 length %d\n", @@ -1822,10 +1860,9 @@ again: } to_copy = min_t(int, data_length - offset, to_read); - memcpy( - buf + data_read, - (char *)data_transfer + data_offset + offset, - to_copy); + if (copy_to_iter((char *)data_transfer + data_offset + offset, + to_copy, &msg->msg_iter) != to_copy) + return -EFAULT; /* move on to the next buffer? */ if (to_copy == data_length - offset) { @@ -1891,90 +1928,6 @@ read_rfc1002_done: } /* - * Receive a page from receive reassembly queue - * page: the page to read data into - * to_read: the length of data to read - * return value: actual data read - */ -static int smbd_recv_page(struct smbd_connection *info, - struct page *page, unsigned int page_offset, - unsigned int to_read) -{ - struct smbdirect_socket *sc = &info->socket; - int ret; - char *to_address; - void *page_address; - - /* make sure we have the page ready for read */ - ret = wait_event_interruptible( - info->wait_reassembly_queue, - info->reassembly_data_length >= to_read || - sc->status != SMBDIRECT_SOCKET_CONNECTED); - if (ret) - return ret; - - /* now we can read from reassembly queue and not sleep */ - page_address = kmap_atomic(page); - to_address = (char *) page_address + page_offset; - - log_read(INFO, "reading from page=%p address=%p to_read=%d\n", - page, to_address, to_read); - - ret = smbd_recv_buf(info, to_address, to_read); - kunmap_atomic(page_address); - - return ret; -} - -/* - * Receive data from transport - * msg: a msghdr point to the buffer, can be ITER_KVEC or ITER_BVEC - * return: total bytes read, or 0. SMB Direct will not do partial read. - */ -int smbd_recv(struct smbd_connection *info, struct msghdr *msg) -{ - char *buf; - struct page *page; - unsigned int to_read, page_offset; - int rc; - - if (iov_iter_rw(&msg->msg_iter) == WRITE) { - /* It's a bug in upper layer to get there */ - cifs_dbg(VFS, "Invalid msg iter dir %u\n", - iov_iter_rw(&msg->msg_iter)); - rc = -EINVAL; - goto out; - } - - switch (iov_iter_type(&msg->msg_iter)) { - case ITER_KVEC: - buf = msg->msg_iter.kvec->iov_base; - to_read = msg->msg_iter.kvec->iov_len; - rc = smbd_recv_buf(info, buf, to_read); - break; - - case ITER_BVEC: - page = msg->msg_iter.bvec->bv_page; - page_offset = msg->msg_iter.bvec->bv_offset; - to_read = msg->msg_iter.bvec->bv_len; - rc = smbd_recv_page(info, page, page_offset, to_read); - break; - - default: - /* It's a bug in upper layer to get there */ - cifs_dbg(VFS, "Invalid msg type %d\n", - iov_iter_type(&msg->msg_iter)); - rc = -EINVAL; - } - -out: - /* SMBDirect will read it all or nothing */ - if (rc > 0) - msg->msg_iter.count = 0; - return rc; -} - -/* * Send data to transport * Each rqst is transported as a SMBDirect payload * rqst: the data to write @@ -2032,14 +1985,14 @@ int smbd_send(struct TCP_Server_Info *server, klen += rqst->rq_iov[i].iov_len; iov_iter_kvec(&iter, ITER_SOURCE, rqst->rq_iov, rqst->rq_nvec, klen); - rc = smbd_post_send_iter(info, &iter, &remaining_data_length); + rc = smbd_post_send_full_iter(info, &iter, &remaining_data_length); if (rc < 0) break; if (iov_iter_count(&rqst->rq_iter) > 0) { /* And then the data pages if there are any */ - rc = smbd_post_send_iter(info, &rqst->rq_iter, - &remaining_data_length); + rc = smbd_post_send_full_iter(info, &rqst->rq_iter, + &remaining_data_length); if (rc < 0) break; } diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h index 52bcb55d9952..93e5b2bb9f28 100644 --- a/fs/smb/client/trace.h +++ b/fs/smb/client/trace.h @@ -140,7 +140,7 @@ DECLARE_EVENT_CLASS(smb3_rw_err_class, __entry->len = len; __entry->rc = rc; ), - TP_printk("\tR=%08x[%x] xid=%u sid=0x%llx tid=0x%x fid=0x%llx offset=0x%llx len=0x%x rc=%d", + TP_printk("R=%08x[%x] xid=%u sid=0x%llx tid=0x%x fid=0x%llx offset=0x%llx len=0x%x rc=%d", __entry->rreq_debug_id, __entry->rreq_debug_index, __entry->xid, __entry->sesid, __entry->tid, __entry->fid, __entry->offset, __entry->len, __entry->rc) @@ -190,7 +190,7 @@ DECLARE_EVENT_CLASS(smb3_other_err_class, __entry->len = len; __entry->rc = rc; ), - TP_printk("\txid=%u sid=0x%llx tid=0x%x fid=0x%llx offset=0x%llx len=0x%x rc=%d", + TP_printk("xid=%u sid=0x%llx tid=0x%x fid=0x%llx offset=0x%llx len=0x%x rc=%d", __entry->xid, __entry->sesid, __entry->tid, __entry->fid, __entry->offset, __entry->len, __entry->rc) ) @@ -247,7 +247,7 @@ DECLARE_EVENT_CLASS(smb3_copy_range_err_class, __entry->len = len; __entry->rc = rc; ), - TP_printk("\txid=%u sid=0x%llx tid=0x%x source fid=0x%llx source offset=0x%llx target fid=0x%llx target offset=0x%llx len=0x%x rc=%d", + TP_printk("xid=%u sid=0x%llx tid=0x%x source fid=0x%llx source offset=0x%llx target fid=0x%llx target offset=0x%llx len=0x%x rc=%d", __entry->xid, __entry->sesid, __entry->tid, __entry->target_fid, __entry->src_offset, __entry->target_fid, __entry->target_offset, __entry->len, __entry->rc) ) @@ -298,7 +298,7 @@ DECLARE_EVENT_CLASS(smb3_copy_range_done_class, __entry->target_offset = target_offset; __entry->len = len; ), - TP_printk("\txid=%u sid=0x%llx tid=0x%x source fid=0x%llx source offset=0x%llx target fid=0x%llx target offset=0x%llx len=0x%x", + TP_printk("xid=%u sid=0x%llx tid=0x%x source fid=0x%llx source offset=0x%llx target fid=0x%llx target offset=0x%llx len=0x%x", __entry->xid, __entry->sesid, __entry->tid, __entry->target_fid, __entry->src_offset, __entry->target_fid, __entry->target_offset, __entry->len) ) @@ -482,7 +482,7 @@ DECLARE_EVENT_CLASS(smb3_fd_class, __entry->tid = tid; __entry->sesid = sesid; ), - TP_printk("\txid=%u sid=0x%llx tid=0x%x fid=0x%llx", + TP_printk("xid=%u sid=0x%llx tid=0x%x fid=0x%llx", __entry->xid, __entry->sesid, __entry->tid, __entry->fid) ) @@ -521,7 +521,7 @@ DECLARE_EVENT_CLASS(smb3_fd_err_class, __entry->sesid = sesid; __entry->rc = rc; ), - TP_printk("\txid=%u sid=0x%llx tid=0x%x fid=0x%llx rc=%d", + TP_printk("xid=%u sid=0x%llx tid=0x%x fid=0x%llx rc=%d", __entry->xid, __entry->sesid, __entry->tid, __entry->fid, __entry->rc) ) @@ -794,7 +794,7 @@ DECLARE_EVENT_CLASS(smb3_cmd_err_class, __entry->status = status; __entry->rc = rc; ), - TP_printk("\tsid=0x%llx tid=0x%x cmd=%u mid=%llu status=0x%x rc=%d", + TP_printk("sid=0x%llx tid=0x%x cmd=%u mid=%llu status=0x%x rc=%d", __entry->sesid, __entry->tid, __entry->cmd, __entry->mid, __entry->status, __entry->rc) ) @@ -829,7 +829,7 @@ DECLARE_EVENT_CLASS(smb3_cmd_done_class, __entry->cmd = cmd; __entry->mid = mid; ), - TP_printk("\tsid=0x%llx tid=0x%x cmd=%u mid=%llu", + TP_printk("sid=0x%llx tid=0x%x cmd=%u mid=%llu", __entry->sesid, __entry->tid, __entry->cmd, __entry->mid) ) @@ -867,7 +867,7 @@ DECLARE_EVENT_CLASS(smb3_mid_class, __entry->when_sent = when_sent; __entry->when_received = when_received; ), - TP_printk("\tcmd=%u mid=%llu pid=%u, when_sent=%lu when_rcv=%lu", + TP_printk("cmd=%u mid=%llu pid=%u, when_sent=%lu when_rcv=%lu", __entry->cmd, __entry->mid, __entry->pid, __entry->when_sent, __entry->when_received) ) @@ -898,7 +898,7 @@ DECLARE_EVENT_CLASS(smb3_exit_err_class, __assign_str(func_name); __entry->rc = rc; ), - TP_printk("\t%s: xid=%u rc=%d", + TP_printk("%s: xid=%u rc=%d", __get_str(func_name), __entry->xid, __entry->rc) ) @@ -924,7 +924,7 @@ DECLARE_EVENT_CLASS(smb3_sync_err_class, __entry->ino = ino; __entry->rc = rc; ), - TP_printk("\tino=%lu rc=%d", + TP_printk("ino=%lu rc=%d", __entry->ino, __entry->rc) ) @@ -950,7 +950,7 @@ DECLARE_EVENT_CLASS(smb3_enter_exit_class, __entry->xid = xid; __assign_str(func_name); ), - TP_printk("\t%s: xid=%u", + TP_printk("%s: xid=%u", __get_str(func_name), __entry->xid) ) diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 7839efe050bf..000cc7f4a3ce 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -3444,16 +3444,41 @@ xfs_alloc_read_agf( set_bit(XFS_AGSTATE_AGF_INIT, &pag->pag_opstate); } + #ifdef DEBUG - else if (!xfs_is_shutdown(mp)) { - ASSERT(pag->pagf_freeblks == be32_to_cpu(agf->agf_freeblks)); - ASSERT(pag->pagf_btreeblks == be32_to_cpu(agf->agf_btreeblks)); - ASSERT(pag->pagf_flcount == be32_to_cpu(agf->agf_flcount)); - ASSERT(pag->pagf_longest == be32_to_cpu(agf->agf_longest)); - ASSERT(pag->pagf_bno_level == be32_to_cpu(agf->agf_bno_level)); - ASSERT(pag->pagf_cnt_level == be32_to_cpu(agf->agf_cnt_level)); + /* + * It's possible for the AGF to be out of sync if the block device is + * silently dropping writes. This can happen in fstests with dmflakey + * enabled, which allows the buffer to be cleaned and reclaimed by + * memory pressure and then re-read from disk here. We will get a + * stale version of the AGF from disk, and nothing good can happen from + * here. Hence if we detect this situation, immediately shut down the + * filesystem. + * + * This can also happen if we are already in the middle of a forced + * shutdown, so don't bother checking if we are already shut down. + */ + if (!xfs_is_shutdown(pag_mount(pag))) { + bool ok = true; + + ok &= pag->pagf_freeblks == be32_to_cpu(agf->agf_freeblks); + ok &= pag->pagf_freeblks == be32_to_cpu(agf->agf_freeblks); + ok &= pag->pagf_btreeblks == be32_to_cpu(agf->agf_btreeblks); + ok &= pag->pagf_flcount == be32_to_cpu(agf->agf_flcount); + ok &= pag->pagf_longest == be32_to_cpu(agf->agf_longest); + ok &= pag->pagf_bno_level == be32_to_cpu(agf->agf_bno_level); + ok &= pag->pagf_cnt_level == be32_to_cpu(agf->agf_cnt_level); + + if (XFS_IS_CORRUPT(pag_mount(pag), !ok)) { + xfs_ag_mark_sick(pag, XFS_SICK_AG_AGF); + xfs_trans_brelse(tp, agfbp); + xfs_force_shutdown(pag_mount(pag), + SHUTDOWN_CORRUPT_ONDISK); + return -EFSCORRUPTED; + } } -#endif +#endif /* DEBUG */ + if (agfbpp) *agfbpp = agfbp; else diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 0c47b5c6ca7d..750111634d9f 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -2801,12 +2801,35 @@ xfs_ialloc_read_agi( set_bit(XFS_AGSTATE_AGI_INIT, &pag->pag_opstate); } +#ifdef DEBUG /* - * It's possible for these to be out of sync if - * we are in the middle of a forced shutdown. + * It's possible for the AGF to be out of sync if the block device is + * silently dropping writes. This can happen in fstests with dmflakey + * enabled, which allows the buffer to be cleaned and reclaimed by + * memory pressure and then re-read from disk here. We will get a + * stale version of the AGF from disk, and nothing good can happen from + * here. Hence if we detect this situation, immediately shut down the + * filesystem. + * + * This can also happen if we are already in the middle of a forced + * shutdown, so don't bother checking if we are already shut down. */ - ASSERT(pag->pagi_freecount == be32_to_cpu(agi->agi_freecount) || - xfs_is_shutdown(pag_mount(pag))); + if (!xfs_is_shutdown(pag_mount(pag))) { + bool ok = true; + + ok &= pag->pagi_freecount == be32_to_cpu(agi->agi_freecount); + ok &= pag->pagi_count == be32_to_cpu(agi->agi_count); + + if (XFS_IS_CORRUPT(pag_mount(pag), !ok)) { + xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI); + xfs_trans_brelse(tp, agibp); + xfs_force_shutdown(pag_mount(pag), + SHUTDOWN_CORRUPT_ONDISK); + return -EFSCORRUPTED; + } + } +#endif /* DEBUG */ + if (agibpp) *agibpp = agibp; else diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 8af83bd161f9..ba5bd6031ece 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -2082,44 +2082,6 @@ xfs_buf_delwri_submit( return error; } -/* - * Push a single buffer on a delwri queue. - * - * The purpose of this function is to submit a single buffer of a delwri queue - * and return with the buffer still on the original queue. - * - * The buffer locking and queue management logic between _delwri_pushbuf() and - * _delwri_queue() guarantee that the buffer cannot be queued to another list - * before returning. - */ -int -xfs_buf_delwri_pushbuf( - struct xfs_buf *bp, - struct list_head *buffer_list) -{ - int error; - - ASSERT(bp->b_flags & _XBF_DELWRI_Q); - - trace_xfs_buf_delwri_pushbuf(bp, _RET_IP_); - - xfs_buf_lock(bp); - bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC); - bp->b_flags |= XBF_WRITE; - xfs_buf_submit(bp); - - /* - * The buffer is now locked, under I/O but still on the original delwri - * queue. Wait for I/O completion, restore the DELWRI_Q flag and - * return with the buffer unlocked and still on the original queue. - */ - error = xfs_buf_iowait(bp); - bp->b_flags |= _XBF_DELWRI_Q; - xfs_buf_unlock(bp); - - return error; -} - void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref) { /* diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 9d2ab567cf81..15fc56948346 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -326,7 +326,6 @@ extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *); void xfs_buf_delwri_queue_here(struct xfs_buf *bp, struct list_head *bl); extern int xfs_buf_delwri_submit(struct list_head *); extern int xfs_buf_delwri_submit_nowait(struct list_head *); -extern int xfs_buf_delwri_pushbuf(struct xfs_buf *, struct list_head *); static inline xfs_daddr_t xfs_buf_daddr(struct xfs_buf *bp) { diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 90139e0f3271..7fc54725c5f6 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -32,6 +32,61 @@ static inline struct xfs_buf_log_item *BUF_ITEM(struct xfs_log_item *lip) return container_of(lip, struct xfs_buf_log_item, bli_item); } +static void +xfs_buf_item_get_format( + struct xfs_buf_log_item *bip, + int count) +{ + ASSERT(bip->bli_formats == NULL); + bip->bli_format_count = count; + + if (count == 1) { + bip->bli_formats = &bip->__bli_format; + return; + } + + bip->bli_formats = kzalloc(count * sizeof(struct xfs_buf_log_format), + GFP_KERNEL | __GFP_NOFAIL); +} + +static void +xfs_buf_item_free_format( + struct xfs_buf_log_item *bip) +{ + if (bip->bli_formats != &bip->__bli_format) { + kfree(bip->bli_formats); + bip->bli_formats = NULL; + } +} + +static void +xfs_buf_item_free( + struct xfs_buf_log_item *bip) +{ + xfs_buf_item_free_format(bip); + kvfree(bip->bli_item.li_lv_shadow); + kmem_cache_free(xfs_buf_item_cache, bip); +} + +/* + * xfs_buf_item_relse() is called when the buf log item is no longer needed. + */ +static void +xfs_buf_item_relse( + struct xfs_buf_log_item *bip) +{ + struct xfs_buf *bp = bip->bli_buf; + + trace_xfs_buf_item_relse(bp, _RET_IP_); + + ASSERT(!test_bit(XFS_LI_IN_AIL, &bip->bli_item.li_flags)); + ASSERT(atomic_read(&bip->bli_refcount) == 0); + + bp->b_log_item = NULL; + xfs_buf_rele(bp); + xfs_buf_item_free(bip); +} + /* Is this log iovec plausibly large enough to contain the buffer log format? */ bool xfs_buf_log_check_iovec( @@ -390,6 +445,42 @@ xfs_buf_item_pin( } /* + * For a stale BLI, process all the necessary completions that must be + * performed when the final BLI reference goes away. The buffer will be + * referenced and locked here - we return to the caller with the buffer still + * referenced and locked for them to finalise processing of the buffer. + */ +static void +xfs_buf_item_finish_stale( + struct xfs_buf_log_item *bip) +{ + struct xfs_buf *bp = bip->bli_buf; + struct xfs_log_item *lip = &bip->bli_item; + + ASSERT(bip->bli_flags & XFS_BLI_STALE); + ASSERT(xfs_buf_islocked(bp)); + ASSERT(bp->b_flags & XBF_STALE); + ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL); + ASSERT(list_empty(&lip->li_trans)); + ASSERT(!bp->b_transp); + + if (bip->bli_flags & XFS_BLI_STALE_INODE) { + xfs_buf_item_done(bp); + xfs_buf_inode_iodone(bp); + ASSERT(list_empty(&bp->b_li_list)); + return; + } + + /* + * We may or may not be on the AIL here, xfs_trans_ail_delete() will do + * the right thing regardless of the situation in which we are called. + */ + xfs_trans_ail_delete(lip, SHUTDOWN_LOG_IO_ERROR); + xfs_buf_item_relse(bip); + ASSERT(bp->b_log_item == NULL); +} + +/* * This is called to unpin the buffer associated with the buf log item which was * previously pinned with a call to xfs_buf_item_pin(). We enter this function * with a buffer pin count, a buffer reference and a BLI reference. @@ -438,13 +529,6 @@ xfs_buf_item_unpin( } if (stale) { - ASSERT(bip->bli_flags & XFS_BLI_STALE); - ASSERT(xfs_buf_islocked(bp)); - ASSERT(bp->b_flags & XBF_STALE); - ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL); - ASSERT(list_empty(&lip->li_trans)); - ASSERT(!bp->b_transp); - trace_xfs_buf_item_unpin_stale(bip); /* @@ -455,22 +539,7 @@ xfs_buf_item_unpin( * processing is complete. */ xfs_buf_rele(bp); - - /* - * If we get called here because of an IO error, we may or may - * not have the item on the AIL. xfs_trans_ail_delete() will - * take care of that situation. xfs_trans_ail_delete() drops - * the AIL lock. - */ - if (bip->bli_flags & XFS_BLI_STALE_INODE) { - xfs_buf_item_done(bp); - xfs_buf_inode_iodone(bp); - ASSERT(list_empty(&bp->b_li_list)); - } else { - xfs_trans_ail_delete(lip, SHUTDOWN_LOG_IO_ERROR); - xfs_buf_item_relse(bp); - ASSERT(bp->b_log_item == NULL); - } + xfs_buf_item_finish_stale(bip); xfs_buf_relse(bp); return; } @@ -543,43 +612,42 @@ xfs_buf_item_push( * Drop the buffer log item refcount and take appropriate action. This helper * determines whether the bli must be freed or not, since a decrement to zero * does not necessarily mean the bli is unused. - * - * Return true if the bli is freed, false otherwise. */ -bool +void xfs_buf_item_put( struct xfs_buf_log_item *bip) { - struct xfs_log_item *lip = &bip->bli_item; - bool aborted; - bool dirty; + + ASSERT(xfs_buf_islocked(bip->bli_buf)); /* drop the bli ref and return if it wasn't the last one */ if (!atomic_dec_and_test(&bip->bli_refcount)) - return false; + return; - /* - * We dropped the last ref and must free the item if clean or aborted. - * If the bli is dirty and non-aborted, the buffer was clean in the - * transaction but still awaiting writeback from previous changes. In - * that case, the bli is freed on buffer writeback completion. - */ - aborted = test_bit(XFS_LI_ABORTED, &lip->li_flags) || - xlog_is_shutdown(lip->li_log); - dirty = bip->bli_flags & XFS_BLI_DIRTY; - if (dirty && !aborted) - return false; + /* If the BLI is in the AIL, then it is still dirty and in use */ + if (test_bit(XFS_LI_IN_AIL, &bip->bli_item.li_flags)) { + ASSERT(bip->bli_flags & XFS_BLI_DIRTY); + return; + } /* - * The bli is aborted or clean. An aborted item may be in the AIL - * regardless of dirty state. For example, consider an aborted - * transaction that invalidated a dirty bli and cleared the dirty - * state. + * In shutdown conditions, we can be asked to free a dirty BLI that + * isn't in the AIL. This can occur due to a checkpoint aborting a BLI + * instead of inserting it into the AIL at checkpoint IO completion. If + * there's another bli reference (e.g. a btree cursor holds a clean + * reference) and it is released via xfs_trans_brelse(), we can get here + * with that aborted, dirty BLI. In this case, it is safe to free the + * dirty BLI immediately, as it is not in the AIL and there are no + * other references to it. + * + * We should never get here with a stale BLI via that path as + * xfs_trans_brelse() specifically holds onto stale buffers rather than + * releasing them. */ - if (aborted) - xfs_trans_ail_delete(lip, 0); - xfs_buf_item_relse(bip->bli_buf); - return true; + ASSERT(!(bip->bli_flags & XFS_BLI_DIRTY) || + test_bit(XFS_LI_ABORTED, &bip->bli_item.li_flags)); + ASSERT(!(bip->bli_flags & XFS_BLI_STALE)); + xfs_buf_item_relse(bip); } /* @@ -600,6 +668,15 @@ xfs_buf_item_put( * if necessary but do not unlock the buffer. This is for support of * xfs_trans_bhold(). Make sure the XFS_BLI_HOLD field is cleared if we don't * free the item. + * + * If the XFS_BLI_STALE flag is set, the last reference to the BLI *must* + * perform a completion abort of any objects attached to the buffer for IO + * tracking purposes. This generally only happens in shutdown situations, + * normally xfs_buf_item_unpin() will drop the last BLI reference and perform + * completion processing. However, because transaction completion can race with + * checkpoint completion during a shutdown, this release context may end up + * being the last active reference to the BLI and so needs to perform this + * cleanup. */ STATIC void xfs_buf_item_release( @@ -607,18 +684,19 @@ xfs_buf_item_release( { struct xfs_buf_log_item *bip = BUF_ITEM(lip); struct xfs_buf *bp = bip->bli_buf; - bool released; bool hold = bip->bli_flags & XFS_BLI_HOLD; bool stale = bip->bli_flags & XFS_BLI_STALE; -#if defined(DEBUG) || defined(XFS_WARN) - bool ordered = bip->bli_flags & XFS_BLI_ORDERED; - bool dirty = bip->bli_flags & XFS_BLI_DIRTY; bool aborted = test_bit(XFS_LI_ABORTED, &lip->li_flags); + bool dirty = bip->bli_flags & XFS_BLI_DIRTY; +#if defined(DEBUG) || defined(XFS_WARN) + bool ordered = bip->bli_flags & XFS_BLI_ORDERED; #endif trace_xfs_buf_item_release(bip); + ASSERT(xfs_buf_islocked(bp)); + /* * The bli dirty state should match whether the blf has logged segments * except for ordered buffers, where only the bli should be dirty. @@ -634,16 +712,56 @@ xfs_buf_item_release( bp->b_transp = NULL; bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD | XFS_BLI_ORDERED); + /* If there are other references, then we have nothing to do. */ + if (!atomic_dec_and_test(&bip->bli_refcount)) + goto out_release; + + /* + * Stale buffer completion frees the BLI, unlocks and releases the + * buffer. Neither the BLI or buffer are safe to reference after this + * call, so there's nothing more we need to do here. + * + * If we get here with a stale buffer and references to the BLI remain, + * we must not unlock the buffer as the last BLI reference owns lock + * context, not us. + */ + if (stale) { + xfs_buf_item_finish_stale(bip); + xfs_buf_relse(bp); + ASSERT(!hold); + return; + } + /* - * Unref the item and unlock the buffer unless held or stale. Stale - * buffers remain locked until final unpin unless the bli is freed by - * the unref call. The latter implies shutdown because buffer - * invalidation dirties the bli and transaction. + * Dirty or clean, aborted items are done and need to be removed from + * the AIL and released. This frees the BLI, but leaves the buffer + * locked and referenced. */ - released = xfs_buf_item_put(bip); - if (hold || (stale && !released)) + if (aborted || xlog_is_shutdown(lip->li_log)) { + ASSERT(list_empty(&bip->bli_buf->b_li_list)); + xfs_buf_item_done(bp); + goto out_release; + } + + /* + * Clean, unreferenced BLIs can be immediately freed, leaving the buffer + * locked and referenced. + * + * Dirty, unreferenced BLIs *must* be in the AIL awaiting writeback. + */ + if (!dirty) + xfs_buf_item_relse(bip); + else + ASSERT(test_bit(XFS_LI_IN_AIL, &lip->li_flags)); + + /* Not safe to reference the BLI from here */ +out_release: + /* + * If we get here with a stale buffer, we must not unlock the + * buffer as the last BLI reference owns lock context, not us. + */ + if (stale || hold) return; - ASSERT(!stale || aborted); xfs_buf_relse(bp); } @@ -729,33 +847,6 @@ static const struct xfs_item_ops xfs_buf_item_ops = { .iop_push = xfs_buf_item_push, }; -STATIC void -xfs_buf_item_get_format( - struct xfs_buf_log_item *bip, - int count) -{ - ASSERT(bip->bli_formats == NULL); - bip->bli_format_count = count; - - if (count == 1) { - bip->bli_formats = &bip->__bli_format; - return; - } - - bip->bli_formats = kzalloc(count * sizeof(struct xfs_buf_log_format), - GFP_KERNEL | __GFP_NOFAIL); -} - -STATIC void -xfs_buf_item_free_format( - struct xfs_buf_log_item *bip) -{ - if (bip->bli_formats != &bip->__bli_format) { - kfree(bip->bli_formats); - bip->bli_formats = NULL; - } -} - /* * Allocate a new buf log item to go with the given buffer. * Set the buffer's b_log_item field to point to the new @@ -976,34 +1067,6 @@ xfs_buf_item_dirty_format( return false; } -STATIC void -xfs_buf_item_free( - struct xfs_buf_log_item *bip) -{ - xfs_buf_item_free_format(bip); - kvfree(bip->bli_item.li_lv_shadow); - kmem_cache_free(xfs_buf_item_cache, bip); -} - -/* - * xfs_buf_item_relse() is called when the buf log item is no longer needed. - */ -void -xfs_buf_item_relse( - struct xfs_buf *bp) -{ - struct xfs_buf_log_item *bip = bp->b_log_item; - - trace_xfs_buf_item_relse(bp, _RET_IP_); - ASSERT(!test_bit(XFS_LI_IN_AIL, &bip->bli_item.li_flags)); - - if (atomic_read(&bip->bli_refcount)) - return; - bp->b_log_item = NULL; - xfs_buf_rele(bp); - xfs_buf_item_free(bip); -} - void xfs_buf_item_done( struct xfs_buf *bp) @@ -1023,5 +1086,5 @@ xfs_buf_item_done( xfs_trans_ail_delete(&bp->b_log_item->bli_item, (bp->b_flags & _XBF_LOGRECOVERY) ? 0 : SHUTDOWN_CORRUPT_INCORE); - xfs_buf_item_relse(bp); + xfs_buf_item_relse(bp->b_log_item); } diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h index e10e324cd245..416890b84f8c 100644 --- a/fs/xfs/xfs_buf_item.h +++ b/fs/xfs/xfs_buf_item.h @@ -49,8 +49,7 @@ struct xfs_buf_log_item { int xfs_buf_item_init(struct xfs_buf *, struct xfs_mount *); void xfs_buf_item_done(struct xfs_buf *bp); -void xfs_buf_item_relse(struct xfs_buf *); -bool xfs_buf_item_put(struct xfs_buf_log_item *); +void xfs_buf_item_put(struct xfs_buf_log_item *bip); void xfs_buf_item_log(struct xfs_buf_log_item *, uint, uint); bool xfs_buf_item_dirty_format(struct xfs_buf_log_item *); void xfs_buf_inode_iodone(struct xfs_buf *); diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index b4e32f0860b7..0bd8022e47b4 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -1398,11 +1398,9 @@ xfs_qm_dqflush( ASSERT(XFS_DQ_IS_LOCKED(dqp)); ASSERT(!completion_done(&dqp->q_flush)); + ASSERT(atomic_read(&dqp->q_pincount) == 0); trace_xfs_dqflush(dqp); - - xfs_qm_dqunpin_wait(dqp); - fa = xfs_qm_dqflush_check(dqp); if (fa) { xfs_alert(mp, "corrupt dquot ID 0x%x in memory at %pS", diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 48254a72071b..0b41b18debf3 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1335,9 +1335,10 @@ xfs_falloc_allocate_range( } #define XFS_FALLOC_FL_SUPPORTED \ - (FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | \ - FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | \ - FALLOC_FL_INSERT_RANGE | FALLOC_FL_UNSHARE_RANGE) + (FALLOC_FL_ALLOCATE_RANGE | FALLOC_FL_KEEP_SIZE | \ + FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE | \ + FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE | \ + FALLOC_FL_UNSHARE_RANGE) STATIC long __xfs_file_fallocate( diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 726e29b837e6..bbc2f2973dcc 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -979,7 +979,15 @@ xfs_reclaim_inode( */ if (xlog_is_shutdown(ip->i_mount->m_log)) { xfs_iunpin_wait(ip); + /* + * Avoid a ABBA deadlock on the inode cluster buffer vs + * concurrent xfs_ifree_cluster() trying to mark the inode + * stale. We don't need the inode locked to run the flush abort + * code, but the flush abort needs to lock the cluster buffer. + */ + xfs_iunlock(ip, XFS_ILOCK_EXCL); xfs_iflush_shutdown_abort(ip); + xfs_ilock(ip, XFS_ILOCK_EXCL); goto reclaim; } if (xfs_ipincount(ip)) diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index ee3e0f284287..761a996a857c 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1635,7 +1635,7 @@ retry: iip = ip->i_itemp; if (__xfs_iflags_test(ip, XFS_IFLUSHING)) { ASSERT(!list_empty(&iip->ili_item.li_bio_list)); - ASSERT(iip->ili_last_fields); + ASSERT(iip->ili_last_fields || xlog_is_shutdown(mp->m_log)); goto out_iunlock; } diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index c6cb0b6b9e46..285e27ff89e2 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -758,11 +758,14 @@ xfs_inode_item_push( * completed and items removed from the AIL before the next push * attempt. */ + trace_xfs_inode_push_stale(ip, _RET_IP_); return XFS_ITEM_PINNED; } - if (xfs_ipincount(ip) > 0 || xfs_buf_ispinned(bp)) + if (xfs_ipincount(ip) > 0 || xfs_buf_ispinned(bp)) { + trace_xfs_inode_push_pinned(ip, _RET_IP_); return XFS_ITEM_PINNED; + } if (xfs_iflags_test(ip, XFS_IFLUSHING)) return XFS_ITEM_FLUSHING; diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index f66d2d430e4f..a80cb6b9969a 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -793,8 +793,10 @@ xlog_cil_ail_insert( struct xfs_log_item *lip = lv->lv_item; xfs_lsn_t item_lsn; - if (aborted) + if (aborted) { + trace_xlog_ail_insert_abort(lip); set_bit(XFS_LI_ABORTED, &lip->li_flags); + } if (lip->li_ops->flags & XFS_ITEM_RELEASE_WHEN_COMMITTED) { lip->li_ops->iop_release(lip); diff --git a/fs/xfs/xfs_mru_cache.c b/fs/xfs/xfs_mru_cache.c index 08443ceec329..866c71d9fbae 100644 --- a/fs/xfs/xfs_mru_cache.c +++ b/fs/xfs/xfs_mru_cache.c @@ -320,7 +320,7 @@ xfs_mru_cache_create( xfs_mru_cache_free_func_t free_func) { struct xfs_mru_cache *mru = NULL; - int err = 0, grp; + int grp; unsigned int grp_time; if (mrup) @@ -341,8 +341,8 @@ xfs_mru_cache_create( mru->lists = kzalloc(mru->grp_count * sizeof(*mru->lists), GFP_KERNEL | __GFP_NOFAIL); if (!mru->lists) { - err = -ENOMEM; - goto exit; + kfree(mru); + return -ENOMEM; } for (grp = 0; grp < mru->grp_count; grp++) @@ -361,14 +361,7 @@ xfs_mru_cache_create( mru->free_func = free_func; mru->data = data; *mrup = mru; - -exit: - if (err && mru && mru->lists) - kfree(mru->lists); - if (err && mru) - kfree(mru); - - return err; + return 0; } /* @@ -425,10 +418,6 @@ xfs_mru_cache_insert( { int error = -EINVAL; - ASSERT(mru && mru->lists); - if (!mru || !mru->lists) - goto out_free; - error = -ENOMEM; if (radix_tree_preload(GFP_KERNEL)) goto out_free; diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 417439b58785..fa135ac26471 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -134,6 +134,7 @@ xfs_qm_dqpurge( dqp->q_flags |= XFS_DQFLAG_FREEING; + xfs_qm_dqunpin_wait(dqp); xfs_dqflock(dqp); /* @@ -465,6 +466,7 @@ xfs_qm_dquot_isolate( struct xfs_dquot *dqp = container_of(item, struct xfs_dquot, q_lru); struct xfs_qm_isolate *isol = arg; + enum lru_status ret = LRU_SKIP; if (!xfs_dqlock_nowait(dqp)) goto out_miss_busy; @@ -478,6 +480,16 @@ xfs_qm_dquot_isolate( goto out_miss_unlock; /* + * If the dquot is pinned or dirty, rotate it to the end of the LRU to + * give some time for it to be cleaned before we try to isolate it + * again. + */ + ret = LRU_ROTATE; + if (XFS_DQ_IS_DIRTY(dqp) || atomic_read(&dqp->q_pincount) > 0) { + goto out_miss_unlock; + } + + /* * This dquot has acquired a reference in the meantime remove it from * the freelist and try again. */ @@ -492,41 +504,14 @@ xfs_qm_dquot_isolate( } /* - * If the dquot is dirty, flush it. If it's already being flushed, just - * skip it so there is time for the IO to complete before we try to - * reclaim it again on the next LRU pass. + * The dquot may still be under IO, in which case the flush lock will be + * held. If we can't get the flush lock now, just skip over the dquot as + * if it was dirty. */ if (!xfs_dqflock_nowait(dqp)) goto out_miss_unlock; - if (XFS_DQ_IS_DIRTY(dqp)) { - struct xfs_buf *bp = NULL; - int error; - - trace_xfs_dqreclaim_dirty(dqp); - - /* we have to drop the LRU lock to flush the dquot */ - spin_unlock(&lru->lock); - - error = xfs_dquot_use_attached_buf(dqp, &bp); - if (!bp || error == -EAGAIN) { - xfs_dqfunlock(dqp); - goto out_unlock_dirty; - } - - /* - * dqflush completes dqflock on error, and the delwri ioend - * does it on success. - */ - error = xfs_qm_dqflush(dqp, bp); - if (error) - goto out_unlock_dirty; - - xfs_buf_delwri_queue(bp, &isol->buffers); - xfs_buf_relse(bp); - goto out_unlock_dirty; - } - + ASSERT(!XFS_DQ_IS_DIRTY(dqp)); xfs_dquot_detach_buf(dqp); xfs_dqfunlock(dqp); @@ -548,13 +533,7 @@ out_miss_unlock: out_miss_busy: trace_xfs_dqreclaim_busy(dqp); XFS_STATS_INC(dqp->q_mount, xs_qm_dqreclaim_misses); - return LRU_SKIP; - -out_unlock_dirty: - trace_xfs_dqreclaim_busy(dqp); - XFS_STATS_INC(dqp->q_mount, xs_qm_dqreclaim_misses); - xfs_dqunlock(dqp); - return LRU_RETRY; + return ret; } static unsigned long @@ -1486,7 +1465,6 @@ xfs_qm_flush_one( struct xfs_dquot *dqp, void *data) { - struct xfs_mount *mp = dqp->q_mount; struct list_head *buffer_list = data; struct xfs_buf *bp = NULL; int error = 0; @@ -1497,34 +1475,8 @@ xfs_qm_flush_one( if (!XFS_DQ_IS_DIRTY(dqp)) goto out_unlock; - /* - * The only way the dquot is already flush locked by the time quotacheck - * gets here is if reclaim flushed it before the dqadjust walk dirtied - * it for the final time. Quotacheck collects all dquot bufs in the - * local delwri queue before dquots are dirtied, so reclaim can't have - * possibly queued it for I/O. The only way out is to push the buffer to - * cycle the flush lock. - */ - if (!xfs_dqflock_nowait(dqp)) { - /* buf is pinned in-core by delwri list */ - error = xfs_buf_incore(mp->m_ddev_targp, dqp->q_blkno, - mp->m_quotainfo->qi_dqchunklen, 0, &bp); - if (error) - goto out_unlock; - - if (!(bp->b_flags & _XBF_DELWRI_Q)) { - error = -EAGAIN; - xfs_buf_relse(bp); - goto out_unlock; - } - xfs_buf_unlock(bp); - - xfs_buf_delwri_pushbuf(bp, buffer_list); - xfs_buf_rele(bp); - - error = -EAGAIN; - goto out_unlock; - } + xfs_qm_dqunpin_wait(dqp); + xfs_dqflock(dqp); error = xfs_dquot_use_attached_buf(dqp, &bp); if (error) diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 6484c596ecea..736eb0924573 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -1259,6 +1259,8 @@ xfs_growfs_check_rtgeom( kfree(nmp); + trace_xfs_growfs_check_rtgeom(mp, min_logfsbs); + if (min_logfsbs > mp->m_sb.sb_logblocks) return -EINVAL; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 0bc4b5489078..bb0a82635a77 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -2020,14 +2020,13 @@ xfs_remount_rw( int error; if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp && - bdev_read_only(mp->m_logdev_targp->bt_bdev)) { + xfs_readonly_buftarg(mp->m_logdev_targp)) { xfs_warn(mp, "ro->rw transition prohibited by read-only logdev"); return -EACCES; } - if (mp->m_rtdev_targp && - bdev_read_only(mp->m_rtdev_targp->bt_bdev)) { + if (mp->m_rtdev_targp && xfs_readonly_buftarg(mp->m_rtdev_targp)) { xfs_warn(mp, "ro->rw transition prohibited by read-only rtdev"); return -EACCES; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 01d284a1c759..ba45d801df1c 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -778,7 +778,6 @@ DEFINE_BUF_EVENT(xfs_buf_iowait_done); DEFINE_BUF_EVENT(xfs_buf_delwri_queue); DEFINE_BUF_EVENT(xfs_buf_delwri_queued); DEFINE_BUF_EVENT(xfs_buf_delwri_split); -DEFINE_BUF_EVENT(xfs_buf_delwri_pushbuf); DEFINE_BUF_EVENT(xfs_buf_get_uncached); DEFINE_BUF_EVENT(xfs_buf_item_relse); DEFINE_BUF_EVENT(xfs_buf_iodone_async); @@ -1147,6 +1146,7 @@ DECLARE_EVENT_CLASS(xfs_iref_class, __field(xfs_ino_t, ino) __field(int, count) __field(int, pincount) + __field(unsigned long, iflags) __field(unsigned long, caller_ip) ), TP_fast_assign( @@ -1154,13 +1154,15 @@ DECLARE_EVENT_CLASS(xfs_iref_class, __entry->ino = ip->i_ino; __entry->count = atomic_read(&VFS_I(ip)->i_count); __entry->pincount = atomic_read(&ip->i_pincount); + __entry->iflags = ip->i_flags; __entry->caller_ip = caller_ip; ), - TP_printk("dev %d:%d ino 0x%llx count %d pincount %d caller %pS", + TP_printk("dev %d:%d ino 0x%llx count %d pincount %d iflags 0x%lx caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->count, __entry->pincount, + __entry->iflags, (char *)__entry->caller_ip) ) @@ -1250,6 +1252,8 @@ DEFINE_IREF_EVENT(xfs_irele); DEFINE_IREF_EVENT(xfs_inode_pin); DEFINE_IREF_EVENT(xfs_inode_unpin); DEFINE_IREF_EVENT(xfs_inode_unpin_nowait); +DEFINE_IREF_EVENT(xfs_inode_push_pinned); +DEFINE_IREF_EVENT(xfs_inode_push_stale); DECLARE_EVENT_CLASS(xfs_namespace_class, TP_PROTO(struct xfs_inode *dp, const struct xfs_name *name), @@ -1654,6 +1658,8 @@ DEFINE_LOG_ITEM_EVENT(xfs_ail_flushing); DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_mark); DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_skip); DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_unpin); +DEFINE_LOG_ITEM_EVENT(xlog_ail_insert_abort); +DEFINE_LOG_ITEM_EVENT(xfs_trans_free_abort); DECLARE_EVENT_CLASS(xfs_ail_class, TP_PROTO(struct xfs_log_item *lip, xfs_lsn_t old_lsn, xfs_lsn_t new_lsn), diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index c6657072361a..b4a07af513ba 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -742,8 +742,10 @@ xfs_trans_free_items( list_for_each_entry_safe(lip, next, &tp->t_items, li_trans) { xfs_trans_del_item(lip); - if (abort) + if (abort) { + trace_xfs_trans_free_abort(lip); set_bit(XFS_LI_ABORTED, &lip->li_flags); + } if (lip->li_ops->iop_release) lip->li_ops->iop_release(lip); } diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c index 80add26c0111..01315ed75502 100644 --- a/fs/xfs/xfs_zone_alloc.c +++ b/fs/xfs/xfs_zone_alloc.c @@ -727,7 +727,7 @@ xfs_select_zone( for (;;) { prepare_to_wait(&zi->zi_zone_wait, &wait, TASK_UNINTERRUPTIBLE); oz = xfs_select_zone_nowait(mp, write_hint, pack_tight); - if (oz) + if (oz || xfs_is_shutdown(mp)) break; schedule(); } @@ -777,26 +777,6 @@ xfs_mark_rtg_boundary( ioend->io_flags |= IOMAP_IOEND_BOUNDARY; } -static void -xfs_submit_zoned_bio( - struct iomap_ioend *ioend, - struct xfs_open_zone *oz, - bool is_seq) -{ - ioend->io_bio.bi_iter.bi_sector = ioend->io_sector; - ioend->io_private = oz; - atomic_inc(&oz->oz_ref); /* for xfs_zoned_end_io */ - - if (is_seq) { - ioend->io_bio.bi_opf &= ~REQ_OP_WRITE; - ioend->io_bio.bi_opf |= REQ_OP_ZONE_APPEND; - } else { - xfs_mark_rtg_boundary(ioend); - } - - submit_bio(&ioend->io_bio); -} - /* * Cache the last zone written to for an inode so that it is considered first * for subsequent writes. @@ -891,6 +871,26 @@ xfs_zone_cache_create_association( xfs_mru_cache_insert(mp->m_zone_cache, ip->i_ino, &item->mru); } +static void +xfs_submit_zoned_bio( + struct iomap_ioend *ioend, + struct xfs_open_zone *oz, + bool is_seq) +{ + ioend->io_bio.bi_iter.bi_sector = ioend->io_sector; + ioend->io_private = oz; + atomic_inc(&oz->oz_ref); /* for xfs_zoned_end_io */ + + if (is_seq) { + ioend->io_bio.bi_opf &= ~REQ_OP_WRITE; + ioend->io_bio.bi_opf |= REQ_OP_ZONE_APPEND; + } else { + xfs_mark_rtg_boundary(ioend); + } + + submit_bio(&ioend->io_bio); +} + void xfs_zone_alloc_and_submit( struct iomap_ioend *ioend, diff --git a/include/crypto/internal/sha2.h b/include/crypto/internal/sha2.h index b9bccd3ff57f..21a27fd5e198 100644 --- a/include/crypto/internal/sha2.h +++ b/include/crypto/internal/sha2.h @@ -25,7 +25,7 @@ void sha256_blocks_arch(u32 state[SHA256_STATE_WORDS], void sha256_blocks_simd(u32 state[SHA256_STATE_WORDS], const u8 *data, size_t nblocks); -static inline void sha256_choose_blocks( +static __always_inline void sha256_choose_blocks( u32 state[SHA256_STATE_WORDS], const u8 *data, size_t nblocks, bool force_generic, bool force_simd) { diff --git a/include/linux/dpll.h b/include/linux/dpll.h index 6ad6c2968a28..fa1e76920d0e 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -103,6 +103,16 @@ struct dpll_pin_ops { const struct dpll_device *dpll, void *dpll_priv, struct dpll_pin_esync *esync, struct netlink_ext_ack *extack); + int (*ref_sync_set)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_pin *ref_sync_pin, + void *ref_sync_pin_priv, + const enum dpll_pin_state state, + struct netlink_ext_ack *extack); + int (*ref_sync_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_pin *ref_sync_pin, + void *ref_sync_pin_priv, + enum dpll_pin_state *state, + struct netlink_ext_ack *extack); }; struct dpll_pin_frequency { @@ -202,6 +212,9 @@ int dpll_pin_on_pin_register(struct dpll_pin *parent, struct dpll_pin *pin, void dpll_pin_on_pin_unregister(struct dpll_pin *parent, struct dpll_pin *pin, const struct dpll_pin_ops *ops, void *priv); +int dpll_pin_ref_sync_pair_add(struct dpll_pin *pin, + struct dpll_pin *ref_sync_pin); + int dpll_device_change_ntf(struct dpll_device *dpll); int dpll_pin_change_ntf(struct dpll_pin *pin); diff --git a/include/linux/futex.h b/include/linux/futex.h index 005b040c4791..b37193653e6b 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -89,6 +89,7 @@ void futex_hash_free(struct mm_struct *mm); static inline void futex_mm_init(struct mm_struct *mm) { RCU_INIT_POINTER(mm->futex_phash, NULL); + mm->futex_phash_new = NULL; mutex_init(&mm->futex_hash_lock); } diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index 043d442994b0..80166eb62f41 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -19,11 +19,6 @@ struct tun_msg_ctl { void *ptr; }; -struct tun_xdp_hdr { - int buflen; - struct virtio_net_hdr gso; -}; - #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE) struct socket *tun_get_socket(struct file *); struct ptr_ring *tun_get_tx_ring(struct file *file); diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h index 93a73c076d16..fbd424b2abb1 100644 --- a/include/linux/kmemleak.h +++ b/include/linux/kmemleak.h @@ -28,6 +28,7 @@ extern void kmemleak_update_trace(const void *ptr) __ref; extern void kmemleak_not_leak(const void *ptr) __ref; extern void kmemleak_transient_leak(const void *ptr) __ref; extern void kmemleak_ignore(const void *ptr) __ref; +extern void kmemleak_ignore_percpu(const void __percpu *ptr) __ref; extern void kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp) __ref; extern void kmemleak_no_scan(const void *ptr) __ref; extern void kmemleak_alloc_phys(phys_addr_t phys, size_t size, @@ -97,6 +98,9 @@ static inline void kmemleak_not_leak(const void *ptr) static inline void kmemleak_transient_leak(const void *ptr) { } +static inline void kmemleak_ignore_percpu(const void __percpu *ptr) +{ +} static inline void kmemleak_ignore(const void *ptr) { } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index db5bfd4e7ec8..5847c20994d3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3316,13 +3316,6 @@ static inline struct net_device *first_net_device(struct net *net) net_device_entry(net->dev_base_head.next); } -static inline struct net_device *first_net_device_rcu(struct net *net) -{ - struct list_head *lh = rcu_dereference(list_next_rcu(&net->dev_base_head)); - - return lh == &net->dev_base_head ? NULL : net_device_entry(lh); -} - int netdev_boot_setup_check(struct net_device *dev); struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, const char *hwaddr); diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index eced7e9bf69a..3d089bd4d5e9 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -477,40 +477,14 @@ static inline ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp, static inline void ptp_read_system_prets(struct ptp_system_timestamp *sts) { - if (sts) { - switch (sts->clockid) { - case CLOCK_REALTIME: - ktime_get_real_ts64(&sts->pre_ts); - break; - case CLOCK_MONOTONIC: - ktime_get_ts64(&sts->pre_ts); - break; - case CLOCK_MONOTONIC_RAW: - ktime_get_raw_ts64(&sts->pre_ts); - break; - default: - break; - } - } + if (sts) + ktime_get_clock_ts64(sts->clockid, &sts->pre_ts); } static inline void ptp_read_system_postts(struct ptp_system_timestamp *sts) { - if (sts) { - switch (sts->clockid) { - case CLOCK_REALTIME: - ktime_get_real_ts64(&sts->post_ts); - break; - case CLOCK_MONOTONIC: - ktime_get_ts64(&sts->post_ts); - break; - case CLOCK_MONOTONIC_RAW: - ktime_get_raw_ts64(&sts->post_ts); - break; - default: - break; - } - } + if (sts) + ktime_get_clock_ts64(sts->clockid, &sts->post_ts); } #endif diff --git a/include/linux/soc/amd/isp4_misc.h b/include/linux/soc/amd/isp4_misc.h new file mode 100644 index 000000000000..6738796986a7 --- /dev/null +++ b/include/linux/soc/amd/isp4_misc.h @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0+ + +/* + * Copyright (C) 2025 Advanced Micro Devices, Inc. + */ + +#ifndef __SOC_ISP4_MISC_H +#define __SOC_ISP4_MISC_H + +#define AMDISP_I2C_ADAP_NAME "AMDISP DesignWare I2C adapter" + +#endif diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 542773650200..4a4c2778abae 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -44,6 +44,7 @@ extern void ktime_get_ts64(struct timespec64 *ts); extern void ktime_get_real_ts64(struct timespec64 *tv); extern void ktime_get_coarse_ts64(struct timespec64 *ts); extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); +extern void ktime_get_clock_ts64(clockid_t id, struct timespec64 *ts); /* Multigrain timestamp interfaces */ extern void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts); @@ -345,4 +346,13 @@ void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock, extern int update_persistent_clock64(struct timespec64 now); #endif +/* Temporary workaround to avoid merge dependencies and cross tree messes */ +#ifndef CLOCK_AUX +#define CLOCK_AUX MAX_CLOCKS +#define MAX_AUX_CLOCKS 8 +#define CLOCK_AUX_LAST (CLOCK_AUX + MAX_AUX_CLOCKS - 1) + +static inline bool ktime_get_aux_ts64(clockid_t id, struct timespec64 *kt) { return false; } +#endif + #endif diff --git a/include/net/aligned_data.h b/include/net/aligned_data.h new file mode 100644 index 000000000000..e1a1c8aedc79 --- /dev/null +++ b/include/net/aligned_data.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _NET_ALIGNED_DATA_H +#define _NET_ALIGNED_DATA_H + +#include <linux/atomic.h> +#include <linux/types.h> + +/* Structure holding cacheline aligned fields on SMP builds. + * Each field or group should have an ____cacheline_aligned_in_smp + * attribute to ensure no accidental false sharing can happen. + */ +struct net_aligned_data { + atomic64_t net_cookie ____cacheline_aligned_in_smp; +#if defined(CONFIG_INET) + atomic_long_t tcp_memory_allocated ____cacheline_aligned_in_smp; + atomic_long_t udp_memory_allocated ____cacheline_aligned_in_smp; +#endif +}; + +extern struct net_aligned_data net_aligned_data; + +#endif /* _NET_ALIGNED_DATA_H */ diff --git a/include/net/devlink.h b/include/net/devlink.h index 63517646a497..d0ce5a7e984c 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -118,6 +118,8 @@ struct devlink_rate { u32 tx_priority; u32 tx_weight; + + u32 tc_bw[DEVLINK_RATE_TCS_MAX]; }; struct devlink_port { @@ -1486,6 +1488,9 @@ struct devlink_ops { u32 tx_priority, struct netlink_ext_ack *extack); int (*rate_leaf_tx_weight_set)(struct devlink_rate *devlink_rate, void *priv, u32 tx_weight, struct netlink_ext_ack *extack); + int (*rate_leaf_tc_bw_set)(struct devlink_rate *devlink_rate, + void *priv, u32 *tc_bw, + struct netlink_ext_ack *extack); int (*rate_node_tx_share_set)(struct devlink_rate *devlink_rate, void *priv, u64 tx_share, struct netlink_ext_ack *extack); int (*rate_node_tx_max_set)(struct devlink_rate *devlink_rate, void *priv, @@ -1494,6 +1499,9 @@ struct devlink_ops { u32 tx_priority, struct netlink_ext_ack *extack); int (*rate_node_tx_weight_set)(struct devlink_rate *devlink_rate, void *priv, u32 tx_weight, struct netlink_ext_ack *extack); + int (*rate_node_tc_bw_set)(struct devlink_rate *devlink_rate, + void *priv, u32 *tc_bw, + struct netlink_ext_ack *extack); int (*rate_node_new)(struct devlink_rate *rate_node, void **priv, struct netlink_ext_ack *extack); int (*rate_node_del)(struct devlink_rate *rate_node, void *priv, diff --git a/include/net/dst.h b/include/net/dst.h index 78c78cdce0e9..00467c1b5093 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -240,9 +240,9 @@ static inline void dst_hold(struct dst_entry *dst) static inline void dst_use_noref(struct dst_entry *dst, unsigned long time) { - if (unlikely(time != dst->lastuse)) { + if (unlikely(time != READ_ONCE(dst->lastuse))) { dst->__use++; - dst->lastuse = time; + WRITE_ONCE(dst->lastuse, time); } } @@ -431,13 +431,15 @@ static inline void dst_link_failure(struct sk_buff *skb) static inline void dst_set_expires(struct dst_entry *dst, int timeout) { - unsigned long expires = jiffies + timeout; + unsigned long old, expires = jiffies + timeout; if (expires == 0) expires = 1; - if (dst->expires == 0 || time_before(expires, dst->expires)) - dst->expires = expires; + old = READ_ONCE(dst->expires); + + if (!old || time_before(expires, old)) + WRITE_ONCE(dst->expires, expires); } static inline unsigned int dst_dev_overhead(struct dst_entry *dst, @@ -456,7 +458,7 @@ INDIRECT_CALLABLE_DECLARE(int ip_output(struct net *, struct sock *, /* Output packet to network from transport. */ static inline int dst_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - return INDIRECT_CALL_INET(skb_dst(skb)->output, + return INDIRECT_CALL_INET(READ_ONCE(skb_dst(skb)->output), ip6_output, ip_output, net, sk, skb); } @@ -466,7 +468,7 @@ INDIRECT_CALLABLE_DECLARE(int ip_local_deliver(struct sk_buff *)); /* Input packet from network to transport. */ static inline int dst_input(struct sk_buff *skb) { - return INDIRECT_CALL_INET(skb_dst(skb)->input, + return INDIRECT_CALL_INET(READ_ONCE(skb_dst(skb)->input), ip6_input, ip_local_deliver, skb); } @@ -476,7 +478,7 @@ INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, u32)); static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie) { - if (dst->obsolete) + if (READ_ONCE(dst->obsolete)) dst = INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check, dst, cookie); return dst; @@ -561,6 +563,26 @@ static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu) dst->ops->update_pmtu(dst, NULL, skb, mtu, false); } +static inline struct net_device *dst_dev(const struct dst_entry *dst) +{ + return READ_ONCE(dst->dev); +} + +static inline struct net_device *skb_dst_dev(const struct sk_buff *skb) +{ + return dst_dev(skb_dst(skb)); +} + +static inline struct net *skb_dst_dev_net(const struct sk_buff *skb) +{ + return dev_net(skb_dst_dev(skb)); +} + +static inline struct net *skb_dst_dev_net_rcu(const struct sk_buff *skb) +{ + return dev_net_rcu(skb_dst_dev(skb)); +} + struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie); void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh); diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index c32878c69179..ab3929a2a956 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -150,7 +150,7 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, int iif, int sdif, bool *refcounted) { - struct net *net = dev_net_rcu(skb_dst(skb)->dev); + struct net *net = skb_dst_dev_net_rcu(skb); const struct ipv6hdr *ip6h = ipv6_hdr(skb); struct sock *sk; diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index ae09e91398a5..19dbd9081d5a 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -481,7 +481,7 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, const int sdif, bool *refcounted) { - struct net *net = dev_net_rcu(skb_dst(skb)->dev); + struct net *net = skb_dst_dev_net_rcu(skb); const struct iphdr *iph = ip_hdr(skb); struct sock *sk; diff --git a/include/net/ip.h b/include/net/ip.h index 375304bb99f6..befcba575129 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -472,12 +472,12 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, rcu_read_lock(); - net = dev_net_rcu(dst->dev); + net = dev_net_rcu(dst_dev(dst)); if (READ_ONCE(net->ipv4.sysctl_ip_fwd_use_pmtu) || ip_mtu_locked(dst) || !forwarding) { mtu = rt->rt_pmtu; - if (mtu && time_before(jiffies, rt->dst.expires)) + if (mtu && time_before(jiffies, READ_ONCE(rt->dst.expires))) goto out; } @@ -486,7 +486,7 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, if (mtu) goto out; - mtu = READ_ONCE(dst->dev->mtu); + mtu = READ_ONCE(dst_dev(dst)->mtu); if (unlikely(ip_mtu_locked(dst))) { if (rt->rt_uses_gateway && mtu > 576) @@ -506,16 +506,17 @@ out: static inline unsigned int ip_skb_dst_mtu(struct sock *sk, const struct sk_buff *skb) { + const struct dst_entry *dst = skb_dst(skb); unsigned int mtu; if (!sk || !sk_fullsock(sk) || ip_sk_use_pmtu(sk)) { bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED; - return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding); + return ip_dst_mtu_maybe_forward(dst, forwarding); } - mtu = min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU); - return mtu - lwtunnel_headroom(skb_dst(skb)->lwtstate, mtu); + mtu = min(READ_ONCE(dst_dev(dst)->mtu), IP_MAX_MTU); + return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } struct dst_metrics *ip_fib_metrics_init(struct nlattr *fc_mx, int fc_mx_len, diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 6dbdf60b342f..9255f21818ee 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -274,7 +274,7 @@ static inline unsigned int ip6_skb_dst_mtu(const struct sk_buff *skb) unsigned int mtu; if (np && READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE) { - mtu = READ_ONCE(dst->dev->mtu); + mtu = READ_ONCE(dst_dev(dst)->mtu); mtu -= lwtunnel_headroom(dst->lwtstate, mtu); } else { mtu = dst_mtu(dst); @@ -337,7 +337,7 @@ static inline unsigned int ip6_dst_mtu_maybe_forward(const struct dst_entry *dst mtu = IPV6_MIN_MTU; rcu_read_lock(); - idev = __in6_dev_get(dst->dev); + idev = __in6_dev_get(dst_dev(dst)); if (idev) mtu = READ_ONCE(idev->cnf.mtu6); rcu_read_unlock(); diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index dd163495f353..120db2865811 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -159,7 +159,7 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); IP6CB(skb)->flags = ip6cb_flags; pkt_len = skb->len - skb_inner_network_offset(skb); - err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb); + err = ip6_local_out(skb_dst_dev_net(skb), sk, skb); if (dev) { if (unlikely(net_xmit_eval(err))) diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index c306ebe379a0..26232f603e33 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -138,12 +138,12 @@ int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, static inline void lwtunnel_set_redirect(struct dst_entry *dst) { if (lwtunnel_output_redirect(dst->lwtstate)) { - dst->lwtstate->orig_output = dst->output; - dst->output = lwtunnel_output; + dst->lwtstate->orig_output = READ_ONCE(dst->output); + WRITE_ONCE(dst->output, lwtunnel_output); } if (lwtunnel_input_redirect(dst->lwtstate)) { - dst->lwtstate->orig_input = dst->input; - dst->input = lwtunnel_input; + dst->lwtstate->orig_input = READ_ONCE(dst->input); + WRITE_ONCE(dst->input, lwtunnel_input); } } #else diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 92ab85061df0..57df78cfbf82 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -62,6 +62,7 @@ enum gdma_eqe_type { GDMA_EQE_HWC_FPGA_RECONFIG = 132, GDMA_EQE_HWC_SOC_RECONFIG_DATA = 133, GDMA_EQE_HWC_SOC_SERVICE = 134, + GDMA_EQE_HWC_RESET_REQUEST = 135, GDMA_EQE_RNIC_QP_FATAL = 176, }; @@ -584,6 +585,9 @@ enum { /* Driver supports dynamic MSI-X vector allocation */ #define GDMA_DRV_CAP_FLAG_1_DYNAMIC_IRQ_ALLOC_SUPPORT BIT(13) +/* Driver can self reset on EQE notification */ +#define GDMA_DRV_CAP_FLAG_1_SELF_RESET_ON_EQE BIT(14) + /* Driver can self reset on FPGA Reconfig EQE notification */ #define GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE BIT(17) @@ -594,6 +598,7 @@ enum { GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT | \ GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP | \ GDMA_DRV_CAP_FLAG_1_DYNAMIC_IRQ_ALLOC_SUPPORT | \ + GDMA_DRV_CAP_FLAG_1_SELF_RESET_ON_EQE | \ GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE) #define GDMA_DRV_CAP_FLAGS2 0 @@ -921,4 +926,9 @@ void mana_unregister_debugfs(void); int mana_rdma_service_event(struct gdma_context *gc, enum gdma_service_type event); +int mana_gd_suspend(struct pci_dev *pdev, pm_message_t state); +int mana_gd_resume(struct pci_dev *pdev); + +bool mana_need_log(struct gdma_context *gc, int err); + #endif /* _GDMA_H */ diff --git a/include/net/neighbour.h b/include/net/neighbour.h index c7ce5ec7be23..7e865b14749d 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -261,13 +261,15 @@ static inline void *neighbour_priv(const struct neighbour *n) #define NEIGH_UPDATE_F_EXT_LEARNED BIT(5) #define NEIGH_UPDATE_F_ISROUTER BIT(6) #define NEIGH_UPDATE_F_ADMIN BIT(7) +#define NEIGH_UPDATE_F_EXT_VALIDATED BIT(8) /* In-kernel representation for NDA_FLAGS_EXT flags: */ #define NTF_OLD_MASK 0xff #define NTF_EXT_SHIFT 8 -#define NTF_EXT_MASK (NTF_EXT_MANAGED) +#define NTF_EXT_MASK (NTF_EXT_MANAGED | NTF_EXT_EXT_VALIDATED) #define NTF_MANAGED (NTF_EXT_MANAGED << NTF_EXT_SHIFT) +#define NTF_EXT_VALIDATED (NTF_EXT_EXT_VALIDATED << NTF_EXT_SHIFT) extern const struct nla_policy nda_policy[]; diff --git a/include/net/netlink.h b/include/net/netlink.h index 90a560dc167a..1a8356ca4b78 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -68,6 +68,8 @@ * nlmsg_for_each_msg() loop over all messages * nlmsg_validate() validate netlink message incl. attrs * nlmsg_for_each_attr() loop over all attributes + * nlmsg_for_each_attr_type() loop over all attributes with the + * given type * * Misc: * nlmsg_report() report back to application? @@ -967,6 +969,18 @@ static inline u32 nlmsg_seq(const struct nlmsghdr *nlh) nlmsg_attrlen(nlh, hdrlen), rem) /** + * nlmsg_for_each_attr_type - iterate over a stream of attributes + * @pos: loop counter, set to the current attribute + * @type: required attribute type for @pos + * @nlh: netlink message header + * @hdrlen: length of the family specific header + * @rem: initialized to len, holds bytes currently remaining in stream + */ +#define nlmsg_for_each_attr_type(pos, type, nlh, hdrlen, rem) \ + nlmsg_for_each_attr(pos, nlh, hdrlen, rem) \ + if (nla_type(pos) == type) + +/** * nlmsg_put - Add a new netlink message to an skb * @skb: socket buffer to store message in * @portid: netlink PORTID of requesting application diff --git a/include/net/request_sock.h b/include/net/request_sock.h index b07b1cd14e9f..6a5ec1418e85 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -30,8 +30,6 @@ struct request_sock_ops { unsigned int obj_size; struct kmem_cache *slab; char *slab_name; - int (*rtx_syn_ack)(const struct sock *sk, - struct request_sock *req); void (*send_ack)(const struct sock *sk, struct sk_buff *skb, struct request_sock *req); void (*send_reset)(const struct sock *sk, @@ -41,8 +39,6 @@ struct request_sock_ops { void (*syn_ack_timeout)(const struct request_sock *req); }; -int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req); - struct saved_syn { u32 mac_hdrlen; u32 network_hdrlen; diff --git a/include/net/route.h b/include/net/route.h index 3d3d6048ffca..7ea840daa775 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -390,7 +390,7 @@ static inline int ip4_dst_hoplimit(const struct dst_entry *dst) const struct net *net; rcu_read_lock(); - net = dev_net_rcu(dst->dev); + net = dev_net_rcu(dst_dev(dst)); hoplimit = READ_ONCE(net->ipv4.sysctl_ip_default_ttl); rcu_read_unlock(); } diff --git a/include/net/tcp.h b/include/net/tcp.h index 761c4a0ad386..bc08de49805c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -267,7 +267,6 @@ extern long sysctl_tcp_mem[3]; #define TCP_RACK_STATIC_REO_WND 0x2 /* Use static RACK reo wnd */ #define TCP_RACK_NO_DUPTHRESH 0x4 /* Do not use DUPACK threshold in RACK */ -extern atomic_long_t tcp_memory_allocated; DECLARE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc); extern struct percpu_counter tcp_sockets_allocated; diff --git a/include/net/udp.h b/include/net/udp.h index a772510b2aa5..f8ae2c4ade14 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -205,7 +205,6 @@ static inline void udp_hash4_dec(struct udp_hslot *hslot2) extern struct proto udp_prot; -extern atomic_long_t udp_memory_allocated; DECLARE_PER_CPU(int, udp_memory_per_cpu_fw_alloc); /* sysctl variables for udp */ diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index d3ef86c97ae3..18c0ac514fcb 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -168,25 +168,7 @@ DEFINE_EVENT(xdp_redirect_template, xdp_redirect_err, #define _trace_xdp_redirect_map_err(dev, xdp, to, map_type, map_id, index, err) \ trace_xdp_redirect_err(dev, xdp, to, err, map_type, map_id, index) -/* not used anymore, but kept around so as not to break old programs */ -DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map, - TP_PROTO(const struct net_device *dev, - const struct bpf_prog *xdp, - const void *tgt, int err, - enum bpf_map_type map_type, - u32 map_id, u32 index), - TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index) -); - -DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map_err, - TP_PROTO(const struct net_device *dev, - const struct bpf_prog *xdp, - const void *tgt, int err, - enum bpf_map_type map_type, - u32 map_id, u32 index), - TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index) -); - +#ifdef CONFIG_BPF_SYSCALL TRACE_EVENT(xdp_cpumap_kthread, TP_PROTO(int map_id, unsigned int processed, unsigned int drops, @@ -300,6 +282,7 @@ TRACE_EVENT(xdp_devmap_xmit, __entry->sent, __entry->drops, __entry->err) ); +#endif /* CONFIG_BPF_SYSCALL */ /* Expect users already include <net/xdp.h>, but not xdp_priv.h */ #include <net/xdp_priv.h> diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index a5ee0f13740a..e72bcc239afd 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -221,6 +221,11 @@ enum devlink_port_flavour { */ }; +/* IEEE 802.1Qaz standard supported values. */ + +#define DEVLINK_RATE_TCS_MAX 8 +#define DEVLINK_RATE_TC_INDEX_MAX (DEVLINK_RATE_TCS_MAX - 1) + enum devlink_rate_type { DEVLINK_RATE_TYPE_LEAF, DEVLINK_RATE_TYPE_NODE, @@ -629,6 +634,10 @@ enum devlink_attr { DEVLINK_ATTR_REGION_DIRECT, /* flag */ + DEVLINK_ATTR_RATE_TC_BWS, /* nested */ + DEVLINK_ATTR_RATE_TC_INDEX, /* u8 */ + DEVLINK_ATTR_RATE_TC_BW, /* u32 */ + /* Add new attributes above here, update the spec in * Documentation/netlink/specs/devlink.yaml and re-generate * net/devlink/netlink_gen.c. diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h index 349e1b3ca1ae..37b438ce8efc 100644 --- a/include/uapi/linux/dpll.h +++ b/include/uapi/linux/dpll.h @@ -249,6 +249,7 @@ enum dpll_a_pin { DPLL_A_PIN_ESYNC_FREQUENCY, DPLL_A_PIN_ESYNC_FREQUENCY_SUPPORTED, DPLL_A_PIN_ESYNC_PULSE, + DPLL_A_PIN_REFERENCE_SYNC, __DPLL_A_PIN_MAX, DPLL_A_PIN_MAX = (__DPLL_A_PIN_MAX - 1) diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index b851c36ad25d..c34a81245f87 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -54,6 +54,7 @@ enum { /* Extended flags under NDA_FLAGS_EXT: */ #define NTF_EXT_MANAGED (1 << 0) #define NTF_EXT_LOCKED (1 << 1) +#define NTF_EXT_EXT_VALIDATED (1 << 2) /* * Neighbor Cache Entry States. @@ -92,6 +93,10 @@ enum { * bridge in response to a host trying to communicate via a locked bridge port * with MAB enabled. Their purpose is to notify user space that a host requires * authentication. + * + * NTF_EXT_EXT_VALIDATED flagged neighbor entries were externally validated by + * a user space control plane. The kernel will not remove or invalidate them, + * but it can probe them and notify user space when they become reachable. */ struct nda_cacheinfo { diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 77d9d6af46da..c9751bdfd937 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -135,8 +135,28 @@ #define UBLKSRV_IO_BUF_TOTAL_SIZE (1ULL << UBLKSRV_IO_BUF_TOTAL_BITS) /* - * zero copy requires 4k block size, and can remap ublk driver's io - * request into ublksrv's vm space + * ublk server can register data buffers for incoming I/O requests with a sparse + * io_uring buffer table. The request buffer can then be used as the data buffer + * for io_uring operations via the fixed buffer index. + * Note that the ublk server can never directly access the request data memory. + * + * To use this feature, the ublk server must first register a sparse buffer + * table on an io_uring instance. + * When an incoming ublk request is received, the ublk server submits a + * UBLK_U_IO_REGISTER_IO_BUF command to that io_uring instance. The + * ublksrv_io_cmd's q_id and tag specify the request whose buffer to register + * and addr is the index in the io_uring's buffer table to install the buffer. + * SQEs can now be submitted to the io_uring to read/write the request's buffer + * by enabling fixed buffers (e.g. using IORING_OP_{READ,WRITE}_FIXED or + * IORING_URING_CMD_FIXED) and passing the registered buffer index in buf_index. + * Once the last io_uring operation using the request's buffer has completed, + * the ublk server submits a UBLK_U_IO_UNREGISTER_IO_BUF command with q_id, tag, + * and addr again specifying the request buffer to unregister. + * The ublk request is completed when its buffer is unregistered from all + * io_uring instances and the ublk server issues UBLK_U_IO_COMMIT_AND_FETCH_REQ. + * + * Not available for UBLK_F_UNPRIVILEGED_DEV, as a ublk server can leak + * uninitialized kernel memory by not reading into the full request buffer. */ #define UBLK_F_SUPPORT_ZERO_COPY (1ULL << 0) @@ -450,10 +470,10 @@ static inline struct ublk_auto_buf_reg ublk_sqe_addr_to_auto_buf_reg( __u64 sqe_addr) { struct ublk_auto_buf_reg reg = { - .index = sqe_addr & 0xffff, - .flags = (sqe_addr >> 16) & 0xff, - .reserved0 = (sqe_addr >> 24) & 0xff, - .reserved1 = sqe_addr >> 32, + .index = (__u16)sqe_addr, + .flags = (__u8)(sqe_addr >> 16), + .reserved0 = (__u8)(sqe_addr >> 24), + .reserved1 = (__u32)(sqe_addr >> 32), }; return reg; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 5111ec040c53..73648d26a622 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1666,11 +1666,12 @@ static void io_iopoll_req_issued(struct io_kiocb *req, unsigned int issue_flags) io_req_flags_t io_file_get_flags(struct file *file) { + struct inode *inode = file_inode(file); io_req_flags_t res = 0; BUILD_BUG_ON(REQ_F_ISREG_BIT != REQ_F_SUPPORT_NOWAIT_BIT + 1); - if (S_ISREG(file_inode(file)->i_mode)) + if (S_ISREG(inode->i_mode) && !(inode->i_flags & S_ANON_INODE)) res |= REQ_F_ISREG; if ((file->f_flags & O_NONBLOCK) || (file->f_mode & FMODE_NOWAIT)) res |= REQ_F_SUPPORT_NOWAIT; diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index ce95e3af44a9..f2d2cc319faa 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -271,6 +271,7 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg, if (len > arg->max_len) { len = arg->max_len; if (!(bl->flags & IOBL_INC)) { + arg->partial_map = 1; if (iov != arg->iovs) break; buf->len = len; diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h index 5d83c7adc739..723d0361898e 100644 --- a/io_uring/kbuf.h +++ b/io_uring/kbuf.h @@ -58,7 +58,8 @@ struct buf_sel_arg { size_t max_len; unsigned short nr_iovs; unsigned short mode; - unsigned buf_group; + unsigned short buf_group; + unsigned short partial_map; }; void __user *io_buffer_select(struct io_kiocb *req, size_t *len, diff --git a/io_uring/net.c b/io_uring/net.c index 9550d4c8f866..43a43522f406 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -75,12 +75,17 @@ struct io_sr_msg { u16 flags; /* initialised and used only by !msg send variants */ u16 buf_group; - bool retry; + unsigned short retry_flags; void __user *msg_control; /* used only for send zerocopy */ struct io_kiocb *notif; }; +enum sr_retry_flags { + IO_SR_MSG_RETRY = 1, + IO_SR_MSG_PARTIAL_MAP = 2, +}; + /* * Number of times we'll try and do receives if there's more data. If we * exceed this limit, then add us to the back of the queue and retry from @@ -187,7 +192,7 @@ static inline void io_mshot_prep_retry(struct io_kiocb *req, req->flags &= ~REQ_F_BL_EMPTY; sr->done_io = 0; - sr->retry = false; + sr->retry_flags = 0; sr->len = 0; /* get from the provided buffer */ } @@ -397,7 +402,7 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); sr->done_io = 0; - sr->retry = false; + sr->retry_flags = 0; sr->len = READ_ONCE(sqe->len); sr->flags = READ_ONCE(sqe->ioprio); if (sr->flags & ~SENDMSG_FLAGS) @@ -751,7 +756,7 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); sr->done_io = 0; - sr->retry = false; + sr->retry_flags = 0; if (unlikely(sqe->file_index || sqe->addr2)) return -EINVAL; @@ -823,7 +828,7 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret, cflags |= io_put_kbufs(req, this_ret, io_bundle_nbufs(kmsg, this_ret), issue_flags); - if (sr->retry) + if (sr->retry_flags & IO_SR_MSG_RETRY) cflags = req->cqe.flags | (cflags & CQE_F_MASK); /* bundle with no more immediate buffers, we're done */ if (req->flags & REQ_F_BL_EMPTY) @@ -832,12 +837,12 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret, * If more is available AND it was a full transfer, retry and * append to this one */ - if (!sr->retry && kmsg->msg.msg_inq > 1 && this_ret > 0 && + if (!sr->retry_flags && kmsg->msg.msg_inq > 1 && this_ret > 0 && !iov_iter_count(&kmsg->msg.msg_iter)) { req->cqe.flags = cflags & ~CQE_F_MASK; sr->len = kmsg->msg.msg_inq; sr->done_io += this_ret; - sr->retry = true; + sr->retry_flags |= IO_SR_MSG_RETRY; return false; } } else { @@ -1077,6 +1082,14 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg if (unlikely(ret < 0)) return ret; + if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->vec.iovec) { + kmsg->vec.nr = ret; + kmsg->vec.iovec = arg.iovs; + req->flags |= REQ_F_NEED_CLEANUP; + } + if (arg.partial_map) + sr->retry_flags |= IO_SR_MSG_PARTIAL_MAP; + /* special case 1 vec, can be a fast path */ if (ret == 1) { sr->buf = arg.iovs[0].iov_base; @@ -1085,11 +1098,6 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg } iov_iter_init(&kmsg->msg.msg_iter, ITER_DEST, arg.iovs, ret, arg.out_len); - if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->vec.iovec) { - kmsg->vec.nr = ret; - kmsg->vec.iovec = arg.iovs; - req->flags |= REQ_F_NEED_CLEANUP; - } } else { void __user *buf; @@ -1275,7 +1283,7 @@ int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) int ret; zc->done_io = 0; - zc->retry = false; + zc->retry_flags = 0; if (unlikely(READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3))) return -EINVAL; diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 6e0882b051f9..6de6229207a8 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -216,6 +216,7 @@ const struct io_issue_def io_issue_defs[] = { }, [IORING_OP_FALLOCATE] = { .needs_file = 1, + .hash_reg_file = 1, .prep = io_fallocate_prep, .issue = io_fallocate, }, diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index d724602697e7..f2b31fb68992 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -112,8 +112,11 @@ static void io_release_ubuf(void *priv) struct io_mapped_ubuf *imu = priv; unsigned int i; - for (i = 0; i < imu->nr_bvecs; i++) - unpin_user_page(imu->bvec[i].bv_page); + for (i = 0; i < imu->nr_bvecs; i++) { + struct folio *folio = page_folio(imu->bvec[i].bv_page); + + unpin_user_folio(folio, 1); + } } static struct io_mapped_ubuf *io_alloc_imu(struct io_ring_ctx *ctx, @@ -731,6 +734,7 @@ bool io_check_coalesce_buffer(struct page **page_array, int nr_pages, data->nr_pages_mid = folio_nr_pages(folio); data->folio_shift = folio_shift(folio); + data->first_folio_page_idx = folio_page_idx(folio, page_array[0]); /* * Check if pages are contiguous inside a folio, and all folios have @@ -824,7 +828,11 @@ static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx, if (coalesced) imu->folio_shift = data.folio_shift; refcount_set(&imu->refs, 1); - off = (unsigned long) iov->iov_base & ((1UL << imu->folio_shift) - 1); + + off = (unsigned long)iov->iov_base & ~PAGE_MASK; + if (coalesced) + off += data.first_folio_page_idx << PAGE_SHIFT; + node->buf = imu; ret = 0; @@ -840,8 +848,10 @@ done: if (ret) { if (imu) io_free_imu(ctx, imu); - if (pages) - unpin_user_pages(pages, nr_pages); + if (pages) { + for (i = 0; i < nr_pages; i++) + unpin_user_folio(page_folio(pages[i]), 1); + } io_cache_free(&ctx->node_cache, node); node = ERR_PTR(ret); } @@ -1329,7 +1339,6 @@ static int io_vec_fill_bvec(int ddir, struct iov_iter *iter, { unsigned long folio_size = 1 << imu->folio_shift; unsigned long folio_mask = folio_size - 1; - u64 folio_addr = imu->ubuf & ~folio_mask; struct bio_vec *res_bvec = vec->bvec; size_t total_len = 0; unsigned bvec_idx = 0; @@ -1351,8 +1360,13 @@ static int io_vec_fill_bvec(int ddir, struct iov_iter *iter, if (unlikely(check_add_overflow(total_len, iov_len, &total_len))) return -EOVERFLOW; - /* by using folio address it also accounts for bvec offset */ - offset = buf_addr - folio_addr; + offset = buf_addr - imu->ubuf; + /* + * Only the first bvec can have non zero bv_offset, account it + * here and work with full folios below. + */ + offset += imu->bvec[0].bv_offset; + src_bvec = imu->bvec + (offset >> imu->folio_shift); offset &= folio_mask; diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index 0d2138f16322..25e7e998dcfd 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -49,6 +49,7 @@ struct io_imu_folio_data { unsigned int nr_pages_mid; unsigned int folio_shift; unsigned int nr_folios; + unsigned long first_folio_page_idx; }; bool io_rsrc_cache_init(struct io_ring_ctx *ctx); diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index 797247a34cb7..085eeed8cd50 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -106,8 +106,10 @@ static int io_import_dmabuf(struct io_zcrx_ifq *ifq, for_each_sgtable_dma_sg(mem->sgt, sg, i) total_size += sg_dma_len(sg); - if (total_size < off + len) - return -EINVAL; + if (total_size < off + len) { + ret = -EINVAL; + goto err; + } mem->dmabuf_offset = off; mem->size = len; diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec index e64ce21f9a80..2ee603a98813 100644 --- a/kernel/Kconfig.kexec +++ b/kernel/Kconfig.kexec @@ -134,6 +134,7 @@ config CRASH_DM_CRYPT depends on KEXEC_FILE depends on CRASH_DUMP depends on DM_CRYPT + depends on KEYS help With this option enabled, user space can intereact with /sys/kernel/config/crash_dm_crypt_keys to make the dm crypt keys diff --git a/kernel/events/core.c b/kernel/events/core.c index 1f746469fda5..7281230044d0 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7251,15 +7251,15 @@ static void __perf_pending_disable(struct perf_event *event) * CPU-A CPU-B * * perf_event_disable_inatomic() - * @pending_disable = CPU-A; + * @pending_disable = 1; * irq_work_queue(); * * sched-out - * @pending_disable = -1; + * @pending_disable = 0; * * sched-in * perf_event_disable_inatomic() - * @pending_disable = CPU-B; + * @pending_disable = 1; * irq_work_queue(); // FAILS * * irq_work_run() diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index d2aef87c7e9f..aa9a759e824f 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -441,7 +441,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle, * store that will be enabled on successful return */ if (!handle->size) { /* A, matches D */ - event->pending_disable = smp_processor_id(); + perf_event_disable_inatomic(handle->event); perf_output_wakeup(handle); WRITE_ONCE(rb->aux_nest, 0); goto err_put; @@ -526,7 +526,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) if (wakeup) { if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED) - handle->event->pending_disable = smp_processor_id(); + perf_event_disable_inatomic(handle->event); perf_output_wakeup(handle); } diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index a009c91f7b05..572e3bd0cc94 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1573,6 +1573,39 @@ void ktime_get_raw_ts64(struct timespec64 *ts) } EXPORT_SYMBOL(ktime_get_raw_ts64); +/** + * ktime_get_clock_ts64 - Returns time of a clock in a timespec + * @id: POSIX clock ID of the clock to read + * @ts: Pointer to the timespec64 to be set + * + * The timestamp is invalidated (@ts->sec is set to -1) if the + * clock @id is not available. + */ +void ktime_get_clock_ts64(clockid_t id, struct timespec64 *ts) +{ + /* Invalidate time stamp */ + ts->tv_sec = -1; + ts->tv_nsec = 0; + + switch (id) { + case CLOCK_REALTIME: + ktime_get_real_ts64(ts); + return; + case CLOCK_MONOTONIC: + ktime_get_ts64(ts); + return; + case CLOCK_MONOTONIC_RAW: + ktime_get_raw_ts64(ts); + return; + case CLOCK_AUX ... CLOCK_AUX_LAST: + if (IS_ENABLED(CONFIG_POSIX_AUX_CLOCKS)) + ktime_get_aux_ts64(id, ts); + return; + default: + WARN_ON_ONCE(1); + } +} +EXPORT_SYMBOL_GPL(ktime_get_clock_ts64); /** * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 08141f105c95..3885aadc434d 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1436,13 +1436,6 @@ static void filter_free_subsystem_filters(struct trace_subsystem_dir *dir, INIT_LIST_HEAD(&head->list); - item = kmalloc(sizeof(*item), GFP_KERNEL); - if (!item) - goto free_now; - - item->filter = filter; - list_add_tail(&item->list, &head->list); - list_for_each_entry(file, &tr->events, list) { if (file->system != dir) continue; @@ -1454,6 +1447,13 @@ static void filter_free_subsystem_filters(struct trace_subsystem_dir *dir, event_clear_filter(file); } + item = kmalloc(sizeof(*item), GFP_KERNEL); + if (!item) + goto free_now; + + item->filter = filter; + list_add_tail(&item->list, &head->list); + delay_free_filter(head); return; free_now: diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index d48b80f3f007..3a74d63a959e 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -10,6 +10,7 @@ #include <linux/seq_buf.h> #include <linux/seq_file.h> #include <linux/vmalloc.h> +#include <linux/kmemleak.h> #define ALLOCINFO_FILE_NAME "allocinfo" #define MODULE_ALLOC_TAG_VMAP_SIZE (100000UL * sizeof(struct alloc_tag)) @@ -632,8 +633,13 @@ static int load_module(struct module *mod, struct codetag *start, struct codetag mod->name); return -ENOMEM; } - } + /* + * Avoid a kmemleak false positive. The pointer to the counters is stored + * in the alloc_tag section of the module and cannot be directly accessed. + */ + kmemleak_ignore_percpu(tag->counters); + } return 0; } diff --git a/lib/group_cpus.c b/lib/group_cpus.c index ee272c4cefcc..18d43a406114 100644 --- a/lib/group_cpus.c +++ b/lib/group_cpus.c @@ -352,6 +352,9 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps) int ret = -ENOMEM; struct cpumask *masks = NULL; + if (numgrps == 0) + return NULL; + if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL)) return NULL; @@ -426,8 +429,12 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps) #else /* CONFIG_SMP */ struct cpumask *group_cpus_evenly(unsigned int numgrps) { - struct cpumask *masks = kcalloc(numgrps, sizeof(*masks), GFP_KERNEL); + struct cpumask *masks; + if (numgrps == 0) + return NULL; + + masks = kcalloc(numgrps, sizeof(*masks), GFP_KERNEL); if (!masks) return NULL; diff --git a/lib/raid6/rvv.c b/lib/raid6/rvv.c index f0887344b274..7d82efa5b14f 100644 --- a/lib/raid6/rvv.c +++ b/lib/raid6/rvv.c @@ -26,9 +26,9 @@ static int rvv_has_vector(void) static void raid6_rvv1_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs) { u8 **dptr = (u8 **)ptrs; - unsigned long d; - int z, z0; u8 *p, *q; + unsigned long vl, d; + int z, z0; z0 = disks - 3; /* Highest data disk */ p = dptr[z0 + 1]; /* XOR parity */ @@ -36,8 +36,9 @@ static void raid6_rvv1_gen_syndrome_real(int disks, unsigned long bytes, void ** asm volatile (".option push\n" ".option arch,+v\n" - "vsetvli t0, x0, e8, m1, ta, ma\n" + "vsetvli %0, x0, e8, m1, ta, ma\n" ".option pop\n" + : "=&r" (vl) ); /* v0:wp0, v1:wq0, v2:wd0/w20, v3:w10 */ @@ -99,7 +100,7 @@ static void raid6_rvv1_xor_syndrome_real(int disks, int start, int stop, { u8 **dptr = (u8 **)ptrs; u8 *p, *q; - unsigned long d; + unsigned long vl, d; int z, z0; z0 = stop; /* P/Q right side optimization */ @@ -108,8 +109,9 @@ static void raid6_rvv1_xor_syndrome_real(int disks, int start, int stop, asm volatile (".option push\n" ".option arch,+v\n" - "vsetvli t0, x0, e8, m1, ta, ma\n" + "vsetvli %0, x0, e8, m1, ta, ma\n" ".option pop\n" + : "=&r" (vl) ); /* v0:wp0, v1:wq0, v2:wd0/w20, v3:w10 */ @@ -195,9 +197,9 @@ static void raid6_rvv1_xor_syndrome_real(int disks, int start, int stop, static void raid6_rvv2_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs) { u8 **dptr = (u8 **)ptrs; - unsigned long d; - int z, z0; u8 *p, *q; + unsigned long vl, d; + int z, z0; z0 = disks - 3; /* Highest data disk */ p = dptr[z0 + 1]; /* XOR parity */ @@ -205,8 +207,9 @@ static void raid6_rvv2_gen_syndrome_real(int disks, unsigned long bytes, void ** asm volatile (".option push\n" ".option arch,+v\n" - "vsetvli t0, x0, e8, m1, ta, ma\n" + "vsetvli %0, x0, e8, m1, ta, ma\n" ".option pop\n" + : "=&r" (vl) ); /* @@ -287,7 +290,7 @@ static void raid6_rvv2_xor_syndrome_real(int disks, int start, int stop, { u8 **dptr = (u8 **)ptrs; u8 *p, *q; - unsigned long d; + unsigned long vl, d; int z, z0; z0 = stop; /* P/Q right side optimization */ @@ -296,8 +299,9 @@ static void raid6_rvv2_xor_syndrome_real(int disks, int start, int stop, asm volatile (".option push\n" ".option arch,+v\n" - "vsetvli t0, x0, e8, m1, ta, ma\n" + "vsetvli %0, x0, e8, m1, ta, ma\n" ".option pop\n" + : "=&r" (vl) ); /* @@ -413,9 +417,9 @@ static void raid6_rvv2_xor_syndrome_real(int disks, int start, int stop, static void raid6_rvv4_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs) { u8 **dptr = (u8 **)ptrs; - unsigned long d; - int z, z0; u8 *p, *q; + unsigned long vl, d; + int z, z0; z0 = disks - 3; /* Highest data disk */ p = dptr[z0 + 1]; /* XOR parity */ @@ -423,8 +427,9 @@ static void raid6_rvv4_gen_syndrome_real(int disks, unsigned long bytes, void ** asm volatile (".option push\n" ".option arch,+v\n" - "vsetvli t0, x0, e8, m1, ta, ma\n" + "vsetvli %0, x0, e8, m1, ta, ma\n" ".option pop\n" + : "=&r" (vl) ); /* @@ -539,7 +544,7 @@ static void raid6_rvv4_xor_syndrome_real(int disks, int start, int stop, { u8 **dptr = (u8 **)ptrs; u8 *p, *q; - unsigned long d; + unsigned long vl, d; int z, z0; z0 = stop; /* P/Q right side optimization */ @@ -548,8 +553,9 @@ static void raid6_rvv4_xor_syndrome_real(int disks, int start, int stop, asm volatile (".option push\n" ".option arch,+v\n" - "vsetvli t0, x0, e8, m1, ta, ma\n" + "vsetvli %0, x0, e8, m1, ta, ma\n" ".option pop\n" + : "=&r" (vl) ); /* @@ -721,9 +727,9 @@ static void raid6_rvv4_xor_syndrome_real(int disks, int start, int stop, static void raid6_rvv8_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs) { u8 **dptr = (u8 **)ptrs; - unsigned long d; - int z, z0; u8 *p, *q; + unsigned long vl, d; + int z, z0; z0 = disks - 3; /* Highest data disk */ p = dptr[z0 + 1]; /* XOR parity */ @@ -731,8 +737,9 @@ static void raid6_rvv8_gen_syndrome_real(int disks, unsigned long bytes, void ** asm volatile (".option push\n" ".option arch,+v\n" - "vsetvli t0, x0, e8, m1, ta, ma\n" + "vsetvli %0, x0, e8, m1, ta, ma\n" ".option pop\n" + : "=&r" (vl) ); /* @@ -915,7 +922,7 @@ static void raid6_rvv8_xor_syndrome_real(int disks, int start, int stop, { u8 **dptr = (u8 **)ptrs; u8 *p, *q; - unsigned long d; + unsigned long vl, d; int z, z0; z0 = stop; /* P/Q right side optimization */ @@ -924,8 +931,9 @@ static void raid6_rvv8_xor_syndrome_real(int disks, int start, int stop, asm volatile (".option push\n" ".option arch,+v\n" - "vsetvli t0, x0, e8, m1, ta, ma\n" + "vsetvli %0, x0, e8, m1, ta, ma\n" ".option pop\n" + : "=&r" (vl) ); /* diff --git a/lib/ref_tracker.c b/lib/ref_tracker.c index dcf923a1edf5..a9e6ffcff04b 100644 --- a/lib/ref_tracker.c +++ b/lib/ref_tracker.c @@ -516,13 +516,19 @@ static void debugfs_reap_work(struct work_struct *work) } while (reaped); } -static int __init ref_tracker_debugfs_init(void) +static int __init ref_tracker_debugfs_postcore_init(void) { INIT_WORK(&debugfs_reap_worker, debugfs_reap_work); xa_init_flags(&debugfs_dentries, XA_FLAGS_LOCK_IRQ); xa_init_flags(&debugfs_symlinks, XA_FLAGS_LOCK_IRQ); + return 0; +} +postcore_initcall(ref_tracker_debugfs_postcore_init); + +static int __init ref_tracker_debugfs_late_init(void) +{ ref_tracker_debug_dir = debugfs_create_dir("ref_tracker", NULL); return 0; } -late_initcall(ref_tracker_debugfs_init); +late_initcall(ref_tracker_debugfs_late_init); #endif /* CONFIG_DEBUG_FS */ diff --git a/lib/test_objagg.c b/lib/test_objagg.c index a67b8ef5c5be..ce5c4c36a084 100644 --- a/lib/test_objagg.c +++ b/lib/test_objagg.c @@ -899,8 +899,10 @@ static int check_expect_hints_stats(struct objagg_hints *objagg_hints, int err; stats = objagg_hints_stats_get(objagg_hints); - if (IS_ERR(stats)) + if (IS_ERR(stats)) { + *errmsg = "objagg_hints_stats_get() failed."; return PTR_ERR(stats); + } err = __check_expect_stats(stats, expect_stats, errmsg); objagg_stats_put(stats); return err; diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 0f6c9e1fec0b..30ae7518ffbf 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -472,6 +472,7 @@ static ssize_t memcg_path_store(struct kobject *kobj, return -ENOMEM; strscpy(path, buf, count + 1); + kfree(filter->memcg_path); filter->memcg_path = path; return count; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 8746ed2fec13..9dc95eac558c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2787,20 +2787,24 @@ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, /* * alloc_and_dissolve_hugetlb_folio - Allocate a new folio and dissolve * the old one - * @h: struct hstate old page belongs to * @old_folio: Old folio to dissolve * @list: List to isolate the page in case we need to * Returns 0 on success, otherwise negated error. */ -static int alloc_and_dissolve_hugetlb_folio(struct hstate *h, - struct folio *old_folio, struct list_head *list) +static int alloc_and_dissolve_hugetlb_folio(struct folio *old_folio, + struct list_head *list) { - gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; + gfp_t gfp_mask; + struct hstate *h; int nid = folio_nid(old_folio); struct folio *new_folio = NULL; int ret = 0; retry: + /* + * The old_folio might have been dissolved from under our feet, so make sure + * to carefully check the state under the lock. + */ spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(old_folio)) { /* @@ -2829,8 +2833,10 @@ retry: cond_resched(); goto retry; } else { + h = folio_hstate(old_folio); if (!new_folio) { spin_unlock_irq(&hugetlb_lock); + gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; new_folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, NULL, NULL); if (!new_folio) @@ -2874,35 +2880,24 @@ free_new: int isolate_or_dissolve_huge_folio(struct folio *folio, struct list_head *list) { - struct hstate *h; int ret = -EBUSY; - /* - * The page might have been dissolved from under our feet, so make sure - * to carefully check the state under the lock. - * Return success when racing as if we dissolved the page ourselves. - */ - spin_lock_irq(&hugetlb_lock); - if (folio_test_hugetlb(folio)) { - h = folio_hstate(folio); - } else { - spin_unlock_irq(&hugetlb_lock); + /* Not to disrupt normal path by vainly holding hugetlb_lock */ + if (!folio_test_hugetlb(folio)) return 0; - } - spin_unlock_irq(&hugetlb_lock); /* * Fence off gigantic pages as there is a cyclic dependency between * alloc_contig_range and them. Return -ENOMEM as this has the effect * of bailing out right away without further retrying. */ - if (hstate_is_gigantic(h)) + if (folio_order(folio) > MAX_PAGE_ORDER) return -ENOMEM; if (folio_ref_count(folio) && folio_isolate_hugetlb(folio, list)) ret = 0; else if (!folio_ref_count(folio)) - ret = alloc_and_dissolve_hugetlb_folio(h, folio, list); + ret = alloc_and_dissolve_hugetlb_folio(folio, list); return ret; } @@ -2916,7 +2911,6 @@ int isolate_or_dissolve_huge_folio(struct folio *folio, struct list_head *list) */ int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn) { - struct hstate *h; struct folio *folio; int ret = 0; @@ -2925,23 +2919,9 @@ int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn) while (start_pfn < end_pfn) { folio = pfn_folio(start_pfn); - /* - * The folio might have been dissolved from under our feet, so make sure - * to carefully check the state under the lock. - */ - spin_lock_irq(&hugetlb_lock); - if (folio_test_hugetlb(folio)) { - h = folio_hstate(folio); - } else { - spin_unlock_irq(&hugetlb_lock); - start_pfn++; - continue; - } - spin_unlock_irq(&hugetlb_lock); - - if (!folio_ref_count(folio)) { - ret = alloc_and_dissolve_hugetlb_folio(h, folio, - &isolate_list); + /* Not to disrupt normal path by vainly holding hugetlb_lock */ + if (folio_test_hugetlb(folio) && !folio_ref_count(folio)) { + ret = alloc_and_dissolve_hugetlb_folio(folio, &isolate_list); if (ret) break; diff --git a/mm/kmemleak.c b/mm/kmemleak.c index da9cee34ee1b..8d588e685311 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1247,6 +1247,20 @@ void __ref kmemleak_transient_leak(const void *ptr) EXPORT_SYMBOL(kmemleak_transient_leak); /** + * kmemleak_ignore_percpu - similar to kmemleak_ignore but taking a percpu + * address argument + * @ptr: percpu address of the object + */ +void __ref kmemleak_ignore_percpu(const void __percpu *ptr) +{ + pr_debug("%s(0x%px)\n", __func__, ptr); + + if (kmemleak_enabled && ptr && !IS_ERR_PCPU(ptr)) + make_black_object((unsigned long)ptr, OBJECT_PERCPU); +} +EXPORT_SYMBOL_GPL(kmemleak_ignore_percpu); + +/** * kmemleak_ignore - ignore an allocated object * @ptr: pointer to beginning of the object * diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 66052d6aaa1d..4d5ace9d245d 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -2150,40 +2150,6 @@ static u8 hci_cc_set_adv_param(struct hci_dev *hdev, void *data, return rp->status; } -static u8 hci_cc_set_ext_adv_param(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_rp_le_set_ext_adv_params *rp = data; - struct hci_cp_le_set_ext_adv_params *cp; - struct adv_info *adv_instance; - - bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); - - if (rp->status) - return rp->status; - - cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_EXT_ADV_PARAMS); - if (!cp) - return rp->status; - - hci_dev_lock(hdev); - hdev->adv_addr_type = cp->own_addr_type; - if (!cp->handle) { - /* Store in hdev for instance 0 */ - hdev->adv_tx_power = rp->tx_power; - } else { - adv_instance = hci_find_adv_instance(hdev, cp->handle); - if (adv_instance) - adv_instance->tx_power = rp->tx_power; - } - /* Update adv data as tx power is known now */ - hci_update_adv_data(hdev, cp->handle); - - hci_dev_unlock(hdev); - - return rp->status; -} - static u8 hci_cc_read_rssi(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -4164,8 +4130,6 @@ static const struct hci_cc { HCI_CC(HCI_OP_LE_READ_NUM_SUPPORTED_ADV_SETS, hci_cc_le_read_num_adv_sets, sizeof(struct hci_rp_le_read_num_supported_adv_sets)), - HCI_CC(HCI_OP_LE_SET_EXT_ADV_PARAMS, hci_cc_set_ext_adv_param, - sizeof(struct hci_rp_le_set_ext_adv_params)), HCI_CC_STATUS(HCI_OP_LE_SET_EXT_ADV_ENABLE, hci_cc_le_set_ext_adv_enable), HCI_CC_STATUS(HCI_OP_LE_SET_ADV_SET_RAND_ADDR, diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 6687f2a4d1eb..77b3691f3423 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -1205,9 +1205,126 @@ static int hci_set_adv_set_random_addr_sync(struct hci_dev *hdev, u8 instance, sizeof(cp), &cp, HCI_CMD_TIMEOUT); } +static int +hci_set_ext_adv_params_sync(struct hci_dev *hdev, struct adv_info *adv, + const struct hci_cp_le_set_ext_adv_params *cp, + struct hci_rp_le_set_ext_adv_params *rp) +{ + struct sk_buff *skb; + + skb = __hci_cmd_sync(hdev, HCI_OP_LE_SET_EXT_ADV_PARAMS, sizeof(*cp), + cp, HCI_CMD_TIMEOUT); + + /* If command return a status event, skb will be set to -ENODATA */ + if (skb == ERR_PTR(-ENODATA)) + return 0; + + if (IS_ERR(skb)) { + bt_dev_err(hdev, "Opcode 0x%4.4x failed: %ld", + HCI_OP_LE_SET_EXT_ADV_PARAMS, PTR_ERR(skb)); + return PTR_ERR(skb); + } + + if (skb->len != sizeof(*rp)) { + bt_dev_err(hdev, "Invalid response length for 0x%4.4x: %u", + HCI_OP_LE_SET_EXT_ADV_PARAMS, skb->len); + kfree_skb(skb); + return -EIO; + } + + memcpy(rp, skb->data, sizeof(*rp)); + kfree_skb(skb); + + if (!rp->status) { + hdev->adv_addr_type = cp->own_addr_type; + if (!cp->handle) { + /* Store in hdev for instance 0 */ + hdev->adv_tx_power = rp->tx_power; + } else if (adv) { + adv->tx_power = rp->tx_power; + } + } + + return rp->status; +} + +static int hci_set_ext_adv_data_sync(struct hci_dev *hdev, u8 instance) +{ + DEFINE_FLEX(struct hci_cp_le_set_ext_adv_data, pdu, data, length, + HCI_MAX_EXT_AD_LENGTH); + u8 len; + struct adv_info *adv = NULL; + int err; + + if (instance) { + adv = hci_find_adv_instance(hdev, instance); + if (!adv || !adv->adv_data_changed) + return 0; + } + + len = eir_create_adv_data(hdev, instance, pdu->data, + HCI_MAX_EXT_AD_LENGTH); + + pdu->length = len; + pdu->handle = adv ? adv->handle : instance; + pdu->operation = LE_SET_ADV_DATA_OP_COMPLETE; + pdu->frag_pref = LE_SET_ADV_DATA_NO_FRAG; + + err = __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EXT_ADV_DATA, + struct_size(pdu, data, len), pdu, + HCI_CMD_TIMEOUT); + if (err) + return err; + + /* Update data if the command succeed */ + if (adv) { + adv->adv_data_changed = false; + } else { + memcpy(hdev->adv_data, pdu->data, len); + hdev->adv_data_len = len; + } + + return 0; +} + +static int hci_set_adv_data_sync(struct hci_dev *hdev, u8 instance) +{ + struct hci_cp_le_set_adv_data cp; + u8 len; + + memset(&cp, 0, sizeof(cp)); + + len = eir_create_adv_data(hdev, instance, cp.data, sizeof(cp.data)); + + /* There's nothing to do if the data hasn't changed */ + if (hdev->adv_data_len == len && + memcmp(cp.data, hdev->adv_data, len) == 0) + return 0; + + memcpy(hdev->adv_data, cp.data, sizeof(cp.data)); + hdev->adv_data_len = len; + + cp.length = len; + + return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_ADV_DATA, + sizeof(cp), &cp, HCI_CMD_TIMEOUT); +} + +int hci_update_adv_data_sync(struct hci_dev *hdev, u8 instance) +{ + if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) + return 0; + + if (ext_adv_capable(hdev)) + return hci_set_ext_adv_data_sync(hdev, instance); + + return hci_set_adv_data_sync(hdev, instance); +} + int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance) { struct hci_cp_le_set_ext_adv_params cp; + struct hci_rp_le_set_ext_adv_params rp; bool connectable; u32 flags; bdaddr_t random_addr; @@ -1316,8 +1433,12 @@ int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance) cp.secondary_phy = HCI_ADV_PHY_1M; } - err = __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EXT_ADV_PARAMS, - sizeof(cp), &cp, HCI_CMD_TIMEOUT); + err = hci_set_ext_adv_params_sync(hdev, adv, &cp, &rp); + if (err) + return err; + + /* Update adv data as tx power is known now */ + err = hci_set_ext_adv_data_sync(hdev, cp.handle); if (err) return err; @@ -1822,79 +1943,6 @@ int hci_le_terminate_big_sync(struct hci_dev *hdev, u8 handle, u8 reason) sizeof(cp), &cp, HCI_CMD_TIMEOUT); } -static int hci_set_ext_adv_data_sync(struct hci_dev *hdev, u8 instance) -{ - DEFINE_FLEX(struct hci_cp_le_set_ext_adv_data, pdu, data, length, - HCI_MAX_EXT_AD_LENGTH); - u8 len; - struct adv_info *adv = NULL; - int err; - - if (instance) { - adv = hci_find_adv_instance(hdev, instance); - if (!adv || !adv->adv_data_changed) - return 0; - } - - len = eir_create_adv_data(hdev, instance, pdu->data, - HCI_MAX_EXT_AD_LENGTH); - - pdu->length = len; - pdu->handle = adv ? adv->handle : instance; - pdu->operation = LE_SET_ADV_DATA_OP_COMPLETE; - pdu->frag_pref = LE_SET_ADV_DATA_NO_FRAG; - - err = __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EXT_ADV_DATA, - struct_size(pdu, data, len), pdu, - HCI_CMD_TIMEOUT); - if (err) - return err; - - /* Update data if the command succeed */ - if (adv) { - adv->adv_data_changed = false; - } else { - memcpy(hdev->adv_data, pdu->data, len); - hdev->adv_data_len = len; - } - - return 0; -} - -static int hci_set_adv_data_sync(struct hci_dev *hdev, u8 instance) -{ - struct hci_cp_le_set_adv_data cp; - u8 len; - - memset(&cp, 0, sizeof(cp)); - - len = eir_create_adv_data(hdev, instance, cp.data, sizeof(cp.data)); - - /* There's nothing to do if the data hasn't changed */ - if (hdev->adv_data_len == len && - memcmp(cp.data, hdev->adv_data, len) == 0) - return 0; - - memcpy(hdev->adv_data, cp.data, sizeof(cp.data)); - hdev->adv_data_len = len; - - cp.length = len; - - return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_ADV_DATA, - sizeof(cp), &cp, HCI_CMD_TIMEOUT); -} - -int hci_update_adv_data_sync(struct hci_dev *hdev, u8 instance) -{ - if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) - return 0; - - if (ext_adv_capable(hdev)) - return hci_set_ext_adv_data_sync(hdev, instance); - - return hci_set_adv_data_sync(hdev, instance); -} - int hci_schedule_adv_instance_sync(struct hci_dev *hdev, u8 instance, bool force) { @@ -1970,13 +2018,10 @@ static int hci_clear_adv_sets_sync(struct hci_dev *hdev, struct sock *sk) static int hci_clear_adv_sync(struct hci_dev *hdev, struct sock *sk, bool force) { struct adv_info *adv, *n; - int err = 0; if (ext_adv_capable(hdev)) /* Remove all existing sets */ - err = hci_clear_adv_sets_sync(hdev, sk); - if (ext_adv_capable(hdev)) - return err; + return hci_clear_adv_sets_sync(hdev, sk); /* This is safe as long as there is no command send while the lock is * held. @@ -2004,13 +2049,11 @@ static int hci_clear_adv_sync(struct hci_dev *hdev, struct sock *sk, bool force) static int hci_remove_adv_sync(struct hci_dev *hdev, u8 instance, struct sock *sk) { - int err = 0; + int err; /* If we use extended advertising, instance has to be removed first. */ if (ext_adv_capable(hdev)) - err = hci_remove_ext_adv_instance_sync(hdev, instance, sk); - if (ext_adv_capable(hdev)) - return err; + return hci_remove_ext_adv_instance_sync(hdev, instance, sk); /* This is safe as long as there is no command send while the lock is * held. @@ -2109,16 +2152,13 @@ int hci_read_tx_power_sync(struct hci_dev *hdev, __le16 handle, u8 type) int hci_disable_advertising_sync(struct hci_dev *hdev) { u8 enable = 0x00; - int err = 0; /* If controller is not advertising we are done. */ if (!hci_dev_test_flag(hdev, HCI_LE_ADV)) return 0; if (ext_adv_capable(hdev)) - err = hci_disable_ext_adv_instance_sync(hdev, 0x00); - if (ext_adv_capable(hdev)) - return err; + return hci_disable_ext_adv_instance_sync(hdev, 0x00); return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable, HCI_CMD_TIMEOUT); @@ -2481,6 +2521,10 @@ static int hci_pause_advertising_sync(struct hci_dev *hdev) int err; int old_state; + /* If controller is not advertising we are done. */ + if (!hci_dev_test_flag(hdev, HCI_LE_ADV)) + return 0; + /* If already been paused there is nothing to do. */ if (hdev->advertising_paused) return 0; @@ -6277,6 +6321,7 @@ static int hci_le_ext_directed_advertising_sync(struct hci_dev *hdev, struct hci_conn *conn) { struct hci_cp_le_set_ext_adv_params cp; + struct hci_rp_le_set_ext_adv_params rp; int err; bdaddr_t random_addr; u8 own_addr_type; @@ -6318,8 +6363,12 @@ static int hci_le_ext_directed_advertising_sync(struct hci_dev *hdev, if (err) return err; - err = __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EXT_ADV_PARAMS, - sizeof(cp), &cp, HCI_CMD_TIMEOUT); + err = hci_set_ext_adv_params_sync(hdev, NULL, &cp, &rp); + if (err) + return err; + + /* Update adv data as tx power is known now */ + err = hci_set_ext_adv_data_sync(hdev, cp.handle); if (err) return err; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index d540f7b4f75f..1485b455ade4 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -1080,7 +1080,8 @@ static int mesh_send_done_sync(struct hci_dev *hdev, void *data) struct mgmt_mesh_tx *mesh_tx; hci_dev_clear_flag(hdev, HCI_MESH_SENDING); - hci_disable_advertising_sync(hdev); + if (list_empty(&hdev->adv_instances)) + hci_disable_advertising_sync(hdev); mesh_tx = mgmt_mesh_next(hdev, NULL); if (mesh_tx) @@ -2153,6 +2154,9 @@ static int set_mesh_sync(struct hci_dev *hdev, void *data) else hci_dev_clear_flag(hdev, HCI_MESH); + hdev->le_scan_interval = __le16_to_cpu(cp->period); + hdev->le_scan_window = __le16_to_cpu(cp->window); + len -= sizeof(*cp); /* If filters don't fit, forward all adv pkts */ @@ -2167,6 +2171,7 @@ static int set_mesh(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_cp_set_mesh *cp = data; struct mgmt_pending_cmd *cmd; + __u16 period, window; int err = 0; bt_dev_dbg(hdev, "sock %p", sk); @@ -2180,6 +2185,23 @@ static int set_mesh(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_MESH_RECEIVER, MGMT_STATUS_INVALID_PARAMS); + /* Keep allowed ranges in sync with set_scan_params() */ + period = __le16_to_cpu(cp->period); + + if (period < 0x0004 || period > 0x4000) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_MESH_RECEIVER, + MGMT_STATUS_INVALID_PARAMS); + + window = __le16_to_cpu(cp->window); + + if (window < 0x0004 || window > 0x4000) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_MESH_RECEIVER, + MGMT_STATUS_INVALID_PARAMS); + + if (window > period) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_MESH_RECEIVER, + MGMT_STATUS_INVALID_PARAMS); + hci_dev_lock(hdev); cmd = mgmt_pending_add(sk, MGMT_OP_SET_MESH_RECEIVER, hdev, data, len); @@ -6432,6 +6454,7 @@ static int set_scan_params(struct sock *sk, struct hci_dev *hdev, return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS, MGMT_STATUS_NOT_SUPPORTED); + /* Keep allowed ranges in sync with set_mesh() */ interval = __le16_to_cpu(cp->interval); if (interval < 0x0004 || interval > 0x4000) diff --git a/net/core/dev.c b/net/core/dev.c index 7ee808eb068e..96d33dead604 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5937,8 +5937,6 @@ check_vlan_id: } if (pt_prev) { - if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) - goto drop; *ppt_prev = pt_prev; } else { drop: diff --git a/net/core/dst.c b/net/core/dst.c index 795ca07e28a4..e2de8b68c41d 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -145,12 +145,12 @@ void dst_dev_put(struct dst_entry *dst) { struct net_device *dev = dst->dev; - dst->obsolete = DST_OBSOLETE_DEAD; + WRITE_ONCE(dst->obsolete, DST_OBSOLETE_DEAD); if (dst->ops->ifdown) dst->ops->ifdown(dst, dev); - dst->input = dst_discard; - dst->output = dst_discard_out; - dst->dev = blackhole_netdev; + WRITE_ONCE(dst->input, dst_discard); + WRITE_ONCE(dst->output, dst_discard_out); + WRITE_ONCE(dst->dev, blackhole_netdev); netdev_ref_replace(dev, blackhole_netdev, &dst->dev_tracker, GFP_ATOMIC); } @@ -263,7 +263,7 @@ unsigned int dst_blackhole_mtu(const struct dst_entry *dst) { unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); - return mtu ? : dst->dev->mtu; + return mtu ? : dst_dev(dst)->mtu; } EXPORT_SYMBOL_GPL(dst_blackhole_mtu); diff --git a/net/core/dst_cache.c b/net/core/dst_cache.c index 93a04d18e505..9ab4902324e1 100644 --- a/net/core/dst_cache.c +++ b/net/core/dst_cache.c @@ -52,7 +52,7 @@ static struct dst_entry *dst_cache_per_cpu_get(struct dst_cache *dst_cache, if (unlikely(!time_after(idst->refresh_ts, READ_ONCE(dst_cache->reset_ts)) || - (dst->obsolete && !dst->ops->check(dst, idst->cookie)))) { + (READ_ONCE(dst->obsolete) && !dst->ops->check(dst, idst->cookie)))) { dst_cache_per_cpu_dst_set(idst, NULL, 0); dst_release(dst); goto fail; diff --git a/net/core/hotdata.c b/net/core/hotdata.c index 0bc893d5f07b..95d0a4df1006 100644 --- a/net/core/hotdata.c +++ b/net/core/hotdata.c @@ -2,7 +2,9 @@ #include <linux/cache.h> #include <linux/jiffies.h> #include <linux/list.h> +#include <net/aligned_data.h> #include <net/hotdata.h> +#include <net/ip.h> #include <net/proto_memory.h> struct net_hotdata net_hotdata __cacheline_aligned = { @@ -22,3 +24,6 @@ struct net_hotdata net_hotdata __cacheline_aligned = { .sysctl_mem_pcpu_rsv = SK_MEMORY_PCPU_RESERVE }; EXPORT_SYMBOL(net_hotdata); + +struct net_aligned_data net_aligned_data; +EXPORT_IPV6_MOD(net_aligned_data); diff --git a/net/core/ieee8021q_helpers.c b/net/core/ieee8021q_helpers.c index 759a9b9f3f89..669b357b73b2 100644 --- a/net/core/ieee8021q_helpers.c +++ b/net/core/ieee8021q_helpers.c @@ -7,6 +7,11 @@ #include <net/dscp.h> #include <net/ieee8021q.h> +/* verify that table covers all 8 traffic types */ +#define TT_MAP_SIZE_OK(tbl) \ + compiletime_assert(ARRAY_SIZE(tbl) == IEEE8021Q_TT_MAX, \ + #tbl " size mismatch") + /* The following arrays map Traffic Types (TT) to traffic classes (TC) for * different number of queues as shown in the example provided by * IEEE 802.1Q-2022 in Annex I "I.3 Traffic type to traffic class mapping" and @@ -101,51 +106,28 @@ int ieee8021q_tt_to_tc(enum ieee8021q_traffic_type tt, unsigned int num_queues) switch (num_queues) { case 8: - compiletime_assert(ARRAY_SIZE(ieee8021q_8queue_tt_tc_map) != - IEEE8021Q_TT_MAX - 1, - "ieee8021q_8queue_tt_tc_map != max - 1"); + TT_MAP_SIZE_OK(ieee8021q_8queue_tt_tc_map); return ieee8021q_8queue_tt_tc_map[tt]; case 7: - compiletime_assert(ARRAY_SIZE(ieee8021q_7queue_tt_tc_map) != - IEEE8021Q_TT_MAX - 1, - "ieee8021q_7queue_tt_tc_map != max - 1"); - + TT_MAP_SIZE_OK(ieee8021q_7queue_tt_tc_map); return ieee8021q_7queue_tt_tc_map[tt]; case 6: - compiletime_assert(ARRAY_SIZE(ieee8021q_6queue_tt_tc_map) != - IEEE8021Q_TT_MAX - 1, - "ieee8021q_6queue_tt_tc_map != max - 1"); - + TT_MAP_SIZE_OK(ieee8021q_6queue_tt_tc_map); return ieee8021q_6queue_tt_tc_map[tt]; case 5: - compiletime_assert(ARRAY_SIZE(ieee8021q_5queue_tt_tc_map) != - IEEE8021Q_TT_MAX - 1, - "ieee8021q_5queue_tt_tc_map != max - 1"); - + TT_MAP_SIZE_OK(ieee8021q_5queue_tt_tc_map); return ieee8021q_5queue_tt_tc_map[tt]; case 4: - compiletime_assert(ARRAY_SIZE(ieee8021q_4queue_tt_tc_map) != - IEEE8021Q_TT_MAX - 1, - "ieee8021q_4queue_tt_tc_map != max - 1"); - + TT_MAP_SIZE_OK(ieee8021q_4queue_tt_tc_map); return ieee8021q_4queue_tt_tc_map[tt]; case 3: - compiletime_assert(ARRAY_SIZE(ieee8021q_3queue_tt_tc_map) != - IEEE8021Q_TT_MAX - 1, - "ieee8021q_3queue_tt_tc_map != max - 1"); - + TT_MAP_SIZE_OK(ieee8021q_3queue_tt_tc_map); return ieee8021q_3queue_tt_tc_map[tt]; case 2: - compiletime_assert(ARRAY_SIZE(ieee8021q_2queue_tt_tc_map) != - IEEE8021Q_TT_MAX - 1, - "ieee8021q_2queue_tt_tc_map != max - 1"); - + TT_MAP_SIZE_OK(ieee8021q_2queue_tt_tc_map); return ieee8021q_2queue_tt_tc_map[tt]; case 1: - compiletime_assert(ARRAY_SIZE(ieee8021q_1queue_tt_tc_map) != - IEEE8021Q_TT_MAX - 1, - "ieee8021q_1queue_tt_tc_map != max - 1"); - + TT_MAP_SIZE_OK(ieee8021q_1queue_tt_tc_map); return ieee8021q_1queue_tt_tc_map[tt]; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 8ad9898f8e42..d1de7f292eea 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -154,11 +154,12 @@ static void neigh_update_gc_list(struct neighbour *n) if (n->dead) goto out; - /* remove from the gc list if new state is permanent or if neighbor - * is externally learned; otherwise entry should be on the gc list + /* remove from the gc list if new state is permanent or if neighbor is + * externally learned / validated; otherwise entry should be on the gc + * list */ exempt_from_gc = n->nud_state & NUD_PERMANENT || - n->flags & NTF_EXT_LEARNED; + n->flags & (NTF_EXT_LEARNED | NTF_EXT_VALIDATED); on_gc_list = !list_empty(&n->gc_list); if (exempt_from_gc && on_gc_list) { @@ -205,6 +206,7 @@ static void neigh_update_flags(struct neighbour *neigh, u32 flags, int *notify, ndm_flags = (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0; ndm_flags |= (flags & NEIGH_UPDATE_F_MANAGED) ? NTF_MANAGED : 0; + ndm_flags |= (flags & NEIGH_UPDATE_F_EXT_VALIDATED) ? NTF_EXT_VALIDATED : 0; if ((old_flags ^ ndm_flags) & NTF_EXT_LEARNED) { if (ndm_flags & NTF_EXT_LEARNED) @@ -222,6 +224,14 @@ static void neigh_update_flags(struct neighbour *neigh, u32 flags, int *notify, *notify = 1; *managed_update = true; } + if ((old_flags ^ ndm_flags) & NTF_EXT_VALIDATED) { + if (ndm_flags & NTF_EXT_VALIDATED) + neigh->flags |= NTF_EXT_VALIDATED; + else + neigh->flags &= ~NTF_EXT_VALIDATED; + *notify = 1; + *gc_update = true; + } } bool neigh_remove_one(struct neighbour *n) @@ -379,7 +389,9 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev, dev_head = neigh_get_dev_table(dev, tbl->family); hlist_for_each_entry_safe(n, tmp, dev_head, dev_list) { - if (skip_perm && n->nud_state & NUD_PERMANENT) + if (skip_perm && + (n->nud_state & NUD_PERMANENT || + n->flags & NTF_EXT_VALIDATED)) continue; hlist_del_rcu(&n->hash); @@ -942,7 +954,8 @@ static void neigh_periodic_work(struct work_struct *work) state = n->nud_state; if ((state & (NUD_PERMANENT | NUD_IN_TIMER)) || - (n->flags & NTF_EXT_LEARNED)) { + (n->flags & + (NTF_EXT_LEARNED | NTF_EXT_VALIDATED))) { write_unlock(&n->lock); continue; } @@ -1095,9 +1108,15 @@ static void neigh_timer_handler(struct timer_list *t) if ((neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) && atomic_read(&neigh->probes) >= neigh_max_probes(neigh)) { - WRITE_ONCE(neigh->nud_state, NUD_FAILED); + if (neigh->nud_state == NUD_PROBE && + neigh->flags & NTF_EXT_VALIDATED) { + WRITE_ONCE(neigh->nud_state, NUD_STALE); + neigh->updated = jiffies; + } else { + WRITE_ONCE(neigh->nud_state, NUD_FAILED); + neigh_invalidate(neigh); + } notify = 1; - neigh_invalidate(neigh); goto out; } @@ -1245,6 +1264,8 @@ static void neigh_update_hhs(struct neighbour *neigh) NTF_ROUTER flag. NEIGH_UPDATE_F_ISROUTER indicates if the neighbour is known as a router. + NEIGH_UPDATE_F_EXT_VALIDATED means that the entry will not be removed + or invalidated. Caller MUST hold reference count on the entry. */ @@ -1407,7 +1428,8 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, * we can reinject the packet there. */ n2 = NULL; - if (dst && dst->obsolete != DST_OBSOLETE_DEAD) { + if (dst && + READ_ONCE(dst->obsolete) != DST_OBSOLETE_DEAD) { n2 = dst_neigh_lookup_skb(dst, skb); if (n2) n1 = n2; @@ -1979,7 +2001,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (ndm_flags & NTF_PROXY) { struct pneigh_entry *pn; - if (ndm_flags & NTF_MANAGED) { + if (ndm_flags & (NTF_MANAGED | NTF_EXT_VALIDATED)) { NL_SET_ERR_MSG(extack, "Invalid NTF_* flag combination"); goto out; } @@ -2010,7 +2032,8 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (neigh == NULL) { bool ndm_permanent = ndm->ndm_state & NUD_PERMANENT; bool exempt_from_gc = ndm_permanent || - ndm_flags & NTF_EXT_LEARNED; + ndm_flags & (NTF_EXT_LEARNED | + NTF_EXT_VALIDATED); if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { err = -ENOENT; @@ -2021,10 +2044,27 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, err = -EINVAL; goto out; } + if (ndm_flags & NTF_EXT_VALIDATED) { + u8 state = ndm->ndm_state; + + /* NTF_USE and NTF_MANAGED will result in the neighbor + * being created with an invalid state (NUD_NONE). + */ + if (ndm_flags & (NTF_USE | NTF_MANAGED)) + state = NUD_NONE; + + if (!(state & NUD_VALID)) { + NL_SET_ERR_MSG(extack, + "Cannot create externally validated neighbor with an invalid state"); + err = -EINVAL; + goto out; + } + } neigh = ___neigh_create(tbl, dst, dev, ndm_flags & - (NTF_EXT_LEARNED | NTF_MANAGED), + (NTF_EXT_LEARNED | NTF_MANAGED | + NTF_EXT_VALIDATED), exempt_from_gc, true); if (IS_ERR(neigh)) { err = PTR_ERR(neigh); @@ -2036,6 +2076,24 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, neigh_release(neigh); goto out; } + if (ndm_flags & NTF_EXT_VALIDATED) { + u8 state = ndm->ndm_state; + + /* NTF_USE and NTF_MANAGED do not update the existing + * state other than clearing it if it was + * NUD_PERMANENT. + */ + if (ndm_flags & (NTF_USE | NTF_MANAGED)) + state = READ_ONCE(neigh->nud_state) & ~NUD_PERMANENT; + + if (!(state & NUD_VALID)) { + NL_SET_ERR_MSG(extack, + "Cannot mark neighbor as externally validated with an invalid state"); + err = -EINVAL; + neigh_release(neigh); + goto out; + } + } if (!(nlh->nlmsg_flags & NLM_F_REPLACE)) flags &= ~(NEIGH_UPDATE_F_OVERRIDE | @@ -2052,6 +2110,8 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, flags |= NEIGH_UPDATE_F_MANAGED; if (ndm_flags & NTF_USE) flags |= NEIGH_UPDATE_F_USE; + if (ndm_flags & NTF_EXT_VALIDATED) + flags |= NEIGH_UPDATE_F_EXT_VALIDATED; err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags, NETLINK_CB(skb).portid, extack); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index d0f607507ee8..f58ef920a3a1 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -19,9 +19,9 @@ #include <linux/net_namespace.h> #include <linux/sched/task.h> #include <linux/uidgid.h> -#include <linux/cookie.h> #include <linux/proc_fs.h> +#include <net/aligned_data.h> #include <net/sock.h> #include <net/netlink.h> #include <net/net_namespace.h> @@ -64,8 +64,6 @@ DECLARE_RWSEM(pernet_ops_rwsem); static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS; -DEFINE_COOKIE(net_cookie); - static struct net_generic *net_alloc_generic(void) { unsigned int gen_ptrs = READ_ONCE(max_gen_ptrs); @@ -319,10 +317,10 @@ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp) if (refcount_read(&net->ns.count) == 0) return NETNSA_NSID_NOT_ASSIGNED; - spin_lock_bh(&net->nsid_lock); + spin_lock(&net->nsid_lock); id = __peernet2id(net, peer); if (id >= 0) { - spin_unlock_bh(&net->nsid_lock); + spin_unlock(&net->nsid_lock); return id; } @@ -332,12 +330,12 @@ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp) * just been idr_remove()'d from there in cleanup_net(). */ if (!maybe_get_net(peer)) { - spin_unlock_bh(&net->nsid_lock); + spin_unlock(&net->nsid_lock); return NETNSA_NSID_NOT_ASSIGNED; } id = alloc_netid(net, peer, -1); - spin_unlock_bh(&net->nsid_lock); + spin_unlock(&net->nsid_lock); put_net(peer); if (id < 0) @@ -434,9 +432,7 @@ static __net_init int setup_net(struct net *net) LIST_HEAD(net_exit_list); int error = 0; - preempt_disable(); - net->net_cookie = gen_cookie_next(&net_cookie); - preempt_enable(); + net->net_cookie = atomic64_inc_return(&net_aligned_data.net_cookie); list_for_each_entry(ops, &pernet_list, list) { error = ops_init(ops, net); @@ -628,20 +624,20 @@ static void unhash_nsid(struct net *net, struct net *last) for_each_net(tmp) { int id; - spin_lock_bh(&tmp->nsid_lock); + spin_lock(&tmp->nsid_lock); id = __peernet2id(tmp, net); if (id >= 0) idr_remove(&tmp->netns_ids, id); - spin_unlock_bh(&tmp->nsid_lock); + spin_unlock(&tmp->nsid_lock); if (id >= 0) rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL, GFP_KERNEL); if (tmp == last) break; } - spin_lock_bh(&net->nsid_lock); + spin_lock(&net->nsid_lock); idr_destroy(&net->netns_ids); - spin_unlock_bh(&net->nsid_lock); + spin_unlock(&net->nsid_lock); } static LLIST_HEAD(cleanup_list); @@ -880,9 +876,9 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, return PTR_ERR(peer); } - spin_lock_bh(&net->nsid_lock); + spin_lock(&net->nsid_lock); if (__peernet2id(net, peer) >= 0) { - spin_unlock_bh(&net->nsid_lock); + spin_unlock(&net->nsid_lock); err = -EEXIST; NL_SET_BAD_ATTR(extack, nla); NL_SET_ERR_MSG(extack, @@ -891,7 +887,7 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, } err = alloc_netid(net, peer, nsid); - spin_unlock_bh(&net->nsid_lock); + spin_unlock(&net->nsid_lock); if (err >= 0) { rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid, nlh, GFP_KERNEL); diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index d22f0919821e..dff66d8fb325 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -21,7 +21,9 @@ static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state struct cgroup_cls_state *task_cls_state(struct task_struct *p) { return css_cls_state(task_css_check(p, net_cls_cgrp_id, - rcu_read_lock_bh_held())); + rcu_read_lock_held() || + rcu_read_lock_bh_held() || + rcu_read_lock_trace_held())); } EXPORT_SYMBOL_GPL(task_cls_state); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index c57692eb8da9..a9555bfc372f 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1026,9 +1026,11 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, .rta_error = error, .rta_id = id, }; + unsigned long delta; if (dst) { - ci.rta_lastuse = jiffies_delta_to_clock_t(jiffies - dst->lastuse); + delta = jiffies - READ_ONCE(dst->lastuse); + ci.rta_lastuse = jiffies_delta_to_clock_t(delta); ci.rta_used = dst->__use; ci.rta_clntref = rcuref_read(&dst->__rcuref); } diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 34c51eb1a14f..83c78379932e 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -656,6 +656,13 @@ static void sk_psock_backlog(struct work_struct *work) bool ingress; int ret; + /* If sk is quickly removed from the map and then added back, the old + * psock should not be scheduled, because there are now two psocks + * pointing to the same sk. + */ + if (!sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + return; + /* Increment the psock refcnt to synchronize with close(fd) path in * sock_map_close(), ensuring we wait for backlog thread completion * before sk_socket freed. If refcnt increment fails, it indicates diff --git a/net/core/sock.c b/net/core/sock.c index 3a71d6c4ccf0..8b7623c7d547 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -602,7 +602,7 @@ struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = __sk_dst_get(sk); - if (dst && dst->obsolete && + if (dst && READ_ONCE(dst->obsolete) && INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check, dst, cookie) == NULL) { sk_tx_queue_clear(sk); @@ -620,7 +620,7 @@ struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = sk_dst_get(sk); - if (dst && dst->obsolete && + if (dst && READ_ONCE(dst->obsolete) && INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check, dst, cookie) == NULL) { sk_dst_reset(sk); @@ -2588,8 +2588,8 @@ static u32 sk_dst_gso_max_size(struct sock *sk, struct dst_entry *dst) !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)); #endif /* pairs with the WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */ - max_size = is_ipv6 ? READ_ONCE(dst->dev->gso_max_size) : - READ_ONCE(dst->dev->gso_ipv4_max_size); + max_size = is_ipv6 ? READ_ONCE(dst_dev(dst)->gso_max_size) : + READ_ONCE(dst_dev(dst)->gso_ipv4_max_size); if (max_size > GSO_LEGACY_MAX_SIZE && !sk_is_tcp(sk)) max_size = GSO_LEGACY_MAX_SIZE; @@ -2600,7 +2600,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { u32 max_segs = 1; - sk->sk_route_caps = dst->dev->features; + sk->sk_route_caps = dst_dev(dst)->features; if (sk_is_tcp(sk)) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -2618,7 +2618,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; sk->sk_gso_max_size = sk_dst_gso_max_size(sk, dst); /* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */ - max_segs = max_t(u32, READ_ONCE(dst->dev->gso_max_segs), 1); + max_segs = max_t(u32, READ_ONCE(dst_dev(dst)->gso_max_segs), 1); } } sk->sk_gso_max_segs = max_segs; diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c index e340d955cf3b..c50436433c18 100644 --- a/net/devlink/netlink_gen.c +++ b/net/devlink/netlink_gen.c @@ -45,6 +45,11 @@ const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_FN_ATTR_ [DEVLINK_PORT_FN_ATTR_CAPS] = NLA_POLICY_BITFIELD32(15), }; +const struct nla_policy devlink_dl_rate_tc_bws_nl_policy[DEVLINK_ATTR_RATE_TC_BW + 1] = { + [DEVLINK_ATTR_RATE_TC_INDEX] = NLA_POLICY_MAX(NLA_U8, DEVLINK_RATE_TC_INDEX_MAX), + [DEVLINK_ATTR_RATE_TC_BW] = { .type = NLA_U32, }, +}; + const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1] = { [DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .type = NLA_FLAG, }, }; @@ -523,7 +528,7 @@ static const struct nla_policy devlink_rate_get_dump_nl_policy[DEVLINK_ATTR_DEV_ }; /* DEVLINK_CMD_RATE_SET - do */ -static const struct nla_policy devlink_rate_set_nl_policy[DEVLINK_ATTR_RATE_TX_WEIGHT + 1] = { +static const struct nla_policy devlink_rate_set_nl_policy[DEVLINK_ATTR_RATE_TC_BWS + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING, }, @@ -532,10 +537,11 @@ static const struct nla_policy devlink_rate_set_nl_policy[DEVLINK_ATTR_RATE_TX_W [DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32, }, [DEVLINK_ATTR_RATE_TX_WEIGHT] = { .type = NLA_U32, }, [DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_RATE_TC_BWS] = NLA_POLICY_NESTED(devlink_dl_rate_tc_bws_nl_policy), }; /* DEVLINK_CMD_RATE_NEW - do */ -static const struct nla_policy devlink_rate_new_nl_policy[DEVLINK_ATTR_RATE_TX_WEIGHT + 1] = { +static const struct nla_policy devlink_rate_new_nl_policy[DEVLINK_ATTR_RATE_TC_BWS + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING, }, @@ -544,6 +550,7 @@ static const struct nla_policy devlink_rate_new_nl_policy[DEVLINK_ATTR_RATE_TX_W [DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32, }, [DEVLINK_ATTR_RATE_TX_WEIGHT] = { .type = NLA_U32, }, [DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_RATE_TC_BWS] = NLA_POLICY_NESTED(devlink_dl_rate_tc_bws_nl_policy), }; /* DEVLINK_CMD_RATE_DEL - do */ @@ -1191,7 +1198,7 @@ const struct genl_split_ops devlink_nl_ops[74] = { .doit = devlink_nl_rate_set_doit, .post_doit = devlink_nl_post_doit, .policy = devlink_rate_set_nl_policy, - .maxattr = DEVLINK_ATTR_RATE_TX_WEIGHT, + .maxattr = DEVLINK_ATTR_RATE_TC_BWS, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, { @@ -1201,7 +1208,7 @@ const struct genl_split_ops devlink_nl_ops[74] = { .doit = devlink_nl_rate_new_doit, .post_doit = devlink_nl_post_doit, .policy = devlink_rate_new_nl_policy, - .maxattr = DEVLINK_ATTR_RATE_TX_WEIGHT, + .maxattr = DEVLINK_ATTR_RATE_TC_BWS, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, { diff --git a/net/devlink/netlink_gen.h b/net/devlink/netlink_gen.h index 8f2bd50ddf5e..fb733b5d4ff1 100644 --- a/net/devlink/netlink_gen.h +++ b/net/devlink/netlink_gen.h @@ -13,6 +13,7 @@ /* Common nested types */ extern const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_FN_ATTR_CAPS + 1]; +extern const struct nla_policy devlink_dl_rate_tc_bws_nl_policy[DEVLINK_ATTR_RATE_TC_BW + 1]; extern const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1]; /* Ops table for devlink */ diff --git a/net/devlink/rate.c b/net/devlink/rate.c index 8828ffaf6cbc..d39300a9b3d4 100644 --- a/net/devlink/rate.c +++ b/net/devlink/rate.c @@ -80,6 +80,29 @@ devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info) return ERR_PTR(-EINVAL); } +static int devlink_rate_put_tc_bws(struct sk_buff *msg, u32 *tc_bw) +{ + struct nlattr *nla_tc_bw; + int i; + + for (i = 0; i < DEVLINK_RATE_TCS_MAX; i++) { + nla_tc_bw = nla_nest_start(msg, DEVLINK_ATTR_RATE_TC_BWS); + if (!nla_tc_bw) + return -EMSGSIZE; + + if (nla_put_u8(msg, DEVLINK_ATTR_RATE_TC_INDEX, i) || + nla_put_u32(msg, DEVLINK_ATTR_RATE_TC_BW, tc_bw[i])) + goto nla_put_failure; + + nla_nest_end(msg, nla_tc_bw); + } + return 0; + +nla_put_failure: + nla_nest_cancel(msg, nla_tc_bw); + return -EMSGSIZE; +} + static int devlink_nl_rate_fill(struct sk_buff *msg, struct devlink_rate *devlink_rate, enum devlink_command cmd, u32 portid, u32 seq, @@ -129,6 +152,9 @@ static int devlink_nl_rate_fill(struct sk_buff *msg, devlink_rate->parent->name)) goto nla_put_failure; + if (devlink_rate_put_tc_bws(msg, devlink_rate->tc_bw)) + goto nla_put_failure; + genlmsg_end(msg, hdr); return 0; @@ -316,6 +342,87 @@ devlink_nl_rate_parent_node_set(struct devlink_rate *devlink_rate, return 0; } +static int devlink_nl_rate_tc_bw_parse(struct nlattr *parent_nest, u32 *tc_bw, + unsigned long *bitmap, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[DEVLINK_ATTR_MAX + 1]; + u8 tc_index; + int err; + + err = nla_parse_nested(tb, DEVLINK_ATTR_MAX, parent_nest, + devlink_dl_rate_tc_bws_nl_policy, extack); + if (err) + return err; + + if (!tb[DEVLINK_ATTR_RATE_TC_INDEX]) { + NL_SET_ERR_ATTR_MISS(extack, parent_nest, + DEVLINK_ATTR_RATE_TC_INDEX); + return -EINVAL; + } + + tc_index = nla_get_u8(tb[DEVLINK_ATTR_RATE_TC_INDEX]); + + if (!tb[DEVLINK_ATTR_RATE_TC_BW]) { + NL_SET_ERR_ATTR_MISS(extack, parent_nest, + DEVLINK_ATTR_RATE_TC_BW); + return -EINVAL; + } + + if (test_and_set_bit(tc_index, bitmap)) { + NL_SET_ERR_MSG_FMT(extack, + "Duplicate traffic class index specified (%u)", + tc_index); + return -EINVAL; + } + + tc_bw[tc_index] = nla_get_u32(tb[DEVLINK_ATTR_RATE_TC_BW]); + + return 0; +} + +static int devlink_nl_rate_tc_bw_set(struct devlink_rate *devlink_rate, + struct genl_info *info) +{ + DECLARE_BITMAP(bitmap, DEVLINK_RATE_TCS_MAX) = {}; + struct devlink *devlink = devlink_rate->devlink; + const struct devlink_ops *ops = devlink->ops; + u32 tc_bw[DEVLINK_RATE_TCS_MAX] = {}; + int rem, err = -EOPNOTSUPP, i; + struct nlattr *attr; + + nlmsg_for_each_attr_type(attr, DEVLINK_ATTR_RATE_TC_BWS, info->nlhdr, + GENL_HDRLEN, rem) { + err = devlink_nl_rate_tc_bw_parse(attr, tc_bw, bitmap, + info->extack); + if (err) + return err; + } + + for (i = 0; i < DEVLINK_RATE_TCS_MAX; i++) { + if (!test_bit(i, bitmap)) { + NL_SET_ERR_MSG_FMT(info->extack, + "Bandwidth values must be specified for all %u traffic classes", + DEVLINK_RATE_TCS_MAX); + return -EINVAL; + } + } + + if (devlink_rate_is_leaf(devlink_rate)) + err = ops->rate_leaf_tc_bw_set(devlink_rate, devlink_rate->priv, + tc_bw, info->extack); + else if (devlink_rate_is_node(devlink_rate)) + err = ops->rate_node_tc_bw_set(devlink_rate, devlink_rate->priv, + tc_bw, info->extack); + + if (err) + return err; + + memcpy(devlink_rate->tc_bw, tc_bw, sizeof(tc_bw)); + + return 0; +} + static int devlink_nl_rate_set(struct devlink_rate *devlink_rate, const struct devlink_ops *ops, struct genl_info *info) @@ -388,6 +495,12 @@ static int devlink_nl_rate_set(struct devlink_rate *devlink_rate, return err; } + if (attrs[DEVLINK_ATTR_RATE_TC_BWS]) { + err = devlink_nl_rate_tc_bw_set(devlink_rate, info); + if (err) + return err; + } + return 0; } @@ -423,6 +536,13 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, "TX weight set isn't supported for the leafs"); return false; } + if (attrs[DEVLINK_ATTR_RATE_TC_BWS] && + !ops->rate_leaf_tc_bw_set) { + NL_SET_ERR_MSG_ATTR(info->extack, + attrs[DEVLINK_ATTR_RATE_TC_BWS], + "TC bandwidth set isn't supported for the leafs"); + return false; + } } else if (type == DEVLINK_RATE_TYPE_NODE) { if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_node_tx_share_set) { NL_SET_ERR_MSG(info->extack, "TX share set isn't supported for the nodes"); @@ -449,6 +569,13 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, "TX weight set isn't supported for the nodes"); return false; } + if (attrs[DEVLINK_ATTR_RATE_TC_BWS] && + !ops->rate_node_tc_bw_set) { + NL_SET_ERR_MSG_ATTR(info->extack, + attrs[DEVLINK_ATTR_RATE_TC_BWS], + "TC bandwidth set isn't supported for the nodes"); + return false; + } } else { WARN(1, "Unknown type of rate object"); return false; diff --git a/net/ethtool/common.c b/net/ethtool/common.c index eb253e0fd61b..d62dc56f2f5b 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -707,7 +707,9 @@ static u32 ethtool_get_max_rxfh_channel(struct net_device *dev) if (!rxfh.indir) return U32_MAX; + mutex_lock(&dev->ethtool->rss_lock); ret = dev->ethtool_ops->get_rxfh(dev, &rxfh); + mutex_unlock(&dev->ethtool->rss_lock); if (ret) { current_max = U32_MAX; goto out_free; diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index c34bac7bffd8..b6d96e562c9a 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1079,16 +1079,17 @@ ethtool_set_rxfh_fields(struct net_device *dev, u32 cmd, void __user *useraddr) !ops->rxfh_per_ctx_fields) return -EINVAL; + mutex_lock(&dev->ethtool->rss_lock); if (ops->get_rxfh) { struct ethtool_rxfh_param rxfh = {}; rc = ops->get_rxfh(dev, &rxfh); if (rc) - return rc; + goto exit_unlock; rc = ethtool_check_xfrm_rxfh(rxfh.input_xfrm, info.data); if (rc) - return rc; + goto exit_unlock; } fields.data = info.data; @@ -1096,7 +1097,10 @@ ethtool_set_rxfh_fields(struct net_device *dev, u32 cmd, void __user *useraddr) if (info.flow_type & FLOW_RSS) fields.rss_context = info.rss_context; - return ops->set_rxfh_fields(dev, &fields, NULL); + rc = ops->set_rxfh_fields(dev, &fields, NULL); +exit_unlock: + mutex_unlock(&dev->ethtool->rss_lock); + return rc; } static noinline_for_stack int @@ -1123,7 +1127,9 @@ ethtool_get_rxfh_fields(struct net_device *dev, u32 cmd, void __user *useraddr) if (info.flow_type & FLOW_RSS) fields.rss_context = info.rss_context; + mutex_lock(&dev->ethtool->rss_lock); ret = ops->get_rxfh_fields(dev, &fields); + mutex_unlock(&dev->ethtool->rss_lock); if (ret < 0) return ret; @@ -1269,7 +1275,9 @@ static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev, if (!rxfh.indir) return -ENOMEM; + mutex_lock(&dev->ethtool->rss_lock); ret = dev->ethtool_ops->get_rxfh(dev, &rxfh); + mutex_unlock(&dev->ethtool->rss_lock); if (ret) goto out; if (copy_to_user(useraddr + @@ -1334,9 +1342,11 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, } rxfh_dev.hfunc = ETH_RSS_HASH_NO_CHANGE; + + mutex_lock(&dev->ethtool->rss_lock); ret = ops->set_rxfh(dev, &rxfh_dev, extack); if (ret) - goto out; + goto out_unlock; /* indicate whether rxfh was set to default */ if (user_size == 0) @@ -1344,6 +1354,8 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, else dev->priv_flags |= IFF_RXFH_CONFIGURED; +out_unlock: + mutex_unlock(&dev->ethtool->rss_lock); out: kfree(rxfh_dev.indir); return ret; @@ -1404,6 +1416,7 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, if (user_key_size) rxfh_dev.key = rss_config + indir_bytes; + mutex_lock(&dev->ethtool->rss_lock); if (rxfh.rss_context) { ctx = xa_load(&dev->ethtool->rss_ctx, rxfh.rss_context); if (!ctx) { @@ -1449,6 +1462,7 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, ret = -EFAULT; } out: + mutex_unlock(&dev->ethtool->rss_lock); kfree(rss_config); return ret; @@ -1500,7 +1514,6 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, struct netlink_ext_ack *extack = NULL; struct ethtool_rxnfc rx_rings; struct ethtool_rxfh rxfh; - bool locked = false; /* dev->ethtool->rss_lock taken */ bool create = false; bool mod = false; u8 *rss_config; @@ -1550,10 +1563,6 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, rxfh.input_xfrm == RXH_XFRM_NO_CHANGE)) return -EINVAL; - ret = ethtool_check_flow_types(dev, rxfh.input_xfrm); - if (ret) - return ret; - indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]); /* Check settings which may be global rather than per RSS-context */ @@ -1570,7 +1579,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, rx_rings.cmd = ETHTOOL_GRXRINGS; ret = ops->get_rxnfc(dev, &rx_rings, NULL); if (ret) - goto out; + goto out_free; /* rxfh.indir_size == 0 means reset the indir table to default (master * context) or delete the context (other RSS contexts). @@ -1586,7 +1595,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, &rx_rings, rxfh.indir_size); if (ret) - goto out; + goto out_free; } else if (rxfh.indir_size == 0) { if (rxfh.rss_context == 0) { u32 *indir; @@ -1608,30 +1617,31 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, useraddr + rss_cfg_offset + user_indir_len, rxfh.key_size)) { ret = -EFAULT; - goto out; + goto out_free; } } - if (rxfh.rss_context) { - mutex_lock(&dev->ethtool->rss_lock); - locked = true; - } + mutex_lock(&dev->ethtool->rss_lock); + + ret = ethtool_check_flow_types(dev, rxfh.input_xfrm); + if (ret) + goto out_unlock; if (rxfh.rss_context && rxfh_dev.rss_delete) { ret = ethtool_check_rss_ctx_busy(dev, rxfh.rss_context); if (ret) - goto out; + goto out_unlock; } if (create) { if (rxfh_dev.rss_delete) { ret = -EINVAL; - goto out; + goto out_unlock; } ctx = ethtool_rxfh_ctx_alloc(ops, dev_indir_size, dev_key_size); if (!ctx) { ret = -ENOMEM; - goto out; + goto out_unlock; } if (ops->create_rxfh_context) { @@ -1644,7 +1654,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, GFP_KERNEL_ACCOUNT); if (ret < 0) { kfree(ctx); - goto out; + goto out_unlock; } WARN_ON(!ctx_id); /* can't happen */ rxfh.rss_context = ctx_id; @@ -1653,7 +1663,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, ctx = xa_load(&dev->ethtool->rss_ctx, rxfh.rss_context); if (!ctx) { ret = -ENOENT; - goto out; + goto out_unlock; } } rxfh_dev.hfunc = rxfh.hfunc; @@ -1687,7 +1697,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context); kfree(ctx); } - goto out; + goto out_unlock; } mod = !create && !rxfh_dev.rss_delete; @@ -1708,13 +1718,13 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, if (WARN_ON(xa_load(&dev->ethtool->rss_ctx, rxfh_dev.rss_context))) { /* context ID reused, our tracking is screwed */ kfree(ctx); - goto out; + goto out_unlock; } /* Allocate the exact ID the driver gave us */ if (xa_is_err(xa_store(&dev->ethtool->rss_ctx, rxfh_dev.rss_context, ctx, GFP_KERNEL))) { kfree(ctx); - goto out; + goto out_unlock; } /* Fetch the defaults for the old API, in the new API drivers @@ -1730,7 +1740,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, if (WARN_ON(ret)) { xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context); kfree(ctx); - goto out; + goto out_unlock; } } if (rxfh_dev.rss_delete) { @@ -1755,9 +1765,9 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, ctx->input_xfrm = rxfh_dev.input_xfrm; } -out: - if (locked) - mutex_unlock(&dev->ethtool->rss_lock); +out_unlock: + mutex_unlock(&dev->ethtool->rss_lock); +out_free: kfree(rss_config); if (mod) ethtool_rss_notify(dev, rxfh.rss_context); diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 09c81cc9a08f..b1f8999c1adc 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -455,10 +455,15 @@ static int ethnl_default_parse(struct ethnl_req_info *req_info, if (request_ops->parse_request) { ret = request_ops->parse_request(req_info, tb, info->extack); if (ret < 0) - return ret; + goto err_dev; } return 0; + +err_dev: + netdev_put(req_info->dev, &req_info->dev_tracker); + req_info->dev = NULL; + return ret; } /** @@ -508,7 +513,7 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info) ret = ethnl_default_parse(req_info, info, ops, !ops->allow_nodev_do); if (ret < 0) - goto err_dev; + goto err_free; ethnl_init_reply_data(reply_data, ops, req_info->dev); rtnl_lock(); @@ -554,6 +559,7 @@ err_cleanup: ops->cleanup_data(reply_data); err_dev: netdev_put(req_info->dev, &req_info->dev_tracker); +err_free: kfree(reply_data); kfree(req_info); return ret; @@ -656,6 +662,8 @@ static int ethnl_default_start(struct netlink_callback *cb) } ret = ethnl_default_parse(req_info, &info->info, ops, false); + if (ret < 0) + goto free_reply_data; if (req_info->dev) { /* We ignore device specification in dump requests but as the * same parser as for non-dump (doit) requests is used, it @@ -664,8 +672,6 @@ static int ethnl_default_start(struct netlink_callback *cb) netdev_put(req_info->dev, &req_info->dev_tracker); req_info->dev = NULL; } - if (ret < 0) - goto free_reply_data; ctx->ops = ops; ctx->req_info = req_info; @@ -714,13 +720,13 @@ static int ethnl_perphy_start(struct netlink_callback *cb) * the dev's ifindex, .dumpit() will grab and release the netdev itself. */ ret = ethnl_default_parse(req_info, &info->info, ops, false); + if (ret < 0) + goto free_reply_data; if (req_info->dev) { phy_ctx->ifindex = req_info->dev->ifindex; netdev_put(req_info->dev, &req_info->dev_tracker); req_info->dev = NULL; } - if (ret < 0) - goto free_reply_data; ctx->ops = ops; ctx->req_info = req_info; diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 373a8d5e86ae..94a7eb402022 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -467,7 +467,7 @@ extern const struct nla_policy ethnl_channels_set_policy[ETHTOOL_A_CHANNELS_COMB extern const struct nla_policy ethnl_coalesce_get_policy[ETHTOOL_A_COALESCE_HEADER + 1]; extern const struct nla_policy ethnl_coalesce_set_policy[ETHTOOL_A_COALESCE_MAX + 1]; extern const struct nla_policy ethnl_pause_get_policy[ETHTOOL_A_PAUSE_STATS_SRC + 1]; -extern const struct nla_policy ethnl_pause_set_policy[ETHTOOL_A_PAUSE_TX + 1]; +extern const struct nla_policy ethnl_pause_set_policy[ETHTOOL_A_PAUSE_STATS_SRC + 1]; extern const struct nla_policy ethnl_eee_get_policy[ETHTOOL_A_EEE_HEADER + 1]; extern const struct nla_policy ethnl_eee_set_policy[ETHTOOL_A_EEE_TX_LPI_TIMER + 1]; extern const struct nla_policy ethnl_tsinfo_get_policy[ETHTOOL_A_TSINFO_MAX + 1]; diff --git a/net/ethtool/pause.c b/net/ethtool/pause.c index f7c847aeb1a2..0f9af1e66548 100644 --- a/net/ethtool/pause.c +++ b/net/ethtool/pause.c @@ -168,6 +168,7 @@ const struct nla_policy ethnl_pause_set_policy[] = { [ETHTOOL_A_PAUSE_AUTONEG] = { .type = NLA_U8 }, [ETHTOOL_A_PAUSE_RX] = { .type = NLA_U8 }, [ETHTOOL_A_PAUSE_TX] = { .type = NLA_U8 }, + [ETHTOOL_A_PAUSE_STATS_SRC] = { .type = NLA_REJECT }, }; static int diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index 3adddca7e215..e717f23cbc10 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -139,6 +139,15 @@ rss_prepare_ctx(const struct rss_req_info *request, struct net_device *dev, } static int +rss_prepare(const struct rss_req_info *request, struct net_device *dev, + struct rss_reply_data *data, const struct genl_info *info) +{ + if (request->rss_context) + return rss_prepare_ctx(request, dev, data, info); + return rss_prepare_get(request, dev, data, info); +} + +static int rss_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) @@ -147,20 +156,22 @@ rss_prepare_data(const struct ethnl_req_info *req_base, struct rss_req_info *request = RSS_REQINFO(req_base); struct net_device *dev = reply_base->dev; const struct ethtool_ops *ops; + int ret; ops = dev->ethtool_ops; if (!ops->get_rxfh) return -EOPNOTSUPP; /* Some drivers don't handle rss_context */ - if (request->rss_context) { - if (!ops->cap_rss_ctx_supported && !ops->create_rxfh_context) - return -EOPNOTSUPP; + if (request->rss_context && + !ops->cap_rss_ctx_supported && !ops->create_rxfh_context) + return -EOPNOTSUPP; - return rss_prepare_ctx(request, dev, data, info); - } + mutex_lock(&dev->ethtool->rss_lock); + ret = rss_prepare(request, dev, data, info); + mutex_unlock(&dev->ethtool->rss_lock); - return rss_prepare_get(request, dev, data, info); + return ret; } static int diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 4b5bc6eb52e7..c2b2cda1a7e5 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -109,7 +109,7 @@ void ip4_datagram_release_cb(struct sock *sk) rcu_read_lock(); dst = __sk_dst_get(sk); - if (!dst || !dst->obsolete || dst->ops->check(dst, 0)) { + if (!dst || !READ_ONCE(dst->obsolete) || dst->ops->check(dst, 0)) { rcu_read_unlock(); return; } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index f7c9c6a9f53e..a2f04992f579 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -625,11 +625,6 @@ int fib_nh_common_init(struct net *net, struct fib_nh_common *nhc, if (encap) { struct lwtunnel_state *lwtstate; - if (encap_type == LWTUNNEL_ENCAP_NONE) { - NL_SET_ERR_MSG(extack, "LWT encap type not specified"); - err = -EINVAL; - goto lwt_failure; - } err = lwtunnel_build_state(net, encap_type, encap, nhc->nhc_family, cfg, &lwtstate, extack); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 717cb7d3607a..2ffe73ea644f 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -311,18 +311,20 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, { struct dst_entry *dst = &rt->dst; struct inet_peer *peer; + struct net_device *dev; bool rc = true; if (!apply_ratelimit) return true; /* No rate limit on loopback */ - if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) + dev = dst_dev(dst); + if (dev && (dev->flags & IFF_LOOPBACK)) goto out; rcu_read_lock(); peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, - l3mdev_master_ifindex_rcu(dst->dev)); + l3mdev_master_ifindex_rcu(dev)); rc = inet_peer_xrlim_allow(peer, READ_ONCE(net->ipv4.sysctl_icmp_ratelimit)); rcu_read_unlock(); @@ -466,13 +468,13 @@ out_bh_enable: */ static struct net_device *icmp_get_route_lookup_dev(struct sk_buff *skb) { - struct net_device *route_lookup_dev = NULL; + struct net_device *dev = skb->dev; + const struct dst_entry *dst; - if (skb->dev) - route_lookup_dev = skb->dev; - else if (skb_dst(skb)) - route_lookup_dev = skb_dst(skb)->dev; - return route_lookup_dev; + if (dev) + return dev; + dst = skb_dst(skb); + return dst ? dst_dev(dst) : NULL; } static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, @@ -869,7 +871,7 @@ static enum skb_drop_reason icmp_unreach(struct sk_buff *skb) struct net *net; u32 info = 0; - net = dev_net_rcu(skb_dst(skb)->dev); + net = skb_dst_dev_net_rcu(skb); /* * Incomplete header ? @@ -1012,7 +1014,7 @@ static enum skb_drop_reason icmp_echo(struct sk_buff *skb) struct icmp_bxm icmp_param; struct net *net; - net = dev_net_rcu(skb_dst(skb)->dev); + net = skb_dst_dev_net_rcu(skb); /* should there be an ICMP stat for ignored echos? */ if (READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_all)) return SKB_NOT_DROPPED_YET; @@ -1182,7 +1184,7 @@ static enum skb_drop_reason icmp_timestamp(struct sk_buff *skb) return SKB_NOT_DROPPED_YET; out_err: - __ICMP_INC_STATS(dev_net_rcu(skb_dst(skb)->dev), ICMP_MIB_INERRORS); + __ICMP_INC_STATS(skb_dst_dev_net_rcu(skb), ICMP_MIB_INERRORS); return SKB_DROP_REASON_PKT_TOO_SMALL; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index d1769034b643..7182f1419c2a 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -427,7 +427,7 @@ static int igmpv3_sendpack(struct sk_buff *skb) pig->csum = ip_compute_csum(igmp_hdr(skb), igmplen); - return ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); + return ip_local_out(skb_dst_dev_net(skb), skb->sk, skb); } static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index f4157d26ec9e..1e2df51427fe 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -884,15 +884,6 @@ static void syn_ack_recalc(struct request_sock *req, req->num_timeout >= rskq_defer_accept - 1; } -int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req) -{ - int err = req->rsk_ops->rtx_syn_ack(parent, req); - - if (!err) - req->num_retrans++; - return err; -} - static struct request_sock * reqsk_alloc_noprof(const struct request_sock_ops *ops, struct sock *sk_listener, bool attach_listener) @@ -1132,7 +1123,7 @@ static void reqsk_timer_handler(struct timer_list *t) req->rsk_ops->syn_ack_timeout(req); if (!expire && (!resend || - !inet_rtx_syn_ack(sk_listener, req) || + !tcp_rtx_synack(sk_listener, req) || inet_rsk(req)->acked)) { if (req->num_timeout++ == 0) atomic_dec(&queue->young); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 64b3fb3208af..b2584cce90ae 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -476,7 +476,7 @@ out_fail: /* Process an incoming IP datagram fragment. */ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user) { - struct net_device *dev = skb->dev ? : skb_dst(skb)->dev; + struct net_device *dev = skb->dev ? : skb_dst_dev(skb); int vif = l3mdev_master_ifindex_rcu(dev); struct ipq *qp; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 30a5e9460d00..fc323994b1fa 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -226,6 +226,12 @@ resubmit: static int ip_local_deliver_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { + if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) { + __IP_INC_STATS(net, IPSTATS_MIB_INDISCARDS); + kfree_skb_reason(skb, SKB_DROP_REASON_NOMEM); + return 0; + } + skb_clear_delivery_time(skb); __skb_pull(skb, skb_network_header_len(skb)); @@ -319,8 +325,8 @@ static int ip_rcv_finish_core(struct net *net, const struct sk_buff *hint) { const struct iphdr *iph = ip_hdr(skb); - int err, drop_reason; struct rtable *rt; + int drop_reason; if (ip_can_use_hint(skb, iph, hint)) { drop_reason = ip_route_use_hint(skb, iph->daddr, iph->saddr, @@ -345,9 +351,10 @@ static int ip_rcv_finish_core(struct net *net, break; case IPPROTO_UDP: if (READ_ONCE(net->ipv4.sysctl_udp_early_demux)) { - err = udp_v4_early_demux(skb); - if (unlikely(err)) + drop_reason = udp_v4_early_demux(skb); + if (unlikely(drop_reason)) goto drop_error; + drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; /* must reload iph, skb->head might have changed */ iph = ip_hdr(skb); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index a2705d454fd6..414b47a0d513 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -116,7 +116,7 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) skb->protocol = htons(ETH_P_IP); return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, - net, sk, skb, NULL, skb_dst(skb)->dev, + net, sk, skb, NULL, skb_dst_dev(skb), dst_output); } @@ -199,7 +199,7 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = dst_rtable(dst); - struct net_device *dev = dst->dev; + struct net_device *dev = dst_dev(dst); unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; bool is_v6gw = false; @@ -425,7 +425,7 @@ int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb) int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev; + struct net_device *dev = skb_dst_dev(skb), *indev = skb->dev; skb->dev = dev; skb->protocol = htons(ETH_P_IP); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 686e4f3d83aa..95b6bb78fcd2 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -229,7 +229,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error_icmp; } - tdev = dst->dev; + tdev = dst_dev(dst); if (tdev == dev) { dst_release(dst); @@ -259,7 +259,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, xmit: skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev))); skb_dst_set(skb, dst); - skb->dev = skb_dst(skb)->dev; + skb->dev = skb_dst_dev(skb); err = dst_output(tunnel->net, skb->sk, skb); if (net_xmit_eval(err) == 0) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index f78c4e53dc8c..3a2044e6033d 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2299,7 +2299,8 @@ int ip_mr_output(struct net *net, struct sock *sk, struct sk_buff *skb) struct mr_table *mrt; int vif; - WARN_ON_ONCE(!rcu_read_lock_held()); + guard(rcu)(); + dev = rt->dst.dev; if (IPCB(skb)->flags & IPSKB_FORWARDED) @@ -2313,7 +2314,6 @@ int ip_mr_output(struct net *net, struct sock *sk, struct sk_buff *skb) if (IS_ERR(mrt)) goto mc_output; - /* already under rcu_read_lock() */ cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); if (!cache) { vif = ipmr_find_vif(mrt, dev); diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 08bc3f2c0078..0565f001120d 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -20,12 +20,12 @@ /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */ int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int addr_type) { + struct net_device *dev = skb_dst_dev(skb); const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; struct flowi4 fl4 = {}; __be32 saddr = iph->saddr; __u8 flags; - struct net_device *dev = skb_dst(skb)->dev; struct flow_keys flkeys; unsigned int hh_len; @@ -74,7 +74,7 @@ int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, un #endif /* Change in oif may mean change in hh_len. */ - hh_len = skb_dst(skb)->dev->hard_header_len; + hh_len = skb_dst_dev(skb)->hard_header_len; if (skb_headroom(skb) < hh_len && pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)), 0, GFP_ATOMIC)) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a2b7cadf66af..64ba377cd6cc 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -413,7 +413,7 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const void *daddr) { const struct rtable *rt = container_of(dst, struct rtable, dst); - struct net_device *dev = dst->dev; + struct net_device *dev = dst_dev(dst); struct neighbour *n; rcu_read_lock(); @@ -440,7 +440,7 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr) { const struct rtable *rt = container_of(dst, struct rtable, dst); - struct net_device *dev = dst->dev; + struct net_device *dev = dst_dev(dst); const __be32 *pkey = daddr; if (rt->rt_gw_family == AF_INET) { @@ -717,7 +717,7 @@ static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr, */ rt = rcu_dereference(nhc->nhc_rth_input); if (rt) - rt->dst.obsolete = DST_OBSOLETE_KILL; + WRITE_ONCE(rt->dst.obsolete, DST_OBSOLETE_KILL); for_each_possible_cpu(i) { struct rtable __rcu **prt; @@ -725,7 +725,7 @@ static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr, prt = per_cpu_ptr(nhc->nhc_pcpu_rth_output, i); rt = rcu_dereference(*prt); if (rt) - rt->dst.obsolete = DST_OBSOLETE_KILL; + WRITE_ONCE(rt->dst.obsolete, DST_OBSOLETE_KILL); } } @@ -797,7 +797,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow jiffies + ip_rt_gc_timeout); } if (kill_route) - rt->dst.obsolete = DST_OBSOLETE_KILL; + WRITE_ONCE(rt->dst.obsolete, DST_OBSOLETE_KILL); call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); } neigh_release(n); @@ -842,9 +842,9 @@ static void ipv4_negative_advice(struct sock *sk, { struct rtable *rt = dst_rtable(dst); - if ((dst->obsolete > 0) || + if ((READ_ONCE(dst->obsolete) > 0) || (rt->rt_flags & RTCF_REDIRECTED) || - rt->dst.expires) + READ_ONCE(rt->dst.expires)) sk_dst_reset(sk); } @@ -1026,14 +1026,15 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) return; rcu_read_lock(); - net = dev_net_rcu(dst->dev); + net = dev_net_rcu(dst_dev(dst)); if (mtu < net->ipv4.ip_rt_min_pmtu) { lock = true; mtu = min(old_mtu, net->ipv4.ip_rt_min_pmtu); } if (rt->rt_pmtu == mtu && !lock && - time_before(jiffies, dst->expires - net->ipv4.ip_rt_mtu_expires / 2)) + time_before(jiffies, READ_ONCE(dst->expires) - + net->ipv4.ip_rt_mtu_expires / 2)) goto out; if (fib_lookup(net, fl4, &res, 0) == 0) { @@ -1136,7 +1137,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0); rt = dst_rtable(odst); - if (odst->obsolete && !odst->ops->check(odst, 0)) { + if (READ_ONCE(odst->obsolete) && !odst->ops->check(odst, 0)) { rt = ip_route_output_flow(sock_net(sk), &fl4, sk); if (IS_ERR(rt)) goto out; @@ -1211,7 +1212,8 @@ INDIRECT_CALLABLE_SCOPE struct dst_entry *ipv4_dst_check(struct dst_entry *dst, * this is indicated by setting obsolete to DST_OBSOLETE_KILL or * DST_OBSOLETE_DEAD. */ - if (dst->obsolete != DST_OBSOLETE_FORCE_CHK || rt_is_expired(rt)) + if (READ_ONCE(dst->obsolete) != DST_OBSOLETE_FORCE_CHK || + rt_is_expired(rt)) return NULL; return dst; } @@ -1324,7 +1326,7 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst) struct net *net; rcu_read_lock(); - net = dev_net_rcu(dst->dev); + net = dev_net_rcu(dst_dev(dst)); advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size, net->ipv4.ip_rt_min_advmss); rcu_read_unlock(); @@ -1571,7 +1573,7 @@ void rt_flush_dev(struct net_device *dev) static bool rt_cache_valid(const struct rtable *rt) { return rt && - rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && + READ_ONCE(rt->dst.obsolete) == DST_OBSOLETE_FORCE_CHK && !rt_is_expired(rt); } @@ -1685,8 +1687,8 @@ struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt) else if (rt->rt_gw_family == AF_INET6) new_rt->rt_gw6 = rt->rt_gw6; - new_rt->dst.input = rt->dst.input; - new_rt->dst.output = rt->dst.output; + new_rt->dst.input = READ_ONCE(rt->dst.input); + new_rt->dst.output = READ_ONCE(rt->dst.output); new_rt->dst.error = rt->dst.error; new_rt->dst.lastuse = jiffies; new_rt->dst.lwtstate = lwtstate_get(rt->dst.lwtstate); @@ -3009,7 +3011,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, } } - expires = rt->dst.expires; + expires = READ_ONCE(rt->dst.expires); if (expires) { unsigned long now = jiffies; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8a3c99246d2e..925b2c572ca2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -302,8 +302,6 @@ EXPORT_PER_CPU_SYMBOL_GPL(tcp_tw_isn); long sysctl_tcp_mem[3] __read_mostly; EXPORT_IPV6_MOD(sysctl_tcp_mem); -atomic_long_t tcp_memory_allocated ____cacheline_aligned_in_smp; /* Current allocated memory. */ -EXPORT_IPV6_MOD(tcp_memory_allocated); DEFINE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc); EXPORT_PER_CPU_SYMBOL_GPL(tcp_memory_per_cpu_fw_alloc); diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 5107121c5e37..f1884f0c9e52 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -559,6 +559,7 @@ bool tcp_fastopen_active_should_disable(struct sock *sk) void tcp_fastopen_active_disable_ofo_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + struct net_device *dev; struct dst_entry *dst; struct sk_buff *skb; @@ -576,7 +577,8 @@ void tcp_fastopen_active_disable_ofo_check(struct sock *sk) } else if (tp->syn_fastopen_ch && atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times)) { dst = sk_dst_get(sk); - if (!(dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK))) + dev = dst ? dst_dev(dst) : NULL; + if (!(dev && (dev->flags & IFF_LOOPBACK))) atomic_set(&sock_net(sk)->ipv4.tfo_active_disable_times, 0); dst_release(dst); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 19a1542883df..79e3bfb0108f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4845,8 +4845,9 @@ static void tcp_ofo_queue(struct sock *sk) if (before(TCP_SKB_CB(skb)->seq, dsack_high)) { __u32 dsack = dsack_high; + if (before(TCP_SKB_CB(skb)->end_seq, dsack_high)) - dsack_high = TCP_SKB_CB(skb)->end_seq; + dsack = TCP_SKB_CB(skb)->end_seq; tcp_dsack_extend(sk, TCP_SKB_CB(skb)->seq, dsack); } p = rb_next(p); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 429fb34b075e..a847d894ace3 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -59,6 +59,7 @@ #include <linux/slab.h> #include <linux/sched.h> +#include <net/aligned_data.h> #include <net/net_namespace.h> #include <net/icmp.h> #include <net/inet_hashtables.h> @@ -787,7 +788,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, arg.iov[0].iov_base = (unsigned char *)&rep; arg.iov[0].iov_len = sizeof(rep.th); - net = sk ? sock_net(sk) : dev_net_rcu(skb_dst(skb)->dev); + net = sk ? sock_net(sk) : skb_dst_dev_net_rcu(skb); /* Invalid TCP option size or twice included auth */ if (tcp_parse_auth_options(tcp_hdr(skb), &md5_hash_location, &aoh)) @@ -1703,7 +1704,6 @@ static struct dst_entry *tcp_v4_route_req(const struct sock *sk, struct request_sock_ops tcp_request_sock_ops __read_mostly = { .family = PF_INET, .obj_size = sizeof(struct tcp_request_sock), - .rtx_syn_ack = tcp_rtx_synack, .send_ack = tcp_v4_reqsk_send_ack, .destructor = tcp_v4_reqsk_destructor, .send_reset = tcp_v4_send_reset, @@ -3391,7 +3391,7 @@ struct proto tcp_prot = { .sockets_allocated = &tcp_sockets_allocated, .orphan_count = &tcp_orphan_count, - .memory_allocated = &tcp_memory_allocated, + .memory_allocated = &net_aligned_data.tcp_memory_allocated, .per_cpu_fw_alloc = &tcp_memory_per_cpu_fw_alloc, .memory_pressure = &tcp_memory_pressure, diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 4251670e328c..03c068ea27b6 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -166,11 +166,11 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, unsigned int hash) { struct tcp_metrics_block *tm; - struct net *net; bool reclaim = false; + struct net *net; spin_lock_bh(&tcp_metrics_lock); - net = dev_net_rcu(dst->dev); + net = dev_net_rcu(dst_dev(dst)); /* While waiting for the spin-lock the cache might have been populated * with this entry and so we have to check again. @@ -273,7 +273,7 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req, return NULL; } - net = dev_net_rcu(dst->dev); + net = dev_net_rcu(dst_dev(dst)); hash ^= net_hash_mix(net); hash = hash_32(hash, tcp_metrics_hash_log); @@ -318,7 +318,7 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk, else return NULL; - net = dev_net_rcu(dst->dev); + net = dev_net_rcu(dst_dev(dst)); hash ^= net_hash_mix(net); hash = hash_32(hash, tcp_metrics_hash_log); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 43d7852ce07e..2994c9222c9c 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -726,7 +726,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, LINUX_MIB_TCPACKSKIPPEDSYNRECV, &tcp_rsk(req)->last_oow_ack_time) && - !inet_rtx_syn_ack(sk, req)) { + !tcp_rtx_synack(sk, req)) { unsigned long expires = jiffies; expires += reqsk_timeout(req, TCP_RTO_MAX); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 28f840724fe8..b616776e3354 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -4425,6 +4425,7 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) tcp_sk_rw(sk)->total_retrans++; } trace_tcp_retransmit_synack(sk, req); + req->num_retrans++; } return res; } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index bb37e24b97a7..a207877270fb 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -478,7 +478,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) * regular retransmit because if the child socket has been accepted * it's not good to give up too easily. */ - inet_rtx_syn_ack(sk, req); + tcp_rtx_synack(sk, req); req->num_timeout++; tcp_update_rto_stats(sk); if (!tp->retrans_stamp) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 19573ee64a0f..49f43c54cfb0 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -127,8 +127,6 @@ struct udp_table udp_table __read_mostly; long sysctl_udp_mem[3] __read_mostly; EXPORT_IPV6_MOD(sysctl_udp_mem); -atomic_long_t udp_memory_allocated ____cacheline_aligned_in_smp; -EXPORT_IPV6_MOD(udp_memory_allocated); DEFINE_PER_CPU(int, udp_memory_per_cpu_fw_alloc); EXPORT_PER_CPU_SYMBOL_GPL(udp_memory_per_cpu_fw_alloc); @@ -3235,7 +3233,7 @@ struct proto udp_prot = { #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = udp_bpf_update_proto, #endif - .memory_allocated = &udp_memory_allocated, + .memory_allocated = &net_aligned_data.udp_memory_allocated, .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, .sysctl_mem = sysctl_udp_mem, diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h index e1ff3a375996..c7142213fc21 100644 --- a/net/ipv4/udp_impl.h +++ b/net/ipv4/udp_impl.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _UDP4_IMPL_H #define _UDP4_IMPL_H +#include <net/aligned_data.h> #include <net/udp.h> #include <net/udplite.h> #include <net/protocol.h> diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index af37af3ab727..d3e621a11a1a 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -60,7 +60,7 @@ struct proto udplite_prot = { .rehash = udp_v4_rehash, .get_port = udp_v4_get_port, - .memory_allocated = &udp_memory_allocated, + .memory_allocated = &net_aligned_data.udp_memory_allocated, .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, .sysctl_mem = sysctl_udp_mem, diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 3cff51ba72bb..0ae67d537499 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -31,7 +31,7 @@ static int __xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb) int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb) { return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, - net, sk, skb, skb->dev, skb_dst(skb)->dev, + net, sk, skb, skb->dev, skb_dst_dev(skb), __xfrm4_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index a247bb93908b..df1986973430 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -32,7 +32,7 @@ #include <linux/unaligned.h> #include <linux/crc-ccitt.h> -/* Maximium size of the calipso option including +/* Maximum size of the calipso option including * the two-byte TLV header. */ #define CALIPSO_OPT_LEN_MAX (2 + 252) @@ -42,13 +42,13 @@ */ #define CALIPSO_HDR_LEN (2 + 8) -/* Maximium size of the calipso option including +/* Maximum size of the calipso option including * the two-byte TLV header and upto 3 bytes of * leading pad and 7 bytes of trailing pad. */ #define CALIPSO_OPT_LEN_MAX_WITH_PAD (3 + CALIPSO_OPT_LEN_MAX + 7) - /* Maximium size of u32 aligned buffer required to hold calipso + /* Maximum size of u32 aligned buffer required to hold calipso * option. Max of 3 initial pad bytes starting from buffer + 3. * i.e. the worst case is when the previous tlv finishes on 4n + 3. */ diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 281722817a65..972bf0426d59 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -127,7 +127,7 @@ void ip6_datagram_release_cb(struct sock *sk) rcu_read_lock(); dst = __sk_dst_get(sk); - if (!dst || !dst->obsolete || + if (!dst || !READ_ONCE(dst->obsolete) || dst->ops->check(dst, inet6_sk(sk)->dst_cookie)) { rcu_read_unlock(); return; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 457de0745a33..d1ef9644f826 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -306,7 +306,7 @@ static int ipv6_destopt_rcv(struct sk_buff *skb) if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + ((skb_transport_header(skb)[1] + 1) << 3)))) { - __IP6_INC_STATS(dev_net(dst->dev), idev, + __IP6_INC_STATS(dev_net(dst_dev(dst)), idev, IPSTATS_MIB_INHDRERRORS); fail_and_free: kfree_skb(skb); @@ -460,7 +460,7 @@ looped_back: return -1; } - if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) { + if (skb_dst_dev(skb)->flags & IFF_LOOPBACK) { if (ipv6_hdr(skb)->hop_limit <= 1) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, @@ -621,7 +621,7 @@ looped_back: return -1; } - if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) { + if (skb_dst_dev(skb)->flags & IFF_LOOPBACK) { if (ipv6_hdr(skb)->hop_limit <= 1) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, @@ -783,7 +783,7 @@ looped_back: kfree_skb(skb); return -1; } - if (!ipv6_chk_home_addr(dev_net(skb_dst(skb)->dev), addr)) { + if (!ipv6_chk_home_addr(skb_dst_dev_net(skb), addr)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; @@ -809,7 +809,7 @@ looped_back: return -1; } - if (skb_dst(skb)->dev->flags&IFF_LOOPBACK) { + if (skb_dst_dev(skb)->flags & IFF_LOOPBACK) { if (ipv6_hdr(skb)->hop_limit <= 1) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 3fd19a84b358..44550957fd4e 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -196,6 +196,7 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type, struct flowi6 *fl6, bool apply_ratelimit) { struct net *net = sock_net(sk); + struct net_device *dev; struct dst_entry *dst; bool res = false; @@ -208,10 +209,11 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type, * this lookup should be more aggressive (not longer than timeout). */ dst = ip6_route_output(net, sk, fl6); + dev = dst_dev(dst); if (dst->error) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); - } else if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) { + } else if (dev && (dev->flags & IFF_LOOPBACK)) { res = true; } else { struct rt6_info *rt = dst_rt6_info(dst); diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index 7d574f5132e2..7bb9edc5c28c 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -70,7 +70,7 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb) */ memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_oif = orig_dst->dev->ifindex; + fl6.flowi6_oif = dst_dev(orig_dst)->ifindex; fl6.flowi6_iif = LOOPBACK_IFINDEX; fl6.daddr = *rt6_nexthop(dst_rt6_info(orig_dst), &ip6h->daddr); diff --git a/net/ipv6/ioam6.c b/net/ipv6/ioam6.c index a84d332f952f..9553a3200081 100644 --- a/net/ipv6/ioam6.c +++ b/net/ipv6/ioam6.c @@ -696,6 +696,7 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb, struct ioam6_schema *sc, u8 sclen, bool is_input) { + struct net_device *dev = skb_dst_dev(skb); struct timespec64 ts; ktime_t tstamp; u64 raw64; @@ -712,7 +713,7 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb, if (is_input) byte--; - raw32 = dev_net(skb_dst(skb)->dev)->ipv6.sysctl.ioam6_id; + raw32 = dev_net(dev)->ipv6.sysctl.ioam6_id; *(__be32 *)data = cpu_to_be32((byte << 24) | raw32); data += sizeof(__be32); @@ -728,10 +729,10 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb, *(__be16 *)data = cpu_to_be16(raw16); data += sizeof(__be16); - if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) + if (dev->flags & IFF_LOOPBACK) raw16 = IOAM6_U16_UNAVAILABLE; else - raw16 = (__force u16)READ_ONCE(__in6_dev_get(skb_dst(skb)->dev)->cnf.ioam6_id); + raw16 = (__force u16)READ_ONCE(__in6_dev_get(dev)->cnf.ioam6_id); *(__be16 *)data = cpu_to_be16(raw16); data += sizeof(__be16); @@ -783,10 +784,10 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb, struct Qdisc *qdisc; __u32 qlen, backlog; - if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) { + if (dev->flags & IFF_LOOPBACK) { *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); } else { - queue = skb_get_tx_queue(skb_dst(skb)->dev, skb); + queue = skb_get_tx_queue(dev, skb); qdisc = rcu_dereference(queue->qdisc); qdisc_qstats_qlen_backlog(qdisc, &qlen, &backlog); @@ -807,7 +808,7 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb, if (is_input) byte--; - raw64 = dev_net(skb_dst(skb)->dev)->ipv6.sysctl.ioam6_id_wide; + raw64 = dev_net(dev)->ipv6.sysctl.ioam6_id_wide; *(__be64 *)data = cpu_to_be64(((u64)byte << 56) | raw64); data += sizeof(__be64); @@ -823,10 +824,10 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb, *(__be32 *)data = cpu_to_be32(raw32); data += sizeof(__be32); - if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) + if (dev->flags & IFF_LOOPBACK) raw32 = IOAM6_U32_UNAVAILABLE; else - raw32 = READ_ONCE(__in6_dev_get(skb_dst(skb)->dev)->cnf.ioam6_id_wide); + raw32 = READ_ONCE(__in6_dev_get(dev)->cnf.ioam6_id_wide); *(__be32 *)data = cpu_to_be32(raw32); data += sizeof(__be32); diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c index 40df8bdfaacd..1fe7894f14dd 100644 --- a/net/ipv6/ioam6_iptunnel.c +++ b/net/ipv6/ioam6_iptunnel.c @@ -335,7 +335,7 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb, if (has_tunsrc) memcpy(&hdr->saddr, tunsrc, sizeof(*tunsrc)); else - ipv6_dev_get_saddr(net, dst->dev, &hdr->daddr, + ipv6_dev_get_saddr(net, dst_dev(dst), &hdr->daddr, IPV6_PREFER_SRC_PUBLIC, &hdr->saddr); skb_postpush_rcsum(skb, hdr, len); @@ -442,7 +442,7 @@ do_encap: dst_cache_set_ip6(&ilwt->cache, dst, &fl6.saddr); local_bh_enable(); - err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); + err = skb_cow_head(skb, LL_RESERVED_SPACE(dst_dev(dst))); if (unlikely(err)) goto drop; } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 93578b2ec35f..7272d7e0fc36 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -963,8 +963,7 @@ insert_above: } static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh, - const struct fib6_info *match, - const struct fib6_table *table) + const struct fib6_info *match) { int cpu; @@ -999,21 +998,15 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh, rcu_read_unlock(); } -struct fib6_nh_pcpu_arg { - struct fib6_info *from; - const struct fib6_table *table; -}; - static int fib6_nh_drop_pcpu_from(struct fib6_nh *nh, void *_arg) { - struct fib6_nh_pcpu_arg *arg = _arg; + struct fib6_info *arg = _arg; - __fib6_drop_pcpu_from(nh, arg->from, arg->table); + __fib6_drop_pcpu_from(nh, arg); return 0; } -static void fib6_drop_pcpu_from(struct fib6_info *f6i, - const struct fib6_table *table) +static void fib6_drop_pcpu_from(struct fib6_info *f6i) { /* Make sure rt6_make_pcpu_route() wont add other percpu routes * while we are cleaning them here. @@ -1022,19 +1015,14 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i, mb(); /* paired with the cmpxchg() in rt6_make_pcpu_route() */ if (f6i->nh) { - struct fib6_nh_pcpu_arg arg = { - .from = f6i, - .table = table - }; - rcu_read_lock(); - nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_drop_pcpu_from, &arg); + nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_drop_pcpu_from, f6i); rcu_read_unlock(); } else { struct fib6_nh *fib6_nh; fib6_nh = f6i->fib6_nh; - __fib6_drop_pcpu_from(fib6_nh, f6i, table); + __fib6_drop_pcpu_from(fib6_nh, f6i); } } @@ -1045,7 +1033,7 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn, /* Flush all cached dst in exception table */ rt6_flush_exceptions(rt); - fib6_drop_pcpu_from(rt, table); + fib6_drop_pcpu_from(rt); if (rt->nh) { spin_lock(&rt->nh->lock); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 2dc9dcffe2ca..a1210fd6404e 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1085,9 +1085,11 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, htonl(atomic_fetch_inc(&t->o_seqno))); /* TooBig packet may have updated dst->dev's mtu */ - if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu) - dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu, false); - + if (!t->parms.collect_md && dst) { + mtu = READ_ONCE(dst_dev(dst)->mtu); + if (dst_mtu(dst) > mtu) + dst->ops->update_pmtu(dst, NULL, skb, mtu, false); + } err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, NEXTHDR_GRE); if (err != 0) { diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 39da6a7ce5f1..168ec07e31cc 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -187,7 +187,9 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev, * arrived via the sending interface (ethX), because of the * nature of scoping architecture. --yoshfuji */ - IP6CB(skb)->iif = skb_valid_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex; + IP6CB(skb)->iif = skb_valid_dst(skb) ? + ip6_dst_idev(skb_dst(skb))->dev->ifindex : + dev->ifindex; if (unlikely(!pskb_may_pull(skb, sizeof(*hdr)))) goto err; @@ -476,6 +478,13 @@ discard: static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { + if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) { + __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_INDISCARDS); + kfree_skb_reason(skb, SKB_DROP_REASON_NOMEM); + return 0; + } + skb_clear_delivery_time(skb); ip6_protocol_deliver_rcu(net, skb, 0, false); @@ -499,38 +508,32 @@ EXPORT_SYMBOL_GPL(ip6_input); int ip6_mc_input(struct sk_buff *skb) { + struct net_device *dev = skb->dev; int sdif = inet6_sdif(skb); const struct ipv6hdr *hdr; - struct net_device *dev; bool deliver; - __IP6_UPD_PO_STATS(dev_net(skb_dst(skb)->dev), - __in6_dev_get_safely(skb->dev), IPSTATS_MIB_INMCAST, - skb->len); + __IP6_UPD_PO_STATS(skb_dst_dev_net_rcu(skb), + __in6_dev_get_safely(dev), IPSTATS_MIB_INMCAST, + skb->len); /* skb->dev passed may be master dev for vrfs. */ if (sdif) { - rcu_read_lock(); - dev = dev_get_by_index_rcu(dev_net(skb->dev), sdif); + dev = dev_get_by_index_rcu(dev_net_rcu(dev), sdif); if (!dev) { - rcu_read_unlock(); kfree_skb(skb); return -ENODEV; } - } else { - dev = skb->dev; } hdr = ipv6_hdr(skb); deliver = ipv6_chk_mcast_addr(dev, &hdr->daddr, NULL); - if (sdif) - rcu_read_unlock(); #ifdef CONFIG_IPV6_MROUTE /* * IPv6 multicast router mode is now supported ;) */ - if (atomic_read(&dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding) && + if (atomic_read(&dev_net_rcu(skb->dev)->ipv6.devconf_all->mc_forwarding) && !(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL)) && likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) { @@ -571,22 +574,21 @@ int ip6_mc_input(struct sk_buff *skb) /* unknown RA - process it normally */ } - if (deliver) + if (deliver) { skb2 = skb_clone(skb, GFP_ATOMIC); - else { + } else { skb2 = skb; skb = NULL; } - if (skb2) { + if (skb2) ip6_mr_input(skb2); - } } out: #endif - if (likely(deliver)) + if (likely(deliver)) { ip6_input(skb); - else { + } else { /* discard */ kfree_skb(skb); } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 7bd29a9ff0db..877bee7ffee9 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -60,7 +60,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - struct net_device *dev = dst->dev; + struct net_device *dev = dst_dev(dst); struct inet6_dev *idev = ip6_dst_idev(dst); unsigned int hh_len = LL_RESERVED_SPACE(dev); const struct in6_addr *daddr, *nexthop; @@ -232,8 +232,9 @@ static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *s int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev; - struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); + struct dst_entry *dst = skb_dst(skb); + struct net_device *dev = dst_dev(dst), *indev = skb->dev; + struct inet6_dev *idev = ip6_dst_idev(dst); skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; @@ -271,7 +272,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, const struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *first_hop = &fl6->daddr; struct dst_entry *dst = skb_dst(skb); - struct net_device *dev = dst->dev; + struct net_device *dev = dst_dev(dst); struct inet6_dev *idev = ip6_dst_idev(dst); struct hop_jumbo_hdr *hop_jumbo; int hoplen = sizeof(*hop_jumbo); @@ -503,7 +504,8 @@ int ip6_forward(struct sk_buff *skb) struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *hdr = ipv6_hdr(skb); struct inet6_skb_parm *opt = IP6CB(skb); - struct net *net = dev_net(dst->dev); + struct net *net = dev_net(dst_dev(dst)); + struct net_device *dev; struct inet6_dev *idev; SKB_DR(reason); u32 mtu; @@ -591,12 +593,12 @@ int ip6_forward(struct sk_buff *skb) goto drop; } dst = skb_dst(skb); - + dev = dst_dev(dst); /* IPv6 specs say nothing about it, but it is clear that we cannot send redirects to source routed frames. We don't send redirects to frames decapsulated from IPsec. */ - if (IP6CB(skb)->iif == dst->dev->ifindex && + if (IP6CB(skb)->iif == dev->ifindex && opt->srcrt == 0 && !skb_sec_path(skb)) { struct in6_addr *target = NULL; struct inet_peer *peer; @@ -644,7 +646,7 @@ int ip6_forward(struct sk_buff *skb) if (ip6_pkt_too_big(skb, mtu)) { /* Again, force OUTPUT device used as source address */ - skb->dev = dst->dev; + skb->dev = dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); __IP6_INC_STATS(net, idev, IPSTATS_MIB_INTOOBIGERRORS); __IP6_INC_STATS(net, ip6_dst_idev(dst), @@ -653,7 +655,7 @@ int ip6_forward(struct sk_buff *skb) return -EMSGSIZE; } - if (skb_cow(skb, dst->dev->hard_header_len)) { + if (skb_cow(skb, dev->hard_header_len)) { __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS); goto drop; @@ -666,7 +668,7 @@ int ip6_forward(struct sk_buff *skb) hdr->hop_limit--; return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, - net, NULL, skb, skb->dev, dst->dev, + net, NULL, skb, skb->dev, dev, ip6_forward_finish); error: @@ -1093,7 +1095,7 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk, #ifdef CONFIG_IPV6_SUBTREES ip6_rt_check(&rt->rt6i_src, &fl6->saddr, np->saddr_cache) || #endif - (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex)) { + (fl6->flowi6_oif && fl6->flowi6_oif != dst_dev(dst)->ifindex)) { dst_release(dst); dst = NULL; } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index a885bb5c98ea..3262e81223df 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -632,7 +632,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } else { if (ip_route_input(skb2, eiph->daddr, eiph->saddr, ip4h_dscp(eiph), skb2->dev) || - skb_dst(skb2)->dev->type != ARPHRD_TUNNEL6) + skb_dst_dev(skb2)->type != ARPHRD_TUNNEL6) goto out; } @@ -1179,7 +1179,7 @@ route_lookup: ndst = dst; } - tdev = dst->dev; + tdev = dst_dev(dst); if (tdev == dev) { DEV_STATS_INC(dev, collisions); @@ -1255,7 +1255,7 @@ route_lookup: /* Calculate max headroom for all the headers and adjust * needed_headroom if necessary. */ - max_headroom = LL_RESERVED_SPACE(dst->dev) + sizeof(struct ipv6hdr) + max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr) + dst->header_len + t->hlen; if (max_headroom > READ_ONCE(dev->needed_headroom)) WRITE_ONCE(dev->needed_headroom, max_headroom); @@ -1562,11 +1562,22 @@ static void ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) netdev_state_change(t->dev); } -static void ip6_tnl0_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) +static int ip6_tnl0_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p, + bool strict) { - /* for default tnl0 device allow to change only the proto */ + /* For the default ip6tnl0 device, allow changing only the protocol + * (the IP6_TNL_F_CAP_PER_PACKET flag is set on ip6tnl0, and all other + * parameters are 0). + */ + if (strict && + (!ipv6_addr_any(&p->laddr) || !ipv6_addr_any(&p->raddr) || + p->flags != t->parms.flags || p->hop_limit || p->encap_limit || + p->flowinfo || p->link || p->fwmark || p->collect_md)) + return -EINVAL; + t->parms.proto = p->proto; netdev_state_change(t->dev); + return 0; } static void @@ -1680,7 +1691,7 @@ ip6_tnl_siocdevprivate(struct net_device *dev, struct ifreq *ifr, } else t = netdev_priv(dev); if (dev == ip6n->fb_tnl_dev) - ip6_tnl0_update(t, &p1); + ip6_tnl0_update(t, &p1, false); else ip6_tnl_update(t, &p1); } @@ -2053,8 +2064,28 @@ static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct ip_tunnel_encap ipencap; - if (dev == ip6n->fb_tnl_dev) - return -EINVAL; + if (dev == ip6n->fb_tnl_dev) { + if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { + /* iproute2 always sets TUNNEL_ENCAP_FLAG_CSUM6, so + * let's ignore this flag. + */ + ipencap.flags &= ~TUNNEL_ENCAP_FLAG_CSUM6; + if (memchr_inv(&ipencap, 0, sizeof(ipencap))) { + NL_SET_ERR_MSG(extack, + "Only protocol can be changed for fallback tunnel, not encap params"); + return -EINVAL; + } + } + + ip6_tnl_netlink_parms(data, &p); + if (ip6_tnl0_update(t, &p, true) < 0) { + NL_SET_ERR_MSG(extack, + "Only protocol can be changed for fallback tunnel"); + return -EINVAL; + } + + return 0; + } if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { int err = ip6_tnl_encap_setup(t, &ipencap); diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c index 8ebe17a6058a..0ff547a4bff7 100644 --- a/net/ipv6/ip6_udp_tunnel.c +++ b/net/ipv6/ip6_udp_tunnel.c @@ -168,7 +168,7 @@ struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb, netdev_dbg(dev, "no route to %pI6\n", &fl6.daddr); return ERR_PTR(-ENETUNREACH); } - if (dst->dev == dev) { /* is this necessary? */ + if (dst_dev(dst) == dev) { /* is this necessary? */ netdev_dbg(dev, "circular route to %pI6\n", &fl6.daddr); dst_release(dst); return ERR_PTR(-ELOOP); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 40464a88bca6..ad5290be4dd6 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -497,7 +497,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) (const struct in6_addr *)&x->id.daddr)) goto tx_err_link_failure; - tdev = dst->dev; + tdev = dst_dev(dst); if (tdev == dev) { DEV_STATS_INC(dev, collisions); @@ -529,7 +529,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) xmit: skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); skb_dst_set(skb, dst); - skb->dev = skb_dst(skb)->dev; + skb->dev = dst_dev(dst); err = dst_output(t->net, skb->sk, skb); if (net_xmit_eval(err) == 0) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index a35f4f1c6589..e047a4680ab0 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -2301,21 +2301,20 @@ dont_forward: int ip6_mr_input(struct sk_buff *skb) { + struct net_device *dev = skb->dev; + struct net *net = dev_net_rcu(dev); struct mfc6_cache *cache; - struct net *net = dev_net(skb->dev); struct mr_table *mrt; struct flowi6 fl6 = { - .flowi6_iif = skb->dev->ifindex, + .flowi6_iif = dev->ifindex, .flowi6_mark = skb->mark, }; int err; - struct net_device *dev; /* skb->dev passed in is the master dev for vrfs. * Get the proper interface that does have a vif associated with it. */ - dev = skb->dev; - if (netif_is_l3_master(skb->dev)) { + if (netif_is_l3_master(dev)) { dev = dev_get_by_index_rcu(net, IPCB(skb)->iif); if (!dev) { kfree_skb(skb); @@ -2373,7 +2372,7 @@ int ip6_mr_output(struct net *net, struct sock *sk, struct sk_buff *skb) int err; int vif; - WARN_ON_ONCE(!rcu_read_lock_held()); + guard(rcu)(); if (IP6CB(skb)->flags & IP6SKB_FORWARDED) goto ip6_output; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index ecb5c4b8518f..f2299b61221b 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -473,6 +473,7 @@ void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr, { struct icmp6hdr *icmp6h = icmp6_hdr(skb); struct dst_entry *dst = skb_dst(skb); + struct net_device *dev; struct inet6_dev *idev; struct net *net; struct sock *sk; @@ -507,11 +508,12 @@ void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr, ip6_nd_hdr(skb, saddr, daddr, READ_ONCE(inet6_sk(sk)->hop_limit), skb->len); - idev = __in6_dev_get(dst->dev); + dev = dst_dev(dst); + idev = __in6_dev_get(dev); IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, - net, sk, skb, NULL, dst->dev, + net, sk, skb, NULL, dev, dst_output); if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 4541836ee3da..45f9105f9ac1 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -24,7 +24,7 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff { const struct ipv6hdr *iph = ipv6_hdr(skb); struct sock *sk = sk_to_full_sk(sk_partial); - struct net_device *dev = skb_dst(skb)->dev; + struct net_device *dev = skb_dst_dev(skb); struct flow_keys flkeys; unsigned int hh_len; struct dst_entry *dst; @@ -72,7 +72,7 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff #endif /* Change in oif may mean change in hh_len. */ - hh_len = skb_dst(skb)->dev->hard_header_len; + hh_len = skb_dst_dev(skb)->hard_header_len; if (skb_headroom(skb) < hh_len && pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)), 0, GFP_ATOMIC)) diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c index b903c62c00c9..6da3102b7c1b 100644 --- a/net/ipv6/netfilter/nf_dup_ipv6.c +++ b/net/ipv6/netfilter/nf_dup_ipv6.c @@ -38,7 +38,7 @@ static bool nf_dup_ipv6_route(struct net *net, struct sk_buff *skb, } skb_dst_drop(skb); skb_dst_set(skb, dst); - skb->dev = dst->dev; + skb->dev = dst_dev(dst); skb->protocol = htons(ETH_P_IPV6); return true; diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index 9ae2b2725bf9..838295fa32e3 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -300,7 +300,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, skb_dst_set(oldskb, dst); } - fl6.flowi6_oif = l3mdev_master_ifindex(skb_dst(oldskb)->dev); + fl6.flowi6_oif = l3mdev_master_ifindex(skb_dst_dev(oldskb)); fl6.flowi6_mark = IP6_REPLY_MARK(net, oldskb->mark); security_skb_classify_flow(oldskb, flowi6_to_flowi_common(&fl6)); dst = ip6_route_output(net, NULL, &fl6); diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 806d4b5dd1e6..d21fe27fe21e 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -105,7 +105,7 @@ int ip6_dst_hoplimit(struct dst_entry *dst) { int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); if (hoplimit == 0) { - struct net_device *dev = dst->dev; + struct net_device *dev = dst_dev(dst); struct inet6_dev *idev; rcu_read_lock(); @@ -141,7 +141,7 @@ int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) skb->protocol = htons(ETH_P_IPV6); return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, - net, sk, skb, NULL, skb_dst(skb)->dev, + net, sk, skb, NULL, skb_dst_dev(skb), dst_output); } EXPORT_SYMBOL_GPL(__ip6_local_out); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 7d4bcf3fda5b..25ec8001898d 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -104,11 +104,11 @@ fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif) return container_of(q, struct frag_queue, q); } -static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, +static int ip6_frag_queue(struct net *net, + struct frag_queue *fq, struct sk_buff *skb, struct frag_hdr *fhdr, int nhoff, u32 *prob_offset, int *refs) { - struct net *net = dev_net(skb_dst(skb)->dev); int offset, end, fragsize; struct sk_buff *prev_tail; struct net_device *dev; @@ -324,10 +324,10 @@ out_fail: static int ipv6_frag_rcv(struct sk_buff *skb) { + const struct ipv6hdr *hdr = ipv6_hdr(skb); + struct net *net = skb_dst_dev_net(skb); struct frag_hdr *fhdr; struct frag_queue *fq; - const struct ipv6hdr *hdr = ipv6_hdr(skb); - struct net *net = dev_net(skb_dst(skb)->dev); u8 nexthdr; int iif; @@ -384,7 +384,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) spin_lock(&fq->q.lock); fq->iif = iif; - ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff, + ret = ip6_frag_queue(net, fq, skb, fhdr, IP6CB(skb)->nhoff, &prob_offset, &refs); spin_unlock(&fq->q.lock); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 46a4f9d1900f..3fbe0885c21c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -228,13 +228,13 @@ static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst, const struct rt6_info *rt = dst_rt6_info(dst); return ip6_neigh_lookup(rt6_nexthop(rt, &in6addr_any), - dst->dev, skb, daddr); + dst_dev(dst), skb, daddr); } static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr) { const struct rt6_info *rt = dst_rt6_info(dst); - struct net_device *dev = dst->dev; + struct net_device *dev = dst_dev(dst); daddr = choose_neigh_daddr(rt6_nexthop(rt, &in6addr_any), NULL, daddr); if (!daddr) @@ -391,9 +391,8 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev) static bool __rt6_check_expired(const struct rt6_info *rt) { if (rt->rt6i_flags & RTF_EXPIRES) - return time_after(jiffies, rt->dst.expires); - else - return false; + return time_after(jiffies, READ_ONCE(rt->dst.expires)); + return false; } static bool rt6_check_expired(const struct rt6_info *rt) @@ -403,10 +402,10 @@ static bool rt6_check_expired(const struct rt6_info *rt) from = rcu_dereference(rt->from); if (rt->rt6i_flags & RTF_EXPIRES) { - if (time_after(jiffies, rt->dst.expires)) + if (time_after(jiffies, READ_ONCE(rt->dst.expires))) return true; } else if (from) { - return rt->dst.obsolete != DST_OBSOLETE_FORCE_CHK || + return READ_ONCE(rt->dst.obsolete) != DST_OBSOLETE_FORCE_CHK || fib6_check_expired(from); } return false; @@ -2134,12 +2133,13 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket, * expired, independently from their aging, as per RFC 8201 section 4 */ if (!(rt->rt6i_flags & RTF_EXPIRES)) { - if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) { + if (time_after_eq(now, READ_ONCE(rt->dst.lastuse) + + gc_args->timeout)) { pr_debug("aging clone %p\n", rt); rt6_remove_exception(bucket, rt6_ex); return; } - } else if (time_after(jiffies, rt->dst.expires)) { + } else if (time_after(jiffies, READ_ONCE(rt->dst.expires))) { pr_debug("purging expired route %p\n", rt); rt6_remove_exception(bucket, rt6_ex); return; @@ -2777,11 +2777,10 @@ static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie) { if (!__rt6_check_expired(rt) && - rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && + READ_ONCE(rt->dst.obsolete) == DST_OBSOLETE_FORCE_CHK && fib6_check(from, cookie)) return &rt->dst; - else - return NULL; + return NULL; } INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, @@ -2871,7 +2870,7 @@ static void rt6_update_expires(struct rt6_info *rt0, int timeout) rcu_read_lock(); from = rcu_dereference(rt0->from); if (from) - rt0->dst.expires = from->expires; + WRITE_ONCE(rt0->dst.expires, from->expires); rcu_read_unlock(); } @@ -2944,7 +2943,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, if (res.f6i->nh) { struct fib6_nh_match_arg arg = { - .dev = dst->dev, + .dev = dst_dev(dst), .gw = &rt6->rt6i_gateway, }; @@ -3014,7 +3013,7 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu) sk_uid(sk)); dst = __sk_dst_get(sk); - if (!dst || !dst->obsolete || + if (!dst || !READ_ONCE(dst->obsolete) || dst->ops->check(dst, inet6_sk(sk)->dst_cookie)) return; @@ -3239,7 +3238,7 @@ EXPORT_SYMBOL_GPL(ip6_sk_redirect); static unsigned int ip6_default_advmss(const struct dst_entry *dst) { - struct net_device *dev = dst->dev; + struct net_device *dev = dst_dev(dst); unsigned int mtu = dst_mtu(dst); struct net *net; @@ -4302,7 +4301,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu if (res.f6i->nh) { struct fib6_nh_match_arg arg = { - .dev = dst->dev, + .dev = dst_dev(dst), .gw = &rt->rt6i_gateway, }; @@ -4588,13 +4587,14 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg) static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes) { struct dst_entry *dst = skb_dst(skb); - struct net *net = dev_net(dst->dev); + struct net_device *dev = dst_dev(dst); + struct net *net = dev_net(dev); struct inet6_dev *idev; SKB_DR(reason); int type; if (netif_is_l3_master(skb->dev) || - dst->dev == net->loopback_dev) + dev == net->loopback_dev) idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); else idev = ip6_dst_idev(dst); @@ -4631,7 +4631,7 @@ static int ip6_pkt_discard(struct sk_buff *skb) static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) { - skb->dev = skb_dst(skb)->dev; + skb->dev = skb_dst_dev(skb); return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES); } @@ -4642,7 +4642,7 @@ static int ip6_pkt_prohibit(struct sk_buff *skb) static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb) { - skb->dev = skb_dst(skb)->dev; + skb->dev = skb_dst_dev(skb); return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES); } @@ -5845,11 +5845,14 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, * each as a nexthop within RTA_MULTIPATH. */ if (rt6) { + struct net_device *dev; + if (rt6_flags & RTF_GATEWAY && nla_put_in6_addr(skb, RTA_GATEWAY, &rt6->rt6i_gateway)) goto nla_put_failure; - if (dst->dev && nla_put_u32(skb, RTA_OIF, dst->dev->ifindex)) + dev = dst_dev(dst); + if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex)) goto nla_put_failure; if (lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) @@ -5904,7 +5907,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, } if (rt6_flags & RTF_EXPIRES) { - expires = dst ? dst->expires : rt->expires; + expires = dst ? READ_ONCE(dst->expires) : rt->expires; expires -= jiffies; } diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c index 7c05ac846646..1f41f53fbaff 100644 --- a/net/ipv6/rpl_iptunnel.c +++ b/net/ipv6/rpl_iptunnel.c @@ -242,7 +242,7 @@ static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb) local_bh_enable(); } - err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); + err = skb_cow_head(skb, LL_RESERVED_SPACE(dst_dev(dst))); if (unlikely(err)) goto drop; } @@ -297,7 +297,7 @@ static int rpl_input(struct sk_buff *skb) local_bh_enable(); } - err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); + err = skb_cow_head(skb, LL_RESERVED_SPACE(dst_dev(dst))); if (unlikely(err)) goto drop; } else { diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 51583461ae29..3e1b9991131a 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -128,7 +128,8 @@ static int __seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto, struct dst_entry *cache_dst) { struct dst_entry *dst = skb_dst(skb); - struct net *net = dev_net(dst->dev); + struct net_device *dev = dst_dev(dst); + struct net *net = dev_net(dev); struct ipv6hdr *hdr, *inner_hdr; struct ipv6_sr_hdr *isrh; int hdrlen, tot_len, err; @@ -181,7 +182,7 @@ static int __seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, isrh->nexthdr = proto; hdr->daddr = isrh->segments[isrh->first_segment]; - set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr); + set_tun_src(net, dev, &hdr->daddr, &hdr->saddr); #ifdef CONFIG_IPV6_SEG6_HMAC if (sr_has_hmac(isrh)) { @@ -212,7 +213,8 @@ static int seg6_do_srh_encap_red(struct sk_buff *skb, { __u8 first_seg = osrh->first_segment; struct dst_entry *dst = skb_dst(skb); - struct net *net = dev_net(dst->dev); + struct net_device *dev = dst_dev(dst); + struct net *net = dev_net(dev); struct ipv6hdr *hdr, *inner_hdr; int hdrlen = ipv6_optlen(osrh); int red_tlv_offset, tlv_offset; @@ -270,7 +272,7 @@ static int seg6_do_srh_encap_red(struct sk_buff *skb, if (skip_srh) { hdr->nexthdr = proto; - set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr); + set_tun_src(net, dev, &hdr->daddr, &hdr->saddr); goto out; } @@ -306,7 +308,7 @@ static int seg6_do_srh_encap_red(struct sk_buff *skb, srcaddr: isrh->nexthdr = proto; - set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr); + set_tun_src(net, dev, &hdr->daddr, &hdr->saddr); #ifdef CONFIG_IPV6_SEG6_HMAC if (unlikely(!skip_srh && sr_has_hmac(isrh))) { @@ -362,7 +364,7 @@ static int __seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, #ifdef CONFIG_IPV6_SEG6_HMAC if (sr_has_hmac(isrh)) { - struct net *net = dev_net(skb_dst(skb)->dev); + struct net *net = skb_dst_dev_net(skb); err = seg6_push_hmac(net, &hdr->saddr, isrh); if (unlikely(err)) @@ -507,7 +509,7 @@ static int seg6_input_core(struct net *net, struct sock *sk, local_bh_enable(); } - err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); + err = skb_cow_head(skb, LL_RESERVED_SPACE(dst_dev(dst))); if (unlikely(err)) goto drop; } else { @@ -518,7 +520,7 @@ static int seg6_input_core(struct net *net, struct sock *sk, if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, dev_net(skb->dev), NULL, skb, NULL, - skb_dst(skb)->dev, seg6_input_finish); + skb_dst_dev(skb), seg6_input_finish); return seg6_input_finish(dev_net(skb->dev), NULL, skb); drop: @@ -528,7 +530,7 @@ drop: static int seg6_input_nf(struct sk_buff *skb) { - struct net_device *dev = skb_dst(skb)->dev; + struct net_device *dev = skb_dst_dev(skb); struct net *net = dev_net(skb->dev); switch (skb->protocol) { @@ -593,7 +595,7 @@ static int seg6_output_core(struct net *net, struct sock *sk, local_bh_enable(); } - err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); + err = skb_cow_head(skb, LL_RESERVED_SPACE(dst_dev(dst))); if (unlikely(err)) goto drop; } @@ -603,7 +605,7 @@ static int seg6_output_core(struct net *net, struct sock *sk, if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, - NULL, skb_dst(skb)->dev, dst_output); + NULL, dst_dev(dst), dst_output); return dst_output(net, sk, skb); drop: @@ -614,7 +616,7 @@ drop: static int seg6_output_nf(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net_device *dev = skb_dst(skb)->dev; + struct net_device *dev = skb_dst_dev(skb); switch (skb->protocol) { case htons(ETH_P_IP): diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index dfa825ee870e..2b41e4c0dddd 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -313,7 +313,7 @@ seg6_lookup_any_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, if (!local_delivery) dev_flags |= IFF_LOOPBACK; - if (dst && (dst->dev->flags & dev_flags) && !dst->error) { + if (dst && (dst_dev(dst)->flags & dev_flags) && !dst->error) { dst_release(dst); dst = NULL; } @@ -2087,7 +2087,7 @@ struct nla_policy seg6_local_flavors_policy[SEG6_LOCAL_FLV_MAX + 1] = { static int seg6_chk_next_csid_cfg(__u8 block_len, __u8 func_len) { /* Locator-Block and Locator-Node Function cannot exceed 128 bits - * (i.e. C-SID container lenghts). + * (i.e. C-SID container length). */ if (next_csid_chk_cntr_bits(block_len, func_len)) return -EINVAL; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f0ce62549d90..8f2c3cba1f1f 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -41,6 +41,7 @@ #include <linux/random.h> #include <linux/indirect_call_wrapper.h> +#include <net/aligned_data.h> #include <net/tcp.h> #include <net/ndisc.h> #include <net/inet6_hashtables.h> @@ -835,7 +836,6 @@ static struct dst_entry *tcp_v6_route_req(const struct sock *sk, struct request_sock_ops tcp6_request_sock_ops __read_mostly = { .family = AF_INET6, .obj_size = sizeof(struct tcp6_request_sock), - .rtx_syn_ack = tcp_rtx_synack, .send_ack = tcp_v6_reqsk_send_ack, .destructor = tcp_v6_reqsk_destructor, .send_reset = tcp_v6_send_reset, @@ -868,7 +868,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 int oif, int rst, u8 tclass, __be32 label, u32 priority, u32 txhash, struct tcp_key *key) { - struct net *net = sk ? sock_net(sk) : dev_net_rcu(skb_dst(skb)->dev); + struct net *net = sk ? sock_net(sk) : skb_dst_dev_net_rcu(skb); unsigned int tot_len = sizeof(struct tcphdr); struct sock *ctl_sk = net->ipv6.tcp_sk; const struct tcphdr *th = tcp_hdr(skb); @@ -1043,7 +1043,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb, if (!sk && !ipv6_unicast_destination(skb)) return; - net = sk ? sock_net(sk) : dev_net_rcu(skb_dst(skb)->dev); + net = sk ? sock_net(sk) : skb_dst_dev_net_rcu(skb); /* Invalid TCP option size or twice included auth */ if (tcp_parse_auth_options(th, &md5_hash_location, &aoh)) return; @@ -2357,7 +2357,7 @@ struct proto tcpv6_prot = { .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, - .memory_allocated = &tcp_memory_allocated, + .memory_allocated = &net_aligned_data.tcp_memory_allocated, .per_cpu_fw_alloc = &tcp_memory_per_cpu_fw_alloc, .memory_pressure = &tcp_memory_pressure, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index ebb95d8bc681..6bbdadbd5fec 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1925,7 +1925,7 @@ struct proto udpv6_prot = { .psock_update_sk_prot = udp_bpf_update_proto, #endif - .memory_allocated = &udp_memory_allocated, + .memory_allocated = &net_aligned_data.udp_memory_allocated, .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, .sysctl_mem = sysctl_udp_mem, diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h index 0590f566379d..8a406be25a3a 100644 --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _UDP6_IMPL_H #define _UDP6_IMPL_H +#include <net/aligned_data.h> #include <net/udp.h> #include <net/udplite.h> #include <net/protocol.h> diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index a60bec9b14f1..2cec542437f7 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -59,7 +59,7 @@ struct proto udplitev6_prot = { .rehash = udp_v6_rehash, .get_port = udp_v6_get_port, - .memory_allocated = &udp_memory_allocated, + .memory_allocated = &net_aligned_data.udp_memory_allocated, .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, .sysctl_mem = sysctl_udp_mem, diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index b3d5d1f266ee..512bdaf13699 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -106,7 +106,7 @@ skip_frag: int xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, - net, sk, skb, skb->dev, skb_dst(skb)->dev, + net, sk, skb, skb->dev, skb_dst_dev(skb), __xfrm6_output, !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 8699755081ad..caa3e6b3f46e 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4245,10 +4245,16 @@ static bool ieee80211_rx_data_set_sta(struct ieee80211_rx_data *rx, rx->link_sta = NULL; } - if (link_id < 0) - rx->link = &rx->sdata->deflink; - else if (!ieee80211_rx_data_set_link(rx, link_id)) + if (link_id < 0) { + if (ieee80211_vif_is_mld(&rx->sdata->vif) && + sta && !sta->sta.valid_links) + rx->link = + rcu_dereference(rx->sdata->link[sta->deflink.link_id]); + else + rx->link = &rx->sdata->deflink; + } else if (!ieee80211_rx_data_set_link(rx, link_id)) { return false; + } return true; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e7972e633236..5f904fc5ac4c 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -11,6 +11,7 @@ #include <linux/netdevice.h> #include <linux/sched/signal.h> #include <linux/atomic.h> +#include <net/aligned_data.h> #include <net/sock.h> #include <net/inet_common.h> #include <net/inet_hashtables.h> @@ -3729,7 +3730,7 @@ static struct proto mptcp_prot = { .stream_memory_free = mptcp_stream_memory_free, .sockets_allocated = &mptcp_sockets_allocated, - .memory_allocated = &tcp_memory_allocated, + .memory_allocated = &net_aligned_data.tcp_memory_allocated, .per_cpu_fw_alloc = &tcp_memory_per_cpu_fw_alloc, .memory_pressure = &tcp_memory_pressure, diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 014f07740369..95af252b2939 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -97,7 +97,7 @@ __ip_vs_dst_check(struct ip_vs_dest *dest) if (!dest_dst) return NULL; dst = dest_dst->dst_cache; - if (dst->obsolete && + if (READ_ONCE(dst->obsolete) && dst->ops->check(dst, dest_dst->dst_cookie) == NULL) return NULL; return dest_dst; diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index 2dd6bd3a3011..b72bf8a08d48 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -497,22 +497,15 @@ void rose_rt_device_down(struct net_device *dev) t = rose_node; rose_node = rose_node->next; - for (i = 0; i < t->count; i++) { + for (i = t->count - 1; i >= 0; i--) { if (t->neighbour[i] != s) continue; t->count--; - switch (i) { - case 0: - t->neighbour[0] = t->neighbour[1]; - fallthrough; - case 1: - t->neighbour[1] = t->neighbour[2]; - break; - case 2: - break; - } + memmove(&t->neighbour[i], &t->neighbour[i + 1], + sizeof(t->neighbour[0]) * + (t->count - i)); } if (t->count <= 0) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index c5e3673aadbe..d8a33486c511 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -780,15 +780,12 @@ static u32 qdisc_alloc_handle(struct net_device *dev) void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len) { - bool qdisc_is_offloaded = sch->flags & TCQ_F_OFFLOADED; const struct Qdisc_class_ops *cops; unsigned long cl; u32 parentid; bool notify; int drops; - if (n == 0 && len == 0) - return; drops = max_t(int, n, 0); rcu_read_lock(); while ((parentid = sch->parent)) { @@ -797,17 +794,8 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len) if (sch->flags & TCQ_F_NOPARENT) break; - /* Notify parent qdisc only if child qdisc becomes empty. - * - * If child was empty even before update then backlog - * counter is screwed and we skip notification because - * parent class is already passive. - * - * If the original child was offloaded then it is allowed - * to be seem as empty, so the parent is notified anyway. - */ - notify = !sch->q.qlen && !WARN_ON_ONCE(!n && - !qdisc_is_offloaded); + /* Notify parent qdisc only if child qdisc becomes empty. */ + notify = !sch->q.qlen; /* TODO: perform the search on a per txq basis */ sch = qdisc_lookup_rcu(qdisc_dev(sch), TC_H_MAJ(parentid)); if (sch == NULL) { @@ -816,6 +804,9 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len) } cops = sch->ops->cl_ops; if (notify && cops->qlen_notify) { + /* Note that qlen_notify must be idempotent as it may get called + * multiple times. + */ cl = cops->find(sch, parentid); cops->qlen_notify(sch, cl); } diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 6946c1462793..4d258a6e8033 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -240,7 +240,7 @@ void sctp_transport_set_owner(struct sctp_transport *transport, void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) { /* If we don't have a fresh route, look one up */ - if (!transport->dst || transport->dst->obsolete) { + if (!transport->dst || READ_ONCE(transport->dst->obsolete)) { sctp_transport_dst_release(transport); transport->af_specific->get_dst(transport, &transport->saddr, &transport->fl, sk); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 0fa244f16876..7b943fbafcc3 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1724,7 +1724,7 @@ gss_validate(struct rpc_task *task, struct xdr_stream *xdr) maj_stat = gss_validate_seqno_mic(ctx, task->tk_rqstp->rq_seqnos[0], seq, p, len); /* RFC 2203 5.3.3.1 - compute the checksum of each sequence number in the cache */ while (unlikely(maj_stat == GSS_S_BAD_SIG && i < task->tk_rqstp->rq_seqno_count)) - maj_stat = gss_validate_seqno_mic(ctx, task->tk_rqstp->rq_seqnos[i], seq, p, len); + maj_stat = gss_validate_seqno_mic(ctx, task->tk_rqstp->rq_seqnos[i++], seq, p, len); if (maj_stat == GSS_S_CONTEXT_EXPIRED) clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags); if (maj_stat) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index fc88e34b7f33..549d1ea01a72 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -872,6 +872,19 @@ more_data: delta = msg->sg.size; psock->eval = sk_psock_msg_verdict(sk, psock, msg); delta -= msg->sg.size; + + if ((s32)delta > 0) { + /* It indicates that we executed bpf_msg_pop_data(), + * causing the plaintext data size to decrease. + * Therefore the encrypted data size also needs to + * correspondingly decrease. We only need to subtract + * delta to calculate the new ciphertext length since + * ktls does not support block encryption. + */ + struct sk_msg *enc = &ctx->open_rec->msg_encrypted; + + sk_msg_trim(sk, enc, enc->sg.size - delta); + } } if (msg->cork_bytes && msg->cork_bytes > msg->sg.size && !enospc && !full_record) { diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index b370070194fa..7eccd6708d66 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -119,6 +119,8 @@ vmci_transport_packet_init(struct vmci_transport_packet *pkt, u16 proto, struct vmci_handle handle) { + memset(pkt, 0, sizeof(*pkt)); + /* We register the stream control handler as an any cid handle so we * must always send from a source address of VMADDR_CID_ANY */ @@ -131,8 +133,6 @@ vmci_transport_packet_init(struct vmci_transport_packet *pkt, pkt->type = type; pkt->src_port = src->svm_port; pkt->dst_port = dst->svm_port; - memset(&pkt->proto, 0, sizeof(pkt->proto)); - memset(&pkt->_reserved2, 0, sizeof(pkt->_reserved2)); switch (pkt->type) { case VMCI_TRANSPORT_PACKET_TYPE_INVALID: diff --git a/net/wireless/reg.c b/net/wireless/reg.c index c1752b31734f..2524bc187a19 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -53,7 +53,7 @@ #include <linux/list.h> #include <linux/ctype.h> #include <linux/nl80211.h> -#include <linux/platform_device.h> +#include <linux/device/faux.h> #include <linux/verification.h> #include <linux/moduleparam.h> #include <linux/firmware.h> @@ -105,7 +105,7 @@ static struct regulatory_request __rcu *last_request = (void __force __rcu *)&core_request_world; /* To trigger userspace events and load firmware */ -static struct platform_device *reg_pdev; +static struct faux_device *reg_fdev; /* * Central wireless core regulatory domains, we only need two, @@ -583,7 +583,7 @@ static int call_crda(const char *alpha2) else pr_debug("Calling CRDA to update world regulatory domain\n"); - ret = kobject_uevent_env(®_pdev->dev.kobj, KOBJ_CHANGE, env); + ret = kobject_uevent_env(®_fdev->dev.kobj, KOBJ_CHANGE, env); if (ret) return ret; @@ -779,7 +779,7 @@ static bool regdb_has_valid_signature(const u8 *data, unsigned int size) const struct firmware *sig; bool result; - if (request_firmware(&sig, "regulatory.db.p7s", ®_pdev->dev)) + if (request_firmware(&sig, "regulatory.db.p7s", ®_fdev->dev)) return false; result = verify_pkcs7_signature(data, size, sig->data, sig->size, @@ -1061,7 +1061,7 @@ static int query_regdb_file(const char *alpha2) return -ENOMEM; err = request_firmware_nowait(THIS_MODULE, true, "regulatory.db", - ®_pdev->dev, GFP_KERNEL, + ®_fdev->dev, GFP_KERNEL, (void *)alpha2, regdb_fw_cb); if (err) kfree(alpha2); @@ -1077,7 +1077,7 @@ int reg_reload_regdb(void) const struct ieee80211_regdomain *current_regdomain; struct regulatory_request *request; - err = request_firmware(&fw, "regulatory.db", ®_pdev->dev); + err = request_firmware(&fw, "regulatory.db", ®_fdev->dev); if (err) return err; @@ -4300,12 +4300,12 @@ static int __init regulatory_init_db(void) * in that case, don't try to do any further work here as * it's doomed to lead to crashes. */ - if (IS_ERR_OR_NULL(reg_pdev)) + if (!reg_fdev) return -EINVAL; err = load_builtin_regdb_keys(); if (err) { - platform_device_unregister(reg_pdev); + faux_device_destroy(reg_fdev); return err; } @@ -4313,7 +4313,7 @@ static int __init regulatory_init_db(void) err = regulatory_hint_core(cfg80211_world_regdom->alpha2); if (err) { if (err == -ENOMEM) { - platform_device_unregister(reg_pdev); + faux_device_destroy(reg_fdev); return err; } /* @@ -4342,9 +4342,9 @@ late_initcall(regulatory_init_db); int __init regulatory_init(void) { - reg_pdev = platform_device_register_simple("regulatory", 0, NULL, 0); - if (IS_ERR(reg_pdev)) - return PTR_ERR(reg_pdev); + reg_fdev = faux_device_create("regulatory", NULL, NULL); + if (!reg_fdev) + return -ENODEV; rcu_assign_pointer(cfg80211_regdomain, cfg80211_world_regdom); @@ -4372,9 +4372,9 @@ void regulatory_exit(void) reset_regdomains(true, NULL); rtnl_unlock(); - dev_set_uevent_suppress(®_pdev->dev, true); + dev_set_uevent_suppress(®_fdev->dev, true); - platform_device_unregister(reg_pdev); + faux_device_destroy(reg_fdev); list_for_each_entry_safe(reg_beacon, btmp, ®_pending_beacons, list) { list_del(®_beacon->list); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 094d2454602e..c5035a9bc3bb 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3925,7 +3925,7 @@ static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie) * This will force stale_bundle() to fail on any xdst bundle with * this dst linked in it. */ - if (dst->obsolete < 0 && !stale_bundle(dst)) + if (READ_ONCE(dst->obsolete) < 0 && !stale_bundle(dst)) return dst; return NULL; @@ -3953,7 +3953,7 @@ static void xfrm_link_failure(struct sk_buff *skb) static void xfrm_negative_advice(struct sock *sk, struct dst_entry *dst) { - if (dst->obsolete) + if (READ_ONCE(dst->obsolete)) sk_dst_reset(sk); } diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs index 32ea43ece646..b37de09651cb 100644 --- a/rust/kernel/net/phy.rs +++ b/rust/kernel/net/phy.rs @@ -163,20 +163,20 @@ impl Device { let phydev = self.0.get(); // SAFETY: The struct invariant ensures that we may access // this field without additional synchronization. - unsafe { (*phydev).speed = speed as i32 }; + unsafe { (*phydev).speed = speed as c_int }; } /// Sets duplex mode. pub fn set_duplex(&mut self, mode: DuplexMode) { let phydev = self.0.get(); let v = match mode { - DuplexMode::Full => bindings::DUPLEX_FULL as i32, - DuplexMode::Half => bindings::DUPLEX_HALF as i32, - DuplexMode::Unknown => bindings::DUPLEX_UNKNOWN as i32, + DuplexMode::Full => bindings::DUPLEX_FULL, + DuplexMode::Half => bindings::DUPLEX_HALF, + DuplexMode::Unknown => bindings::DUPLEX_UNKNOWN, }; // SAFETY: The struct invariant ensures that we may access // this field without additional synchronization. - unsafe { (*phydev).duplex = v }; + unsafe { (*phydev).duplex = v as c_int }; } /// Reads a PHY register. @@ -312,9 +312,7 @@ impl<T: Driver> Adapter<T> { /// # Safety /// /// `phydev` must be passed by the corresponding callback in `phy_driver`. - unsafe extern "C" fn soft_reset_callback( - phydev: *mut bindings::phy_device, - ) -> crate::ffi::c_int { + unsafe extern "C" fn soft_reset_callback(phydev: *mut bindings::phy_device) -> c_int { from_result(|| { // SAFETY: This callback is called only in contexts // where we hold `phy_device->lock`, so the accessors on @@ -328,7 +326,7 @@ impl<T: Driver> Adapter<T> { /// # Safety /// /// `phydev` must be passed by the corresponding callback in `phy_driver`. - unsafe extern "C" fn probe_callback(phydev: *mut bindings::phy_device) -> crate::ffi::c_int { + unsafe extern "C" fn probe_callback(phydev: *mut bindings::phy_device) -> c_int { from_result(|| { // SAFETY: This callback is called only in contexts // where we can exclusively access `phy_device` because @@ -343,9 +341,7 @@ impl<T: Driver> Adapter<T> { /// # Safety /// /// `phydev` must be passed by the corresponding callback in `phy_driver`. - unsafe extern "C" fn get_features_callback( - phydev: *mut bindings::phy_device, - ) -> crate::ffi::c_int { + unsafe extern "C" fn get_features_callback(phydev: *mut bindings::phy_device) -> c_int { from_result(|| { // SAFETY: This callback is called only in contexts // where we hold `phy_device->lock`, so the accessors on @@ -359,7 +355,7 @@ impl<T: Driver> Adapter<T> { /// # Safety /// /// `phydev` must be passed by the corresponding callback in `phy_driver`. - unsafe extern "C" fn suspend_callback(phydev: *mut bindings::phy_device) -> crate::ffi::c_int { + unsafe extern "C" fn suspend_callback(phydev: *mut bindings::phy_device) -> c_int { from_result(|| { // SAFETY: The C core code ensures that the accessors on // `Device` are okay to call even though `phy_device->lock` @@ -373,7 +369,7 @@ impl<T: Driver> Adapter<T> { /// # Safety /// /// `phydev` must be passed by the corresponding callback in `phy_driver`. - unsafe extern "C" fn resume_callback(phydev: *mut bindings::phy_device) -> crate::ffi::c_int { + unsafe extern "C" fn resume_callback(phydev: *mut bindings::phy_device) -> c_int { from_result(|| { // SAFETY: The C core code ensures that the accessors on // `Device` are okay to call even though `phy_device->lock` @@ -387,9 +383,7 @@ impl<T: Driver> Adapter<T> { /// # Safety /// /// `phydev` must be passed by the corresponding callback in `phy_driver`. - unsafe extern "C" fn config_aneg_callback( - phydev: *mut bindings::phy_device, - ) -> crate::ffi::c_int { + unsafe extern "C" fn config_aneg_callback(phydev: *mut bindings::phy_device) -> c_int { from_result(|| { // SAFETY: This callback is called only in contexts // where we hold `phy_device->lock`, so the accessors on @@ -403,9 +397,7 @@ impl<T: Driver> Adapter<T> { /// # Safety /// /// `phydev` must be passed by the corresponding callback in `phy_driver`. - unsafe extern "C" fn read_status_callback( - phydev: *mut bindings::phy_device, - ) -> crate::ffi::c_int { + unsafe extern "C" fn read_status_callback(phydev: *mut bindings::phy_device) -> c_int { from_result(|| { // SAFETY: This callback is called only in contexts // where we hold `phy_device->lock`, so the accessors on @@ -422,7 +414,7 @@ impl<T: Driver> Adapter<T> { unsafe extern "C" fn match_phy_device_callback( phydev: *mut bindings::phy_device, _phydrv: *const bindings::phy_driver, - ) -> crate::ffi::c_int { + ) -> c_int { // SAFETY: This callback is called only in contexts // where we hold `phy_device->lock`, so the accessors on // `Device` are okay to call. diff --git a/scripts/gdb/linux/vfs.py b/scripts/gdb/linux/vfs.py index c77b9ce75f6d..b5fbb18ccb77 100644 --- a/scripts/gdb/linux/vfs.py +++ b/scripts/gdb/linux/vfs.py @@ -22,7 +22,7 @@ def dentry_name(d): if parent == d or parent == 0: return "" p = dentry_name(d['d_parent']) + "/" - return p + d['d_iname'].string() + return p + d['d_shortname']['string'].string() class DentryName(gdb.Function): """Return string of the full path of a dentry. diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 2e1618494c20..5d6d01ecfee2 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2656,6 +2656,7 @@ static const struct hda_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX), SND_PCI_QUIRK(0x1558, 0x3702, "Clevo X370SN[VW]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x50d3, "Clevo PC50[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x5802, "Clevo X58[05]WN[RST]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65d1, "Clevo PB51[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65d2, "Clevo PB51R[CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65e1, "Clevo PB51[ED][DF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), @@ -6609,6 +6610,7 @@ static void alc294_fixup_bass_speaker_15(struct hda_codec *codec, if (action == HDA_FIXUP_ACT_PRE_PROBE) { static const hda_nid_t conn[] = { 0x02, 0x03 }; snd_hda_override_conn_list(codec, 0x15, ARRAY_SIZE(conn), conn); + snd_hda_gen_add_micmute_led_cdev(codec, NULL); } } @@ -10737,6 +10739,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8975, "HP EliteBook x360 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x897d, "HP mt440 Mobile Thin Client U74", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8981, "HP Elite Dragonfly G3", ALC245_FIXUP_CS35L41_SPI_4), + SND_PCI_QUIRK(0x103c, 0x898a, "HP Pavilion 15-eg100", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x898e, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x898f, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8991, "HP EliteBook 845 G9", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), @@ -10907,7 +10910,9 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8def, "HP EliteBook 660 G12", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8df0, "HP EliteBook 630 G12", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8df1, "HP EliteBook 630 G12", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8dfb, "HP EliteBook 6 G1a 14", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8dfc, "HP EliteBook 645 G12", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8dfd, "HP EliteBook 6 G1a 16", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8dfe, "HP EliteBook 665 G12", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8e11, "HP Trekker", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8e12, "HP Trekker", ALC287_FIXUP_CS35L41_I2C_2), @@ -11026,6 +11031,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1df3, "ASUS UM5606WA", ALC294_FIXUP_BASS_SPEAKER_15), SND_PCI_QUIRK(0x1043, 0x1264, "ASUS UM5606KA", ALC294_FIXUP_BASS_SPEAKER_15), SND_PCI_QUIRK(0x1043, 0x1e02, "ASUS UX3402ZA", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x1043, 0x1e10, "ASUS VivoBook X507UAR", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502), SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1e1f, "ASUS Vivobook 15 X1504VAP", ALC2XX_FIXUP_HEADSET_MIC), @@ -11135,6 +11141,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x14a1, "Clevo L141MU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x2624, "Clevo L240TU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x28c1, "Clevo V370VND", ALC2XX_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1558, 0x35a1, "Clevo V3[56]0EN[CDE]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x35b1, "Clevo V3[57]0WN[MNP]Q", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x4018, "Clevo NV40M[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x4019, "Clevo NV40MZ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x4020, "Clevo NV40MB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), @@ -11162,6 +11170,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x51b1, "Clevo NS50AU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x51b3, "Clevo NS70AU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x5630, "Clevo NP50RNJS", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x5700, "Clevo X560WN[RST]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x70a1, "Clevo NB70T[HJK]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x70b3, "Clevo NK70SB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x70f2, "Clevo NH79EPY", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), @@ -11201,6 +11210,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0xa650, "Clevo NP[567]0SN[CD]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0xa671, "Clevo NP70SN[CDE]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0xa741, "Clevo V54x_6x_TNE", ALC245_FIXUP_CLEVO_NOISY_MIC), + SND_PCI_QUIRK(0x1558, 0xa743, "Clevo V54x_6x_TU", ALC245_FIXUP_CLEVO_NOISY_MIC), SND_PCI_QUIRK(0x1558, 0xa763, "Clevo V54x_6x_TU", ALC245_FIXUP_CLEVO_NOISY_MIC), SND_PCI_QUIRK(0x1558, 0xb018, "Clevo NP50D[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0xb019, "Clevo NH77D[BE]Q", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), diff --git a/sound/soc/amd/ps/acp63.h b/sound/soc/amd/ps/acp63.h index 85feae45c44c..d7c994e26e4d 100644 --- a/sound/soc/amd/ps/acp63.h +++ b/sound/soc/amd/ps/acp63.h @@ -334,6 +334,8 @@ struct acp_hw_ops { * @addr: pci ioremap address * @reg_range: ACP reigister range * @acp_rev: ACP PCI revision id + * @acp_sw_pad_keeper_en: store acp SoundWire pad keeper enable register value + * @acp_pad_pulldown_ctrl: store acp pad pulldown control register value * @acp63_sdw0-dma_intr_stat: DMA interrupt status array for ACP6.3 platform SoundWire * manager-SW0 instance * @acp63_sdw_dma_intr_stat: DMA interrupt status array for ACP6.3 platform SoundWire @@ -367,6 +369,8 @@ struct acp63_dev_data { u32 addr; u32 reg_range; u32 acp_rev; + u32 acp_sw_pad_keeper_en; + u32 acp_pad_pulldown_ctrl; u16 acp63_sdw0_dma_intr_stat[ACP63_SDW0_DMA_MAX_STREAMS]; u16 acp63_sdw1_dma_intr_stat[ACP63_SDW1_DMA_MAX_STREAMS]; u16 acp70_sdw0_dma_intr_stat[ACP70_SDW0_DMA_MAX_STREAMS]; diff --git a/sound/soc/amd/ps/ps-common.c b/sound/soc/amd/ps/ps-common.c index 1c89fb5fe1da..7b4966b75dc6 100644 --- a/sound/soc/amd/ps/ps-common.c +++ b/sound/soc/amd/ps/ps-common.c @@ -160,6 +160,8 @@ static int __maybe_unused snd_acp63_suspend(struct device *dev) adata = dev_get_drvdata(dev); if (adata->is_sdw_dev) { + adata->acp_sw_pad_keeper_en = readl(adata->acp63_base + ACP_SW0_PAD_KEEPER_EN); + adata->acp_pad_pulldown_ctrl = readl(adata->acp63_base + ACP_PAD_PULLDOWN_CTRL); adata->sdw_en_stat = check_acp_sdw_enable_status(adata); if (adata->sdw_en_stat) { writel(1, adata->acp63_base + ACP_ZSC_DSP_CTRL); @@ -197,6 +199,7 @@ static int __maybe_unused snd_acp63_runtime_resume(struct device *dev) static int __maybe_unused snd_acp63_resume(struct device *dev) { struct acp63_dev_data *adata; + u32 acp_sw_pad_keeper_en; int ret; adata = dev_get_drvdata(dev); @@ -209,6 +212,12 @@ static int __maybe_unused snd_acp63_resume(struct device *dev) if (ret) dev_err(dev, "ACP init failed\n"); + acp_sw_pad_keeper_en = readl(adata->acp63_base + ACP_SW0_PAD_KEEPER_EN); + dev_dbg(dev, "ACP_SW0_PAD_KEEPER_EN:0x%x\n", acp_sw_pad_keeper_en); + if (!acp_sw_pad_keeper_en) { + writel(adata->acp_sw_pad_keeper_en, adata->acp63_base + ACP_SW0_PAD_KEEPER_EN); + writel(adata->acp_pad_pulldown_ctrl, adata->acp63_base + ACP_PAD_PULLDOWN_CTRL); + } return ret; } @@ -408,6 +417,8 @@ static int __maybe_unused snd_acp70_suspend(struct device *dev) adata = dev_get_drvdata(dev); if (adata->is_sdw_dev) { + adata->acp_sw_pad_keeper_en = readl(adata->acp63_base + ACP_SW0_PAD_KEEPER_EN); + adata->acp_pad_pulldown_ctrl = readl(adata->acp63_base + ACP_PAD_PULLDOWN_CTRL); adata->sdw_en_stat = check_acp_sdw_enable_status(adata); if (adata->sdw_en_stat) { writel(1, adata->acp63_base + ACP_ZSC_DSP_CTRL); @@ -445,6 +456,7 @@ static int __maybe_unused snd_acp70_runtime_resume(struct device *dev) static int __maybe_unused snd_acp70_resume(struct device *dev) { struct acp63_dev_data *adata; + u32 acp_sw_pad_keeper_en; int ret; adata = dev_get_drvdata(dev); @@ -459,6 +471,12 @@ static int __maybe_unused snd_acp70_resume(struct device *dev) if (ret) dev_err(dev, "ACP init failed\n"); + acp_sw_pad_keeper_en = readl(adata->acp63_base + ACP_SW0_PAD_KEEPER_EN); + dev_dbg(dev, "ACP_SW0_PAD_KEEPER_EN:0x%x\n", acp_sw_pad_keeper_en); + if (!acp_sw_pad_keeper_en) { + writel(adata->acp_sw_pad_keeper_en, adata->acp63_base + ACP_SW0_PAD_KEEPER_EN); + writel(adata->acp_pad_pulldown_ctrl, adata->acp63_base + ACP_PAD_PULLDOWN_CTRL); + } return ret; } diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 98022e5fd428..97e340140d0c 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -356,6 +356,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { { .driver_data = &acp6x_card, .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "RB"), + DMI_MATCH(DMI_PRODUCT_NAME, "Nitro ANV15-41"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "83J2"), } @@ -363,6 +370,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { { .driver_data = &acp6x_card, .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "83J3"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "UM5302TA"), } diff --git a/sound/soc/codecs/rt721-sdca.c b/sound/soc/codecs/rt721-sdca.c index 1c9f32e405cf..ba080957e933 100644 --- a/sound/soc/codecs/rt721-sdca.c +++ b/sound/soc/codecs/rt721-sdca.c @@ -430,6 +430,7 @@ static int rt721_sdca_set_gain_get(struct snd_kcontrol *kcontrol, unsigned int read_l, read_r, ctl_l = 0, ctl_r = 0; unsigned int adc_vol_flag = 0; const unsigned int interval_offset = 0xc0; + const unsigned int tendA = 0x200; const unsigned int tendB = 0xa00; if (strstr(ucontrol->id.name, "FU1E Capture Volume") || @@ -439,9 +440,16 @@ static int rt721_sdca_set_gain_get(struct snd_kcontrol *kcontrol, regmap_read(rt721->mbq_regmap, mc->reg, &read_l); regmap_read(rt721->mbq_regmap, mc->rreg, &read_r); - if (mc->shift == 8) /* boost gain */ + if (mc->shift == 8) { + /* boost gain */ ctl_l = read_l / tendB; - else { + } else if (mc->shift == 1) { + /* FU33 boost gain */ + if (read_l == 0x8000 || read_l == 0xfe00) + ctl_l = 0; + else + ctl_l = read_l / tendA + 1; + } else { if (adc_vol_flag) ctl_l = mc->max - (((0x1e00 - read_l) & 0xffff) / interval_offset); else @@ -449,9 +457,16 @@ static int rt721_sdca_set_gain_get(struct snd_kcontrol *kcontrol, } if (read_l != read_r) { - if (mc->shift == 8) /* boost gain */ + if (mc->shift == 8) { + /* boost gain */ ctl_r = read_r / tendB; - else { /* ADC/DAC gain */ + } else if (mc->shift == 1) { + /* FU33 boost gain */ + if (read_r == 0x8000 || read_r == 0xfe00) + ctl_r = 0; + else + ctl_r = read_r / tendA + 1; + } else { /* ADC/DAC gain */ if (adc_vol_flag) ctl_r = mc->max - (((0x1e00 - read_r) & 0xffff) / interval_offset); else diff --git a/sound/soc/qcom/Kconfig b/sound/soc/qcom/Kconfig index e86b4a03dd61..3d9ba13ee1e5 100644 --- a/sound/soc/qcom/Kconfig +++ b/sound/soc/qcom/Kconfig @@ -186,6 +186,7 @@ config SND_SOC_SM8250 tristate "SoC Machine driver for SM8250 boards" depends on QCOM_APR && SOUNDWIRE depends on COMMON_CLK + depends on SND_SOC_QCOM_OFFLOAD_UTILS || !SND_SOC_QCOM_OFFLOAD_UTILS select SND_SOC_QDSP6 select SND_SOC_QCOM_COMMON select SND_SOC_QCOM_SDW diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c index bdfe388da198..3b47191ea7a5 100644 --- a/sound/soc/sof/intel/hda.c +++ b/sound/soc/sof/intel/hda.c @@ -1257,11 +1257,11 @@ static int check_tplg_quirk_mask(struct snd_soc_acpi_mach *mach) return 0; } -static char *remove_file_ext(const char *tplg_filename) +static char *remove_file_ext(struct device *dev, const char *tplg_filename) { char *filename, *tmp; - filename = kstrdup(tplg_filename, GFP_KERNEL); + filename = devm_kstrdup(dev, tplg_filename, GFP_KERNEL); if (!filename) return NULL; @@ -1345,7 +1345,7 @@ struct snd_soc_acpi_mach *hda_machine_select(struct snd_sof_dev *sdev) */ if (!sof_pdata->tplg_filename) { /* remove file extension if it exists */ - tplg_filename = remove_file_ext(mach->sof_tplg_filename); + tplg_filename = remove_file_ext(sdev->dev, mach->sof_tplg_filename); if (!tplg_filename) return NULL; diff --git a/sound/usb/qcom/qc_audio_offload.c b/sound/usb/qcom/qc_audio_offload.c index 5bc27c82e0af..3543b5a53592 100644 --- a/sound/usb/qcom/qc_audio_offload.c +++ b/sound/usb/qcom/qc_audio_offload.c @@ -759,7 +759,7 @@ static void qmi_stop_session(void) subs = find_substream(pcm_card_num, info->pcm_dev_num, info->direction); if (!subs || !chip || atomic_read(&chip->shutdown)) { - dev_err(&subs->dev->dev, + dev_err(&uadev[idx].udev->dev, "no sub for c#%u dev#%u dir%u\n", info->pcm_card_num, info->pcm_dev_num, @@ -1360,20 +1360,21 @@ static int prepare_qmi_response(struct snd_usb_substream *subs, if (!uadev[card_num].ctrl_intf) { dev_err(&subs->dev->dev, "audio ctrl intf info not cached\n"); - ret = -ENODEV; - goto err; + return -ENODEV; } ret = uaudio_populate_uac_desc(subs, resp); if (ret < 0) - goto err; + return ret; resp->slot_id = subs->dev->slot_id; resp->slot_id_valid = 1; data = snd_soc_usb_find_priv_data(uaudio_qdev->auxdev->dev.parent); - if (!data) - goto err; + if (!data) { + dev_err(&subs->dev->dev, "No private data found\n"); + return -ENODEV; + } uaudio_qdev->data = data; @@ -1382,7 +1383,7 @@ static int prepare_qmi_response(struct snd_usb_substream *subs, &resp->xhci_mem_info.tr_data, &resp->std_as_data_ep_desc); if (ret < 0) - goto err; + return ret; resp->std_as_data_ep_desc_valid = 1; @@ -1500,7 +1501,6 @@ drop_data_ep: xhci_sideband_remove_endpoint(uadev[card_num].sb, usb_pipe_endpoint(subs->dev, subs->data_endpoint->pipe)); -err: return ret; } diff --git a/sound/usb/stream.c b/sound/usb/stream.c index c1ea8844a46f..aa91d63749f2 100644 --- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -987,6 +987,8 @@ snd_usb_get_audioformat_uac3(struct snd_usb_audio *chip, * and request Cluster Descriptor */ wLength = le16_to_cpu(hc_header.wLength); + if (wLength < sizeof(cluster)) + return NULL; cluster = kzalloc(wLength, GFP_KERNEL); if (!cluster) return ERR_PTR(-ENOMEM); diff --git a/tools/arch/loongarch/include/asm/orc_types.h b/tools/arch/loongarch/include/asm/orc_types.h index caf1f71a1057..d5fa98d1d177 100644 --- a/tools/arch/loongarch/include/asm/orc_types.h +++ b/tools/arch/loongarch/include/asm/orc_types.h @@ -34,7 +34,7 @@ #define ORC_TYPE_REGS 3 #define ORC_TYPE_REGS_PARTIAL 4 -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ /* * This struct is more or less a vastly simplified version of the DWARF Call * Frame Information standard. It contains only the necessary parts of DWARF @@ -53,6 +53,6 @@ struct orc_entry { unsigned int type:3; unsigned int signal:1; }; -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* _ORC_TYPES_H */ diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c index b6c471da5c28..b87e7f39e15a 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c @@ -314,6 +314,95 @@ out: test_sockmap_ktls__destroy(skel); } +static void test_sockmap_ktls_tx_pop(int family, int sotype) +{ + char msg[37] = "0123456789abcdefghijklmnopqrstuvwxyz\0"; + int c = 0, p = 0, one = 1, sent, recvd; + struct test_sockmap_ktls *skel; + int prog_fd, map_fd; + char rcv[50] = {0}; + int err; + int i, m, r; + + skel = test_sockmap_ktls__open_and_load(); + if (!ASSERT_TRUE(skel, "open ktls skel")) + return; + + err = create_pair(family, sotype, &c, &p); + if (!ASSERT_OK(err, "create_pair()")) + goto out; + + prog_fd = bpf_program__fd(skel->progs.prog_sk_policy); + map_fd = bpf_map__fd(skel->maps.sock_map); + + err = bpf_prog_attach(prog_fd, map_fd, BPF_SK_MSG_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach sk msg")) + goto out; + + err = bpf_map_update_elem(map_fd, &one, &c, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(c)")) + goto out; + + err = init_ktls_pairs(c, p); + if (!ASSERT_OK(err, "init_ktls_pairs(c, p)")) + goto out; + + struct { + int pop_start; + int pop_len; + } pop_policy[] = { + /* trim the start */ + {0, 2}, + {0, 10}, + {1, 2}, + {1, 10}, + /* trim the end */ + {35, 2}, + /* New entries should be added before this line */ + {-1, -1}, + }; + + i = 0; + while (pop_policy[i].pop_start >= 0) { + skel->bss->pop_start = pop_policy[i].pop_start; + skel->bss->pop_end = pop_policy[i].pop_len; + + sent = send(c, msg, sizeof(msg), 0); + if (!ASSERT_EQ(sent, sizeof(msg), "send(msg)")) + goto out; + + recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1); + if (!ASSERT_EQ(recvd, sizeof(msg) - pop_policy[i].pop_len, "pop len mismatch")) + goto out; + + /* verify the data + * msg: 0123456789a bcdefghij klmnopqrstuvwxyz + * | | + * popped data + */ + for (m = 0, r = 0; m < sizeof(msg);) { + /* skip checking the data that has been popped */ + if (m >= pop_policy[i].pop_start && + m <= pop_policy[i].pop_start + pop_policy[i].pop_len - 1) { + m++; + continue; + } + + if (!ASSERT_EQ(msg[m], rcv[r], "data mismatch")) + goto out; + m++; + r++; + } + i++; + } +out: + if (c) + close(c); + if (p) + close(p); + test_sockmap_ktls__destroy(skel); +} + static void run_tests(int family, enum bpf_map_type map_type) { int map; @@ -338,6 +427,8 @@ static void run_ktls_test(int family, int sotype) test_sockmap_ktls_tx_cork(family, sotype, true); if (test__start_subtest("tls tx egress with no buf")) test_sockmap_ktls_tx_no_buf(family, sotype, true); + if (test__start_subtest("tls tx with pop")) + test_sockmap_ktls_tx_pop(family, sotype); } void test_sockmap_ktls(void) diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c b/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c index 8bdb9987c0c7..83df4919c224 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c @@ -7,6 +7,8 @@ int cork_byte; int push_start; int push_end; int apply_bytes; +int pop_start; +int pop_end; struct { __uint(type, BPF_MAP_TYPE_SOCKMAP); @@ -22,6 +24,8 @@ int prog_sk_policy(struct sk_msg_md *msg) bpf_msg_cork_bytes(msg, cork_byte); if (push_start > 0 && push_end > 0) bpf_msg_push_data(msg, push_start, push_end, 0); + if (pop_start >= 0 && pop_end > 0) + bpf_msg_pop_data(msg, pop_start, pop_end, 0); return SK_PASS; } diff --git a/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py b/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py new file mode 100755 index 000000000000..820d8a03becc --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py @@ -0,0 +1,466 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +Devlink Rate TC Bandwidth Test Suite +=================================== + +This test suite verifies the functionality of devlink-rate traffic class (TC) +bandwidth distribution in a virtualized environment. The tests validate that +bandwidth can be properly allocated between different traffic classes and +that TC mapping works as expected. + +Test Environment: +---------------- +- Creates 1 VF +- Establishes a bridge connecting the VF representor and the uplink representor +- Sets up 2 VLAN interfaces on the VF with different VLAN IDs (101, 102) +- Configures different traffic classes (TC3 and TC4) for each VLAN + +Test Cases: +---------- +1. test_no_tc_mapping_bandwidth: + - Verifies that without TC mapping, bandwidth is NOT distributed according to + the configured 80/20 split between TC4 and TC3 + - This test should fail if bandwidth matches the 80/20 split without TC + mapping + - Expected: Bandwidth should NOT be distributed as 80/20 + +2. test_tc_mapping_bandwidth: + - Configures TC mapping using mqprio qdisc + - Verifies that with TC mapping, bandwidth IS distributed according to the + configured 80/20 split between TC3 and TC4 + - Expected: Bandwidth should be distributed as 80/20 + +Bandwidth Distribution: +---------------------- +- TC3 (VLAN 101): Configured for 80% of total bandwidth +- TC4 (VLAN 102): Configured for 20% of total bandwidth +- Total bandwidth: 1Gbps +- Tolerance: +-12% + +Hardware-Specific Behavior (mlx5): +-------------------------- +mlx5 hardware enforces traffic class separation by ensuring that each transmit +queue (SQ) is associated with a single TC. If a packet is sent on a queue that +doesn't match the expected TC (based on DSCP or VLAN priority and hypervisor-set +mapping), the hardware moves the queue to the correct TC scheduler to preserve +traffic isolation. + +This behavior means that even without explicit TC-to-queue mapping, bandwidth +enforcement may still appear to work—because the hardware dynamically adjusts +the scheduling context. However, this can lead to performance issues in high +rates and HOL blocking if traffic from different TCs is mixed on the same queue. +""" + +import json +import os +import subprocess +import threading +import time + +from lib.py import ksft_pr, ksft_run, ksft_exit +from lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx +from lib.py import NetDrvEpEnv, DevlinkFamily +from lib.py import NlError +from lib.py import cmd, defer, ethtool, ip + + +class BandwidthValidator: + """ + Validates bandwidth totals and per-TC shares against expected values + with a tolerance. + """ + + def __init__(self): + self.tolerance_percent = 12 + self.expected_total_gbps = 1.0 + self.total_min_expected = self.min_expected(self.expected_total_gbps) + self.total_max_expected = self.max_expected(self.expected_total_gbps) + self.tc_expected_percent = { + 3: 20.0, + 4: 80.0, + } + + def min_expected(self, value): + """Calculates the minimum acceptable value based on tolerance.""" + return value - (value * self.tolerance_percent / 100) + + def max_expected(self, value): + """Calculates the maximum acceptable value based on tolerance.""" + return value + (value * self.tolerance_percent / 100) + + def bound(self, expected, value): + """Returns True if value is within expected tolerance.""" + return self.min_expected(expected) <= value <= self.max_expected(expected) + + def tc_bandwidth_bound(self, value, tc_ix): + """ + Returns True if the given bandwidth value is within tolerance + for the TC's expected bandwidth. + """ + expected = self.tc_expected_percent[tc_ix] + return self.bound(expected, value) + + +def setup_vf(cfg, set_tc_mapping=True): + """ + Sets up a VF on the given network interface. + + Enables SR-IOV and switchdev mode, brings the VF interface up, + and optionally configures TC mapping using mqprio. + """ + try: + cmd(f"devlink dev eswitch set pci/{cfg.pci} mode switchdev") + defer(cmd, f"devlink dev eswitch set pci/{cfg.pci} mode legacy") + except Exception as exc: + raise KsftSkipEx(f"Failed to enable switchdev mode on {cfg.pci}") from exc + try: + cmd(f"echo 1 > /sys/class/net/{cfg.ifname}/device/sriov_numvfs") + defer(cmd, f"echo 0 > /sys/class/net/{cfg.ifname}/device/sriov_numvfs") + except Exception as exc: + raise KsftSkipEx(f"Failed to enable SR-IOV on {cfg.ifname}") from exc + + time.sleep(2) + vf_ifc = (os.listdir( + f"/sys/class/net/{cfg.ifname}/device/virtfn0/net") or [None])[0] + if vf_ifc: + ip(f"link set dev {vf_ifc} up") + else: + raise KsftSkipEx("VF interface not found") + if set_tc_mapping: + cmd(f"tc qdisc add dev {vf_ifc} root handle 5 mqprio mode dcb hw 1 num_tc 8") + + return vf_ifc + + +def setup_vlans_on_vf(vf_ifc): + """ + Sets up two VLAN interfaces on the given VF, each mapped to a different TC. + """ + vlan_configs = [ + {"vlan_id": 101, "tc": 3, "ip": "198.51.100.2"}, + {"vlan_id": 102, "tc": 4, "ip": "198.51.100.10"}, + ] + + for config in vlan_configs: + vlan_dev = f"{vf_ifc}.{config['vlan_id']}" + ip(f"link add link {vf_ifc} name {vlan_dev} type vlan id {config['vlan_id']}") + ip(f"addr add {config['ip']}/29 dev {vlan_dev}") + ip(f"link set dev {vlan_dev} up") + ip(f"link set dev {vlan_dev} type vlan egress-qos-map 0:{config['tc']}") + ksft_pr(f"Created VLAN {vlan_dev} on {vf_ifc} with tc {config['tc']} and IP {config['ip']}") + + +def get_vf_info(cfg): + """ + Finds the VF representor interface and devlink port index + for the given PCI device used in the test environment. + """ + cfg.vf_representor = None + cfg.vf_port_index = None + out = subprocess.check_output(["devlink", "-j", "port", "show"], encoding="utf-8") + ports = json.loads(out)["port"] + + for port_name, props in ports.items(): + netdev = props.get("netdev") + + if (port_name.startswith(f"pci/{cfg.pci}/") and + props.get("vfnum") == 0): + cfg.vf_representor = netdev + cfg.vf_port_index = int(port_name.split("/")[-1]) + break + + +def setup_bridge(cfg): + """ + Creates and configures a Linux bridge, with both the uplink + and VF representor interfaces attached to it. + """ + bridge_name = f"br_{os.getpid()}" + ip(f"link add name {bridge_name} type bridge") + defer(cmd, f"ip link del name {bridge_name} type bridge") + + ip(f"link set dev {cfg.ifname} master {bridge_name}") + + rep_name = cfg.vf_representor + if rep_name: + ip(f"link set dev {rep_name} master {bridge_name}") + ip(f"link set dev {rep_name} up") + ksft_pr(f"Set representor {rep_name} up and added to bridge") + else: + raise KsftSkipEx("Could not find representor for the VF") + + ip(f"link set dev {bridge_name} up") + + +def setup_devlink_rate(cfg): + """ + Configures devlink rate tx_max and traffic class bandwidth for the VF. + """ + port_index = cfg.vf_port_index + if port_index is None: + raise KsftSkipEx("Could not find VF port index") + try: + cfg.devnl.rate_set({ + "bus-name": "pci", + "dev-name": cfg.pci, + "port-index": port_index, + "rate-tx-max": 125000000, + "rate-tc-bws": [ + {"rate-tc-index": 0, "rate-tc-bw": 0}, + {"rate-tc-index": 1, "rate-tc-bw": 0}, + {"rate-tc-index": 2, "rate-tc-bw": 0}, + {"rate-tc-index": 3, "rate-tc-bw": 20}, + {"rate-tc-index": 4, "rate-tc-bw": 80}, + {"rate-tc-index": 5, "rate-tc-bw": 0}, + {"rate-tc-index": 6, "rate-tc-bw": 0}, + {"rate-tc-index": 7, "rate-tc-bw": 0}, + ] + }) + except NlError as exc: + if exc.error == 95: # EOPNOTSUPP + raise KsftSkipEx("devlink rate configuration is not supported on the VF") from exc + raise KsftFailEx(f"rate_set failed on VF port {port_index}") from exc + + +def setup_remote_server(cfg): + """ + Sets up VLAN interfaces and starts iperf3 servers on the remote side. + """ + remote_dev = cfg.remote_ifname + vlan_ids = [101, 102] + remote_ips = ["198.51.100.1", "198.51.100.9"] + + for vlan_id, ip_addr in zip(vlan_ids, remote_ips): + vlan_dev = f"{remote_dev}.{vlan_id}" + cmd(f"ip link add link {remote_dev} name {vlan_dev} " + f"type vlan id {vlan_id}", host=cfg.remote) + cmd(f"ip addr add {ip_addr}/29 dev {vlan_dev}", host=cfg.remote) + cmd(f"ip link set dev {vlan_dev} up", host=cfg.remote) + cmd(f"iperf3 -s -1 -B {ip_addr}",background=True, host=cfg.remote) + defer(cmd, f"ip link del {vlan_dev}", host=cfg.remote) + + +def setup_test_environment(cfg, set_tc_mapping=True): + """ + Sets up the complete test environment including VF creation, VLANs, + bridge configuration, devlink rate setup, and the remote server. + """ + vf_ifc = setup_vf(cfg, set_tc_mapping) + ksft_pr(f"Created VF interface: {vf_ifc}") + + setup_vlans_on_vf(vf_ifc) + + get_vf_info(cfg) + setup_bridge(cfg) + + setup_devlink_rate(cfg) + setup_remote_server(cfg) + time.sleep(2) + + +def run_iperf_client(server_ip, local_ip, barrier, min_expected_gbps=0.1): + """ + Runs a single iperf3 client instance, binding to the given local IP. + Waits on a barrier to synchronize with other threads. + """ + try: + barrier.wait(timeout=10) + except Exception as exc: + raise KsftFailEx("iperf3 barrier wait timed") from exc + + iperf_cmd = ["iperf3", "-c", server_ip, "-B", local_ip, "-J"] + result = subprocess.run(iperf_cmd, capture_output=True, text=True, + check=True) + + try: + output = json.loads(result.stdout) + bits_per_second = output["end"]["sum_received"]["bits_per_second"] + gbps = bits_per_second / 1e9 + if gbps < min_expected_gbps: + ksft_pr( + f"iperf3 bandwidth too low: {gbps:.2f} Gbps " + f"(expected ≥ {min_expected_gbps} Gbps)" + ) + return None + return gbps + except json.JSONDecodeError as exc: + ksft_pr(f"Failed to parse iperf3 JSON output: {exc}") + return None + + +def run_bandwidth_test(): + """ + Launches iperf3 client threads for each VLAN/TC pair and collects results. + """ + def _run_iperf_client_thread(server_ip, local_ip, results, barrier, tc_ix): + results[tc_ix] = run_iperf_client(server_ip, local_ip, barrier) + + vf_vlan_data = [ + # (local_ip, remote_ip, TC) + ("198.51.100.2", "198.51.100.1", 3), + ("198.51.100.10", "198.51.100.9", 4), + ] + + results = {} + threads = [] + start_barrier = threading.Barrier(len(vf_vlan_data)) + + for local_ip, remote_ip, tc_ix in vf_vlan_data: + thread = threading.Thread( + target=_run_iperf_client_thread, + args=(remote_ip, local_ip, results, start_barrier, tc_ix) + ) + thread.start() + threads.append(thread) + + for thread in threads: + thread.join() + + for tc_ix, tc_bw in results.items(): + if tc_bw is None: + raise KsftFailEx("iperf3 client failed; cannot evaluate bandwidth") + + return results + +def calculate_bandwidth_percentages(results): + """ + Calculates the percentage of total bandwidth received by TC3 and TC4. + """ + if 3 not in results or 4 not in results: + raise KsftFailEx(f"Missing expected TC results in {results}") + + tc3_bw = results[3] + tc4_bw = results[4] + total_bw = tc3_bw + tc4_bw + tc3_percentage = (tc3_bw / total_bw) * 100 + tc4_percentage = (tc4_bw / total_bw) * 100 + + return { + 'tc3_bw': tc3_bw, + 'tc4_bw': tc4_bw, + 'tc3_percentage': tc3_percentage, + 'tc4_percentage': tc4_percentage, + 'total_bw': total_bw + } + + +def print_bandwidth_results(bw_data, test_name): + """ + Prints bandwidth measurements and TC usage summary for a given test. + """ + ksft_pr(f"Bandwidth check results {test_name}:") + ksft_pr(f"TC 3: {bw_data['tc3_bw']:.2f} Gbits/sec") + ksft_pr(f"TC 4: {bw_data['tc4_bw']:.2f} Gbits/sec") + ksft_pr(f"Total bandwidth: {bw_data['total_bw']:.2f} Gbits/sec") + ksft_pr(f"TC 3 percentage: {bw_data['tc3_percentage']:.1f}%") + ksft_pr(f"TC 4 percentage: {bw_data['tc4_percentage']:.1f}%") + + +def verify_total_bandwidth(bw_data, validator): + """ + Ensures the total measured bandwidth falls within the acceptable tolerance. + """ + total = bw_data['total_bw'] + + if validator.bound(validator.expected_total_gbps, total): + return + + if total < validator.total_min_expected: + raise KsftSkipEx( + f"Total bandwidth {total:.2f} Gbps < minimum " + f"{validator.total_min_expected:.2f} Gbps; " + f"parent tx_max ({validator.expected_total_gbps:.1f} G) " + f"not reached, cannot validate share" + ) + + raise KsftFailEx( + f"Total bandwidth {total:.2f} Gbps exceeds allowed ceiling " + f"{validator.total_max_expected:.2f} Gbps " + f"(VF tx_max set to {validator.expected_total_gbps:.1f} G)" + ) + + +def check_bandwidth_distribution(bw_data, validator): + """ + Checks whether the measured TC3 and TC4 bandwidth percentages + fall within their expected tolerance ranges. + + Returns: + bool: True if both TC3 and TC4 percentages are within bounds. + """ + tc3_valid = validator.tc_bandwidth_bound(bw_data['tc3_percentage'], 3) + tc4_valid = validator.tc_bandwidth_bound(bw_data['tc4_percentage'], 4) + + return tc3_valid and tc4_valid + + +def run_bandwidth_distribution_test(cfg, set_tc_mapping): + """ + Runs parallel iperf3 tests for both TCs and collects results. + """ + setup_test_environment(cfg, set_tc_mapping) + bandwidths = run_bandwidth_test() + bw_data = calculate_bandwidth_percentages(bandwidths) + test_name = "with TC mapping" if set_tc_mapping else "without TC mapping" + print_bandwidth_results(bw_data, test_name) + + verify_total_bandwidth(bw_data, cfg.bw_validator) + + return check_bandwidth_distribution(bw_data, cfg.bw_validator) + + +def test_no_tc_mapping_bandwidth(cfg): + """ + Verifies that bandwidth is not split 80/20 without traffic class mapping. + """ + pass_bw_msg = "Bandwidth is NOT distributed as 80/20 without TC mapping" + fail_bw_msg = "Bandwidth matched 80/20 split without TC mapping" + is_mlx5 = "driver: mlx5" in ethtool(f"-i {cfg.ifname}").stdout + + if run_bandwidth_distribution_test(cfg, set_tc_mapping=False): + if is_mlx5: + raise KsftXfailEx(fail_bw_msg) + raise KsftFailEx(fail_bw_msg) + if is_mlx5: + raise KsftFailEx("mlx5 behavior changed:" + pass_bw_msg) + ksft_pr(pass_bw_msg) + + +def test_tc_mapping_bandwidth(cfg): + """ + Verifies that bandwidth is correctly split 80/20 between TC3 and TC4 + when traffic class mapping is set. + """ + if run_bandwidth_distribution_test(cfg, set_tc_mapping=True): + ksft_pr("Bandwidth is distributed as 80/20 with TC mapping") + else: + raise KsftFailEx("Bandwidth did not match 80/20 split with TC mapping") + + +def main() -> None: + """ + Main entry point for running the test cases. + """ + with NetDrvEpEnv(__file__, nsim_test=False) as cfg: + cfg.devnl = DevlinkFamily() + + cfg.pci = os.path.basename( + os.path.realpath(f"/sys/class/net/{cfg.ifname}/device") + ) + if not cfg.pci: + raise KsftSkipEx("Could not get PCI address of the interface") + cfg.require_cmd("iperf3") + cfg.require_cmd("iperf3", remote=True) + + cfg.bw_validator = BandwidthValidator() + + cases = [test_no_tc_mapping_bandwidth, test_tc_mapping_bandwidth] + + ksft_run(cases=cases, args=(cfg,)) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py index 56ff11074b55..1462a339a74b 100644 --- a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py +++ b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py @@ -13,7 +13,7 @@ try: # Import one by one to avoid pylint false positives from net.lib.py import EthtoolFamily, NetdevFamily, NetshaperFamily, \ - NlError, RtnlFamily + NlError, RtnlFamily, DevlinkFamily from net.lib.py import CmdExitFailure from net.lib.py import bkg, cmd, defer, ethtool, fd_read_timeout, ip, \ rand_port, tool, wait_port_listen diff --git a/tools/testing/selftests/drivers/net/lib/py/__init__.py b/tools/testing/selftests/drivers/net/lib/py/__init__.py index 9ed1d8f70524..fce5d9218f1d 100644 --- a/tools/testing/selftests/drivers/net/lib/py/__init__.py +++ b/tools/testing/selftests/drivers/net/lib/py/__init__.py @@ -12,7 +12,7 @@ try: # Import one by one to avoid pylint false positives from net.lib.py import EthtoolFamily, NetdevFamily, NetshaperFamily, \ - NlError, RtnlFamily + NlError, RtnlFamily, DevlinkFamily from net.lib.py import CmdExitFailure from net.lib.py import bkg, cmd, defer, ethtool, fd_read_timeout, ip, \ rand_port, tool, wait_port_listen diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh index 899b6892603f..d7505b933aef 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh @@ -51,7 +51,7 @@ for current_test in ${TESTS:-$ALL_TESTS}; do fi ${current_test}_setup_prepare - setup_wait $num_netifs + setup_wait_n $num_netifs # Update target in case occupancy of a certain resource changed # following the test setup. target=$(${current_test}_get_target "$should_fail") diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh index 482ebb744eba..7b98cdd0580d 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh @@ -55,7 +55,7 @@ for current_test in ${TESTS:-$ALL_TESTS}; do continue fi ${current_test}_setup_prepare - setup_wait $num_netifs + setup_wait_n $num_netifs # Update target in case occupancy of a certain resource # changed following the test setup. target=$(${current_test}_get_target "$should_fail") diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh index b5ea2526f23c..a102803ff74f 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh @@ -608,6 +608,46 @@ rate_attr_parent_check() check_err $? "Unexpected parent attr value $api_value != $parent" } +rate_attr_tc_bw_check() +{ + local handle=$1 + local tc_bw=$2 + local debug_file=$3 + + local tc_bw_str="" + for bw in $tc_bw; do + local tc=${bw%%:*} + local value=${bw##*:} + tc_bw_str="$tc_bw_str $tc:$value" + done + tc_bw_str=${tc_bw_str# } + + rate_attr_set "$handle" tc-bw "$tc_bw_str" + check_err $? "Failed to set tc-bw values" + + for bw in $tc_bw; do + local tc=${bw%%:*} + local value=${bw##*:} + local debug_value + debug_value=$(cat "$debug_file"/tc"${tc}"_bw) + check_err $? "Failed to read tc-bw value from debugfs for tc$tc" + [ "$debug_value" == "$value" ] + check_err $? "Unexpected tc-bw debug value for tc$tc: $debug_value != $value" + done + + for bw in $tc_bw; do + local tc=${bw%%:*} + local expected_value=${bw##*:} + local api_value + api_value=$(rate_attr_get "$handle" tc_"$tc") + if [ "$api_value" = "null" ]; then + api_value=0 + fi + [ "$api_value" == "$expected_value" ] + check_err $? "Unexpected tc-bw value for tc$tc: $api_value != $expected_value" + done +} + rate_node_add() { local handle=$1 @@ -649,6 +689,13 @@ rate_test() rate=$(($rate+100)) done + local tc_bw="0:0 1:40 2:0 3:0 4:0 5:0 6:60 7:0" + for r_obj in $leafs + do + rate_attr_tc_bw_check "$r_obj" "$tc_bw" \ + "$DEBUGFS_DIR"/ports/"${r_obj##*/}" + done + local node1_name='group1' local node1="$DL_HANDLE/$node1_name" rate_node_add "$node1" @@ -666,6 +713,12 @@ rate_test() rate_attr_tx_rate_check $node1 tx_max $node_tx_max \ $DEBUGFS_DIR/rate_nodes/${node1##*/}/tx_max + + local tc_bw="0:20 1:0 2:0 3:0 4:0 5:20 6:60 7:0" + rate_attr_tc_bw_check $node1 "$tc_bw" \ + "$DEBUGFS_DIR"/rate_nodes/"${node1##*/}" + + rate_node_del "$node1" check_err $? "Failed to delete node $node1" local num_nodes=`rate_nodes_get $DL_HANDLE | wc -w` diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 1a8e85afe9aa..1926ef6b40ab 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -54,6 +54,8 @@ static __attribute__((constructor)) void setup_sizes(void) mfd_buffer = memfd_mmap(BUFFER_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED, &mfd); + assert(mfd_buffer != MAP_FAILED); + assert(mfd > 0); } FIXTURE(iommufd) @@ -1746,13 +1748,15 @@ TEST_F(iommufd_mock_domain, all_aligns) unsigned int end; uint8_t *buf; int prot = PROT_READ | PROT_WRITE; - int mfd; + int mfd = -1; if (variant->file) buf = memfd_mmap(buf_size, prot, MAP_SHARED, &mfd); else buf = mmap(0, buf_size, prot, self->mmap_flags, -1, 0); ASSERT_NE(MAP_FAILED, buf); + if (variant->file) + ASSERT_GT(mfd, 0); check_refs(buf, buf_size, 0); /* @@ -1798,13 +1802,15 @@ TEST_F(iommufd_mock_domain, all_aligns_copy) unsigned int end; uint8_t *buf; int prot = PROT_READ | PROT_WRITE; - int mfd; + int mfd = -1; if (variant->file) buf = memfd_mmap(buf_size, prot, MAP_SHARED, &mfd); else buf = mmap(0, buf_size, prot, self->mmap_flags, -1, 0); ASSERT_NE(MAP_FAILED, buf); + if (variant->file) + ASSERT_GT(mfd, 0); check_refs(buf, buf_size, 0); /* @@ -2008,6 +2014,7 @@ FIXTURE_VARIANT(iommufd_dirty_tracking) FIXTURE_SETUP(iommufd_dirty_tracking) { + size_t mmap_buffer_size; unsigned long size; int mmap_flags; void *vrc; @@ -2022,22 +2029,33 @@ FIXTURE_SETUP(iommufd_dirty_tracking) self->fd = open("/dev/iommu", O_RDWR); ASSERT_NE(-1, self->fd); - rc = posix_memalign(&self->buffer, HUGEPAGE_SIZE, variant->buffer_size); - if (rc || !self->buffer) { - SKIP(return, "Skipping buffer_size=%lu due to errno=%d", - variant->buffer_size, rc); - } - mmap_flags = MAP_SHARED | MAP_ANONYMOUS | MAP_FIXED; + mmap_buffer_size = variant->buffer_size; if (variant->hugepages) { /* * MAP_POPULATE will cause the kernel to fail mmap if THPs are * not available. */ mmap_flags |= MAP_HUGETLB | MAP_POPULATE; + + /* + * Allocation must be aligned to the HUGEPAGE_SIZE, because the + * following mmap() will automatically align the length to be a + * multiple of the underlying huge page size. Failing to do the + * same at this allocation will result in a memory overwrite by + * the mmap(). + */ + if (mmap_buffer_size < HUGEPAGE_SIZE) + mmap_buffer_size = HUGEPAGE_SIZE; + } + + rc = posix_memalign(&self->buffer, HUGEPAGE_SIZE, mmap_buffer_size); + if (rc || !self->buffer) { + SKIP(return, "Skipping buffer_size=%lu due to errno=%d", + mmap_buffer_size, rc); } assert((uintptr_t)self->buffer % HUGEPAGE_SIZE == 0); - vrc = mmap(self->buffer, variant->buffer_size, PROT_READ | PROT_WRITE, + vrc = mmap(self->buffer, mmap_buffer_size, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); assert(vrc == self->buffer); @@ -2066,8 +2084,8 @@ FIXTURE_SETUP(iommufd_dirty_tracking) FIXTURE_TEARDOWN(iommufd_dirty_tracking) { - munmap(self->buffer, variant->buffer_size); - munmap(self->bitmap, DIV_ROUND_UP(self->bitmap_size, BITS_PER_BYTE)); + free(self->buffer); + free(self->bitmap); teardown_iommufd(self->fd, _metadata); } diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index 72f6636e5d90..6e967b58acfd 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -60,13 +60,18 @@ static inline void *memfd_mmap(size_t length, int prot, int flags, int *mfd_p) { int mfd_flags = (flags & MAP_HUGETLB) ? MFD_HUGETLB : 0; int mfd = memfd_create("buffer", mfd_flags); + void *buf = MAP_FAILED; if (mfd <= 0) return MAP_FAILED; if (ftruncate(mfd, length)) - return MAP_FAILED; + goto out; *mfd_p = mfd; - return mmap(0, length, prot, flags, mfd, 0); + buf = mmap(0, length, prot, flags, mfd, 0); +out: + if (buf == MAP_FAILED) + close(mfd); + return buf; } /* diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c index b380e102b22f..169dbd692bf5 100644 --- a/tools/testing/selftests/mm/virtual_address_range.c +++ b/tools/testing/selftests/mm/virtual_address_range.c @@ -77,8 +77,11 @@ static void validate_addr(char *ptr, int high_addr) { unsigned long addr = (unsigned long) ptr; - if (high_addr && addr < HIGH_ADDR_MARK) - ksft_exit_fail_msg("Bad address %lx\n", addr); + if (high_addr) { + if (addr < HIGH_ADDR_MARK) + ksft_exit_fail_msg("Bad address %lx\n", addr); + return; + } if (addr > HIGH_ADDR_MARK) ksft_exit_fail_msg("Bad address %lx\n", addr); diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 227f9e067d25..543776596529 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -100,6 +100,7 @@ TEST_PROGS += test_vxlan_mdb.sh TEST_PROGS += test_bridge_neigh_suppress.sh TEST_PROGS += test_vxlan_nolocalbypass.sh TEST_PROGS += test_bridge_backup_port.sh +TEST_PROGS += test_neigh.sh TEST_PROGS += fdb_flush.sh fdb_notify.sh TEST_PROGS += fq_band_pktlimit.sh TEST_PROGS += vlan_hw_filter.sh diff --git a/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c b/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c index f183d5e30dc6..cb6468adbda4 100644 --- a/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c +++ b/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c @@ -5,26 +5,17 @@ */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/interrupt.h> +#include <linux/limits.h> #include <linux/module.h> #include <linux/mutex.h> - -#include <linux/version.h> #include <net/page_pool/helpers.h> -#include <linux/interrupt.h> -#include <linux/limits.h> - #include "time_bench.h" static int verbose = 1; #define MY_POOL_SIZE 1024 -static void _page_pool_put_page(struct page_pool *pool, struct page *page, - bool allow_direct) -{ - page_pool_put_page(pool, page, -1, allow_direct); -} - /* Makes tests selectable. Useful for perf-record to analyze a single test. * Hint: Bash shells support writing binary number like: $((2#101010) * @@ -124,7 +115,7 @@ static void pp_fill_ptr_ring(struct page_pool *pp, int elems) for (i = 0; i < elems; i++) array[i] = page_pool_alloc_pages(pp, gfp_mask); for (i = 0; i < elems; i++) - _page_pool_put_page(pp, array[i], false); + page_pool_put_page(pp, array[i], -1, false); kfree(array); } @@ -183,14 +174,14 @@ static int time_bench_page_pool(struct time_bench_record *rec, void *data, } else if (type == type_ptr_ring) { /* Normal return path */ - _page_pool_put_page(pp, page, false); + page_pool_put_page(pp, page, -1, false); } else if (type == type_page_allocator) { /* Test if not pages are recycled, but instead * returned back into systems page allocator */ get_page(page); /* cause no-recycling */ - _page_pool_put_page(pp, page, false); + page_pool_put_page(pp, page, -1, false); put_page(page); } else { BUILD_BUG(); diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 83ee6a07e072..9308b2f77fed 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -526,9 +526,9 @@ setup_wait_dev_with_timeout() return 1 } -setup_wait() +setup_wait_n() { - local num_netifs=${1:-$NUM_NETIFS} + local num_netifs=$1; shift local i for ((i = 1; i <= num_netifs; ++i)); do @@ -539,6 +539,11 @@ setup_wait() sleep $WAIT_TIME } +setup_wait() +{ + setup_wait_n "$NUM_NETIFS" +} + wait_for_dev() { local dev=$1; shift diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh index 7ec58b6b1128..462db0b603e7 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh @@ -765,7 +765,7 @@ ipv6_mcroute_fdb_sep_rx() trap cleanup EXIT setup_prepare -setup_wait "$NUM_NETIFS" +setup_wait tests_run exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/net/lib/py/__init__.py b/tools/testing/selftests/net/lib/py/__init__.py index 8697bd27dc30..02be28dcc089 100644 --- a/tools/testing/selftests/net/lib/py/__init__.py +++ b/tools/testing/selftests/net/lib/py/__init__.py @@ -6,4 +6,4 @@ from .netns import NetNS, NetNSEnter from .nsim import * from .utils import * from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily, RtnlAddrFamily -from .ynl import NetshaperFamily +from .ynl import NetshaperFamily, DevlinkFamily diff --git a/tools/testing/selftests/net/lib/py/ynl.py b/tools/testing/selftests/net/lib/py/ynl.py index 6329ae805abf..2b3a61ea3bfa 100644 --- a/tools/testing/selftests/net/lib/py/ynl.py +++ b/tools/testing/selftests/net/lib/py/ynl.py @@ -56,3 +56,8 @@ class NetshaperFamily(YnlFamily): def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('net_shaper.yaml')).as_posix(), schema='', recv_size=recv_size) + +class DevlinkFamily(YnlFamily): + def __init__(self, recv_size=0): + super().__init__((SPEC_PATH / Path('devlink.yaml')).as_posix(), + schema='', recv_size=recv_size) diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c index 7ea5fb28c93d..1d5d3c4e7e87 100644 --- a/tools/testing/selftests/net/msg_zerocopy.c +++ b/tools/testing/selftests/net/msg_zerocopy.c @@ -77,6 +77,7 @@ static int cfg_cork; static bool cfg_cork_mixed; static int cfg_cpu = -1; /* default: pin to last cpu */ +static int cfg_expect_zerocopy = -1; static int cfg_family = PF_UNSPEC; static int cfg_ifindex = 1; static int cfg_payload_len; @@ -92,9 +93,9 @@ static socklen_t cfg_alen; static struct sockaddr_storage cfg_dst_addr; static struct sockaddr_storage cfg_src_addr; +static int exitcode; static char payload[IP_MAXPACKET]; static long packets, bytes, completions, expected_completions; -static int zerocopied = -1; static uint32_t next_completion; static uint32_t sends_since_notify; @@ -444,11 +445,13 @@ static bool do_recv_completion(int fd, int domain) next_completion = hi + 1; zerocopy = !(serr->ee_code & SO_EE_CODE_ZEROCOPY_COPIED); - if (zerocopied == -1) - zerocopied = zerocopy; - else if (zerocopied != zerocopy) { - fprintf(stderr, "serr: inconsistent\n"); - zerocopied = zerocopy; + if (cfg_expect_zerocopy != -1 && + cfg_expect_zerocopy != zerocopy) { + fprintf(stderr, "serr: ee_code: %u != expected %u\n", + zerocopy, cfg_expect_zerocopy); + exitcode = 1; + /* suppress repeated messages */ + cfg_expect_zerocopy = zerocopy; } if (cfg_verbose >= 2) @@ -571,7 +574,7 @@ static void do_tx(int domain, int type, int protocol) fprintf(stderr, "tx=%lu (%lu MB) txc=%lu zc=%c\n", packets, bytes >> 20, completions, - zerocopied == 1 ? 'y' : 'n'); + cfg_zerocopy && cfg_expect_zerocopy == 1 ? 'y' : 'n'); } static int do_setup_rx(int domain, int type, int protocol) @@ -715,7 +718,7 @@ static void parse_opts(int argc, char **argv) cfg_payload_len = max_payload_len; - while ((c = getopt(argc, argv, "46c:C:D:i:l:mp:rs:S:t:vz")) != -1) { + while ((c = getopt(argc, argv, "46c:C:D:i:l:mp:rs:S:t:vzZ:")) != -1) { switch (c) { case '4': if (cfg_family != PF_UNSPEC) @@ -770,6 +773,9 @@ static void parse_opts(int argc, char **argv) case 'z': cfg_zerocopy = true; break; + case 'Z': + cfg_expect_zerocopy = !!atoi(optarg); + break; } } @@ -817,5 +823,5 @@ int main(int argc, char **argv) else error(1, 0, "unknown cfg_test %s", cfg_test); - return 0; + return exitcode; } diff --git a/tools/testing/selftests/net/msg_zerocopy.sh b/tools/testing/selftests/net/msg_zerocopy.sh index 89c22f5320e0..28178a38a4e7 100755 --- a/tools/testing/selftests/net/msg_zerocopy.sh +++ b/tools/testing/selftests/net/msg_zerocopy.sh @@ -6,6 +6,7 @@ set -e readonly DEV="veth0" +readonly DUMMY_DEV="dummy0" readonly DEV_MTU=65535 readonly BIN="./msg_zerocopy" @@ -14,21 +15,25 @@ readonly NSPREFIX="ns-${RAND}" readonly NS1="${NSPREFIX}1" readonly NS2="${NSPREFIX}2" -readonly SADDR4='192.168.1.1' -readonly DADDR4='192.168.1.2' -readonly SADDR6='fd::1' -readonly DADDR6='fd::2' +readonly LPREFIX4='192.168.1' +readonly RPREFIX4='192.168.2' +readonly LPREFIX6='fd' +readonly RPREFIX6='fc' + readonly path_sysctl_mem="net.core.optmem_max" # No arguments: automated test if [[ "$#" -eq "0" ]]; then - $0 4 tcp -t 1 - $0 6 tcp -t 1 - $0 4 udp -t 1 - $0 6 udp -t 1 - echo "OK. All tests passed" - exit 0 + ret=0 + + $0 4 tcp -t 1 || ret=1 + $0 6 tcp -t 1 || ret=1 + $0 4 udp -t 1 || ret=1 + $0 6 udp -t 1 || ret=1 + + [[ "$ret" == "0" ]] && echo "OK. All tests passed" + exit $ret fi # Argument parsing @@ -45,11 +50,18 @@ readonly EXTRA_ARGS="$@" # Argument parsing: configure addresses if [[ "${IP}" == "4" ]]; then - readonly SADDR="${SADDR4}" - readonly DADDR="${DADDR4}" + readonly SADDR="${LPREFIX4}.1" + readonly DADDR="${LPREFIX4}.2" + readonly DUMMY_ADDR="${RPREFIX4}.1" + readonly DADDR_TXONLY="${RPREFIX4}.2" + readonly MASK="24" elif [[ "${IP}" == "6" ]]; then - readonly SADDR="${SADDR6}" - readonly DADDR="${DADDR6}" + readonly SADDR="${LPREFIX6}::1" + readonly DADDR="${LPREFIX6}::2" + readonly DUMMY_ADDR="${RPREFIX6}::1" + readonly DADDR_TXONLY="${RPREFIX6}::2" + readonly MASK="64" + readonly NODAD="nodad" else echo "Invalid IP version ${IP}" exit 1 @@ -89,33 +101,61 @@ ip netns exec "${NS2}" sysctl -w -q "${path_sysctl_mem}=1000000" ip link add "${DEV}" mtu "${DEV_MTU}" netns "${NS1}" type veth \ peer name "${DEV}" mtu "${DEV_MTU}" netns "${NS2}" +ip link add "${DUMMY_DEV}" mtu "${DEV_MTU}" netns "${NS2}" type dummy + # Bring the devices up ip -netns "${NS1}" link set "${DEV}" up ip -netns "${NS2}" link set "${DEV}" up +ip -netns "${NS2}" link set "${DUMMY_DEV}" up # Set fixed MAC addresses on the devices ip -netns "${NS1}" link set dev "${DEV}" address 02:02:02:02:02:02 ip -netns "${NS2}" link set dev "${DEV}" address 06:06:06:06:06:06 # Add fixed IP addresses to the devices -ip -netns "${NS1}" addr add 192.168.1.1/24 dev "${DEV}" -ip -netns "${NS2}" addr add 192.168.1.2/24 dev "${DEV}" -ip -netns "${NS1}" addr add fd::1/64 dev "${DEV}" nodad -ip -netns "${NS2}" addr add fd::2/64 dev "${DEV}" nodad +ip -netns "${NS1}" addr add "${SADDR}/${MASK}" dev "${DEV}" ${NODAD} +ip -netns "${NS2}" addr add "${DADDR}/${MASK}" dev "${DEV}" ${NODAD} +ip -netns "${NS2}" addr add "${DUMMY_ADDR}/${MASK}" dev "${DUMMY_DEV}" ${NODAD} + +ip -netns "${NS1}" route add default via "${DADDR}" dev "${DEV}" +ip -netns "${NS2}" route add default via "${DADDR_TXONLY}" dev "${DUMMY_DEV}" + +ip netns exec "${NS2}" sysctl -wq net.ipv4.ip_forward=1 +ip netns exec "${NS2}" sysctl -wq net.ipv6.conf.all.forwarding=1 # Optionally disable sg or csum offload to test edge cases # ip netns exec "${NS1}" ethtool -K "${DEV}" sg off +ret=0 + do_test() { local readonly ARGS="$1" - echo "ipv${IP} ${TXMODE} ${ARGS}" - ip netns exec "${NS2}" "${BIN}" "-${IP}" -i "${DEV}" -t 2 -C 2 -S "${SADDR}" -D "${DADDR}" ${ARGS} -r "${RXMODE}" & + # tx-rx test + # packets queued to a local socket are copied, + # sender notification has SO_EE_CODE_ZEROCOPY_COPIED. + + echo -e "\nipv${IP} ${TXMODE} ${ARGS} tx-rx\n" + ip netns exec "${NS2}" "${BIN}" "-${IP}" -i "${DEV}" -t 2 -C 2 \ + -S "${SADDR}" -D "${DADDR}" ${ARGS} -r "${RXMODE}" & sleep 0.2 - ip netns exec "${NS1}" "${BIN}" "-${IP}" -i "${DEV}" -t 1 -C 3 -S "${SADDR}" -D "${DADDR}" ${ARGS} "${TXMODE}" + ip netns exec "${NS1}" "${BIN}" "-${IP}" -i "${DEV}" -t 1 -C 3 \ + -S "${SADDR}" -D "${DADDR}" ${ARGS} "${TXMODE}" -Z 0 || ret=1 wait + + # next test is unconnected tx to dummy0, cannot exercise with tcp + [[ "${TXMODE}" == "tcp" ]] && return + + # tx-only test: send out dummy0 + # packets leaving the host are not copied, + # sender notification does not have SO_EE_CODE_ZEROCOPY_COPIED. + + echo -e "\nipv${IP} ${TXMODE} ${ARGS} tx-only\n" + ip netns exec "${NS1}" "${BIN}" "-${IP}" -i "${DEV}" -t 1 -C 3 \ + -S "${SADDR}" -D "${DADDR_TXONLY}" ${ARGS} "${TXMODE}" -Z 1 || ret=1 } do_test "${EXTRA_ARGS}" do_test "-z ${EXTRA_ARGS}" -echo ok + +[[ "$ret" == "0" ]] && echo "OK" diff --git a/tools/testing/selftests/net/packetdrill/tcp_dsack_mult.pkt b/tools/testing/selftests/net/packetdrill/tcp_dsack_mult.pkt new file mode 100644 index 000000000000..c790d0af635e --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_dsack_mult.pkt @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test various DSACK (RFC 2883) behaviors. + +--mss=1000 + +`./defaults.sh` + + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 1024 + +0 accept(3, ..., ...) = 4 + +// First SACK range. + +0 < P. 1001:2001(1000) ack 1 win 1024 + +0 > . 1:1(0) ack 1 <nop, nop, sack 1001:2001> + +// Check SACK coalescing (contiguous sequence). + +0 < P. 2001:3001(1000) ack 1 win 1024 + +0 > . 1:1(0) ack 1 <nop,nop,sack 1001:3001> + +// Check we have two SACK ranges for non contiguous sequences. + +0 < P. 4001:5001(1000) ack 1 win 1024 + +0 > . 1:1(0) ack 1 <nop,nop,sack 4001:5001 1001:3001> + +// Three ranges. + +0 < P. 7001:8001(1000) ack 1 win 1024 + +0 > . 1:1(0) ack 1 <nop,nop,sack 7001:8001 4001:5001 1001:3001> + +// DSACK (1001:3001) + SACK (6001:7001) + +0 < P. 1:6001(6000) ack 1 win 1024 + +0 > . 1:1(0) ack 6001 <nop,nop,sack 1001:3001 7001:8001> + +// DSACK (7001:8001) + +0 < P. 6001:8001(2000) ack 1 win 1024 + +0 > . 1:1(0) ack 8001 <nop,nop,sack 7001:8001> + +// DSACK for an older segment. + +0 < P. 1:1001(1000) ack 1 win 1024 + +0 > . 1:1(0) ack 8001 <nop,nop,sack 1:1001> diff --git a/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh index ba730655a7bf..4bc135e5c22c 100755 --- a/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh @@ -594,7 +594,7 @@ setup_rt_local_sids() dev "${DUMMY_DEVNAME}" # all SIDs for VPNs start with a common locator. Routes and SRv6 - # Endpoint behavior instaces are grouped together in the 'localsid' + # Endpoint behavior instances are grouped together in the 'localsid' # table. ip -netns "${nsname}" -6 rule \ add to "${VPN_LOCATOR_SERVICE}::/16" \ diff --git a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh index bedf0ce885c2..34b781a2ae74 100755 --- a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh @@ -681,7 +681,7 @@ setup_rt_local_sids() set_underlay_sids_reachability "${rt}" "${rt_neighs}" # all SIDs for VPNs start with a common locator. Routes and SRv6 - # Endpoint behavior instaces are grouped together in the 'localsid' + # Endpoint behavior instances are grouped together in the 'localsid' # table. ip -netns "${nsname}" -6 rule \ add to "${VPN_LOCATOR_SERVICE}::/16" \ diff --git a/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh b/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh index 3efce1718c5f..6a68c7eff1dc 100755 --- a/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh @@ -395,7 +395,7 @@ setup_rt_local_sids() dev "${VRF_DEVNAME}" # all SIDs for VPNs start with a common locator. Routes and SRv6 - # Endpoint behavior instaces are grouped together in the 'localsid' + # Endpoint behavior instances are grouped together in the 'localsid' # table. ip -netns "${nsname}" -6 rule \ add to "${VPN_LOCATOR_SERVICE}::/16" \ diff --git a/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh b/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh index cabc70538ffe..0979b5316fdf 100755 --- a/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh +++ b/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh @@ -343,7 +343,7 @@ setup_rt_local_sids() encap seg6local action End dev "${DUMMY_DEVNAME}" # all SIDs for VPNs start with a common locator. Routes and SRv6 - # Endpoint behaviors instaces are grouped together in the 'localsid' + # Endpoint behaviors instances are grouped together in the 'localsid' # table. ip -netns "${nsname}" -6 rule add \ to "${VPN_LOCATOR_SERVICE}::/16" \ diff --git a/tools/testing/selftests/net/test_neigh.sh b/tools/testing/selftests/net/test_neigh.sh new file mode 100755 index 000000000000..388056472b5b --- /dev/null +++ b/tools/testing/selftests/net/test_neigh.sh @@ -0,0 +1,366 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh +TESTS=" + extern_valid_ipv4 + extern_valid_ipv6 +" +VERBOSE=0 + +################################################################################ +# Utilities + +run_cmd() +{ + local cmd="$1" + local out + local stderr="2>/dev/null" + + if [ "$VERBOSE" = "1" ]; then + echo "COMMAND: $cmd" + stderr= + fi + + out=$(eval "$cmd" "$stderr") + rc=$? + if [ "$VERBOSE" -eq 1 ] && [ -n "$out" ]; then + echo " $out" + fi + + return $rc +} + +################################################################################ +# Setup + +setup() +{ + set -e + + setup_ns ns1 ns2 + + ip -n "$ns1" link add veth0 type veth peer name veth1 netns "$ns2" + ip -n "$ns1" link set dev veth0 up + ip -n "$ns2" link set dev veth1 up + + ip -n "$ns1" address add 192.0.2.1/24 dev veth0 + ip -n "$ns1" address add 2001:db8:1::1/64 dev veth0 nodad + ip -n "$ns2" address add 192.0.2.2/24 dev veth1 + ip -n "$ns2" address add 2001:db8:1::2/64 dev veth1 nodad + + ip netns exec "$ns1" sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 + ip netns exec "$ns2" sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 + + sleep 5 + + set +e +} + +exit_cleanup_all() +{ + cleanup_all_ns + exit "${EXIT_STATUS}" +} + +################################################################################ +# Tests + +extern_valid_common() +{ + local af_str=$1; shift + local ip_addr=$1; shift + local tbl_name=$1; shift + local subnet=$1; shift + local mac + + mac=$(ip -n "$ns2" -j link show dev veth1 | jq -r '.[]["address"]') + + RET=0 + + # Check that simple addition works. + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "No \"extern_valid\" flag after addition" + + log_test "$af_str \"extern_valid\" flag: Add entry" + + RET=0 + + # Check that an entry cannot be added with "extern_valid" flag and an + # invalid state. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr nud none dev veth0 extern_valid" + check_fail $? "Managed to add an entry with \"extern_valid\" flag and an invalid state" + + log_test "$af_str \"extern_valid\" flag: Add with an invalid state" + + RET=0 + + # Check that entry cannot be added with both "extern_valid" flag and + # "use" / "managed" flag. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid use" + check_fail $? "Managed to add an entry with \"extern_valid\" flag and \"use\" flag" + + log_test "$af_str \"extern_valid\" flag: Add with \"use\" flag" + + RET=0 + + # Check that "extern_valid" flag can be toggled using replace. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0" + run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "Did not manage to set \"extern_valid\" flag with replace" + run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_fail $? "Did not manage to clear \"extern_valid\" flag with replace" + + log_test "$af_str \"extern_valid\" flag: Replace entry" + + RET=0 + + # Check that an existing "extern_valid" entry can be marked as + # "managed". + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0 extern_valid managed" + check_err $? "Did not manage to add \"managed\" flag to an existing \"extern_valid\" entry" + + log_test "$af_str \"extern_valid\" flag: Replace entry with \"managed\" flag" + + RET=0 + + # Check that entry cannot be replaced with "extern_valid" flag and an + # invalid state. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh replace $ip_addr nud none dev veth0 extern_valid" + check_fail $? "Managed to replace an entry with \"extern_valid\" flag and an invalid state" + + log_test "$af_str \"extern_valid\" flag: Replace with an invalid state" + + RET=0 + + # Check that an "extern_valid" entry is flushed when the interface is + # put administratively down. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 link set dev veth0 down" + run_cmd "ip -n $ns1 link set dev veth0 up" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0" + check_fail $? "\"extern_valid\" entry not flushed upon interface down" + + log_test "$af_str \"extern_valid\" flag: Interface down" + + RET=0 + + # Check that an "extern_valid" entry is not flushed when the interface + # loses its carrier. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns2 link set dev veth1 down" + run_cmd "ip -n $ns2 link set dev veth1 up" + run_cmd "sleep 2" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0" + check_err $? "\"extern_valid\" entry flushed upon carrier down" + + log_test "$af_str \"extern_valid\" flag: Carrier down" + + RET=0 + + # Check that when entry transitions to "reachable" state it maintains + # the "extern_valid" flag. Wait "delay_probe" seconds for ARP request / + # NS to be sent. + local delay_probe + + delay_probe=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["delay_probe"]') + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0 extern_valid use" + run_cmd "sleep $((delay_probe / 1000 + 2))" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"REACHABLE\"" + check_err $? "Entry did not transition to \"reachable\" state" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "Entry did not maintain \"extern_valid\" flag after transition to \"reachable\" state" + + log_test "$af_str \"extern_valid\" flag: Transition to \"reachable\" state" + + RET=0 + + # Drop all packets, trigger resolution and check that entry goes back + # to "stale" state instead of "failed". + local mcast_reprobes + local retrans_time + local ucast_probes + local app_probes + local probes + local delay + + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "tc -n $ns2 qdisc add dev veth1 clsact" + run_cmd "tc -n $ns2 filter add dev veth1 ingress proto all matchall action drop" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0 extern_valid use" + retrans_time=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["retrans"]') + ucast_probes=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["ucast_probes"]') + app_probes=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["app_probes"]') + mcast_reprobes=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["mcast_reprobes"]') + delay=$((delay_probe + (ucast_probes + app_probes + mcast_reprobes) * retrans_time)) + run_cmd "sleep $((delay / 1000 + 2))" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"STALE\"" + check_err $? "Entry did not return to \"stale\" state" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "Entry did not maintain \"extern_valid\" flag after returning to \"stale\" state" + probes=$(ip -n "$ns1" -j -s neigh get "$ip_addr" dev veth0 | jq '.[]["probes"]') + if [[ $probes -eq 0 ]]; then + check_err 1 "No probes were sent" + fi + + log_test "$af_str \"extern_valid\" flag: Transition back to \"stale\" state" + + run_cmd "tc -n $ns2 qdisc del dev veth1 clsact" + + RET=0 + + # Forced garbage collection runs whenever the number of entries is + # larger than "thresh3" and deletes stale entries that have not been + # updated in the last 5 seconds. + # + # Check that an "extern_valid" entry survives a forced garbage + # collection. Add an entry, wait 5 seconds and add more entries than + # "thresh3" so that forced garbage collection will run. + # + # Note that the garbage collection thresholds are global resources and + # that changes in the initial namespace affect all the namespaces. + local forced_gc_runs_t0 + local forced_gc_runs_t1 + local orig_thresh1 + local orig_thresh2 + local orig_thresh3 + + run_cmd "ip -n $ns1 neigh flush dev veth0" + orig_thresh1=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh1")) | .["thresh1"]') + orig_thresh2=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh2")) | .["thresh2"]') + orig_thresh3=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh3")) | .["thresh3"]') + run_cmd "ip ntable change name $tbl_name thresh3 10 thresh2 9 thresh1 8" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh add ${subnet}3 lladdr $mac nud stale dev veth0" + run_cmd "sleep 5" + forced_gc_runs_t0=$(ip -j -s ntable show name "$tbl_name" | jq '.[] | select(has("forced_gc_runs")) | .["forced_gc_runs"]') + for i in {1..20}; do + run_cmd "ip -n $ns1 neigh add ${subnet}$((i + 4)) nud none dev veth0" + done + forced_gc_runs_t1=$(ip -j -s ntable show name "$tbl_name" | jq '.[] | select(has("forced_gc_runs")) | .["forced_gc_runs"]') + if [[ $forced_gc_runs_t1 -eq $forced_gc_runs_t0 ]]; then + check_err 1 "Forced garbage collection did not run" + fi + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "Entry with \"extern_valid\" flag did not survive forced garbage collection" + run_cmd "ip -n $ns1 neigh get ${subnet}3 dev veth0" + check_fail $? "Entry without \"extern_valid\" flag survived forced garbage collection" + + log_test "$af_str \"extern_valid\" flag: Forced garbage collection" + + run_cmd "ip ntable change name $tbl_name thresh3 $orig_thresh3 thresh2 $orig_thresh2 thresh1 $orig_thresh1" + + RET=0 + + # Periodic garbage collection runs every "base_reachable"/2 seconds and + # if the number of entries is larger than "thresh1", then it deletes + # stale entries that have not been used in the last "gc_stale" seconds. + # + # Check that an "extern_valid" entry survives a periodic garbage + # collection. Add an "extern_valid" entry, add more than "thresh1" + # regular entries, wait "base_reachable" (longer than "gc_stale") + # seconds and check that the "extern_valid" entry was not deleted. + # + # Note that the garbage collection thresholds and "base_reachable" are + # global resources and that changes in the initial namespace affect all + # the namespaces. + local periodic_gc_runs_t0 + local periodic_gc_runs_t1 + local orig_base_reachable + local orig_gc_stale + + run_cmd "ip -n $ns1 neigh flush dev veth0" + orig_thresh1=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh1")) | .["thresh1"]') + orig_base_reachable=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh1")) | .["base_reachable"]') + run_cmd "ip ntable change name $tbl_name thresh1 10 base_reachable 10000" + orig_gc_stale=$(ip -n "$ns1" -j ntable show name "$tbl_name" dev veth0 | jq '.[]["gc_stale"]') + run_cmd "ip -n $ns1 ntable change name $tbl_name dev veth0 gc_stale 5000" + # Wait orig_base_reachable/2 for the new interval to take effect. + run_cmd "sleep $(((orig_base_reachable / 1000) / 2 + 2))" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh add ${subnet}3 lladdr $mac nud stale dev veth0" + for i in {1..20}; do + run_cmd "ip -n $ns1 neigh add ${subnet}$((i + 4)) nud none dev veth0" + done + periodic_gc_runs_t0=$(ip -j -s ntable show name "$tbl_name" | jq '.[] | select(has("periodic_gc_runs")) | .["periodic_gc_runs"]') + run_cmd "sleep 10" + periodic_gc_runs_t1=$(ip -j -s ntable show name "$tbl_name" | jq '.[] | select(has("periodic_gc_runs")) | .["periodic_gc_runs"]') + [[ $periodic_gc_runs_t1 -ne $periodic_gc_runs_t0 ]] + check_err $? "Periodic garbage collection did not run" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "Entry with \"extern_valid\" flag did not survive periodic garbage collection" + run_cmd "ip -n $ns1 neigh get ${subnet}3 dev veth0" + check_fail $? "Entry without \"extern_valid\" flag survived periodic garbage collection" + + log_test "$af_str \"extern_valid\" flag: Periodic garbage collection" + + run_cmd "ip -n $ns1 ntable change name $tbl_name dev veth0 gc_stale $orig_gc_stale" + run_cmd "ip ntable change name $tbl_name thresh1 $orig_thresh1 base_reachable $orig_base_reachable" +} + +extern_valid_ipv4() +{ + extern_valid_common "IPv4" 192.0.2.2 "arp_cache" 192.0.2. +} + +extern_valid_ipv6() +{ + extern_valid_common "IPv6" 2001:db8:1::2 "ndisc_cache" 2001:db8:1:: +} + +################################################################################ +# Usage + +usage() +{ + cat <<EOF +usage: ${0##*/} OPTS + + -t <test> Test(s) to run (default: all) + (options: $TESTS) + -p Pause on fail + -v Verbose mode (show commands and output) +EOF +} + +################################################################################ +# Main + +while getopts ":t:pvh" opt; do + case $opt in + t) TESTS=$OPTARG;; + p) PAUSE_ON_FAIL=yes;; + v) VERBOSE=$((VERBOSE + 1));; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +require_command jq + +if ! ip neigh help 2>&1 | grep -q "extern_valid"; then + echo "SKIP: iproute2 ip too old, missing \"extern_valid\" support" + exit "$ksft_skip" +fi + +trap exit_cleanup_all EXIT + +for t in $TESTS +do + setup; $t; cleanup_all_ns; +done diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index db176fe7d0c3..8e902f7f1a18 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -21,6 +21,7 @@ CONFIG_NF_NAT=m CONFIG_NETFILTER_XT_TARGET_LOG=m CONFIG_NET_SCHED=y +CONFIG_IP_SET=m # # Queueing/Scheduling diff --git a/tools/testing/selftests/ublk/test_stress_03.sh b/tools/testing/selftests/ublk/test_stress_03.sh index 6eef282d569f..3ed4c9b2d8c0 100755 --- a/tools/testing/selftests/ublk/test_stress_03.sh +++ b/tools/testing/selftests/ublk/test_stress_03.sh @@ -32,22 +32,23 @@ _create_backfile 2 128M ublk_io_and_remove 8G -t null -q 4 -z & ublk_io_and_remove 256M -t loop -q 4 -z "${UBLK_BACKFILES[0]}" & ublk_io_and_remove 256M -t stripe -q 4 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & +wait if _have_feature "AUTO_BUF_REG"; then ublk_io_and_remove 8G -t null -q 4 --auto_zc & ublk_io_and_remove 256M -t loop -q 4 --auto_zc "${UBLK_BACKFILES[0]}" & ublk_io_and_remove 256M -t stripe -q 4 --auto_zc "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & ublk_io_and_remove 8G -t null -q 4 -z --auto_zc --auto_zc_fallback & + wait fi -wait if _have_feature "PER_IO_DAEMON"; then ublk_io_and_remove 8G -t null -q 4 --auto_zc --nthreads 8 --per_io_tasks & ublk_io_and_remove 256M -t loop -q 4 --auto_zc --nthreads 8 --per_io_tasks "${UBLK_BACKFILES[0]}" & ublk_io_and_remove 256M -t stripe -q 4 --auto_zc --nthreads 8 --per_io_tasks "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & ublk_io_and_remove 8G -t null -q 4 -z --auto_zc --auto_zc_fallback --nthreads 8 --per_io_tasks & + wait fi -wait _cleanup_test "stress" _show_result $TID $ERR_CODE diff --git a/tools/testing/vsock/Makefile b/tools/testing/vsock/Makefile index 6e0b4e95e230..88211fd132d2 100644 --- a/tools/testing/vsock/Makefile +++ b/tools/testing/vsock/Makefile @@ -5,6 +5,7 @@ vsock_test: vsock_test.o vsock_test_zerocopy.o timeout.o control.o util.o msg_ze vsock_diag_test: vsock_diag_test.o timeout.o control.o util.o vsock_perf: vsock_perf.o msg_zerocopy_common.o +vsock_test: LDLIBS = -lpthread vsock_uring_test: LDLIBS = -luring vsock_uring_test: control.o util.o vsock_uring_test.o timeout.o msg_zerocopy_common.o diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index 71895192cc02..fdd4649fe2d4 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -33,6 +33,10 @@ static const char * const transport_ksyms[] = { static_assert(ARRAY_SIZE(transport_ksyms) == TRANSPORT_NUM); static_assert(BITS_PER_TYPE(int) >= TRANSPORT_NUM); +#define TRANSPORTS_G2H (TRANSPORT_VIRTIO | TRANSPORT_VMCI | TRANSPORT_HYPERV) +#define TRANSPORTS_H2G (TRANSPORT_VHOST | TRANSPORT_VMCI) +#define TRANSPORTS_LOCAL (TRANSPORT_LOOPBACK) + /* Tests can either run as the client or the server */ enum test_mode { TEST_MODE_UNSET, diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index eb6f54378667..be6ce764f694 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -22,6 +22,8 @@ #include <signal.h> #include <sys/ioctl.h> #include <linux/time64.h> +#include <pthread.h> +#include <fcntl.h> #include "vsock_test_zerocopy.h" #include "timeout.h" @@ -1867,6 +1869,169 @@ static void test_stream_connect_retry_server(const struct test_opts *opts) close(fd); } +#define TRANSPORT_CHANGE_TIMEOUT 2 /* seconds */ + +static void *test_stream_transport_change_thread(void *vargp) +{ + pid_t *pid = (pid_t *)vargp; + int ret; + + ret = pthread_setcanceltype(PTHREAD_CANCEL_ASYNCHRONOUS, NULL); + if (ret) { + fprintf(stderr, "pthread_setcanceltype: %d\n", ret); + exit(EXIT_FAILURE); + } + + while (true) { + if (kill(*pid, SIGUSR1) < 0) { + perror("kill"); + exit(EXIT_FAILURE); + } + } + return NULL; +} + +static void test_transport_change_signal_handler(int signal) +{ + /* We need a custom handler for SIGUSR1 as the default one terminates the process. */ +} + +static void test_stream_transport_change_client(const struct test_opts *opts) +{ + __sighandler_t old_handler; + pid_t pid = getpid(); + pthread_t thread_id; + time_t tout; + int ret, tr; + + tr = get_transports(); + + /* Print a warning if there is a G2H transport loaded. + * This is on a best effort basis because VMCI can be either G2H and H2G, and there is + * no easy way to understand it. + * The bug we are testing only appears when G2H transports are not loaded. + * This is because `vsock_assign_transport`, when using CID 0, assigns a G2H transport + * to vsk->transport. If none is available it is set to NULL, causing the null-ptr-deref. + */ + if (tr & TRANSPORTS_G2H) + fprintf(stderr, "G2H Transport detected. This test will not fail.\n"); + + old_handler = signal(SIGUSR1, test_transport_change_signal_handler); + if (old_handler == SIG_ERR) { + perror("signal"); + exit(EXIT_FAILURE); + } + + ret = pthread_create(&thread_id, NULL, test_stream_transport_change_thread, &pid); + if (ret) { + fprintf(stderr, "pthread_create: %d\n", ret); + exit(EXIT_FAILURE); + } + + control_expectln("LISTENING"); + + tout = current_nsec() + TRANSPORT_CHANGE_TIMEOUT * NSEC_PER_SEC; + do { + struct sockaddr_vm sa = { + .svm_family = AF_VSOCK, + .svm_cid = opts->peer_cid, + .svm_port = opts->peer_port, + }; + int s; + + s = socket(AF_VSOCK, SOCK_STREAM, 0); + if (s < 0) { + perror("socket"); + exit(EXIT_FAILURE); + } + + ret = connect(s, (struct sockaddr *)&sa, sizeof(sa)); + /* The connect can fail due to signals coming from the thread, + * or because the receiver connection queue is full. + * Ignoring also the latter case because there is no way + * of synchronizing client's connect and server's accept when + * connect(s) are constantly being interrupted by signals. + */ + if (ret == -1 && (errno != EINTR && errno != ECONNRESET)) { + perror("connect"); + exit(EXIT_FAILURE); + } + + /* Set CID to 0 cause a transport change. */ + sa.svm_cid = 0; + + /* Ignore return value since it can fail or not. + * If the previous connect is interrupted while the + * connection request is already sent, the second + * connect() will wait for the response. + */ + connect(s, (struct sockaddr *)&sa, sizeof(sa)); + + close(s); + + control_writeulong(CONTROL_CONTINUE); + + } while (current_nsec() < tout); + + control_writeulong(CONTROL_DONE); + + ret = pthread_cancel(thread_id); + if (ret) { + fprintf(stderr, "pthread_cancel: %d\n", ret); + exit(EXIT_FAILURE); + } + + ret = pthread_join(thread_id, NULL); + if (ret) { + fprintf(stderr, "pthread_join: %d\n", ret); + exit(EXIT_FAILURE); + } + + if (signal(SIGUSR1, old_handler) == SIG_ERR) { + perror("signal"); + exit(EXIT_FAILURE); + } +} + +static void test_stream_transport_change_server(const struct test_opts *opts) +{ + int s = vsock_stream_listen(VMADDR_CID_ANY, opts->peer_port); + + /* Set the socket to be nonblocking because connects that have been interrupted + * (EINTR) can fill the receiver's accept queue anyway, leading to connect failure. + * As of today (6.15) in such situation there is no way to understand, from the + * client side, if the connection has been queued in the server or not. + */ + if (fcntl(s, F_SETFL, fcntl(s, F_GETFL, 0) | O_NONBLOCK) < 0) { + perror("fcntl"); + exit(EXIT_FAILURE); + } + control_writeln("LISTENING"); + + while (control_readulong() == CONTROL_CONTINUE) { + /* Must accept the connection, otherwise the `listen` + * queue will fill up and new connections will fail. + * There can be more than one queued connection, + * clear them all. + */ + while (true) { + int client = accept(s, NULL, NULL); + + if (client < 0) { + if (errno == EAGAIN) + break; + + perror("accept"); + exit(EXIT_FAILURE); + } + + close(client); + } + } + + close(s); +} + static void test_stream_linger_client(const struct test_opts *opts) { int fd; @@ -2106,6 +2271,11 @@ static struct test_case test_cases[] = { .run_client = test_stream_nolinger_client, .run_server = test_stream_nolinger_server, }, + { + .name = "SOCK_STREAM transport change null-ptr-deref", + .run_client = test_stream_transport_change_client, + .run_server = test_stream_transport_change_server, + }, {}, }; |